add85ee833e2a1c5cdbcd206d5423d63f20cda24,International Journal of Advanced Robotic Systems Embedded Face Detection and Recognition Regular Paper,"International Journal of Advanced Robotic Systems Embedded Face Detection nd Recognition Regular Paper Göksel Günlü Department of Electrical and Electronics Engineering Turgut Özal University, Ankara, Turkey * Corresponding author E-mail: Received 07 May 2012; Accepted 28 Jun 2012 DOI: 10.5772/51132 © 2012 Günlü; licensee InTech. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited." ad2afeb4c1975c637291bc3f7087d665c3f501c8,WebVision Challenge: Visual Learning and Understanding With Web Data,"WebVision Challenge: Visual Learning and Understanding With Web Data Wen Li, Limin Wang, Wei Li, Eirikur Agustsson, Jesse Berent, Abhinav Gupta, Rahul Sukthankar, nd Luc Van Gool" ada73060c0813d957576be471756fa7190d1e72d,VRPBench: A Vehicle Routing Benchmark Tool.,"VRPBench: A Vehicle Routing Benchmark Tool October 19, 2016 Guilherme A. Zeni1 , Mauro Menzori1, P. S. Martins1, Luis A. A. Meira1" ad9d1fb6d39f2c42f9070032c2f8a4a4da1c7128,Ear Segmetation using Topographic Labels,"EAR SEGMETATION USING TOPOGRAPHIC LABELS Department of Electrical Engineering and Robotics, Shahrood University of Technology, Shahrood, Iran Milad Lankarany and Alireza Ahmadyfard Keywords: Ear Biometrics, Ear Segmentation, Topographic Features." ad7a7f70e460d4067d7170bcc0f1ea62eedd7234,CBinfer: Exploiting Frame-to-Frame Locality for Faster Convolutional Network Inference on Video Streams,"CBinfer: Exploiting Frame-to-Frame Locality for Faster Convolutional Network Inference on Video Streams Lukas Cavigelli, Luca Benini" ad30152944a42975f16a53cf0e0666e9937e9d73,Dyadic Interaction Detection from Pose and Flow,"Dyadic interaction detection from pose and flow Anonymous ECCV submission Paper ID 17" adca02d4b34a9851d1c9c0a7c1bb8d5178b59b85,Modeling the dynamics of individual behaviors for group detection in crowds using low-level features,"Modeling the dynamics of individual behaviors for group detection in crowds using low-level features Omar Adair Islas Ram´ırez Giovanna Varni Mihai Andries Mohamed Chetouani Raja Chatila" ad9b3dc6c0e54070cec79df86458ed38566da1ff,Automated Image Captioning for Rapid Prototyping and Resource Constrained Environments,"Automated Image Captioning for Rapid Prototyping nd Resource Constrained Environments Department of Computer Science, The University of Georgia, Athens, Georgia 30602-7404, USA Karan Sharma Arun CS Kumar Emails: Suchendra M. Bhandarkar" ade32e04dceeaed72c3e99a9f3698b2fe01c9863,Learning confidence measures in the wild,"F. TOSI ET AL.: LEARNING CONFIDENCE MEASURES IN THE WILD Learning confidence measures in the wild University of Bologna Department of Computer Science and Engineering Bologna, Italy Fabio Tosi http://vision.disi.unibo.it/~ftosi Matteo Poggi http://vision.disi.unibo.it/~mpoggi Alessio Tonioni Luigi Di Stefano Stefano Mattoccia http://vision.disi.unibo.it/~smatt" adba4fe9640c03d8a98bf7604edb32cb868df655,Large Scale Hard Sample Mining with Monte Carlo Tree Search,"Large Scale Hard Sample Mining with Monte Carlo Tree Search – Supplementary material – Olivier Can´evet1,2 and Franc¸ois Fleuret1 Idiap Research Institut, Switzerland ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL), Switzerland" ad109cfebcb512ce83b0a6b2fe640466ccb8a1d9,Reliability-Based Voting Schemes Using Modality-Independent Features in Multi-classifier Biometric Authentication,"Reliability-Based Voting Schemes Using Modality-Independent Features in Multi-classifier Biometric Authentication Jonas Richiardi and Andrzej Drygajlo Laboratory of IDIAP, Signal Processing Institute Swiss Federal Institute of Technology Lausanne http://scgwww.epfl.ch" ade18cf978e4b00fb74352a7eba90b4f4509d645,Articulated Multi-body Tracking under Egomotion,"Articulated Multi-body Tracking Under Egomotion S. Gammeter1, A. Ess1, T. J¨aggli1, K. Schindler1, B. Leibe1,2, and L. Van Gool1,3 ETH Z¨urich RWTH Aachen KU Leuven, IBBT" addab6e00b0c79d89c5ba177ac316e7d175e4427,An Optimized Sliding Window Approach to Pedestrian Detection, ade1034d5daec9e3eba1d39ae3f33ebbe3e8e9a7,Multimodal Caricatural Mirror,"Multimodal Caricatural Mirror Martin O.(1), Adell J.(2), Huerta A.(3), Kotsia I.(4), Savran A.(5), Sebbe R.(6) (1) : Université catholique de Louvain, Belgium (2) Universitat Polytecnica de Barcelona, Spain (3) Universidad Polytècnica de Madrid, Spain (4) Aristotle University of Thessaloniki, Greece (5) Bogazici University, Turkey (6) Faculté Polytechnique de Mons, Belgium" adf62dfa00748381ac21634ae97710bb80fc2922,ViFaI : A trained video face indexing scheme Harsh,"ViFaI: A trained video face indexing scheme Harsh Nayyar Audrey Wei . Introduction With the increasing prominence of inexpensive video recording devices (e.g., digital camcorders and video recording smartphones), the average user’s video collection today is increasing rapidly. With this development, there arises a natural desire to rapidly ccess a subset of one’s collection of videos. The solu- tion to this problem requires an effective video index- ing scheme. In particular, we must be able to easily process a video to extract such indexes. Today, there also exist large sets of labeled (tagged) face images. One important example is an individual’s Facebook profile. Such a set of of tagged images of one’s self, family, friends, and colleagues represents n extremely valuable potential training set. In this work, we explore how to leverage the afore-" ad75879082132a73fe173a890a0f414f2c279739,A comparison of CNN-based face and head detectors for real-time video surveillance applications,"A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications Le Thanh Nguyen-Meidine1, Eric Granger 1, Madhu Kiran1 and Louis-Antoine Blais-Morin2 ´Ecole de technologie sup´erieure, Universit´e du Qu´ebec, Montreal, Canada Genetec Inc., Montreal, Canada" adf7ccb81b8515a2d05fd3b4c7ce5adf5377d9be,Apprentissage de métrique appliqué à la détection de changement de page Web et aux attributs relatifs,"Apprentissage de métrique appliqué à la détection de changement de page Web et ux attributs relatifs Marc T. Law* — Nicolas Thome* — Stéphane Gançarski* — Mat- thieu Cord* * Sorbonne Universités, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005, Paris, France RÉSUMÉ. Nous proposons dans cet article un nouveau schéma d’apprentissage de métrique. Basé sur l’exploitation de contraintes qui impliquent des quadruplets d’images, notre approche vise à modéliser des relations sémantiques de similarités riches ou complexes. Nous étudions omment ce schéma peut être utilisé dans des contextes tels que la détection de régions impor- tantes dans des pages Web ou la reconnaissance à partir d’attributs relatifs." adefabe194863b4f764ec982e3120554165c841c,Radius based Block Local Binary Pattern on T-Zone Face Area for Face Recognition,"Journal of Computer Science 11 (1): 96-108, 2015 ISSN: 1549-3636 © 2015 Science Publications RADIUS BASED BLOCK LOCAL BINARY PATTERN ON T- ZONE FACE AREA FOR FACE RECOGNITION Md. Jan Nordin, 2Abdul Aziz K. Abdul Hamid, Sumazly Ulaiman and 2R.U. Gobithaasan Center for Artificial Intelligent Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia School of Informatics and App. Maths, Universiti Malaysia Terengganu, Terengganu, Malaysia Received 2014-02-20; Revised 2014-04-29; Accepted 2014-08-04" ad88fcfd12b62d607259db8d98e2a1a0a9642ca0,Real-time tracking-with-detection for coping with viewpoint change,"Real-Time Tracking-with-Detection for Coping With Viewpoint Change Shaul Oron · Aharon Bar-Hillel · Shai Avidan Received: 11 May 2014 / Revised: 02 Nov 2014 / Accepted: 09 Mar 2015" ad3caae50feee550b047e17699cfe7bb9e243cf5,Sparse similarity-preserving hashing,"Sparse similarity-preserving hashing Jonathan Masci Alex M. Bronstein Michael M. Bronstein Pablo Sprechmann Guillermo Sapiro" ad6bcf4384a7604b6252a6eeefade4c486b01240,Cluster-Based Distributed Face Tracking in Camera Networks,"Cluster-Based Distributed Face Tracking in Camera Networks Josiah Yoder, Henry Medeiros, Johnny Park, and Avinash C. Kak" ad8642e186c5c81d06934d4e6fc249b7cbca40e8,Learning Transferable Architectures for Scalable Image Recognition,"Learning Transferable Architectures for Scalable Image Recognition Barret Zoph Google Brain Vijay Vasudevan Google Brain Jonathon Shlens Google Brain Quoc V. Le Google Brain" ad8b8eb07491b3e771e873703bac23568f134bad,Monocular Depth Estimation with Augmented Ordinal Depth Relationships,"Monocular Depth Estimation with Augmented Ordinal Depth Relationships Yuanzhouhan Cao, Tianqi Zhao, Ke Xian, Chunhua Shen, Zhiguo Cao" adaf2b138094981edd615dbfc4b7787693dbc396,Statistical methods for facial shape-from-shading and recognition,"Statistical Methods For Facial Shape-from-shading and Recognition William A. P. Smith Submitted for the degree of Doctor of Philosophy Department of Computer Science 0th February 2007" adbdb6f3c6c79c29f3af1cf39d24c0dccf2d6b2d,Robust Face Recognition by Hierarchical Kernel Associative Memory Models Based on Spatial Domain Gabor Transforms,"Robust Face Recognition by Hierarchical Kernel Associative Memory Models Based on Spatial Domain Gabor Transforms Bai-ling Zhang, Pietro Cerone School of Computer Science and Mathematics, Victoria University Email: (cid:0)bzhang, Yongsheng Gao School of Engineering, Griffith University" ad01c5761c89fdf523565cc0dec77b9a6ec8e694,Global and Local Consistent Wavelet-domain Age Synthesis,"Global and Local Consistent Wavelet-domain Age Synthesis Peipei Li†, Yibo Hu†, Ran He Member, IEEE and Zhenan Sun Member, IEEE" 040033d73d1efe316c8f0a8ed702b833a0550d83,Generating Expressions that Refer to Visible Objects,"Atlanta, Georgia, 9–14 June 2013. c(cid:13)2013 Association for Computational Linguistics Proceedings of NAACL-HLT 2013, pages 1174–1184," 04743c503620baffd75f93f8e4583fcba369ac9d,Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction,"Proceedings of the The 8th International Joint Conference on Natural Language Processing, pages 436–441, Taipei, Taiwan, November 27 – December 1, 2017 c(cid:13)2017 AFNLP" 04241ba56d4499a00beb6991d2460d571a218d85,Learning appearance in virtual scenarios for pedestrian detection,"Learning Appearance in Virtual Scenarios for Pedestrian Detection Javier Mar´ın, David V´azquez, David Ger´onimo and Antonio M. L´opez Computer Vision Center and Computer Science Dpt. UAB, 08193 Bellaterra, Barcelona, Spain {jmarin, dvazquez, dgeronimo," 044da4715e439b4f91cee8eec55299e30a615c56,Inducing a Concurrent Motor Load Reduces Categorization Precision for Facial Expressions,"Journal of Experimental Psychology: Human Perception and Performance 016, Vol. 42, No. 5, 706 –718 0096-1523/16/$12.00 © 2015 The Author(s) http://dx.doi.org/10.1037/xhp0000177 Inducing a Concurrent Motor Load Reduces Categorization Precision for Facial Expressions Alberta Ipser and Richard Cook City University London Motor theories of expression perception posit that observers simulate facial expressions within their own motor system, aiding perception and interpretation. Consistent with this view, reports have suggested that locking facial mimicry induces expression labeling errors and alters patterns of ratings. Crucially, however, it is unclear whether changes in labeling and rating behavior reflect genuine perceptual phenomena (e.g., greater internal noise associated with expression perception or interpretation) or are products of response bias. In an effort to advance this literature, the present study introduces a new psychophysical paradigm for investigating motor contributions to expression perception that overcomes some of the limitations inherent in simple labeling and rating tasks. Observers were asked to judge whether smiles drawn from a morph continuum were sincere or insincere, in the presence or absence of motor load induced by the concurrent production of vowel sounds. Having confirmed that smile" 04cb43806ca57040100b33af0781e4331f8daa56,Long-term Multi-granularity Deep Framework for Driver Drowsiness Detection,"Long-term Multi-granularity Deep Framework for Driver Drowsiness Detection Jie Lyu Zejian Yuan Dapeng Chen Xi’an Jiaotong University Xi’an Jiaotong University Xi’an Jiaotong University Email: Email: Email:" 047d7cf4301cae3d318468fe03a1c4ce43b086ed,Co-Localization of Audio Sources Using Binaural Features and Locally-Linear Regression,"Co-Localization of Audio Sources in Images Using Binaural Features and Locally-Linear Regression Antoine Deleforge, Radu Horaud, Yoav Y. Schechner, Laurent Girin To cite this version: Antoine Deleforge, Radu Horaud, Yoav Y. Schechner, Laurent Girin. Co-Localization of Audio Sources in Images Using Binaural Features and Locally-Linear Regression. IEEE Transactions on Audio Speech and Language Processing, 2015, 15p. HAL Id: hal-01112834 https://hal.inria.fr/hal-01112834 Submitted on 3 Feb 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 04379f40d2a26dd769c53488b7b08a5123f89347,3D Facial Expression Recognition Based on Histograms of Surface Differential Quantities,"D Facial Expression Recognition Based on Histograms of Surface Differential Quantities Huibin Li1,2, Jean-Marie Morvan1,3,4, and Liming Chen1,2 Universit´e de Lyon, CNRS Ecole Centrale de Lyon, LIRIS UMR5205, F-69134, Lyon, France Universit´e Lyon 1, Institut Camille Jordan, 3 blvd du 11 Novembre 1918, F-69622 Villeurbanne - Cedex, France King Abdullah University of Science and Technology, GMSV Research Center, Bldg 1, Thuwal 23955-6900, Saudi Arabia" 048eb50c398fa01bd15329945113341102d96454,Addressing perceptual insensitivity to facial affect in violent offenders: first evidence for the efficacy of a novel implicit training approach.,"doi:10.1017/S0033291713001517 O R I G I N A L A R T I C L E Addressing perceptual insensitivity to facial affect in violent offenders: first evidence for the efficacy of a novel implicit training approach M. Schönenberg*, S. Christian, A.-K. Gaußer, S. V. Mayer, M. Hautzinger and A. Jusyte Department of Clinical Psychology and Psychotherapy, University of Tübingen, Germany Background. Although impaired recognition of affective facial expressions has been conclusively linked to antisocial ehavior, little is known about the modifiability of this deficit. This study investigated whether and under which circum- stances the proposed perceptual insensitivity can be addressed with a brief implicit training approach. Method. Facial affect recognition was assessed with an animated morph task, in which the participants (44 male incar- erated violent offenders and 43 matched controls) identified the onset of emotional expressions in animated morph clips that gradually changed from neutral to one of the six basic emotions. Half of the offenders were then implicitly trained to direct attention to salient face regions (attention training, AT) using a modified dot-probe task. The other half underwent the same protocol but the intensity level of the presented expressions was additionally manipulated over the course of training sessions (sensitivity to emotional expressions training, SEE training). Subsequently, participants were reassessed with the animated morph task. Results. Facial affect recognition was significantly impaired in violent offenders as compared with controls. Further, our results indicate that only the SEE training group exhibited a pronounced improvement in emotion recognition. Conclusions. We demonstrated for the first time that perceptual insensitivity to facial affect can be addressed by an" 0449b56b6b19a3c42766962782bfb88576b5bd62,Spontaneous and cued gaze-following in autism and Williams syndrome,"Spontaneous and cued gaze-following in autism nd Williams syndrome Riby et al. Riby et al. Journal of Neurodevelopmental Disorders 2013, 5:13 http://www.jneurodevdisorders.com/content/5/1/13" 0470b0ab569fac5bbe385fa5565036739d4c37f8,Automatic face naming with caption-based supervision,"Automatic Face Naming with Caption-based Supervision Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, Cordelia Schmid To cite this version: Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, Cordelia Schmid. Automatic Face Naming with Caption-based Supervision. CVPR 2008 - IEEE Conference on Computer Vision Pattern Recognition, iety, <10.1109/CVPR.2008.4587603>. 008, pp.1-8, 008, Anchorage, United . IEEE Computer States. HAL Id: inria-00321048 https://hal.inria.fr/inria-00321048v2 Submitted on 11 Apr 2011 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub-" 04f6a747cba48be1cabbf5efe6ce3eb85e061395,Discriminative Detection and Alignment in Volumetric Data,"Discriminative Detection nd Alignment in Volumetric Data Dominic Mai1,2, Philipp Fischer1, Thomas Blein4, Jasmin D¨urr3, Klaus Palme2,3, Thomas Brox1,2, and Olaf Ronneberger1,2 Lehrstuhl f¨ur Mustererkennung und Bildverabeitung, Institut f¨ur Informatik BIOSS Centre of Biological Signalling Studies Institut f¨ur Biologie II, Albert-Ludwigs-Universit¨at Freiburg INRA Versailles" 04b29b6f1210f4309f3d5ab9e6bd2c8a026ce244,Face Recognition in the Presence of Expressions,"Journal of Software Engineering and Applications, 2012, 5, 321-329 http://dx.doi.org/10.4236/jsea.2012.55038 Published Online May 2012 (http://www.SciRP.org/journal/jsea) Face Recognition in the Presence of Expressions Xia Han1*, Moi Hoon Yap2, Ian Palmer3 Centre for Visual Computing, University of Bradford, Bradford, UK; 2School of Computing, Mathematics, and Digital Technology, Manchester Metropolitan University (MMU), Manchester, UK; 3School of Computing, Informatics and Media, University of Bradford, Bradford, UK. Email: Received February 21st, 2012; revised March 25th, 2012; accepted April 27th, 2012" 04d71c17c46f25ce3087792ab995c19f22d3e4e9,Automatic Person Verification Using Speech and Face Information,"Automatic Person Verification Using Speech and Face Information A Dissertation Presented to The School of Microelectronic Engineering Faculty of Engineering and Information Technology Grif‌f‌ith University Submitted in Fulfillment of the Requirements of the Degree of Doctor of Philosophy Conrad Sanderson, BEng (Hons) August 2002 [revised February 2003]" 04e5d374c10b70a74d79070103cab1f362b113ba,"DeepHash: Getting Regularization, Depth and Fine-Tuning Right","DeepHash: Getting Regularization, Depth and Fine-Tuning Right Jie Lin∗,1,3, Olivier Mor`ere∗,1,2,3, Vijay Chandrasekhar1,3, Antoine Veillard2,3, Hanlin Goh1,3 I2R1, UPMC2, IPAL3" 0485e96bb0c1276fe2a27271b939b6e67997acfc,Active Learning for Structured Probabilistic Models,"Active Learning for Structured Probabilistic Models Qing Sun Virginia Tech Ankit Laddha ∗ Virginia Tech Dhruv Batra Virginia Tech" 042510b39c6cdb463610fdda2081b36ff469a353,Human Pose Estimation from Video and IMUs,"Human Pose Estimation from Video and IMUs Timo von Marcard, Gerard Pons-Moll, and Bodo Rosenhahn" 0468b2b98f6bc190a84daa5902b094ca23122ff6,Low-drift and real-time lidar odometry and mapping,"Auton Robot DOI 10.1007/s10514-016-9548-2 Low-drift and real-time lidar odometry and mapping Ji Zhang1 · Sanjiv Singh1 Received: 25 October 2014 / Accepted: 7 February 2016 © Springer Science+Business Media New York 2016" 0431e8a01bae556c0d8b2b431e334f7395dd803a,Learning Localized Perceptual Similarity Metrics for Interactive Categorization,"Learning Localized Perceptual Similarity Metrics for Interactive Categorization Catherine Wah ∗ Google Inc. google.com" 04a88ab3ee6314997a51f8ce60da6111226e0f37,Locally Supervised Deep Hybrid Model for Scene Recognition,"Locally-Supervised Deep Hybrid Model for Scene Recognition Sheng Guo, Weilin Huang, and Yu Qiao" 0464b56c5beee717b074ed950abcc959372256a6,Fast and Robust Optimization Approaches for Pedestrian Detection,"Fast and Robust Optimization Approaches for Pedestrian Detection Victor Hugo Cunha de Melo∗, David Menotti (Co-advisor)†, William Robson Schwartz (Advisor)∗ Computer Science Department, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil Computer Science Department, Universidade Federal de Ouro Preto, Ouro Preto, Brazil Email:" 041d3eedf5e45ce5c5229f0181c5c576ed1fafd6,How to Take a Good Selfie?,"How to Take a Good Selfie? Mahdi M. Kalayeh(cid:63) Misrak Seifu◦ Wesna LaLanne(cid:5) Mubarak Shah(cid:63) (cid:63)Center for Research in Computer Vision at University of Central Florida ◦Jackson State University (cid:5)University of Central Florida" 045fbe21ea8e501d443fa2d297c1292264712c62,Links between multisensory processing and autism,"Exp Brain Res DOI 10.1007/s00221-012-3223-4 R E S E A R C H A R T I C L E Links between multisensory processing and autism Sarah E. Donohue • Elise F. Darling • Stephen R. Mitroff Received: 1 June 2012 / Accepted: 7 August 2012 Ó Springer-Verlag 2012" 046f1c194a09fc84f535c27a3373622223a80c67,Memory-efficient groupby-aggregate using compressed buffer trees,"Memory-Efficient GroupBy-Aggregate using Compressed Buffer Trees Hrishikesh Amur†, Wolfgang Richter(cid:63), David G. Andersen(cid:63), Michael Kaminsky‡, Karsten Schwan†, Athula Balachandran(cid:63), Erik Zawadzki(cid:63) (cid:63)Carnegie Mellon University, †Georgia Institute of Technology, ‡Intel Labs Pittsburgh" 047f6afa87f48de7e32e14229844d1587185ce45,An Improvement of Energy-Transfer Features Using DCT for Face Detection,"An Improvement of Energy-Transfer Features Using DCT for Face Detection Radovan Fusek, Eduard Sojka, Karel Mozdˇreˇn, and Milan ˇSurkala Technical University of Ostrava, FEECS, Department of Computer Science, 7. listopadu 15, 708 33 Ostrava-Poruba, Czech Republic" 044600cc4b93bb0504e8d72a5476d16f1a61a107,Discriminant Analysis of Principal Components for Face Recognition,"DiscriminantAnalysisofPrincipalComponentsforFace Recognition(cid:3) W.Zhao R.Chellappa A.Krishnaswamy CenterforAutomationResearch ElectricalEngineeringDept UniversityofMaryland StanfordUniversity CollegePark,MD- Stanford,CA  LDAofPrincipalComponentsface" 04cdc847f3b10d894582969feee0f37fbd3745e5,Compressed Sensing with Deep Image Prior and Learned Regularization,"Compressed Sensing with Deep Image Prior nd Learned Regularization David Van Veen∗† Ajil Jalal∗† Eric Price ‡ Sriram Vishwanath † Alexandros G. Dimakis † June 19, 2018" 040806bc41c0dd50273921d8d839fda58d20b01e,Socio-affective touch expression database,"RESEARCH ARTICLE Socio-affective touch expression database Haemy Lee Masson*, Hans Op de Beeck* Department of Brain and Cognition, KU Leuven, Leuven, Belgium * (HLM); (HOB)" 0447bdb71490c24dd9c865e187824dee5813a676,Manifold Estimation in View-based Feature Space for Face Synthesis Across Pose Paper 27,"Manifold Estimation in View-based Feature Space for Face Synthesis Across Pose Paper 27" 04ff060369c86ccb07414935bd3e3b85e4896261,Object detection can be improved using human-derived contextual expectations,"Object detection can be improved using human-derived contextual expectations Harish Katti, Marius V. Peelen, and S. P. Arun" 04dca7c7f85d607cba64ca56de3364a4085effa1,ExprGAN: Facial Expression Editing With Controllable Expression Intensity,"ExprGAN: Facial Expression Editing with Controllable Expression Intensity Hui Ding,1 Kumar Sricharan2, Rama Chellappa3 ,3University of Maryland, College Park PARC, Palo Alto" 040eb316cec08b36ae0b57fede86043ee0526686,Learning Reliable and Scalable Representations Using Multimodal Multitask Deep Learning,"Learning Reliable and Scalable Representations Using Multimodal Multitask Deep Learning Abhinav Valada, and Wolfram Burgard Department of Computer Science, University of Freiburg, Germany I. INTRODUCTION Modality 1 Modality 2 Unimodal Seg. Multimodal Seg. Fifties - in 5 years robots would be everywhere. Sixties - in 10 years robots would be everywhere. Seventies - in 20 years robots would be everywhere. Eighties - in 40 years robots would be everywhere. -Marvin Minsky Those were the words from one of the pioneers of AI when asked to comment on the progress of robotics in the twentieth century. This shows the high expectations and unforeseen challenges that we are faced with for deploying robots in complex real-world environments. One of the primary impediments has been the robustness of scene understanding" 04bf170753cee3d1da1b9ab41a5b0874685142fa,Casualty Detection for Mobile Rescue Robots via Ground-Projected Point Clouds,"TAROS2018, 037, v5 (final): ’Casualty Detection for Mobile Rescue Robots via Ground- . . ." 0462aa8b7120a34f111e81f77acd1cc7d81680a6,Color Emotions in Large Scale Content Based Image Indexing,"Link¨oping Studies in Science and Technology Dissertations, No. 1362 Color Emotions in Large Scale Content Based Image Indexing Martin Solli Department of Science and Technology Link¨oping University, SE-601 74 Norrk¨oping, Sweden Norrk¨oping, March 2011" 044fdb693a8d96a61a9b2622dd1737ce8e5ff4fa,Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions,"Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions Guoying Zhao and Matti Pietik¨ainen, Senior Member, IEEE" 0407866be9938f24acc44afd6760e27e15e6e160,Simplest representation yet for gait recognition: averaged silhouette,"Simplest Representation Yet for Gait Recognition: Averaged Silhouette Zongyi Liu and Sudeep Sarkar University of South Florida; Tampa; FL 33620 Computer Science and Engineering {zliu4," 048dc2682fd7b4fbef5b8c30cf75d422fe1a4108,Part I Face Recognition in General,"Face Recognition Jens Fagertun Kongens Lyngby 2005 Master Thesis IMM-Thesis-2005-74" 04616814f1aabe3799f8ab67101fbaf9fd115ae4,Spécialité : Informatique Et Applications Description Sémantique Des Humains Présents Dans Des Images Vidéo (semantic Description of Humans in Images),"UNIVERSIT´EDECAENBASSENORMANDIEU.F.R.deSciences´ECOLEDOCTORALESIMEMTH`ESEPr´esent´eeparM.GauravSHARMAsoutenuele17D´ecembre2012envuedel’obtentionduDOCTORATdel’UNIVERSIT´EdeCAENSp´ecialit´e:InformatiqueetapplicationsArrˆet´edu07aoˆut2006Titre:DescriptionS´emantiquedesHumainsPr´esentsdansdesImagesVid´eo(SemanticDescriptionofHumansinImages)TheworkpresentedinthisthesiswascarriedoutatGREYC-UniversityofCaenandLEAR–INRIAGrenobleJuryM.PatrickPEREZDirecteurdeRechercheINRIA/Technicolor,RennesRapporteurM.FlorentPERRONNINPrincipalScientistXeroxRCE,GrenobleRapporteurM.JeanPONCEProfesseurdesUniversit´esENS,ParisExaminateurMme.CordeliaSCHMIDDirectricedeRechercheINRIA,GrenobleDirectricedeth`eseM.Fr´ed´ericJURIEProfesseurdesUniversit´esUniversit´edeCaenDirecteurdeth`ese" 04c606e8e33cccc69060e42db53738ec6a0f1d03,Evaluation of speech quality measures for the purpose of speaker verification,"Evaluation of speech quality measures for the purpose of speaker verification Jonas Richiardi, Andrzej Drygajlo Signal Processing Institute Swiss Federal Instiute of Technology (EPFL)" 040dc119d5ca9ea3d5fc39953a91ec507ed8cc5d,Large-scale Bisample Learning on ID vs. Spot Face Recognition,"Noname manuscript No. (will be inserted by the editor) Large-scale Bisample Learning on ID vs. Spot Face Recognition Xiangyu Zhu∗ · Hao Liu∗ · Zhen Lei · Hailin Shi · Fan Yang · Dong Yi · Stan Z. Li Received: date / Accepted: date" 04bb0a1ccca86a4c1084fc7472ea07189c110aa7,Tracking Interacting Objects Using Intertwined Flows,"Tracking Interacting Objects Using Intertwined Flows Xinchao Wang∗ , Engin T¨uretken∗, Franc¸ois Fleuret, and Pascal Fua, Fellow, IEEE" 042a71e5c19bfce4e6f7b98492e68192b471a449,Towards speaker independent continuous speechreading,"TOWARDS SPEAKER INDEPENDENT CONTINUOUS SPEECHREADING Juergen Luettin IDIAP CP  ,   Martigny, Switzerland" 04b08a2735eff524f17d3f1a63eb7fc6484d4f83,Facial emotion detection using deep learning,IT 16 040Examensarbete 30 hpJuni 2016Facial emotion detection using deep learning Daniel Llatas SpiersInstitutionen för informationsteknologiDepartment of Information Technology 04bd29ec1ae0b64367ec37ddde51a0d8f8b7f670,Few-shot Object Detection,"SUBMITTED TO IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017. Few-shot Object Detection Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng" 04f4679765d2f71576dd77c1b00a2fd92e5c6da4,Part Detector Discovery in Deep Convolutional Neural Networks,"Part Detector Discovery in Deep Convolutional Neural Networks Marcel Simon, Erik Rodner, and Joachim Denzler Computer Vision Group, Friedrich Schiller University of Jena, Germany www.inf-cv.uni-jena.de" 04f7eab5d03ac6ad678f2fc8adf29bc1a84a2084,Tree based object matching using multi-scale covariance descriptor,"Tree based object matching using multi-scale covariance descriptor Walid AYEDI1,2, Hichem SNOUSSI1, Fethi SMACH2 and Mohamed ABID2 Charles Delaunay Institute (FRE CNRS 2848), University of Technology of Troyes, 10010 Troyes, France Sfax University, National Engineering School of Sfax, 3052 Sfax, Tunisia" 047f8d5d5134dd12c67038623417f05ab9885056,Motion Synthesis In : Static Scan + Expression Out : Best Fitting Sequence + Angry Out : Animated Sequence Statistical Analysis Expression Recognition,"D Faces in Motion: Fully Automatic Registration and Statistical Analysis Timo Bolkarta,∗, Stefanie Wuhrera Saarland University, Saarbr¨ucken, Germany" 044ae9738c2445d4fda30fcd6c289eddf8b3add9,Multiple Instance Learning: A Survey of Problem Characteristics and Applications,"Multiple Instance Learning: A Survey of Problem Characteristics and Applications Marc-Andr´e Carbonneau∗ Veronika Cheplygina† Eric Granger∗ Ghyslain Gagnon‡" 0480b458439069687ec41c90178ba7e9a056bcca,Gender Classification Using Gradient Direction Pattern,"Sci.Int(Lahore),25(4),797-799,2013 ISSN 1013-5316; CODEN: SINTE 8 GENDER CLASSIFICATION USING GRADIENT DIRECTION PATTERN Department of Computer Science, School of Applied Statistics, National Institute of Development Administration, Bangkok, Thailand. Mohammad Shahidul Islam" 041ac91c85276f61bec3f0f3c42782e4f9a31f88,Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform,"Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform Lingni Ma1, J¨org St¨uckler2, Tao Wu1 and Daniel Cremers1" 04dcdb7cb0d3c462bdefdd05508edfcff5a6d315,Assisting the training of deep neural networks with applications to computer vision,"Assisting the training of deep neural networks with applications to computer vision Adriana Romero tesi doctoral està subjecta a Aquesta CompartirIgual 4.0. Espanya de Creative Commons. Esta tesis doctoral está sujeta a la licencia Reconocimiento - NoComercial – CompartirIgual .0. España de Creative Commons. This doctoral thesis is licensed under the Creative Commons Attribution-NonCommercial- ShareAlike 4.0. Spain License. llicència Reconeixement- NoComercial –" 04b851f25d6d49e61a528606953e11cfac7df2b2,Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition,"Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition Shuyang Sun1,2, Zhanghui Kuang2, Lu Sheng3, Wanli Ouyang1, Wei Zhang2 The University of Sydney 2SenseTime Research 3The Chinese University of Hong Kong {shuyang.sun {wayne.zhang" 045b45adbcb83a34d087c917b79274858a878937,A Methodology for Extracting Standing Human Bodies From Single Images,"Invention Journal of Research Technology in Engineering & Management (IJRTEM) ISSN: 2455-3689 www.ijrtem.com ǁ Volume 1 ǁ Issue 8 ǁ A Methodology for Extracting Standing Human Bodies from Single Images Dr. Y. Raghavender Rao1, N. Devadas Naik2 Head ECE JNTUHCEJ Jagtityal Asst professor Sri Chaitanya engineering college" 04ceb15dfe33884ac38fa9ec0abb1e19ab090679,Resolving Referring Expressions in Images With Labeled Elements,"RESOLVING REFERRING EXPRESSIONS IN IMAGES WITH LABELED ELEMENTS Nevan Wichers, Dilek Hakkani-T¨ur, Jindong Chen Google AI, Mountain View, CA, USA" 9d35d4fba9217404a7aab84a7d09e53c324710be,Biometrics Project : Bayesian Face Recognition,"Biometrics Project: Bayesian Face Recognition Jinwei Gu Computer Science Department" 9d1940f843c448cc378214ff6bad3c1279b1911a,Shape-aware Instance Segmentation,"Shape-aware Instance Segmentation Zeeshan Hayder1,2, Xuming He2,1 Australian National University & 2Data61/CSIRO ∗ Mathieu Salzmann2,3 CVLab, EPFL, Switzerland" 9da2b79c6942852e8076cdaa4d4c93eb1ae363f1,Constraint-Based Visual Generation,"Constraint-Based Visual Generation Giuseppe Marra Francesco Giannini Marco Gori Michelangelo Diligenti Department of Information Engineering and Mathematical Sciences http://sailab.diism.unisi.it/ October 9, 2018" 9d1e32f6af50354b64ca8f004746073473559056,A visual surveillance system for person re-identification,"International Conference on Quality Control by Artificial Vision 2017, edited by Hajime Nagahara,Kazunori Umeda, Atsushi Yamashita, Proc. of SPIE Vol. 10338, 103380D · © 2017 SPIECCC code: 0277-786X/17/$18 · doi: 10.1117/12.2266509Proc. of SPIE Vol. 10338 103380D-1" 9d24179aa33a94c8c61f314203bf9e906d6b64de,Searching for People through Textual and Visual Attributes,"Searching for People through Textual and Visual Attributes Junior Fabian, Ramon Pires, Anderson Rocha Institute of Computing University of Campinas (Unicamp) Campinas-SP, Brazil Fig. 1. The proposed approach aims at searching for people using textual and visual attributes. Given an image database of faces, we extract the points of interest (PoIs) to construct a visual dictionary that allow us to obtain the feature vectors by a quantization process (top). Then we train attribute classifiers to generate a score for each image (middle). Finally, given a textual query (e.g., male), we fusion obtained scores to return a unique final rank (bottom)." 9d2ad0b408bddc9c5a713e250b52aa48f1786a46,Visual Recognition Using Local Quantized Patterns,"Visual Recognition using Local Quantized Patterns Sibt Ul Hussain, Bill Triggs To cite this version: Sibt Ul Hussain, Bill Triggs. Visual Recognition using Local Quantized Patterns. Andrew Fitzgibbon, Svetlana Lazebnik, Pietro Perona, Yoichi Sato, and Cordelia Schmid. ECCV 2012 - 12th European Conference on Computer Vision, Oct 2012, Florence, Italy. Springer, 7573, pp.716-729, 2012, Lecture Notes in Computer Science. <10.1007/978-3-642-33709-3_51>. HAL Id: hal-00695627 https://hal.archives-ouvertes.fr/hal-00695627 Submitted on 9 May 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 9d58e8ab656772d2c8a99a9fb876d5611fe2fe20,Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video,"Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video Lionel Pigou, A¨aron van den Oord∗ , Sander Dieleman∗ , {lionel.pigou,aaron.vandenoord,sander.dieleman, Mieke Van Herreweghe & Joni Dambre mieke.vanherreweghe, Ghent University February 11, 2016" 9d6a2180a5f452356526edd8b4833180fa09cb3f,Photo Aesthetics Analysis via DCNN Feature Encoding,"Photo Aesthetics Analysis via DCNN Feature Encoding Hui-Jin Lee, Ki-Sang Hong, Henry Kang, and Seungyong Lee" 9dc263210770e7e836040c8e9d0edff40814254b,A track before detect approach for sequential Bayesian tracking of multiple speech sources,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010" 9d743bbef448e7c145aeb11e55cc05fdbafe9d6d,Person tracking and gesture recognition in challenging visibility conditions using 3D thermal sensing,"Person Tracking and Gesture Recognition in Challenging Visibility Conditions Using 3D Thermal Sensing Ariel Kapusta and Patrick Beeson IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN) August, 30, 2016" 9d0ceae3747467488ba914cb2ca5b30ac3032286,Modèles graphiques probabilistes pour la reconnaissance de formes. (Probabilistic graphical models for shape recognition),"Modèles graphiques probabilistes pour la reconnaissance de formes Sabine Barrat To cite this version: Sabine Barrat. Modèles graphiques probabilistes pour la reconnaissance de formes. Interface homme- machine [cs.HC]. Université Nancy II, 2009. Français. HAL Id: tel-00530755 https://tel.archives-ouvertes.fr/tel-00530755 Submitted on 29 Oct 2010 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 9d357bbf014289fb5f64183c32aa64dc0bd9f454,Face Identification by Fitting a 3D Morphable Model Using Linear Shape and Texture Error Functions,"Face Identification by Fitting a 3D Morphable Model using Linear Shape and Texture Error Functions Sami Romdhani, Volker Blanz, and Thomas Vetter University of Freiburg, Instit¨ut f¨ur Informatik, Georges-K¨ohler-Allee 52, 79110 Freiburg, Germany, fromdhani, volker," 9d3ac3d29164c2665c371a3c71de75bea753eb47,Skeleton-Aided Articulated Motion Generation,"Skeleton-aided Articulated Motion Generation Yichao Yan, Jingwei Xu, Bingbing Ni, Xiaokang Yang" 9d8978ee319d671283a90761aaed150c7cc9154b,Fader Networks: Manipulating Images by Sliding Attributes,"Fader Networks: Manipulating Images by Sliding Attributes Guillaume Lample1,2, Neil Zeghidour1,3, Nicolas Usunier1, Antoine Bordes1, Ludovic Denoyer2, Marc’Aurelio Ranzato1" 9d9166e1d9e80bbe772423384af53a3d5da898ae,Object Geolocation Using MRF Based Multi-Sensor Fusion,"OBJECT GEOLOCATION USING MRF BASED MULTI-SENSOR FUSION Vladimir A. Krylov and Rozenn Dahyot ADAPT Centre, School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland" 9d5db7427b44d83bf036ff4cff382c23c6c7b6d8,Video redaction: a survey and comparison of enabling technologies,"Downloaded From: https://biomedicaloptics.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 10/14/2018 Terms of Use: https://biomedicaloptics.spiedigitallibrary.org/terms-of-use Videoredaction:asurveyandcomparisonofenablingtechnologiesShaganSahAmeyaShringiRaymondPtuchaAaronBurryRobertLoceShaganSah,AmeyaShringi,RaymondPtucha,AaronBurry,RobertLoce,“Videoredaction:asurveyandcomparisonofenablingtechnologies,”J.Electron.Imaging26(5),051406(2017),doi:10.1117/1.JEI.26.5.051406." 9df3c81ce84b027d9cda37c754250d31a5561005,Semantic scene modeling and retrieval,"DISS. ETH NO. 15751 Semantic Scene Modeling and Retrieval A dissertation submitted to the SWISS FEDERAL INSTITUTE OF TECHNOLOGY ZURICH for the degree of Doctor of Technical Sciences presented by JULIA VOGEL Dipl. Ing. Elektrotechnik, M.S. Electrical and Computer Engineering orn November 23, 1973 itizen of Germany ccepted on the recommendation of Prof. Dr. Bernt Schiele, examiner Prof. Dr. Andrew Zisserman, co-examiner" 9df7ea3eed6b0c9c067521119698cfa79cc1f91d,Representations and Matching Techniques for 3 D Free-form Object and Face Recognition,"Representations and Matching Techniques for 3D Free-form Object and Face Recognition Ajmal Saeed Mian This thesis is presented for the degree of Doctor of Philosophy of The University of Western Australia School of Computer Science and Software Engineering. March 2006" 9da2abae3072fd9fcff0e13b8f00fc21f22d0085,NOKMeans: Non-Orthogonal K-means Hashing,"NOKMeans: Non-Orthogonal K-means Hashing Xiping Fu, Brendan McCane, Steven Mills, and Michael Albert Dep. of Computer Science, University of Otago, Dunedin, NZ" 9d6e386a83dab99232b7b519761894a9f9b3bb41,Wide and deep volumetric residual networks for volumetric image classification,"Wide and deep volumetric residual networks for volumetric image classification Varun Arvind 1, Anthony Costa 2, Marcus Badgeley2, Samuel Cho1, Eric Oermann 2 Department of Orthopedics, Icahn School of Medicine at Mount Sinai, 1 Gustave Levy Pl. New York, NY 10029 Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, 1 Gustave Levy Pl. New York, NY 10029" 9d0bf3b351fb4d80cee5168af8367c5f6c8b2f3a,"The Tromso Infant Faces Database (TIF): Development, Validation and Application to Assess Parenting Experience on Clarity and Intensity Ratings","METHODS published: 24 March 2017 doi: 10.3389/fpsyg.2017.00409 The Tromso Infant Faces Database (TIF): Development, Validation and Application to Assess Parenting Experience on Clarity and Intensity Ratings Jana K. Maack†, Agnes Bohne†, Dag Nordahl, Lina Livsdatter, Åsne A. W. Lindahl, Morten Øvervoll, Catharina E. A. Wang and Gerit Pfuhl* Department of Psychology, UiT – The Arctic University of Norway, Tromsø, Norway Newborns and infants are highly depending on successfully communicating their needs; e.g., through crying and facial expressions. Although there is a growing interest in the mechanisms of and possible influences on the recognition of facial expressions in infants, heretofore there exists no validated database of emotional infant faces. In the present article we introduce a standardized and freely available face database containing Caucasian infant face images from 18 infants 4 to 12 months old. The development nd validation of the Tromsø Infant Faces (TIF) database is presented in Study 1. Over 700 adults categorized the photographs by seven emotion categories (happy, sad, disgusted, angry, afraid, surprised, neutral) and rated intensity, clarity and their valance." 9d8747468f0fed8e335656d7fe9737e4dc21c798,RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free,"RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free Cheng-Yang Fu Mykhailo Shvets Alexander C. Berg Computer Science Department of UNC at Chapel Hill {cyfu, mshvets," 9d8fd639a7aeab0dd1bc6eef9d11540199fd6fe2,EARNING TO C LUSTER,"Workshop track - ICLR 2018 LEARNING TO CLUSTER Benjamin B. Meier, Thilo Stadelmann & Oliver D¨urr ZHAW Datalab, Zurich University of Applied Sciences Winterthur, Switzerland" 9dc70aa3d51a9403e1894a7fa535ace99b527861,3 Bayesian Tracking by Online Co-Training and Sequential Evolutionary Importance Resampling,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,700 08,500 .7 M Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact" 9d17e897e8344d1cf42a322359b48d1ff50b4aef,Learning to Fuse Things and Stuff,"Learning to Fuse Things and Stuff Jie Li*, Allan Raventos*, Arjun Bhargava*, Takaaki Tagawa, Adrien Gaidon Toyota Research Institute (TRI)" 9d839dfc9b6a274e7c193039dfa7166d3c07040b,Augmented faces,"Augmented Faces Matthias Dantone1 Lukas Bossard1 Till Quack1,2 Luc van Gool1,3 ETH Z¨urich Kooaba AG K.U. Leuven" 9d518344d5c7d889f9c90c6193be4757fa584770,3 D registration based on a multi-references local parametrisation : Application to 3 D faces,"D registration based on a multi-references local parametrisation: Application to 3D faces Wieme Gadacha1, Faouzi Ghorbel1 CRISTAL laboratory, GRIFT research group National School of Computer Sciences (NSCS), La Manouba 2010, Tunisia" 9d138bc60593c2770d968ba56172332773e02fa5,GPLAC: Generalizing Vision-Based Robotic Skills Using Weakly Labeled Images, 9d67af2158807aa815b5a4485b076f7a18ce6ab4,Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding,"Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding Christos Sakaridis1(), Dengxin Dai1, Simon Hecker1, and Luc Van Gool1,2 ETH Z¨urich, Z¨urich, Switzerland KU Leuven, Leuven, Belgium" c27f64eaf48e88758f650e38fa4e043c16580d26,Title of the proposed research project: Subspace analysis using Locality Preserving Projection and its applications for image recognition,"Title of the proposed research project: Subspace analysis using Locality Preserving Projection and its applications for image recognition Research area: Data manifold learning for pattern recognition Contact Details: Name: Gitam C Shikkenawis Email Address: University: Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar." c2b8b49526e3dd537b641a6495e49a3d1a0ebbf2,Extended Feature-Fusion Guidelines to Improve Image-Based Multi-Modal Biometrics,"Extended Feature-Fusion Guidelines to Improve Image-Based Multi-Modal Biometrics Dane Brown Council for Scientific and Industrial Research Information Security Pretoria, South Africa" c274a4428e81f49c2395f4b3888e768e2dec9ee9,CPU / GPGPU / HW comparison of an Eigenfaces face recognition system,"Universidad Politécnica de Madrid Escuela Técnica Superior de Ingenieros Industriales Departamento de Automática, Ingeniería Electrónica e Informática Industrial Master on Industrial Electronics CPU/GPGPU/HW comparison of n Eigenfaces face recognition system Author: Julio Camarero Mateo Advisor: Eduardo de la Torre Arnanz March 2014 Master Thesis" c26735fb53c54b7319857797dc16786123626d14,Model Cards for Model Reporting,"Model Cards for Model Reporting Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, Timnit Gebru" c2e6daebb95c9dfc741af67464c98f1039127627,Efficient Measuring of Facial Action Unit Activation Intensities using Active Appearance Models,"MVA2013 IAPR International Conference on Machine Vision Applications, May 20-23, 2013, Kyoto, JAPAN Ef‌f‌icient Measuring of Facial Action Unit Activation Intensities using Active Appearance Models Daniel Haase1, Michael Kemmler1, Orlando Guntinas-Lichius2, Joachim Denzler1 Computer Vision Group, Friedrich Schiller University of Jena, Germany Department of Otolaryngology, University Hospital Jena, Germany" c219244bf27ed16c5c710f3a7c7d92b1ea16e8cc,An Independent Evaluation of Subspace Face Recognition Algorithms,"An Independent Evaluation of Subspace Face Recognition Algorithms Dhiresh R. Surajpal and Tshilidzi Marwala" c2cb401f73ee13f35368127939c6db8654aa422a,Learning Optical Flow from Real Robot Data,"Learning Optical Flow from Real Robot Data Parth Shah" c2d35b387518496d8100f70e82597b002eba600e,Online Multi-player Tracking in Monocular Soccer Videos,"Available online at www.sciencedirect.com AASRI Procedia 00 (2014) 000–000 014 AASRI Conference on Sports Engineering and Computer Science (SECS 2014) Online Multi-player Tracking in Monocular Soccer Videos Michael Herrmanna,*, Martin Hoerniga, Bernd Radiga Technische Universität München, Image Understanding and Knowledge-Based Systems, Boltzmannstr. 3, D-85748 Garching, Germany" c21db705a33212768c63be11747d075371c7307f,A Content-Based Late Fusion Approach Applied to Pedestrian Detection,"A Content-Based Late Fusion Approach Applied to Pedestrian Detection Jessica Sena, Artur Jord˜ao, William Robson Schwartz Smart Surveillance Interest Group Department of Computer Science, Universidade Federal de Minas Gerais Av. Presidente Antˆonio Carlos, 6627 - Pampulha, Belo Horizonte, Brazil" c2cb4da617168c76c4560a01de8b5e68b5250749,FineTag: Multi-attribute Classification at Fine-grained Level in Images,"FineTag: Multi-attribute Classification at Fine-grained Level in Images Roshanak Zakizadeh, Michele Sasdelli, Yu Qian and Eduard Vazquez Cortexica Vision Systems, London, UK" c259693737ce52e2e37972e15334cbe78b653e69,Image Processing Supports HCI in Museum Application,"Image Processing Supports HCI in Museum Application Niki Martinel, Marco Vernier, Gian Luca Foresti and Elisabetta Lamedica Department of Mathematics and Computer Science, University of Udine, Via Delle Scienze 206, Udine, Italy {niki.martinel, marco.vernier, Keywords: Augmented Reality: Information Visualization: User Interface Design: Mobile HCI." c29487c5eb0cdb67d92af1bc0ecbcf825e2abec3,3-D Face Recognition With the Geodesic Polar Representation,"-D Face Recognition With the Geodesic Polar Representation Iordanis Mpiperis, Sotiris Malassiotis, and Michael G. Strintzis, Fellow, IEEE therefore," c2b9d6742e504491800cee44adb05d2d706fc209,Semantic-Based Web Mining For Image Retrieval Using Enhanced Support Vector Machine,"International Journal of Applied Engineering Research ISSN 0973-4562 Volume 11, Number 5 (2016) pp 3276-3281 © Research India Publications. http://www.ripublication.com Semantic-Based Web Mining For Image Retrieval Using Enhanced Support Vector Machine Ph.D Research Scholar, Research Department of Computer Science, NGM College, Pollachi, Coimbatore, Tamil Nadu, India. P. Sumathi R. Manickachezian Associate Professor, Research Department of Computer Science, NGM College, Pollachi, Coimbatore, Tamil Nadu, India." c231d8638e8b5292c479d20f7dd387c53e581a1a,Multi-View Data Generation Without View Supervision,"MULTI-VIEW DATA GENERATION WITHOUT VIEW SUPERVISION Micka¨el Chen, Ludovic Denoyer Sorbonne Universit´es, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005, Paris, France Thierry Arti`eres Ecole Centrale Marseille - Laboratoire d’Informatique Fondamentale (Aix-Marseille Univ.), France." c254b4c0f6d5a5a45680eb3742907ec93c3a222b,A Fusion-based Gender Recognition Method Using Facial Images,"A Fusion-based Gender Recognition Method Using Facial Images Benyamin Ghojogh, Saeed Bagheri Shouraki, Hoda Mohammadzade*, Ensieh Iranmehr" c28f57d0a22e54fdd3c4a57ecb1785dda49f0e5e,From Scores to Face Templates: A Model-Based Approach,"From Scores to Face Templates: A Model-Based Approach Pranab Mohanty, Student Member, IEEE, Sudeep Sarkar, Senior Member, IEEE, and Rangachar Kasturi, Fellow, IEEE" c2adfc55e0ab9be6e8f5e4ebeb20770dca307cef,"The effect of diagnosis, age, and symptom severity on cortical surface area in the cingulate cortex and insula in autism spectrum disorders.","http://jcn.sagepub.com/ The Effect of Diagnosis, Age, and Symptom Severity on Cortical Surface Area in the Cingulate Cortex nd Insula in Autism Spectrum Disorders Krissy A.R. Doyle-Thomas, Azadeh Kushki, Emma G. Duerden, Margot J. Taylor, Jason P. Lerch, Latha V. Soorya, A. Ting Wang, Jin Fan and Evdokia Anagnostou J Child Neurol 2013 28: 729 originally published online 25 July 2012 DOI: 10.1177/0883073812451496 The online version of this article can be found at: http://jcn.sagepub.com/content/28/6/729 Published by: http://www.sagepublications.com Additional services and information for can be found at: Email Alerts: http://jcn.sagepub.com/cgi/alerts Subscriptions: http://jcn.sagepub.com/subscriptions Reprints: http://www.sagepub.com/journalsReprints.nav" c2fb2cb5487ad404b8e66daf74198496c40bef32,Learning to Transfer Privileged Information,"Learning to Transfer Privileged Information Viktoriia Sharmanska1∗, Novi Quadrianto2, and Christoph Lampert1, Institute of Science and Technology Austria, Austria SMiLe CLiNiC, University of Sussex, UK" c2b1007824fa7ce3a7a94209f0be0902a3454bae,Project Description 1 Introduction,"Project Description Introduction Recognizing human action is a key component in many vision applications, such as video surveil- lance, 3D human pose estimation and video indexing. From the human-centered computing (HCC) point of view, an automatic action recognition system can provide an interface between artificial gents and human users accounting for perception and action in a novel interaction paradigm. Although significant progress has been made in action recognition [1], the problem remains inher- ently challenging due to significant intra-class variations, viewpoint change, partial occlusion and ackground dynamic variations. A key limitation of many action-recognition approaches is that their models are learned from single 2D view video features on individual datasets and thus un- ble to handle arbitrary view change or scale and background variations. Also, since they are not generalizable across different datasets, retraining is necessary for any new dataset. Our research is motivated by the requirement of view-invariant action recognition and the fact that the existing human motion capture data provides useful knowledge to understand the intrinsic motion structure (Fig. 2). In particular, we address the problem of modeling and analyzing human motion in the joint-trajectories space. Our view-invariant recognition system has the following functions (Fig. 1), (1) Given a labeled Mocap sequences with M markers in 3D, which is a 3M -dimensional sequential data, the low dimensional manifold structure (i.e., geodesics distance, intrinsic dimensionality, etc) is learnt by using Tensor Voting. This is an offline process, as shown in Fig. 1." c2f2c89d7615df07b540748d6c53485c4cbfa9c0,An Experience Report on Requirements-Driven Model-Based Synthetic Vision Testing,"An Experience Report on Requirements-Driven Model-Based Synthetic Vision Testing Markus Murschitz and Oliver Zendel and Martin Humenberger nd Christoph Sulzbachner and Gustavo Fern´andez Dom´ınguez 1" c2eed73654b544a705b194ade58cd82488c6c5b9,Pixels labeled with a scene ’ s semantics and geometry let computers describe what they see,"ontributed articles DOI:10.1145/2629637 Pixels labeled with a scene’s semantics and geometry let computers describe what they see. BY STEPHEN GOULD AND XUMING HE Scene Understanding y Labeling Pixels PROGRAMMING COMPUTERS TO automatically interpret the content of an image is a long-standing challenge in rtificial intelligence and computer vision. That difficulty is echoed in a well-known anecdote from the early years of computer-vision research in which an undergraduate student at MIT was asked to spend his summer getting a omputer to describe what it “saw” in images obtained from a video camera.35 Almost 50 years later researchers re still grappling with the same problem. A scene can be described in many ways and include details about objects, regions, geometry, location," c2cb38fc68b877a96be99b814e8ee437e585f5b2,Mining on Manifolds: Metric Learning without Labels,"Mining on Manifolds: Metric Learning without Labels Ahmet Iscen1 Giorgos Tolias1 Yannis Avrithis2 Ondˇrej Chum1 VRG, FEE, CTU in Prague Inria Rennes" c2e9300b0e72dca0b95ccd4181fc2a7a5178dea7,Improving Bilayer Product Quantization for Billion-Scale Approximate Nearest Neighbors in High Dimensions.,"Improving Bilayer Product Quantization for Billion-Scale Approximate Nearest Neighbors in High Dimensions Artem Babenko Yandex Moscow Institute of Physics and Technology Victor Lempitsky Skolkovo Institute of Science and Technology" c223b2b7d38dc4e0ad418c404b2d3c43c62213bc,Trade-off Between GPGPU based Implementations of Multi Object Tracking Particle Filter,"Trade-off between GPGPU based implementations of multi object tracking particle filter Petr Jecmen, Frédéric Lerasle, Alhayat Ali Mekonnen To cite this version: Petr Jecmen, Frédéric Lerasle, Alhayat Ali Mekonnen. Trade-off between GPGPU based implemen- tations of multi object tracking particle filter. International Conference on Computer Vision Theory nd Applications, Feb 2017, Porto, Portugal. 10p., 2017. HAL Id: hal-01763095 https://hal.laas.fr/hal-01763095 Submitted on 10 Apr 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" c20b2ec72ebf798e9567a145465e37a755fc34d8,Fully Automatic Multi-person Human Motion Capture for VR Applications,"Fully Automatic Multi-person Human Motion Capture for VR Applications Ahmed Elhayek1,2, Onorina Kovalenko1, Pramod Murthy1,2, Jameel Malik1,2, and Didier Stricker1,2 German Research Centre for Artificial Intelligence (DFKI), Kaiserslautern, Germany University of Kaiserslautern, Germany {ahmed.elhayek, onorina.kovalenko, pramod.murthy, jameel.malik," 3f7723ab51417b85aa909e739fc4c43c64bf3e84,Improved Performance in Facial Expression Recognition Using 32 Geometric Features,"Improved Performance in Facial Expression Recognition Using 32 Geometric Features Giuseppe Palestra1(B), Adriana Pettinicchio2, Marco Del Coco2, Pierluigi Carcagn`ı2, Marco Leo2, and Cosimo Distante2 Department of Computer Science, University of Bari, Bari, Italy National Institute of Optics, National Research Council, Arnesano, LE, Italy" 3f9210830e31f42103c6550f75cb37fde18e5af1,HeadFusion: 360° Head Pose Tracking Combining 3D Morphable Model and 3D Reconstruction,"PAMI SPECIAL ISSUE HeadFusion: 360◦Head Pose tracking combining D Morphable Model and 3D Reconstruction Yu Yu, Kenneth Alberto Funes Mora, Jean-Marc Odobez" 3f848d6424f3d666a1b6dd405a48a35a797dd147,Is 2D Information Enough For Viewpoint Estimation?,"GHODRATI et al.: IS 2D INFORMATION ENOUGH FOR VIEWPOINT ESTIMATION? Is 2D Information Enough For Viewpoint Estimation? Amir Ghodrati Marco Pedersoli Tinne Tuytelaars KU Leuven, ESAT - PSI, iMinds Leuven, Belgium" 3f10b9d98a276fb9e21e5742ce88bc7f48629715,Imparare a Quantificare Guardando (Learning to Quantify by Watching),"Imparare a quantificare guardando Sandro Pezzelle CIMeC Ionut Sorodoc Aurelie Herbelot CIMeC EM LCT Universit`a degli Studi di Trento Raffaella Bernardi CIMeC, DISI" 3fd90098551bf88c7509521adf1c0ba9b5dfeb57,Attribute-Based Classification for Zero-Shot Visual Object Categorization,"Page 1 of 21 *****For Peer Review Only***** Attribute-Based Classification for Zero-Shot Visual Object Categorization Christoph H. Lampert, Hannes Nickisch and Stefan Harmeling" 3f06d445371c252d5a6ba977181987094148d6de,Fast Single Shot Detection and Pose Estimation,"Fast Single Shot Detection and Pose Estimation Patrick Poirson1, Phil Ammirato1, Cheng-Yang Fu1, Wei Liu1, Jana Koˇseck´a2, Alexander C. Berg1 UNC Chapel Hill 2George Mason University 201 S. Columbia St., Chapel Hill, NC 27599 24400 University Dr, Fairfax, VA 22030" 3f6a6050609ba205ec94b8af186a9dca60a8f65e,Harmonizing Maximum Likelihood with Gans,"Under review as a conference paper at ICLR 2019 HARMONIZING MAXIMUM LIKELIHOOD WITH GANS FOR MULTIMODAL CONDITIONAL GENERATION Anonymous authors Paper under double-blind review" 3f60b1f800178841f4e0ecb79b64fe60b48ed03b,Video Scene Parsing with Predictive Feature Learning,"Video Scene Parsing with Predictive Feature Learning Xiaojie Jin1 Xin Li2 Huaxin Xiao2 Xiaohui Shen3 Zhe Lin3 Jimei Yang3 Yunpeng Chen2 Jian Dong4 Luoqi Liu4 Zequn Jie2 Jiashi Feng2 Shuicheng Yan4,2 NUS Graduate School for Integrative Science and Engineering, NUS 360 AI Institute Department of ECE, NUS Adobe Research" 3f0f3c2bc151ef91959b06442b9ad80d405387a5,Evidential combination of pedestrian detectors,"XU ET AL.: EVIDENTIAL COMBINATION OF PEDESTRIAN DETECTORS Evidential combination of pedestrian detectors Philippe Xu1 https://www.hds.utc.fr/~xuphilip Franck Davoine12 Thierry Denœux1 https://www.hds.utc.fr/~tdenoeux UMR CNRS 7253, Heudiasyc, Université de Technologie de Compiègne, France CNRS, LIAMA, Beijing, P. R. China" 3f8e481ea845aa20704d8c93f6a3a72025219f64,Data mapping by probabilistic modular networks and information-theoretic criteria,"IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 46, NO. 12, DECEMBER 1998 Data Mapping by Probabilistic Modular Networks and Information-Theoretic Criteria Yue Wang, Shang-Hung Lin, Huai Li, and Sun-Yuan Kung, Fellow, IEEE" 3f600008dd9745e8357f5b7b3c1a69b8be6b7767,Atypical reflexive gaze patterns on emotional faces in autism spectrum disorders.,"The Journal of Neuroscience, September 15, 2010 • 30(37):12281–12287 • 12281 Behavioral/Systems/Cognitive Atypical Reflexive Gaze Patterns on Emotional Faces in Autism Spectrum Disorders Dorit Kliemann,1,2,3 Isabel Dziobek,2 Alexander Hatri,1,2 Rosa Steimke,2,4 and Hauke R. Heekeren1,2,3 Department of Educational Science and Psychology, and 2Cluster of Excellence, “Languages of Emotion,” Freie Universita¨t Berlin, 14195 Berlin, Germany, nd 3Max Planck Institute for Human Development, 14195 Berlin, Germany, and 4Department of Psychiatry and Psychotherapy, Charité University Medicine, 10117 Berlin, Germany Atypical scan paths on emotional faces and reduced eye contact represent a prominent feature of autism symptomatology, yet the reason for these abnormalities remains a puzzle. Do individuals with autism spectrum disorders (ASDs) fail to orient toward the eyes or do they ctively avoid direct eye contact? Here, we used a new task to investigate reflexive eye movements on fearful, happy, and neutral faces. Participants (ASDs: 12; controls: 11) initially fixated either on the eyes or on the mouth. By analyzing the frequency of participants’ eye movements away from the eyes and toward the eyes, respectively, we explored both avoidance and orientation reactions. The ASD group showed a reduced preference for the eyes relative to the control group, primarily characterized by more frequent eye movements away from the eyes. Eye-tracking data revealed a pronounced influence of active avoidance of direct eye contact on atypical gaze in ASDs. The ombination of avoidance and reduced orientation into an individual index predicted emotional recognition performance. Crucially, this result provides evidence for a direct link between individual gaze patterns and associated social symptomatology. These findings thereby give important insights into the social pathology of ASD, with implications for future research and interventions. Introduction Recent reports from the social-cognitive neurosciences have em-" 3f9d1e2dd09a4f2ab939693e91fcfd77d51d90c9,Reducing drift in visual odometry by inferring sun direction using a Bayesian Convolutional Neural Network,"Reducing Drift in Visual Odometry by Inferring Sun Direction Using a Bayesian Convolutional Neural Network‡ Valentin Peretroukhin†, Lee Clement†, and Jonathan Kelly" 3f9a7d690db82cf5c3940fbb06b827ced59ec01e,VIP: Finding important people in images,"VIP: Finding Important People in Images Clint Solomon Mathialagan Virginia Tech Andrew C. Gallagher Google Inc. Dhruv Batra Virginia Tech Project: https://computing.ece.vt.edu/~mclint/vip/ Demo: http://cloudcv.org/vip/" 3f5b20c35f55417823f0201862d85af1f31e9348,Salience Biased Loss for Object Detection in Aerial Images,"Salience Biased Loss for Object Detection in Aerial Images Peng Sun Guerdan Luke Guang Chen University of Missouri-Columbia Yi Shang over regular and dense sampling of object scales, locations, nd aspect ratios, such as YOLO [8], SSD [11], and RetinaNet [18]. Each of these demonstrates promising results with faster speed, a simpler network, and similar accuracy of two-stage object detectors. RetinaNet [18] even outperforms one of the est two-stage detectors, Faster R-CNN [5], with a relative 4.0 mAP improvement in COCO data [17]." 3fdcc1e2ebcf236e8bb4a6ce7baf2db817f30001,A Top-Down Approach for a Synthetic Autobiographical Memory System,"A top-down approach for a synthetic utobiographical memory system Andreas Damianou1,2, Carl Henrik Ek3, Luke Boorman1, Neil D. Lawrence2, nd Tony J. Prescott1 Shef‌f‌ield Centre for Robotics (SCentRo), Univ. of Shef‌f‌ield, Shef‌f‌ield, S10 2TN, UK Dept. of Computer Science, Univ. of Shef‌f‌ield, Shef‌f‌ield, S1 4DP, UK CVAP Lab, KTH, Stockholm, Sweden" 3fac7c60136a67b320fc1c132fde45205cd2ac66,Remarks on Computational Facial Expression Recognition from HOG Features Using Quaternion Multi-layer Neural Network,"Remarks on Computational Facial Expression Recognition from HOG Features Using Quaternion Multi-layer Neural Network Kazuhiko Takahashi1, Sae Takahashi1, Yunduan Cui2, nd Masafumi Hashimoto3 Information Systems Design, Doshisha University, Kyoto, Japan Graduate School of Doshisha University, Kyoto, Japan Intelligent Information Engineering and Science, Doshisha University, Kyoto, Japan" 3fa9bf4649ff5e0d63ee20a546e8814f3a93ca4d,Digital Image Technique using Gabor Filter and SVM in Heterogeneous Face Recognition,"Research Inventy: International Journal of Engineering And Science Vol.4, Issue 4 (April 2014), PP 45-52 Issn (e): 2278-4721, Issn (p):2319-6483, www.researchinventy.com Digital Image Technique using Gabor Filter and SVM in Heterogeneous Face Recognition M.Janani#1, K.Nandhini*2, K.Senthilvadivel*3,S.Jothilakshmi*4, PG Student#1,*2*3, Assistant Professor*4,, Dept of CSE#1,*2,*3,*4 S.V.S College of Engineering#1,*4,, PPG Institute of Technology*2,*3, Coimbatore, Tamilnadu" 3f0e0739677eb53a9d16feafc2d9a881b9677b63,Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification,"Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification Ali Diba ESAT-KU Leuven Ali Pazandeh Sharif UTech Luc Van Gool ESAT-KU Leuven, ETH Zurich" 3f55d26dd638c849745b95e912c28d88445ba5e1,Supervised Learning of Universal Sentence Representations from Natural Language Inference Data,"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data Alexis Conneau Facebook AI Research Douwe Kiela Facebook AI Research Holger Schwenk Facebook AI Research Lo¨ıc Barrault LIUM, Universit´e Le Mans Antoine Bordes Facebook AI Research" 3fa738ab3c79eacdbfafa4c9950ef74f115a3d84,DaMN - Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition,"DaMN – Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition Rui Hou1, Amir Roshan Zamir1, Rahul Sukthankar2, and Mubarak Shah1 Center for Research in Computer Vision at UCF, Orlando, USA Google Research, Mountain View, USA http://crcv.ucf.edu/projects/DaMN/" 3f9c09e2fbefc9aeba6505f49317f9a2fc03a615,Understanding fundamental design choices in single-ISA heterogeneous multicore architectures,"Understanding Fundamental Design Choices in Single-ISA Heterogeneous Multicore Architectures KENZO VAN CRAEYNEST and LIEVEN EECKHOUT, Ghent University Single-ISA heterogeneous multicore processors have gained substantial interest over the past few years ecause of their power efficiency, as they offer the potential for high overall chip throughput within a given power budget. Prior work in heterogeneous architectures has mainly focused on how heterogeneity an improve overall system throughput. To what extent heterogeneity affects per-program performance has remained largely unanswered. In this article, we aim at understanding how heterogeneity affects both hip throughput and per-program performance; how heterogeneous architectures compare to homogeneous rchitectures under both performance metrics; and how fundamental design choices, such as core type, cache size, and off-chip bandwidth, affect performance. We use analytical modeling to explore a large space of single-ISA heterogeneous architectures. The ana- lytical model has linear-time complexity in the number of core types and programs of interest, and offers a unique opportunity for exploring the large space of both homogeneous and heterogeneous multicore proces- sors in limited time. Our analysis provides several interesting insights: While it is true that heterogeneity an improve system throughput, it fundamentally trades per-program performance for chip throughput; lthough some heterogeneous configurations yield better throughput and per-program performance than homogeneous designs, some homogeneous configurations are optimal for particular throughput versus per- program performance trade-offs. Two core types provide most of the benefits from heterogeneity and a larger number of core types does not contribute much; job-to-core mapping is both important and challenging for" 3f44352b857f2fc18c18c5ebb2cbf994ee22f44c,Humanist computing for knowledge discovery from ordered datasets,"HumanistComputingforKnowledgeDiscovery fromOrderedDatasets JonathanMichaelRossiter DepartmentofEngineeringMathematics UniversityofBristol AdissertationsubmittedtotheUniversityofBristol inaccordancewiththerequirementsofthedegreeof DoctorofPhilosophyintheFacultyofEngineering January" 3f5158ea65bb483c6797462faffa16fea9f0b004,"Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups","Lie-X : Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups Chi Xu1, Lakshmi Narasimhan Govindarajan1, Yu Zhang1, and Li Cheng∗1 Bioinformatics Institute, A*STAR, Singapore" 3fea412361b2d14cb3c6723968b421c1c8cb38e8,Shake-Shake regularization,"Shake-Shake regularization Xavier Gastaldi" 3f63f9aaec8ba1fa801d131e3680900680f14139,Facial Expression Recognition using Local Binary Patterns and Kullback Leibler Divergence,"Facial Expression Recognition using Local Binary Patterns and Kullback Leibler Divergence AnushaVupputuri, SukadevMeher divergence." 3f0e00188d751829c4548f9aacb939b982425ebd,Template Protection For 3 D Face Recognition 315 Template Protection For 3 D Face Recognition,"Template Protection For 3D Face Recognition Template Protection For 3D Face Recognition Xuebing Zhou, Arjan Kuijper and Christoph Busch Fraunhofer Institute for Computer Graphics Research IGD Germany" 3faebe9d5c47fc90998811c4ac768706283d605c,Semi-Supervised Detection of Extreme Weather Events in Large Climate Datasets,"Under review as a conference paper at ICLR 2017 SEMI-SUPERVISED DETECTION OF EXTREME WEATHER EVENTS IN LARGE CLIMATE DATASETS Evan Racah1, Christopher Beckham2, Tegan Maharaj2 Prabhat1, Christopher Pal2 Lawrence Berkeley National Lab, Berkeley, CA, ´Ecole Polytechnique de Montr´eal," 3faff93758fe7fc58b3832055cb15c6ca3f306a7,Evaluation of multi feature fusion at score-level for appearance-based person re-identification,"Evaluation of Multi Feature Fusion at Score-Level for Appearance-based Person Re-Identification Markus Eisenbach Ilmenau University of Technology 98684 Ilmenau, Germany Alexander Kolarow Alexander Vorndran Julia Niebling Horst-Michael Gross Ilmenau University of Technology Ilmenau University of Technology 98684 Ilmenau, Germany 98684 Ilmenau, Germany" 3f2270762ff68d6771d93d800683ae6bc76855e7,Human Motion Tracking and Pose Estimation using Probabilistic Activity Models,"MANCHESTER METROPOLITAN UNIVERSITY D Human Motion Tracking and Pose Estimation using Probabilistic Activity Models John Darby A thesis submitted in partial fulfillment for the degree of Doctor of Philosophy Faculty of Science and Engineering The Department of Computing and Mathematics October 2010" e5eb7fa8c9a812d402facfe8e4672670541ed108,Performance of PCA Based Semi-supervised Learning in Face Recognition Using MPEG-7 Edge Histogram Descriptor,"Performance of PCA Based Semi-supervised Learning in Face Recognition Using MPEG-7 Edge Histogram Descriptor Shafin Rahman, Sheikh Motahar Naim, Abdullah Al Farooq and Md. Monirul Islam Department of Computer Science and Engineering Bangladesh University of Engineering and Technology(BUET) Dhaka-1000, Bangladesh Email: {shafin buet, naim sbh2007," e5d13afe956d8581a69e9dc2d1f43a43f1e2f311,Automatic Facial Feature Extraction for Face Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,700 08,500 .7 M Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact" e5320955580401d5a5b2ae8b507e8f0b47e08118,Deep Supervision with Intermediate Concepts,"Deep Supervision with Intermediate Concepts Chi Li, M. Zeeshan Zia, Quoc-Huy Tran, Xiang Yu, Gregory D. Hager, and Manmohan Chandraker" e58f08ad6e0edd567f217ef08de1701a8c29fcc8,Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing - and Back,"Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back Elliot Meyerson 1 2 Risto Miikkulainen 1 2" e59a68c328c69c294991f87b741a5d4e952defba,NISTIR 7972 Performance Metrics for Evaluating Object and Human Detection and Tracking Systems,"This publication is available free of charge from http://dx.doi.org/10.6028/NIST.IR.7972 NISTIR 7972 Performance Metrics for Evaluating Object and Human Detection and Tracking Systems Afzal Godil Roger Bostelman Will Shackleford Tsai Hong Michael Shneier http://dx.doi.org/10.6028/NIST.IR.7972" e577847c36251dc31282ad57ea969ea8297369be,Face scanning and spontaneous emotion preference in Cornelia de Lange syndrome and Rubinstein-Taybi syndrome,"Crawford et al. Journal of Neurodevelopmental Disorders (2015) 7:22 DOI 10.1186/s11689-015-9119-4 R ES EAR CH Face scanning and spontaneous emotion preference in Cornelia de Lange syndrome nd Rubinstein-Taybi syndrome Hayley Crawford1,2*, Joanna Moss2,3, Joseph P. McCleery4, Giles M. Anderson5 and Chris Oliver2 Open Access" e596a4aedb5cda6f0df35d38549564a0dd5546a7,Public Document Document Evolution Executive Summary,"Project N° IST-2002-507634 - BioSecure D 9.1.3 – Revision: b2 09 June 2006 Contract Number : Project Acronym : Project Title : Instrument : Start Date of Project : Duration : Deliverable Number : Title of Deliverable : Contractual Due Date : Actual Date of Completion : IST-2002-507634 BioSecure Biometrics for Secure Authentication Network of Excellence 01 June, 2004 6 months D 9.1.3" e596753824ed56f17927984f78f51713b321588d,3DOF Pedestrian Trajectory Prediction Learned from Long-Term Autonomous Mobile Robot Deployment Data,"DOF Pedestrian Trajectory Prediction Learned from Long-Term Autonomous Mobile Robot Deployment Data Li Sun1 and Zhi Yan2 and Sergi Molina Mellado1 and Marc Hanheide1 and Tom Duckett1" e5563a0d6a2312c614834dc784b5cc7594362bff,Real-Time Demographic Profiling from Face Imagery with Fisher Vectors,"Noname manuscript No. (will be inserted by the editor) Real-Time Demographic Profiling from Face Imagery with Fisher Vectors Lorenzo Seidenari · Alessandro Rozza · Alberto Del Bimbo Received: ... / Accepted: ..." e524f222a117890126bd9597934d0504adce85ec,Error Correction for Dense Semantic Image Labeling,"Yu-Hui Huang1∗ Xu Jia2∗ Stamatios Georgoulis1 Tinne Tuytelaars2 Luc Van Gool1,3 KU-Leuven/ESAT-PSI, Toyota Motor Europe (TRACE) ETH/DITET-CVL KU-Leuven/ESAT-PSI, IMEC" e58434a01c45505995b000f5e631843a2f2ea582,Scale coding bag of deep features for human attribute and action recognition,"Noname manuscript No. (will be inserted by the editor) Scale Coding Bag of Deep Features for Human Attribute nd Action Recognition Fahad Shahbaz Khan, Joost van de Weijer, Rao Muhammad Anwer, Andrew D. Bagdanov, Michael Felsberg, Jorma Laaksonen Received:" e5918229f44f0215d73a0b9d5eb13eb56764a2e4,Counting Vehicles with Cameras,"Counting Vehicles with Cameras Luca Ciampi1, Giuseppe Amato1, Fabrizio Falchi1, Claudio Gennaro1, and Fausto Rabitti1 Institute of Information, Science and Technologies of the National Research Council of Italy (ISTI-CNR), via G. Moruzzi 1, 56124 Pisa, Italy" e5c468c859faf03954d9440fa33b913d01c65141,Retina alapú mintavételezés arckomponens detektálási feladaton,"-JLI 6AH =H AJE= ==Fœ EJ=L JAA I =H?FAI 5=> J )==JJ =JA=JEKI D=C=J 6 =LAAJfi 5=JHO BH=JE= 2D, D=C=J -6- 66 1BH?EI 6=I " e525ba29497bab9b530ea7b056dd0128be22c48a,Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning.,"Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning Baoyuan Wu, Weidong Chen, Yanbo Fan, Yong Zhang, Jinlong Hou, Jie Liu, Junzhou Huang, Wei Liu, Tong Zhang" e5799fd239531644ad9270f49a3961d7540ce358,Kinship classification by modeling facial feature heredity,"KINSHIP CLASSIFICATION BY MODELING FACIAL FEATURE HEREDITY Ruogu Fang1, Andrew C. Gallagher1, Tsuhan Chen1, Alexander Loui2 Dept. of Elec. and Computer Eng., Cornell University 2Eastman Kodak Company" e5604c3f61eb7e8b80bf423f7828d8c1fa0f1d32,Towards Image Understanding from Deep Compression without Decoding,"Published as a conference paper at ICLR 2018 TOWARDS IMAGE UNDERSTANDING FROM DEEP COMPRESSION WITHOUT DECODING Robert Torfason ETH Zurich, Merantix Fabian Mentzer ETH Zurich Eirikur Agustsson ETH Zurich Michael Tschannen ETH Zurich Radu Timofte ETH Zurich, Merantix Luc Van Gool ETH Zurich, KU Leuven" e56c4c41bfa5ec2d86c7c9dd631a9a69cdc05e69,Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art,"Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art Artur Jord˜ao, Antonio C. Nazare Jr., Jessica Sena and William Robson Schwartz Smart Surveillance Interest Group, Computer Science Department Universidade Federal de Minas Gerais, Brazil Email: {arturjordao, antonio.nazare, jessicasena," e564268a03b21fa092390db0c11ba1c33d2323f9,Multi-view Stereo with Single-View Semantic Mesh Refinement,"Multi-View Stereo with Single-View Semantic Mesh Refinement Andrea Romanoni Marco Ciccone Francesco Visin Matteo Matteucci {andrea.romanoni, marco.ciccone, francesco.visin, Politecnico di Milano, Italy" e5dcec59afdab7c15e3a874e9b602b8fc42b9019,Nonparametric Video Retrieval and Frame Classification using Tiny Videos,"International Conference on Recent Trends in Computational Methods, Communication and Controls (ICON3C 2012) Proceedings published in International Journal of Computer Applications® (IJCA) Nonparametric Video Retrieval and Frame Classification using Tiny Videos A.K. M. Shanawas Fathima, PG Student, Department of CSE GCE, Tirunelveli. R. Kanthavel, Department of CSE, Government College of Engineering, Tirunelveli." e502dad3aa196a47ed3cfb727b6b75c65be8a871,A Baseline for Multi-Label Image Classification Using Ensemble Deep CNN.,"A Baseline for Multi-Label Image Classification Using Ensemble Deep CNN Qian Wang Toby Breckon Ning Jia Durham University {qian.wang,ning.jia," e56c99e8a94d3e585166fcd66f2ab6da60932f09,Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech,"Semantic speech retrieval with a visually grounded model of untranscribed speech Herman Kamper, Gregory Shakhnarovich, and Karen Livescu" e592f6dc3bf1d53044cd59ce4a75fdacd0ecc80d,Hand Vein Infrared Image Segmentation for Biometric Recognition,"Hand Vein Infrared Image Segmentation for Biometric Recognition Ignacio Irving Morales-Montiel1, J. Arturo Olvera-López1, Manuel Martín-Ortíz1, and Eber E. Orozco-Guillén2 Facultad de Ciencias de la Computación Benemérita Universidad Autónoma de Puebla Av. San Claudio y 14 sur. Ciudad Universitaria. Puebla, Pue., Mexico Mazatlán, Sin., Mexico Programa de Ingeniería en Informática Universidad Politécnica de Sinaloa Carretera Municipal Libre Mazatlán Higueras Km. 3." e5bcbfd346121769b674a7ad35e594758de5553f,A Dataset for Lane Instance Segmentation in Urban Environments,"A Dataset for Lane Instance Segmentation in Urban Environments Brook Roberts, Sebastian Kaltwang, Sina Samangooei, Mark Pender-Bare, Konstantinos Tertikas, and John Redford FiveAI Ltd., Cambridge CB2 1NS, U.K." a472d59cff9d822f15f326a874e666be09b70cfd,VISUAL LEARNING WITH WEAKLY LABELED VIDEO A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"VISUAL LEARNING WITH WEAKLY LABELED VIDEO A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Kevin Tang May 2015" a493a731dadababb6f2ae0b4b6233d861206345b,Studio2Shop: from studio photo shoots to fashion articles,"Studio2Shop: from studio photo shoots to fashion articles Julia Lasserre1, Katharina Rasch1 and Roland Vollgraf Zalando Research, Muehlenstr. 25, 10243 Berlin, Germany Keywords: omputer vision, deep learning, fashion, item recognition, street-to-shop" a4dd2ff517ae61d7f39ec176915d8da5cafe8323,Lip Processing and Modeling based on Spatial Fuzzy Clustering in Color Images,"International Journal of Fuzzy Systems, Vol. 13, No. 2, June 2011 65 Lip Processing and Modeling based on Spatial Fuzzy Clustering in Color Images R. Rohani, F. Sobhanmanesh, S. Alizadeh, and R. Boostani" a46f285b928aa547df8d8d8d63d2f9256a73aae7,Networked Decision Making for Poisson Processes With Applications to Nuclear Detection,"[16] E. D. Sontag, “Input-to-state stability: Basic concepts and results,” in Nonlinear and Optimal Control Theory, P. Nistri and G. Stefani, Eds. Berlin, Germany: Springer–Verlag, 2006, pp. 163–220. [17] Z.-P. Jiang, A. R. Teel, and L. Praly, “Small-gain theorem for ISS sys- tems and applications,” Mathem. of Control, Signals, and Syst., vol. 7, pp. 95–120, 1994. [18] A. R. Teel, “A nonlinear small gain theorem for the analysis of control systems with saturation,” IEEE Trans. Autom. Control, vol. AC-41, no. 9, pp. 1256–1270, Sep. 1996. [19] Z.-P. Jiang and I. M. Y. Mareels, “A small-gain control method for nonlinear cascaded systems with dynamic uncertainties,” IEEE Trans. Autom. Control, vol. 42, no. 3, pp. 292–308, Mar. 1997. [20] S. Dashkovskiy, Z.-P. Jiang, and B. Rüffer, “Special issue on robust sta- ility and control of large-scale nonlinear systems,” Mathem. of Con- trol, Signals, and Syst., vol. 24, no. 1, pp. 1–2, 2012. [21] H. K. Khalil, Nonlinear Systems, third ed. Upper Saddle River, NJ: Prentice–Hall, 2002. [22] R. A. Horn and C. R. Johnson, Matrix Analysis. Cambridge, U.K.: Cambridge University Press, 1985. [23] W. Ren and R. W. Beard, “Consensus seeking in multiagent systems" a4ee9f089ab9a48a6517a6967281247339a51747,Resembled Generative Adversarial Networks: Two Domains with Similar Attributes,"DUHYEON BANG, HYUNJUNG SHIM: RESEMBLED GAN Resembled Generative Adversarial Networks: Two Domains with Similar Attributes School of Integrated Technology, Yonsei University, South Korea Duhyeon Bang Hyunjung Shim" a42eb9e4c2506640446f07df3a9a0134752b00da,Domain Adaptive Transfer Learning with Specialist Models,"Domain Adaptive Transfer Learning with Specialist Models Jiquan Ngiam, Daiyi Peng, Vijay Vasudevan, Simon Kornblith, Quoc V. Le, Ruoming Pang Google Brain" a46b950e1aa97ab3033d8a21fabb1952fb7eb5ce,Mixtures of boosted classifiers for frontal face detection,"SIViP (2007) 1:29–38 DOI 10.1007/s11760-007-0003-x O R I G I NA L PA P E R Mixtures of boosted classifiers for frontal face detection Julien Meynet · Vlad Popovici · Jean-Philippe Thiran Received: 12 October 2006 / Revised: 12 January 2007 / Accepted: 12 January 2007 / Published online: 3 March 2007 © Springer-Verlag London Limited 2007" a4f345a8a7b3d5933282cb7fa641b2957ca89113,Comparison of focus measures in face detection environments,"+2)415 . .+75 -)574-5 1 .)+- ,-6-+61 -814-65  HA  ,AE  +=IJHE + /KAHH= IJ B 1JAECAJ 5OIJAI KAHE?= )FF E -CEAAHEC 1751)1 7ELAHIEJO B =I 2==I /H= +==HE= +=FKI 7EL 6=H= !#% )I 2==I 5F=E +=FKI 7EL 6=H= !#% )I 2==I 5F=E )>IJH=?J 0K=+FKJAH 1JAH=?JE +FKJAH 8EIE )KJB?KI A=IKHAI 6DEI MH FHAIAJI = ?F=HEI =C B?KI A=IKHAI E JDA EJAH=JKHA BH =KJB?KIEC E =  FHALEKIO =FFE?=JE B B=?A 6DEI =FFE?=JE D=I ?D=H=?JAHEIJE?I J JDIA MDAHA =KJB?KI D=LA >AA EA E?HI?FO H BH B?KI 6DA =E B JDA MH EI J EB JDA >AIJ B?KI A=IKHAI E =FFE?=JEI B =KJB?KI D=LA JDA I=A FAHBH=?A E B=?A =FFE?=JEI 6 JD=J IEN B?KI A=IKHAI D=I >AA E BKH IAJJECI BH JDA J HA HA?AJ AI  B=?A B=?A HA?CEJE AJ = ''"" 4MAO AJ = ''& /HII AJ =  0A=I M  ;=C AJ =  D= AJ = ! F=O = EFHJ=J HA >A?=KIA JDAO JDA B=?E= BA=JKHAI JD=J =FFA=H E JDA B=?A IK?D =I AOAI KJD IA MDE?D =HA" a4c430b7d849a8f23713dc283794d8c1782198b2,Video Concept Embedding,"Video Concept Embedding Anirudh Vemula Rahul Nallamothu Syed Zahir Bokhari . Introduction In the area of natural language processing, there has been much success in learning distributed representations for words as vectors. Doing so has an advantage over using simple labels, or a one-hot coding scheme for representing individual words. In learning distributed vector representa- tions for words, we manage to capture semantic relatedness of words in vector distance. For example, the word vector for ”car” and ”road” should end up being closer together in the vector space representation than ”car” and ”penguin”. This has been very useful in NLP areas of machine transla- tion and semantic understanding. In the computer vision domain, video understanding is a very important topic. It is made hard due to the large mount of high dimensional data in videos. One strategy" a49b661e42aea6f205e543a80106fc9c6ff0f9d4,Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry,"Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry Nan Yang1,2, Rui Wang1,2, J¨org St¨uckler1, and Daniel Cremers1,2 Technical University of Munich Artisense" a422c2bd9030c8a2c89b6db79be2743c4a4609fb,Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure,"Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure Hamed Hakkak1" a44b91f46ba66c8279b93caab6842444de0c9343,Frequency-domain Tracking Spatial-domain Detection Generic Object Proposal Histogram based Representation Detection Result Tracking State Estimation Spatial Regressor Correlation Model IFFT Search Space Feature Extraction Correlation Map Correlation Model FFT,"Monocular Long-term Target Following on UAVs Rui Li ∗ Minjian Pang† Cong Zhao ‡ Guyue Zhou ‡ Lu Fang †§" a432f815d753121267ffb524f8fabac21be32733,Proyecto Aguará : Automatic Face Recognition,"Proyecto Aguar´a: Automatic Face Recognition C. AGUERREBERE, G. CAPDEHOURAT, M. DELBRACIO AND M. MATEU Instituto de Ingenier´ıa El´ectrica, Facultad de Ingenier´ıa, Universidad de la Rep ´ublica, Montevideo, Uruguay We present a biometric system performing both, verification and identification, implementing automatic face recognition. The algorithm is based on Elastic Bunch Graph Matching [1]. EBGM is a technique that uses local information extracted with Gabor filters for discrimination. CSU implementation [2] was used as the main reference of this work. The results are comparable with those of the state of the art." a4bab165158b9627280fb3052b1c731210f2a901,"Pedestrian Localization, Tracking and Behavior Analysis from Multiple Cameras","Pedestrian Localization, Tracking and Behavior Analysis from Multiple Cameras THÈSE NO 4629 (2010) PRÉSENTÉE LE 9 AVRIL 2010 À LA FACULTÉ INFORMATIQUE ET COMMUNICATIONS LABORATOIRE DE VISION PAR ORDINATEUR PROGRAMME DOCTORAL EN INFORMATIQUE, COMMUNICATIONS ET INFORMATION ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES Jérôme BERCLAZ cceptée sur proposition du jury: Prof. P. Thiran, président du jury Prof. P. Fua, Dr F. Fleuret, directeurs de thèse Prof. M. Bierlaire, rapporteur Prof. H. Bischof, rapporteur Dr J. Ferryman, rapporteur Suisse" a48ac2ebade8a0c77c936e45756bccef9668d8e6,Scale-Space Techniques for Fiducial Points Extraction from 3D Faces,"Scale-Space Techniques for Fiducial Points Extraction from 3D Faces Nikolas De Giorgis(B), Luigi Rocca, and Enrico Puppo Department of Informatics, Bio-engineering, Robotics and System Engineering, University of Genova, Via Dodecaneso 35, 16146 Genova, Italy" a427ee25ef515ddd9cf50b4cc3a7376f57d58926,Human-Drone-Interaction: A Case Study to Investigate the Relation Between Autonomy and User Experience,"Human-Drone-Interaction: A Case Study to Investigate the Relation between Autonomy and User Experience Patrick Ferdinand Christ1,3(cid:63), Florian Lachner2,3(cid:63), Axel H¨osl3, Bjoern Menze1, Klaus Diepold3, and Andreas Butz2 Image-based Biomedical Modeling Group, Technical University of Munich (TUM) {patrick.christ, Chair for Human-Computer-Interaction, University of Munich (LMU) {florian.lachner, axel.hoesl, Center for Digital and Technology Management, TUM and LMU Chair for Data Processing, Technical University of Munich (TUM)" a43f460f6c1abbe8eb0097594df6eafc0f651d49,Saliency-based object recognition in video,"Saliency-based object recognition in video Iv´an Gonz´alez-D´ıaz, Hugo Boujut, Vincent Buso, Jenny Benois-Pineau, Jean-Philippe Domenger To cite this version: Iv´an Gonz´alez-D´ıaz, Hugo Boujut, Vincent Buso, Jenny Benois-Pineau, Jean-Philippe Domenger. Saliency-based object recognition in video. 10 pages. 2013. HAL Id: hal-00799127 https://hal.archives-ouvertes.fr/hal-00799127 Submitted on 1 Jan 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires" a47ac8569ab1970740cff9f1643f77e9143a62d4,Associative Compression Networks for Representation Learning,"Associative Compression Networks for Representation Learning Alex Graves 1 Jacob Menick 1 A¨aron van den Oord 1" a47e51dd3f73817679ff0e987a0064d43db25060,Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization,"Visual Explanations from Deep Networks via Gradient-based Localization Grad-CAM: Why did you say that? Ramprasaath R. Selvaraju Abhishek Das Devi Parikh Ramakrishna Vedantam Dhruv Batra Virginia Tech Michael Cogswell {ram21, abhshkdz, vrama91, cogswell, parikh, (a) Original Image (b) Guided Backprop ‘Cat’ (c) Grad-CAM for ‘Cat’ (d) Guided Grad-CAM ‘Cat’ (e) Occlusion Map ‘Cat’ (f) ResNet Grad-CAM ‘Cat’ (g) Original Image (h) Guided Backprop ‘Dog’ (i) Grad-CAM for ‘Dog’ (l) ResNet Grad-CAM ‘Dog’" a4a0b5f08198f6d7ea2d1e81bd97fea21afe3fc3,cient Recurrent Residual Networks Improved by Feature Transfer MSc Thesis,"Ecient Recurrent Residual Networks Improved by Feature Transfer MSc Thesis written by Yue Liu under the supervision of Dr. Silvia-Laura Pintea, Dr. Jan van Gemert, nd Dr. Ildiko Suveg and submitted to the Board of Examiners for the degree of Master of Science t the Delft University of Technology. Date of the public defense: Members of the Thesis Committee: August 31, 2017 Prof. Marcel Reinders Dr. Jan van Gemert Dr. Julian Urbano Merino Dr. Silvia-Laura Pintea Dr. Ildiko Suveg (Bosch) Dr. Gonzalez Adrlana (Bosch)" a4f37cfdde3af723336205b361aefc9eca688f5c,Recent Advances in Face Recognition,"Recent Advances in Face Recognition" a4ce0f8cfa7d9aa343cb30b0792bb379e20ef41b,Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning,"Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning Lingbo Liu, Guanbin Li, Yuan Xie, Yizhou Yu, Qing Wang and Liang Lin" a45450824c6e8e6b42fd9bbf52871104b6c6ce8b,Optimizing the Latent Space of Generative Networks,"Optimizing the Latent Space of Generative Networks Piotr Bojanowski, Armand Joulin, David Lopez-Paz, Arthur Szlam {bojanowski, ajoulin, dlp, Facebook AI Research" a49acd70550c209965a6d39d7ff92d11f0a5b1b6,"YouTube Scale, Large Vocabulary Video Annotation","YouTube Scale, Large Vocabulary Video Annotation Nicholas Morsillo, Gideon Mann and Christopher Pal" a4a90a2db209db2d5c49adfd2091ede2d4130f60,Interactive Grounded Language Acquisition and Generalization in a 2D World,"Published as a conference paper at ICLR 2018 INTERACTIVE GROUNDED LANGUAGE ACQUISITION AND GENERALIZATION IN A 2D WORLD Haonan Yu1, Haichao Zhang1 & Wei Xu1,2 Baidu Research, Sunnyvale USA National Engineering Laboratory for Deep Learning Technology and Applications, Beijing China" a40f8881a36bc01f3ae356b3e57eac84e989eef0,"End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks","End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks Umut Güçlü*, 1, Yağmur Güçlütürk*, 1, Meysam Madadi2, Sergio Escalera3, Xavier Baró4, Jordi González2, Rob van Lier1, Marcel van Gerven1" a40f614499dab76b477ca5bbb4614d6f1a5c8b4b,Highly Efficient Compact Pose SLAM with SLAM++,"Highly Efficient Compact Pose SLAM with SLAM++1 Viorela Ila, Lukas Polok, Marek Solony and Pavel Svoboda" a416513aaf97060287bf3e64ccdc1ccf85106c07,Seasonal Separation of African Savanna Components Using Worldview-2 Imagery: A Comparison of Pixel- and Object-Based Approaches and Selected Classification Algorithms,"Article Seasonal Separation of African Savanna Components Using Worldview-2 Imagery: A Comparison of Pixel- nd Object-Based Approaches and Selected Classification Algorithms ˙Zaneta Kaszta 1,2,*, Ruben Van De Kerchove 1,3, Abel Ramoelo 4, Moses Azong Cho 4, Sabelo Madonsela 4, Renaud Mathieu 4,5 and Eléonore Wolff 1 Institut de Gestion de l’Environnement et d’Aménagement de Territoire (IGEAT), Université Libre de Bruxelles, Brussels 1050, Belgium; School of Applied Environmental Sciences, Pietermaritzburg 3209, South Africa Mol 2400, Belgium; Council for Scientific and Industrial Research, Pretoria 0001, South Africa; (A.R.); (M.A.C.); (S.M.); (R.M.) 5 Department of Geography, Geoinformatics and Meteorology, University of Pretoria, Pretoria 0028, South Africa * Correspondence: Tel.: +32-02-650-68-20 Academic Editors: Giles M. Foody, Magaly Koch, Clement Atzberger and Prasad S. Thenkabail Received: 15 May 2016; Accepted: 8 September 2016; Published: 16 September 2016" a453863082a7fb42c9b402023294390eb4167fbe,Identifying Where to Focus in Reading Comprehension for Neural Question Generation,"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2067–2073 Copenhagen, Denmark, September 7–11, 2017. c(cid:13)2017 Association for Computational Linguistics" a4f38e32c23fd1f5a1e1157a4e62b38731f2e5d8,Online Learning for Ship Detection in Maritime Surveillance,"Online Learning for Ship Detection in Maritime Surveillance Rob Wijnhoven1 ViNotion1 , Kris van Rens1, Egbert G. T. Jaspers1, Peter H. N. de With2 University of Technol. Eindhoven2 CycloMedia Technol.3 P.O. Box 2346 5600 CH Eindhoven The Netherlands P.O. Box 513 5600 MB Eindhoven The Netherlands" a481de6e9a7303784a7492ede7a7f055be7bc831,Egocentric Audio-Visual Scene Analysis. A Machine Learning and Signal Processing Approach. (Analyse Égocentrique de Scènes Audio-Visuelles. Une approche par Apprentissage Automatique et Traitement du Signal),"Egocentric Audio-Visual Scene Analysis : a machine learning and signal processing approach Xavier Alameda-Pineda To cite this version: Xavier Alameda-Pineda. Egocentric Audio-Visual Scene Analysis : a machine learning and signal pro- essing approach. General Mathematics [math.GM]. Université de Grenoble, 2013. English. . HAL Id: tel-00880117 https://tel.archives-ouvertes.fr/tel-00880117v2 Submitted on 31 Mar 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" bc749f0e81eafe9e32d56336750782f45d82609d,Combination of Texture and Geometric Features for Age Estimation in Face Images, bc8373b3d4110786a597b21f3ae9c8e5ffd34a2e,Optimal Gabor kernel location selection for face recognition,"OPTIMAL GABOR KERNEL LOCATION SELECTION FOR FACE RECOGNITION B. G¨okberk, M. O. Irfanoglu, L. Akarun, and E. Alpaydın Bo˘gazic¸i University, Computer Engineering Dept. {gokberk,irfanogl,akarun, Istanbul, TURKEY" bc9af4c2c22a82d2c84ef7c7fcc69073c19b30ab,MoCoGAN: Decomposing Motion and Content for Video Generation,"MoCoGAN: Decomposing Motion and Content for Video Generation Sergey Tulyakov, Snap Research Ming-Yu Liu, Xiaodong Yang, NVIDIA Jan Kautz" bcac3a870501c5510df80c2a5631f371f2f6f74a,Structured Face Hallucination,"#1387 CVPR 2013 Submission #1387. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. #1387 Structured Face Hallucination Anonymous CVPR submission Paper ID 1387" bc995457cf5f4b2b5ef62106856571588d7d70f2,Comparison of Maximum Likelihood and GAN-based training of Real NVPs,"Comparison of Maximum Likelihood and GAN-based training of Real NVPs Ivo Danihelka 1 2 Balaji Lakshminarayanan 1 Benigno Uria 1 Daan Wierstra 1 Peter Dayan 3" bcaa5fab589d95890d539a3119657fa253176f0d,"THE PROBLEM : MID-RANGE FR AT NIGHT No Active Illumination Night Time 120 meters Evaluating the Efficiency of a Night-Time , Middle-Range Infrared Sensor for Applications in Human Detection and Recognition","THE PROBLEM: MID-RANGE FR AT NIGHT No Active Illumination NIR Led Illuminator Night Time 120 meters eters Infrared Imaging Systems: Design, Analysis, Modeling, and Testing XXIII, edited by Gerald C. Holst, Keith A. Krapels, Proc. of SPIE Vol. 8355, 83551B · © 2012 SPIE · CCC code: 0277-786X/12/$18 · doi: 10.1117/12.917831 Proc. of SPIE Vol. 8355 83551B-1 From: http://proceedings.spiedigitallibrary.org/ on 04/30/2013 Terms of Use: http://spiedl.org/terms" bcf73131c2be397fa2105ac45df3ce1a55c07c2f,Automated markerless extraction of walking people using deformable contour models,"This is a preprint of an article published in Computer Animation and Virtual Worlds, 15(3-4):399-406, 2004. This journal may be found at: http://www.interscience.wiley.com" bc1fa3efa43dfb79f6f8243d29327c8ee06e8a97,No 275 Learning object classes with generic knowledge,"ETH Zurich, D-ITET, BIWI Technical Report No 275 Learning object classes with generic knowledge Thomas Deselaers, Bogdan Alexe, and Vittorio Ferrari" bca09d92a25e5cc96df5c8d2eb87e2854cdc02b1,Pose Invariant 3 D Face Authentication based on Gaussian Fields Approach,"To the Graduate Council: I am submitting herewith a thesis written by Venkat Rao Ayyagari entitled “Pose Invariant 3D Face Authentication based on Gaussian Fields Approach”. I have examined the final electronic copy of this thesis for form and content and recommend that it be ccepted in partial fulfillment of the requirements for the degree of Master of Science, with a major in Electrical Engineering. Mongi A. Abidi Major Professor We have read this thesis and recommend its acceptance: Andreas Koschan Seong G. Kong Accepted for the Council: Anne Mayhew Vice Chancellor and Dean of Graduate Studies (Original signatures are on file with official student records.)" bc7f431c4c5cecfc7bf95b2f0704d81469f23580,AN INTELLIGENT APPAREL RECOMMENDATION SYSTEM FOR ONLINE SHOPPING USING STYLE CLASSIFICATION,"I J A B E R, Vol. 13, No. 2, (2015): 671-686 AN INTELLIGENT APPAREL RECOMMENDATION SYSTEM FOR ONLINE SHOPPING USING STYLE CLASSIFICATION C. Perkinian* and P. Vikkraman**" bcf7fb98ab0137d8a8b8a952819f5e13ec4648aa,FACE RECOGNITION WITH SINGLE SAMPLE PER CLASS USING CS-LBP AND GABOR FILTER 1,"Journal of Theoretical and Applied Information Technology 31st October 2014. Vol. 68 No.3 © 2005 - 2014 JATIT & LLS. All rights reserved. ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 FACE RECOGNITION WITH SINGLE SAMPLE PER CLASS USING CS-LBP AND GABOR FILTER A.USHA RUBY, DR.J.GEORGE CHELLIN CHANDRAN Research Scholar, Department of CSE, Bharath University Principal, CSI College of Engineering, Ketti E-mail: ," bc843c35530e38396e8ba55b8891dbe8324054a8,Group Visual Sentiment Analysis,"Group Visual Sentiment Analysis Zeshan Hussain, Tariq Patanam and Hardie Cate June 6, 2016" bc4537bc5834b41a631d9a807500d199b438fb27,Perceptual Integration Deficits in Autism Spectrum Disorders Are Associated with Reduced Interhemispheric Gamma-Band Coherence.,"6352 • The Journal of Neuroscience, December 16, 2015 • 35(50):16352–16361 Neurobiology of Disease Perceptual Integration Deficits in Autism Spectrum Disorders Are Associated with Reduced Interhemispheric Gamma-Band Coherence Ina Peiker,1* Nicole David,1* X Till R. Schneider,1 Guido Nolte,1 Daniel Scho¨ttle,2 and XAndreas K. Engel1 Departments of 1Neurophysiology and Pathophysiology and 2Psychiatry and Psychotherapy, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany The integration of visual details into a holistic percept is essential for object recognition. This integration has been reported as a key deficit in patients with autism spectrum disorders (ASDs). The weak central coherence account posits an altered disposition to integrate features into a coherent whole in ASD. Here, we test the hypothesis that such weak perceptual coherence may be reflected in weak neural coherence cross different cortical sites. We recorded magnetoencephalography from 20 adult human participants with ASD and 20 matched ontrols, who performed a slit-viewing paradigm, in which objects gradually passed behind a vertical or horizontal slit so that only fragments of the object were visible at any given moment. Object recognition thus required perceptual integration over time and, in case of the horizontal slit, also across visual hemifields. ASD participants were selectively impaired in the horizontal slit condition, indicating specific difficulties in long-range synchronization between the hemispheres. Specifically, the ASD group failed to show condition-related enhancement of imaginary coherence between the posterior superior temporal sulci in both hemispheres during horizontal slit-viewing in contrast to controls. Moreover, local synchronization reflected in occipitocerebellar beta-band power was selectively reduced for horizontal compared with vertical slit-viewing in ASD. Furthermore, we found disturbed connectivity between right posterior superior temporal sulcus and left cerebellum. Together, our results suggest that perceptual integration deficits co-occur with specific patterns of" bcc172a1051be261afacdd5313619881cbe0f676,A fast face clustering method for indexing applications on mobile phones,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" bc4627e1bc3bbe21c46c4011ec4f9bd377ec83a4,Towards recognition of degraded words by probabilistic parsing,"Towards Recognition of Degraded Words by Probabilistic Parsing Karthika Mohan IIIT, Hyderabad AP, India 500 032 K. J. Jinesh IIIT, Hyderabad AP, India 500 032 C. V. Jawahar IIIT, Hyderabad AP, India 500 032" bca52740ba679b67a508894e68a0e52f6bf62079,Development of an Efficient Face Recognition System Based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" bc4e86b6d2d386805466b822a04ea0c015debfff,Robust 3D Face Recognition from Expression Categorisation,"Cook, Jamie A and Cox, Mark and Chandran, Vinod and Sridharan, Sridha (2007) Robust 3D Face Recognition from Expression Categorisation. In Proceedings International Conference on Biometrics 642, pages pp. 271-280, Seoul, Korea. This is the author-manuscript version of this work - accessed from http://eprints.qut.edu.au Copyright 2007 Springer" bc15e0ebe7ff84e090aa2d74d753d87906d497f7,The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments,"The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments Luiz A. Zanlorensi∗, Eduardo Luz†, Rayson Laroca∗, Alceu S. Britto Jr.‡, Luiz S. Oliveira∗, David Menotti∗ Department of Informatics, Federal University of Paran´a (UFPR), Curitiba, PR, Brazil Computing Department, Federal University of Ouro Preto (UFOP), Ouro Preto, MG, Brazil Postgraduate Program in Informatics, Pontifical Catholic University of Paran´a (PUCPR), Curitiba, PR, Brazil" bcee40c25e8819955263b89a433c735f82755a03,Biologically Inspired Vision for Human-Robot Interaction,"Biologically inspired vision for human-robot interaction M. Saleiro, M. Farrajota, K. Terzi´c, S. Krishna, J.M.F. Rodrigues, and J.M.H. du Buf Vision Laboratory, LARSyS, University of the Algarve, 8005-139 Faro, Portugal, {masaleiro, mafarrajota, kterzic, jrodrig," bcf52629788e210f9c87945fa9cf792609e9154a,Ð ×ýñññøöý Éùùòøø¬¬¬øøóò Óö Üôöö×××óò Áòúöööòø Àùññò Áááòøø¬¬¬øøóò £,"Facia Ayey ai(cid:12)cai f Exei vaia a dei(cid:12)cai Y. i .ed  .. Schid ad .F. Ch Deae f ychgy Uiveiy f ib gh Caegie e Uiveiy The Rbic i e R.. Weave Saiic De Caegie e Uiveiy ib gh A 15213 ib gh A 15260 ib gh A 15213" bc8bd3f5653165809af3d4525f266219add4d132,Symbolic principal component for interval-valued observations, bc40057335e589c30e0b6c7b71685ef0433b5af5,"Recounting ( MER ) , Surveillance Event Detection ( SED ) , and Semantic Indexing ( SIN ) Systems","IBM Research and Columbia University TRECVID-2013 Multimedia Event Detection (MED), Multimedia Event Recounting (MER), Surveillance Event Detection (SED), and Semantic Indexing (SIN) Systems Lisa Browny, Liangliang Caoy, Shih-Fu Chang(cid:3), Yu Chengy, Alok Choudharyy, Noel Codellay, Courtenay Cotton(cid:3), Dan Ellis,(cid:3) Quanfu Fany, Rogerio Ferisy, Leiguang Gongy, Matthew Hilly, Gang Huay, John Kenderz, Michele Merlery, Yadong Mu(cid:3), Sharath Pankantiy, John R. Smithy, Felix X. Yu(cid:3)x" bc8e1c2284008319ee325ff7ea19916726235f55,Autonomic responses to social and nonsocial pictures in adolescents with autism spectrum disorder.,"RESEARCH ARTICLE Autonomic Responses to Social and Nonsocial Pictures in Adolescents With Autism Spectrum Disorder Anneke Louwerse, Joke H. M. Tulen, Jos N. van der Geest, Jan van der Ende, Frank C. Verhulst, and Kirstin Greaves-Lord It remains unclear why individuals with autism spectrum disorder (ASD) tend to respond in an atypical manner in social situations. Investigating autonomic and subjective responses to social vs. nonsocial stimuli may help to reveal underlying mechanisms of these atypical responses. This study examined autonomic responses (skin conductance level and heart rate) and subjective responses to social vs. nonsocial pictures in 37 adolescents with an ASD and 36 typically developing (TD) adolescents. Thirty-six pictures from the International Affective Picture System were presented, divided into six ategories based on social content (social vs. nonsocial) and pleasantness (pleasant, neutral, and unpleasant). Both in dolescents with ASD as well as TD adolescents, pictures with a social content resulted in higher skin conductance responses (SCRs) for pleasant and unpleasant pictures than for neutral pictures. No differences in SCRs were found for the three nonsocial picture categories. Unpleasant pictures, both with and without a social content, showed more heart rate deceleration than neutral pictures. Self-reported arousal ratings were influenced by the social and affective content of a picture. No differences were found between individuals with ASD and TD individuals in their autonomic and subjective responses to the picture categories. These results suggest that adolescents with ASD do not show atypical utonomic or subjective responses to pictures with and without a social content. These findings make it less likely that impairments in social information processing in individuals with ASD can be explained by atypical autonomic responses to social stimuli. Autism Res 2013, (cid:129)(cid:129): (cid:129)(cid:129)–(cid:129)(cid:129). © 2013 International Society for Autism Research, Wiley Periodicals, Inc." bcd299eb32f17b531fa281cb750a89895cb4feb5,Computer Vision Research at the Computational Vision Laboratory of the Universidad de Chile,"Computer Vision Research at the Computational Vision Laboratory of the Universidad de Chile Javier Ruiz-del-Solar Department of Electrical Engineering, Universidad de Chile" 8a866bc0d925dfd8bb10769b8b87d7d0ff01774d,WikiArt Emotions: An Annotated Dataset of Emotions Evoked by Art,"WikiArt Emotions: An Annotated Dataset of Emotions Evoked by Art Saif M. Mohammad and Svetlana Kiritchenko National Research Council Canada" 8a12ee3c98b76d99531d5965f15bb77a10ec2569,Holistic Face Recognition through Multivariate Analysis and Genetic Algorithms,"Holistic Face Recognition through Multivariate Analysis and Genetic Algorithms" 8acb55a72c4d6eae528a99e571b4a24d51f57fe6,Toward Crowd-Sensitive Path Planning,"Toward Crowd-Sensitive Path Planning Anoop Aroor1 and Susan L. Epstein1,2 The Graduate Center1 and Hunter College2 of The City University of New York New York, NY 10065" 8abfda3c1e1599bed454661f15ee0bbe7f6b8c12,Who is Mistaken?,"Who is Mistaken? Benjamin Eysenbach Carl Vondrick Antonio Torralba" 8a02a0517b841b53fba478a851948b86869a0582,Fast Neural Networks with Circulant Projections,"Fast Neural Networks with Circulant Projections Yu Cheng∗, Felix X. Yu∗, Rogerio S. Feris, Sanjiv Kumar, Alok Choudhary, Shih-Fu Chang" 8a05d0a98570be20bccd106602f3e981d9b05334,A Unified Framework for Manifold Landmarking,"A unified framework for manifold landmarking Hongteng Xu, Licheng Yu, Mark A. Davenport, Senior Member, IEEE, Hongyuan Zha" 8a4119c2898f611a6ffa0b4b72acf322d1b455b1,A Diagram Is Worth A Dozen Images,"A Diagram Is Worth A Dozen Images Aniruddha Kembhavi†, Mike Salvato†(cid:63), Eric Kolve†(cid:63), Minjoon Seo§, Hannaneh Hajishirzi§, Ali Farhadi†§ Allen Institute for Artificial Intelligence, §University of Washington" 8ad4742e656c409e5a813c1a6d5f21fd2e3a9225,A Novel Algorithm for Face Recognition From Very Low Resolution Images,"J Electr Eng Technol Vol. 10, No. ?: 742-?, 2015 http://dx.doi.org/10.5370/JEET.2015.10.1.742 ISSN(Print) 1975-0102 ISSN(Online) 2093-7423 A Novel Algorithm for Face Recognition From Very Low Resolution Images C. Senthilsingh† and M. Manikandan*" 8aed6ec62cfccb4dba0c19ee000e6334ec585d70,Localizing and Visualizing Relative Attributes,"Localizing and Visualizing Relative Attributes Fanyi Xiao and Yong Jae Lee" 8ae02cef563120be51f8655e199a54af856059b7,Three-Dimensional Anthropometric Database of Attractive Caucasian Women: Standards and Comparisons,"SCIENTIFIC FOUNDATION Three-Dimensional Anthropometric Database of Attractive Caucasian Women: Standards nd Comparisons Luigi Maria Galantucci, PhD, MSE, Alberto Laino, PhD, DS, Eliana Di Gioia, DS, MD,§jj Raoul D’Alessio, DS, MD,ô Fulvio Lavecchia, PhD, MSE,# Roberto Deli, PhD, DS, Gianluca Percoco, PhD, MSE,# and Carmela Savastano, DS, MD" 8aa6c3601924c99ca420c7c37ffcffe00db1eb78,3D facial expression recognition via multiple kernel learning of Multi-Scale Local Normal Patterns,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-0-9 ©2012 ICPR" 8ab2bc0f298cf595d50064a5bce57065d5b69c59,Development of Multimedia Application for Smartphones,"International Journal of Computer Applications (0975 – 8887) Volume 95 – No 2, June 2014 Development of Multimedia Application for Smartphones M. A. Mohamed Assoc. Prof. Mansoura University Mansoura Egypt A. I. Abdel-Fatah Prof. Mansoura University Mansoura Egypt Bassant M. El-Den Demonstrator Delta University Mansoura Egypt" 8a14dfe0e11e03505db9c0d84bce96f165223cae,Learning from Demonstration in the Wild,"Learning from Demonstration in the Wild Feryal Behbahani1, Kyriacos Shiarlis1, Xi Chen1, Vitaly Kurin1,2, Sudhanshu Kasewa1,2, Ciprian Stirbu1,2, Jo˜ao Gomes1, Supratik Paul1,2, Frans A. Oliehoek1,3, Jo˜ao Messias1, Shimon Whiteson1,2" 8ac2736683dac9a467602ee19f5a290096259148,HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection,"HyperNet: Towards Accurate Region Proposal Generation nd Joint Object Detection Tao Kong1 Anbang Yao2 Yurong Chen2 Fuchun Sun1 State Key Lab. of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology (TNList) Department of Computer Science and Technology, Tsinghua University 2Intel Labs China {anbang.yao," 8aae23847e1beb4a6d51881750ce36822ca7ed0b,Comparison between geometry-based and Gabor-wavelets-based facial expression recognition using multi-layer perceptron,"Comparison Between Geometry-Based and Gabor-Wavelets-Based Facial Expression Recognition Using Multi-Layer Perceptron Zhengyou Zhang Shigeru Akamatsu  Michael Lyons Michael Schuster ATR Human Information Processing Research Laboratories  ATR Interpreting Telecommunications Research Laboratories -2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan INRIA, 2004 route des Lucioles, BP 93, F-06902 Sophia-Antipolis Cedex, France e-mail:" 8ac074829b55bb6b4c67f062ca9ec62bb79f865f,Person re-identification based on deep multi-instance learning,"Person Re-identification based on Deep Multi-instance Learning Domonkos Varga∗†, Tam´as Szir´anyi∗‡ MTA SZTAKI, Institute for Computer Science and Control {varga.domonkos, Budapest University of Technology and Economics, Department of Networked Systems and Services Budapest University of Technology and Economics, Department of Material Handling and Logistics Systems" 8a91cb96dd520ba3e1f883aa6d57d4d716c5d1c8,Low Cost Eye Tracking: The Current Panorama,"Hindawi Publishing Corporation Computational Intelligence and Neuroscience Volume 2016, Article ID 8680541, 14 pages http://dx.doi.org/10.1155/2016/8680541 Review Article Low Cost Eye Tracking: The Current Panorama Onur Ferhat1,2 and Fernando Vilariño1,2 Computer Vision Center, Edifici O, Campus UAB, 08193 Bellaterra, Spain Computer Science Department, Universitat Aut`onoma de Barcelona, Edifici Q, Campus UAB, 08193 Bellaterra, Spain Correspondence should be addressed to Onur Ferhat; Received 27 November 2015; Accepted 18 February 2016 Academic Editor: Ying Wei Copyright © 2016 O. Ferhat and F. Vilari˜no. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly ited. Despite the availability of accurate, commercial gaze tracker devices working with infrared (IR) technology, visible light gaze tracking constitutes an interesting alternative by allowing scalability and removing hardware requirements. Over the last years, this field has seen examples of research showing performance comparable to the IR alternatives. In this work, we survey the previous work on remote, visible light gaze trackers and analyze the explored techniques from various perspectives such as calibration strategies, head pose invariance, and gaze estimation techniques. We also provide information on related aspects of research such" 8ab16c26678245ef009cbbf87d750cfd18e21572,A Wearable Ultrasonic Obstacle Sensor for Aiding Visually Impaired and Blind Individuals,"A Wearable Ultrasonic Obstacle Sensor for Aiding Visually Impaired and Blind Individuals {tag} {/tag} IJCA Proceedings on National Conference on Growth of Technologies in Electronics, Telecom and Computers - India Perception © 2014 by IJCA Journal GTETC-IP Year of Publication: 2014 Authors: V. Diana Earshia S. M. Kalaivanan Angel Dayana {bibtex}gtetc1314.bib{/bibtex}" 8aaa97c686c60f611fe5a979d9afbc29dde3d33f,Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent,"Published as a conference paper at ICLR 2018 MASTERING THE DUNGEON: GROUNDED LANGUAGE LEARNING BY MECHANICAL TURKER DESCENT Zhilin Yang, Saizheng Zhang, Jack Urbanek, Will Feng, Alexander H. Miller Arthur Szlam, Douwe Kiela & Jason Weston Facebook AI Research" 8afe84f915d3dbc45c57011e62f5dbf9003dfb4c,Adaptive Binary Quantization for Fast Nearest Neighbor Search,"Adaptive Binary Quantization for Fast Nearest Neighbor Search Zhujin Li1 and Xianglong Liu∗2 and Junjie Wu3 and Hao Su4" 8aac66d15e0903257ec3abe6f126bf6316779011,Constructive Autoassociative Neural Network for Facial Recognition,"RESEARCH ARTICLE Constructive Autoassociative Neural Network for Facial Recognition Bruno J. T. Fernandes1*, George D. C. Cavalcanti2, Tsang I. Ren2 . Escola Polite´ cnica, Universidade de Pernambuco, Recife-PE, Brazil, 2. Centro de Informa´ tica, Universidade Federal de Pernambuco, Recife-PE, Brazil" 8aea75940c90fac8c1e5d7ece7d04a61555c3bf6,Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN, 8ae470fba004309d3dd107fb201940324f400654,Finding and Archiving the Internet Footprint ∗,"Finding and Archiving the Internet Footprint∗ Simson Garfinkel† and David Cox Naval Postgraduate School Monterey, CA, USA February 10, 2009" 8ad407142de84b66144029845587c77ae94fd240,Multi-class speed-density relationship for pedestrian traffic,"Multi-class speed-density relationship for pedestrian traffic Marija Nikoli´c ∗ Matthieu de Lapparent ∗ Michel Bierlaire ∗ Riccardo Scarinci ∗ January 15, 2017 Report TRANSP-OR 170115 Transport and Mobility Laboratory School of Architecture, Civil and Environmental Engineering Ecole Polytechnique Fédérale de Lausanne transp-or.epfl.ch Transport and Mobility Laboratory, School of Architecture, Civil and Environmental Engi- neering, École Polytechnique Fédérale de Lausanne, Switzerland, {marija.nikolic, michel.bierlaire, matthieu.delapparent," 8a29378973987bdb040f35349d1c5a86a538c0fc,Hierarchical Temporal Memory Using Memristor Networks: A Survey,"Hierarchical Temporal Memory using Memristor Networks: A Survey Olga Krestinskaya, Graduate Student Member, IEEE, Irina Dolzhikova, Graduate Student Member, IEEE, and Alex Pappachen James, Senior Member, IEEE" 8aa5f1b2639da73c2579ea9037a4ebf4579fdc4f,A Steerable multitouch Display for Surface Computing and its Evaluation,"December S0218213013600166 013 14:51 WSPC/INSTRUCTION st Reading International Journal on Artificial Intelligence Tools Vol. 22, No. 6 (2013) 1360016 (29 pages) (cid:13) World Scientific Publishing Company DOI: 10.1142/S0218213013600166 A STEERABLE MULTITOUCH DISPLAY FOR SURFACE COMPUTING AND ITS EVALUATION PANAGIOTIS KOUTLEMANIS, ANTONIOS NTELIDAKIS, XENOPHON ZABULIS, DIMITRIS GRAMMENOS and ILIA ADAMI Foundation for Research and Technology – Hellas (FORTH ) Institute of Computer Science, N. Plastira 100 Vassilika Vouton, GR-700 13 Heraklion, Crete, Greece {koutle, ntelidak, zabulis, grammenos, Received 28 January 2013 Accepted 19 March 2013 Published 20 December 2013 In this paper, a steerable, interactive projection display that has the shape of a disk is" 8a48904820b6cfffe8bd951877a3e6e0d5dd6eaa,Dynamic machine learning for supervised and unsupervised classification. (Apprentissage automatique dynamique pour la classification supervisée et non supervisée),"Dynamic machine learning for supervised and unsupervised classification Adela-Maria Sîrbu To cite this version: Adela-Maria Sîrbu. Dynamic machine learning for supervised and unsupervised classification. Machine Learning [cs.LG]. INSA de Rouen, 2016. English. . HAL Id: tel-01402052 https://tel.archives-ouvertes.fr/tel-01402052 Submitted on 24 Nov 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 8af0854c652c90d4004e1868bc5fafec3e4ce724,Etiquetage du comportement de descripteurs locaux pour une recherche sélective de contenus vidéo,"INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE Labelling the Behaviour of Local Descriptors for Selective Video Content Retrieval Julien Law-To — Valerie Gouet-Brunet — Olivier Buisson — Nozha Boujemaa N° 5821 January 2006 Thème COG p p o r t (cid:13) (cid:13) d e r e c h e r c h e (cid:13)" 8a158fb9380a6666b922bc7a00121b6bf4a5ab0b,UnDEMoN 2.0: Improved Depth and Ego Motion Estimation through Deep Image Sampling,"UnDEMoN 2.0: Improved Depth and Ego Motion Estimation through Deep Image Sampling Madhu Babu V, Swagat Kumar, Anima Majumder and Kaushik Das TATA Consultancy Services, Bangalore, India. Technical Report November 28, 2018 (madhu.vankadari, swagat.kumar, anima.majumder," 8a382f000f98cdab7f7b79e543c75c6b8f93b6f9,Learning Semantic Image Representations at a Large Scale,"Learning Semantic Image Representations at a Large Scale Yangqing Jia Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2014-93 http://www.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-93.html May 16, 2014" 8a7726e58c2e24b0a738b48ae35185aaaacb8fe9,PILOT ASSESSMENT OF NONVERBAL PRAGMATIC ABILITY IN PEOPLE WITH ASPERGER SYNDROME,"Psychology of Language and Communication 2013, Vol. 17, No. 3 DOI: 10.2478/plc-2013-0018 FRANCISCO J. RODRÍGUEZ MUÑOZ University of Almería PILOT ASSESSMENT OF NONVERBAL PRAGMATIC ABILITY IN PEOPLE WITH ASPERGER SYNDROME The purpose of this study is to present a diagnostic tool to assess the nonverbal pragmatic ehaviors of people with Asperger syndrome, with the intent to give an account of the severity of symptoms in the area of nonverbal interaction, as well as providing a profile of nonverbal behaviors that may be targeted for intervention. Through this communica- tion profile, overall nonverbal ability is calculated in a group of 20 subjects with Asperger syndrome. The proposed scale also includes the measurement of the following nonverbal dimensions: (1) eye gaze, (2) facial expression, (3) body language and posture, (4) proxemics, (5) gestures, and (6) paralanguage. The results of this assessment suggest low nonverbal pragmatic ability in these subjects, show specific deficits in nonverbal communication, and apture variability in nonverbal behavior in individuals with AS. Key words: Asperger syndrome, autism spectrum disorders, communication profile, non- verbal communication, pragmatic assessment, speech-language pathology Introduction Nobody can deny that nonverbal behavior, understood as a communication" 8acdc4be8274e5d189fb67b841c25debf5223840,Improving clustering performance using independent component analysis and unsupervised feature learning,"Gultepe and Makrehchi Hum. Cent. Comput. Inf. Sci. (2018) 8:25 https://doi.org/10.1186/s13673-018-0148-3 RESEARCH Improving clustering performance using independent component analysis nd unsupervised feature learning Open Access Eren Gultepe* and Masoud Makrehchi *Correspondence: Department of Electrical nd Computer Engineering, University of Ontario Institute of Technology, 2000 Simcoe St N, Oshawa, ON L1H 7K4, Canada" 8aa41170a9591ff2e5e56ed218d955a4222101b8,Towards Accurate Task Accomplishment with Low-Cost Robotic Arms,"Towards Accurate Task Accomplishment with Low-Cost Robotic Arms Yiming Zuo1∗, Weichao Qiu2, Lingxi Xie2, Fangwei Zhong3, Yizhou Wang3, Alan L. Yuille2 Tsinghua University 2The Johns Hopkins University 3Peking University" 8a56adc9605a894c513537f1a2c8d9459573c0a8,EFFECT OF IDENTITY ON TRUST LEARNING,"This is an author produced version of Incidental learning of trust from eye-gaze: Effects of race and facial trustworthiness. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/119885/ Article: Strachan, James, Kirkham, Alexander James orcid.org/0000-0001-9286-9448, Manssuer, Luis et al. (2 more authors) (2017) Incidental learning of trust from eye-gaze: Effects of race and facial trustworthiness. VISUAL COGNITION. pp. 1-13. ISSN 1350-6285 https://doi.org/10.1080/13506285.2017.1338321 promoting access to White Rose research papers http://eprints.whiterose.ac.uk/" 8a336e9a4c42384d4c505c53fb8628a040f2468e,Detecting Visually Observable Disease Symptoms from Faces,"Wang and Luo EURASIP Journal on Bioinformatics nd Systems Biology (2016) 2016:13 DOI 10.1186/s13637-016-0048-7 R ES EAR CH Detecting Visually Observable Disease Symptoms from Faces Kuan Wang* and Jiebo Luo Open Access" 6d2b633743178bd5aac1073b60d81ceb41933a4a,Carried Object Detection Based on an Ensemble of Contour Exemplars,"Carried Object Detection based on an Ensemble of Contour Exemplars Farnoosh Ghadiri1, Robert Bergevin1, Guillaume-Alexandre Bilodeau2 LVSN-REPARTI, Universit(cid:19)e Laval LITIV lab., Polytechnique Montr(cid:19)eal" 6dc17e91c0b02ff3b9e5c9283924279c28641db7,A Methodology for Extracting Standing Human Bodies from Single Images,"Invention Journal of Research Technology in Engineering & Management (IJRTEM) ISSN: 2455-3689 www.ijrtem.com ǁ Volume 1 ǁ Issue 8 ǁ A Methodology for Extracting Standing Human Bodies from Single Images Dr. Y. Raghavender Rao1, N. Devadas Naik2 Head ECE JNTUHCEJ Jagtityal Asst professor Sri Chaitanya engineering college" 6dd5dbb6735846b214be72983e323726ef77c7a9,A Survey on Newer Prospective Biometric Authentication Modalities,"Josai Mathematical Monographs vol. 7 (2014), pp. 25-40 A Survey on Newer Prospective Biometric Authentication Modalities Narishige Abe, Takashi Shinzaki" 6d7ba173121edd5defadfde04f7c1e7bc72859c2,The study of autism as a distributed disorder.,"MENTAL RETARDATION AND DEVELOPMENTAL DISABILITIES RESEARCH REVIEWS 13: 85 – 95 (2007) THE STUDY OF AUTISM AS A DISTRIBUTED DISORDER Brain Development Imaging Laboratory, Department of Psychology, San Diego State University, San Diego, California Department of Cognitive Science, University of California, San Diego, California Ralph-Axel Mu¨ ller1,2* Past autism research has often been dedicated to tracing the auses of the disorder to a localized neurological abnormality, a single functional network, or a single cognitive-behavioral domain. In this review, I argue that autism is a ‘‘distributed disorder’’ on various levels of study (genetic, neuroanatomical, neurofunctional, behavioral). ‘‘Localizing’’ models are therefore not promising. The large array of potential genetic risk factors suggests that multiple (or all) emerging functional brain net- works are affected during early development. This is supported by wide- spread growth abnormalities throughout the brain. Interactions during development between affected functional networks and atypical experi- ential effects (associated with atypical behavior) in children with autism further complicate the neurological bases of the disorder, resulting in" 6ddcc4ce66f301954132c13e629899a27f729112,Unsupervised Deep Network Pretraining via Human Design,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Unsupervised Network Pretraining via Encoding Human Design Liu, M.-Y.; Mallya, A.; Tuzel, C.O.; Chen, X. TR2016-022 March 2016" 6d994076a6ef3b6e74e2a0149af759e48b71f9a0,Could dynamic attractors explain associative prosopagnosia?,"http://intl.elsevierhealth.com/journals/mehy Could dynamic attractors explain associative prosopagnosia? Ali Zifan a,1, Shahriar Gharibzadeh a,*, Mohammad Hassan Moradi b Neuromuscular Systems Laboratory, Faculty of Biomedical Engineering, Amirkabir University of Technology, Tehran 15875-4413, Iran Biological Signal Processing Laboratory, Faculty of Biomedical Engineering, Amirkabir University of Technology, Tehran 15875-4413, Iran Received 21 June 2006; accepted 28 June 2006 Summary Prosopagnosia is one of the many forms of visual associative agnosia, in which familiar faces lose their distinctive association. In the case of prosopagnosia, the ability to recognize familiar faces is lost, due to lesions in the medial occipitotemporal region. In ‘‘associative’’ prosopagnosia, the perceptual system seems adequate to allow for recognition, yet recognition cannot take place. Our hypothesis is that a possible cause of associative prosopagnosia might be the occurrence of Dynamic attractors in the brain’s auto-associative circuits. We present a biologically plausible model composed of two stages: Pre-processing and face recognition. In the first stage, the face image is passed through Gabor filters which model the kind of visual processing carried out by the simple and complex cells of the primary visual cortex of higher mammals and the resulting features are fed into a Pseudo-inverse associative neural network for the recognition task. Next, we damage the network by reducing self-connections below a certain threshold in order to create dynamic attractors and hence hinder the networks ability to recognize familiar faces (faces already learned). Results obtained from simulations show that the resulting network responses are very similar to those of" 6db59b031406546682a773baed2caed529aaf37c,Inferring the semantics of direction signs in public places,"Inferring the Semantics of Direction Signs in Public Places J´erˆome Maye∗, Luciano Spinello∗†, Rudolph Triebel∗, and Roland Siegwart∗ Autonomous Systems Lab, ETH Zurich, Switzerland email: {jerome.maye, rudolph.triebel, Social Robotics Lab, Department of Computer Science, University of Freiburg, Germany email:" 6dd850acb928457ffd44e5d9dceb7946a7f0c6ee,Template-based matching using weight maps,"    [1-8]   !!""  !! ""                    && &    !!'                       " 6d79999f8dc0cb9f86a87eaa2eb313a4eaeb2e5a,Instructions for use Title Bregman pooling : feature-space local pooling for imageclassification,"Title Bregman pooling : feature-space local pooling for image lassification Author(s) Najjar, Alameen; Ogawa, Takahiro; Haseyama, Miki Citation International Journal of Multimedia Information Retrieval Issue Date 015-09-04 Doc URL http://hdl.handle.net/2115/62753 Right The final publication is available at link.springer.com rticle (author version) Additional Information Information BP.pdf Instructions for use Hokkaido University Collection of Scholarly and Academic Papers : HUSCAP" 6dfa82f00ec6faee1db319c1e306ae779cfc1c36,"The Role of Methodology and Spatiotemporal Scale in Understanding Environmental Change in Peri-Urban Ouagadougou, Burkina Faso","Remote Sens. 2013, 5, 1465-1483; doi:10.3390/rs5031465 OPEN ACCESS ISSN 2072-4292 www.mdpi.com/journal/remotesensing Article The Role of Methodology and Spatiotemporal Scale in Understanding Environmental Change in Peri-Urban Ouagadougou, Burkina Faso Yonatan Kelder 1,*, Thomas Theis Nielsen 1 and Rasmus Fensholt 2 Roskilde University, Universitetsvej 1, ENSPAC House 0.2, Roskilde 4000, Denmark; E-Mail: Copenhagen University, Institute for Geography and Geology, Øster Voldgade 10, Copenhagen K 1350, Denmark; E-Mail: * Author to whom correspondence should be addressed; E-Mail: Tel.: +45-30-49-14-92. Received: 18 January 2013; in revised form: 24 February 2013 / Accepted: 15 March 2013 / Published: 19 March 2013" 6d902439b736a7546dd8872b307fb760087ca629,SIFT Meets CNN: A Decade Survey of Instance Retrieval,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 SIFT Meets CNN: A Decade Survey of Instance Retrieval Liang Zheng, Yi Yang, and Qi Tian, Fellow, IEEE" 6d6bb981bc8470de23e30890bd96a76ffd2b7ced,The Eyes Are the Windows to the Mind: Direct Eye Gaze Triggers the Ascription of Others' Minds.,"669124 PSPXXX10.1177/0146167216669124Personality and Social Psychology BulletinKhalid et al. research-article2016 Article The Eyes Are the Windows to the Mind: Direct Eye Gaze Triggers the Ascription of Others’ Minds Saara Khalid1, Jason C. Deska1, and Kurt Hugenberg1 Personality and Social Psychology Bulletin 016, Vol. 42(12) 1666 –1677 © 2016 by the Society for Personality nd Social Psychology, Inc Reprints and permissions: sagepub.com/journalsPermissions.nav DOI: 10.1177/0146167216669124 pspb.sagepub.com" 6d8057ce549db311b7ddaeed8dfd934b58c1c281,A RELIEF Based Feature Extraction Algorithm,"A RELIEF Based Feature Extraction Algorithm Yijun Sun∗ Dapeng Wu†" 6dd007b6e518a3aa96111028c4664f2647e5e81a,3D Face Synthesis Driven by Personality Impression,"D Face Synthesis Driven by Personality Impression Yining Lang1 Wei Liang1 Yujia Wang1 Lap-Fai Yu2 Beijing Institute of Technology University of Massachusetts Boston" 6ddb65ce430f8db2eb66b0a98ed8981049b3f520,PML-SLAM : a solution for localization in large-scale urban environments,"PML-SLAM: a solution for localization in large-scale urban environments Zayed Alsayed∗†, Guillaume Bresson∗, Fawzi Nashashibi† and Anne Verroust-Blondet† Institut VEDECOM Versailles, France Inria Paris-Rocquencourt Le Chesnay, France" 6d76eefecdcaa130a000d1d6c93cf57166ebd18e,Resource Aware Person Re-identification Across Multiple Resolutions,"Resource Aware Person Re-identification across Multiple Resolutions Yan Wang∗ †, Lequn Wang∗ †, Yurong You∗ ‡, Xu Zou§, Vincent Chen† Serena Li†, Gao Huang†, Bharath Hariharan†, Kilian Q. Weinberger†" 6d88fb85fe5c61bd65e0a373cd39fac81a19596a,DC-Image for Real Time Compressed Video Matching,"DC-Image for Real Time Compressed Video Matching Saddam Bekhet, Amr Ahmed and Andrew Hunter" 6d7dabc58f53c0233d6d593a8fee76d1c7f44033,Robust Observation Detection for Single Object Tracking: Deterministic and Probabilistic Patch-Based Approaches,"Sensors 2012, 12, 15638-15670; doi:10.3390/s121115638 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article Robust Observation Detection for Single Object Tracking: Deterministic and Probabilistic Patch-Based Approaches Mohd Asyraf Zulkifley 1,*, David Rawlinson 2 and Bill Moran 2 Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 Bangi, Malaysia Department of Electrical and Electronic Engineering, The University of Melbourne, VIC 3010, Australia; E-Mails: (D.R.); (B.M.) * Author to whom correspondence should be addressed; E-Mail: Tel.: +603-8921-6335. Received: 18 September 2012; in revised form: 5 November 2012 / Accepted: 5 November 2012 / Published: 12 November 2012 the problems of blurring, moderate deformation," 6da06fc70f32454f7841b153c582e65aed7047e9,Deep pipelined one-chip FPGA implementation of a real-time image-based human detection algorithm,"NAOSITE: Nagasaki University's Academic Output SITE Title Deep pipelined one-chip FPGA implementation of a real-time image-based human detection algorithm Author(s) Negi, Kazuhiro; Dohi, Keisuke; Shibata, Yuichiro; Oguri, Kiyoshi Citation 011, Article number6132679; 2011 Issue Date 011-12 Right http://hdl.handle.net/10069/29887 © 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This document is downloaded at: 2018-12-08T05:46:10Z http://naosite.lb.nagasaki-u.ac.jp" 6dc3b8a5fdceaea4b32df8552cbb5a22ef83c197,Speech-Based Visual Question Answering,"Speech-Based Visual Question Answering Ted Zhang KU Leuven Dengxin Dai ETH Zurich Tinne Tuytelaars KU Leuven Marie-Francine Moens KU Leuven" 6d618657fa5a584d805b562302fe1090957194ba,Human Facial Expression Recognition based on Principal Component Analysis and Artificial Neural Network,"Full Paper NNGT Int. J. of Artificial Intelligence , Vol. 1, July 2014 Human Facial Expression Recognition based on Principal Component Analysis and Artificial Neural Network Laboratory of Automatic and Signals Annaba (LASA) , Department of electronics, Faculty of Engineering, Zermi.Narima, Ramdani.M, Saaidia.M Badji-Mokhtar University, P.O.Box 12, Annaba-23000, Algeria. E-Mail :" 6d500b0c342c1cf23efff049ef121bcf5e606ea1,Real-Time Category-Based and General Obstacle Detection for Autonomous Driving,"Real-time category-based and general obstacle detection for autonomous driving Noa Garnett Uri Verner Ariel Ayash Shai Silberstein Vlad Goldner Shaul Oron Rafi Cohen Ethan Fetaya Kobi Horn Dan Levi Advanced Technical Center Israel, General Motors R&D Hamada 7, Herzlyia, Israel" 6dd052df6b0e89d394192f7f2af4a3e3b8f89875,A literature survey on Facial Expression Recognition using Global Features,"International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Volume-2, Issue-4, April 2013 A literature survey on Facial Expression Recognition using Global Features Vaibhavkumar J. Mistry, Mahesh M. Goyani" 6d96bf377c96e1dd9b43e9f12e0ee2a66543edbe,Viewpoint invariant 3D landmark model inference from monocular 2D images using higher-order priors,"011 IEEE International Conference on Computer Vision 978-1-4577-1102-2/11/$26.00 c(cid:13)2011 IEEE" 6d6a106caef228b3eee1f5765740938a534db828,Density-based clustering: A ‘landscape view’ of multi-channel neural data for inference and dynamic complexity analysis,"RESEARCH ARTICLE Density-based clustering: A ‘landscape view’ of multi-channel neural data for inference and dynamic complexity analysis Gabriel Baglietto1,2*, Guido Gigante3,4, Paolo Del Giudice1,3 INFN-Roma1, Italian National Institute for Nuclear Research (INFN), Rome, Italy, 2 IFLYSIB Instituto de Fı´sica de Lı´quidos y Sistemas Biolo´gicos (UNLP-CONICET), La Plata, Argentina, 3 Italian Institute of Health (ISS), Rome, Italy, 4 Mperience srl, Rome, Italy" 6d84d92d9ed6c226f0cc6401bc425a23432c9f96,Autism spectrum disorders: clinical and research frontiers.,"Downloaded from dc.bmj.com on 22 May 2008 Autism spectrum disorders: clinical and research frontiers E B Caronna, J M Milunsky and H Tager-Flusberg Arch. Dis. Child. doi:10.1136/adc.2006.115337 2008;93;518-523; originally published online 27 Feb 2008; Updated information and services can be found at: http://adc.bmj.com/cgi/content/full/93/6/518 These include: References This article cites 70 articles, 25 of which can be accessed free at: http://adc.bmj.com/cgi/content/full/93/6/518#BIBL Rapid responses You can respond to this article at: http://adc.bmj.com/cgi/eletter-submit/93/6/518 Email alerting service" 6d432962055a8c521e6b388d5a0a2140a0019a5e,Sensor network reconfiguration and big multimedia data fusion for situational awareness in smart environments,"Sensor network reconfiguration and big multimedia data fusion for situational wareness in smart environments Z. Akhtar, C. Drioli, M. Farinosi, G. Ferrin, G.L. Foresti, N. Martinel, C. Micheloni, C. Piciarelli, D. Salvati, L. Snidaro and M. Vernier AVIRES Lab - Department of Mathematics and Computer Science, Università degli Studi di Udine Via delle Scienze, 206, 33100 Udine - Italy last years, an INTRODUCTION increasing number of environments have been enhanced with smart sensors and have become more and more smart and self-organizing [1]. Situational awareness (SA) in these wide areas covers a huge range of topics and hallenges [2]. As matter of fact, understanding ctivities for situation assessment cannot be chieved locally but it requires to widen as much as possible the monitored area. Several different and new problems must be investigated from the use of single sensors able to adapt internal or external" 6d8c9a1759e7204eacb4eeb06567ad0ef4229f93,"Face Alignment Robust to Pose, Expressions and Occlusions","Face Alignment Robust to Pose, Expressions and Occlusions Vishnu Naresh Boddeti†, Myung-Cheol Roh†, Jongju Shin, Takaharu Oguri, Takeo Kanade" 6dead19a89cbcbb71350a19925cb2c6f71261dfc,Fair k-Center Clustering for Data Summarization,"Fair k-Center Clustering for Data Summarization Matth¨aus Kleindessner 1 Pranjal Awasthi 1 Jamie Morgenstern 2" 6d10beb027fd7213dd4bccf2427e223662e20b7d,User Adaptive and Context-Aware Smart Home Using Pervasive and Semantic Technologies,"Publishing CorporationJournal of Electrical and Computer EngineeringVolume 2016, Article ID 4789803, 20 pageshttp://dx.doi.org/10.1155/2016/4789803" 6d77b214a39b8592cd6ce48c9945e8a2466b22ba,Videana: A Software Toolkit for Scientific Film Studies,"Ralph Ewerth, Markus Mühling, Thilo Stadelmann, Julinda Gllavata, Manfred Grauer, Bernd Freisleben Videana: A Software Toolkit for Scientific Film Studies" 309e17e6223e13b1f76b5b0eaa123b96ef22f51b,Face recognition based on a 3D morphable model,"Face Recognition based on a 3D Morphable Model Volker Blanz University of Siegen H¤olderlinstr. 3 57068 Siegen, Germany" 30fa389899ab0577779ce0aa19d2a69702d251a1,Sensor Selection by Linear Programming,"Noname manuscript No. (will be inserted by the editor) Sensor Selection by Linear Programming Joseph Wang · Kirill Trapeznkov · Venkatesh Saligrama Received: date / Accepted: date" 3046baea53360a8c5653f09f0a31581da384202e,Deformable Face Alignment via Local Measurements and Global Constraints,"Deformable Face Alignment via Local Measurements and Global Constraints Jason M. Saragih" 30a68bea6a43c239d899d7f02bb8ef9f3c5a8f47,Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild,"Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild Jianfeng Dong, Xirong Li, and Duanqing Xu" 30fd7b1f8502b1c1d7a855946d99d2d5323ec973,Big Data Analysis for 2 Media Production,"I N V I T E D P A P E R Big Data Analysis for Media Production By Josep Blat, Alun Evans, Hansung Kim, Evren Imre, Luka`sˇ Polok, Viorela Ila, Nikos Nikolaidis, Senior Member IEEE, Pavel Zemcˇı´k, Anastasios Tefas, Pavel Smrzˇ, Adrian Hilton, Member IEEE, and Ioannis Pitas, Fellow IEEE" 30f113d985d876a3974838b2ead49a069b474e57,Guided Upsampling Network for Real-Time Semantic Segmentation,"MAZZINI: GUN FOR REAL-TIME SEMANTIC SEGMENTATION Guided Upsampling Network for Real-Time Semantic Segmentation Davide Mazzini Department of Informatics, Systems nd Communication University of Milano-Bicocca viale Sarca 336 Milano, Italy" 306ae56a4fc8f090e58a237749950e1607382ed7,Spatio-Temporal Matching for Human Pose Estimation in Video,"Spatio-temporal Matching for Human Pose Estimation in Video Feng Zhou and Fernando De la Torre" 300b819bbbe857f5fe89d0895f907073fc288719,"Towards a Robust People Tracking Framework for Service Robots in Crowded , Dynamic Environments","Towards a Robust People Tracking Framework for Service Robots in Crowded, Dynamic Environments Timm Linder Fabian Girrbach Kai O. Arras" 305c4d91b0f70853a1cb0ed2a60a466b84e5c13d,Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMs,"Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMs Nachiket Deo and Mohan M. Trivedi" 300fd9ae3bb33fba3e48b605e49d59b3ce3957ff,Recurrent Neural Networks for Emotion Recognition in Video,"Recurrent Neural Networks for Emotion Recognition in Video Samira Ebrahimi Kahou École Polytechnique de Montréal, Canada samira.ebrahimi- Vincent Michalski Université de Montréal, Montréal, Canada Kishore Konda Goethe-Universität Frankfurt, Germany Roland Memisevic Université de Montréal, Montréal, Canada Christopher Pal École Polytechnique de Montréal, Canada" 30f78071ac2bc965ffbf452a7b315d6dfddae30e,Lingusitic Analysis of Multi-Modal Recurrent Neural Networks,"Proceedings of the 2015 Workshop on Vision and Language (VL’15), pages 8–9, Lisbon, Portugal, 18 September 2015. c(cid:13)2015 Association for Computational Linguistics." 30ad88ca5b834ca78619f3938b5f8ee534fd3ea8,Random Forest with Learned Representations for Semantic Segmentation,"Random Forest with Learned Representations for Semantic Segmentation Byeongkeun Kang and Truong Q. Nguyen, Fellow, IEEE" 305346d01298edeb5c6dc8b55679e8f60ba97efb,Fine-Grained Face Annotation Using Deep Multi-Task CNN,"Article Fine-Grained Face Annotation Using Deep Multi-Task CNN Luigi Celona * , Simone Bianco nd Raimondo Schettini Department of Informatics, Systems and Communication, University of Milano-Bicocca, viale Sarca, 336 Milano, Italy; (S.B.); (R.S.) * Correspondence: Received: 3 July 2018; Accepted: 13 August 2018; Published: 14 August 2018" 30ff70a3afea6b6b46bde883ca1ade0e932bbe71,"Image Parsing: Unifying Segmentation, Detection, and Recognition","Int’l J. of Computer Vision, Marr Prize Issue, 2005. Image Parsing: Unifying Segmentation, Detection, and Recognition Zhuowen Tu1, Xiangrong Chen1, Alan L. Yuille1,2, and Song-Chun Zhu1,3 Departments of Statistics1, Psychology2, and Computer Science3, University of California, Los Angeles, Los Angeles, CA 90095. emails:" 309011919f45062ceefcd2275ded5171762baa59,"Principles "" Generic Object Recognition Via Integrating Distinct Features with SVM "" by","Notice of Violation of IEEE Publication Principles ""Generic Object Recognition Via Integrating Distinct Features with SVM"" y Tong-Cheng Huang and You-Dong Ding in Proceedings of 2006 International Conference on Machine Learning and Cybernetics, pp 3897-3902. After careful and considered review of the content and authorship of this paper by a duly onstituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles. This paper is a near duplication of the original text from the papers cited below. The original text was copied without attribution and without permission. Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following articles: ""Generic Object Recognition by Combining Distinct Features in Machine Learning,"" y Hongying Meng, David R. Hardoon, John Shawe-Taylor, Sandor Szedmak, in the Proceedings of the 17th Annual Symposium on Electronic Imaging, January 2005, Authorized licensed use limited to: University College London. Downloaded on June 6, 2009 at 03:32 from IEEE Xplore. Restrictions apply." 30d4d6bf4bd09f5b5a4f3631aa1ef18fe07efef8,Subtraction with Dirichlet Process Mixture Models,"Background Subtraction with Dirichlet Process Mixture Models. Haines, TS; Xiang, T For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle/123456789/11343 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 30eed14dfdee78279536e680871bed4f128d5f46,A Study of Calorie Estimation in Pictures of Food, 30b103d59f8460d80bb9eac0aa09aaa56c98494f,Enhancing Human Action Recognition with Region Proposals,"Enhancing Human Action Recognition with Region Proposals Fahimeh Rezazadegan, Sareh Shirazi, Niko Sünderhauf, Michael Milford, Ben Upcroft Australian Centre for Robotic Vision(ACRV), School of Electrical Engineering and Computer Science Queensland University of Technology(QUT)" 302fee58f8c9498e8a5e543312e7c11baf7e0827,Robust voting algorithm based on labels of behavior for video copy detection,"Robust Voting Algorithm Based on Labels of Behavior for Video Copy Detection Julien Law-To, Olivier Buisson Valerie Gouet-Brunet, Nozha Boujemaa INRIA Institut National de la Recherche et de l’Informatique Rocquencourt, France Institut National de l’Audiovisuel Bry Sur Marne, France (jlawto,obuisson)" 300b8caf79783a7eba5608b5819b6fed14273d2d,Unsupervised Joint Mining of Deep Features and Image Labels for Large-Scale Radiology Image Categorization and Scene Recognition,"Unsupervised Joint Mining of Deep Features and Image Labels for Large-scale Radiology Image Categorization and Scene Recognition Xiaosong Wang, Le Lu, Hoo-chang Shin, Lauren Kim, Mohammadhadi Bagheri, Isabella Nogues, Jianhua Yao, Ronald M. Summers Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, 0 Center Drive, Bethesda, MD 20892" 30861d747c87e2e838c1c30eed334b17cc93cdb6,Bootstrapping Face Detection with Hard Negative Examples,"Bootstrapping Face Detection with Hard Negative Examples Shaohua Wan Zhijun Chen Tao Zhang Bo Zhang Kong-kat Wong {wanshaohua, chenzhijun, tao.zhang, zhangbo, Xiaomi Inc. August 9, 2016" 30962cf6f47396df88bf1c8827ebda8f0a6ff516,A Convolutional Neural Network Approach for Assisting Avalanche Search and Rescue Operations with UAV Imagery,"Article A Convolutional Neural Network Approach for Assisting Avalanche Search and Rescue Operations with UAV Imagery Mesay Belete Bejiga 1, Abdallah Zeggada 1, Abdelhamid Nouffidj 2 and Farid Melgani 1,* Department of Information Engineering and Computer Science University of Trento, 38123 Trento, Italy; (M.B.B.); (A.Z.) Département des Télécommunications, Faculté d’Electronique et d’Informatique, USTHB BP 32, El-Alia, Bab-Ezzouar, 16111 Algiers, Algeria; * Correspondence: Tel.: +39-046-128-1573 Academic Editors: Francesco Nex, Xiaofeng Li and Prasad S. Thenkabail Received: 11 November 2016; Accepted: 14 January 2017; Published: 24 January 2017" 30bb582c2c09abc7eb9dda7d9f80804eeb89f9d7,Research Problems and Opportunities in Memory Systems,"ResearchProblemsandOpportunitiesinMemorySystemsOnurMutlu1,LavanyaSubramanian1c(cid:13)TheAuthors2014.ThispaperispublishedwithopenaccessatSuperFri.orgThememorysystemisafundamentalperformanceandenergybottleneckinalmostallcom-putingsystems.Recentsystemdesign,application,andtechnologytrendsthatrequiremoreca-pacity,bandwidth,ef‌f‌iciency,andpredictabilityoutofthememorysystemmakeitanevenmoreimportantsystembottleneck.Atthesametime,DRAMtechnologyisexperiencingdif‌f‌iculttech-nologyscalingchallengesthatmakethemaintenanceandenhancementofitscapacity,energy-ef‌f‌iciency,andreliabilitysignificantlymorecostlywithconventionaltechniques.Inthisarticle,afterdescribingthedemandsandchallengesfacedbythememorysystem,weexaminesomepromisingresearchanddesigndirectionstoovercomechallengesposedbymemoryscaling.Specifically,wedescribethreemajornewresearchchallengesandsolutiondirections:1)enablingnewDRAMarchitectures,functions,interfaces,andbetterintegrationoftheDRAMandtherestofthesystem(anapproachwecallsystem-DRAMco-design),2)designingamemorysystemthatemploysemergingnon-volatilememorytechnologiesandtakesadvantageofmultipledifferenttechnologies(i.e.,hybridmemorysystems),3)providingpredictableperformanceandQoStoapplicationssharingthememorysystem(i.e.,QoS-awarememorysystems).WealsobrieflydescribeourongoingrelatedworkincombatingscalingchallengesofNANDflashmemory.Keywords:memorysystems,scaling,DRAM,flash,non-volatilememory,QoS,reliability.IntroductionMainmemoryisacriticalcomponentofallcomputingsystems,employedinserver,em-bedded,desktop,mobileandsensorenvironments.Memorycapacity,energy,cost,performance,andmanagementalgorithmsmustscaleaswescalethesizeofthecomputingsysteminordertomaintainperformancegrowthandenablenewapplications.Unfortunately,suchscalinghasbe-comedif‌f‌icultbecauserecenttrendsinsystems,applications,andtechnologygreatlyexacerbatethememorysystembottleneck.1.MemorySystemTrendsInparticular,onthesystems/architecturefront,energyandpowerconsumptionhavebecomekeydesignlimitersasthememorysystemcontinuestoberesponsibleforasignificantfractionofoverallsystemenergy/power[112].Moreandincreasinglyheterogeneousprocessingcoresandagents/clientsaresharingthememorysystem[11,36,39,60,78,79,178,181],leadingtoincreasingdemandformemorycapacityandbandwidthalongwitharelativelynewdemandforpredictableperformanceandqualityofservice(QoS)fromthememorysystem[129,137,176].Ontheapplicationsfront,importantapplicationsareusuallyverydataintensiveandarebecomingincreasinglyso[17],requiringbothreal-timeandof‌f‌linemanipulationofgreatamountsofdata.Forexample,next-generationgenomesequencingtechnologiesproducemassiveamountsofsequencedatathatoverwhelmsmemorystorageandbandwidthrequirementsoftoday’shigh-enddesktopandlaptopsystems[9,111,186,196,197]yetresearchershavethegoalofenablinglow-costpersonalizedmedicine,whichrequiresevenlargeramountsofdataandtheireffectiveanalyses.Creationofnewkillerapplicationsandusagemodelsforcomputerslikelydependsonhowwellthememorysystemcansupporttheef‌f‌icientstorageandmanipulationofdatainsuch1CarnegieMellonUniversityDOI:10.14529/jsfi1403022014,Vol.1,No.319" 30f84c48bdf2f6152075dd9651a761a84b2f2166,"No fear, no panic: probing negation as a means for emotion regulation.","doi:10.1093/scan/nss043 SCAN (2013) 8, 654 ^661 No fear, no panic: probing negation as a means for emotion regulation Cornelia Herbert,1 Roland Deutsch,2 Petra Platte,1 and Paul Pauli1 Department of Psychology, Biological Psychology, Clinical Psychology and Psychotherapy, University of Wu¨rzburg, 97070 Wu¨rzburg and Department of Psychology, Technische Universita¨t Dresden, Dresden, Germany This electroencephalographic study investigated if negating one’s emotion results in paradoxical effects or leads to effective emotional downregulation. Healthy participants were asked to downregulate their emotions to happy and fearful faces by using negated emotional cue words (e.g. no fun, no fear). Cue words were congruent with the emotion depicted in the face and presented prior to each face. Stimuli were presented in blocks of happy and fearful faces. Blocks of passive stimulus viewing served as control condition. Active regulation reduced amplitudes of early event-related brain potentials (early posterior negativity, but not N170) and the late positive potential for fearful faces. A fronto-central negativity peaking at about 250 ms after target face onset showed larger amplitude modulations during downregulation of fearful and happy faces. Behaviorally, negating was more associated with reappraisal than with suppression. Our results suggest that in an emotional context, negation processing could be quite effective for emotional downregulation but that its effects depend on the type of the negated emotion (pleasant vs unpleasant). Results are discussed in the context of dual process models of cognition and emotion regulation. Keywords: emotion regulation; event-related brain potentials; negation; reappraisal; suppression INTRODUCTION Emotion regulation is an important aspect of everyday life (Gross and John, 2003; Nezlek and Kuppens, 2008). Imagine the following situ-" 30ccfd2b4b6d5b30581356ccefcf96fd77c1766a,Overview of the ImageCLEF 2014 Scalable Concept Image Annotation Task,"Overview of the ImageCLEF 2016 Scalable Concept Image Annotation Task Andrew Gilbert, Luca Piras, Josiah Wang, Fei Yan, Arnau Ramisa, Emmanuel Dellandrea, Robert Gaizauskas, Mauricio Villegas and Krystian Mikolajczyk" 3035bcbad93767570d444c136f4036f357648d60,Feature Extraction for Incomplete Data Via Low-Rank Tensor Decomposition With Feature Regularization.,"This is a repository copy of Feature extraction for incomplete data via low-rank tensor decomposition with feature regularization. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/138784/ Version: Accepted Version Article: Shi, Q., Cheung, Y.-M., Zhao, Q. et al. (1 more author) (2018) Feature extraction for incomplete data via low-rank tensor decomposition with feature regularization. IEEE Transactions on Neural Networks and Learning Systems. ISSN 2162-237X https://doi.org/10.1109/TNNLS.2018.2873655 © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Reproduced in accordance with the publisher's self-archiving policy. Reuse Items deposited in White Rose Research Online are protected by copyright, with all rights reserved unless indicated otherwise. They may be downloaded and/or printed for private study, or other acts as permitted by national copyright laws. The publisher or other rights holders may allow further reproduction and re-use of the full text version. This is indicated by the licence information on the White Rose Research Online record" 30a319d6e1472c81a1987133afb01f524df459dc,Pedestrian Detection Based on Adaptive Selection of Visible Light or Far-Infrared Light Camera Image by Fuzzy Inference System and Convolutional Neural Network-Based Verification,"Article Pedestrian Detection Based on Adaptive Selection of Visible Light or Far-Infrared Light Camera Image by Fuzzy Inference System and Convolutional Neural Network-Based Verification Jin Kyu Kang, Hyung Gil Hong and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (J.K.K.); (H.G.H.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 16 June 2017; Accepted: 5 July 2017; Published: 8 July 2017" 30256c10cb7ec139b4245855850998c39b297975,Functional magnetic resonance imaging of autism spectrum disorders,"C l i n i c a l r e s e a r c h Functional magnetic resonance imaging of utism spectrum disorders Gabriel S. Dichter, PhD Introduction utism was first described by Leo Kanner1 and Hans Asperger2 in a series of clinical case studies. Both linicians suggested that the conditions now referred to s autism spectrum disorders (ASDs) may have a neu- robiological basis. With the relatively recent advent of modern brain imaging techniques, translational psychi- tric research has embraced the systematic study of This review presents an overview of functional magnetic resonance imaging findings in autism spectrum disorders (ASDs). Although there is considerable heterogeneity with respect to results across studies, common themes have emerged, including: (i) hypoactivation in nodes of the “social brain” during social processing tasks, including regions within the prefrontal cortex, the posterior superior temporal sulcus, the amygdala, and the fusiform gyrus; (ii) aber- rant frontostriatal activation during cognitive control tasks relevant to restricted and repetitive behaviors and inter- ests, including regions within the dorsal prefrontal cortex and the basal ganglia; (iii) differential lateralization and ctivation of language processing and production regions during communication tasks; (iv) anomalous mesolimbic responses to social and nonsocial rewards; (v) task-based long-range functional hypoconnectivity and short-range" 300eb15b819ecc9668be26735e5038efc4e05281,Object-based Place Recognition for Mobile Robots Using Panoramas,"Object-based Place Recognition for Mobile Robots Using Panoramas Arturo RIBES a,1, Arnau RAMISA a and Ramon LOPEZ DE MANTARAS a and Ricardo TOLEDO b Artificial Intelligence Research Institute (IIIA-CSIC), Campus UAB, 08193 Bellaterra, Computer Vision Center (CVC), Campus UAB, 08193 Bellaterra, Spain Spain" 30870ef75aa57e41f54310283c0057451c8c822b,Overcoming catastrophic forgetting with hard attention to the task,"Overcoming Catastrophic Forgetting with Hard Attention to the Task Joan Serr`a 1 D´ıdac Sur´ıs 1 2 Marius Miron 1 3 Alexandros Karatzoglou 1" 3099615de73bb1d6442ce29dc9959ddb91cfc282,Detecting and Tracking Sports Players with Random Forests and Context-Conditioned Motion Models,"Detecting and Tracking Sports Players with Random Forests and Context-Conditioned Motion Models Jingchen Liu and Peter Carr" 301474a50a39b24917ad79bd2493f1168c4c1227,Eigen-disfigurement model for simulating plausible facial disfigurement after reconstructive surgery,"Lee et al. BMC Medical Imaging (2015) 15:12 DOI 10.1186/s12880-015-0050-7 R ES EAR CH A R T I C LE Open Access Eigen-disfigurement model for simulating plausible facial disfigurement after reconstructive surgery Juhun Lee1,2, Michelle C Fingeret2,3, Alan C Bovik1, Gregory P Reece2, Roman J Skoracki2, Matthew M Hanasono2 and Mia K Markey4,5*" 301b0da87027d6472b98361729faecf6e1d5e5f6,HEAD POSE ESTIMATION IN FACE RECOGNITION ACROSS POSE SCENARIOS,"HEAD POSE ESTIMATION IN FACE RECOGNITION ACROSS POSE SCENARIOS M. Saquib Sarfraz and Olaf Hellwich Computer vision and Remote Sensing, Berlin university of Technology Sekr. FR-3-1, Franklinstr. 28/29, D-10587, Berlin, Germany. Keywords: Pose estimation, facial pose, face recognition, local energy models, shape description, local features, head pose classification." 305dccd4004560572af2e849a36faf5626990517,Comparative Analysis of Face Recognition Approaches : A Survey,"Comparative Analysis of Face Recognition Approaches: International Journal of Computer Applications (0975 – 8887) Volume 57– No.17, November 2012 A Survey Ripal Patel, Nidhi Rathod, Ami Shah Electronics & Telecommunication Department, BVM Engineering College, Vallabh Vidyanagar-388120, Gujarat, India." 30c8a2b6a505645b9f93dcc4d365eee6f46c4c37,Using Curvilinear Features in Focus for Registering a Single Image to a 3D Object,"Using Curvilinear Features in Focus for Registering Single Image to a 3D Object Hatem A. Rashwan, Sylvie Chambon, Pierre Gurdjos, G´eraldine Morin and Vincent Charvillat" 307a810d1bf6f747b1bd697a8a642afbd649613d,An affordable contactless security system access for restricted area,"An affordable contactless security system access for restricted area Pierre Bonazza1, Johel Mitéran1, Barthélémy Heyrman1, Dominique Ginhac1, Vincent Thivent2, Julien Dubois1 Laboratory Le2i University Bourgogne Franche-Comté, France Odalid compagny, France Contact Keywords – Smart Camera, Real-time Image Processing, Biometrics, Face Detection, Face Verifica- tion, EigenFaces, Support Vector Machine, We present in this paper a security system based on identity verification process and a low-cost smart cam- era, intended to avoid unauthorized access to restricted rea. The Le2i laboratory has a longstanding experi- ence in smart cameras implementation and design [1], for example in the case of real-time classical face de- tection [2] or human fall detection [3]. The principle of the system, fully thought and designed in our laboratory, is as follows: the allowed user pre- sents a RFID card to the reader based on Odalid system" 30a059872d0fff3442504c24880c93738036e6aa,Distributed neural computation for the visual perception of motion. (Calcul neuronal distribué pour la perception visuelle du mouvement),"UFRmath´ematiquesetinformatique´EcoledoctoraleIAEMLorraineD´epartementdeformationdoctoraleeninformatiqueCalculneuronaldistribu´epourlaperceptionvisuelledumouvementTH`ESEpr´esent´eeetsoutenuepubliquementle14Octobre2011pourl’obtentionduDoctoratdel’universit´eNancy2(sp´ecialit´einformatique)parMauricioDavidCerdaVillablancaCompositiondujuryPr´esident:Lepr´esidentRapporteurs:MathiasQUOYProfesseur,Universit´edeCergy-Pontoise,FranceAdrianPALACIOSProfesseur,UniversidaddeValparaiso,ChiliExaminateurs:HeikoNEUMANNProfesseur,UniversityofUlm,AllemagneAnneBOYERProfesseur,Universit´eNancy2,FranceRachidDERICHEDirecteurdeRecherche,INRIA,Sophia-Antipolis,FranceBernardGIRAU(directeur)Professeur,Universit´eHenriPoincar´e,Nancy1LaboratoireLorraindeRechercheenInformatiqueetsesApplications—UMR7503" 30aac3becead355545b5ab7f0c3158040360021e,ACD: Action Concept Discovery from Image-Sentence Corpora,"ACD: Action Concept Discovery from Image-Sentence Corpora Jiyang Gao Univ. of Southern California Chen Sun Univ. of Southern California Ram Nevatia Univ. of Southern California" 308647f22e3f1c80b7416b3c53fd56f9abfa904f,Robust Real-Time Tracking with Diverse Ensembles and Random Projections,"Robust Real-Time Tracking with Diverse Ensembles and Random Projections Center for Informatics Science, Center for Informatics Science, Sara Maher Nile University Giza, Egypt Mohamed El Helw Center for Informatics Science, Nile University Giza, Egypt Ahmed Salaheldin Nile University Giza, Egypt" 309e5ae1554d2afc3b94eaea66b8f31ba85c434a,"Bian, Xiao. Sparse and Low-rank Modeling on High Dimensional Data: a Geometric Perspective. (under the Direction of Dr. Hamid Krim.) Sparse and Low-rank Modeling on High Dimensional Data: a Geometric Perspective", 300fb25626bebfc84cf2f6458784b5cdf5c3ffc2,Cross-Dataset Adaptation for Visual Question Answering,"Cross-Dataset Adaptation for Visual Question Answering Wei-Lun Chao∗ Hexiang Hu∗ Fei Sha U. of Southern California U. of Southern California U. of Southern California Los Angeles, CA Los Angeles, CA Los Angeles, CA" 3b9a2f0fd429016b531ed398017da029fe5154da,Gabor Parameter Selection for Local Feature Detection,"Gabor Parameter Selection for Local Feature Detection ⋆ Plinio Moreno, Alexandre Bernardino, and Jos´e Santos-Victor {plinio, alex, Instituto Superior T´ecnico & Instituto de Sistemas e Rob´otica 049-001 Lisboa - Portugal" 3b54cf5eb7fe173def6e81eefeff17a1b9960cb2,Efficient Computation of Collision Probabilities for Safe Motion Planning,"Efficient Computation of Collision Probabilities for Safe Motion Planning∗ Andrew Blake, Alejandro Bordallo, Majd Hawasly, Svetlin Penkov, Subramanian Ramamoorthy†, Alexandre Silva" 3bf66814817f582510e0f0a717112b78aca075a0,UNIVERSITY OF CALIFORNIA RIVERSIDE Bio-Image Analysis for Understanding Plant Development and Mosquito Behaviors A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy,"UNIVERSITY OF CALIFORNIA RIVERSIDE Bio-Image Analysis for Understanding Plant Development and Mosquito Behaviors A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Computer Science Katya Mkrtchyan March 2017 Dissertation Committee: Professor Amit Roy-Chowdhury, Chairperson Professor Eamonn Keogh Professor Stefano Lonardi Professor Tamar Shinar" 3bd63bea64c770df5049879f4398e65f958ebd23,Predicting an Object Location Using a Global Image Representation,"Predicting an Object Location using a Global Image Representation Jose A. Rodriguez-Serrano and Diane Larlus Computer Vision Group, Xerox Research Centre Europe" 3b410ae97e4564bc19d6c37bc44ada2dcd608552,Scalability Analysis of Audio-Visual Person Identity Verification,"Scalability Analysis of Audio-Visual Person Identity Verification Jacek Czyz1, Samy Bengio2, Christine Marcel2, and Luc Vandendorpe1 Communications Laboratory, Universit´e catholique de Louvain, B-1348 Belgium, IDIAP, CH-1920 Martigny, Switzerland" 3beb94f61b5909fca8917b0475983ea2c66f1df2,Shape model fitting algorithm without point correspondence,"0th European Signal Processing Conference (EUSIPCO 2012) © EURASIP, 2012 - ISSN 2076-1465 . INTRODUCTION" 3baa3d5325f00c7edc1f1427fcd5bdc6a420a63f,Enhancing convolutional neural networks for face recognition with occlusion maps and batch triplet loss,"Enhancing Convolutional Neural Networks for Face Recognition with Occlusion Maps and Batch Triplet Loss Daniel S´aez Triguerosa,b, Li Menga,∗, Margaret Hartnettb School of Engineering and Technology, University of Hertfordshire, Hatfield AL10 9AB, UK IDscan Biometrics (a GBG company), London E14 9QD, UK" 3ba3ef6d8394055d43bf4fe62227fbae8ab9b195,Finding images of difficult entities in the long tail,"Finding Images of Difficult Entities in the Long Tail Bilyana Taneva Max-Planck Institute for Informatics Saarbrücken, Germany Mouna Kacimi Free University of Bozen-Bolzano Italy Gerhard Weikum Max-Planck Institute for Informatics Saarbrücken, Germany" 3b304585d5af0afe98a85d6e0559315fbf3a7807,An Improved Labelling for the INRIA Person Data Set for Pedestrian Detection,"An Improved Labelling for the INRIA Person Data Set for Pedestrian Detection Matteo Taiana, Jacinto Nascimento, and Alexandre Bernardino(cid:63) Institute for Systems and Robotics, IST, Lisboa, Portugal, WWW home page: http://users.isr.ist.utl.pt/~mtaiana" 3b2acab4fc2bcf86ceaf3526c75a7a9eb01a589a,Separating conditional and unconditional cooperation in a sequential Prisoner’s Dilemma game,"RESEARCH ARTICLE Separating conditional and unconditional ooperation in a sequential Prisoner’s Dilemma game Raoul Bell*, Laura Mieth, Axel Buchner Department of Experimental Psychology, Heinrich Heine University Du¨sseldorf, Du¨sseldorf, Germany" 3b4177556f1c9f5a8f8e1b2e8d824dee20e388e4,Spatial Weighting for Bag-of-Features,"Spatial Weighting for Bag-of-Features Marcin Marsza(cid:7)ek Cordelia Schmid INRIA Rh(cid:136)one-Alpes, LEAR - GRAVIR 665 av de l’Europe, 38330 Montbonnot, France" 3b08ef7aa0cf9528da42b2b594b66e4a6f7fdb7f,Active Learning for Delineation of Curvilinear Structures,"Active Learning for Delineation of Curvilinear Structures Agata Mosinska Raphael Sznitman University of Bern Przemysław Głowacki Pascal Fua {agata.mosinska, przemyslaw.glowacki," 3b6310052026fc641d3fa639647342c45d8f5bd5,Eye Contact Modulates Cognitive Processing Differently in Children With Autism,"Child Development, xxxx 2014, Volume 00, Number 0, Pages 1–11 Eye Contact Modulates Cognitive Processing Differently in Children With Autism Terje Falck-Ytter Karolinska Institutet and Uppsala University Christoffer Carlstr€om and Martin Johansson Uppsala University In humans, effortful cognitive processing frequently takes place during social interaction, with eye contact eing an important component. This study shows that the effect of eye contact on memory for nonsocial infor- mation is different in children with typical development than in children with autism, a disorder of social ommunication. Direct gaze facilitated memory performance in children with typical development (n = 25, 6 years old), but no such facilitation was seen in the clinical group (n = 10, 6 years old). Eye tracking con- ducted during the cognitive test revealed strikingly similar patterns of eye movements, indicating that the results cannot be explained by differences in overt attention. Collectively, these findings have theoretical sig- nificance and practical implications for testing practices in children. Being looked at is a strong signal, indicating that the other person is attending to you and processing information about you. In many nonhuman species, direct gaze functions as an aversive stimulus, likely ecause of the threat value associated with eye con-" 3bc776eb1f4e2776f98189e17f0d5a78bb755ef4,View Synthesis from Image and Video for Object Recognition Applications, 3b14bdb0b1a7353d94973ef4c1578e1bd4a4e35e,Three dimensional binary edge feature representation for pain expression analysis,"Three Dimensional Binary Edge Feature Representation for Pain Expression Analysis Xing Zhang1, Lijun Yin1, Jeffrey F. Cohn2 State University of New York at Binghamton; 2University of Pittsburgh" 3b92916dd9d772cf1d167461a548115013a954a8,Unsupervised Framework for Interactions Modeling between Multiple Objects, 3b1b94441010615195a5c404409ce2416860508c,Image Captioning and Visual Question Answering Based on Attributes and External Knowledge,"MANUSCRIPT, 2016 Image Captioning and Visual Question Answering Based on Attributes nd External Knowledge Qi Wu, Chunhua Shen, Peng Wang, Anthony Dick, Anton van den Hengel" 3b557c4fd6775afc80c2cf7c8b16edde125b270e,Face recognition: Perspectives from the real world,"Face Recognition: Perspectives from the Real-World Bappaditya Mandal Institute for Infocomm Research, A*STAR, Fusionopolis Way, #21-01 Connexis (South Tower), Singapore 138632. Phone: +65 6408 2071; Fax: +65 6776 1378; E-mail:" 3b8ad690f8d43d189ea2f2559c41b6eebac8dcc8,Mobile 3D object detection in clutter,"Mobile 3D Object Detection in Clutter David Meger and James J. Little" 3b8ad1f2335fc755e5cd75ee5922b8a0d432018a,A Fast and Compact Saliency Score Regression Network Based on Fully Convolutional Network,"A Fast and Compact Saliency Score Regression Network Based on Fully Convolutional Network Xuanyang Xi, Yongkang Luo, Fengfu Li, Peng Wang and Hong Qiao" 3b15a48ffe3c6b3f2518a7c395280a11a5f58ab0,On knowledge transfer in object class recognition,"On Knowledge Transfer in Object Class Recognition A dissertation approved by TECHNISCHE UNIVERSITÄT DARMSTADT Fachbereich Informatik for the degree of Doktor-Ingenieur (Dr.-Ing.) presented by MICHAEL STARK Dipl.-Inform. orn in Mainz, Germany Prof. Dr.-Ing. Michael Goesele, examiner Prof. Martial Hebert, Ph.D., co-examiner Prof. Dr. Bernt Schiele, co-examiner Date of Submission: 12th of August, 2010 Date of Defense: 23rd of September, 2010 Darmstadt, 2010" 3b1aaac41fc7847dd8a6a66d29d8881f75c91ad5,Sparse Representation-Based Open Set Recognition,"Sparse Representation-based Open Set Recognition He Zhang, Student Member, IEEE and Vishal M. Patel, Senior Member, IEEE" 3b9ee03255eb5a0040676eead1767db431e83562,2013 Ieee Conference on Computer Vision and Pattern Recognition 2013 Ieee Conference on Computer Vision and Pattern Recognition 2013 Ieee Conference on Computer Vision and Pattern Recognition,"013 IEEE Conference on Computer Vision and Pattern Recognition 013 IEEE Conference on Computer Vision and Pattern Recognition 013 IEEE Conference on Computer Vision and Pattern Recognition 063-6919/13 $26.00 © 2013 IEEE 063-6919/13 $26.00 © 2013 IEEE 063-6919/13 $26.00 © 2013 IEEE DOI 10.1109/CVPR.2013.236 DOI 10.1109/CVPR.2013.236 DOI 10.1109/CVPR.2013.236" 3b2697d76f035304bfeb57f6a682224c87645065,ImageNet Large Scale Visual Recognition Challenge,"Noname manuscript No. (will be inserted by the editor) ImageNet Large Scale Visual Recognition Challenge Olga Russakovsky* · Jia Deng* · Hao Su · Jonathan Krause · Sanjeev Satheesh · Sean Ma · Zhiheng Huang · Andrej Karpathy · Aditya Khosla · Michael Bernstein · Alexander C. Berg · Li Fei-Fei Received: date / Accepted: date" 3b1ba9818e2ee6a54e7ec033c5b2ec8bdbe2935f,Social Signaling Descriptor for Group Behaviour Analysis,"Social Signaling Descriptor for Group Behaviour Analysis Eduardo M. Pereira1,2(B), Lucian Ciobanu1, and Jaime S. Cardoso1,2 Faculty of Engineering of the University of Porto, Rua Dr. Roberto Frias, 378, INESC TEC, Porto, Portugal 200 - 465 Porto, Portugal" 3b38dc6d4f676ace52672f6788b66c9abb10d702,Ph . D . Showcase : Measuring Terrain Distances Through Extracted Channel Networks,"Ph.D. Showcase: Measuring Terrain Distances Through Extracted Channel Networks PhD Student: Christopher Stuetzle Dept. Computer Science PhD Superviser: W. Randolph Franklin Dept. Electrical Engineering PhD Superviser: Barbara Cutler Dept. Computer Science Mehrad Kamalzare Dept. Civil Engineering Zhongxian Chen Dept. Computer Science Thomas Zimmie Dept. Civil Engineering" 3b9d94752f8488106b2c007e11c193f35d941e92,"Appearance , Visual and Social Ensembles for Face Recognition in Personal Photo Collections","#2052 CVPR 2013 Submission #2052. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. #2052 Appearance, Visual and Social Ensembles for Face Recognition in Personal Photo Collections Anonymous CVPR submission Paper ID 2052" 3b2f78a4edf5da876e52513d0e3960da7d3a253f,Qualitative Evaluation of Detection and Tracking Performance,"Qualitative Evaluation of Detection and Tracking Performance Swaminathan Sankaranarayanan, Francois Bremond, David Tax To cite this version: Swaminathan Sankaranarayanan, Francois Bremond, David Tax. Qualitative Evaluation of Detection nd Tracking Performance. 9th IEEE International Conference On Advanced Video and Signal Based Surveillance (AVSS 12), Sep 2012, Beijing, China. IEEE, pp.362-367, 2012, 2012 IEEE Ninth Inter- national Conference on Advanced Video and Signal-Based Surveillance. <10.1109/AVSS.2012.57>. HAL Id: hal-00763587 https://hal.inria.fr/hal-00763587 Submitted on 14 Dec 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents" 3bb80697a28b9876e668de2228003dbbdcb84a25,Face Recognition with semi-supervised learning and Multiple Classifiers,"Face Recognition with semi-supervised learning and Multiple Classifiers NEAMAT EL GAYAR*, SHABAN A. SHABAN† SAYED HAMDY† Institute of Statistical Studies and Research *Faculty of Computers and Information Cairo University 5 Ahmed Zewel St., 12613 Orman, Giza EGYPT" 3bfb3db230b429423dcbdc623ac55b63d038bba8,A new model for Gabor coefficients' magnitude in face recognition,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010 Γ(3β)Γ(1β)!β/2." 3b319645bfdc67da7d02db766e17a3e0a37be47b,On the relationship between visual attributes and convolutional networks,"On the Relationship between Visual Attributes and Convolutional Networks Victor Escorcia1,2, Juan Carlos Niebles2, Bernard Ghanem1 King Abdullah University of Science and Technology (KAUST), Saudi Arabia. 2Universidad del Norte, Colombia. The seminal work of Krizhevsky et al. [3] that trained a large convo- lutional network (conv-net) for image-level object recognition on the Ima- geNet challenge is considered a major stepping stone for subsequent work in onv-net based visual recognition. Such a network is able to automatically learn a hierarchy of nonlinear features that richly describe image content as well as discriminate between object classes. Recent work [4] has shown that features extracted from a conv-net trained on ImageNet are general purpose (or black-box) enough to achieve state-of-the-art results in various other recognition tasks, including scene, fine-grained, and even action recogni- tion. However, unlike hand-crafted features, those learned by a conv-net re usually not visually intuitive and straightforward to interpret. Despite their excellent recognition performance, understanding and interpreting the inner workings of conv-nets remains mostly elusive to the community. It is this lack of deep understanding that is currently motivating researchers to look under the hood and comprehend how and why these deep networks work so well in practice. Inspired by recent observations on the analysis of onv-nets [1], this paper takes another step in a similar direction, namely" 3b996a2e641be7bd395620d30364a27d1558cbad,Tracking Related Multiple Targets in Videos DISSERTATION submitted in partial fulfillment of the requirements for the degree of Doktor / in der technischen Wissenschaften,"Tracking Related Multiple Targets in Videos DISSERTATION zur Erlangung des akademischen Grades Doktor/in der technischen Wissenschaften eingereicht von Nicole M. Artner Matrikelnummer 0727746 n der Fakultät für Informatik der Technischen Universität Wien Betreuung: O.Univ.Prof. Dipl.Ing. Dr.techn. Walter G. Kropatsch Diese Dissertation haben begutachtet: (O.Univ.Prof. Dipl.Ing. Dr.techn. (Prof. Em. Dr. Horst Bunke) Walter G. Kropatsch) Wien, 10.10.2013 (Nicole M. Artner) A-1040 Wien (cid:2) Karlsplatz 13 (cid:2) Tel. +43-1-58801-0 (cid:2) www.tuwien.ac.at Technische Universität Wien" 47f8ba44fde1f8a3a621b20cabb7e84515fb8313,Superpixel-based Road Segmentation for Real-time Systems using CNN, 475de283dad61a8a9ed231dce0d8d62a54f4d062,Person Following by Autonomous Robots: A Categorical Overview,"Islam et al. Person Following by Autonomous Robots: A Categorical Overview Md Jahidul Islam, Jungseok Hong and Junaed Sattar Preprint Version I XX(X):1–25 (cid:13)The Author(s) 2018 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/ToBeAssigned www.sagepub.com/" 474b6593d37c9c6547e2f0fcbfa8a9866b5cccd6,The Iteration-Tuned Dictionary for sparse representations,"The Iteration-Tuned Dictionary for Sparse Representations Joaquin Zepeda #1, Christine Guillemot #2, Ewa Kijak ∗3 # INRIA Centre Rennes - Bretagne Atlantique Campus de Beaulieu, 35042 Rennes Cedex, FRANCE Universit´e de Rennes 1, IRISA Campus de Beaulieu, 35042 Rennes Cedex, FRANCE" 47be79c0ecb598e1af44e57f386f79adf491f82b,Scenes categorization based on appears objects probability,"016 IEEE 6th International Conference on System Engineering and Technology (ICSET) Oktober 3-4, 2016 Bandung – Indonesia Scenes Categorization based on Appears Objects Probability Marzuki1, Egi Muhamad Hidayat2, Rinaldi Munir3, Ary Setijadi P4 ,Carmadi Machbub5 School of Electrical Engineering and Informatics, Institut Teknologi Bandung Bandung, Indonesia lskk.ee.itb.ac.id" 47719d391417a237701c5e275ebb1034418e20f2,Human Face Processing with 1.5D Models,"Human Face Processing with 1.5D Models Gin´es Garc´ıa-Mateos1, Alberto Ruiz1, and Pedro E. L´opez-de-Teruel2 Dept. de Inform´atica y Sistemas Dept. Ing. y Tecn. de Computadores Universidad de Murcia, 30.100 Espinardo, Murcia, Spain" 47c0c7f1a27d467e00a6fa7ea2ca0af2e3328b9e,Predicting Scene Parsing and Motion Dynamics in the Future,"Predicting Scene Parsing and Motion Dynamics in the Future Xiaojie Jin1, Huaxin Xiao2, Xiaohui Shen3, Jimei Yang3, Zhe Lin3 Yunpeng Chen2, Zequn Jie4, Jiashi Feng2, Shuicheng Yan5,2 NUS Graduate School for Integrative Science and Engineering (NGS), NUS Department of ECE, NUS Adobe Research Tencent AI Lab 5Qihoo 360 AI Institute" 474b461cd12c6d1a2fbd67184362631681defa9e,Multi-resolution fusion of DTCWT and DCT for shift invariant face recognition,"014 IEEE International Conference on Systems, Man nd Cybernetics (SMC 2014) San Diego, California, USA 5-8 October 2014 Pages 1-789 IEEE Catalog Number: ISBN: CFP14SMC-POD 978-1-4799-3841-4" 47bc34ae6f5dc104bc289ae3bb4fa75ef75fbc21,Unsupervised Deep Learning for Optical Flow Estimation,"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) Unsupervised Deep Learning for Optical Flow Estimation Zhe Ren,1 Junchi Yan,2,3∗ Bingbing Ni,1 Bin Liu,4 Xiaokang Yang,1 Hongyuan Zha5 Shanghai Jiao Tong University 2East China Normal University 3IBM Research 4Moshanghua Tech 5Georgia Tech" 4753a125469da7649e9f58fb0db781622dff41f8,Single-View Semantic Mesh Refinement,"Multi-View Stereo with Single-View Semantic Mesh Refinement Andrea Romanoni Marco Ciccone Francesco Visin Matteo Matteucci {andrea.romanoni, marco.ciccone, francesco.visin, Politecnico di Milano, Italy" 47fc921add1421ff8adb730df7aa9e7f865bfdeb,Toward Practical Smile Detection,"Towards Practical Smile Detection Jacob Whitehill, Gwen Littlewort, Ian Fasel, Marian Bartlett, and Javier Movellan" 47e8db3d9adb79a87c8c02b88f432f911eb45dc5,MAGMA: Multilevel Accelerated Gradient Mirror Descent Algorithm for Large-Scale Convex Composite Minimization,"MAGMA: Multi-level accelerated gradient mirror descent algorithm for large-scale convex composite minimization Vahan Hovhannisyan Panos Parpas Stefanos Zafeiriou July 15, 2016" 47e225ad6293ebd589c3c1268bcb70730cfeb8f6,Unsupervised Video Indexing based on Audiovisual Characterization of Persons. (Indexation vidéo non-supervisée basée sur la caractérisation des personnes),"TTHHÈÈSSEE En vue de l'obtention du DDOOCCTTOORRAATT DDEE LL’’UUNNIIVVEERRSSIITTÉÉ DDEE TTOOUULLOOUUSSEE Délivré par l'Université Toulouse III - Paul Sabatier Discipline ou spécialité : Science Informatique Présentée et soutenue par EL-KHOURY Elie Le 3 juin 2010 Titre : Unsupervised video indexing based on audiovisual characterization of persons Shih-Fu CHANG…………….…………………Columbia University, United States of America Bernard MERIALDO……………………………………….…………..……………………Eurocom, France Sylvain MEIGNIER………………………………………………..….University of Le Maine, France Rémi LANDAIS………………………………………………………………………………..…Exalead, France Philippe JOLY…………………………………………………………University of Toulouse III, France Christine SENAC……………………………………………………University of Toulouse III, France Ecole doctorale : Mathématiques, Informatique, Télécommunications de Toulouse Unité de recherche : I.R.I.T. --- UMR 5505 Directeur(s) de Thèse : Régine ANDRE-OBRECHT………University of Toulouse III, France" 477236563c6a6c6db922045453b74d3f9535bfa1,Attribute Based Image Search Re-Ranking Snehal,"International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013): 6.14 | Impact Factor (2014): 5.611 Attribute Based Image Search Re-Ranking Snehal S Patil1, Ajay Dani2 Master of Computer Engg, Savitribai Phule Pune University, G. H. Raisoni Collage of Engg and Technology, Wagholi, Pune 2Professor, Computer and Science Dept, Savitribai Phule Pune University, G. H .Raisoni Collage of Engg and Technology, Wagholi, Pune integrating images by" 4707175ebc50e4036412f441a7cec6673c4ad31f,Analysis and Comparison of Eigenspace-Based Face Recognition Approaches,"Analysis and Comparison of Eigenspace-based Face Recognition Approaches Pablo Navarrete and Javier Ruiz-del-Solar Department of Electrical Engineering, Universidad de Chile, CHILE Email: {pnavarre," 479f44f9b4c401327a721550334b8d491f6b3f16,OR-PCA with MRF for Robust Foreground Detection in Highly Dynamic Backgrounds,"OR-PCA with MRF for Robust Foreground Detection in Highly Dynamic Backgrounds Sajid Javed1, Seon Ho Oh1, Andrews Sobral2, Thierry Bouwmans2 and Soon Ki Jung1 School of Computer Science and Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu,Daegu, 702-701, Republic of Korea {sajid, Laboratoire MIA (Mathematiques, Image et Applications)- Universit´e de La Rochelle, 17000, France, {andrews.sobral," 47980c6e42f1a3381e6c5f3db7230e6a64c40218,Finding People in Images and Videos,"INSTITUTNATIONALPOLYTECHNIQUEDEGRENOBLENum´eroattribu´eparlabiblioth`equeTH`ESEpourobtenirlegradedeDOCTEURDEL’INSTITUTNATIONALPOLYTECHNIQUEDEGRENOBLESp´ecialit´e:Imagerie,VisionetRobotiquedanslecardedel’´EcoleDoctoraleMath´ematiques,SciencesetTechnologiedel’Informationpr´esent´eeetsoutenuepubliquementparNavneetDALALle17Juillet,2006FindingPeopleinImagesandVideosJURYM.JamesL.CROWLEYPr´esidentM.MartialHEBERTRapporteurM.LucVanGOOLRapporteurM.ShaiAVIDANExaminateurMme.CordeliaSCHMIDDirecteurdeth`eseM.WilliamJ.TRIGGSDirecteurdeth`eseTh`esepr´epar´eedanslelaboratoireGRAVIR–IMAGauseinduProjetLEAR,INRIARhˆone-Alpes655avenuedel’Europe,38334SaintIsmier,France." 47f2088afb616bde5468818e23d79e1ae5a562cd,Multi-view gender classification based on local Gabor binary mapping pattern and support vector machines,"Multi-view Gender Classification based on Local Gabor Binary Mapping Pattern and Support Vector Machines Bin Xia, He Sun and Bao-Liang Lu∗ Senior Member, IEEE" 470b89e2c5248eb58e09129aa9b4d8bc77497e7e,Cortical folding abnormalities in autism revealed by surface-based morphometry.,"The Journal of Neuroscience, October 24, 2007 • 27(43):11725–11735 • 11725 Neurobiology of Disease Cortical Folding Abnormalities in Autism Revealed by Surface-Based Morphometry Christine Wu Nordahl,1 Donna Dierker,2 Iman Mostafavi,1 Cynthia M. Schumann,1,3 Susan M. Rivera,4 David G. Amaral,1 and David C. Van Essen2 The Medical Investigation of Neurodevelopmental Disorders (M.I.N.D.) Institute and the Department of Psychiatry and Behavioral Sciences, University of California, Davis, Sacramento, California 95817, 2Department of Anatomy and Neurobiology, Washington University in St. Louis, St. Louis, Missouri 63110, Department of Neurosciences, University of California, San Diego, La Jolla, California 92093, and 4The M.I.N.D. Institute and the Department of Psychology, University of California, Davis, Davis, California 95616 We tested for cortical shape abnormalities using surface-based morphometry across a range of autism spectrum disorders (7.5–18 years of age). We generated sulcal depth maps from structural magnetic resonance imaging data and compared typically developing controls to three autism spectrum disorder subgroups: low-functioning autism, high-functioning autism, and Asperger’s syndrome. The low- functioning autism group had a prominent shape abnormality centered on the pars opercularis of the inferior frontal gyrus that was ssociated with a sulcal depth difference in the anterior insula and frontal operculum. The high-functioning autism group had bilateral shape abnormalities similar to the low-functioning group, but smaller in size and centered more posteriorly, in and near the parietal operculum and ventral postcentral gyrus. Individuals with Asperger’s syndrome had bilateral abnormalities in the intraparietal sulcus that correlated with age, intelligence quotient, and Autism Diagnostic Interview-Revised social and repetitive behavior scores. Because of evidence suggesting age-related differences in the developmental time course of neural alterations in autism, separate analyses on hildren (7.5–12.5 years of age) and adolescents (12.75–18 years of age) were also carried out. All of the cortical shape abnormalities" 47096e7103a2fbb6f6ede05e996209497d41db6a,Implementation of Artificial Intelligence Methods for Virtual Reality Solutions: a Review of the Literature,"Implementation of Artificial Intelligence Methods for Virtual Reality Solutions: a Review of the Literature Rytis Augustauskas Department of Automation Aurimas Kudarauskas Department of Automation Kaunas University of Technology, Kaunas University of Technology, Kaunas, Lithuania Kaunas, Lithuania Cenker Canbulut Department of Multimedia Engineering Kaunas University of Technology, Kaunas, Lithuania" 4701112bfe9946a97a60c2bbb2d47dc784942c3f,Understanding classifier errors by examining influential neighbors,"Understanding Classifier Errors by Examining Influential Neighbors Mayank Kabra, Alice Robie, Kristin Branson Janelia Research Campus of the Howard Hughes Medical Institute Ashburn, VA, 20147, USA" 47440f514318b438ebf04d9932f5dafdb488a536,EMOTION RECOGNITION FROM FACIAL IMAGES USING BINARY FACE RELEVANCE MAPS,"STUDIA INFORMATICA Volume 36 Number 4 (122) Tomasz HERUD, Michal KAWULOK Silesian University of Technology, Institute of Informatics Future Processing, Gliwice, Poland Bogdan SMOLKA Silesian University of Technology, Institute of Automatic Control EMOTION RECOGNITION FROM FACIAL IMAGES USING BINARY FACE RELEVANCE MAPS1 Summary. This paper is focused on automatic emotion recognition from static grayscale images. Here, we propose a new approach to this problem, which combines few other methods. The facial region is divided into small subregions, which are selected for processing based on a face relevance map. From these regions, local directional pattern histograms are extracted and concatenated into a single feature histogram, which is classified into one of seven defined emotional states using support vector machines. In our case, we distinguish: anger, disgust, fear, happiness, neutrality, sadness and surprise. In our experimental study we demonstrate that the expression recognition accuracy for Japanese Female Facial Expression database is one of the best compared with the results reported in the literature." 47ca2df3d657d7938d7253bed673505a6a819661,UNIVERSITY OF CALIFORNIA Santa Barbara Facial Expression Analysis on Manifolds A Dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy,"UNIVERSITY OF CALIFORNIA Santa Barbara Facial Expression Analysis on Manifolds A Dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Computer Science Ya Chang Committee in charge: Professor Matthew Turk, Chair Professor Yuan-Fang Wang Professor B.S. Manjunath Professor Andy Beall September 2006" 47f5f740e225281c02c8a2ae809be201458a854f,Simultaneous Unsupervised Learning of Disparate Clusterings,"Simultaneous Unsupervised Learning of Disparate Clusterings Prateek Jain*, Raghu Meka and Inderjit S. Dhillon Department of Computer Sciences, University of Texas, Austin, TX 78712-1188, USA Received 14 April 2008; accepted 05 May 2008 DOI:10.1002/sam.10007 Published online 3 November 2008 in Wiley InterScience (www.interscience.wiley.com)." 47a567ef9d049e5775ffd005f9d74e6aab108f82,A Survey of Automatic Event Detection in Multi-Camera Third Generation Surveillance Systems,"3:40 WSPC/INSTRUCTION International Journal of Pattern Recognition and Artificial Intelligence (cid:176) World Scientific Publishing Company A survey of automatic event detection in multi-camera third generation surveillance systems Tiziana D’Orazio Institute of Intelligent Systems for Automation - C.N.R. via Amendola 122/D-I Bari, 70126,ITALY Cataldo Guaragnella Politecnico di Bari, Via Orabona 4, Bari, 70126, IATLY Third generation surveillance systems are largely requested for intelligent surveillance of different scenarios such as public areas, urban traf‌f‌ic control, smart homes and so on. They are based on multiple cameras and processing modules that integrate data oming from a large surveillance space. The semantic interpretation of data from a multi view context is a challenging task and requires the development of image processing methodologies that could support applications in extensive and real time contexts. This paper presents a survey of automatic event detection functionalities that have been developed for third generation surveillance systems with a particular emphasis on open problems that limit the application of computer vision methodologies to commercial" 47ce78c9f49248a7d1bd395befb43e45d89555ee,Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments,"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments Peter Anderson1 Niko S¨underhauf3 Qi Wu2 Damien Teney2 Jake Bruce3 Mark Johnson4 Ian Reid2 Stephen Gould1 Anton van den Hengel2 Australian National University 2University of Adelaide 3Queensland University of Technology 4Macquarie University" 47fdd1579f732dd6389f9342027560e385853180,Deep Sparse Subspace Clustering,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Deep Sparse Subspace Clustering Xi Peng, Jiashi Feng, Shijie Xiao, Jiwen Lu Senior Member, IEEE, Zhang Yi Fellow, IEEE, Shuicheng Yan Fellow, IEEE," 47e3029a3d4cf0a9b0e96252c3dc1f646e750b14,Facial expression recognition in still pictures and videos using active appearance models: a comparison approach,"International Conference on Computer Systems and Technologies - CompSysTech’07 Facial Expression Recognition in still pictures and videos using Active Appearance Models. A comparison approach. Drago(cid:1) Datcu Léon Rothkrantz" 478261574ddc6cf297611000735aa9808f8f0030,ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes, 47541d04ec24662c0be438531527323d983e958e,Affective Information Processing,Affective Information Processing 47b34a8ad5100582aa7cbfd85df3ca7659adc392,Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world,"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 1403–1414, Baltimore, Maryland, USA, June 23-25 2014. c(cid:13)2014 Association for Computational Linguistics" 478a1ed7dc1890ca9476dcc1befe7f21c9bf9149,Learning to Learn from Noisy Labeled Data,"Learning to Learn from Noisy Labeled Data Junnan Li, Yongkang Wong, Qi Zhao, Mohan S. Kankanhalli" 474d9967b69f9afd5404686f16c8f53c1951526b,"Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images","Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images Iljoo Baek∗, Albert Davies∗, Geng Yan, and Ragunathan (Raj) Rajkumar" 99302fc2bc72ff166fe41e1614df606120b2f1b7,Combining passive visual cameras and active IMU sensors to track cooperative people,"Combining Passive Visual Cameras and Active IMU Sensors to Track Cooperative People Wenchao Jiang Missouri University of Science and Technology, Mo, USA, 65401 Email: Zhaozheng Yin Missouri University of Science and Technology, Mo, USA, 65401 Email:" 99ae92bae7c873432a6a60238b33d494bbae13eb,RECOGNITION OF HUMAN POSE FROM IMAGES BASED ON GRAPH SPECTRA,"RECOGNITION OF HUMAN POSE FROM IMAGES BASED ON GRAPH SPECTRA A. A. Zakharov a *, A. E. Barinov a, A. L. Zhiznyakov a Murom Institut Vladimir State University, CAD Department, , 602264, Orlovskaya 23, Murom, Russian Federation, aa- Commission VI, WG VI/4 KEY WORDS: Image Recognition, Human Pose, Spectral Graph Matching" 99f565df31ef710a2d8a1b606e3b7f5f92ab657c,Geometry Score: A Method For Comparing Generative Adversarial Networks,"Geometry Score: A Method For Comparing Generative Adversarial Networks Valentin Khrulkov 1 Ivan Oseledets 1 2" 99d7678039ad96ee29ab520ff114bb8021222a91,Political image analysis with deep neural networks,"Political image analysis with deep neural networks L. Jason Anastasopoulos∗ Shiry Ginosar§. Dhruvil Badani† Jake Ryland Williams¶ Crystal Lee‡ November 28, 2017" 998f2cfb4a3bac6b38d8a4a96a3827e06a0eaadb,Geo-Supervised Visual Depth Prediction,"Geo-Supervised Visual Depth Prediction Xiaohan Fei Alex Wong Stefano Soatto" 998e829cc72080c88a780f322d6bf7ab78dbd743,Towards Real-Time Multiresolution Face/Head Detection,"´AAAAAAAAAAAAAAAAAAAAAAAA ´AAAAAAAAAAAAAAAAAAAAAAAA ART´ICULO Towards Real-Time Multiresolution Face/Head Detection* M. Castrill´on-Santana, H. Kruppa**, C. Guerra-Artal, M. Hern´andez-Tejera Universidad de Las Palmas de Gran Canaria Instituto Universitario de Sistemas Inteligentes y Aplicaciones Num´ericas en Ingenier´ıa Edificio Central del Parque Cient´ıfico-Tecnol´ogico Campus Universitario de Tafira 5017 Las Palmas - Espa˜na" 9974a806bb69ed26fb8cf49ebdd53d7756336eec,Object Recognition Using Multiresolution Trees,"Object recognition using Multiresolution trees Monica Bianchini, Marco Maggini, and Lorenzo Sarti DII - Universit`a degli Studi di Siena Via Roma, 56 - 53100 Siena - Italy Email:" 994f7c469219ccce59c89badf93c0661aae34264,Model Based Face Recognition Across Facial Expressions,"Model Based Face Recognition Across Facial Expressions Zahid Riaz, Christoph Mayer, Matthias Wimmer, and Bernd Radig, Senior Member, IEEE screens, embedded into mobiles and installed into everyday living and working environments they become valuable tools for human system interaction. A particular important aspect of this interaction is detection and recognition of faces and interpretation of facial expressions. These capabilities are deeply rooted in the human visual system and a crucial uilding block for social interaction. Consequently, these apabilities are an important step towards the acceptance of many technical systems. trees as a classifier lies not only" 9900be092f81547ad71e4124cd850048e1969063,3 D Face Analysis for Facial Expression Recognition,"Author manuscript, published in ""20th International Conference on Pattern Recognition (ICPR 2010), Istanbul : Turquie (2010)""" 99c20eb5433ed27e70881d026d1dbe378a12b342,Semi-Supervised and Unsupervised Data Extraction Targeting Speakers: From Speaker Roles to Fame?,"ISCA Archive http://www.isca-speech.org/archive First Workshop on Speech, Language nd Audio in Multimedia Marseille, France August 22-23, 2013 Proceedings of the First Workshop on Speech, Language and Audio in Multimedia (SLAM), Marseille, France, August 22-23, 2013." 99ced8f36d66dce20d121f3a29f52d8b27a1da6c,Organizing Multimedia Data in Video Surveillance Systems Based on Face Verification with Convolutional Neural Networks,"Organizing Multimedia Data in Video Surveillance Systems Based on Face Verification with Convolutional Neural Networks Anastasiia D. Sokolova, Angelina S. Kharchevnikova, Andrey V. Savchenko National Research University Higher School of Economics, Nizhny Novgorod, Russian Federation" 9993f1a7cfb5b0078f339b9a6bfa341da76a3168,"A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image","JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image Ruiqi Zhao, Yan Wang, Aleix M. Martinez" 9963af1199679e176f0836e6d63572b3a69fa7da,23 Generating Facial Expressions with Deep Belief Nets,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,500 08,000 .7 M Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact" 9990e0b05f34b586ffccdc89de2f8b0e5d427067,Auto-Optimized Multimodal Expression Recognition Framework Using 3 D Kinect Data for ASD Therapeutic Aid,"International Journal of Modeling and Optimization, Vol. 3, No. 2, April 2013 Auto-Optimized Multimodal Expression Recognition Framework Using 3D Kinect Data for ASD Therapeutic Amira E. Youssef, Sherin F. Aly, Ahmed S. Ibrahim, and A. Lynn Abbott regarding emotion recognize" 99e1ab1fb08af137cad6efbc0454c6e1e68dca51,3D human action recognition and motion analysis using selective representations,"D HUMAN ACTION RECOGNITION AND MOTION ANALYSIS USING SELECTIVE REPRESENTATIONS D LEIGHTLEY PhD 2015" 99582ce8439dce17d9d6f74eb54fc5c89dbe06d9,"Hough Forests for Object Detection, Tracking, and Action Recognition","Hough Forests for Object Detection, Tracking, nd Action Recognition Juergen Gall Member, IEEE, Angela Yao, Nima Razavi, Luc Van Gool Member, IEEE, and Victor Lempitsky" 9941a408ae031d1254bbc0fe7a63fac5f85fe347,Neural Processes,"Neural Processes Marta Garnelo 1 Jonathan Schwarz 1 Dan Rosenbaum 1 Fabio Viola 1 Danilo J. Rezende 1 S. M. Ali Eslami 1 Yee Whye Teh 1" 99df887213407f612c1f5df502b637709a29cd6b,Ensembles of exemplar-SVMs for video face recognition from a single sample per person,"Ensembles of Exemplar-SVMs for Video Face Recognition from a Single Sample Per Person Saman Bashbaghi, Eric Granger, Robert Sabourin Guillaume-Alexandre Bilodeau Laboratoire d’imagerie de vision et d’intelligence artificielle LITIV Lab École de technologie supérieure, Université du Québec, Montréal, Canada Polytechnique Montréal, Montréal, Canada {eric.granger," 99a3a4151abbc2e5d33d4beec88dc55a057df299,DISCRETE SCALAR DATA,"TOPOLOGICAL ANALYSIS OF DISCRETE SCALAR DATA DAVID GÜNTHER DISSERTATION ZUR ERLANGUNG DES GRADES DES DOKTORS DER INGENIEURWISSENSCHAFTEN DER NATURWISSENSCHAFTLICH-TECHNISCHEN FAKULTÄTEN DER UNIVERSITÄT DES SAARLANDES SAARBRÜCKEN, 2012" 992ebd81eb448d1eef846bfc416fc929beb7d28b,Exemplar-Based Face Parsing Supplementary Material,"Exemplar-Based Face Parsing Supplementary Material Brandon M. Smith Li Zhang Jonathan Brandt Zhe Lin Jianchao Yang University of Wisconsin–Madison Adobe Research http://www.cs.wisc.edu/~lizhang/projects/face-parsing/ . Additional Selected Results Figures 1 and 2 supplement Figure 4 in our paper. In all cases, the input images come from our Helen [1] test set. We note that our algorithm generally produces accurate results, as shown in Figures 1. However, our algorithm is not perfect and makes mistakes on especially challenging input images, as shown in Figure 2. In our view, the mouth is the most challenging region of the face to segment: the shape and appearance of the lips vary widely from subject to subject, mouths deform significantly, and the overall appearance of the mouth region changes depending on whether the inside of the mouth is visible or not. Unusual mouth expressions, like those shown in Figure 2, are not repre- sented well in the exemplar images, which results in poor label transfer from the top exemplars to the test image. Despite these hallenges, our algorithm generally performs well on the mouth, with large segmentation errors occurring infrequently. . Comparisons with Liu et al. [2] The scene parsing approach by Liu et al. [2] shares sevaral similarities with our work. Like our approach, they propose a nonparametric system that transfers labels from exemplars in a database to annotate a test image. This begs the question, Why not simply apply the approach from Liu et al. to face images?" 9922a2ec8dfb307bb1fcb334098fd912e23b3bab,Particle-based pedestrian path prediction using LSTM-MDL models,"Particle-based Pedestrian Path Prediction using LSTM-MDL Models Ronny Hug∗, Stefan Becker∗, Wolfgang H¨ubner∗ and Michael Arens∗" 99227909e5733d76b0d50fc3fab975ab7a43fce3,A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation,"A Cascaded Inception of Inception Network with Attention Modulated Feature Fusion for Human Pose Estimation Submission ID: 2065" 998b7c8608fb9f80177ce54230761d8c3d82b2da,SHEF-Multimodal: Grounding Machine Translation on Images,"Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers, pages 660–665, Berlin, Germany, August 11-12, 2016. c(cid:13)2016 Association for Computational Linguistics" 99246f998a684879038f39583bcf75b8f218e0a3,Object Detection for Autonomous Driving Using Deep Learning,"UNIVERSITAT POLITÈCNICA DE CATALUNYA Doctoral Programme: AUTOMÀTICA, ROBÒTICA I VISIÓ Research Plan: Object Detection for Autonomous Driving Using Deep Learning Victor Vaquero Gomez Advisors: Alberto Sanfeliu Cortes, Prof. Francesc Moreno Noguer, Dr. December 2015" 99e1fd6a378209d48c12a70229e4f6d4d83f4417,Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs,"Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using Patrick Wenzel1,2∗ , Qadeer Khan1,2∗ , Daniel Cremers1,2, and Laura Leal-Taixé1 Technical University of Munich Artisense" 29bd7de310438c2b9d8b6e7eb7df662079934747,Semantic Scene Mapping with Spatio-temporal Deep Neural Network for Robotic Applications,"Cogn Comput https://doi.org/10.1007/s12559-017-9526-9 Semantic Scene Mapping with Spatio-temporal Deep Neural Network for Robotic Applications Ruihao Li1 · Dongbing Gu1 · Qiang Liu1 · Zhiqiang Long2 · Huosheng Hu1 Received: 25 September 2017 / Accepted: 31 October 2017 © Springer Science+Business Media, LLC, part of Springer Nature 2017" 29933de38d72a0941d763b7ac5a480e733ef74a2,Set Logo Detection and Retrieval,"Open Set Logo Detection and Retrieval Andras T¨uzk¨o1, Christian Herrmann1,2, Daniel Manger1, J¨urgen Beyerer1,2 Fraunhofer IOSB, Karlsruhe, Germany Karlsruhe Institute of Technology KIT, Vision and Fusion Lab, Karlsruhe, Germany Keywords: Logo Detection, Logo Retrieval, Logo Dataset, Trademark Retrieval, Open Set Retrieval, Deep Learning." 2903630d9582172f38108dc171fd239e337654a7,Deep Face Image Retrieval: a Comparative Study with Dictionary Learning,"Deep Face Image Retrieval: a Comparative Study with Dictionary Learning Ahmad S. Tarawneh1, Ahmad B. A. Hassanat2, Ceyhun Celik3, Dmitry Chetverikov1, M. Sohel Rahman4 and Chaman Verma1 Department of Algorithms and Their Applications , Eötvös Loránd University, Budapest, Hungary Department of Information Technology, Mutah University, Karak, Jordan Department of Computer Engineering, Gazi University, Ankara, Turkey Department of CSE, BUET, ECE Building, West Palasi, Dhaka 1205, Bangladesh December 14, 2018" 2939169aed69aa2626c5774d9b20e62c905e479b,Fast Exact HyperGraph Matching with Dynamic Programming for Spatio-Temporal Data,"Fast Exact Hyper-Graph Matching with Dynamic Programming for Spatio-Temporal Data Oya Celiktutan, Christian Wolf, Bülent Sankur, Eric Lombardi To cite this version: Oya Celiktutan, Christian Wolf, Bülent Sankur, Eric Lombardi. Fast Exact Hyper-Graph Matching with Dynamic Programming for Spatio-Temporal Data. Journal of Mathematical Imaging and Vision, Springer Verlag, 2015, 51, pp.1-21. HAL Id: hal-01151755 https://hal.archives-ouvertes.fr/hal-01151755 Submitted on 13 May 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 29c6b06ac98dbdaf25e4cc9a05b4ab314923cccd,Assessment of the communicative and coordination skills of children with Autism Spectrum Disorders and typically developing children using social signal processing,"Research in Autism Spectrum Disorders 7 (2013) 741–756 Contents lists available at SciVerse ScienceDirect Research in Autism Spectrum Disorders J o u r n a l h o m e p a g e : h t t p : / / e e s . e l s e v i e r . c o m / R A S D / d e f a u l t . a s p Assessment of the communicative and coordination skills of hildren with Autism Spectrum Disorders and typically developing children using social signal processing Emilie Delaherche a, Mohamed Chetouani a, Fabienne Bigouret b,c, Jean Xavier c, Monique Plaza a, David Cohen a,c,* Institute of Intelligent Systems and Robotics, University Pierre and Marie Curie, 75005 Paris, France University of Paris 8, 93526 Saint-Denis, France Department of Child and Adolescent Psychiatry, Hoˆpital de la Pitie´-Salpeˆtrie`re, University Pierre and Marie Curie, 75013 Paris, France A R T I C L E I N F O A B S T R A C T Article history: Received 27 November 2012 Received in revised form 5 February 2013 Accepted 8 February 2013 Keywords:" 2962f226b658b13c358695bcd1f403133afa19ed,Optical Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation,"Highly Accurate Large Displacement Optical Flow Estimation Christian Bailer, Bertram Taetz and Didier Stricker" 29f46586c95af2fa6326724c867aa88b55b5400e,Failure Prediction for Autonomous Driving,"Failure Prediction for Autonomous Driving Simon Hecker1, Dengxin Dai1, and Luc Van Gool1,2" 29a46aed79df53a1984ee755bed4c8ba2ae94040,Multiple Object Tracking Using K-Shortest Paths Optimization,"Multiple Object Tracking using K-Shortest Paths Optimization J´erˆome Berclaz, Franc¸ois Fleuret, Engin T¨uretken, and Pascal Fua, Senior Member, IEEE" 29a705a5fa76641e0d8963f1fdd67ee4c0d92d3d,SCface – surveillance cameras face database,"Multimed Tools Appl (2011) 51:863–879 DOI 10.1007/s11042-009-0417-2 SCface – surveillance cameras face database Mislav Grgic & Kresimir Delac & Sonja Grgic Published online: 30 October 2009 # Springer Science + Business Media, LLC 2009" 290c8196341bbac80efc8c89af5fc60e1b8c80e6,Learning deep representations by mutual information estimation and maximization,"Learning deep representations by mutual information estimation and maximization R Devon Hjelm MSR Montreal, MILA, UdeM, IVADO Alex Fedorov MRN, UNM Samuel Lavoie-Marchildon MILA, UdeM Karan Grewal U Toronto Phil Bachman MSR Montreal Adam Trischler MSR Montreal Yoshua Bengio MILA, UdeM, IVADO, CIFAR" 295d978cf47c873936ad774169cac651ea5f3c96,Monocular Depth Prediction using Generative Adversarial Networks,"018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops Monocular Depth Prediction using Generative Adversarial Networks Arun CS Kumar Suchendra M. Bhandarkar The University of Georgia Mukta Prasad Trinity College Dublin" 292eba47ef77495d2613373642b8372d03f7062b,Deep Secure Encoding: An Application to Face Recognition,"Deep Secure Encoding: An Application to Face Recognition Rohit Pandey Yingbo Zhou Venu Govindaraju" 29d94f275b1483f575c05b90464994ecfa86e27f,A Passive Learning Sensor Architecture for Multimodal Image Labeling: An Application for Social Robots,"Article A Passive Learning Sensor Architecture for Multimodal Image Labeling: An Application for Social Robots Marco A. Gutiérrez 1,*, Luis J. Manso 1, Harit Pandya 2 and Pedro Núñez 1 Robotics and Artificial Vision Laboratory, University of Extremadura, 10003 Cáceres, Spain; (L.J.M.); (P.N.) Robotics Research Center, IIIT Hyderabad, 500032 Hyderabad, India; * Correspondence: Tel.: +34-927-257-259 Academic Editor: Vittorio M. N. Passaro Received: 21 December 2016; Accepted: 8 February 2017; Published: 11 February 2017" 291be6e3027575287c24f4363e4bf7a8b415d4c1,MSER-Based Real-Time Text Detection and Tracking,"To appear in the proceedings of the 2014 International Conference on Pattern Recognition. MSER-based Real-Time Text Detection and Tracking Llu´ıs G´omez and Dimosthenis Karatzas Computer Vision Center Universitat Aut`onoma de Barcelona Email:" 2988f24908e912259d7a34c84b0edaf7ea50e2b3,A Model of Brightness Variations Due to Illumination Changes and Non-rigid Motion Using Spherical Harmonics,"A Model of Brightness Variations Due to Illumination Changes and Non-rigid Motion Using Spherical Harmonics Jos´e M. Buenaposada Alessio Del Bue Dep. Ciencias de la Computaci´on, U. Rey Juan Carlos, Spain http://www.dia.fi.upm.es/~pcr Inst. for Systems and Robotics Inst. Superior T´ecnico, Portugal http://www.isr.ist.utl.pt/~adb Enrique Mu˜noz Facultad de Inform´atica, U. Complutense de Madrid, Spain Luis Baumela Dep. de Inteligencia Artificial, U. Polit´ecnica de Madrid, Spain http://www.dia.fi.upm.es/~pcr http://www.dia.fi.upm.es/~pcr" 2965d092ed72822432c547830fa557794ae7e27b,Improving representation and classification of image and video data for surveillance applications,"Improving Representation and Classification of Image and Video Data for Surveillance Applications Andres Sanin BSc(Biol), MSc(Biol), MSc(CompSc) A thesis submitted for the degree of Doctor of Philosophy at The University of Queensland in 2012 School of Information Technology and Electrical Engineering" 2914a20df10f3bb55c5d4764ece85101c1a3e5a8,User interest profiling using tracking-free coarse gaze estimation,"User Interest Profiling Using Tracking-free Coarse Gaze Estimation Federico Bartoli, Giuseppe Lisanti, Lorenzo Seidenari, Alberto Del Bimbo Media Integration and Communication Center Universit`a degli Studi di Firenze Firenze, Italy" 29633712a36c3efc77ce3a9844a2e9a029daf310,AdaBoost for Parking Lot Occupation Detection,"AdaBoost for Parking Lot Occupation Detection Radovan Fusek1, Karel Mozdˇreˇn1, Milan ˇSurkala1 and Eduard Sojka1" 2903b8f45b3fafc26c8416eae0ba264f5b76d8ef,Interactive and life-long learning for identification and categorization tasks,"Stephan Kirstein Interactive and life-long learning for identification nd categorization tasks" 29d414bfde0dfb1478b2bdf67617597dd2d57fc6,Perfect histogram matching PCA for face recognition,"Multidim Syst Sign Process (2010) 21:213–229 DOI 10.1007/s11045-009-0099-y Perfect histogram matching PCA for face recognition Ana-Maria Sevcenco · Wu-Sheng Lu Received: 10 August 2009 / Revised: 21 November 2009 / Accepted: 29 December 2009 / Published online: 14 January 2010 © Springer Science+Business Media, LLC 2010" 29107badb19e7c5c89f57f81f50df08422e53304,Automatic localisation and segmentation of the Left Ventricle in Cardiac Ultrasound Images,"MASTER THESIS Automatic localisation and segmentation of the Left Ventricle in Cardiac Ultrasound Images Presented by: Esther PUYOL IG 3A F4B and MR 2A SISEA 013/2014 Supervisor: Paolo PIRO Academic supervisor: Guy CAZUGUEL MEDISYS - PHILIPS RESEARCH PARIS Company: University: TELECOM BRETAGNE 7th March - 12th September 2014" 29230bbb447b39b7fc3de7cb34b313cc3afe0504,Face Detection and Recognition Using Maximum Likelihood Classifiers on Gabor Graphs,"SPI-J068 00721 International Journal of Pattern Recognition nd Artificial Intelligence Vol. 23, No. 3 (2009) 433–461 (cid:1) World Scientific Publishing Company FACE DETECTION AND RECOGNITION USING MAXIMUM LIKELIHOOD CLASSIFIERS ON GABOR GRAPHS MANUEL G ¨UNTHER and ROLF P. W ¨URTZ Institut f¨ur Neuroinformatik Ruhr-Universit¨at Bochum D–44780 Bochum, Germany We present an integrated face recognition system that combines a Maximum Likelihood (ML) estimator with Gabor graphs for face detection under varying scale and in-plane rotation and matching as well as a Bayesian intrapersonal/extrapersonal classifier (BIC) on graph similarities for face recognition. We have tested a variety of similarity functions nd achieved verification rates (at FAR 0.1%) of 90.5% on expression-variation and 95.8% on size-varying frontal images within the CAS-PEAL database. Performing Experiment 1 of FRGC ver2.0, the method achieved a verification rate of 72%. Keywords: Face recognition; Maximum Likelihood estimators; Gabor graphs. . Introduction" 29c7dfbbba7a74e9aafb6a6919629b0a7f576530,Automatic Facial Expression Analysis and Emotional Classification,"Automatic Facial Expression Analysis and Emotional Classification Robert Fischer Submitted to the Department of Math and Natural Sciences in partial fulfillment of the requirements for the degree of a Diplomingenieur der Optotechnik und Bildverarbeitung (FH) (Diplom Engineer of Photonics and Image Processing) t the UNIVERSITY OF APPLIED SCIENCE DARMSTADT (FHD) Accomplished and written at the MASSACHUSETTS INSTITUTE OF TECHNOLOGY (MIT) October 2004 Author . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Department of Math and Natural Sciences October 30, 2004 Certified by . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Dr. Harald Scharfenberg Professor at FHD Thesis Supervisor Accepted by . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ." 2926a7b4e6f92498236817300a253e8f3a88bd49,Neural Paraphrase Generation using Transfer Learning,"Proceedings of The 10th International Natural Language Generation conference, pages 257–261, Santiago de Compostela, Spain, September 4-7 2017. c(cid:13)2017 Association for Computational Linguistics" 299af7d4fe6da8ac0b390e3ce45c48f7a8b5bb37,"Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose.","Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose Seyoung Park, Bruce Xiaohan Nie and Song-Chun Zhu" 29756b6b16d7b06ea211f21cdaeacad94533e8b4,Thresholding Approach based on GPU for Facial Expression Recognition,"Thresholding Approach based on GPU for Facial Expression Recognition Jesús García-Ramírez1, J. Arturo Olvera-López1, Ivan Olmos-Pineda1, Georgina Flores-Becerra2, Adolfo Aguilar-Rico2 Benemérita Universidad Autónoma de Puebla, Faculty of Computer Science, Puebla, México Instituto Tecnológico de Puebla, Puebla, México" 29a6cbf089a8d916b563e02480a1844909754bcf,"The rules of implicit evaluation by race, religion, and age.","The Rules of Implicit Evaluation by Race, Religion, and Age Axt JR, Ebersole CR, Nosek BA. 014; 25(9):1804-1815 ARTICLE IDENTIFIERS DOI: 10.1177/0956797614543801 PMID: 25079218 PMCID: not available JOURNAL IDENTIFIERS LCCN: not available pISSN: 0956-7976 eISSN: 1467-9280 OCLC ID: not available CONS ID: not available US National Library of Medicine ID: not available This article was identified from a query of the SafetyLit database. Powered by TCPDF (www.tcpdf.org)" 29c5a44e01d1126505471b2ab46163d598c871c7,Improving Landmark Localization with Semi-Supervised Learning,"Improving Landmark Localization with Semi-Supervised Learning Sina Honari1∗, Pavlo Molchanov2, Stephen Tyree2, Pascal Vincent1,4,5, Christopher Pal1,3, Jan Kautz2 MILA-University of Montreal, 2NVIDIA, 3Ecole Polytechnique of Montreal, 4CIFAR, 5Facebook AI Research. {honaris, {pmolchanov, styree," 29113ed00421953e0ddc4fa6784eaba60f05e801,Automatic Track Creation and Deletion Framework for Face Tracking,"IJCSNS International Journal of Computer Science and Network Security, VOL.15 No.2, February 2015 Automatic Track Creation and Deletion Framework for Face Tracking Dept. of Information and Communication, St.Xavier’s Catholic College of Engineering, Nagercoil, Tamilnadu, India. Renimol T G, Anto Kumar R.P" 29bd9cdcb6f3c8c7475df5918c0d87283ffa254f,Evolution of Visual Odometry Techniques,"Evolution of Visual Odometry Techniques Shashi Poddar, Rahul Kottath, Vinod Karar" 292c6b743ff50757b8230395c4a001f210283a34,Fast violence detection in video,"Fast Violence Detection in Video O. Deniz1, I. Serrano1, G. Bueno1 and T-K. Kim2 VISILAB group, University of Castilla-La Mancha, E.T.S.I.Industriales, Avda. Camilo Jose Cela s.n, 13071 Spain Department of Electrical and Electronic Engineering, Imperial College, South Kensington Campus, London SW7 2AZ, UK. {oscar.deniz, ismael.serrano, Keywords: ction recognition, violence detection, fight detection" 299c14458e13eb290534eb4484ad910ea0e828a7,Evaluation of the most appropriate Kernel Function for the Purpose of Feature Extraction in Face Recognition in video surveillance systems,"Evaluation of the most appropriate Kernel Function for the Purpose of Feature Extraction in Face Recognition in video surveillance systems Sepehr Damavandinejadmonfared1, Sina Ashooritootkaboni2, and 3Taha Bahraminezhad Jooneghani , 2 School of Electrical and Electronic Engineering, UniversitiSains Malaysia (USM), Penang, Malaysia School of Software Engeenering, Jaber Ebn Hayan University, Rasht, Iran" 294163a4126b3a886bf62ab896865ce3fc1147a8,Group Sparse Non-negative Matrix Factorization for Multi-Manifold Learning,BMVC 2011 http://dx.doi.org/10.5244/C.25.56 29b3f9f0fb821883a3c3bccbf0337c242c3b8a64,Transfer Learning for Video Recognition with Scarce Training Data,"Transfer Learning for Video Recognition with Scarce Training Data for Deep Convolutional Neural Network Yu-Chuan Su, Tzu-Hsuan Chiu, Chun-Yen Yeh, Hsin-Fu Huang, Winston H. Hsu" 29e96ec163cb12cd5bd33bdf3d32181c136abaf9,Regularized Locality Preserving Projections with Two-Dimensional Discretized Laplacian Smoothing ∗,"Report No. UIUCDCS-R-2006-2748 UILU-ENG-2006-1788 Regularized Locality Preserving Projections with Two-Dimensional Discretized Laplacian Smoothing Deng Cai, Xiaofei He, and Jiawei Han July 2006" 295266d09fde8f85e6e577b5181cbc73a1594b6b,Parallel effects of processing fluency and positive affect on familiarity-based recognition decisions for faces,"ORIGINAL RESEARCH ARTICLE published: 22 April 2014 doi: 10.3389/fpsyg.2014.00328 Parallel effects of processing fluency and positive affect on familiarity-based recognition decisions for faces Devin Duke*, Chris M. Fiacconi and Stefan Köhler* Department of Psychology, Brain and Mind Institute, Western University, London, ON, Canada Edited by: Kevin Bradley Clark, Veterans Affairs Greater Los Angeles Healthcare System, USA Reviewed by: Bernhard Hommel, Leiden University, Netherlands Sascha Topolinski, Universität Würzburg, Germany *Correspondence: Devin Duke and Stefan Köhler, Department of Psychology, Brain nd Mind Institute, Western" 29ca8ddf79d4cd1dc20cc8160a6d3326933e943f,Pragmatic descriptions of perceptual stimuli,"Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics, pages 1–10, Valencia, Spain, April 3-7 2017. c(cid:13)2017 Association for Computational Linguistics" 29dbb9492292b574f7bfd8629d6801d3136887b7,Towards Autonomous Situation Awareness,"Towards Autonomous Situation Awareness Nikhil Naikal Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2014-124 http://www.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-124.html May 21, 2014" 296afa5f7e99fc16df47f961c9539347732f7b13,GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks,"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks Zhao Chen 1 Vijay Badrinarayanan 1 Chen-Yu Lee 1 Andrew Rabinovich 1" 293193d24d5c4d2975e836034bbb2329b71c4fe7,Building a Corpus of Facial Expressions for Learning-Centered Emotions,"Building a Corpus of Facial Expressions for Learning-Centered Emotions María Lucía Barrón-Estrada, Ramón Zatarain-Cabada, Bianca Giovanna Aispuro-Medina, Elvia Minerva Valencia-Rodríguez, Ana Cecilia Lara-Barrera Instituto Tecnológico de Culiacán, Culiacán, Sinaloa, Mexico {lbarron, rzatarain, m06170904, m95170906, m15171452}" 2933da06df9e47da8e855266f5ff50e03c0ccd27,Combination of RGB-D Features for Head and Upper Body Orientation Classification,"Combination of RGB-D Features for Head and Upper Body Orientation Classification Laurent Fitte-Duval, Alhayat Ali Mekonnen, Frédéric Lerasle To cite this version: Laurent Fitte-Duval, Alhayat Ali Mekonnen, Frédéric Lerasle. Combination of RGB-D Features for Head and Upper Body Orientation Classification. Advanced Concepts for Intelligent Vision Systems , Oct 2016, Lecce, Italy. 2016. HAL Id: hal-01763125 https://hal.laas.fr/hal-01763125 Submitted on 10 Apr 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 29d591806cdc6ef0d580e4a21f32e5ad9d09d148,Large scale image annotation: learning to rank with joint word-image embeddings,"Large Scale Image Annotation: Learning to Rank with Joint Word-Image Embeddings Jason Weston1, Samy Bengio1, and Nicolas Usunier2 Google, USA Universit´e Paris 6, LIP6, France" 294eef6848403520016bb2c93bfb71b3c75c73fa,Extension of Robust Principal Component Analysis for Incremental Face Recognition,"Extension of Robust Principal Component Analysis for Incremental Face Recognition Ha¨ıfa Nakouri and Mohamed Limam Institut Sup´erieur de Gestion, LARODEC Laboratory University of Tunis, Tunis, Tunisia Keywords: Image alignment, Robust Principal Component Analysis, Incremental RPCA." 293ca770a66313c9427dc71cf86bef7e1b94f2d9,Steerable part models,"Steerable Part Models Hamed Pirsiavash Deva Ramanan Department of Computer Science, University of California, Irvine" 296502c6370cabd2b7e38e71cfc757d2e5fa2199,Detection of Deep Network Generated Images Using Disparities in Color Components,"Detection of Deep Network Generated Images Using Disparities in Color Components Haodong Li, Bin Li, Shunquan Tan, Jiwu Huang" 29cf7937a1c1848c24b294569d50a2f7122de51b,MarioQA: Answering Questions by Watching Gameplay Videos,"MarioQA: Answering Questions by Watching Gameplay Videos Jonghwan Mun* Bohyung Han Paul Hongsuck Seo* Ilchae Jung Department of Computer Science and Engineering, POSTECH, Korea {choco1916, hsseo, chey0313," 29ade322a7d4a88da0b451d8ff814193991fb4fc,Real-time reliability measure-driven multi-hypothesis tracking using 2D and 3D features,"Zúñiga et al. EURASIP Journal on Advances in Signal Processing 2011, 2011:142 http://asp.eurasipjournals.com/content/2011/1/142 RESEARCH Real-time reliability measure-driven multi- hypothesis tracking using 2D and 3D features Marcos D Zúñiga1*, François Brémond2 and Monique Thonnat2 Open Access" 2921719b57544cfe5d0a1614d5ae81710ba804fa,Face Recognition Enhancement Based on Image File Formats and Wavelet,"Face Recognition Enhancement Based on Image File Formats and Wavelet De-noising Isra’a Abdul-Ameer Abdul-Jabbar, Jieqing Tan, and Zhengfeng Hou" 2960663d6d9f09bf52b030fb5b760cd32afdff99,CURE-OR: Challenging Unreal and Real Environments for Object Recognition,"Citation D. Temel, J. Lee, and G. AlRegib, “CURE-OR: Challenging unreal and real environments for object recognition,” 2018 17th IEEE International Conference on Machine Learning nd Applications (ICMLA), Orlando, Florida, USA, 2018. Dataset https://ghassanalregib.com/cure-or/ ICMLA, uthor={D. Temel and J. Lee and G. AlRegib}, ooktitle={2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)}, title={CURE-OR: Challenging unreal and real environments for object recognition}, year=2018,} Copyright c(cid:13)2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Contact https://ghassanalregib.com/ http://cantemel.com/" 292c4bd6fa516393e9c8c5f1dae5afe0bb0ece35,IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 Interacting Multiview Tracker,"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 38, NO. 5, MAY 2016 Interacting Multiview Tracker Ju Hong Yoon, Ming-Hsuan Yang, Senior Member, IEEE, and Kuk-Jin Yoon" 29e793271370c1f9f5ac03d7b1e70d1efa10577c,Face Recognition Based on Multi-classifierWeighted Optimization and Sparse Representation,"International Journal of Signal Processing, Image Processing and Pattern Recognition Vol.6, No.5 (2013), pp.423-436 http://dx.doi.org/10.14257/ijsip.2013.6.5.37 Face Recognition Based on Multi-classifierWeighted Optimization nd Sparse Representation Deng Nan1, Zhengguang Xu2 and ShengQin Bian3 ,2,3Institute of control science and engineering, University of Science and Technology Beijing ,2,330 Xueyuan Road, Haidian District, Beijing 100083 P. R.China" 294d1fa4e1315e1cf7cc50be2370d24cc6363a41,A modular non-negative matrix factorization for parts-based object recognition using subspace representation,"008 SPIE Digital Library -- Subscriber Archive Copy Processing: Machine Vision Applications, edited by Kurt S. Niel, David Fofi, Proc. of SPIE-IS&T Electronic Imaging, SPIE Vol. 6813, 68130C, © 2008 SPIE-IS&T · 0277-786X/08/$18SPIE-IS&T/ Vol. 6813 68130C-1" 29d6176f2ac871446cfa2b8ac52e9d26a2b0838e,Fast Pedestrian Detection Using Histogram of Oriented Gradients and Principal Components Analysis,"In Seop Na : Fast Pedestrian Detection Using Histogram of Oriented Gradients and Principal Components Analysis http://dx.doi.org/10.5392/IJoC.2013.9.3.001 Histogram of Oriented Gradients and Principal Components Analysis Fast Pedestrian Detection Using Trung Quy Nguyen, Soo Hyung Kim, In Seop Na School of Electronics and Computer Engineering Chonnam National University, 77 Yongbong-ro, Buk-gu, Gwangju, 500-757, Korea" 29d291e71334392f6a04c53a4194d4ff29a460bf,Multiple human tracking in RGB-depth data: a survey,"Camplani, M., Paiement, A., Mirmehdi, M., Damen, D., Hannuna, S., Burghardt, T. and Tao, L. (2016) Multiple human tracking in ISSN 1751-9632 Available from: http://eprints.uwe.ac.uk/35666 We recommend you cite the published version. The publisher’s URL is: http://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2016.0178 Refereed: Yes (no note) Disclaimer UWE has obtained warranties from all depositors as to their title in the material deposited and as to their right to deposit such material. UWE makes no representation or warranties of commercial utility, title, or fit- ness for a particular purpose or any other warranty, express or implied in respect of any material deposited. UWE makes no representation that the use of the materials will not infringe ny patent, copyright, trademark or other property or proprietary rights. UWE accepts no liability for any infringement of intellectual property rights in any material deposited but will remove such material from public view pend- ing investigation in the event of an allegation of any such infringement. PLEASE SCROLL DOWN FOR TEXT." 29ce6b54a87432dc8371f3761a9568eb3c5593b0,Age Sensitivity of Face Recognition Algorithms,"Kent Academic Repository Full text document (pdf) Citation for published version Yassin, DK H. PHM and Hoque, Sanaul and Deravi, Farzin (2013) Age Sensitivity of Face Recognition pp. 12-15. https://doi.org/10.1109/EST.2013.8 Link to record in KAR http://kar.kent.ac.uk/43222/ Document Version Author's Accepted Manuscript Copyright & reuse Content in the Kent Academic Repository is made available for research purposes. Unless otherwise stated all ontent is protected by copyright and in the absence of an open licence (eg Creative Commons), permissions for further reuse of content should be sought from the publisher, author or other copyright holder. Versions of research The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record. Enquiries For any further enquiries regarding the licence status of this document, please contact:" 2942964bc62b3d693b9bf238173fdca6e1f57875,An LSTM network for highway trajectory prediction,"An LSTM Network for Highway Trajectory Prediction Florent Altché2,1 and Arnaud de La Fortelle1" 290136947fd44879d914085ee51d8a4f433765fa,On a taxonomy of facial features,"On a Taxonomy of Facial Features Brendan Klare and Anil K. Jain" 9b3ed8190d99b107837de142324e4aa2be8b7eb2,An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition,"An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition Ajmal S. Mian, Mohammed Bennamoun, and Robyn Owens" 9bd973e64750a94dcf528da402b39e3a53118312,An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles,"An FPGA-Accelerated Design for Deep Learning Pedestrian Detection in Self-Driving Vehicles Abdallah Moussawi, Kamal Haddad, and Anthony Chahine Department of Electrical and Computer Engineering American University of Beirut Beirut, Lebanon Email:" 9bf6fbccfdf013cfd076f9357a05fb00b50735ee,JAR-Aibo: A Multi-view Dataset for Evaluation of Model-Free Action Recognition Systems,"JAR-Aibo: A Multi-View Dataset for Evaluation of Model-Free Action Recognition Systems Marco K¨orner and Joachim Denzler Friedrich Schiller University of Jena Computer Vision Group Ernst-Abbe-Platz 3, 07743 Jena, Germany http://www.inf-cv.uni-jena.de" 9be5129fec3b6f1efc22e19dae3ae684961f5efb,Probability based Extended Direct Attribute Prediction,"Probability based Extended Direct Attribute Prediction International Journal of Computer Applications (0975 – 8887) Volume 155 – No 5, December 2016 Manju Research Scholar, Department of computer science, Baba Mastnath University, Rohtak" 9b18cc5c938062161a4b6b0c71ee7a6c550a15f7,A Scalable Optimization Mechanism for Pairwise based Discrete Hashing.,"A Scalable Optimization Mechanism for Pairwise ased Discrete Hashing Xiaoshuang Shi, Fuyong Xing, Zizhao Zhang, Manish Sapkota, Zhenhua Guo, and Lin Yang" 9b318098f3660b453fbdb7a579778ab5e9118c4c,Joint Patch and Multi-label Learning for Facial Action Unit and Holistic Expression Recognition,"Joint Patch and Multi-label Learning for Facial Action Unit and Holistic Expression Recognition Kaili Zhao, Wen-Sheng Chu, Student Member, IEEE, Fernando De la Torre, Jeffrey F. Cohn, and Honggang Zhang, Senior Member, IEEE lassifiers without" 9b164cef4b4ad93e89f7c1aada81ae7af802f3a4,A Fully Automatic and Haar like Feature Extraction-Based Method for Lip Contour Detection,"Research Journal of Recent Sciences _________________________________________________ ISSN 2277-2502 Vol. 2(1), 17-20, January (2013) Res.J.Recent Sci. A Fully Automatic and Haar like Feature Extraction-Based Method for Lip Contour Detection Zahedi Morteza and Mohamadian Zahra School of Computer Engineering, Shahrood University of Technology, Shahrood, IRAN Received 26th September 2012, revised 27th October 2012, accepted 6th November 2012 Available online at: www.isca.in" 9b69ea8034a24db2bb1a1eef73ec11b6367d2f2e,Face Recognition System Using PCA and DCT in HMM,"International Journal of Advanced Research in Computer and Communication Engineering Vol. 4, Issue 1, January 2015 Face Recognition System Using PCA and DCT ISSN (Online) : 2278-1021 ISSN (Print) : 2319-5940 in HMM SamerKais Jameel Lecturer, Computer Science, University of Raparin, Sulaimaniya, Iraq" 9b474d6e81e3b94e0c7881210e249689139b3e04,VG-RAM Weightless Neural Networks for Face Recognition,"VG-RAM Weightless Neural Networks for Face Recognition Alberto F. De Souza, Claudine Badue, Felipe Pedroni, Stiven Schwanz Dias, Hallysson Oliveira and Soterio Ferreira de Souza Departamento de Inform´atica Universidade Federal do Esp´ırito Santo Av. Fernando Ferrari, 514, 29075-910 - Vit´oria-ES Brazil . Introduction Computerized human face recognition has many practical applications, such as access control, security monitoring, and surveillance systems, and has been one of the most challenging and ctive research areas in computer vision for many decades (Zhao et al.; 2003). Even though urrent machine recognition systems have reached a certain level of maturity, the recognition of faces with different facial expressions, occlusions, and changes in illumination and/or pose is still a hard problem. A general statement of the problem of machine recognition of faces can be formulated as fol- lows: given an image of a scene, (i) identify or (ii) verify one or more persons in the scene using a database of faces. In identification problems, given a face as input, the system reports ack the identity of an individual based on a database of known individuals; whereas in veri- fication problems, the system confirms or rejects the claimed identity of the input face. In both" 9beac041302100493681cb8ce82eb4383f48f603,Acoustic-labial Speaker Verification,"Pattern Recognition Letters 18 1997 853–858 (cid:14) Acoustic-labial speaker verification 1 P. Jourlin a,b,), J. Luettin a, D. Genoud a, H. Wassner a IDIAP, rue du Simplon 4, CP 592, CH-1920 Martigny, Switzerland LIA, 339 chemin des Meinajaries, BP 1228, 84911 A˝ignon Cedex 9, France" 9b19be86280c8dbb3fdccc24297449290bd2b6aa,Robust Compressive Phase Retrieval via Deep Generative Priors,"Robust Compressive Phase Retrieval via Deep Generative Priors Fahad Shamshad, Ali Ahmed Dept. of Electrical Engg., Information Technology University, Lahore, Pakistan. {fahad.shamshad," 9b74de11c62ce16d0b4509554556e6b6b0d4f5c0,Bayesian Probabilistic Co-Subspace Addition,"Bayesian Probabilistic Co-Subspace Addition Lei Shi Baidu.com, Inc" 9bcfadd22b2c84a717c56a2725971b6d49d3a804,How to Detect a Loss of Attention in a Tutoring System using Facial Expressions and Gaze Direction,"How to Detect a Loss of Attention in a Tutoring System using Facial Expressions and Gaze Direction Mark ter Maat" 9b678aa28facf4f90081d41c2c484c6addddb86d,Fully Convolutional Attention Networks for Fine-Grained Recognition,"Fully Convolutional Attention Networks for Fine-Grained Recognition Xiao Liu, Tian Xia, Jiang Wang, Yi Yang, Feng Zhou and Yuanqing Lin Baidu Research {liuxiao12,xiatian,wangjiang03,yangyi05, zhoufeng09," 9bddd98289ecc7a8dc5517122d21d5c6f5a9a01a,DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems, 9bac481dc4171aa2d847feac546c9f7299cc5aa0,Matrix Product State for Higher-Order Tensor Compression and Classification,"Matrix Product State for Higher-Order Tensor Compression and Classification Johann A. Bengua1, Ho N. Phien1, Hoang D. Tuan1 and Minh N. Do2" 9b7974d9ad19bb4ba1ea147c55e629ad7927c5d7,Faical Expression Recognition by Combining Texture and Geometrical Features,"Faical Expression Recognition by Combining Texture and Geometrical Features Renjie Liu, Ruofei Du, Bao-Liang Lu*" 9b6d61491120bdd579f53e8c5f7cbe1e05cbc91e,Modeling Multimodal Behaviors from Speech Prosody,"Modeling Multimodal Behaviors From Speech Prosody Yu Ding1, Catherine Pelachaud1, and Thierry Arti`eres2 CNRS-LTCI, Institut Mines-TELECOM, TELECOM ParisTech, Paris, France {yu.ding, Universit´e Pierre et Marie Curie (LIP6), Paris, France" 9b5b2fd938a9337475cb90a143cf7568f8f63709,Illumination Processing in Face Recognition,"Illumination Processing in Face Recognition187Illumination Processing in Face RecognitionYongping Li, Chao Wang and Xinyu AoX Illumination Processing in Face Recognition Yongping Li, Chao Wang and Xinyu Ao Shanghai Institute of Applied Physics, Chinese Academy of Sciences China 1. Introduction Driven by the demanding of public security, face recognition has emerged as a viable solution and achieved comparable accuracies to fingerprint system under controlled lightning environment. In recent years, with wide installing of camera in open area, the automatic face recognition in watch-list application is facing a serious problem. Under the open environment, lightning changes is unpredictable, and the performance of face recognition degrades seriously. Illumination processing is a necessary step for face recognition to be useful in the uncontrolled environment. NIST has started a test called FRGC to boost the research in improving the performance under changing illumination. In this chapter, we will focus on the research effort made in this direction and the influence on face recognition caused by illumination. First of all, we will discuss the quest on the image formation mechanism under various illumination situations, and the corresponding mathematical modelling. The Lambertian lighting model, bilinear illuminating model and some recent model are reviewed. Secondly, under different state of face, like various head pose and different facial expression, how illumination influences the recognition result, where the different pose and illuminating will be examined carefully. Thirdly, the current methods researcher employ to counter the change of illumination to maintain good performance on face recognition are assessed briefly. The processing technique in video and how it will improve face recognition on video, where Wang’s (Wang & Li, 2009) work will be discussed to give an example on the related advancement in the fourth part. And finally, the current state-of-art of illumination processing and its future trends will be discussed. 2. The formation of camera imaging and its difference from the human visual system With the camera invented in 1814 by Joseph N, recording of human face began its new era. Since we do not need to hire a painter to draw our figures, as the nobles did in the middle age. And the machine recorded our image as it is, if the camera is in good condition. Currently, the imaging system is mostly to be digital format. The central part is CCD (charge-coupled device) or CMOS (complimentary metal-oxide semiconductor). The CCD/CMOS operates just like the human eyes. Both CCD and CMOS image sensors operate 11www.intechopen.com" 9badcba793a54dd90383a55d7dfee1281c510f75,Local Gradients Smoothing: Defense against localized adversarial attacks,"Local Gradients Smoothing: Defense against localized adversarial attacks Muzammal Naseer Australian National University (ANU) Salman H. Khan Data61, CSIRO Fatih Porikli Australian National University (ANU)" 9b30771968b577ea1b71c0cfaee31f3824bfa027,Capturing Form of Non-verbal Conversational Behavior for Recreation on Synthetic Conversational Agent,"Capturing Form of Non-verbal Conversational Behavior for Recreation on Synthetic Conversational Agent EVA IZIDOR MLAKAR, 2MATEJ ROJC Roboti c.s. d.o.o, 2Faculty of Electrical Engineering and Computer Science, University of Maribor Tržaška cesta 23, 2Smetanova ulica 17 SLOVENIA" 9be0de78bb69e7b243e92ab7530f9fd5a08c62cc,Spontaneous Trait Inferences on Social Media,"Article Spontaneous Trait Inferences on Social Media Ana Levordashka1 and Sonja Utz1 Social Psychological and Personality Science 017, Vol. 8(1) 93-101 ª The Author(s) 2016 Reprints and permission: sagepub.com/journalsPermissions.nav DOI: 10.1177/1948550616663803 journals.sagepub.com/home/spp" 9b555d8c8f518d907fa273d8691b008d55aedd92,Reasoning with shapes: profiting cognitive susceptibilities to infer linear mapping transformations between shapes,"REASONING WITH SHAPES Reasoning with shapes: profiting cognitive susceptibilities to infer linear mapping transformations between shapes Vahid Jalili" 9b7c6ef333c6e64f2dfa97a1a3614d0775d81a8a,A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval,"A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval Ruoyu Liu, Yao Zhao, Liang Zheng, Shikui Wei, and Yi Yang" 9bda5f8659b3834369cbc52fe8f852c6bfd2eaf8,Efficient decentralized visual place recognition from full-image descriptors,"Efficient Decentralized Visual Place Recognition From Full-Image Descriptors Titus Cieslewski and Davide Scaramuzza" 9b0f2fb0faa27c4fd9d50e84c65ecd81ab26bd75,POTs: Protective Optimization Technologies,"POTs: Protective Optimization Technologies Rebekah Overdorf imec-COSIC KU Leuven Bogdan Kulynych EPFL SPRING Lab Ero Balsa imec-COSIC KU Leuven Carmela Troncoso EPFL SPRING Lab Seda Gürses imec-COSIC KU Leuven" 9bdd3ce1879f8fd32d2a3f2c4cedcadcf292a1a5,Geometric Active Learning via Enclosing Ball Boundary,"IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING Geometric Active Learning via Enclosing Ball Boundary Xiaofeng Cao, Ivor W. Tsang, Jianliang Xu, Zenglin Shi, Guandong Xu" 9b6d0b3fbf7d07a7bb0d86290f97058aa6153179,"NII , Japan at the first THUMOS Workshop 2013","NII, Japan at the first THUMOS Workshop 2013 Sang Phan, Duy-Dinh Le, Shin’ichi Satoh National Institute of Informatics -1-2 Hitotsubashi, Chiyoda-ku, Tokyo, Japan 101-8430" 13b8d657f0f9a0178339570bdc153bfd10a81300,Harvesting large-scale weakly-tagged image databases from the web,"Harvesting Large-Scale Weakly-Tagged Image Databases from the Web Jianping Fan1, Yi Shen1, Ning Zhou1, Yuli Gao2 Department of Computer Science, UNC-Charlotte, NC28223, USA Multimedia Interaction and Understanding, HP Labs, Palo Alto, CA94304, USA" 138f079382e2802f3c98c4c81218d413472c6d53,Large Scale Deep Convolutional Neural Network Features Search with Lucene,"Large Scale Deep Convolutional Neural Network Features Search with Lucene Claudio Gennaro ISTI-CNR April 4, 2016" 13aac86217231a7d118ecdff444ee07234fcff50,Classification via Incoherent Subspaces,"Classification via Incoherent Subspaces Karin Schnass, Pierre Vandergheynst, Senior Member, IEEE" 13451899558d7217206b275ca0bb1f48fa4afdd9,Hidden Markov Models Training by a Particle Swarm Optimization Algorithm,"Journal of Mathematical Modelling and Algorithms (2007) 6: 175–193 DOI: 10.1007/s10852-005-9037-7 # Springer 2006 Hidden Markov Models Training by a Particle Swarm Optimization Algorithm , NICOLAS MONMARCHE´ SE´ BASTIEN AUPETIT nd MOHAMED SLIMANE Laboratoire d’Informatique, Polytech’Tours, Universite´ Franc¸ois-Rabelais de Tours, 64 avenue Jean Portalis, 37200 Tours, France. e-mail: {sebastien.aupetit, nicolas.monmarche, (Received 16 July 2005; in final form 22 December 2005; published online 28 February 2006) In this work we consider the problem of Hidden Markov Models (HMM) training. This" 138e3f6bc164a7b26a0ff283379a325afc0fee14,Geo-Supervised Visual Depth Prediction,"Geo-Supervised Visual Depth Prediction Xiaohan Fei Alex Wong Stefano Soatto" 137457bbf46009b25d7f6d853083b6da02bfd6b9,Following Eye Gaze Activates a Patch in the Posterior Temporal Cortex That Is not Part of the Human “Face Patch” System,"New Research Cognition and Behavior Following Eye Gaze Activates a Patch in the Posterior Temporal Cortex That Is not Part of the Human “Face Patch” System Kira Marquardt,1,ⴱ Hamidreza Ramezanpour,1,2,3,ⴱ Peter W. Dicke,1 and Peter Thier1,4 DOI:http://dx.doi.org/10.1523/ENEURO.0317-16.2017 Department of Cognitive Neurology, Hertie Institute for Clinical Brain Research, 72076 Tübingen, Germany, Graduate School of Neural and Behavioural Sciences, University of Tübingen, 72074 Tübingen, Germany, International Max Planck Research School for Cognitive and Systems Neuroscience, University of Tübingen, 72074 Tübingen, Germany, 4Werner Reichardt Centre for Integrative Neuroscience (CIN), University of Tübingen, 72076 Tübingen, Germany" 139763a0b2e78b63b245a456f2b9dbde2d1d573c,"RPRG: Toward Real-time Robotic Perception, Reasoning and Grasping with One Multi-task Convolutional Neural Network","RPRG: Toward Real-time Robotic Perception, Reasoning and Grasping with One Multi-task Convolutional Neural Network Hanbo Zhang, Xuguang Lan, Lipeng Wan, Chenjie Yang, Xinwen Zhou, and Nanning Zheng" 135fcdab631ab30ae837a743040f1c8751268e41,DeepStyle: Multimodal Search Engine for Fashion and Interior Design,"SUBMITTED TO IEEE TRANSACTIONS ON MULTIMEDIA DeepStyle: Multimodal Search Engine for Fashion and Interior Design Ivona Tautkute1, 3, Tomasz Trzci´nski2, 3, Aleksander Skorupa3, Lukasz Brocki1 and Krzysztof Marasek1" 13141284f1a7e1fe255f5c2b22c09e32f0a4d465,Object Tracking by Oversampling Local Features,"Object Tracking by Oversampling Local Features Federico Pernici and Alberto Del Bimbo" 13f8c13cfbf2a504f02745bd44da4ac40fd8f8df,Feature Sets and Dimensionality Reduction for Visual Object Detection,"Author manuscript, published in ""British Machine Vision Conference, Aberystwyth : Royaume-Uni (2010)"" DOI : 10.5244/C.24.112" 13ec6666b8b722ad9eb68a21a302e3f2f1ab4df7,0 Biometric Human Identification of Hand Geometry Features Using Discrete Wavelet Transform,"Biometric Human Identification of Hand Geometry Features Using Discrete Wavelet Transform Osslan Osiris Vergara Villegas, Humberto de Jesús Ochoa Domínguez, Vianey Guadalupe Cruz Sánchez, Leticia Ortega Maynez nd Hiram Madero Orozco Universidad Autónoma de Ciudad Juárez Instituto de Ingeniería y Tecnología Mexico . Introduction Since the security factor became a basic need for civilization, a lot of systems have been developed. Those systems, try to ensure the safety in all the things that driving a certain degree of exclusivity. Historically, keys, cards and passwords were used as security systems; however, these methods are vulnerable to loss and theft. As a result biometric identification methods emerge in order to tackle the disadvantages of the non biometric classical methods. Biometrics, is an emerging technology that addresses the automated identification of individuals, based on their physiological and behavioral traits. The main advantage of iometric methods is the ability to recognize, which is made by means of a physical feature or unique pattern (Jain et al. (2008)). With these methods and individual can hardly be victim" 135fe2a0a0e6b726e5d81299edad4b3ce39d6614,Multichannel-Kernel Canonical Correlation Analysis for Cross-View Person Reidentification,"This is a pre-print version, the final version of the manuscript with more experiments can be found at: https://doi.org/10.1145/3038916 Multi Channel-Kernel Canonical Correlation Analysis for Cross-View Person Re-Identification Giuseppe Lisanti, Svebor Karaman, Iacopo Masi" 133dd0f23e52c4e7bf254e8849ac6f8b17fcd22d,Active Clustering with Model-Based Uncertainty Reduction,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI Active Clustering with Model-Based Uncertainty Reduction Caiming Xiong, David M. Johnson, and Jason J. Corso Senior Member, IEEE" 137ff9b84649683326e85df1994932c21eec3e4c,Neural Relational Inference for Interacting Systems,"Neural Relational Inference for Interacting Systems Thomas Kipf * 1 Ethan Fetaya * 2 3 Kuan-Chieh Wang 2 3 Max Welling 1 4 Richard Zemel 2 3 4" 13631379de6487fd0571e5919f4efb65d16c1633,Accelerated Inference in Markov Random Fields via Smooth Riemannian Optimization,"Accelerated Inference in Markov Random Fields via Smooth Riemannian Optimization Siyi Hu and Luca Carlone" 131059ea24073d08de0bd153f9caddc123911e51,Facial emotional recognition in schizophrenia : preliminary results of the Virtual Reality Program for Facial Emotional Recognition,"Facial emotional recognition in schizophrenia: preliminary results of the Virtual Reality Program for Facial Emotional Recognition Reconhecimento emocional de faces na esquizofrenia: resultados preliminares do Programa de Realidade Virtual para o Reconhecimento Emocional de Faces Teresa souTo1,2, alexandre BapTisTa1, diana Tavares1,3, CrisTina Queirós1,2, anTónio MarQues1,3 Psychosocial Rehabilitation Laboratory of Faculty of Psychology and Educational Sciences, Porto University/School of Allied Health Sciences, Porto Polytechnic Institute (FPCEUP/ESTSPIPP), Porto, Portugal. FPCEUP, Porto, Portugal. ESTSPIPP, Porto, Portugal. Institution where the study was elaborated: Faculty of Psychology and Educational Sciences, Porto University, Portugal. Received: 11/6/2012 – Accepted: 2/14/2013" 13ae3c8afef5a0d6f4c9e684da9fc1fa96caaeb6,Online Anomaly Detection in Crowd Scenes via Structure Analysis,"Online Anomaly Detection in Crowd Scenes via Structure Analysis Yuan Yuan, Senior Member, IEEE, Jianwu Fang, and Qi Wang" 13a60e75d05ef4e1ae688526bb5a4b1859a65501,Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteria,"Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteria Keze Wang, Liang Lin, Xiaopeng Yan, Ziliang Chen, Dongyu Zhang, and Lei Zhang, Fellow, IEEE" 13afc4f8d08f766479577db2083f9632544c7ea6,Multiple kernel learning for emotion recognition in the wild,"Multiple Kernel Learning for Emotion Recognition in the Wild Karan Sikka, Karmen Dykstra, Suchitra Sathyanarayana, Gwen Littlewort and Marian S. Bartlett Machine Perception Laboratory EmotiW Challenge, ICMI, 2013" 132f88626f6760d769c95984212ed0915790b625,Exploring Entity Resolution for Multimedia Person Identification,"UC Irvine UC Irvine Electronic Theses and Dissertations Title Exploring Entity Resolution for Multimedia Person Identification Permalink https://escholarship.org/uc/item/9t59f756 Author Zhang, Liyan Publication Date 014-01-01 Peer reviewed|Thesis/dissertation eScholarship.org Powered by the California Digital Library University of California" 13de254db85eefaa9533d746eb2ad2079e8f2c74,Description and evaluation of techniques for transfer learning across sub-categories,"FP7–216529 PinView Deliverable D6.3 Deliverable D6.3 Description and evaluation of techniques for transfer learning across sub-categories Contract number: FP7–216529 PinView Personal Information Navigator Adapting Through Viewing The research leading to these results has received funding from the European Community’s Seventh Framework Programme (FP7/2007-2013) under grant agreement n◦ 216529. Revision: 1.0 Page 1 of 30" 13f6ab2f245b4a871720b95045c41a4204626814,Cortex commands the performance of skilled movement,"RESEARCH ARTICLE Cortex commands the performance of skilled movement Jian-Zhong Guo, Austin R Graves, Wendy W Guo, Jihong Zheng, Allen Lee, Juan Rodrı´guez-Gonza´ lez, Nuo Li, John J Macklin, James W Phillips, Brett D Mensh, Kristin Branson, Adam W Hantman* Janelia Research Campus, Howard Hughes Medical Institute, Ashburn, United States" 134dd3bb637b51c61fa9d2332f11e39efc0b359a,High-level activity learning and recognition in structured environments,"High-level activity learning and recognition in structured environments John Patrick Greenall Submitted in accordance with the requirements for the degree of Doctor of Philosophy. The University of Leeds School of Computing June 2012" 1306ccfec94a36b94085d4cc71fed45abd998b0e,Strategies for Exploiting Independent Cloud Implementations of Biometric Experts in Multibiometric Scenarios,"Publishing CorporationMathematical Problems in EngineeringVolume 2014, Article ID 585139, 15 pageshttp://dx.doi.org/10.1155/2014/585139" 13425bb41d326982ec6b3c6f3034aa978a1300ac,Face Recognition for Smart Environments,"Face Recognition for Smart Environments Alex Pentland and Tanzeem Choudhury Reprint from February 2000 © 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for dvertising or promotional purposes or for creating new ollective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each uthor's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder." 1373195c26eab581138579f7389cdf8b7a94a4bb,Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing,"Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing Magnus Wrenninge1,∗ Jonas Unger1,2,† 7D Labs Link¨oping University, Sweden Figure 1: Example image from Synscapes." 13a82da2bfa24583caf78ab1d14b5cfa4798b3b3,Robust face hallucination using quantization-adaptive dictionaries,"Robust Face Hallucination using Quantization-Adaptive Dictionaries Reuben Farrugia Christine Guillemot IEEE Int. Conf. on Image Processing, Arizona, USA 6th September 2016" 132781c1b2495ff0e792b46b94fdf33867394e4a,Autistic Traits and Symptoms of Social Anxiety are Differentially Related to Attention to Others’ Eyes in Social Anxiety Disorder,"J Autism Dev Disord (2017) 47:3814–3821 DOI 10.1007/s10803-016-2978-z S.I. : ANXIETY IN AUTISM SPECTRUM DISORDERS Autistic Traits and Symptoms of Social Anxiety are Differentially Related to Attention to Others’ Eyes in Social Anxiety Disorder Johan Lundin Kleberg1 · Jens Högström2,3 · Martina Nord2,3 · Sven Bölte4,5 · Eva Serlachius2,3 · Terje Falck‑Ytter1,4,5 Published online: 20 December 2016 © The Author(s) 2016. This article is published with open access at Springerlink.com" 134fe1c4f45cea3339c094fee817e7a024d73d88,Inferring door locations from a teammate's trajectory in stealth human-robot team operations,"Inferring door locations from a teammate’s trajectory in stealth human-robot team operations Jean Oh, Luis Navarro-Serment, Arne Supp´e, Anthony Stentz and Martial Hebert1" 13841d54c55bd74964d877b4b517fa94650d9b65,Generalised ambient reflection models for Lambertian and Phong surfaces,"Generalised Ambient Reflection Models for Lambertian and Phong Surfaces Author Zhang, Paul, Gao, Yongsheng Published Conference Title Proceedings of the 2009 IEEE International Conference on Image Processing (ICIP 2009) https://doi.org/10.1109/ICIP.2009.5413812 Copyright Statement © 2009 IEEE. Personal use of this material is permitted. However, permission to reprint/ republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Downloaded from http://hdl.handle.net/10072/30001 Griffith Research Online https://research-repository.griffith.edu.au" 133900a0e7450979c9491951a5f1c2a403a180f0,Social Grouping for Multi-Target Tracking and Head Pose Estimation in Video,"JOURNAL OF LATEX CLASS FILES Social Grouping for Multi-target Tracking and Head Pose Estimation in Video Zhen Qin and Christian R. Shelton" 13d9da779138af990d761ef84556e3e5c1e0eb94,Learning to Locate Informative Features for Visual Identification,"Int J Comput Vis (2008) 77: 3–24 DOI 10.1007/s11263-007-0093-5 Learning to Locate Informative Features for Visual Identification Andras Ferencz · Erik G. Learned-Miller · Jitendra Malik Received: 18 August 2005 / Accepted: 11 September 2007 / Published online: 9 November 2007 © Springer Science+Business Media, LLC 2007" 13ab059e6b592ca7bcb14337316ec1ac14aa5c5a,Constrained planar cuts - Object partitioning for point clouds,"Constrained Planar Cuts - Object Partitioning for Point Clouds Markus Schoeler, Jeremie Papon and Florentin W¨org¨otter Bernstein Center for Computational Neuroscience (BCCN) III Physikalisches Institut - Biophysik, Georg-August University of G¨ottingen" 139bb2a4034a0498934185e8c6d515d8f9330e2a,One-Shot Segmentation in Clutter,"One-Shot Segmentation in Clutter Claudio Michaelis 1 2 Matthias Bethge 1 2 3 4 Alexander S. Ecker 1 2 4" 13c4a4359e9d7f5b2abe1b9542c0950946b0565a,Learning sparse tag patterns for social image classification,"This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore. Title Learning sparse tag patterns for social image lassification Author(s) Lin, Jie; Duan, Ling-Yu; Yuan, Junsong; Li, Qingyong; Luo, Siwei Citation http://hdl.handle.net/10220/12960 Rights" 1394ca71fc52db972366602a6643dc3e65ee8726,EmoReact: a multimodal approach and dataset for recognizing emotional responses in children,"See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/308407783 EmoReact: A Multimodal Approach and Dataset for Recognizing Emotional Responses in Children Conference Paper · November 2016 DOI: 10.1145/2993148.2993168 CITATIONS READS authors, including: Behnaz Nojavanasghari University of Central Florida PUBLICATIONS 20 CITATIONS Tadas Baltrusaitis Carnegie Mellon University 0 PUBLICATIONS 247 CITATIONS SEE PROFILE SEE PROFILE Charles E. Hughes University of Central Florida 85 PUBLICATIONS 1,248 CITATIONS SEE PROFILE" 135fc59c8adb8d97a0a8dacf615f1b18a2102372,Language-Based Image Editing with Recurrent Attentive Models,"Language-Based Image Editing with Recurrent Attentive Models Jianbo Chen∗, Yelong Shen†, Jianfeng Gao†, Jingjing Liu†, Xiaodong Liu† University of California, Berkeley∗ and Microsoft Research† yeshen, jfgao, jingjl," 13b2e01030ae41983003e3ae53b5bb3ed3e764f0,Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline,"Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline Stefan Breuers1, Lucas Beyer1, Umer Rafi1, Bastian Leibe1" 13f03aab62fc29748114a0219426613cf3ba76ae,MORPH-II: Feature Vector Documentation,"MORPH-II: Feature Vector Documentation Troy P. Kling NSF-REU Site at UNC Wilmington, Summer 2017 MORPH-II Subsets Four different subsets of the MORPH-II database were selected for a wide range of purposes, including age estimate, gender and race classification, and facial recognition. • The “Full” data set contains all 55,134 mugshots [1]. • The “Partial” data set contains 1,000 mugshots randomly selected from the full data set. • The “Partial (Even)” data set contains 1,000 mugshots selected from the full data set according to very strict rules and is intended mainly for age estimation tasks. The subjects range in age from 21 to 45, with exactly 40 subjects in each age category (thus the term “even” in the name of the data set). Of these 40 subjects in each age group, exactly 30 are male and 10 are female, giving rise to a 3:1 gender ratio. Additionally, half of the males in each age group are black, and the same goes for the females, so there is a precise 1:1 ratio of black to white individuals. No subject is represented more than once in this data set, so it should not be used for face recognition tasks. • The “Recognition” data set contains 1,660 mugshots selected from the full data set according to certain rules and is intended to be used for facial recognition tasks. There are 166 subjects present in the data set – 83 males and 83 females – each of whom has exactly 10 images, usually taken over the span of multiple years. No restrictions on age or race were placed on this data set. Image Preprocessing" 133da0d8c7719a219537f4a11c915bf74c320da7,A Novel Method for 3D Image Segmentation with Fusion of Two Images using Color K-means Algorithm,"International Journal of Computer Applications (0975 – 8887) Volume 123 – No.4, August 2015 A Novel Method for 3D Image Segmentation with Fusion of Two Images using Color K-means Algorithm Neelam Kushwah Dept. of CSE ITM Universe Gwalior Priusha Narwariya Dept. of CSE ITM Universe Gwalior" 13f9922632ff5311046229b849615fcd2f5d0c06,On Multi-scale differential features for face recognition,"On Multi-scale differential features for face recognition Center for Intelligent Information Retrieval S. Ravela Allen R. Hanson Vision Laboratory Dept. of Computer Science, University of Massachusetts at Amherst, MA, 01002" 1369e9f174760ea592a94177dbcab9ed29be1649,Geometrical facial modeling for emotion recognition,"Geometrical Facial Modeling for Emotion Recognition Giampaolo L. Libralon and Roseli A. F. Romero" 138778d75fc4e2fd490897ac064b9ac84b6b9f04,Generation and visualization of emotional states in virtual characters,"COMPUTER ANIMATION AND VIRTUAL WORLDS Comp. Anim. Virtual Worlds 2008; 19: 259–270 Published online 25 July 2008 in Wiley InterScience (www.interscience.wiley.com) DOI: 10.1002/cav.234 ........................................................................................... Generation and visualization of emotional states in virtual characters By Diana Arellano*, Javier Varona and Francisco J. Perales .......................................................................... This paper presents an affective model that determines the emotional state of a character ccording to the personality traits and the experienced emotions. We consider an emotional state as the layer between personality and emotion. The proposed affective model offers a mapping between emotions and emotional states. To evidence emotional states of a virtual haracter, we can attribute them facial expressions based on their associated emotions. Facial expressions for intermediate emotions are generated automatically from expressions for universal emotions. The experiments show coherent emotional states produced by a simulated story. They also present how the corresponding emotions were represented through dynamic and static facial expressions. Finally, the obtained results demonstrate the satisfactory recognition by a group of people unfamiliar with the work described. Copyright © 2008 John Wiley & Sons, Ltd." 13347c0790a5f6a8739d293bfaf8e135a10c2c88,Facial Pose Interpretation for Human-Robot Symbiosis,"Daffodil International University Institutional Repository Proceedings of NCCIS February 2009 009-02-14 Facial Pose Interpretation for Human-Robot Symbiosis Bhuiyan, Md. Al-Amin Daffodil International University http://hdl.handle.net/20.500.11948/772 Downloaded from http://dspace.library.daffodilvarsity.edu.bd, Copyright Daffodil International University Library" 132d5724f8531aef54cadb79748929808ba685c0,Handling Occlusions with Franken-Classifiers, 13e348264fe1077caa44e1b59c71e67a8e4b5ad9,EFFECT OF EYES DETECTION AND POSITION ESTIMATION METHODS ON THE ACCURACY OF COMPARATIVE TESTING OF FACE DETECTION ALGORITHMS,"EFFECT OF EYES DETECTION AND POSITION ESTIMATION METHODS ON THE ACCURACY OF COMPARATIVE TESTING OF FACE DETECTION ALGORITHMS1 N. Degtyarev, O. Seredin Tula State University, 92 Lenin Ave., Tula 300600, Russian Federation; Phone: +7(4872)353637; E-mail: Many published comparisons of face detection algorithms used different evaluation procedures for each algorithm or even contain only a summary of the originally reported performance among several face detection algorithms on the pair of small datasets. Deg- tyarev et al. have proposed the FD algorithm evaluation procedure containing model of face representation conversion unifying the FD algorithms comparison procedures, which makes such evaluation more reliable. However, there is no evidence that such ""conversion"" does not diminish the localization accuracy. The aim of this work is to ex- mined the effects of two different face representation conversion techniques - eyes es- timation model proposed by Degtyarev et al. and highly scored eyes detection method proposed by Bolme et al. and based on ASE filters - via routine testing. Introduction Face detection (FD) algorithms are getting widely used in the modern world: security sys- tems, interactive user interfaces, advertisement" 60a33bcfe4b40cf46772e6aa1ead10489e924847,Bayesian representation learning with oracle constraints,"When crowds hold privileges: Bayesian unsupervised representation learning with oracle constraints Theofanis Karaletsos Computational Biology Program, Sloan Kettering Institute 275 York Avenue, New York, USA Serge Belongie Cornell Tech 11 Eighth Avenue #302, New York, USA Gunnar R¨atsch Computational Biology Program, Sloan Kettering Institute 275 York Avenue, New York, USA" 60ffc8db53b02e95d852f5a06f97686486f72195,Video matching using DC-image and local features,"Video Matching Using DC-image and Local Features Saddam Bekhet, Amr Ahmed and Andrew Hunter" 60cdcf75e97e88638ec973f468598ae7f75c59b4,Face Annotation Using Transductive Kernel Fisher Discriminant,"Face Annotation Using Transductive Kernel Fisher Discriminant Jianke Zhu, Steven C.H. Hoi, and Michael R. Lyu" 60d75d32d345c519fa5c0d8d6b6eb62e633a8d13,Person reidentification by semisupervised dictionary rectification learning with retraining module,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 9/13/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use PersonreidentificationbysemisuperviseddictionaryrectificationlearningwithretrainingmoduleHongyuanWangZongyuanDingJiZhangSuolanLiuTongguangNiFuhuaChenHongyuanWang,ZongyuanDing,JiZhang,SuolanLiu,TongguangNi,FuhuaChen,“Personreidentificationbysemisuperviseddictionaryrectificationlearningwithretrainingmodule,”J.Electron.Imaging27(4),043043(2018),doi:10.1117/1.JEI.27.4.043043." 60978f66eac568ae65d3acdc6559273fc30bc8c4,GReTA-A Novel Global and Recursive Tracking Algorithm in Three Dimensions,"GReTA – a novel Global and Recursive Tracking Algorithm in three dimensions Alessandro Attanasi, Andrea Cavagna, Lorenzo Del Castello, Irene Giardina, Asja Jeli´c, Stefania Melillo, Leonardo Parisi, Fabio Pellacini, Edward Shen, Edmondo Silvestri, Massimiliano Viale" 608de8217aeb7851d0425ef412e7e65da804f682,Real-Time Face Recognition from Surveillance Video,"Real-Time Face Recognition from Surveillance Video Davis, M., Popa, S., & Surlea, C. (2010). Real-Time Face Recognition from Surveillance Video. In Intelligent Video Event Analysis and Understanding (1st ed., pp. 155-194). (Studies in Computational Intelligence; Vol. 32). Berlin Heidelberg: Springer. DOI: 10.1007/978-3-642-17554-1_8 Published in: Intelligent Video Event Analysis and Understanding Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights This is the author's version of the publication, with figures in colour. The original publication is available at www.springerlink.com. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to ensure that content in the Research Portal does not infringe any person's rights, or applicable UK laws. If you discover content in the Research Portal that you believe breaches copyright or violates any law, please contact" 60ce4a9602c27ad17a1366165033fe5e0cf68078,Combination of Face Regions in Forensic Scenarios.,"TECHNICAL NOTE DIGITAL & MULTIMEDIA SCIENCES J Forensic Sci, 2015 doi: 10.1111/1556-4029.12800 Available online at: onlinelibrary.wiley.com Pedro Tome,1 Ph.D.; Julian Fierrez,1 Ph.D.; Ruben Vera-Rodriguez,1 Ph.D.; and Javier Ortega-Garcia,1 Ph.D. Combination of Face Regions in Forensic Scenarios*" 6092110d67c8082a1fa16e721aaa0421ec3161d7,Target container: A target-centric parallel programming abstraction for video-based surveillance,Target Container: A Target-Centric Parallel 6017b19c4c0e6c0e5b32e54efda6eff78b69d1dd,An Efficient 3D Geometrical Consistency Criterion for Detection of a Set of Facial Feature Points,"MVA2007 IAPR Conference on Machine Vision Applications, May 16-18, 2007, Tokyo, JAPAN An Ef‌f‌icient 3D Geometrical Consistency Criterion for Detection of a Set of Facial Feature Points Mayumi Yuasa, Tatsuo Koazkaya and Osamu Yamaguchi Corporate Research & Development Center, Toshiba Corporation , Komukai-Toshiba-cho, Saiwai-ku, Kawasaki 212–8582, Japan" 60c06e5884a672e0ba3bf1d3488307489583b7e5,Audiovisual speech perception and eye gaze behavior of adults with asperger syndrome.,"J Autism Dev Disord DOI 10.1007/s10803-011-1400-0 O R I G I N A L P A P E R Audiovisual Speech Perception and Eye Gaze Behavior of Adults with Asperger Syndrome Satu Saalasti • Jari Ka¨tsyri • Kaisa Tiippana • Mari Laine-Hernandez • Lennart von Wendt • Mikko Sams Ó Springer Science+Business Media, LLC 2011" 60e065dbb795cc0d76ec187116eb87d1f42b5485,A General Framework for Density Based Time Series Clustering Exploiting a Novel Admissible Pruning Strategy,"IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, MANUSCRIPT ID A General Framework for Density Based Time Series Clustering Exploiting a Novel Admissible Pruning Strategy Nurjahan Begum1, Liudmila Ulanova1, Hoang Anh Dau1, Jun Wang2, and Eamonn Keogh1" 60bffecd79193d05742e5ab8550a5f89accd8488,Proposal Classification using sparse representation and applications to skin lesion diagnosis,"PhD Thesis Proposal Classification using sparse representation and applications to skin lesion diagnosis I. Description In only a few decades, sparse representation modeling has undergone a tremendous expansion with successful applications in many fields including signal and image processing, computer science, machine learning, statistics. Mathematically, it can be considered as the problem of finding the sparsest solution (the one with the fewest non-zeros entries) to an underdetermined linear system of equations [1]. Based on the observation for natural images (or images rich in textures) that small scale structures tend to repeat themselves in an image or in a group of similar images, a signal source can be sparsely represented over some well-chosen redundant basis (a dictionary). In other words, it can be approximately representable by a linear combination of a few elements (also called toms or basis vectors) of a redundant/over-complete dictionary. Such models have been proven successful in many tasks including denoising [2]-[5], compression [6],[7], super-resolution [8],[9], classification and pattern recognition [10]-[16]. In the context of lassification, the objective is to find the class to which a test signal belongs, given training data from multiple classes. Sparse representation has become a powerful technique in classification and pplications, including texture classification [16], face recognition [12], object detection [10], and segmentation of medical images [17], [18]. In conventional Sparse Representation Classification (SRC) schemes, learned dictionaries and sparse representation are involved to classify image pixels" 60161c712a491764b6f227d72e9d01e956caa873,"Wrong Today, Right Tomorrow: Experience-Based Classification for Robot Perception","Wrong Today, Right Tomorrow: Experience-Based Classification for Robot Perception Jeffrey Hawke†, Corina Gur˘au†, Chi Hay Tong and Ingmar Posner" 6025f0761024006e0ea5782a7cea29ed69231fbf,Neural Mechanisms of Qigong Sensory Training Massage for Children With Autism Spectrum Disorder: A Feasibility Study,"Original Article Neural Mechanisms of Qigong Sensory Training Massage for Children With Autism Spectrum Disorder: A Feasibility Study Global Advances in Health and Medicine Volume 7: 1–10 ! The Author(s) 2018 Reprints and permissions: sagepub.com/journalsPermissions.nav DOI: 10.1177/2164956118769006 journals.sagepub.com/home/gam Kristin K Jerger, MD, LMBT1, Laura Lundegard2, Aaron Piepmeier, PhD1, Keturah Faurot, PA, MPH, PhD1, Amanda Ruffino, BA1, Margaret A Jerger, PhD, CCC-SLP1, and Aysenil Belger, PhD3" 6097c33a382c62a44379926ee96b23b51dba49c4,From Depth Data to Head Pose Estimation: a Siamese approach,"From Depth Data to Head Pose Estimation: a Siamese approach Marco Venturelli, Guido Borghi, Roberto Vezzani, Rita Cucchiara University of Modena and Reggio Emilia, DIEF {marco.venturelli, guido.borghi, roberto.vezzani, Via Vivarelli 10, Modena, Italy Keywords: Head Pose Estimation, Deep Learning, Depth Maps, Automotive" 604a4f7c0958c5cac017b853a7d0f5f5b4a4c509,Can We Teach Empathy ? Techniques Using Standardized Patients to Assist Learners with Empathy ( Submission # 1039 ), 60cdd2ae71d39f2a8a3c6d4c22284a602428b347,Image of face captured Face Detection and localization Feature extraction Learning Classification Decision,"Complete Architecture of a Robust System of Face International Journal of Computer Applications (0975 – 8887) Volume 122 – No.1, July 2015 Abdellatif Hajraoui Faculty of Science and Technology, University Sultan Moulay Slimane, Beni Mellal 3000, Morocco Recognition Mohamed Sabri Faculty of Science and Technology, University Sultan Moulay Slimane, Beni Mellal 3000, Morocco Mohamed Fakir Faculty of Science and Technology, University Sultan Moulay Slimane, Beni Mellal 3000, Morocco" 60fb007eef153fdf9c3d6620c419bef1c657c555,A soft-biometrics dataset for person tracking and re-identification,"A Soft-Biometrics Dataset for Person Tracking and Re-Identification Arne Schumann, Eduardo Monari Fraunhofer Institute for Optronics, System Technologies and Image Exploitation {arne.schumann," 60bc358296ae11ac8f11286bba0a49ac7e797d26,Diverse Image-to-Image Translation via Disentangled Representations,"Diverse Image-to-Image Translation via Disentangled Representations Hsin-Ying Lee(cid:63)1, Hung-Yu Tseng(cid:63)1, Jia-Bin Huang2, Maneesh Singh3, Ming-Hsuan Yang1,4 University of California, Merced 2Virginia Tech 3Verisk Analytics 4Google Cloud Photo to van Gogh Content Attribute Generated Winter to summer Photograph to portrait Input Output Input Output Fig. 1: Unpaired diverse image-to-image translation. (Lef t) Our model learns to perform diverse translation between two collections of images without ligned training pairs. (Right) Example-guided translation." 608c5103ad8e745b98dfe92ef33b66b93f01b051,Amélioration de performance de la navigation basée vision pour la robotique autonome : une approche par couplage vision/commande. (Performance improvment of vision-based navigation for autonomous robotics : a vision and control coupling approach),"Amélioration de performance de la navigation basée vision pour la robotique autonome : une approche par ouplage vision/commande Helène Roggeman To cite this version: Helène Roggeman. Amélioration de performance de la navigation basée vision pour la robotique utonome : une approche par couplage vision/commande. Robotique [cs.RO]. Université Paris-Saclay, 017. Français. . HAL Id: tel-01695641 https://tel.archives-ouvertes.fr/tel-01695641 Submitted on 29 Jan 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 604d7533bdcfb06f4ae217a2cd9fd2e1467192f8,Gender Recognition using Hog with Maximized Inter-Class Difference, 6084cac63fe6fcc1436610f1db4a3764ec2e3692,TST / BTD : An End-to-End Visual Recognition System,"TST/BTD: An End-to-End Visual Recognition System Taehee Lee Stefano Soatto Technical Report UCLA-CSD100008 February 8, 2010, Revised March 18, 2010" 60189e2b592056d43a28b6ffa491867f793ebe1e,Bağlamın Hiyerarşik Doğası,"Ba˘glamın Hiyerar¸sik Do˘gası Fethiye Irmak Do˘gan, Sinan Kalkan Bilgisayar Mühendisli˘gi Bölümü Orta Do˘gu Teknik Üniversitesi Ankara, Türkiye Email: Özetçe —Ba˘glam, insan bili¸si için oldukça elzemdir ve du- ru¸s, davranı¸s, konu¸sma biçimi gibi gündelik insan hayatı için önemli pek çok sürece etki etmektedir. Yakın zamanda hay- tımızda yer edinmesini bekledi˘gimiz robotların da i¸slevlerini yerine do˘gru ve verimli bir biçimde getirebilmesi için, ba˘glamı lgılama ve kullanma yetene˘gine sahip olması beklenmektedir. Ancak ba˘glam, yapay veya do˘gal bili¸s için ne kadar elzem olsa da, ba˘glamın yapısı yeterince çalı¸sılmı¸s ve çözümlenebilmi¸s de˘gildir. Bu çalı¸smada, ba˘glamın çözümlenememi¸s ö˘gelerinden ir tanesine, ba˘glamın yapısının hiyerar¸sik olup olmadı˘gına odaklanılmaktadır. Yaptı˘gımız irdelemeye göre, ba˘glama ait muhtelif sosyal, uzamsal ve zamansal özellikler ve olgular, a˘glamın hiyerar¸sik bir yapıya sahip oldu˘gunu önermektedir. Bu konudaki sinirbilim, psikoloji bulguları ve bili¸simsel modelleme" 60b3601d70f5cdcfef9934b24bcb3cc4dde663e7,Binary Gradient Correlation Patterns for Robust Face Recognition,"SUBMITTED TO IEEE TRANS. ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Binary Gradient Correlation Patterns for Robust Face Recognition Weilin Huang, Student Member, IEEE, and Hujun Yin, Senior Member, IEEE" 603ffcfad879aaf559cac118894cd38666158f2f,Learning from scratch a confidence measure,"M. POGGI, S. MATTOCCIA: LEARNING FROM SCRATCH A CONFIDENCE MEASURE Learning from scratch a confidence measure Matteo Poggi http://vision.disi.unibo.it/~mpoggi Stefano Mattoccia http://vision.disi.unibo.it/~smatt University of Bologna Department of Computer Science and Engineering (DISI) Viale del Risorgimento 2 Bologna, Italy" 60ab5c64375c4f5f8949a184fd9bfb68778ae6ea,Understanding and Verifying Kin Relationships in a Photo 1,"N. S. Syed et al Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.1225-1229 RESEARCH ARTICLE OPEN ACCESS Understanding and Verifying Kin Relationships in a Photo Ms.N.S.Syed, 2mr.B.K.Patil, 3mr.Zafar Ul Hasan (Department of Computer Science, Everest College of Engg. & Tech., Aurangabad, M.S., India ) (Department of Computer Science, Everest College of Engg. & Tech., Aurangabad, M.S., India ) (Department of Computer Science, Sandip Institute of Technology and Research Centre, Nashik, M.S,India)" 60ea05df719973ac4d9d70d3141e671131a55db5,A Practical Subspace Approach To Landmarking,"A Practical Subspace Approach To Landmarking Signals and systems group, Faculty of Electrical Engineering, Mathematics and Computer Science, University of G. M. Beumer, and R.N.J. Veldhuis Twente, Enschede, The Netherlands Email:" 602ff4fd0f5bd10c9fb971ecd2317e542f070883,Object Detection from the Satellite Images using Divide and Conquer Model,"SSRG International Journal of Computer Science and Engineering (SSRG-IJCSE) – volume1 issue10 Dec 2014 Object Detection from the Satellite Images using Divide and Conquer Model Lakhwinder Kaur, Guru Kashi University Er.Vinod Kumar Sharma (Assistant professor), Guru Kashi University" 60c36bfa7881435e2111fe3e522a36880dee6d09,Study of the Changing Trends in Facial Expression Recognition,"Study of the Changing Trends in Facial Expression Recognition {tag} {/tag} International Journal of Computer Applications © 2011 by IJCA Journal Number 5 - Article 3 Year of Publication: 2011 Authors: Dr. S. Ravi Mahima S 10.5120/2509-3397" 60c12b3a1bfd547f5a165c95774a1a17d18a5941,People recognition by mobile robots,"People Recognition by Mobile Robots Grzegorz Cielniak and Tom Duckett Centre for Applied Autonomous Sensor Systems Dept. of Technology, ¨Orebro University SE-70182 ¨Orebro, Sweden Phone: +46 19 30 11 13, +46 19 30 34 83 Email: Telefax: +46 19 30 34 63" 60529952f6346ebe26a3d4e5fdf79a925d68621f,Towards a Generalized Eigenspace-Based Face Recognition Framework,"Towards a Generalized Eigenspace-based Face Recognition Framework Javier Ruiz del Solar and Pablo Navarrete Department of Electrical Engineering, Universidad de Chile. Email: {jruizd," 60824ee635777b4ee30fcc2485ef1e103b8e7af9,Cascaded Collaborative Regression for Robust Facial Landmark Detection Trained Using a Mixture of Synthetic and Real Images With Dynamic Weighting,"Cascaded Collaborative Regression for Robust Facial Landmark Detection Trained using a Mixture of Synthetic and Real Images with Dynamic Weighting Zhen-Hua Feng, Student Member, IEEE, Guosheng Hu, Student Member, IEEE, Josef Kittler, Life Member, IEEE, William Christmas, and Xiao-Jun Wu" 60bd1d33d74619f08baf0d7477b3f8cb8fc711e5,AMYGDALA CONNECTIVITY DURING INVOLUNTARY ATTENTION TO EMOTIONAL FACES IN TYPICAL DEVELOPMENT AND AUTISM SPECTRUM DISORDERS,"AMYGDALA CONNECTIVITY DURING INVOLUNTARY ATTENTION TO EMOTIONAL FACES IN TYPICAL DEVELOPMENT AND AUTISM SPECTRUM DISORDERS A Dissertation Submitted to the Faculty of the Graduate School of Arts and Sciences of Georgetown University in partial fulfillment of the requirement for the degree of Doctor of Philosophy in Psychology Eric R. Murphy, M.A. Washington, DC August 27th, 2013" 60c7711bf9a00f697fff61474433da01f8550bf4,A Hybrid Approach of Facial Emotion Detection using Genetic Algorithm along with Artificial Neural Network,"A Hybrid Approach of Facial Emotion Detection using Genetic Algorithm along with Artificial Neural Network {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 175 Number 4 Year of Publication: 2017 Authors: Amrendra Sharan, Sunil Kumar Chhillar 10.5120/ijca2017915494 {bibtex}2017915494.bib{/bibtex}" 608dfcdbb393f44d4ae1520f6c6fdd736cee337c,Empirical Performance Analysis of Linear Discriminant Classifiers,"EmpiricalPerformanceAnalysisofLinearDiscriminantClassi(cid:12)ers W.Zhao N.Nandhakumar R.Chellappa CenterforAutomationResearch Image&VideoProcessing UniversityofMaryland LGERCA,Inc. CollegePark,MD- PrincetonJct,NJ energyforavoidingsigni(cid:12)cantperformancedegrada-" 60464c4bd94a14b63898e322f9ea651830e54ae0,Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers,"Published as a conference paper at ICLR 2018 RETHINKING THE SMALLER-NORM-LESS- INFORMATIVE ASSUMPTION IN CHANNEL PRUNING OF CONVOLUTION LAYERS Jianbo Ye∗ College of Information Sciences and Technology The Pennsylvania State University James Z. Wang College of Information Sciences and Technology The Pennsylvania State University Xin Lu, Zhe Lin Adobe Research" 60040e4eae81ab6974ce12f1c789e0c05be00303,Graphical Facial Expression Analysis and Design Method: An Approach to Determine Humanoid Skin Deformation,"Yonas Tadesse1,2 e-mail: Shashank Priya e-mail: Center for Energy Harvesting Materials and Systems (CEHMS), Bio-Inspired Materials and Devices Laboratory (BMDL), Center for Intelligent Material Systems and Structure (CIMSS), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA 24061 Graphical Facial Expression Analysis and Design Method: An Approach to Determine Humanoid Skin Deformation The architecture of human face is complex consisting of 268 voluntary muscles that perform oordinated action to create real-time facial expression. In order to replicate facial expres- sion on humanoid face by utilizing discrete actuators, the first and foremost step is the identi-" 609ff585468ad0faba704dde1a69edb9f847c201,LogDet Rank Minimization with Application to Subspace Clustering,"Hindawi Publishing Corporation Computational Intelligence and Neuroscience Volume 2015, Article ID 824289, 10 pages http://dx.doi.org/10.1155/2015/824289 Research Article LogDet Rank Minimization with Application to Subspace Clustering Zhao Kang,1 Chong Peng,1 Jie Cheng,2 and Qiang Cheng1 Computer Science Department, Southern Illinois University, Carbondale, IL 62901, USA Department of Computer Science and Engineering, University of Hawaii at Hilo, Hilo, HI 96720, USA Correspondence should be addressed to Qiang Cheng; Received 25 March 2015; Revised 15 June 2015; Accepted 18 June 2015 Academic Editor: Jos´e Alfredo Hernandez Copyright © 2015 Zhao Kang et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Low-rank matrix is desired in many machine learning and computer vision problems. Most of the recent studies use the nuclear norm as a convex surrogate of the rank operator. However, all singular values are simply added together by the nuclear norm, and thus the rank may not be well approximated in practical problems. In this paper, we propose using a log-determinant (LogDet) function as a smooth and closer, though nonconvex, approximation to rank for obtaining a low-rank representation in subspace lustering. Augmented Lagrange multipliers strategy is applied to iteratively optimize the LogDet-based nonconvex objective" 60efdb2e204b2be6701a8e168983fa666feac1be,Transferring Deep Object and Scene Representations for Event Recognition in Still Images,"Int J Comput Vis DOI 10.1007/s11263-017-1043-5 Transferring Deep Object and Scene Representations for Event Recognition in Still Images Limin Wang1 · Zhe Wang2 · Yu Qiao3 · Luc Van Gool1 Received: 31 March 2016 / Accepted: 1 September 2017 © Springer Science+Business Media, LLC 2017" 77db171a523fc3d08c91cea94c9562f3edce56e1,Gauss-Laguerre wavelet textural feature fusion with geometrical information for facial expression identification,"Poursaberi et al. EURASIP Journal on Image and Video Processing 2012, 2012:17 http://jivp.eurasipjournals.com/content/2012/1/17 R ES EAR CH Open Access Gauss–Laguerre wavelet textural feature fusion with geometrical information for facial expression identification Ahmad Poursaberi1*, Hossein Ahmadi Noubari2, Marina Gavrilova1 and Svetlana N Yanushkevich1" 7711330fb88e2522a5779a09c1622b75557f9254,Real-time detection and tracking of pedestrians in CCTV images using a deep convolutional neural network,"Real-time detection and tracking of pedestrians in CCTV images using a deep convolutional neural network Debaditya Acharya Kourosh Khoshelham Stephan Winter Infrastructure Engineering, The University of Melbourne" 77ad2727065cb3dc5c91975604af01c82ec5c9f6,Convolutional Neural Networks for Disaster Images Retrieval,"Convolutional Neural Networks for Disaster Images Retrieval Sheharyar Ahmad1,Kashif Ahmad2, Nasir Ahmad1, Nicola Conci2 DCSE, UET Peshawar, Pakistan DISI-University of Trento, Trento" 771b7d76df1ed476dea859034a276f14ad1e49f1,Multi-scale elastic graph matching for face detection,"Sato and Kuriya EURASIP Journal on Advances in Signal Processing 2013, 2013:175 http://asp.eurasipjournals.com/content/2013/1/175 REVIEW Open Access Multi-scale elastic graph matching for face detection Yasuomi D Sato1,2,3* and Yasutaka Kuriya1" 771a9e7dc747fa2282815a4863502183f4e887c8,Efficient Bootsrapping and Query Adaptive Ranking for Image Search 1,"The International Journal Of Science & Technoledge (ISSN 2321 – 919X) www.theijst.com THE INTERNATIONAL JOURNAL OF SCIENCE & TECHNOLEDGE Efficient Bootsrapping and Query Adaptive Ranking for Image Search A. A. R. Senthilkumar Head of the Department, Department of Master of Computer Application PGP College of Engineering and Technology, Namakkal P. Mayuri Department of Computer Science and Engineering PGP College of Engineering and Technology, Namakkal" 77d31d2ec25df44781d999d6ff980183093fb3de,The Multiverse Loss for Robust Transfer Learning,"The Multiverse Loss for Robust Transfer Learning Supplementary . Omitted proofs for which the joint loss: m(cid:88) L(F r, br, D, y) J(F 1, b1...F m, bm, D, y) = is bounded by: mL∗(D, y) ≤ J(F 1, b1...F m, bm, D, y) m−1(cid:88) ≤ mL∗(D, y) + Alλd−j+1 where [A1 . . . Am−1] are bounded parameters. We provide proofs that were omitted from the paper for lack of space. We follow the same theorem numbering as in the paper. Lemma 1. The minimizers F ∗, b∗ of L are not unique, and it holds that for any vector v ∈ Rc and scalar s, the solu- tions F ∗ + v1(cid:62) Proof. denoting V = v1(cid:62)" 7714a5aa27ab5ad4d06a81fbb3e973d3b1002ac1,SSD-Sface : Single shot multibox detector for small faces,"SSD-Sface: Single shot multibox detector for small faces C. Thuis" 77052654a37b88719c014c5afd3db89cb2288aeb,Lung Cancer Prediction Using Neural Network Ensemble with Histogram of Oriented Gradient Genomic Features,"Hindawi Publishing Corporation e Scientific World Journal Volume 2015, Article ID 786013, 17 pages http://dx.doi.org/10.1155/2015/786013 Research Article Lung Cancer Prediction Using Neural Network Ensemble with Histogram of Oriented Gradient Genomic Features Emmanuel Adetiba and Oludayo O. Olugbara ICT and Society Research Group, Durban University of Technology, P.O. Box 1334, Durban 4000, South Africa Correspondence should be addressed to Oludayo O. Olugbara; Received 12 December 2014; Accepted 29 January 2015 Academic Editor: Alexander Schonhuth Copyright © 2015 E. Adetiba and O. O. Olugbara. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This paper reports an experimental comparison of artificial neural network (ANN) and support vector machine (SVM) ensembles nd their “nonensemble” variants for lung cancer prediction. These machine learning classifiers were trained to predict lung cancer using samples of patient nucleotides with mutations in the epidermal growth factor receptor, Kirsten rat sarcoma viral oncogene, nd tumor suppressor p53 genomes collected as biomarkers from the IGDB.NSCLC corpus. The Voss DNA encoding was used to map the nucleotide sequences of mutated and normal genomes to obtain the equivalent numerical genomic sequences for training" 77851ca35105ebe007d99e5d78ceb3473491071c,Spatiotemporal Stacked Sequential Learning for Pedestrian Detection,"Spatiotemporal Stacked Sequential Learning for Pedestrian Detection Alejandro Gonz´alez1 Sebastian Ramos1 David V´azquez1 Antonio M. L´opez1 Jaume Amores1 Computer Vision Center, Barcelona Universitat Aut`onoma de Barcelona United Technologies Research Center" 770b3855cdd15b49c89e4053b6cedafe53cecd6f,Improved Face Recognition Using Pseudo 2-D Hidden Markov Models,"ImprovedFaceRecognitionUsingPseudo-D HiddenMarkovModels StefanEickeler,StefanM(cid:127)uller,GerhardRigoll Gerhard-Mercator-UniversityDuisburg DepartmentofComputerScience FacultyofElectricalEngineering Duisburg-Germany -ti.uni-duisburg.de" 77d4843a177031b2b5721824280033e2e601334c,Comparative Evaluation of 3 D versus 2 D Modality for Automatic Detection of Facial Action Units,"Author’s Accepted Manuscript Comparative Evaluation of 3D versus 2D Modality for Automatic Detection of Facial Action Units Arman Savran, Bülent Sankur, M. Taha Bilge Reference: S0031-3203(11)00310-4 doi:10.1016/j.patcog.2011.07.022 PR 4228 To appear in: Pattern Recognition Received date: Revised date: Accepted date: 3 November 2010 5 July 2011 9 July 2011 www.elsevier.com/locate/pr Cite this article as: Arman Savran, Bülent Sankur and M. Taha Bilge, Comparative Eval- uation of 3D versus 2D Modality for Automatic Detection of Facial Action Units, Pattern Recognition, doi:10.1016/j.patcog.2011.07.022" 77351eaeb65e374a4d1e54acc28fea426670e364,COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT MATCHING LEVEL,"Signal & Image Processing : An International Journal (SIPIJ) Vol.8, No.4, August 2017 COMPRESSION BASED FACE RECOGNITION USING TRANSFORM DOMAIN FEATURES FUSED AT MATCHING LEVEL Srinivas Halvia, Nayina Ramapurb , K B Rajac and Shanti Prasadd Dayananda Sagar College of Engineering, Bangalore, India. Sai-Tektronix Pvt. Ltd., Bangalore, India. University Visvesvaraya College of Engineering, Bangalore, India. dK.S. Institute of Technology, Bangalore, India." 77c7f5c5852c189b59c34ebbbbec03e5e4060428,Talking to Robots : Learning to Ground Human Language in Perception and Execution,"(cid:13)Copyright 2014 Cynthia Matuszek" 77acb8847a76bfcc925f45387fb7abd4f2bd38ac,A novel polar-based human face recognition computational model.,"Novel polar-based human face recognition computational model Brazilian Journal of Medical and Biological Research (2009) 42: 637-646 ISSN 0100-879X A novel polar-based human face recognition computational model Y. Zana1, J.P. Mena-Chalco2 and R.M. Cesar Jr.2 Núcleo de Cognição e Sistemas Complexos, Centro de Matemática, Computação e Cognição, Universidade Federal do ABC, Santo André, SP, Brasil Departamento de Ciências da Computação, Instituto de Matemática e Estatística, Universidade de São Paulo, São Paulo, SP, Brasil Correspondence to: Y. Zana, Núcleo de Cognição e Sistemas Complexos, Centro de Matemática, Computação e Cognição, UFABC, Rua Catequese, 242, 09090-400 Santo André, SP, Brasil Fax: +55-11-4437-8403. E-mail: Motivated by a recently proposed biologically inspired face recognition approach, we investigated the relation between human ehavior and a computational model based on Fourier-Bessel (FB) spatial patterns. We measured human recognition performance of FB filtered face images using an 8-alternative forced-choice method. Test stimuli were generated by converting the images from the spatial to the FB domain, filtering the resulting coefficients with a band-pass filter, and finally taking the inverse FB transformation of the filtered coefficients. The performance of the computational models was tested using a simulation of the psychophysical experiment. In the FB model, face images were first filtered by simulated V1- type neurons and later analyzed globally for their content of FB components. In general, there was a higher human contrast sensitivity to radially" 7766ab86a7bea8809129e4af769b4595578e63fc,Improvements to Tracking Pedestrians in Video Streams Using a Pre-trained Convolutional Neural Network,"Western University Electronic Thesis and Dissertation Repository August 2016 Improvements to Tracking Pedestrians in Video Streams Using a Pre-trained Convolutional Neural Network Marjan Ramin The University of Western Ontario Supervisor Dr. Jagath Samarabandu The University of Western Ontario Graduate Program in Electrical and Computer Engineering A thesis submitted in partial fulfillment of the requirements for the degree in Master of Engineering Science © Marjan Ramin 2016 Follow this and additional works at: https://ir.lib.uwo.ca/etd Part of the Computer Engineering Commons Recommended Citation Ramin, Marjan, ""Improvements to Tracking Pedestrians in Video Streams Using a Pre-trained Convolutional Neural Network"" (2016). Electronic Thesis and Dissertation Repository. 3886. https://ir.lib.uwo.ca/etd/3886" 77037a22c9b8169930d74d2ce6f50f1a999c1221,Robust Face Recognition With Kernelized Locality-Sensitive Group Sparsity Representation,"Robust Face Recognition With Kernelized Locality-Sensitive Group Sparsity Representation Shoubiao Tan, Xi Sun, Wentao Chan, Lei Qu, and Ling Shao" 7793c7431f3ddce74fe2d444df614d8d8fd9af4a,A Review of Neural Network based Semantic Segmentation for Scene Understanding in Context of the self driving Car,"A Review of Neural Network based Semantic Segmentation for Scene Understanding in Context of the self driving Car J. Niemeijer1, P. Pekezou Fouopi2, S. Knake-Langhorst2, and E. Barth3 Medizinische Informatik, Universität zu Lübeck, German Aerospace Center, Braunschweig, Institute of Neuro- and Bioinformatics, Universität zu Lübeck," 778bff335ae1b77fd7ec67404f71a1446624331b,Hough forest-based facial expression recognition from video sequences,"Hough Forest-based Facial Expression Recognition from Video Sequences Gabriele Fanelli, Angela Yao, Pierre-Luc Noel, Juergen Gall, and Luc Van Gool BIWI, ETH Zurich http://www.vision.ee.ethz.ch VISICS, K.U. Leuven http://www.esat.kuleuven.be/psi/visics" 775c15a5dfca426d53c634668e58dd5d3314ea89,Image Quality-aware Deep Networks Ensemble for Efficient Gender Recognition in the Wild, 77fb0266b354d33f3725629c2ddce3d2342b318a,Is Attribute-Based Zero-Shot Learning an Ill-Posed Strategy?,"Is Attribute-Based Zero-Shot Learning n Ill-Posed Strategy? Ibrahim Alabdulmohsin1, Moustapha Cisse2, and Xiangliang Zhang1(B) Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia Facebook Artificial Intelligence Research (FAIR), Menlo Park, USA http://mine.kaust.edu.sa" 77c81c13a110a341c140995bedb98101b9e84f7f,WILDTRACK : A Multi-camera HD Dataset for Dense Unscripted Pedestrian Detection,"WILDTRACK: A Multi-camera HD Dataset for Dense Unscripted Pedestrian Detection Tatjana Chavdarova1, Pierre Baqu´e2, St´ephane Bouquet2, Andrii Maksai2, Cijo Jose1, Timur Bagautdinov2, Louis Lettry3, Pascal Fua2, Luc Van Gool3, and Franc¸ois Fleuret1 Machine Learning group, Idiap Research Institute & ´Ecole Polytechnique F´ed´erale de Lausanne CVLab, ´Ecole Polytechnique F´ed´erale de Lausanne Computer Vision Lab, ETH Zurich" 77882930692d41db107430a5a524ff5e4bb2ee5c,Hyperbolic Attention Networks,"Hyperbolic Attention Networks Caglar Gulcehre Misha Denil Mateusz Malinowski Ali Razavi Razvan Pascanu Karl Moritz Hermann Peter Battaglia Victor Bapst David Raposo Adam Santoro Nando de Freitas Deepmind" 7726a6ab26a1654d34ec04c0b7b3dd80c5f84e0d,Content-aware compression using saliency-driven image retargeting,"CONTENT-AWARE COMPRESSION USING SALIENCY-DRIVEN IMAGE RETARGETING Fabio Z¨und*†, Yael Pritch*, Alexander Sorkine-Hornung*, Stefan Mangold*, Thomas Gross† *Disney Research Zurich ETH Zurich" 7796f01b9b128fa09093e6170088c70f20091fcc,Face Recognition: Demystification of Multifarious Aspect in Evaluation Metrics,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,700 08,500 .7 M Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact" 778c9f88839eb26129427e1b8633caa4bd4d275e,Pose pooling kernels for sub-category recognition,"Pose Pooling Kernels for Sub-category Recognition Ning Zhang ICSI & UC Berkeley Ryan Farrell ICSI & UC Berkeley Trever Darrell ICSI & UC Berkeley" 779f67f2fe406828bbe7a19e8736cb5fd309e321,Fine-Grained Recognition in the Wild: A Multi-task Domain Adaptation Approach,"Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach Timnit Gebru Judy Hoffman Li Fei-Fei CS Department Stanford University {tgebru, jhoffman," 77d0c4ed1c2d971b3e81fe7919be7a5a19309f40,Deep Generative Modeling of LiDAR Data,"Deep Generative Modeling of LiDAR Data Lucas Caccia1,2, Herke van Hoof1,4, Aaron Courville2,3, Joelle Pineau1,2,3" 7789252476073a77e80fb0668eecf94a99b81d8d,Fast Landmark Localization With 3D Component Reconstruction and CNN for Cross-Pose Recognition,"Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition Gee-Sern (Jison) Hsu, Hung-Cheng Shie, Cheng-Hua Hsieh" 77b11260154e13e33c84599feba4cdc4f781bf71,Building User Profiles from Shared Photos,Building User Profiles from Shared Photos 774c8945ccf0f5315482abb8cf84ac5d37c60aa0,A Comparative Study of Feature Extraction Methods in Images Classification,"I.J. Image, Graphics and Signal Processing, 2015, 3, 16-23 Published Online February 2015 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijigsp.2015.03.03 A Comparative Study of Feature Extraction Methods in Images Classification University of Sciences and Technology Mohamed Boudiaf USTO-MB, Faculty of Mathematics and Computer Science, Seyyid Ahmed Medjahed Oran, 31000, Algeria Email:" 77205cedeb36ef1e6aadd1927c7b269871571ab9,Robust Pallet Detection for Automated Logistics Operations, 77cb6ea4feff6f44e9977cc7572185d24e48ce40,On the Complementarity of Face Parts for Gender Recognition,"On the Complementarity of Face Parts for Gender Recognition Yasmina Andreu and Ram´on A. Mollineda Dept. Llenguatges i Sistemes Inform`atics Universitat Jaume I. Castell´o de la Plana, Spain" 77b4fad7e1e16b8628289a1fe5c09c55bf83d85b,Image normalization for face recognition using 3D model,"Image Normalization for Face Recognition using 3D Model Zahid Riaz, Michael Beetz and Bernd Radig" 77e69753fc7cf007a136b12f102e1e11a93f87f5,Head and Body Orientation Estimation Using Convolutional Random Projection Forests.,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TPAMI.2017.2784424, IEEE Transactions on Pattern Analysis and Machine Intelligence Head and Body Orientation Estimation Using Convolutional Random Projection Forests Donghoon Lee, Ming-Hsuan Yang, and Songhwai Oh∗" 7730fd15ff14dd84d71f965bfeab8e4d790d91d8,SpaRTA - Tracking across occlusions via global partitioning of 3D clouds of points,"SpaRTA Tracking across occlusions via global partitioning of 3D clouds of points Andrea Cavagna, Stefania Melillo, Leonardo Parisi, Federico Ricci-Tersenghi" 77dc158a979731d2ed01145b1d3ead34a6c33487,Preference for geometric patterns early in life as a risk factor for autism.,"ORIGINAL ARTICLE ONLINE FIRST Preference for Geometric Patterns Early in Life s a Risk Factor for Autism Karen Pierce, PhD; David Conant; Roxana Hazin, BS; Richard Stoner, PhD; Jamie Desmond, MPH Context: Early identification efforts are essential for the early treatment of the symptoms of autism but can only oc- ur if robust risk factors are found. Children with autism often engage in repetitive behaviors and anecdotally pre- fertovisuallyexaminegeometricrepetition,suchasthemov- ing blade of a fan or the spinning of a car wheel. The ex- tent to which a preference for looking at geometric repeti- tion is an early risk factor for autism has yet to be examined. Objectives: To determine if toddlers with an autism spec- trum disorder (ASD) aged 14 to 42 months prefer to vi- sually examine dynamic geometric images more than so- ial images and to determine if visual fixation patterns an correctly classify a toddler as having an ASD. Design: Toddlers were presented with a 1-minute movie depicting moving geometric patterns on 1 side of a video" 776c5e37eecd26049ae31f56b3249c390e25e4e9,Angry and Beautiful : The Interactive Effect of Facial Expression and Attractiveness on Time Perception,"Psihologijske teme, 25, 2016 (2), 299-315 Izvorni znanstveni rad – UDK –159.925.072 59.937.072:115 Angry and Beautiful: The Interactive Effect of Facial Expression and Attractiveness on Time Perception Jasmina Tomas Department of Psychology, Faculty of Humanities and Social Sciences, University of Zagreb, Croatia Ana Marija Španić Child Protection Center of Zagreb, Zagreb, Croatia" 776b77306bdb852c89a22ba142fb57c8e8bb7bb5,Efficient On-Board Stereo Vision Pose Estimation,"Ef‌f‌icient On-Board Stereo Vision Pose Estimation(cid:2) Angel D. Sappa1, Fadi Dornaika2, David Ger´onimo1, and Antonio L´opez1 Computer Vision Center, Edifici O Campus UAB 08193 Bellaterra, Barcelona, Spain {asappa, dgeronimo, Institut G´eographique National 94165 Saint Mand´e, France" 9aad8e52aff12bd822f0011e6ef85dfc22fe8466,Temporal-Spatial Mapping for Action Recognition,"Temporal-Spatial Mapping for Action Recognition Xiaolin Song, Cuiling Lan, Wenjun Zeng, Junliang Xing, Jingyu Yang, and Xiaoyan Sun" 9a9af8a5b6939a1da9936608fbf071f852eca7e1,Deep Part Features Learning by a Normalised Double-Margin-Based Contrastive Loss Function for Person Re-Identification, 9a9a888bcce37e582b8a5b5f12f662e487443e5c,Cascaded Pyramid Network for Multi-Person Pose Estimation,"Cascaded Pyramid Network for Multi-Person Pose Estimation Yilun Chen∗ Zhicheng Wang∗ Yuxiang Peng1 Zhiqiang Zhang2 Gang Yu Jian Sun Megvii Inc. (Face++), {chenyilun, wangzhicheng, pyx, zhangzhiqiang, yugang, Tsinghua University 2HuaZhong University of Science and Technology" 9a03b7b71a82fc2c86b3b4cbec802dfc16978486,One-Shot Observation Learning,"One-Shot Observation Learning Leo Pauly, Wisdom C. Agboh, Mohamed Abdellatif, David C. Hogg, Raul Fuentes" 9a1a9dd3c471bba17e5ce80a53e52fcaaad4373e,Automatic Recognition of Spontaneous Facial Actions,"Automatic Recognition of Spontaneous Facial Actions Marian Stewart Bartlett1, Gwen C. Littlewort1, Mark G. Frank2, Claudia Lainscsek1, Ian R. Fasel1, Javier R. Movellan1 Institute for Neural Computation, University of California, San Diego. Department of Communication, University at Buffalo, State University of New York." 9ad27106b8e0cf14e8e2814dc318142138d5527b,Camera Style Adaptation for Person Re-identification,"Camera 6Style Transfer(a) Example images under two cameras from Market-1501(b) Examples of camera-aware style transfer between two camerasrealtransferredrealtransferredFigure1.(a)ExampleimagesfromMarket-1501[42].(b)Exam-plesofcamera-awarestyletransferbetweentwocamerasusingourmethod.Imagesinthesamecolumnrepresentthesameperson.ancepropertyunderdifferentcameras.Examplesintradi-tionalapproachesincludeKISSME[16],XQDA[20],DNS[39],etc.Examplesindeeprepresentationlearningmeth-odsincludeIDE[43],SVDNet[29],TripletNet[11],etc.Comparingtopreviousmethods,thispaperresortstoanexplicitstrategyfromtheviewofcamerastyleadapta-tion.Wearemostlymotivatedbytheneedforlargedatavolumeindeeplearningbasedpersonre-ID.Tolearnrichfeatureswhicharerobusttocameravariations,annotatinglarge-scaledatasetsisusefulbutprohibitivelyexpensive.Nevertheless,ifwecanaddmoresamplestothetrainingsetthatareawareofthestyledifferencesbetweencameras,weareableto1)addressthedatascarcityprobleminpersonre-IDand2)learninvariantfeaturesacrossdifferentcameras.Preferably,thisprocessshouldnotcostanymorehumanla-beling,sothatthebudgetiskeptlow.Basedontheabovediscussions,weproposeacam-erastyle(CamStyle)adaptationmethodtoregularizeCNNtrainingforpersonre-ID.Initsvanillaversion,welearnimage-imagetranslationmodelsforeachcamerapairwithCycleGAN[51].WiththelearnedCycleGANmodel,foratrainingimagecapturedbyacertaincamera,wecangener-" 9a3b38cec29e78163a135faf953edb5ad30c8d18,Face authentication with sparse grid Gabor information,"FACE AUTHENTICATION WITH SPARSE GRID GABOR INFORMATION Beno t Duc Stefan Fischer and Josef Bigun Signal Processing Laboratory Swiss Federal Institute of Technology CH Lausanne Switzerland" 9ac82909d76b4c902e5dde5838130de6ce838c16,Recognizing Facial Expressions Automatically from Video,"Recognizing Facial Expressions Automatically from Video Caifeng Shan and Ralph Braspenning Introduction Facial expressions, resulting from movements of the facial muscles, are the face hanges in response to a person’s internal emotional states, intentions, or social ommunications. There is a considerable history associated with the study on fa- ial expressions. Darwin (1872) was the first to describe in details the specific fa- ial expressions associated with emotions in animals and humans, who argued that ll mammals show emotions reliably in their faces. Since that, facial expression nalysis has been a area of great research interest for behavioral scientists (Ekman, Friesen, and Hager, 2002). Psychological studies (Mehrabian, 1968; Ambady and Rosenthal, 1992) suggest that facial expressions, as the main mode for non-verbal ommunication, play a vital role in human face-to-face communication. For illus- tration, we show some examples of facial expressions in Fig. 1. Computer recognition of facial expressions has many important applications in intelligent human-computer interaction, computer animation, surveillance and se- urity, medical diagnosis, law enforcement, and awareness systems (Shan, 2007). Therefore, it has been an active research topic in multiple disciplines such as psy- hology, cognitive science, human-computer interaction, and pattern recognition." 9a276c72acdb83660557489114a494b86a39f6ff,Emotion Classification through Lower Facial Expressions using Adaptive Support Vector Machines,"Emotion Classification through Lower Facial Expressions using Adaptive Support Vector Machines Porawat Visutsak Department of Information Technology, Faculty of Industrial Technology and Management, King Mongkut’s University of Technology North Bangkok," 9a08459b0cb133f0f4352c58225446f9dc95ecc4,Metadata of the chapter that will be visualized in SpringerLink,"Metadata of the chapter that will be visualized in SpringerLink Book Title Series Title Chapter Title Copyright Year Copyright HolderName Author Corresponding Author Author Author Instituto de Investigación en Informática de Albacete Universidad de Castilla-La Mancha 02071, Albacete, Spain Ambient Assisted Living. ICT-based Solutions in Real Life Situations Sokolova Marina V. Fernández-Caballero Experimentation on Emotion Regulation with Single-Colored Images Springer International Publishing Switzerland" 9a4db91c5af7866af67f5b043cfb448170d13090,An Investigation of Face and Fingerprint Feature-Fusion Guidelines,"An Investigation of Face and Fingerprint Feature-Fusion Guidelines Dane Brown1,2 and Karen Bradshaw1 Rhodes University, Department of Computer Science, Grahamstown, South Africa Council for Scientific and Industrial Research, Modelling and Digital Sciences, Pretoria, South Africa" 9ad65c5c5a2b22ef0343831fe0dabc2055d72497,EYEDIAP Database: Data Description and Gaze Tracking Evaluation Benchmarks,"EYEDIAP DATABASE: DATA DESCRIPTION AND GAZE TRACKING EVALUATION BENCHMARKS Kenneth Alberto Funes Mora Florent Monay Jean-Marc Odobez Idiap-RR-08-2014 Version of SEPTEMBER 18, 2014 Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" 9ab463d117219ed51f602ff0ddbd3414217e3166,Weighted Transmedia Relevance Feedback for Image Retrieval and Auto-annotation,"Weighted Transmedia Relevance Feedback for Image Retrieval and Auto-annotation Thomas Mensink, Jakob Verbeek, Gabriela Csurka TECHNICAL REPORT N° 0415 December 2011 Project-Teams LEAR - INRIA nd TVPA - XRCE" 9a42c519f0aaa68debbe9df00b090ca446d25bc4,Face Recognition via Centralized Coordinate Learning,"Face Recognition via Centralized Coordinate Learning Xianbiao Qi, Lei Zhang" 9a6b80f8ea7e5f24e3da05a5151ba8b42494962f,Leveraging multiple tasks to regularize fine-grained classification,"Cancún Center, Cancún, México, December 4-8, 2016 978-1-5090-4847-2/16/$31.00 ©2016 IEEE KingfisherRingedKingfisherWhite Breasted KingfisherMegaceryleCeryleChloroceryleHalcyonAlcedinidaeHalcyonidaeFig.1.Leveragingthetaxonomicontologyofbirdsforfinegrainedrecogni-tion.Fromtoptobottom,wehavefamily,orderandspeciesforfiveclassesofkingfishersintheCUB-200-2011dataset[6].Observehowidentifyingthefamilyorordercanhelpidentifyingtheclass,e.g.incaseofringedkingfisherandgreenkingfisher.Bestviewedenlarged,incolor.differencesandstrikinginter-classsimilarities.Mostmodernmethodsforfinegrainedrecognitionrelyonacombinationoflocalizingdiscriminativeregionsandlearningcorrespondingdiscriminativefeatures.Thisinturnrequiresstrongsuper-visionsuchaskeypointorattributeannotations,whichareexpensiveanddifficulttoobtainatscale.Ontheotherhand,sincefinegrainedrecognitiondealswithsubordinate-levelclassification,thereexistsanimpliedrelationshipsamonglabels.Theserelationshipsmaybetaxonomical(suchassuperclasses)orsemantic(suchasattributes)innature.Theontol-ogyobtainedinthismannercontainsrichlatentknowledgeaboutfinerdifferencesbetweenclassesthatcanbeexploitedforvisualclassification.Themodelweproposeconsistsofasingledeepconvolutionalneuralnetwork,witheachleveloftheontologygivingrisetoanadditionalsetoflabelsfortheinputimages.Theseadditionallabelsareusedasauxiliarytasksforamulti-tasknetwork,whichcanbetrainedend-to-endusingasimpleweightedobjectivefunction.Wealsoproposeanovelmethodtodynamicallyupdatethelearningrates(hereforthreferredtoasthetaskcoefficients)foreachtaskinthemulti-tasknetwork,basedonitsrelatednesstotheprimarytask.Inthiswork,weanalyzetheutilityofjointlylearningmultiplerelated/auxiliarytasksthatcouldregularizeeachothertopreventover-fitting,whileensuringthatthenetworkretainsitsdiscriminativecapability.Muchlikedropoutisbaggingtakentotheextreme,multi-tasklearningisanalogoustoboosting,ifeachtaskisconsideredaweaklearner.Wenotethatourmodelcanbepluggedintoorusedinconjunctionwithmorecomplexmulti-stagepipelinemethodssuchas[7]–[10]" 9af1cf562377b307580ca214ecd2c556e20df000,Video-Based Facial Expression Recognition Using Local Directional Binary Pattern,"Feb. 28 International Journal of Advanced Studies in Computer Science and Engineering IJASCSE, Volume 4, Issue 2, 2015 Video-Based Facial Expression Recognition Using Local Directional Binary Pattern Sahar Hooshmand, Ali Jamali Avilaq, Amir Hossein Rezaie Electrical Engineering Dept., AmirKabir Univarsity of Technology Tehran, Iran" 9a7784eea6bfa62bf2834ee0b87a3cdda46006f2,Digital Comics Image Indexing Based on Deep Learning,"Article Digital Comics Image Indexing Based on Deep Learning Nhu-Van Nguyen * ID , Christophe Rigaud ID and Jean-Christophe Burie ID Lab L3I, University of La Rochelle, 17000 La Rochelle, France; (C.R.); (J.-C.B.) * Correspondence: Received: 30 April 2018; Accepted: 27 June 2018; Published: 2 July 2018" 9a7858eda9b40b16002c6003b6db19828f94a6c6,Mooney face classification and prediction by learning across tone,"MOONEY FACE CLASSIFICATION AND PREDICTION BY LEARNING ACROSS TONE Tsung-Wei Ke(cid:63)† Stella X. Yu(cid:63)† David Whitney(cid:63) (cid:63) UC Berkeley / †ICSI" 9a88d23234ee41965ac17fc5774348563448a94d,3021977 GI P_212 Cover.indd,"Gesellschaft für Informatik e.V. (GI) publishes this series in order to make available to a broad public recent findings in informatics (i.e. computer science and informa- tion systems), to document conferences that are organized in co- operation with GI and to publish the annual GI Award dissertation. Broken down into • seminars • proceedings • dissertations • thematics urrent topics are dealt with from the vantage point of research and development, teaching and further training in theory and practice. The Editorial Committee uses an intensive review process in order to ensure high quality contributions. The volumes are published in German or English. Information: http://www.gi.de/service/publikationen/lni/ ISSN 1617-5468 ISBN 978-3-88579-606-0 The proceedings of the BIOSIG 2013 include scientific contributions of the annual onference of the Biometrics Special Interest Group (BIOSIG) of the Gesellschaft" 9a23a0402ae68cc6ea2fe0092b6ec2d40f667adb,High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs,"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs Ting-Chun Wang1 Ming-Yu Liu1 Jun-Yan Zhu2 Andrew Tao1 Jan Kautz1 Bryan Catanzaro1 NVIDIA Corporation UC Berkeley Figure 1: We propose a generative adversarial framework for synthesizing 2048 × 1024 images from semantic label maps (lower left corner in (a)). Compared to previous work [5], our results express more natural textures and details. (b) We can hange labels in the original label map to create new scenes, like replacing trees with buildings. (c) Our framework also llows a user to edit the appearance of individual objects in the scene, e.g. changing the color of a car or the texture of a road. Please visit our website for more side-by-side comparisons as well as interactive editing demos." 9a10845115794117485fc84f9b9e6ada2a7d2b00,Eye In-painting with Exemplar Generative Adversarial Networks,"Eye In-Painting with Exemplar Generative Adversarial Networks Brian Dolhansky, Cristian Canton Ferrer Facebook Inc. Hacker Way, Menlo Park (CA), USA {bdol," 9af9fa7727df11b86301a252db8a916c3a516a8d,VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering,"VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering Marc Bola˜nos1,2, ´Alvaro Peris3, Francisco Casacuberta3, Petia Radeva1,2 Universitat de Barcelona, Barcelona, Spain, Computer Vision Center, Bellaterra, Spain, PRHLT Research Center, Universitat Polit`ecnica de Val`encia, Val`encia, Spain," 9a7843f19b7e1e089db9ba875fbea9773d739f71,A Review of Benchmarking Content Based Image Retrieval,"A Review of Benchmarking Content Based Image Retrieval Gareth Loy∗ and Jan-Olof Eklundh Royal Institute of Technology (KTH) Stockholm, Sweden tel: +46 8 790 6353 e-mail: fax: +46 8 723 0302" 9a9019972dece591f502a2f794e81648b9e064fe,Combination of facial landmarks for robust eye localization using the Discriminative Generalized Hough Transform,"Combination of Facial Landmarks for Robust Eye Localization Using the Discriminative Generalized Hough Transform Ferdinand Hahmann, Gordon B¨oer, Hauke Schramm Institute of Applied Computer Science University of Applied Sciences Kiel Grenzstraße 3, 24149 Kiel" 0cfca73806f443188632266513bac6aaf6923fa8,Predictive Uncertainty in Large Scale Classification using Dropout - Stochastic Gradient Hamiltonian Monte Carlo,"Predictive Uncertainty in Large Scale Classification using Dropout - Stochastic Gradient Hamiltonian Monte Carlo. Vergara, Diego∗1, Hern´andez, Sergio∗2, Valdenegro-Toro, Mat´ıas∗∗3 and Jorquera, Felipe∗4. Laboratorio de Procesamiento de Informaci´on Geoespacial, Universidad Cat´olica del Maule, Chile. German Research Centre for Artificial Intelligence, Bremen, Germany. Email:" 0cd98be65a1a645f3c9618d9920be3a3dfc77574,Just-in-Time Reconstruction: Inpainting Sparse Maps Using Single View Depth Predictors as Priors,"Inpainting Sparse Maps using Single View Depth Predictors as Priors Just-in-Time Reconstruction: Chamara Saroj Weerasekera1, Thanuja Dharmasiri2, Ravi Garg1, Tom Drummond2 and Ian Reid1" 0c769c19d894e0dbd6eb314781dc1db3c626df57,Joint Detection and Identification Feature Learning for Person Search,"Joint Detection and Identification Feature Learning for Person Search Tong Xiao1∗ Shuang Li1∗ Bochao Wang2 Liang Lin2 Xiaogang Wang1 The Chinese University of Hong Kong 2Sun Yat-Sen University" 0ccd410b6ae977a945a84bad1c2785cef4c73214,Pseudo two-dimensional Hidden Markov Models for face detection in colour images,"Pseudo two-dimensional Hidden Markov Models for face detection in colour images ephane Marchand-Maillet Bernard M erialdo Department of Multimedia Communications EURECOM Institute   Sophia-Antipolis, France http:www.eurecom.fr~marchand To be presented in the nd Int. Conf. on Audio- and Video-based Biometric Person Authentication" 0c95ff762bdf6a20609f49f1eb5248de3f748866,Fine-Grained Walking Activity Recognition via Driving Recorder Dataset,"Fine-grained Walking Activity Recognition via Driving Recorder Dataset Hirokatsu Kataoka (AIST), Yoshimitsu Aoki (Keio Univ.), Yutaka Satoh (AIST) Shoko Oikawa (NTSEL), Yasuhiro Matsui (NTSEL) Email: http://hirokatsukataoka.net/" 0c5ddfa02982dcad47704888b271997c4de0674b,Model-driven and Data-driven Approaches for some Object Recognition Problems, 0c3f7272a68c8e0aa6b92d132d1bf8541c062141,Kruskal-Wallis-Based Computationally Efficient Feature Selection for Face Recognition,"Hindawi Publishing Corporation e Scientific World Journal Volume 2014, Article ID 672630, 6 pages http://dx.doi.org/10.1155/2014/672630 Research Article Kruskal-Wallis-Based Computationally Efficient Feature Selection for Face Recognition Sajid Ali Khan,1,2 Ayyaz Hussain,3 Abdul Basit,1 and Sheeraz Akram1 Department of Software Engineering, Foundation University, Rawalpindi 46000, Pakistan Department of Computer Science, Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Islamabad, Islamabad 44000, Pakistan Department of Computer Science and Software Engineering, International Islamic University, Islamabad 44000, Pakistan Correspondence should be addressed to Sajid Ali Khan; Received 5 December 2013; Accepted 10 February 2014; Published 21 May 2014 Academic Editors: S. Balochian, V. Bhatnagar, and Y. Zhang Copyright © 2014 Sajid Ali Khan et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Face recognition in today’s technological world, and face recognition applications attain much more importance. Most of the existing work used frontal face images to classify face image. However these techniques fail when applied on real world face images. The proposed technique effectively extracts the prominent facial features. Most of the features are redundant and do not contribute" 0cc2fc148eef46c1141edd276d903853052fc19d,Estado del arte en reconocimiento facial,"Estado del arte en reconocimiento facial Martín Adrián Garduño Santana, L. E. Díaz-Sánchez, Israel Tabarez Paz, Marcelo Romero Huertas Universidad Autónoma del Estado de México, Toluca, México Resumen. En este trabajo se resumen los métodos más utilizados para el reconocimiento facial, incluyendo las ventajas y desventajas de los sistemas desarrollados hasta ahora. También se describen las futuras líneas de investigación y se discute el rumbo del reconocimiento facial en los próximos ños. Esta revisión es relevante pues se busca la implementación de un novedoso sistema de reconocimiento facial. Palabras clave: reconocimiento facial, sistemas biométricos, ciudades inteligentes, imágenes 2D y 3D. Face Recognition: a Survey" 0c3c469e46668ea2c38a6de610d675975f337522,Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach,"Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach Updated ICCV 2013 Submission Hossein Azizpour Royal Insitute of Technology(KTH) Stefan Carlsson Royal Insitute of Technology(KTH)" 0cff123a31dcc115377ecca6ba137bebca909ff8,Anxiety dissociates the adaptive functions of sensory and motor response enhancements to social threats,"RESEARCH ARTICLE Anxiety dissociates the adaptive functions of sensory and motor response enhancements to social threats Marwa El Zein1,2*, Valentin Wyart1†, Julie Gre` zes1† Laboratoire de Neurosciences Cognitives, De´ partement d’Etudes Cognitives, Ecole Normale Supe´ rieure, PSL Research University, Paris, France; 2Universite´ Pierre et Marie Curie, Paris, France" 0ced7b814ec3bb9aebe0fcf0cac3d78f36361eae,Central Local Directional Pattern Value Flooding Co-occurrence Matrix based Features for Face Recognition,"Dr. P Chandra Sekhar Reddy, International Journal of Computer Science and Mobile Computing, Vol.6 Issue.1, January- 2017, pg. 221-227 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320–088X IMPACT FACTOR: 6.017 IJCSMC, Vol. 6, Issue. 1, January 2017, pg.221 – 227 Central Local Directional Pattern Value Flooding Co-occurrence Matrix based Features for Face Recognition Dr. P Chandra Sekhar Reddy Professor, CSE Department, Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad" 0cfcc1cd8bae5f5899cef0995debd7b38c46e817,Discrete texture traces: Topological representation of geometric context,"Discrete Texture Traces: Topological Representation of Geometric Context Jan Ernst∗ and Maneesh K. Singh Siemens Corporation, Corporate Research and Technology, Princeton, NJ, USA Department of Computer Science and Mathematics, Goethe University, Frankfurt am Main, Germany Visvanathan Ramesh†" 0ceda9dae8b9f322df65ca2ef02caca9758aec6f,Context-Aware CNNs for Person Head Detection,"Context-aware CNNs for person head detection Tuan-Hung Vu∗ Anton Osokin† INRIA/ENS Ivan Laptev∗" 0c79485f64733bd128ef8c395034b6bc77abf94d,Fully automatic expression-invariant face correspondence,"Fully Automatic Expression-Invariant Face Correspondence Augusto Salazar∗† Stefanie Wuhrer†‡ Chang Shu‡ Flavio Prieto § February 1, 2013" 0c91808994a250d7be332400a534a9291ca3b60e,Weak Hypotheses and Boosting for Generic Object Detection and Recognition,"Weak Hypotheses and Boosting for Generic Object Detection and Recognition A. Opelt1,2, M. Fussenegger1,2, A. Pinz2, and P. Auer1 Institute of Computer Science, 8700 Leoben, Austria Institute of Electrical Measurement and Measurement Signal Processing, 8010 Graz, Austria" 0c5a2bb5d1a1e9bb332207be61e13d0afb8f278c,A Supervised Learning Methodology for Real-Time Disguised Face Recognition in the Wild,"A Supervised Learning Methodology for Real-Time Disguised Face Recognition in the Wild Saumya Kumaar3, Abhinandan Dogra4, Abrar Majeedi4, Hanan Gani4, Ravi M. Vishwanath2 and S N Omkar1" 0cd8895b4a8f16618686f622522726991ca2a324,Discrete Choice Models for Static Facial Expression Recognition,"Discrete Choice Models for Static Facial Expression Recognition Gianluca Antonini1, Matteo Sorci1, Michel Bierlaire2, and Jean-Philippe Thiran1 Ecole Polytechnique Federale de Lausanne, Signal Processing Institute Ecole Polytechnique Federale de Lausanne, Operation Research Group Ecublens, 1015 Lausanne, Switzerland Ecublens, 1015 Lausanne, Switzerland" 0c8d675bcd4489e886f35bee2a347c948ffee270,Semantic bottleneck for computer vision tasks,"Semantic bottleneck for computer vision tasks Maxime Bucher1,2, St´ephane Herbin1, and Fr´ed´eric Jurie2 ONERA, Universit´e Paris-Saclay, FR-91123 Palaiseau, France Normandie Univ, UNICAEN, ENSICAEN, CNRS" 0c24ccc6d6c386a8d555a81166eaf6e8d4dfccc3,Person count localization in videos from noisy foreground and detections,"Person Count Localization in Videos from Noisy Foreground and Detections Sheng Chen1, Alan Fern1, Sinisa Todorovic1 Oregon State University. In this paper, we introduce a new problem, person count localization from noisy foreground and person detections. Our formulation strikes a middle- ground between person detection and frame-level counting. Given a video, our goal is to output for each frame a set of: . Detections optimally covering both isolated individuals and crowds of people in the video; and . Counts assigned to each detection indicating the number of people inside. The problem of detecting people in videos of crowded scenes, where people frequently appear under severe occlusion by other people in the rowd is an important line of research, since detecting people in video frames has become the standard initial step of many approaches to activity recogni- tion [1, 3, 4], and multi-object tracking by detection [6, 8, 9]. They typically use as input human appearance, pose, and orientation, and thus critically depend on robust person detections. In many domains, however, such as videos of American football or public spaces crowded with pedestrians, de- tecting every individual person is highly unreliable, and remains an open" 0cbe059c181278a373292a6af1667c54911e7925,"""Owl"" and ""Lizard"": Patterns of Head Pose and Eye Pose in Driver Gaze Classification","Owl and Lizard: Patterns of Head Pose and Eye Pose in Driver Gaze Classification Lex Fridman1, Joonbum Lee1, Bryan Reimer1, and Trent Victor2 Massachusetts Institute of Technology (MIT) Chalmers University of Technology, SAFER" 0c049cc7320f9b92f91210ab6961aa6644c867cd,Delving Deep Into Coarse-to-Fine Framework for Facial Landmark Localization,"Delving Deep into Coarse-to-fine Framework for Facial Landmark Localization Xi Chen, Erjin Zhou, Yuchen Mo, Jiancheng Liu, Zhimin Cao Megvii Research {chenxi, zej, moyuchen, liujiancheng," 0ca96dc1557032ff9259562a5b8fc026334997a6,Spectral Graph-Based Method of Multimodal Word Embedding,"Proceedings of TextGraphs-11: the Workshop on Graph-based Methods for Natural Language Processing, ACL 2017, pages 39–44, Vancouver, Canada, August 3, 2017. c(cid:13)2017 Association for Computational Linguistics" 0c286be42e734c2469563e189d7a8b11155386d5,ABSTRACT Title of Dissertation: GAIT AS A BIOMETRIC FOR PERSON IDENTIFICATION IN VIDEO, 0c17c42d71eacd2244e43fa55a8ed96607337cca,Automatic Face Reenactment,"Automatic Face Reenactment Pablo Garrido1 Thorsten Thorm¨ahlen2 Levi Valgaerts1 Patrick P´erez3 Ole Rehmsen1 Christian Theobalt1 Philipps-Universit¨at Marburg Technicolor MPI for Informatics" 0cb2dd5f178e3a297a0c33068961018659d0f443,IARPA Janus Benchmark-B Face Dataset,"© 2017 Noblis, Inc. IARPA Janus Benchmark-B Face Dataset Cameron Whitelam, Emma Taborsky*, Austin Blanton, Brianna Maze*, Jocelyn Adams*, Tim Miller*, Nathan Kalka*, Anil K. Jain**, James A. Duncan*, Kristen Allen, Jordan Cheney*, Patrick Grother*** Noblis* Michigan State University** NIST*** 21 July 2017" 0ca475433d74abb3c0f38fbe9d212058dc771570,Learning pairwise feature dissimilarities for person re-identification,"Learning Pairwise Feature Dissimilarities for Person Re-Identification Niki Martinel University of Udine Udine, Italy Christian Micheloni University of Udine Udine, Italy Claudio Piciarelli University of Udine Udine, Italy" 0cd032a93890d61b9bd187119abee0d6aeb899f7,Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval,"IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-scale Image Retrieval Yunchao Gong, Svetlana Lazebnik, Albert Gordo, Florent Perronnin" 0c87f5a6deba422c0db261c4497b9b013b4ef5b8,Robust Face Detection using Convolutional Neural Network,"International Journal of Computer Applications (0975 – 8887) Volume 170 – No.6, July 2017 Robust Face Detection using Convolutional Robert Yao Aaronson Sch. of Comp. Sci.& Tech Jiangsu Univ. of Sci. & Tech. No. 2 Mengxi Road Jingkou District Zhenjiang Prov. 212003 Neural Network Wu Chen Sch. of Comp. Sci. & Tech Jiangsu Univ. of Sci. & Tech. No. 2 Mengxi Road Jingkou District Zhenjiang Prov. 212003 Ben-Bright Benuwa Sch. of Comp. Sci. & Comm. Eng. Jiangsu Univ. Xuefu Road 01 Jingkou District Zhenjiang Prov. 212003 supported by" 0cf7da0df64557a4774100f6fde898bc4a3c4840,Shape matching and object recognition using low distortion correspondences,"Shape Matching and Object Recognition using Low Distortion Correspondences Alexander C. Berg Tamara L. Berg Jitendra Malik Department of Electrical Engineering and Computer Science U.C. Berkeley" 0c0b33baf60c787b3361a2671ae9aa077545b845,A meta-analysis of face recognition covariates,"A Meta-Analysis of Face Recognition Covariates Yui Man Lui, David Bolme, Bruce A. Draper, J. Ross Beveridge, Geoff Givens, P. Jonathon Phillips" 0cec42a1593a02ce3f4a44d375e3b95f5797aa21,Recognizing Scene Categories of Historical Postcards,"Recognizing Scene Categories of Historical Postcards Rene Grzeszick, Gernot A. Fink {rene.grzeszick, Department of Computer Science, TU Dortmund" 0c98defb5a83ea5dc5d90538d1cc8c4b6267a1cb,Perception of Dynamic Facial Expressions of Emotion: Electrophysiological Evidence,"Humboldt-Universität zu Berlin Dissertation Perception of Dynamic Facial Expressions of Emotion: Electrophysiological Evidence zur Erlangung des akademischen Grades Doctor rerum naturalium im Fach Psychologie Mathematisch-Naturwisseschafttlichen Fakultät II Guillermo Recio Dekan: Prof. Dr. Dr. Elmar Kulke Gutachter/in: 1. Prof. Dr. Werner Sommer 2. Prof. Dr. Annekathrin Schacht 3. Prof. Dr. Birgit Stürmer Datum der Einreichung: 7.09.2012 Datum der Promotion: 07.03.2013" 0c1fc3636dd9f8c9fd651b78ff65b03277a3aa47,Smart surveillance framework: A versatile tool for video analysis,"Smart Surveillance Framework: A Versatile Tool for Video Analysis Antonio C. Nazare Jr., Cassio E. dos Santos Jr., Renato Ferreira, William Robson Schwartz Department of Computer Science,Universidade Federal de Minas Gerais, Belo Horizonte, Brazil" 0c03bb741972c99b71d8d733b92e5fa9430cbede,Learning rank reduced interpolation with principal component analysis,"Learning Rank Reduced Interpolation with Principal Component Analysis Matthias Ochs1, Henry Bradler1 and Rudolf Mester1,2" 0c25a4636ebde18e229f7e459f1adaab1e9a2db9,Multi-class Classification and Clustering based Multi-object Tracking,"Multi-class Classification and Clustering based Multi-object Tracking Nii Longdon Sowah, Qingbo Wu, Fanman Meng" 0c5f9f5083b9fca4dcdbc4b122099ac1f630728b,Visual Semantic Role Labeling,"Visual Semantic Role Labeling Saurabh Gupta UC Berkeley Jitendra Malik UC Berkeley" 0c30850067c296a01b72cf4803c9712926ae5a95,Text-Dependent Audiovisual Synchrony Detection for Spoofing Detection in Mobile Person Recognition,"INTERSPEECH 2016 September 8–12, 2016, San Francisco, USA Text-Dependent Audiovisual Synchrony Detection for Spoofing Detection in Mobile Person Recognition Amit Aides1,2, Hagai Aronowitz1 Dept of Electrical Engineering,Technion - Israel Institute of Technology, Haifa, Israel IBM Research - Haifa, Israel {amitaid," 0cbefba0f41982bdff091d0e5f0d5ef93185a55c,"Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias, and Rolling Shutter Effect","Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias and Rolling Shutter Effect Nan Yang1,2,∗, Rui Wang1,2,∗, Xiang Gao1 and Daniel Cremers1,2" 0c53ef79bb8e5ba4e6a8ebad6d453ecf3672926d,Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition,"SUBMITTED TO JOURNAL Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition Zhe Wang, Limin Wang, Yali Wang, Bowen Zhang, and Yu Qiao, Senior Member, IEEE" 0cb7e4c2f6355c73bfc8e6d5cdfad26f3fde0baf,XPRESSION R ECOGNITION BASED ON WAPA AND OEPA F AST ICA,"International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 5, No. 3, May 2014 FACIAL EXPRESSION RECOGNITION BASED ON WAPA AND OEPA FASTICA Humayra Binte Ali1 and David M W Powers2 Computer Science, Engineering and Mathematics School, Flinders University, Australia Computer Science, Engineering and Mathematics School, Flinders University, Australia" 0c069a870367b54dd06d0da63b1e3a900a257298,Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs,"Author manuscript, published in ""ICANN 2011 - International Conference on Artificial Neural Networks (2011)""" 0cca85ee872ae6f6a4d305880b4461f152b1d808,Automatic framework for tracking honeybee's antennae and mouthparts from low framerate video,"AUTOMATIC FRAMEWORK FOR TRACKING HONEYBEE’S ANTENNAE AND MOUTHPARTS FROM LOW FRAMERATE VIDEO Minmin Shen⋆ Paul Szyszka† C. Giovanni Galizia† Dorit Merhof⋆ ⋆ INCIDE Center, University of Konstanz Institute of Neurobiology, University of Konstanz" 0ce4110d4c3d8b19ca0f7f75bc680aa9ba8d239a,Genetic algorithms for classifiers' training sets optimisation applied to human face recognition,"JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 11/2007, ISSN 1642-6037 Michał KAWULOK* GENETIC ALGORITHMS FOR CLASSIFIERS’ TRAINING SETS OPTIMISATION APPLIED TO HUMAN FACE RECOGNITION support vector machines, genetic algorithms, human face recognition Human face recognition is a multi-stage process within which many classification problems must be solved. This is performed by learning machines which elaborate classification rules based on a given training set. Therefore, one of the most important issues is selection of a training set which would properly represent the data that will be further classified. This paper presents an approach which utilizes genetic algorithms for selecting lassifiers’ training sets. This approach was implemented for the Support Vector Machines which is applied in two areas of automatic human face recognition: face verification and feature vectors comparison. Effectiveness of the presented concept was confirmed with appropriate experiments which results are described in this paper. . INTRODUCTION Face recognition [7, 13, 14] is among the most popular biometric techniques which are eing developed nowadays and it is worth noticing that this is the method which is the most frequently used naturally by humans. Automatic face recognition is characterized by a low level of required interaction with a person who is being recognized, but offers relatively low effectiveness comparing to other biometric methods [4, 9]. A face recognition system" 0c990e779067c563a79ae17c9d36094a745d7ed8,Model interpolation for eye localization using the Discriminative Generalized Hough Transform,"Model Interpolation for Eye Localization Using the Discriminative Generalized Hough Transform Ferdinand Hahmann, Heike Ruppertshofen, Gordon B¨oer, Hauke Schramm Institute of Applied Computer Science University of Applied Sciences Kiel Grenzstraße 3 4149 Kiel" 0cdf238fd44684b49302c22b062772e7c66ea182,U NSUPERVISED ROBOTIC SORTING : T OWARDS AUTONOMOUS DECISION MAKING ROBOTS,"International Journal of Artificial Intelligence and Applications (IJAIA), Vol.9, No.2, March 2018 UNSUPERVISED ROBOTIC SORTING: TOWARDS AUTONOMOUS DECISION MAKING ROBOTS Joris Gu´Erin, St´Ephane Thiery, Eric Nyiri And Olivier Gibaru Arts et M´etiers ParisTech, Lille, FRANCE" 0cdac46ec42be2d81f64ec4ee53d88be43290d52,Temporal Poselets for Collective Activity Detection and Recognition,"Temporal Poselets for Collective Activity Detection and Recognition Moin Nabi Alessio Del Bue Vittorio Murino Pattern Analysis and Computer Vision (PAVIS) Istituto Italiano di Tecnologia (IIT) Via Morego 30, Genova, Italy" 0c53b45321131e61d1266cb960fc47c401f856f1,Space-Time Body Pose Estimation in Uncontrolled Environments,"Space-time Body Pose Estimation in Uncontrolled Environments Marcel Germann ETH Zurich Switzerland Tiberiu Popa ETH Zurich Switzerland Remo Ziegler LiberoVision AG Switzerland Richard Keiser LiberoVision AG Switzerland Markus Gross ETH Zurich Switzerland" 71766bf224d5c74a0be6996b38d8885c2eed5a2c,Fooling Vision and Language Models Despite Localization and Attention Mechanism, 7135bed472d9a307d0612634d690c6306f5bce26,A Unified Framework for Concurrent Pedestrian and Cyclist Detection,"This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. A Unified Framework for Concurrent Pedestrian nd Cyclist Detection Xiaofei Li, Lingxi Li, Fabian Flohr, Jianqiang Wang, Hui Xiong, Morys Bernhard, Shuyue Pan, Dariu M. Gavrila, and Keqiang Li" 71529e3e51f2967e338124652e93a3d34eb6c5e1,Deep triplet-group network by exploiting symmetric and asymmetric information for person reidentification,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 9/6/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use Deeptriplet-groupnetworkbyexploitingsymmetricandasymmetricinformationforpersonreidentificationBenzhiYuNingXuBenzhiYu,NingXu,“Deeptriplet-groupnetworkbyexploitingsymmetricandasymmetricinformationforpersonreidentification,”J.Electron.Imaging27(3),033033(2018),doi:10.1117/1.JEI.27.3.033033." 71c966967fe77132a6c87999bde17a80e76b1202,Object Detection Using Deep Learning - Learning where to search using visual attention,"Eberhard Karls Universit¨at T¨ubingen Mathematisch-Naturwissenschaftliche Fakult¨at Wilhelm-Schickard-Institut f¨ur Informatik Master Thesis Computer Science Object Detection Using Deep Learning Learning where to search using visual attention Alina Kloss May 26, 2015 Reviewers Prof. Hendrik Lensch Computer Graphics Wilhelm-Schickard-Institute for Computer Science University of T¨ubingen Prof. Martin Butz Cognitive Modeling Wilhelm-Schickard-Institute for Computer Science University of T¨ubingen Supervisors" 71d8fae870ea78a89e231247afb3259267e09799,Probabilistic multi-class segmentation for the Amazon Picking Challenge,"Probabilistic Multi-Class Segmentation for the Amazon Picking Challenge Rico Jonschkowski Clemens Eppner∗ Sebastian H¨ofer∗ Roberto Mart´ın-Mart´ın∗ Oliver Brock" 714794c74941e45798d9c405a4fec1138cff2df3,Iris Segmentation: State of the Art and Innovative Methods,"Iris segmentation: state of the art and innovative methods Ruggero Donida Labati, Angelo Genovese, Vincenzo Piuri, and Fabio Scotti" 7173871866fc7e555e9123d1d7133d20577054e8,Simultaneous Adversarial Training - Learn from Others Mistakes,"Simultaneous Adversarial Training - Learn from Others’ Mistakes Zukang Liao Lite-On Singapore Pte. Ltd, 2Imperial College London" 714947e4d7f79f753c5c44eac701185e37086276,An Exponential Representation in the API Algorithm for Hidden Markov Models Training,"An Exponential Representation in the API Algorithm for Hidden Markov Models Training S´ebastien Aupetit1, Nicolas Monmarch´e1, Mohamed Slimane1, and Pierre Liardet2 Universit´e Fran¸cois-Rabelais de Tours, Laboratoire d’Informatique Polytech’Tours, 64, Av Jean Portalis, 37200 Tours, France Universit´e de Provence, CMI Laboratoire ATP, UMR-CNRS 6632 9 rue F. Joliot-Curie, 13453 Marseille cedex 13, France" 714d487571ca0d676bad75c8fa622d6f50df953b,eBear: An expressive Bear-Like robot,"eBear: An Expressive Bear-Like Robot Xiao Zhang, Ali Mollahosseini, Amir H. Kargar B., Evan Boucher, Richard M. Voyles, Rodney Nielsen and Mohammd H. Mahoor" 719fd645c4da6575ab0e774891ba30d7dfcc53aa,LOAM: Lidar Odometry and Mapping in Real-time,"LOAM: Lidar Odometry and Mapping in Real-time Ji Zhang and Sanjiv Singh" 7174e77f8e26aef3105996512b787b336320d46f,People Counting in High Density Crowds from Still Images,"People Counting in High Density Crowds from Still Images Ankan Bansal, and K S Venkatesh" 7189d5584416ef2a39d6ab16929dfecdddc10081,A Review of Face Sketch Recognition Systems,"Journal of Theoretical and Applied Information Technology 20th November 2015. Vol.81. No.2 © 2005 - 2015 JATIT & LLS. All rights reserved. ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 A REVIEW OF FACE SKETCH RECOGNITION SYSTEMS SALAH EDDINE LAHLALI, 2ABDELALIM SADIQ, 3 SAMIR MBARKI 23Department of Computing, Faculty of sciences, IbnTofail University, Kenitra, Morocco E-mail:" 71286a2b3d564daf171cdef54ff8972159152729,Combinatorial Resampling Particle Filter: An Effective and Efficient Method for Articulated Object Tracking,"Noname manuscript No. (will be inserted by the editor) Combinatorial Resampling Particle Filter: an Effective and Efficient Method for Articulated Object Tracking Christophe Gonzales · S´everine Dubuisson Received: date / Accepted: date" 710ce8cf25f31df8547b888519b414187e989257,Amygdala activation predicts gaze toward fearful eyes.,"The Journal of Neuroscience, July 15, 2009 • 29(28):9123–9126 • 9123 Brief Communications Amygdala Activation Predicts Gaze toward Fearful Eyes Matthias Gamer and Christian Bu¨chel Department of Systems Neuroscience, University Medical Center Hamburg-Eppendorf, D-20246 Hamburg, Germany The human amygdala can be robustly activated by presenting fearful faces, and it has been speculated that this activation has functional relevance for redirecting the gaze toward the eye region. To clarify this relationship between amygdala activation and gaze-orienting behavior, functional magnetic resonance imaging data and eye movements were simultaneously acquired in the current study during the evaluation of facial expressions. Fearful, angry, happy, and neutral faces were briefly presented to healthy volunteers in an event-related manner. We con- trolled for the initial fixation by unpredictably shifting the faces downward or upward on each trial, such that the eyes or the mouth were presentedatfixation.Acrossemotionalexpressions,participantsshowedabiastoshifttheirgazetowardtheeyes,butthemagnitudeofthiseffect followed the distribution of diagnostically relevant regions in the face. Amygdala activity was specifically enhanced for fearful faces with the mouth aligned to fixation, and this differential activation predicted gazing behavior preferentially targeting the eye region. These results reveal direct role of the amygdala in reflexive gaze initiation toward fearfully widened eyes. They mirror deficits observed in patients with amygdala lesions and open a window for future studies on patients with autism spectrum disorder, in which deficits in emotion recognition, probably related to atypical gaze patterns and abnormal amygdala activation, have been observed. Introduction The human amygdala is known to be robustly activated by the presentation of fearful faces (Morris et al., 1996; Hariri et al., 002; Gla¨scher et al., 2004; Reinders et al., 2005), which seems to" 71edcfe5e3a4e1678698a0659a7e51555291d242,Who's that Actor? Automatic Labelling of Actors in TV Series Starting from IMDB Images,"Who’s that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images Rahaf Aljundi(cid:63), Punarjay Chakravarty(cid:63) and Tinne Tuytelaars KU Leuven, ESAT-PSI, iMinds, Belgium" 71f969fdc6990b21536c5662c52110d7fdb29028,Driver Gaze Tracking and Eyes Off the Road Detection System Using a Depth Camera,"X Encontro de Alunos e Docentes do DCA/FEEC/UNICAMP (EADCA) X DCA/FEEC/University of Campinas (UNICAMP) Workshop (EADCA) Campinas, 26 e 27 de outubro de 2017 Campinas, Brazil, October 26-27, 2017 Driver Gaze Tracking and Eyes Off the Road Detection System Using a Depth Camera Ribeiro, Rafael F. , Costa, P. D. P (Orientador) Dept. of Computer Engineering and Industrial Automation (DCA) School of Electrical and Computer Engineering (FEEC) University of Campinas (Unicamp) Postal Code 6101, 13083-970 – Campinas, SP, Brazil" 71f1e72670e676b6902cce0d6fc0b4f63b46ca28,Survey paper : Face Detection and Face Recognition,"Survey paper: Face Detection and Face Recognition By Hyun Hoi James Kim . Introduction Face recognition is one of biometric methods identifying individuals by the features of face. Research in this rea has been conducted for more than 30 years; as a result, the current status of face recognition technology is well advanced. Many commercial applications of face recognition are also available such as criminal identification, security system, image and film processing. From the sequence of images captured by camera, the goal is to find best match with given image. Using a pre-stored image database, the face recognition system should be able to identify or verify one or more persons in the scene. Before face recognition is performed, the system should determine whether or not there is a face in a given image or given video, a sequence of images. This process is called face detection. Once a face is detected, face region should be isolated from the scene for the face recognition. The face detection and face extraction are often performed simultaneously. The overall process is depicted in Fig 1. Identification or Verification Feature Extraction Face Detection Face Recognition Input" 71dcbca34d71bda0bc41c33c04d2c1a740274feb,An Innovative Mean Approach for Plastic Surgery Face Recognition,"International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2014): 6.14 | Impact Factor (2014): 4.438 An Innovative Mean Approach for Plastic Surgery Face Recognition Mahendra P. Randive1, Umesh W. Hore2 Student of M.E., Department of Electronics & Telecommunication Engineering, P. R. Patil College of Engineering, Amravati Maharashtra – India Assistant Professor, Department of Electronics & Telecommunication Engineering, P. R. Patil College of Engineering, Amravati Maharashtra – India" 71f7be73a575f3689b0137446289d02462e1c5b0,Adaptive Multi-Scale Information Flow for Object Detection.,"CHEN ET AL.: ADAPTIVE MULTI-SCALE INFORMATION FLOW FOR DETECTION Adaptive Multi-Scale Information Flow for Object Detection Xiaoyu Chen Wei Li Qingbo Wu Fanman Meng School of Information and Communication Engineering University of Electronic Science and Technology of China" 713f7659eba67f12c0a3ce44518a11d9b748e225,Depth superresolution using motion adaptive regularization,"Depth Superresolution using Motion Adaptive Regularization Ulugbek S. Kamilov∗ and Petros T. Boufounos September 11, 2018" 712237121aa189179ac216bee7ecd5eaa79aff56,Prevention of Problem Gambling : A Comprehensive Review of the Evidence,"University of Lethbridge Research Repository Faculty Research and Publications http://opus.uleth.ca Williams, Robert 008-12-01 Prevention of Problem Gambling: A Comprehensive Review of the Evidence Williams, Robert J. Prepared for the Ontario Problem Gambling Research Centre Williams, R. J., West, B. L., & Simpson, R. I. (2008). Prevention of problem gambling: A omprehensive review of the evidence. Report prepared for the Ontario Problem Gambling Research Centre, Guelph, Ontario, CANADA. Dec 1, 2007 [Revised December 1, 2008]. http://hdl.handle.net/10133/414 Downloaded from University of Lethbridge Research Repository, OPUS" 71dcf25a3ea3801f09d6cc446dbf78e22481d609,Face recognition with the continuous n-tuple classifier.,"FaceRecognitionwiththecontinuous n-tupleclassi(cid:12)er S.M.Lucas DepartmentofElectronicSystemsEngineering UniversityofEssex ColchesterCOSQ,UK" 712609494dd049b44ebfd82698b9305ef07f027b,Biometric bits extraction through phase quantization based on feature level fusion,"Telecommun Syst (2011) 47:255–273 DOI 10.1007/s11235-010-9317-z Biometric bits extraction through phase quantization based on feature level fusion Hyunggu Lee · Andrew Beng Jin Teoh · Jaihie Kim Published online: 4 June 2010 © Springer Science+Business Media, LLC 2010" 710011644006c18291ad512456b7580095d628a2,Learning Residual Images for Face Attribute Manipulation,"Learning Residual Images for Face Attribute Manipulation Wei Shen Rujie Liu Fujitsu Research & Development Center, Beijing, China. {shenwei," 713345804a00c6c0083e4155b904956bb95949da,Scalable Normalized Cut with Improved Spectral Rotation,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 71424a706a2e4b9bc5fd049aefe83d73873c0145,How Unlabeled Web Videos Help Complex Event Detection?,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) positive videosunlabeled web videosObjectfish, human……Actionpull, stand……Scenelake, river……helpful videosharmful videos concepts in positive videosFigure1:Anexampleshowingtheinfluenceofunlabeledwebvideosw.r.tthedetectionoftheeventlandingafish.detection,traditionalapproachesrelyonintroducingsomeexternalsourcesthatarerelevanttothetargetevents.Someresearchesassignedsoftlabelstorelatedexemplarsbyassess-ingtheir“relatedness”withrespecttothepositiveones.Withvariousconceptselectionstrategies,Yeetal.andMaetal.madeuseofhigh-levelconceptsourcessuchasSINdatasettofacilitatethecomplexeventdetection[Yeetal.,2015].In[Duanetal.,2012],event-relatedwebvideoswerefilteredouttohelpdetectcomplexevents.Generally,suchexternalsourcesusedbyextantmethodsareartificiallypickedandla-beled.However,buildingtheseexternaldatausuallyrequiresprofessionalhumanannotators,andtheprocedureistootime-consumingandcostlytoscale.Onthecontrary,thereareplentyoflow-costunlabeledvideosontheweb,whichmighthavesignificantinformationforthecomplexeventdetection.Asaresult,itwouldbebeneficialtoexploitamoreflexibleapproachwhichisabletoutilizetheeasy-to-getunlabeledwebvideostogetherwiththelimitedlabeleddata.Opensourcevideos,i.e.,unlabeledwebvideoswithout" 71406b7358812400d0626e8d62e7eb38cea99bbe,PAID I ON IMPROVING FACE DETECTION PERFORMANCE BY MODELLING CONTEXTUAL INFORMATION,"ON IMPROVING FACE DETECTION PERFORMANCE BY MODELLING CONTEXTUAL INFORMATION Cosmin Atanasoaei Chris McCool Sébastien Marcel Idiap-RR-43-2010 DECEMBER 2010 Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" 71f98c3f7a5b02ab193110d5ae9f9d48a1c5ec38,Deep Human Parsing with Active Template Regression,"Deep Human Parsing with Active Template Regression Xiaodan Liang, Si Liu, Xiaohui Shen, Jianchao Yang, Luoqi Liu, Jian Dong, Liang Lin, Shuicheng Yan, Senior Member, IEEE" 71b376dbfa43a62d19ae614c87dd0b5f1312c966,The temporal connection between smiles and blinks,"The Temporal Connection Between Smiles and Blinks Laura C. Trutoiu, Jessica K. Hodgins, and Jeffrey F. Cohn" 7128f1239cbd1007ef19d8fd8cdab083d33a6984,"Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition","Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition Pei Guo, Ryan Farrell Computer Science Department Brigham Young University" 71ab53b0b3635411d5985f71cc56bb1784023834,RoboCupRescue 2012 - Robot League Team,"RoboCupRescue 2012 - Robot League Team Hector Darmstadt (Germany) Thorsten Graber2, Stefan Kohlbrecher1, Johannes Meyer2, Karen Petersen1, Oskar von Stryk1, Uwe Klingauf2(cid:63) Department of Computer Science (1) and Department of Mechanical Engineering (2), Technische Universit¨at Darmstadt, Karolinenplatz 5, D-64289 Darmstadt, Germany E-Mail: Web: www.gkmm.tu-darmstadt.de/rescue" 711801297f23df9ac8ca1c2d3c9d7dfa2ed12043,Enhancing Energy Efficiency of Multimedia Applications in Heterogeneous Mobile Multi-Core Processors,"Contention-Aware Fair Scheduling for Asymmetric Single-ISA Multicore Systems Adrian Garcia-Garcia , Juan Carlos Saez , and Manuel Prieto-Matias" 71403805e67eeb6ec336e0cb83646fdb7c819757,Visual Strategies for Sparse Spike Coding,"Visual Strategies for Sparse Spike Coding Laurent Perrinet Manuel Samuelides ONERA/DTIM, , av. Belin, 1055 Toulouse, France" 71fd29c2ae9cc9e4f959268674b6b563c06d9480,End-to-end 3D shape inverse rendering of different classes of objects from a single input image,"End-to-end 3D shape inverse rendering of different classes of objects from a single input image Shima Kamyab1 and S. Zohreh Azimifar1 Computer Science and Engineering and Information Technology, Shiraz university, Shiraz, Iran November 17, 2017" 70bfe8dfd9c9b05c8854a5d4aca9c3ee3a3b7eff,3 D Object Reconstruction using Multiple Views,"!, >A?J 4A?IJHK?JE KIEC KJEFA 8EAMI ,CD E ,AF=HJAJ B +FKJAH 5?EA?A 5J=JEIJE?I 7ELAHIEJO B ,K>E 6HEEJO +ACA ) JDAIEI J JDA 7ELAHIEJO B ,K>E 6HEEJO +ACA E BKAJ B JDA HAGKEHAAJI BH JDA B ,?JH B 2DEIFDO 5AFJA>AH" 706236308e1c8d8b8ba7749869c6b9c25fa9f957,Crowdsourced data collection of facial responses,"Crowdsourced Data Collection of Facial Responses Daniel McDuff MIT Media Lab Cambridge 02139, USA Rosalind Picard MIT Media Lab Cambridge 02139, USA Rana el Kaliouby MIT Media Lab Cambridge 02139, USA" 70ce1a17f257320fc718d61964b21e7aeabd8cd5,Person re-identification with fusion of hand-crafted and deep pose-based body region features,"Person re-identification with fusion of hand-crafted and deep pose-based body region features Jubin Johnson1 Shunsuke Yasugi2 Yoichi Sugino2 Sugiri Pranata1 Panasonic R&D Center Singapore Shengmei Shen1 Panasonic Corporation Core Element Technology Development Center Japan http://www.prdcsg.panasonic.com.sg/" 70c58700eb89368e66a8f0d3fc54f32f69d423e1,In Unsupervised Spatio-temporal Feature Learning,"INCORPORATING SCALABILITY IN UNSUPERVISED SPATIO-TEMPORAL FEATURE LEARNING Sujoy Paul, Sourya Roy and Amit K. Roy-Chowdhury Dept. of Electrical and Computer Engineering, University of California, Riverside, CA 92521" 70f0636b14b9e3916a780d70a5c712e8fea739da,"On Artefact Reduction , Segmentation and Classification of 3 D Computed Tomography Imagery in Baggage Security Screening","CRANFIELD UNIVERSITY SCHOOL OF ENGINEERING PhD THESIS Academic Year 2013-2014 ANDRE MOUTON On Artefact Reduction, Segmentation and Classification of D Computed Tomography Imagery in Baggage Security Screening Supervised by: Dr Toby Breckon and Dr Carol Armitage March 2014 This thesis is submitted in partial fulfilment of the requirements for the Degree of Doctor of Philosophy ©Cranfield University, 2014. All rights reserved. No part of this publication may be reproduced without the written permission of the copyright holder." 70480ee0e636a77f6289be98ae39300a584808f6,Iterative Robust Registration Approach based on Feature Descriptors Correspondence - Application to 3D Faces Description,"Iterative Robust Registration Approach based on Feature Descriptors Correspondence Application to 3D Faces Description Cristal lab.Grift research group, National School of Computer Science, La Mannouba, Tunisia Wieme Gadacha and Faouzi Ghorbel Keywords: D Rigid Registration, Hausdorff Distance in Shape Space, 3D Parametrisation, Matching, Face Description, Shannon Theorem." 70f3d3d9a7402a0f62a5646a16583c6c58e3b07a,"An Architecture for Deep, Hierarchical Generative Models","An Architecture for Deep, Hierarchical Generative Models Philip Bachman Maluuba Research" 70b42bbd76e6312d39ea06b8a0c24beb4a93e022,Solving Multiple People Tracking in a Minimum Cost Arborescence,"Solving Multiple People Tracking In A Minimum Cost Arborescence Institut f¨ur Informationsverarbeitung Institute of Geodesy and Photogrammetry Laura Leal-Taix´e ETH Z¨urich Roberto Henschel Universit¨at Hannover Bodo Rosenhahn Institut f¨ur Informationsverarbeitung Universit¨at Hannover . Introduction For many applications of computer vision, it is neces- sary to localize and track humans that appear in a video sequence. Multiple people tracking has thus evolved as an ongoing research topic in the computer vision domain. A commonly used approach to solve the data associa- tion problem within the tracking task is to apply a hierarchi- al tracklet framework [5]. Although there has been great progress in such a model, mainly due to its good bootstrap- ping capabilities, so far little attention has been drawn to" 70bf1769d2d5737fc82de72c24adbb7882d2effd,Face detection in intelligent ambiences with colored illumination,"Face detection in intelligent ambiences with colored illumination Christina Katsimerou, Judith A. Redi, Ingrid Heynderickx Department of Intelligent Systems TU Delft Delft, The Netherlands" 70c38203d9bf5ff3a6f4639a1fb13dcaab233a61,Occlusion-robust Detector Trained with Occluded Pedestrians, 708355d319a88485fdbbea3524104982b8cf37c2,2D/3D Sensor Exploitation and Fusion for Enhanced Object Detection,"D/3D Sensor Exploitation and Fusion for Enhanced Object Detection Jiejun Xu HRL Laboratories LLC Kyungnam Kim HRL Laboratories LLC Zhiqi Zhang HRL Laboratories LLC Hai-wen Chen HRL Laboratories LLC Yuri Owechko HRL Laboratories LLC" 70f0f0ad8fcf45538bbb49dd339e16ba3a0033e0,Mobile Biometrics ( MoBio ) : Joint Face and Voice Verification for a Mobile Platform,"Mobile Biometrics (MoBio): Joint Face and Voice Verification for a Mobile Platform P. A. Tresadern, C. McCool, N. Poh, P. Matejka, A. Hadid, C. Levy, T. F. Cootes and S. Marcel" 70109c670471db2e0ede3842cbb58ba6be804561,Zero-Shot Visual Recognition via Bidirectional Latent Embedding,"Noname manuscript No. (will be inserted by the editor) Zero-Shot Visual Recognition via Bidirectional Latent Embedding Qian Wang · Ke Chen Received: date / Accepted: date" 70e79d7b64f5540d309465620b0dab19d9520df1,Facial Expression Recognition System Using Extreme Learning Machine,"International Journal of Scientific & Engineering Research, Volume 8, Issue 3, March-2017 ISSN 2229-5518 Facial Expression Recognition System Using Extreme Learning Machine Firoz Mahmud, Dr. Md. Al Mamun" 7026aa20d83800aff72f2e13d02770d1e42acd2d,A Tale of Two Losses : Discriminative Deep Feature Learning for Person Re-Identification,"A Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-Identification Borgia, A., Hua, Y., & Robertson, N. (2017). A Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-Identification. In Irish Machine Vision and Image Processing Conference 2017: Proceedings Published in: Irish Machine Vision and Image Processing Conference 2017: Proceedings Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights © 2017 National University of Ireland Maynooth. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to ensure that content in the Research Portal does not infringe any person's rights, or applicable UK laws. If you discover content in the" 70b0538af40672e3be4b72f97cec486693d5204f,Mixture component identification and learning for visual recognition,"Mixture Component Identification and Learning for Visual Recognition Omid Aghazadeh, Hossein Azizpour, Josephine Sullivan, and Stefan Carlsson Computer Vision and Active Perception laboratory (CVAP), KTH, Sweden" 7099e4a8b01b5cf22f9f9ecbfbed16bb44d3d76d,A Regularized Framework for Feature Selection in Face Detection and Authentication,"A Regularized Framework for Feature Selection in Face Detection nd Authentication Augusto Destrero, Christine De Mol, Francesca Odone, Alessandro Verri, 2008 Present By Mr. Apichon Witayangkurn, CSIM ID: 106800 AT70.9011: Machine Vision for Robotics and HCI, Summer 2009" 70f189798c8b9f2b31c8b5566a5cf3107050b349,The challenge of face recognition from digital point-and-shoot cameras,"The Challenge of Face Recognition from Digital Point-and-Shoot Cameras J. Ross Beveridge∗ Geof H. Givens§ W. Todd Scruggs¶ P. Jonathon Phillips† Yui Man Lui∗ Kevin W. Bowyer(cid:107) David Bolme‡ Mohammad Nayeem Teli∗ Patrick J. Flynn(cid:107) Bruce A. Draper∗, Hao Zhang∗ Su Cheng†" 7056a051e0589ab6aa299c7d2a31588800b8c93e,Facial expression recognition and histograms of oriented gradients: a comprehensive study,"Carcagnì et al. SpringerPlus (2015) 4:645 DOI 10.1186/s40064-015-1427-3 RESEARCH Facial expression recognition nd histograms of oriented gradients: a omprehensive study Pierluigi Carcagnì*†, Marco Del Coco†, Marco Leo† and Cosimo Distante† Open Access *Correspondence: Pierluigi Carcagnì, Marco Del Coco, Marco Leo and Cosimo Distante contributed equally to this work National Research Council of Italy, Institute of Applied Sciences and Intelligent Systems, Via della Libertà, 3, 73010 Arnesano , LE, Italy" 70bb5c2570673eae86a3f9ced55c7ef00e0be8b5,Combinaison de Descripteurs Hétérogènes pour la Reconnaissance de Micro-Mouvements Faciaux,"Combinaison de Descripteurs Hétérogènes pour la Reconnaissance de Micro-Mouvements Faciaux. Vincent Rapp1, Thibaud Senechal1, Hanan Salam2, Lionel Prevost3, Renaud Seguier2, Kevin Bailly1 ISIR - CNRS UMR 7222 Université Pierre et Marie Curie, Paris {rapp, senechal, Supelec - ETR (UMR 6164) Avenue de la Boulaie, 35511, Cesson-Sevigne {salam, LAMIA - EA 4540 Université des Antilles et de la Guyanne Résumé Dans cet article, nous présentons notre réponse au premier hallenge international sur la reconnaissance et l’analyse d’émotions faciales (Facial Emotion Recognition and Ana- lysis Challenge). Nous proposons une combinaison de dif- férents types de descripteurs dans le but de détecter de ma- nière automatique, les micro-mouvements faciaux d’un vi- sage. Ce système utilise une Machine à Vecteurs Supports" 70e90b9df5b8617ef6636c5492db727f9d48d0ec,People Search with Textual Queries About Clothing Appearance Attributes,"People search with textual queries about lothing appearance attributes Riccardo Satta, Federico Pala, Giorgio Fumera, and Fabio Roli" 706b9767a444de4fe153b2f3bff29df7674c3161,Fast Metric Learning For Deep Neural Networks,"Fast Metric Learning For Deep Neural Networks Henry Gouk1, Bernhard Pfahringer1, and Michael Cree2 Department of Computer Science, University of Waikato, Hamilton, New Zealand School of Engineering, University of Waikato, Hamilton, New Zealand" 70af8e4ff3c029aea788bc28b45c56932b50c056,Robust Facial Landmark Detection Using a Mixture of Synthetic and Real Images with Dynamic Weighting : A Survey,"Om Prakash Gupta et al. 2016, Volume 4 Issue 1 ISSN (Online): 2348-4098 ISSN (Print): 2395-4752" 703d4f376eb2379ccce814c729d15f1165312167,Location Prediction on Trajectory Data : A Review,"BIG DATA MINING AND ANALYTICS ISSN 2096-0654 02/06 pp108–127 Volume 1, Number 2, June 2018 DOI: 10.26599/BDMA.2018.9020010 Location Prediction on Trajectory Data: A Review Ruizhi Wu, Guangchun Luo(cid:3), Junming Shao, Ling Tian, and Chengzong Peng" 70671018d4597b6d2d0c99b38b1f1a3f1271eaec,Learning Representations Specialized in Spatial Knowledge: Leveraging Language and Vision,"Transactions of the Association for Computational Linguistics, vol. 6, pp. 133–144, 2018. Action Editor: Stefan Riezler. Submission batch: 6/2017; Revision batch: 9/2017; Published 2/2018. (cid:13)2018 Association for Computational Linguistics. Distributed under a CC-BY 4.0 license." 70920447b8300fd65745c0a884523e4d52d000ef,1 AUTOMATED CROWD DETECTION IN STADIUM ARENAS,"AUTOMATED CROWD DETECTION IN STADIUM ARENAS Loris Nanni, 1 Sheryl Brahnam, 2 Stefano Ghidoni, 1 Emanuele Menegatti1 DIE, University of Padua, Via Gradenigo, 6 - 35131- Padova – Italy e-mail: {loris.nanni, ghidoni, CIS, Missouri State University, 901 S. National, Springfield, MO 65804, USA e-mail:" 70990e1b13cec2b3e4831a00c6ac901dae76b27a,"Mareckova , Klara ( 2013 ) Sex differences and the role of sex hormones in face development and face processing","Mareckova, Klara (2013) Sex differences and the role of sex hormones in face development and face processing. PhD thesis, University of Nottingham. Access from the University of Nottingham repository: http://eprints.nottingham.ac.uk/13333/1/KlaraMareckova_PhDThesis_finalversion1.pdf Copyright and reuse: The Nottingham ePrints service makes this work by researchers of the University of Nottingham available open access under the following conditions. · Copyright and all moral rights to the version of the paper presented here belong to the individual author(s) and/or other copyright owners. To the extent reasonable and practicable the material made available in Nottingham ePrints has been checked for eligibility before being made available. · Copies of full items can be used for personal research or study, educational, or not- for-profit purposes without prior permission or charge provided that the authors, title nd full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way. · Quotations or similar reproductions must be sufficiently acknowledged. Please see our full end user licence at: http://eprints.nottingham.ac.uk/end_user_agreement.pdf A note on versions:" 7020df589ef9bf220d5289b0092a07b191534972,"An Automatic Feature Based Face Authentication System,","An Automatic Feature Based Face Authentication System Stefano Arca, Paola Campadelli, Elena Casiraghi, Ra(cid:11)aella Lanzarotti Dipartimento di Scienze dell’Informazione Universit(cid:18)a degli Studi di Milano Via Comelico, 39/41 20135 Milano, Italy farca, campadelli, casiraghi," 70560383cbf7c0dc5e9be1f2fd9efba905377095,Accelerating Online CP Decompositions for Higher Order Tensors,"Accelerating Online CP Decompositions for Higher Order Tensors Shuo Zhou1, Nguyen Xuan Vinh1, James Bailey1, Yunzhe Jia1, Ian Davidson2 Dept. of Computing and Information Systems, The University of Melbourne, Australia Dept. of Computer Science, University of California, Davis, USA" 708a55d65568faf8158417ddfb79e728b2b28f86,3D Body Model Construction and Matching for Real Time People Re-Identification,"Eurographics Italian Chapter Conference (2010) E. Puppo, A. Brogni, and L. De Floriani (Editors) D Body Model Construction and Matching for Real Time People Re-Identification D. Baltieri, R. Vezzani and R. Cucchiara Dipartimento di Ingegneria dell’Informazione University of Modena and Reggio Emilia Via Vignolese, 905 - 41100 Modena - Italy" 70e3c02575e4041519434e0dacb291bbb8791380,Generative 2D and 3D Human Pose Estimation with Vote Distributions,"Generative 2D and 3D Human Pose Estimation with Vote Distributions J¨urgen Brauer, Wolfgang H¨ubner, Michael Arens Fraunhofer Institute of Optronics, System Technologies and Image Exploitation {juergen.brauer, wolfgang.huebner, Gutleuthausstr. 1, 76275 Ettlingen, Germany" 70ec156f7e6de0275c7e4e95e35f1bc1e92e29b3,Deep Learning Ensembles for Melanoma Recognition in Dermoscopy Images,"Deep learning ensembles for melanoma recognition in dermoscopy images1 N. C. F. Codella, Q. B. Nguyen, S. Pankanti, D. Gutman, B. Helba, A. Halpern, J. R. Smith" ff398e7b6584d9a692e70c2170b4eecaddd78357,Face Recognition and Verification in Unconstrained Environments by Huimin Guo, ff7470805588ba1ea63bcd8992e48ac4e9ef9771,Séquences de maillages : classification et méthodes de segmentation. (Mesh sequences : classification and segmentation),"Séquences de maillages : classification et méthodes de segmentation Romain Arcila To cite this version: Romain Arcila. Séquences de maillages : classification et méthodes de segmentation. Ordinateur et société [cs.CY]. Université Claude Bernard - Lyon I, 2011. Français. . HAL Id: tel-00653542 https://tel.archives-ouvertes.fr/tel-00653542v3 Submitted on 26 Jun 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" ff01bc3f49130d436fca24b987b7e3beedfa404d,Fuzzy System-Based Face Detection Robust to In-Plane Rotation Based on Symmetrical Characteristics of a Face,"Article Fuzzy System-Based Face Detection Robust to In-Plane Rotation Based on Symmetrical Characteristics of a Face Hyung Gil Hong, Won Oh Lee, Yeong Gon Kim, Ki Wan Kim, Dat Tien Nguyen and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (H.G.H.); (W.O.L.); (Y.G.K.); (K.W.K.); (D.T.N.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Academic Editor: Angel Garrido Received: 15 June 2016; Accepted: 29 July 2016; Published: 3 August 2016" ffe3779c1102394ffc3c93846a8b5ee51340afeb,Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System,"Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System Lionel Heng1, Benjamin Choi1, Zhaopeng Cui2, Marcel Geppert2, Sixing Hu4, Benson Kuan1, Peidong Liu2, Rang Nguyen4, Ye Chuan Yeo1, Andreas Geiger3, Gim Hee Lee4, Marc Pollefeys2, and Torsten Sattler2" ffcbedb92e76fbab083bb2c57d846a2a96b5ae30,Sparse Dictionary Learning and Domain Adaptation for Face and Action Recognition, ff4dec12d0ba0bb1d2c6bbc194545819bc9c1e5a,Face Recognition at a Distance : System Issues,"Chapter 6 Face Recognition at a Distance: System Issues Meng Ao, Dong Yi, Zhen Lei, and Stan Z. Li" ff9195f99a1a28ced431362f5363c9a5da47a37b,Serial dependence in the perception of attractiveness,"Journal of Vision (2016) 16(15):28, 1–8 Serial dependence in the perception of attractiveness Ye Xia Department of Psychology, University of California, Berkeley, CA, USA Allison Yamanashi Leib Department of Psychology, University of California, Berkeley, CA, USA David Whitney Department of Psychology, University of California, Berkeley, CA, USA Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA Vision Science Group, University of California, Berkeley, CA, USA The perception of attractiveness is essential for choices of food, object, and mate preference. Like perception of other visual features, perception of attractiveness is stable despite constant changes of image properties due to factors like occlusion, visual noise, and eye" ffdaa12d37c720561f74d23fc3b5d47afa268000,Pose Proposal Networks,"Pose Proposal Networks Taiki Sekii[0000−0002−1895−3075] Konica Minolta, Inc." ff83aade985b981fbf2233efbbd749600e97454c,Towards Understanding Adversarial Learning for Joint Distribution Matching,"ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching Chunyuan Li1, Hao Liu2, Changyou Chen3, Yunchen Pu1, Liqun Chen1, Ricardo Henao1 and Lawrence Carin1 Duke University 2Nanjing University 3University at Buffalo" ff3fa31882bb9c7573a38c7d0883503a464522a6,Imcube @ MediaEval 2015 Placing Task: Hierarchical Approach for Geo-referencing Large-Scale Datasets,"Imcube MediaEval 2015 Placing Task: A Hierarchical Approach for Geo-referencing Large-Scale Datasets Pascal Kelm, Sebastian Schmiedeke, and Lutz Goldmann {kelm, schmiedeke, Imcube Labs GmbH Berlin, Germany" ff46c41e9ea139d499dd349e78d7cc8be19f936c,A Novel Method for Movie Character Identification and its Facial Expression Recognition,"International Journal of Modern Engineering Research (IJMER) www.ijmer.com Vol.3, Issue.3, May-June. 2013 pp-1339-1342 ISSN: 2249-6645 A Novel Method for Movie Character Identification and its Facial Expression Recognition M. Dharmateja Purna, 1 N. Praveen2 M.Tech, Sri Sunflower College of Engineering & Technology, Lankapalli Asst. Professor, Dept. of ECE, Sri Sunflower College of Engineering & Technology, Lankapalli" ff70cfaf3e085a6c32bfa7ebedb98adfb7658210,TABULA RASA Trusted Biometrics under Spoofing Attacks,"TABULA RASA Trusted Biometrics under Spoofing Attacks http://www.tabularasa-euproject.org/ Funded under the 7th FP (Seventh Framework Programme) [Trustworthy Information and Communication Technologies] Theme ICT-2009.1.4 D3.2: Evaluation of baseline non-ICAO iometric systems Due date: 30/09/2011 Project start date: 01/11/2010 Duration: 42 months WP Manager: Abdenour Hadid Revision: 0 Submission date: 30/09/2011 Author(s): Federico Alegre, Xuran Zhao, Nick Evans (EURECOM); John Bustard, Mark Nixon (USOU); Abdenour Hadid (UOULU); William Ketchantang, Sylvaine Picard, St´ephane Revelin (MORPHO); Ale- jandro Riera, Aureli Soria-Frisch (STARLAB); Gian Luca Marcialis (UNICA) Project funded by the European Commission in the 7th Framework Programme (2008-2010) Dissemination Level" ff1b253636c878f5b464a7623f36242327e6b485,Visual Place Recognition with Probabilistic Vertex Voting,"Visual Place Recognition with Probabilistic Vertex Voting Mathias Gehrig, Elena Stumm, Timo Hinzmann and Roland Siegwart Autonomous Systems Lab, ETH Zurich" ffeff854e7fcf5af663497be00c86537f7d9ed11,Face recognition in JPEG compressed domain: a novel coefficient selection approach,"SIViP (2015) 9:651–663 DOI 10.1007/s11760-013-0492-8 ORIGINAL PAPER Face recognition in JPEG compressed domain: a novel coefficient selection approach Mohammad-Shahram Moin · Alireza Sepas-Moghaddam Received: 14 October 2012 / Revised: 30 April 2013 / Accepted: 1 May 2013 / Published online: 4 June 2013 © Springer-Verlag London 2013" fff854b3d8f8e916162dc5451cf6f46caf50002b,Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks,"Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks Wasi Uddin Ahmad†, Xueying Bai∗, Zhechao Huang§, Chao Jiang∗, Nanyun Peng(cid:63), Kai-Wei Chang† §Fudan University, ∗University of Virginia (cid:63)University of Southern California, †University of California, Los Angeles" ffd81d784549ee51a9b0b7b8aaf20d5581031b74,Performance Analysis of Retina and DoG Filtering Applied to Face Images for Training Correlation Filters,"Performance Analysis of Retina and DoG Filtering Applied to Face Images for Training Correlation Filters Everardo Santiago Ram(cid:19)(cid:16)rez1, Jos(cid:19)e (cid:19)Angel Gonz(cid:19)alez Fraga1, Omar (cid:19)Alvarez Xochihua1, Everardo Gutierrez L(cid:19)opez1, and Sergio Omar Infante Prieto2 Facultad de Ciencias, Universidad Aut(cid:19)onoma de Baja California, Carretera Transpeninsular Tijuana-Ensenada, N(cid:19)um. 3917, Colonia Playitas, Ensenada, Baja California, C.P. 22860 {everardo.santiagoramirez,angel_fraga, Facultad de Ingenier(cid:19)(cid:16)a, Arquitectura y Dise~no, Universidad Aut(cid:19)onoma de Baja California, Carretera Transpeninsular Tijuana-Ensenada, N(cid:19)um. 3917, Colonia Playitas, Ensenada, Baja California, C.P. 22860" ff44d8938c52cfdca48c80f8e1618bbcbf91cb2a,Towards Video Captioning with Naming: A Novel Dataset and a Multi-modal Approach,"Towards Video Captioning with Naming: a Novel Dataset and a Multi-Modal Approach Stefano Pini, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara Dipartimento di Ingegneria “Enzo Ferrari” Universit`a degli Studi di Modena e Reggio Emilia" ff2e25cb67209de8ae922abdfc31f922b130276e,Chapter 25 Information Granulation and Pattern Recognition,"Chapter 25 Information Granulation and Pattern Recognition Andrzej Skowron,1 Roman W. Swiniarski2 Institute of Mathematics, Warsaw University, Banacha 2, 02-097 Warsaw, Poland San Diego State University, Department of Mathematical and Computer Sciences, 5500 Campanile Drive, San Diego, CA 92182, USA Summary. We discuss information granulation applications in pattern recognition. The chap- ter consists of two parts. In the first part, we present applications of rough set methods for feature selection in pattern recognition. We emphasize the role of different forms of reducts that are the basic constructs of the rough set approach in feature selection. In the overview of methods for feature selection, we discuss feature selection criteria based on the rough set pproach and the relationships between them and other existing criteria. Our algorithm for feature selection used in the application reported is based on an application of the rough set method to the result of principal component analysis used for feature projection and reduc- tion. Finally, the first part presents numerical results of face recognition experiments using a neural network, with feature selection based on proposed principal component analysis and rough set methods. The second part consists of an outline of an approach to pattern recog- nition with the application of background knowledge specified in natural language. The ap- proach is based on constructing approximations of reasoning schemes. Such approximations re called approximate reasoning schemes and rough neural networks." ffd73d1956163a4160ec2c96b3ab256f79fc92e8,Attributes as Semantic Units between Natural Language and Visual Recognition,"Attributes as Semantic Units between Natural Language and Visual Recognition Marcus Rohrbach" ffe8a4cef9dec30ddd2c956c2f63b128a4568f84,Intensity Video Guided 4D Fusion for Improved Highly Dynamic 3D Reconstruction,"Intensity Video Guided 4D Fusion for Improved Highly Dynamic 3D Reconstruction Jie Zhang, Christos Maniatis, Luis Horna and Robert B. Fisher" ffc8f9fe66a14aa0657e59e219364b5a852ecb8f,On the Utility of Context (or the Lack Thereof) for Object Detection,"On the Utility of Context (or the Lack Thereof) for Object Detection Ehud Barnea and Ohad Ben-Shahar Dept. of Computer Science, Ben-Gurion University Beer-Sheva, Israel {barneaeh," ffc9d6a5f353e5aec3116a10cf685294979c63d9,Eigenphase-based face recognition : a comparison of phase-information extraction methods,"Eigenphase-based face recognition: a comparison of phase- information extraction methods Slobodan Ribarić, Marijo Maračić Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10 000 Zagreb E-mail:" ff269353b4e49274ff85dfb98b531888c98da365,Master : a Mobile Autonomous Scientist for Terretrial and Extra-terrestrial Research,"MASTER: A MOBILE AUTONOMOUS SCIENTIST FOR TERRETRIAL AND EXTRA- TERRESTRIAL RESEARCH Iain Wallace (1), Mark Woods (2) (1) SCISYS, 23 Clothier Road, Bristol, BS4 5SS, UK, Email: (2) SCISYS, 23 Clothier Road, Bristol, BS4 5SS, UK, Email: paper includes utonomy. The INTRODUCTION" ff18125a8f549135e6320fed91d0002bd2dae635,Colour Terms: a Categorisation Model Inspired by Visual Cortex Neurons,"Colour Terms: a Categorisation Model Inspired by Visual Cortex Neurons Arash Akbarinia Centre de Visi´o per Computador Universitat Aut`onoma de Barcelona C. Alejandro Parraga Centre de Visi´o per Computador Universitat Aut`onoma de Barcelona" ffae2fe85d3c93610ac6270db2ddf1f2f6779ea8,Learning pullback HMM distances for action recognition,"#**** ICCV 2011 Submission #****. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. Learning pullback HMM distances for action recognition Anonymous ICCV submission Paper ID ****" ff3ec3607b77a1dbb685cf90dd23a273d622dda5,Visual Attribute Extraction Using Human Pose Estimation,"Visual Attribute Extraction using Human Pose Estimation Angelo Nodari, Marco Vanetti, and Ignazio Gallo Universit`a dell’Insubria, Dipartimento di Scienze Teoriche e Applicate via Mazzini 5, 21100 Varese, Italy" ffb2d596c22be7b0ed8f809fdfbeaa95bd4db835,"The BDD-Nexar Collective : A Large-Scale , Crowsourced , Dataset of Driving Scenes Vashisht Madhavan","The BDD-Nexar Collective: A Large-Scale, Crowsourced, Dataset of Driving Scenes Vashisht Madhavan Trevor Darrell Fisher Yu, Ed. Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2017-113 http://www2.eecs.berkeley.edu/Pubs/TechRpts/2017/EECS-2017-113.html May 29, 2017" fff12919cf912347776b70aa76af7635280dc401,Are object detection assessment criteria ready for maritime computer vision?,"Are object detection assessment criteria ready for maritime computer vision? Dilip K. Prasad1,∗, Deepu Rajan2, and Chai Quek2" ffcb92719dcd993dda292ca82d4585950ea22ac9,Handwritten Digit Recognition Using Convolutional Neural Networks,"ISSN(Online): 2320-9801 ISSN (Print): 2320-9798 International Journal of Innovative Research in Computer nd Communication Engineering (An ISO 3297: 2007 Certified Organization) Vol. 4, Issue 2, February 2016 Handwritten Digit Recognition Using Convolutional Neural Networks Haider A. Alwzwazy1, Hayder M. Albehadili2, Younes S. Alwan3, Naz E. Islam4 M.E Student, Dept. of Electrical and Computer Eng. University of Missouri-Columbia, MO, USA1,2,3 Professor, Dept. of Electrical and Computer Eng. University of Missouri-Columbia, MO, USA4" ff7de2ea4d21e7d32d7f07e07fd278bebf6b5d66,Comparative survey of visual object classifiers,"Comparative survey of visual object classifiers Laboratory Le2i, Universite Bourgogne - Franche-Comte, Hiliwi Leake Kidane 1000 Dijon, France," ff25c6602305ac46e9c35ffa4e30b14d679a5413,Face Templates Creation for Surveillance Face Recognition System,"Face Templates Creation for Surveillance Face Recognition System Department of Radio Electronics, Brno University of Technology, Brno, Czech Republic Department of Telecommunications, Brno University of Technology, Brno, Czech Republic Tobias Malach1,2 and Jiri Prinosil3 EBIS, spol. s r.o., Brno, Czech Republic Keywords: Face Templates, Template Database Creation, Face Recognition System Application, Real-world Conditons." ff8ef43168b9c8dd467208a0b1b02e223b731254,BreakingNews: Article Annotation by Image and Text Processing,"BreakingNews: Article Annotation by Image and Text Processing Arnau Ramisa*, Fei Yan*, Francesc Moreno-Noguer, nd Krystian Mikolajczyk" ab98abfbdfd700c27bee31ca1f8850db72120c5d,Video Event Detection by Exploiting Word Dependencies from Image Captions,"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3318–3327, Osaka, Japan, December 11-17 2016." ab58a7db32683aea9281c188c756ddf969b4cdbd,Efficient Solvers for Sparse Subspace Clustering,"Efficient Solvers for Sparse Subspace Clustering Farhad Pourkamali-Anaraki and Stephen Becker" ab03a1656d9e45c80379512161f6c90dfbb0b6b3,Active Learning for Regression Tasks with Expected Model Output Changes,"KÄDING ET AL.: ACTIVE LEARNING FOR REGRESSION TASKS WITH EMOC Active Learning for Regression Tasks with Expected Model Output Changes Computer Vision Group Friedrich Schiller University Jena Jena, Germany Carl Zeiss AG Jena, Germany Christoph Käding1 Erik Rodner2 Alexander Freytag2 Oliver Mothes1 Björn Barz1 Joachim Denzler1" abfcafaa765433b8f5b8be7eae392a8daec54b8e,Facial EMG Responses to Emotional Expressions Are Related to Emotion Perception Ability,"Facial EMG Responses to Emotional Expressions Are Related to Emotion Perception Ability Janina Ku¨ necke1*, Andrea Hildebrandt1, Guillermo Recio1,2, Werner Sommer1, Oliver Wilhelm2 Department of Psychology, Humboldt Universita¨t zu Berlin, Berlin, Germany, 2 Department of Psychology, University Ulm, Ulm, Germany" aba1669b44f853d94f45baf8f28b37b48f469ed7,Image Classification by Sparse Representation-based Transduction,"Sparse Graph-based Transduction for Image Classification Sheng Huanga, Dan Yanga,∗, Jia Zhoua, Luwen Huangfub, Xiaohong Zhangc,d College of Computer Science at Chongqing University, Chongqing, 400044, P.R.C Eller College of Management at University of Arizona, Tucson, AZ, 85712, USA School of Software Engineering at Chongqing University, Chongqing, 400044, P.R.C dMinistry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society, Chongqing, 400044, P.R.C" abeda55a7be0bbe25a25139fb9a3d823215d7536,Understanding Human-Centric Images: From Geometry to Fashion,"UNIVERSITATPOLITÈCNICADECATALUNYAProgramadeDoctorat:AUTOMÀTICA,ROBÒTICAIVISIÓTesiDoctoralUnderstandingHuman-CentricImages:FromGeometrytoFashionEdgarSimoSerraDirectors:FrancescMorenoNoguerCarmeTorrasMay2015" ab969cfae95f62d68c61830128b35786eb6c84a9,Contents 1 Introduction 2,"Contents1Introduction22Tracking:FundamentalNotions22.1Trackingbydetection........................................22.2TrackingusingFlow........................................22.3Flowmodelsfromkinematicmodels................................22.4TrackingwithProbability......................................23Tracking:Relationsbetween3Dand2D23.1KinematicInferencewithMultipleViews.............................23.2Liftingto3D............................................33.3MultipleModes,RandomizedSearchandHumanTracking....................34Tracking:DataAssociationforHumanTracking54.1DetectingHumans.........................................54.2TrackingbyMatchingRevisited..................................64.3Evaluation..............................................75MotionSynthesisandAnimation95.1Motioncapture...........................................95.2Footskate..............................................95.3ResolvingKinematicAmbiguitieswithExamples.........................95.4MotionSignalProcessing......................................95.5MotionGraphs...........................................95.6MotionPrimitives..........................................105.7EnrichingaMotionCollection...................................105.8MotionfromPhysicalConsiderations...............................105.8.1SimplifiedCharacters....................................105.8.2ModifiedPhysics......................................115.8.3ReducedDimensions....................................115.8.4ModifyingExistingMotions................................116DescribingActivities126.1WhatshouldanActivityRepresentationdo?............................126.1.1NecessaryPropertiesofanActivityRepresentation....................136.1.2WhatDataisAvailable?..................................136.2MiscellaneousMethods.......................................146.2.1ActivityRepresentationMethodsbasedaroundTemporalLogics.............146.2.2ActivityRepresentationMethodsbasedonTemplates...................146.3ActivityRepresentationusingHiddenMarkovModelsandFiniteStateRepresentations.....146.4TheSpeechAnalogy........................................146.4.1FiniteStateTransducers..................................156.4.2WhyshouldweCare?...................................156.5ActivityRecognitionMethodsbasedaroundHMM’s.......................166.6SignLanguageRecognition.....................................176.7Morerecentmaterial........................................171" abba22ed4713a5ee5fa91fcf7b8dde58a9b621db,Acquisition of a 3D Audio-Visual Corpus of Affective Speech,"BIWI Technical Report n. 270 Acquisition of a 3D Audio-Visual Corpus of Affective Speech Gabriele Fanelli, Juergen Gall, Harald Romsdorfer, Thibaut Weise, nd Luc Van Gool" aba770a7c45e82b2f9de6ea2a12738722566a149,Face Recognition in the Scrambled Domain via Salience-Aware Ensembles of Many Kernels,"Face Recognition in the Scrambled Domain via Salience-Aware Ensembles of Many Kernels Jiang, R., Al-Maadeed, S., Bouridane, A., Crookes, D., & Celebi, M. E. (2016). Face Recognition in the Scrambled Domain via Salience-Aware Ensembles of Many Kernels. IEEE Transactions on Information Forensics and Security, 11(8), 1807-1817. DOI: 10.1109/TIFS.2016.2555792 Published in: Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights (c) 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to" ab1719f573a6c121d7d7da5053fe5f12de0182e7,Combining visual recognition and computational linguistics : linguistic knowledge for visual recognition and natural language descriptions of visual content,"Combining Visual Recognition nd Computational Linguistics Linguistic Knowledge for Visual Recognition nd Natural Language Descriptions of Visual Content Thesis for obtaining the title of Doctor of Engineering Science (Dr.-Ing.) of the Faculty of Natural Science and Technology I of Saarland University Marcus Rohrbach, M.Sc. Saarbrücken March 2014" ab450a7968555532d9ea79f81189c0d52f9c5f11,RGB-D Face Recognition in Surveillance Videos,"RGB-D Face Recognition in Surveillance Videos Anurag Chowdhury IIIT-D-MTech-CS-GEN-14-002 June 23, 2016 Indraprastha Institute of Information Technology Delhi New Delhi Thesis Advisors Dr. Richa Singh Dr. Mayank Vatsa Submitted in partial fulfillment of the requirements for the Degree of M.Tech. in Computer Science (cid:13) Chowdhury, 2016 Keywords : RGB-D, Kinect, Face Detection, Face Recognition, Deep Learning" ab8fb278db4405f7db08fa59404d9dd22d38bc83,Implicit and automated emotional tagging of videos,"UNIVERSITÉ DE GENÈVE Département d'Informatique FACULTÉ DES SCIENCES Professeur Thierry Pun Implicit and Automated Emotional Tagging of Videos THÈSE présenté à la Faculté des sciences de l'Université de Genève pour obtenir le grade de Docteur ès sciences, mention informatique Mohammad SOLEYMANI Téhéran (IRAN) Thèse No 4368 GENÈVE Repro-Mail - Université de Genève" ab69f49fedb6936ce04b2e9d1f161772b2f24b7d,Architecture-aware optimization of an HEVC decoder on asymmetric multicore processors,"(will be inserted by the editor) Architecture-Aware Optimization of an HEVC decoder on Asymmetric Multicore Processors Rafael Rodr´ıguez-S´anchez · Enrique S. Quintana-Ort´ı Received: date / Revised: date" ab559473a01836e72b9fb9393d6e07c5745528f3,cGANs with Projection Discriminator,"Published as a conference paper at ICLR 2018 CGANS WITH PROJECTION DISCRIMINATOR Takeru Miyato1, Masanori Koyama2 Preferred Networks, Inc. 2Ritsumeikan University" abc4d51d510cd8222484f7f4f11a739e8bce42ff,On Fast Non-metric Similarity Search by Metric Access Methods,"On Fast Non-metric Similarity Search y Metric Access Methods Tom´aˇs Skopal Charles University in Prague, FMP, Department of Software Engineering, Malostransk´e n´am. 25, 118 00 Prague 1, Czech Republic" ab87ab1cf522995510561cd9f494223704f1de91,Human Centric Facial Expression Recognition,"Human Centric Facial Expression Recognition K. Clawson 1*, L. S. Delicato, 2** and C. Bowerman, 1*** Faculty of Computer Science, University of Sunderland, Sunderland, SR1 3SD, UK . Faculty of Health, Sciences and Wellbeing, University of Sunderland, SR1 3QR, UK Facial expression recognition (FER) is an area of active research, both in computer science and in ehavioural science. Across these domains there is evidence to suggest that humans and machines find it easier to recognise certain emotions, for example happiness, in comparison to others. Recent ehavioural studies have explored human perceptions of emotion further, by evaluating the relative ontribution of features in the face when evaluating human sensitivity to emotion. It has been identified that certain facial regions have more salient features for certain expressions of emotion, especially when emotions are subtle in nature. For example, it is easier to detect fearful expressions when the eyes are expressive. Using this observation as a starting point for analysis, we similarly examine the effectiveness with which knowledge of facial feature saliency may be integrated into urrent approaches to automated FER. Specifically, we compare and evaluate the accuracy of ‘full- face’ versus upper and lower facial area convolutional neural network (CNN) modelling for emotion recognition in static images, and propose a human centric CNN hierarchy which uses regional image inputs to leverage current understanding of how humans recognise emotions across the face. Evaluations using the CK+ dataset demonstrate that our hierarchy can enhance classification ccuracy individual CNN architectures, achieving overall true positive" ab8778793b0f2f06d9e97b6277f3b1125f31432c,Stochastic Models for Face Image Analysis,"Stochastic Models for Face Image Analysis St(cid:19)ephane Marchand-Maillet and Bernard M(cid:19)erialdo Department of Multimedia Communications Institut EURECOM { B.P.     Sophia-Antipolis { France" ab989225a55a2ddcd3b60a99672e78e4373c0df1,"Sample, computation vs storage tradeoffs for classification using tensor subspace models","Sample, Computation vs Storage Tradeoffs for Classification Using Tensor Subspace Models Mohammadhossein Chaghazardi and Shuchin Aeron, Senior Member, IEEE" ab2b09b65fdc91a711e424524e666fc75aae7a51,Multi-modal Biomarkers to Discriminate Cognitive State *,"Multi-modal Biomarkers to Discriminate Cognitive State* Thomas F. Quatieri 1, James R. Williamson1, Christopher J. Smalt1, Joey Perricone, Tejash Patel, Laura Brattain, Brian S. Helfer, Daryush D. Mehta, Jeffrey Palmer Kristin Heaton2, Marianna Eddy3, Joseph Moran3 MIT Lincoln Laboratory, Lexington, Massachusetts, USA USARIEM, 3NSRDEC . Introduction Multimodal biomarkers based on behavorial, neurophysiolgical, and cognitive measurements have recently obtained increasing popularity in the detection of cognitive stress- and neurological-based disorders. Such conditions are significantly and adversely affecting human performance and quality of life for a large fraction of the world’s population. Example modalities used in detection of these onditions include voice, facial expression, physiology, eye tracking, gait, and EEG analysis. Toward the goal of finding simple, noninvasive means to detect, predict and monitor cognitive stress and neurological conditions, MIT Lincoln Laboratory is developing biomarkers that satisfy three criteria. First, we seek biomarkers that reflect core components of cognitive status such as working memory capacity, processing speed, attention, and arousal. Second, and as importantly, we seek biomarkers that reflect timing and coordination relations both within components of each modality and across different modalities. This is based on the hypothesis that neural coordination cross different parts of the brain is essential in cognition (Figure 1). An example of timing and oordination within a modality is the set of finely timed and synchronized physiological" ab02c78c9cc4ab80da45def34f0cf2c1b54fd8ed,Multi-agent path topology in support of socially competent navigation planning,"Article Multi-agent path topology in support of socially competent navigation planning The International Journal of Robotics Research © The Author(s) 2018 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/0278364918781016 journals.sagepub.com/home/ijr Christoforos I Mavrogiannis1 nd Ross A Knepper2" abe9f3b91fd26fa1b50cd685c0d20debfb372f73,The Pascal Visual Object Classes Challenge: A Retrospective,"(will be inserted by the editor) The Pascal Visual Object Classes Challenge – a Retrospective Mark Everingham, S. M. Ali Eslami, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserman Received: date / Accepted: date" abb3df5b61dc7550db96fc112f98fb99a9db8c93,End-to-End Learning of Deep Visual Representations for Image Retrieval,"Noname manuscript No. (will be inserted by the editor) End-to-end Learning of Deep Visual Representations for Image Retrieval Albert Gordo · Jon Almaz´an · Jerome Revaud · Diane Larlus Received: date / Accepted: date" ab1f98b59fa98216f052ae19adce6fd94ebb800d,"Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos","Preprint submitted to International Journal of Computer Vision manuscript No. (will be inserted by the editor) Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos Hugo Jair Escalante∗ · Heysem Kaya∗ · Albert Ali Salah∗ · Sergio Escalera · Ya˘gmur G¨u¸cl¨ut¨urk · Umut G¨u¸cl¨u · Xavier Bar´o · Isabelle Guyon · Julio Jacques Junior · Meysam Madadi · Stephane Ayache · Evelyne Viegas · Furkan G¨urpınar · Achmadnoer Sukma Wicaksana · Cynthia C. S. Liem · Marcel A. J. van Gerven · Rob van Lier Received: date / Accepted: date Means equal contribution by the authors. Hugo Jair Escalante INAOE, Mexico and ChaLearn, USA E-mail: Heysem Kaya Namık Kemal University, Department of Computer Engineering, Turkey" ab3baf12ce8316ae495fc7679ba34c5f704934cc,A Convex Max-Flow Approach to Distribution-Based Figure-Ground Separation,"Vol. 5, No. 4, pp. 1333–1354 (cid:2) 2012 Society for Industrial and Applied Mathematics A Convex Max-Flow Approach to Distribution-Based Figure-Ground Separation , Jing Yuan , Ismail Ben Ayed , Shuo Li , and Yuri Boykov Kumaradevan Punithakumar" abc66504927075c5878dc6b0d70f2d4b009a9c9a,Damaged Building Detection in the crisis areas using Image Processing Tools, ab8af4cb5243544e38852bb670aafe5a2fd9b3ec,Real-Time Human Detection Using Relational Depth Similarity Features,"Real-Time Human Detection using Relational Depth Similarity Features Sho Ikemura, Hironobu Fujiyoshi Dept. of Computer Science, Chubu University. Matsumoto 1200, Kasugai, Aichi, 487-8501 Japan. http://www.vision.cs.chubu.ac.jp" ab6776f500ed1ab23b7789599f3a6153cdac84f7,A Survey on Various Facial Expression Techniques,"International Journal of Scientific & Engineering Research, Volume 6, Issue 4, April-2015 1212 ISSN 2229-5518 A Survey on Various Facial Expression Techniques Md. Sarfaraz Jalil, Joy Bhattacharya" ab0f9bc35b777eaefff735cb0dd0663f0c34ad31,Semi-supervised Learning of Geospatial Objects through Multi-modal Data Integration,"Semi-Supervised Learning of Geospatial Objects Through Multi-Modal Data Integration Yi Yang and Shawn Newsam Electrical Engineering and Computer Science University of California, Merced, CA, 95343 Email:" abddbb57258d85b1f3d9789128fd284d30a91e23,A research and education initiative at the MIT Sloan School of Management Network Structure & Information Advantage Paper 235,"A research and education initiative at the MIT Sloan School of Management Network Structure & Information Advantage Paper 235 Sinan Aral Marshall Van Alstyne July 2007 For more information, please visit our website at http://digital.mit.edu or contact the Center directly at or 617-253-7054" abc1ef570bb2d7ea92cbe69e101eefa9a53e1d72,Raisonnement abductif en logique de description exploitant les domaines concrets spatiaux pour l'interprétation d'images,"Raisonnement abductif en logique de description exploitant les domaines concrets spatiaux pour l’interprétation d’images Yifan Yang 1, Jamal Atif 2, Isabelle Bloch 1 . LTCI, Télécom ParisTech, Université Paris-Saclay, Paris, France . Université Paris-Dauphine, PSL Research University, CNRS, UMR 7243, LAMSADE, 75016 Paris, France RÉSUMÉ. L’interprétation d’images a pour objectif non seulement de détecter et reconnaître des objets dans une scène mais aussi de fournir une description sémantique tenant compte des in- formations contextuelles dans toute la scène. Le problème de l’interprétation d’images peut être formalisé comme un problème de raisonnement abductif, c’est-à-dire comme la recherche de la meilleure explication en utilisant une base de connaissances. Dans ce travail, nous présentons une nouvelle approche utilisant une méthode par tableau pour la génération et la sélection d’explications possibles d’une image donnée lorsque les connaissances, exprimées dans une logique de description, comportent des concepts décrivant les objets mais aussi les relations spatiales entre ces objets. La meilleure explication est sélectionnée en exploitant les domaines oncrets pour évaluer le degré de satisfaction des relations spatiales entre les objets." abb4b8f9df14f7b15aa43920d0329eccada33b97,LBP Yardımıyla Görüntüdeki Kişinin Yaşının Bulunması,"C¸ ankaya University Journal of Science and Engineering Volume 8 (2011), No. 1, 27–41 LBP Yardımıyla G¨or¨unt¨udeki Ki¸sinin Ya¸sının Bulunması Vasif V. Nabiyev1,∗ ve Asuman G¨unay1 Karadeniz Teknik ¨Universitesi, Bilgisayar M¨uhendisli˘gi B¨ol¨um¨u, 61080 Trabzon, T¨urkiye Corresponding author: ¨Ozet. Y¨uz g¨or¨unt¨us¨unden ya¸sın do˘gru ¸sekilde tahmin edilmesi ve daha sonra ki¸sinin ge¸cmi¸s ve gelecekteki g¨or¨unt¨ulerinin ¨uretilmesi, g¨uvenlik sistemlerinin tasarımında b¨uy¨uk ¨onem ta¸sımaktadır. Bu ¸calı¸smada y¨uz g¨or¨unt¨us¨unden ya¸sın sınıflandırılmasında yerel ikili ¨or¨unt¨u (local binary pattern-LBP) histogramlarından faydalanılmaktadır. LBP opera- t¨or¨u performansı y¨uksek bir doku tanımlayıcısı olup doku sınıflandırma, segmentasyon, y¨uz tespiti, ki¸si tanıma ve cinsiyet tahmini gibi alanlarda kullanılmaktadır. G¨or¨unt¨u ¨uzerindeki d¨uzg¨un yerel ikili ¨or¨unt¨uler, yerel g¨or¨unt¨u dokusunun ¨onemli ¨ozelliklerindendir. Bunların meydana gelme sıklı˘gını veren histogram ise g¨u¸cl¨u bir doku ¨ozniteli˘gidir. C¸ alı¸smada y¨uz g¨or¨unt¨us¨u k¨u¸c¨uk b¨olgelere ayrılmı¸stır. Her bir b¨olge i¸cin ¨uretilen d¨uzg¨un LBP histogram- larının birle¸stirilmesiyle, y¨uz i¸cin verimli bir vekt¨orel g¨osterim ¸sekli olu¸sturulmu¸stur. Sis- teme sunulan her yeni y¨uz i¸cin b¨olgesel LBP histogramı ¨uretilmekte ve ya¸s sınıflarına it LBP histogramlarıyla kar¸sıla¸stırılarak sınıflandırılmaktadır. Sınıflandırmada minimum uzaklık (minimum distance), en yakın kom¸suluk (nearest neighbor) ve k-en yakın kom¸suluk" abb1289cfdc4c23d72d0680c3ec100eae74d4fdb,PatchMatch : A Fast Randomized Matching Algorithm with Application to Image and Video,"PatchMatch: A Fast Randomized Matching Algorithm with Application to Image and Video Connelly Barnes A Dissertation Presented to the Faculty of Princeton University in Candidacy for the Degree of Doctor of Philosophy Recommended for Acceptance y the Department of Computer Science Adviser: Adam Finkelstein May 2011" ab036048cf90296171ad2bb7265c5a5b7f3252f7,Multimodal Recurrent Neural Networks With Information Transfer Layers for Indoor Scene Labeling,"Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling Abrar H. Abdulnabi, Student Member, IEEE, Bing Shuai, Student Member, IEEE, Zhen Zuo, Student Member, IEEE, Lap-Pui Chau, Fellow, IEEE, and Gang Wang, Senior Member, IEEE" abd4152773ebb97b90163b9a6bbdf2075e825481,Procedural Text Generation from an Execution Video,"Proceedings of the The 8th International Joint Conference on Natural Language Processing, pages 326–335, Taipei, Taiwan, November 27 – December 1, 2017 c(cid:13)2017 AFNLP" ab8f9a6bd8f582501c6b41c0e7179546e21c5e91,Nonparametric Face Verification Using a Novel Face Representation,"Nonparametric Face Verification Using a Novel Face Representation Hae Jong Seo, Student Member, IEEE, Peyman Milanfar, Fellow, IEEE," ae8ed3b0b8043c5af76390751938edfd100fa9cd,An Overview of MultiTask Learning in Deep Neural Networks,"of 21 9 May 2017 An Overview of Multi-Task Learning in Deep Neural Networks  Table of contents: Introduction Motivation Two MTL methods for Deep Learning Hard parameter sharing Soft parameter sharing Why does MTL work? Implicit data augmentation Attention focusing Eavesdropping Representation bias Regularization MTL in non-neural models Block-sparse regularization http://sebastianruder.com/multi-task/index.html 5/31/17, 9:38 AM" ae8cc8db9e05c79adad03da64a4a9ba0b00f4eb5,Large Scale Local Online Similarity/Distance Learning Framework based on Passive/Aggressive,"International Journal of Machine Learning and Cybernetics DOI –x ORI GI NAL ARTI CLE Large Scale Local Online Similarity/Distance Learning Framework based on Passive/Aggressive Baida Hamdan1, Davood Zabihzadeh*1, Monsefi Reza1 Computer Department, Engineering Faculty, Ferdowsi University of Mashhad (FUM), Mashhad, IRAN" aeabcbdff7ab810b961a9f7e4399b6c0421d00cd,TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents,"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents Yuexin Ma1,2, Xinge Zhu3, Sibo Zhang1, Ruigang Yang1, Wenping Wang2, Dinesh Manocha4 Baidu Research, Baidu Inc.1, The University of Hong Kong2, The Chinese University of Hong Kong3, University of Maryland at College Park4" aef3ecc926ed79478f9d1f38c0fec2a29bae9c3b,Counting in High Density Crowd Videos,"Counting in High Density Crowd Videos Edgar Lopez University of Texas at El Paso" ae9257f3be9f815db8d72819332372ac59c1316b,Deciphering the enigmatic face: the importance of facial dynamics in interpreting subtle facial expressions.,"P SY CH O L O GIC AL SC I E NC E Research Article Deciphering the Enigmatic Face The Importance of Facial Dynamics in Interpreting Subtle Facial Expressions Zara Ambadar,1 Jonathan W. Schooler,2 and Jeffrey F. Cohn1 University of Pittsburgh and 2University of British Columbia, Vancouver, British Columbia, Canada" ae818858a88299090748446b8662e68628612c65,Analysis of Expressiveness of Portuguese Sign Language Speakers,"FACULDADE DE ENGENHARIA DA UNIVERSIDADE DO PORTO Analysis of Expressiveness of Portuguese Sign Language Speakers Maria Inês Coutinho Vigário Rodrigues MASTER THESIS Integrated Master in Bioengineering Supervisor: Luis Filipe Pinto de Almeida Teixeira (PhD) Co-supervisor: Eduardo José Marques Pereira (Eng.) June 2014" ae2b2493f35cecf1673eb3913fdce37e037b53a2,Optimal Transport Maps for Distribution Pre- Serving Operations on Latent Spaces of Gener-,"OPTIMAL TRANSPORT MAPS FOR DISTRIBUTION PRE- SERVING OPERATIONS ON LATENT SPACES OF GENER- ATIVE MODELS Eirikur Agustsson D-ITET, ETH Zurich Switzerland Alexander Sage D-ITET, ETH Zurich Switzerland Radu Timofte D-ITET, ETH Zurich Merantix GmbH Luc Van Gool D-ITET, ETH Zurich ESAT, KU Leuven" aeff403079022683b233decda556a6aee3225065,DeepFace: Face Generation using Deep Learning,"DeepFace: Face Generation using Deep Learning Hardie Cate Fahim Dalvi Zeshan Hussain" ae2cf545565c157813798910401e1da5dc8a6199,Cascade of Boolean detector combinations,"Mahkonen et al. EURASIP Journal on Image and Video Processing (2018) 2018:61 https://doi.org/10.1186/s13640-018-0303-9 EURASIP Journal on Image nd Video Processing RESEARCH Open Access Cascade of Boolean detector ombinations Katariina Mahkonen* , Tuomas Virtanen and Joni Kämäräinen" ae419d28ab936cbbc420dcfd1decb16a45afc8a9,Real-time face verification using multiple feature combination and a support vector machine supervisor, ae0514be12d200bd9fecf0d834bdcb30288c7a1e,Automatic Opinion Question Generation,"Automatic Opinion Question Generation Yllias Chali University of Lethbridge 401 University Drive Lethbridge, Alberta, T1K 3M4 Tina Baghaee University of Lethbridge 401 University Drive Lethbridge, Alberta, T1K 3M4" ae32279ce2828286a40800045b2d9f3b53bebb8c,Traffic Signs Recognition and Classification based on Deep Feature Learning, ae0a0ee1c6e2adcddffebf9b0e429a25b7d9c0e1,"A Review and Analysis of Eye-Gaze Estimation Systems, Algorithms and Performance Evaluation Methods in Consumer Platforms","A Review and Analysis of Eye-Gaze Estimation Systems, Algorithms and Performance Evaluation Methods in Consumer Platforms Anuradha Kar, Student Member, IEEE, Peter Corcoran Fellow, IEEE" aeeea6eec2f063c006c13be865cec0c350244e5b,"Induced Disgust , Happiness and Surprise : an Addition to the MMI Facial Expression Database","Induced Disgust, Happiness and Surprise: an Addition to the MMI Facial Expression Database Michel F. Valstar, Maja Pantic Imperial College London / Twente University Department of Computing / EEMCS 80 Queen’s Gate / Drienerlolaan 5 London / Twente" ae2e46a10d6dd83883809aa5df766050f83aaa91,Drivable Road Detection with 3D Point Clouds Based on the MRF for Intelligent Vehicle,"Drivable road detection with 3D Point Clouds ased on the MRF for Intelligent Vehicle Jaemin Byun,Ki-in Na,Beom-su Seo and Myungchan Roh" aeee98c90799cd44dde4046754cff27c8ed28d44,Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review,"Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review Jose Bernal∗, Kaisar Kushibar, Daniel S. Asfaw, Sergi Valverde, Arnau Oliver, Robert Mart´ı, Xavier Llad´o Computer Vision and Robotics Institute Dept. of Computer Architecture and Technology University of Girona Ed. P-IV, Av. Lluis Santal´o s/n, 17003 Girona (Spain)" ae87896c38f1871457d811a0588487db0155a833,Attentional allocation of ASD individuals : Searching for a Face-inthe-Crowd,"Attentional allocation of ASD individuals: Searching for a Face-in-the-Crowd David J. Moore, John Reidy and Lisa Heavey Department of Psychology, Sociology and Politics, Sheffield Hallam University Running Header: Attentional allocation of ASD individuals" ae753fd46a744725424690d22d0d00fb05e53350,Describing clothing by semantic attributes,"Describing Clothing by Semantic Attributes Anonymous ECCV submission Paper ID 727" ae4d06143a6b46ffaf5d228b1fa464dc322ddc18,R 4-A . 3 : Human Detection & Re-Identification for Mass Transit Environments,"R4-A.3: Human Detection & Re-Identification for Mass Transit Environments PARTICIPANTS Rich Radke Title Faculty/Staff Institution Graduate, Undergraduate and REU Students Srikrishna Karanam Eric Lam Degree Pursued Institution Email Month/Year of Graduation 5/2017 5/2017 PROJECT DESCRIPTION Project Overview The computer vision research problem of human re-identification or “re-id” is generally posed as follows: Given a cropped rectangle of pixels representing a human in one view, a re-id algorithm produces a similarity" aed5b3b976077ecdcf3f88ffc511f63d9f9e8697,"A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC","A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC Mark Yatskar Allen Institute for Artificial Intelligence" aef55af11d8ecaeaf4c13ed765e74a3471ce9b7c,Probabilistic Video Generation Using Holistic Attribute Control, ae3a81e69ef3ffc22017cec5bb2c5ea26114ce2b,A weighted voting model of associative memory: theoretical analysis,"A Weighted Voting Model of Associative Memory: Theoretical Analysis Xiaoyan Mu Department of Electrical and Computer Engineering Rose-Hullman Institute of Technology Terre Haute, IN 47803 Paul Watta Dept. Electrical and Computer Engineering University of Michigan-Dearborn Dearborn, MI 48128" ae21fdc2dae83c951c3cc7e5b8a1c0455470909d,Jadisha Yarif Ramírez Cornejo Emotion Recognition based on Facial Expressions Robust to Occlusions Reconhecimento de Emoções Baseado em Expressões Faciais Robusto a Oclusões,"Jadisha Yarif Ramírez Cornejo Emotion Recognition based on Facial Expressions Robust to Occlusions Reconhecimento de Emoções Baseado em Expressões Faciais Robusto a Oclusões CAMPINAS" aeae58c5e326c162fa5b0019e84f867c58dd20a2,Investigation into DCT Feature Selection for Visual Lip-Based Biometric Authentication,"Investigation into DCT Feature Selection for Visual Lip-Based Biometric Authentication Wright, C., Stewart, D., Miller, P., & Campbell-West, F. (2015). Investigation into DCT Feature Selection for Visual Lip-Based Biometric Authentication. In R. Dahyot, G. Lacey, K. Dawson-Howe, F. Pitié, & D. Moloney (Eds.), Irish Machine Vision & Image Processing Conference Proceedings 2015 (pp. 11-18). Irish Pattern Recognition & Classification Society. Published in: Irish Machine Vision & Image Processing Conference Proceedings 2015 Document Version: Publisher's PDF, also known as Version of record Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights © 2015 The Authors This is an open access article published under a Creative Commons Attribution-NonCommercial-ShareAlike License (https://creativecommons.org/licenses/by-nc-sa/4.0/), which permits use, distribution and reproduction for non-commercial purposes, provided the author and source are cited and new creations are licensed under the identical terms. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated" ae9ab89c51d264fb7b6b57d37399a7c629836e35,Transfer Learning Based on AdaBoost for Feature Selection from Multiple ConvNet Layer Features,"Obtaining Better Image Representations by Combining Complementary Activation Features of Multiple ConvNet Layers for Transfer Learning Jumabek Alikhanov School of Computer and Information Engineering Seunghyun Ko School of Computer and Information Engineering Jo Geun Sik School of Computer and Information Engineering Inha University Incheon, South Korea Inha University Incheon, South Korea Inha University Incheon, South Korea Email: Email: Email:" aeec61ef41d55b5c1becfdc00c2e4dbca0e379c0,Automatic Recognition by Gait,"I N V I T E D P A P E R Automatic Recognition by Gait Recognizing people by the way they walk promises to be useful for identifying individuals from a distance; improved techniques are under development. By Mark S. Nixon, Member IEEE, and John N. Carter, Member IEEE" ae5195c44ef7bff090bb5a17a9fe5f86a8c3b316,Web Scale Image Annotation : Learning to Rank with Joint Word-Image Embeddings,"Web Scale Image Annotation: Learning to Rank with Joint Word-Image Embeddings" aeee02b8c8bb749a1203fa634407319dd6874667,VIDEO-SURVEILLANCE IN CLOUD Platform and software aaS for people detection and soft-biometry,"VIDEO-SURVEILLANCE IN CLOUD Platform and software aaS for people detection and soft- iometry R. Cucchiara°,*, A. Prati°,+, R. Vezzani°,*, S. Calderara°,*, C. Grana°,* °SOFTECH-ICT, *Università di Modena e Reggio Emilia, +Università IUAV di Venezia" aef3bcb3b09f708edad335cfc0caf8ad208d4741,Learning robotic perception through prior knowledge,"Learning Robotic Perception Through Prior Knowledge vorgelegt von M.Sc. Rico Jonschkowski geb. in Havelberg von der Fakultät IV – Elektrotechnik und Informatik der Technischen Universität Berlin zur Erlangung des akademischen Grades Doktor der Naturwissenschaften — Dr. rer. nat. — genehmigte Dissertation Promotionsausschuss: Vorsitzender: Prof. Dr. Manfred Opper Gutachter: Gutachter: Gutachter: Tag der wissenschaftlichen Aussprache: 02. Mai 2018 Prof. Dr. Oliver Brock Prof. Dr. George Konidaris" aebb9649bc38e878baef082b518fa68f5cda23a5,A Multi-scale TVQI-based Illumination Normalization Model, aed5aecd3f0a07036e570c84c06cd37ab8904acc,The Resiliency of Memorability: A Predictor of Memory Separate from Attention and Priming,"The Resiliency of Memorability: A Predictor of Memory Separate from Attention and Priming Wilma A. Bainbridge Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology. Cambridge, MA. USA. Keywords: Memorability, top-down attention, bottom-up attention, priming, visual search, spatial cueing, directed forgetting, depth of encoding" aef49f85368baf186d2a95308d14793b9347703c,Automated Fingertip Detection,"Brigham Young University BYU ScholarsArchive All Theses and Dissertations 012-04-10 Automated Fingertip Detection Joseph G. Butler Brigham Young University - Provo Follow this and additional works at: https://scholarsarchive.byu.edu/etd Part of the Computer Sciences Commons BYU ScholarsArchive Citation Butler, Joseph G., ""Automated Fingertip Detection"" (2012). All Theses and Dissertations. 3164. https://scholarsarchive.byu.edu/etd/3164 This Thesis is brought to you for free and open access by BYU ScholarsArchive. It has been accepted for inclusion in All Theses and Dissertations by an uthorized administrator of BYU ScholarsArchive. For more information, please contact" ae89b7748d25878c4dc17bdaa39dd63e9d442a0d,On evaluating face tracks in movies,"On evaluating face tracks in movies Alexey Ozerov, Jean-Ronan Vigouroux, Louis Chevallier, Patrick Pérez To cite this version: Alexey Ozerov, Jean-Ronan Vigouroux, Louis Chevallier, Patrick Pérez. On evaluating face tracks in movies. IEEE International Conference on Image Processing (ICIP 2013), Sep 2013, Melbourne, Australia. 2013. HAL Id: hal-00870059 https://hal.inria.fr/hal-00870059 Submitted on 4 Oct 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" ae0322119c8d70ba98f32aeb205393dad8dd287b,OxIOD: The Dataset for Deep Inertial Odometry,"OxIOD: The Dataset for Deep Inertial Odometry Changhao Chen∗, Peijun Zhao∗, Chris Xiaoxuan Lu, Wei Wang, Andrew Markham, Niki Trigoni" ae8d5be3caea59a21221f02ef04d49a86cb80191,Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks,"Published as a conference paper at ICLR 2018 SKIP RNN: LEARNING TO SKIP STATE UPDATES IN RECURRENT NEURAL NETWORKS V´ıctor Campos∗†, Brendan Jou‡, Xavier Gir´o-i-Nieto§, Jordi Torres†, Shih-Fu ChangΓ Barcelona Supercomputing Center, ‡Google Inc, §Universitat Polit`ecnica de Catalunya, ΓColumbia University {victor.campos," ae13485e75f5e7fc9a9659ce960c8b299c7b889b,SPARSE MODELING FOR HIGH-DIMENSIONAL MULTI-MANIFOLD DATA ANALYSIS by,"SPARSE MODELING FOR HIGH-DIMENSIONAL MULTI-MANIFOLD DATA ANALYSIS Ehsan Elhamifar A dissertation submitted to The Johns Hopkins University in conformity with the requirements for the degree of Doctor of Philosophy. Baltimore, Maryland October, 2012 (cid:13) Ehsan Elhamifar 2012 All rights reserved" 070ab604c3ced2c23cce2259043446c5ee342fd6,An Active Illumination and Appearance (AIA) Model for Face Alignment,"AnActiveIlluminationandAppearance(AIA)ModelforFaceAlignment FatihKahraman,MuhittinGokmen IstanbulTechnicalUniversity, ComputerScienceDept.,Turkey {fkahraman, InformaticsandMathematicalModelling,Denmark SuneDarkner,RasmusLarsen TechnicalUniversityofDenmark" 070199a5087590f96c4422b82e4803911bb0652e,What Are We Tracking: A Unified Approach of Tracking and Recognition,"What Are We Tracking: A Unified Approach of Tracking and Recognition Jialue Fan, Xiaohui Shen, Student Member, IEEE, and Ying Wu, Senior Member, IEEE" 073c9ec4ff069218f358b9dd8451a040cf1a4a82,Object Classification and Detection in High Dimensional Feature Space,"Object Classification and Detection in High Dimensional Feature Space THIS IS A TEMPORARY TITLE PAGE It will be replaced for the final print by a version provided by the service académique. Thèse n. 6043 présentée le 17 Décembre 2013 à la Faculté Sciences et Techniques de l’Ingénieur Laboratoire de l’Idiap Programme doctoral en Informatique, Communications et Infor- mation École Polytechnique Fédérale de Lausanne pour l’obtention du grade de Docteur ès Sciences Charles Dubout cceptée sur proposition du jury: Prof Mark Pauly, président du jury Dr François Fleuret, directeur de thèse Prof Pascal Fua, rapporteur Prof Gilles Blanchard, rapporteur Prof Frédéric Jurie, rapporteur" 07c6744e25ed01967e448a397f5d7e9d540345c3,Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval,"Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval Yang Wang, Xuemin Lin, Lin Wu, Wenjie Zhang" 074061bc12af98e3c9fd7650452d896b2c03b3ac,A FPGA Implementation of Neural / Wavelet Face Detection System,"Australian Journal of Basic and Applied Sciences, 4(3): 379-388, 2010 ISSN 1991-8178 © 2010, INSInet Publication A FPGA Implementation of Neural/Wavelet Face Detection System Hossein Sahoolizadeh, Ahmad Keshavarz Islamic Azad Universitiy, Dashtestan branch, Iran Behin Tadbir Intelligent Systems Co, Kermanshah, Iran Persian Golg University, Bushehr 75169, Iran" 07892741feb277639b8a7d4c1dcc0054077cb7ce,Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach,"Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach Xiaowei Zhou, Menglong Zhu, Spyridon Leonardos, and Kostas Daniilidis, Fellow, IEEE" 0726a45eb129eed88915aa5a86df2af16a09bcc1,Introspective perception: Learning to predict failures in vision systems,"Introspective Perception: Learning to Predict Failures in Vision Systems Shreyansh Daftry, Sam Zeng, J. Andrew Bagnell and Martial Hebert" 0750a816858b601c0dbf4cfb68066ae7e788f05d,CosFace: Large Margin Cosine Loss for Deep Face Recognition,"CosFace: Large Margin Cosine Loss for Deep Face Recognition Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li∗, and Wei Liu∗ Tencent AI Lab" 07ad6bb9b21c065cd92ab2f24a22c1d4a8f205a7,Realtime facial animation with on-the-fly correctives,"Realtime Facial Animation with On-the-fly Correctives Hao Li⇤ Jihun Yu† Yuting Ye‡ Chris Bregler§ Industrial Light & Magic input depth map & 2D features data-driven tracking our tracking data-driven retargeting our retargeting Figure 1: Our adaptive tracking model conforms to the input expressions on-the-fly, producing a better fit to the user than state-of-the-art data driven techniques [Weise et al. 2011] which are confined to learned motion priors and generate plausible but not accurate tracking. Links: Introduction The essence of high quality performance-driven facial animation is to capture every trait and characteristic of an actor’s facial and ver- al expression and to reproduce those on a digital double or crea- ture. Even with the latest 3D scanning and motion capture tech- nology, the creation of realistic digital faces in film and game pro-" 07ea3dd22d1ecc013b6649c9846d67f2bf697008,HUMAN-CENTRIC VIDEO UNDERSTANDING WITH WEAK SUPERVISION A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"HUMAN-CENTRIC VIDEO UNDERSTANDING WITH WEAK SUPERVISION A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Vignesh Ramanathan June 2016" 0717b47ab84b848de37dbefd81cf8bf512b544ac,Robust Face Recognition and Tagging in Visual Surveillance System,"International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 International Conference on Humming Bird ( 01st March 2014) RESEARCH ARTICLE OPEN ACCESS Robust Face Recognition and Tagging in Visual Surveillance Kavitha MS 1, Siva Pradeepa S2 System Kavitha MS Author is currently pursuing M.E(CSE)in VINS Christian college of Engineering,Nagercoil. Siva pradeepa,Assistant Lecturer in VINS Christian college of Engineering" 07e5bd5d3830e55dc85677821eea8256e252f966,Hierarchical Representation Learning for Kinship Verification,"IEEE TRANSACTIONS ON IMAGE PROCESSING Hierarchical Representation Learning for Kinship Verification Naman Kohli, Student Member, IEEE, Mayank Vatsa, Senior Member, IEEE, Richa Singh, Senior Member, IEEE, Afzel Noore, Senior Member, IEEE, and Angshul Majumdar, Senior Member, IEEE" 078d507703fc0ac4bf8ca758be101e75ea286c80,Large-Scale Content Based Face Image Retrieval using Attribute Enhanced Sparse,"ISSN: 2321-8169 International Journal on Recent and Innovation Trends in Computing and Communication Volume: 3 Issue: 8 5287 - 5296 ________________________________________________________________________________________________________________________________ Large- Scale Content Based Face Image Retrieval using Attribute Enhanced Sparse Codewords. Chaitra R, Mtech Digital Coomunication Engineering Acharya Institute Of Technology Bangalore" 074faec2e546f292800c0c028912ced147b25218,Chapter 6 Face Recognition in the Thermal Infrared ?,"Chapter 6 Face Recognition in the Thermal Infrared (cid:63) Lawrence B. Wolff, Diego A. Socolinsky, and Christopher K. Eveland Equinox Corporation, 9 West 57th Street, New York, New York 10019 Summary. Recent research has demonstrated distinct advantages of using thermal infrared imaging for improving face recognition performance. While conventional video cameras sense reflected light, thermal infrared cameras primarily measure emitted radiation from objects such as faces. Visible and thermal infrared image data collections of frontal faces have been on-going at NIST for over two years, pro- ducing the most comprehensive face database known to involve thermal infrared im- gery. Rigorous experimentation with this database has revealed consistently supe- rior recognition performance of algorithms when applied to thermal infrared, partic- ularly under variable illumination conditions. Physical phenomenology responsible for this observation is analyzed. An end-to-end face recognition system incorporat- ing simultaneous coregistered thermal infrared and visible has been developed and tested indoors with good performance. 6.1 Introduction Accelerated developments in camera technology over the last decade have given computer vision researchers a whole new diversity of imaging options, particularly in the infrared spectrum. Conventional video cameras use pho-" 07c83f544d0604e6bab5d741b0bf9a3621d133da,Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition,"Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh National Institute of Advanced Industrial Science and Technology (AIST) Tsukuba, Ibaraki, Japan {kensho.hara, hirokatsu.kataoka," 07faa38d4d0e9d14d72bd049362efa83fae78ee3,Quick Identification of Child Pornography in Digital Videos,"IJoFCS (2012) 2, 21-32 DOI: 10.5769/J201202002 or http://dx.doi.org/10.5769/J201202002 Quick Identification of Child Pornography in Digital Videos Mateus de Castro Polastro and Pedro Monteiro da Silva Eleuterio Brazilian Federal Police Campo Grande/MS E-mails:" 071135dfb342bff884ddb9a4d8af0e70055c22a1,Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification,"New Architecture and Transfer Learning for Video Classification Temporal 3D ConvNets: Ali Diba1,4,(cid:63), Mohsen Fayyaz2,(cid:63), Vivek Sharma3, Amir Hossein Karami4, Mohammad Mahdi Arzani4, Rahman Yousefzadeh4, Luc Van Gool1,4 ESAT-PSI, KU Leuven, 2University of Bonn, 3CV:HCI, KIT, Karlsruhe, 4Sensifai" 0779875eff440365184dd8bf44e9f85f78267c5f,An Intelligent Extraversion Analysis Scheme from Crowd Trajectories for Surveillance,"JOURNAL OF LATEX CLASS FILES, VOL. XX, NO. YY, JULY 2017 An Intelligent Extraversion Analysis Scheme from Crowd Trajectories for Surveillance Wenxi Liu, Yuanlong Yu, Chun-Yang Zhang, Genggeng Liu, Naixue Xiong" 07dbf04089b015db773fe95e664fa73aef874b36,Fishy Faces: Crafting Adversarial Images to Poison Face Authentication,"Fishy Faces: Crafting Adversarial Images to Poison Face Authentication Giuseppe Garofalo Vera Rimmer Tim Van hamme imec-DistriNet, KU Leuven imec-DistriNet, KU Leuven imec-DistriNet, KU Leuven Davy Preuveneers Wouter Joosen imec-DistriNet, KU Leuven imec-DistriNet, KU Leuven" 0744af11a025e9c072ef6ad102af208e79cc6f44,Learning Smooth Pattern Transformation Manifolds,"Learning Smooth Pattern Transformation Manifolds Elif Vural and Pascal Frossard" 079a0a3bf5200994e1f972b1b9197bf2f90e87d4,Component-Based Face Recognition with 3D Morphable Models,"Component-based Face Recognition with 3D Morphable Models Jennifer Huang1, Bernd Heisele1;2, and Volker Blanz3 Center for Biological and Computational Learning, M.I.T., Cambridge, MA, USA Honda Research Institute US, Boston, MA, USA Computer Graphics Group, Max-Planck-Institut, Saarbr˜ucken, Germany" 077492a77812a68c86b970557e97a452a6689427,Automatic 3D face reconstruction from single images or video,"Automatic 3D Face Reconstruction from Single Images or Video Pia Breuer†, Kwang-In Kim‡, Wolf Kienzle‡, Bernhard Sch¨olkopf‡, Volker Blanz† University of Siegen, ‡Max Planck Institute for Biological Cybernetics {pbreuer, {kwangin.kim, kienzle," 07a8a4b8f207b2db2a19e519027f70cd1c276294,Pixel Recursive Super Resolution,"Pixel Recursive Super Resolution Ryan Dahl ∗ Jonathon Shlens Mohammad Norouzi Google Brain" 07d6238d8f8edbfe0fd2887fa0a7939735f21e13,Learning Human Optical Flow,"RANJAN, ROMERO, BLACK: LEARNING HUMAN OPTICAL FLOW Learning Human Optical Flow MPI for Intelligent Systems Tübingen, Germany Amazon Inc. Anurag Ranjan1 Javier Romero∗,2 Michael J. Black1" 07f5c01b1e272fca1fc575ab84ac1710cbe58518,A Deep Structure of Person Re-Identification Using Multi-Level Gaussian Models,"> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < A Deep Structure of Person Re-Identification using Multi-Level Gaussian Models Dinesh Kumar Vishwakarma, IEEE Member, Sakshi Upadhyay" 0716e1ad868f5f446b1c367721418ffadfcf0519,Interactively Guiding Semi-Supervised Clustering via Attribute-Based Explanations,"Interactively Guiding Semi-Supervised Clustering via Attribute-Based Explanations Shrenik Lad and Devi Parikh Virginia Tech, Blacksburg, VA, USA" 07eaf19eecf4ccdd5f8e3367c1675d9f4addd2df,Learning pullback manifolds of dynamical models,"IEEE TRANSACTIONS ON PAMI, VOL. XX, NO. Y, MONTH 2010 SubmittedtoIEEETrans.onPatternAnalysisandMachineIntelligence;October27,2010 Learning pullback manifolds of dynamical models Fabio Cuzzolin" 0725b950792ddbe4edf812a7ee8cef14447236ed,Efficient Large-Scale Multi-Modal Classification,"Efficient Large-Scale Multi-Modal Classification Douwe Kiela, Edouard Grave, Armand Joulin and Tomas Mikolov Facebook AI Research" 0742d051caebf8a5d452c03c5d55dfb02f84baab,Real-time geometric motion blur for a deforming polygonal mesh,"Real-Time Geometric Motion Blur for a Deforming Polygonal Mesh Nathan Jones Formerly: Texas A&M University Currently: The Software Group" 0726152a1c1a5723ac34d54abec0dc8d4659598e,Realtime Image Matching for Vision Based Car Navigation with Built-in Sensory Data,"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume II-3/W2, 2013 ISA13 - The ISPRS Workshop on Image Sequence Analysis 2013, 11 November 2013, Antalya, Turkey" 073c5c27f26c9d174e2ee060b27a090457e3f774,Backprop KF: Learning Discriminative Deterministic State Estimators,"Backprop KF: Learning Discriminative Deterministic State Estimators Tuomas Haarnoja, Anurag Ajay, Sergey Levine, Pieter Abbeel {haarnoja, anuragajay, svlevine, Department of Computer Science, University of California, Berkeley" 07ca211bde38009697c964702a29d0fe3260bf97,Resource Aware Person Re-identification across Multiple Resolutions,"Resource Aware Person Re-identification across Multiple Resolutions Yan Wang∗ †, Lequn Wang∗ †, Yurong You∗ ‡, Xu Zou§, Vincent Chen† Serena Li†, Gao Huang†, Bharath Hariharan†, Kilian Q. Weinberger†" 074a12f9187beafe40386f19aa2544df30fa5703,Product Characterisation towards Personalisation: Learning Attributes from Unstructured Data to Recommend Fashion Products,"Product Characterisation towards Personalisation Learning Attributes from Unstructured Data to Recommend Fashion Products Ângelo Cardoso∗ ISR, IST, Universidade de Lisboa Lisbon, Portugal Fabio Daolio ASOS.com London, UK Saúl Vargas ASOS.com London, UK" 073bbe41f2fdfb2c87b75dbc154adc7020baab0a,Face Recognition by Cortical Multi-scale Line and Edge Representations,"Face recognition by cortical multi-scale line and edge representations Jo˜ao Rodrigues1 and J.M.Hans du Buf 2 Escola Superior de Tecnologia, Campus da Penha Vision Laboratory, Campus de Gambelas – FCT, University of Algarve, 8000-117 Faro, Portugal" 0735e0b0266d94b670fa6e1b974d3676ef4e3e24,Face Recognition by Elastic Bunch Graph Matching,"IEEE Transactions on Pattern Analysis and Machine Intelligence,  :-  . Face Recognition by Elastic Bunch Graph Matching Laurenz Wiskott, Jean-Marc Fellous, Norbert Kruger, and Christoph von der Malsburg" 07adc7429fb22352946b675023df7db11c905701,Active Multitask Learning Using Both Latent and Supervised Shared Topics,"Active Multitask Learning Using Both Latent and Supervised Shared Topics Ayan Acharya∗ Raymond J. Mooney∗ Joydeep Ghosh∗" 0760b9375db1505e9b9c182e98bb9579dd9197af,Robust Subspace Discovery through Supervised Low-Rank Constraints,"Robust Subspace Discovery through Supervised Low-Rank Constraints Sheng Li∗ Yun Fu∗" 071099a4c3eed464388c8d1bff7b0538c7322422,Facial expression recognition in the wild using rich deep features,"FACIAL EXPRESSION RECOGNITION IN THE WILD USING RICH DEEP FEATURES Abubakrelsedik Karali, Ahmad Bassiouny and Motaz El-Saban Microsoft Advanced Technology labs, Microsoft Technology and Research, Cairo, Egypt" 079b6800e3130ca2ef1815a35632ab6998848ef3,Fine-grained Apparel Classification and Retrieval without rich annotations,"Fine-grained Apparel Classification and Retrieval without rich annotations Aniket Bhatnagar · Sanchit Aggarwal" 0770f0f8f168c284a63e46b394150a8c429549da,Project-Team Pulsar Perception Understanding Learning Systems for Activity Recognition,"INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE Project-Team Pulsar Perception Understanding Learning Systems for Activity Recognition Sophia Antipolis - Méditerranée THEME COG tivitytepor2008" 0728f788107122d76dfafa4fb0c45c20dcf523ca,The Best of BothWorlds: Combining Data-Independent and Data-Driven Approaches for Action Recognition,"The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition Zhenzhong Lan, Dezhong Yao, Ming Lin, Shoou-I Yu, Alexander Hauptmann {lanzhzh, minglin, iyu," 07d49098ada2d8e1ca0608c70e559dd517ca3432,Modélisation de contextes pour l'annotation sémantique de vidéos. (Context based modeling for video semantic annotation),"Modélisation de contextes pour l’annotation sémantique de vidéos Nicolas Ballas To cite this version: Nicolas Ballas. Modélisation de contextes pour l’annotation sémantique de vidéos. Autre [cs.OH]. Ecole Nationale Supérieure des Mines de Paris, 2013. Français. . HAL Id: pastel-00958135 https://pastel.archives-ouvertes.fr/pastel-00958135 Submitted on 11 Mar 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 07ca470ed3be3a476b6fc1917bbbf4182846d1db,Transforming sensor data to the image domain for deep learning — An application to footstep detection,"Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection Monit Shah Singh1∗, Vinaychandran Pondenkandath1†§, Bo Zhou‡, Paul Lukowicz∗‡ and Marcus Liwicki†§ MindGarage, TU Kaiserslautern, Germany §DIVA, University of Fribourg, Switzerland TU Kaiserslautern, Germany DFKI, Kaiserslautern, Germany M onit ki.de, r.ch ki.de, P ki.de," 072fd0b8d471f183da0ca9880379b3bb29031b6a,Image-to-Image Translation with Conditional Adversarial Networks,"Image-to-Image Translation with Conditional Adversarial Networks Phillip Isola Jun-Yan Zhu Tinghui Zhou Alexei A. Efros Berkeley AI Research (BAIR) Laboratory, UC Berkeley Figure 1: Many problems in image processing, graphics, and vision involve translating an input image into a corresponding output image. These problems are often treated with application-specific algorithms, even though the setting is always the same: map pixels to pixels. Conditional adversarial nets are a general-purpose solution that appears to work well on a wide variety of these problems. Here we show results of the method on several. In each case we use the same architecture and objective, and simply train on different data." f0418d8029323e37e14ccf2e2a7143e197fb36e4,Robust tracking via weighted online extreme learning machine,"Noname manuscript No. (will be inserted by the editor) Robust Tracking via Weighted Online Extreme Learning Machine Jing Zhang · Huibing Wang · Yonggong Received: date / Accepted: date" f0d18a5d205c23d1309387dfbd4ecfbcf3b1687e,Atypical neural modulation in the right prefrontal cortex during an inhibitory task with eye gaze in autism spectrum disorder as revealed by functional near-infrared spectroscopy.,"Terms of Use: https://journals.spiedigitallibrary.org/terms-of-use Atypicalneuralmodulationintherightprefrontalcortexduringaninhibitorytaskwitheyegazeinautismspectrumdisorderasrevealedbyfunctionalnear-infraredspectroscopyTakahiroIkedaMasahiroHiraiTakeshiSakuradaYukifumiMondenTatsuyaTokudaMasakoNagashimaHideoShimoizumiIppeitaDanTakanoriYamagataTakahiroIkeda,MasahiroHirai,TakeshiSakurada,YukifumiMonden,TatsuyaTokuda,MasakoNagashima,HideoShimoizumi,IppeitaDan,TakanoriYamagata,“Atypicalneuralmodulationintherightprefrontalcortexduringaninhibitorytaskwitheyegazeinautismspectrumdisorderasrevealedbyfunctionalnear-infraredspectroscopy,”Neurophoton.5(3),035008(2018),doi:10.1117/1.NPh.5.3.035008." f050b9f46711e48c5ebe6e79944a54e363bc2939,CoSy Cognitive Systems for Cognitive Assistants Integrated Project Information Society Technologies,"FP6-004250CoSyCognitiveSystemsforCognitiveAssistantsIntegratedProjectInformationSocietyTechnologiesDR.7.5MechanismsforrobustandscalablerecognitionandcategorizationofobjectsandplacesDuedateofdeliverable:30/09/2006Actualsubmissiondate:30/09/2006Startdateofproject:September1st,2004Duration:48monthsOrganisationnameofleadcontractorforthisdeliverable:TUDRevision:draftDisseminationLevel:PU" f0558f6f80e1a8229ad241b3de000f744074a030,Incorporating Computation Time Measures During Heterogeneous Features Selection in a Boosted Cascade People Detector,"Incorporating Computation Time Measures during Heterogeneous Features Selection in a Boosted Cascade People Detector Alhayat Ali Mekonnen, Frédéric Lerasle, Ariane Herbulot, Cyril Briand To cite this version: Alhayat Ali Mekonnen, Frédéric Lerasle, Ariane Herbulot, Cyril Briand. Incorporating Computation Time Measures during Heterogeneous Features Selection in a Boosted Cascade People Detector. Inter- national Journal of Pattern Recognition and Artificial Intelligence, World Scientific Publishing, 2016, 0 (8), pp.1655022. <10.1142/S0218001416550223>. HAL Id: hal-01300472 https://hal.archives-ouvertes.fr/hal-01300472 Submitted on 11 Apr 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents" f06f3e1cef2d04af915a932e83b22e46a45f3b73,Action understanding and social learning in Autism : a developmental perspective,"Life Span and Disability / XIV, 1 (2011), 7-29 Action understanding and social learning in Autism: developmental perspective Giacomo Vivanti1 & Sally J. Rogers2" f0b30a9bb9740c2886d96fc44d6f35b8eacab4f3,Are You Sure You Want To Do That ? Classification with Interpretable Queries,"Are You Sure You Want To Do That? Classification with Interpretable Queries Anonymous Author(s) Affiliation Address email" f05358fb80283f0f242215d459367bddce810cd0,An Efficient Video to Video Face Recognition using Neural Networks,"An Efficient Video to Video Face Recognition using Neural Networks {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 170 Number 8 Year of Publication: 2017 Authors: Wilson S., Lenin Fred 10.5120/ijca2017914924 {bibtex}2017914924.bib{/bibtex}" f0e17f27f029db4ad650ff278fe3c10ecb6cb0c4,The EuroCity Persons Dataset: A Novel Benchmark for Object Detection,"The EuroCity Persons Dataset: A Novel Benchmark for Object Detection Markus Braun, Sebastian Krebs, Fabian Flohr, and Dariu M. Gavrila" f04cffcd0cc68e28cf05827ab998cf84b1ab0f3d,Crowdsourced Data Preprocessing with R and Amazon Mechanical Turk,"CONTRIBUTED RESEARCH ARTICLES Crowdsourced Data Preprocessing with R nd Amazon Mechanical Turk y Thomas J. Leeper" f09432b7f470268c28d3d4ebd17a44773b678900,Structured Attentions for Visual Question Answering,"Structured Attentions for Visual Question Answering Chen Zhu, Yanpeng Zhao, Shuaiyi Huang, Kewei Tu, Yi Ma {zhuchen, zhaoyp1, huangsy, tukw, ShanghaiTech University" f0f876b5bf3d442ef9eb017a6fa873bc5d5830c8,"LOH and behold: Web-scale visual search, recommendation and clustering using Locally Optimized Hashing","LOH and Behold: Web-scale visual search, recommendation and clustering using Locally Optimized Hashing Yannis Kalantidis:, Lyndon Kennedy;‹, Huy Nguyen:, Clayton Mellina: and David A. Shamma§‹ :Computer Vision and Machine Learning Group, Flickr, Yahoo ;Futurewei Technologies Inc. §CWI: Centrum Wiskunde & Informatica, Amsterdam" f07956d0031ff046c5c719296f7916d7897fdd21,A Flexible Real-Time Control System for Autonomous Vehicles,"A Flexible Real-Time Control System for Autonomous Vehicles. Johannes Meyer, Armin Strobel Institute of Flight Systems and Automatic Control, Technische Universität Darmstadt, Germany 1" f040e4fcedca0c07788ecb6e92ad246b9c1697a9,REAL-TIME MULTIPLE HEAD TRACKING USING TEXTURE AND COLOUR CUES,"REAL-TIME MULTIPLE HEAD TRACKING USING TEXTURE AND COLOUR CUES Vasil Khalidov Jean-Marc Odobez Idiap-RR-02-2017 FEBRUARY 2017 Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" f006161327d3ea3484064c1a86e4c87c729fd7b8,ROUGH SETS METHODS IN FEATURE REDUCTION AND CLASSIFICATION,"Int. J. Appl. Math. Comput. Sci., 2001, Vol.11, No.3, 565{582 ROUGH SETS METHODS IN FEATURE REDUCTION AND CLASSIFICATION Roman W. (cid:145)WINIARSKI(cid:3) The paper presents an application of rough sets and statistical methods to fea- ture reduction and pattern recognition. The presented description of rough sets theory emphasizes the role of rough sets reducts in feature selection and data reduction in pattern recognition. The overview of methods of feature selection emphasizes feature selection criteria, including rough set-based methods. The paper also contains a description of the algorithm for feature selection and re- duction based on the rough sets method proposed jointly with Principal Compo- nent Analysis. Finally, the paper presents numerical results of face recognition experiments using the learning vector quantization neural network, with feature selection based on the proposed principal components analysis and rough sets methods. Keywords: rough sets, feature selection, classi(cid:12)cation . Introduction One of the fundamental steps in classi(cid:12)er design is reduction of pattern dimensional- ity through feature extraction and feature selection (Cios et al., 1998; Kittler, 1986; Langley and Sage, 1994; Liu and Motoda, 1999). Feature selection is often isolated as" f0ae807627f81acb63eb5837c75a1e895a92c376,Facial Landmark Detection using Ensemble of Cascaded Regressions,"International Journal of Emerging Engineering Research and Technology Volume 3, Issue 12, December 2015, PP 128-133 ISSN 2349-4395 (Print) & ISSN 2349-4409 (Online) Facial Landmark Detection using Ensemble of Cascaded Regressions Martin Penev1*, Ognian Boumbarov2 Faculty of Telecommunications, Technical University, Sofia, Bulgaria Faculty of Telecommunications, Technical University, Sofia, Bulgaria" f0f4f16d5b5f9efe304369120651fa688a03d495,Temporal Generative Adversarial Nets,"Temporal Generative Adversarial Nets Masaki Saito∗ Eiichi Matsumoto∗ Preferred Networks inc., Japan {msaito," f0cc615b14c97482faa9c47eb855303c71ff03a7,Tracklet clustering for robust multiple object tracking using distance dependent Chinese restaurant processes,"SIViP DOI 10.1007/s11760-015-0817-x ORIGINAL PAPER Tracklet clustering for robust multiple object tracking using distance dependent Chinese restaurant processes Ibrahim Saygin Topkaya1 · Hakan Erdogan1 · Fatih Porikli2,3 Received: 4 June 2015 / Revised: 19 August 2015 / Accepted: 10 September 2015 © Springer-Verlag London 2015" f0b77702c8f2249ee1f48e51ff9b86faffe177c9,Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation,"Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation Ngan Le 1 Kha Gia Quach 1 2 Khoa Luu 1 Marios Savvides 1 Chenchen Zhu 1" f0e609a2e11a093273c0d8e3321e7b20eaca46e9,Closing the gap towards end-to-end autonomous vehicle system,"Closing the gap towards end-to-end autonomous vehicle system Yonatan Glassner∗, Liran Gispan∗, Ariel Ayash∗, and Tal Furman Shohet∗ AV AI Solutions - General Motors Israel January 7, 2019" f0a0e963f1ddd8a0b3269392e3d67043d2ace7d0,Roweis-Saul Classifier for Machine Learning,"MAEI5=K ?=IIEAH BH =?DEA A=HEC  4====H? /KHKKHJDE 8 4===?? )7*+ 4AIA=H?D +AJHA 16 +=FKI B )= 7ELAHIEJO +DHAFAJ +DA=E $ """" 1,1) )>IJH=?J 1  5=K 4MAEI ?=O EA=H =I = J BH EA=H   1 JDEI F=FAH MA JDA - =CHEJD BHK=JA EJ =I = ?=IIEAH E = =AH HAEEI?AJ B 0A AJ = ! =A EJ =BJAH 4MAEI 5=K KH AN FAHEAJI MEJD JDA 4 ;)- .-4-6 B=?A 156 IDM JD=J KH ?=IIEAH D=I HA?CEJE H=JAI B '#"" '### '#"" ' # HAIFA?JELAO ?A=HO KJFAHBHEC JDA >=IAEA 2+) ,) ?=IIEAHI =I MA =I JDA HA?AJO =F=?E=B=?AI 9A FHFIA = J JDA JH=EEC FD=IA B JDA ?=IIEAH >O FAHJKH>EC JDA MEJDE ?=II AJHEAI B JDA HA?IJHK?JE = JHEN JDA JH=EEC FD=IA 6DEI FAHJKH>=JE J = E?HA=IA E JDA IK??AII H=JAI BH IA 9A FEJ KJ JDA HA= JEIDEF >AJMAA JDA 4MAEI5=K ?=IIEAH 2+) ,) 8=HEKI DOFJDAIEI JAIJI D=LA >AA BH ?F=HEC ?=IIEAHI ""# 9A =FFO IA B JDA DOFJDAIEI JAIJI >O ,EAJJAHE?D" f0ca04fe6de04a46f44dabd8744b4163e8e0b4d3,Low-Resolution and Low-Quality Face Super-Resolution in Monitoring Scene via Support-Driven Sparse Coding,"J Sign Process Syst (2014) 75:245–256 DOI 10.1007/s11265-013-0804-9 Low-Resolution and Low-Quality Face Super-Resolution in Monitoring Scene via Support-Driven Sparse Coding Junjun Jiang & Ruimin Hu & Zhen Han & Zhongyuan Wang Received: 25 April 2013 / Revised: 2 June 2013 / Accepted: 4 June 2013 / Published online: 26 June 2013 # Springer Science+Business Media New York 2013" f0483ebab9da2ba4ae6549b681cf31aef2bb6562,3 C-GAN : A N CONDITION-CONTEXT-COMPOSITE GENERATIVE ADVERSARIAL NETWORKS FOR GENERATING IMAGES SEPARATELY,"Under review as a conference paper at ICLR 2018 C-GAN: AN CONDITION-CONTEXT-COMPOSITE GENERATIVE ADVERSARIAL NETWORKS FOR GEN- ERATING IMAGES SEPARATELY Anonymous authors Paper under double-blind review" f0865d11131a84ef1d91e1c8b5718692f153267d,AUTISM SPECTRUM DISORDERS 1 2 Explaining autism spectrum disorders : central coherence versus predictive coding theories,"Articles in PresS. J Neurophysiol (May 28, 2014). doi:10.1152/jn.00242.2014 EXPLAINING AUTISM SPECTRUM DISORDERS Explaining autism spectrum disorders: central coherence versus predictive coding theories. Target Article: Stevenson, R. A., Siemann, J. K., Schneider, B. C., Eberly, H. E., Woynaroski, T. G., Camarata, S. M., & Wallace, M. T. (2014). Multisensory Temporal Integration in Autism Spectrum Disorders. The Journal of Neuroscience, 34(3), 691-697. doi: 10.1523/jneurosci.3615-13.2014 Jason S. Chan* & Marcus J. Naumer Institute of Medical Psychology Goethe-University, Frankfurt KEYWORDS: Autism Spectrum Disorder, Multisensory Integration, Temporal Binding Window Acknowledgements: This was funded by the Hessian initiative for the development of scientific and economic excellence (LOEWE) Neuronal Coordination Research Focus Frankfurt (NeFF). *Corresponding author: Jason Chan Copyright © 2014 by the American Physiological Society." f0dd265dfbe9ffe86ca56ba053335626720059a3,CNN Fixations: An unraveling approach to visualize the discriminative image regions,"CNN Fixations: An unraveling approach to visualize the discriminative image regions Konda Reddy Mopuri*, Utsav Garg*, R. Venkatesh Babu, Senior Member, IEEE" f074f216e6eecd1be64398fdf1e06927b94c8df8,Classifying Faces with Non-negative Matrix Factorization,"Classifying Faces with Non-negative Matrix Factorization David Guillamet , Jordi Vitri`a Computer Vision Center, Dept. Inform`atica Universitat Aut`onoma de Barcelona 08193 Bellaterra, Barcelona, Spain" f00e51ec0e3894bdb2977a01824f37b15bb82c6e,A Gaussian Approximation of Feature Space for Fast Image Similarity,"Computer Science and ArtificialIntelligence LaboratoryTechnical Reportmassachusetts institute of technology, cambridge, ma 02139 usa — www.csail.mit.eduMIT-CSAIL-TR-2012-032October 1, 2012A Gaussian Approximation of Feature Space for Fast Image Similarity Michael Gharbi, Tomasz Malisiewicz, Sylvain Paris, and FrØdo Durand" cfffae38fe34e29d47e6deccfd259788176dc213,Training bookcowgrass flower ? ? water sky doggrass water boat water chair road ? cow grass chair grass dog building ?,"TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. X, NO. X, DECEMBER 2012 Matrix Completion for Weakly-supervised Multi-label Image Classification Ricardo Cabral, Fernando De la Torre, João P. Costeira, Alexandre Bernardino" cfcf66e4b22dc7671a5941e94e9d4afae75ba2f8,The Cramer Distance as a Solution to Biased Wasserstein Gradients,"The Cramer Distance as a Solution to Biased Wasserstein Gradients Marc G. Bellemare1, Ivo Danihelka1,3, Will Dabney1, Shakir Mohamed1 Balaji Lakshminarayanan1, Stephan Hoyer2, Rémi Munos1 Google DeepMind, London UK, 2Google CoMPLEX, Computer Science, UCL" cf77d2e7411814b30aca203376709b12a0eb3e08,Obtaining Better Image Representations by Combining Complementary Activation Features of Multiple ConvNet Layers for Transfer Learning,"Obtaining Better Image Representations by Combining Complementary Activation Features of Multiple ConvNet Layers for Transfer Learning Jumabek Alikhanov School of Computer and Information Engineering Seunghyun Ko School of Computer and Information Engineering Jo Geun Sik School of Computer and Information Engineering Inha University Incheon, South Korea Inha University Incheon, South Korea Inha University Incheon, South Korea Email: Email: Email:" cfd4004054399f3a5f536df71f9b9987f060f434,Person Recognition in Social Media Photos,"Person Recognition in Personal Photo Collections Seong Joon Oh,Rodrigo Benenson, Mario Fritz, and Bernt Schiele, Fellow, IEEE" cfa92e17809e8d20ebc73b4e531a1b106d02b38c,Parametric classification with soft labels using the evidential EM algorithm: linear discriminant analysis versus logistic regression,"Advances in Data Analysis and Classification manuscript No. (will be inserted by the editor) Parametric Classification with Soft Labels using the Evidential EM Algorithm Linear Discriminant Analysis vs. Logistic Regression Benjamin Quost · Thierry Denœux · Shoumei Li Received: date / Accepted: date" cfbfcf538c1c9bbf170a524995098fe4aacde374,Symmetric generalized low rank approximations of matrices,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" cfbb2d32586b58f5681e459afd236380acd86e28,Improving alignment of faces for recognition,"Improving Alignment of Faces for Recognition Md. Kamrul Hasan Christopher J. Pal D´epartement de g´enie informatique et g´enie logiciel ´Ecole Polytechnique de Montr´eal, D´epartement de g´enie informatique et g´enie logiciel ´Ecole Polytechnique de Montr´eal, Qu´ebec, Canada Qu´ebec, Canada" cf40951840bfa9b8721d722e9422c73e3a6fbf59,Real-time Appearance-based Person Re-identification Over Multiple KinectTM Cameras,"Real-time appearance-based person re-identification over multiple KinectTMcameras Riccardo Satta, Federico Pala, Giorgio Fumera and Fabio Roli Department of Electrical and Electronic Engineering, University of Cagliari, Italy {riccardo.satta, fumera, Keywords: Video surveillance, Person Re-identification, Kinect" cf98c333c8d7d5870c1ce5538bb0c3de3de16657,Panoptic Segmentation,"Panoptic Segmentation Alexander Kirillov1,2 Kaiming He1 Ross Girshick1 Carsten Rother2 Piotr Doll´ar1 Facebook AI Research (FAIR) HCI/IWR, Heidelberg University, Germany" cfdc632adcb799dba14af6a8339ca761725abf0a,Probabilistic Formulations of Regression with Mixed Guidance,"Probabilistic Formulations of Regression with Mixed Guidance Aubrey Gress, Ian Davidson University of California, Davis" cf74dceae075bde213d2aafad115d2afc893c21b,Master's Thesis : Deep Learning for Visual Recognition,"Master’s Thesis Deep Learning for Visual Recognition Supervised by Nicolas Thome and Matthieu Cord Remi Cadene Wednesday 7th September, 2016" cf65c5cfa2a2b0370407810479f179f5fbe88fb1,Multi-Modal Biometrics : An Overview,"Multi-Modal Biometrics: An Overview Kevin W. Bowyer,1 K. I. Chang,1 P. Yan,1 P. J. Flynn,1 E. Hansley,2 S. Sarkar2 . Computer Science and Engineering / University of Notre Dame / Notre Dame, IN 46556 USA . Computer Science and Engineering / University of South Florida / Tampa, FL 33620 USA" cfd8c66e71e98410f564babeb1c5fd6f77182c55,Vector Quantization Segmentation for Head Pose Estimation,"Comparative Study of Coarse Head Pose Estimation Lisa M. Brown and Ying-Li Tian IBM T.J. Watson Research Center Hawthorne, NY 10532" cf384eda31030a45238ebd8356ace7600da5076b,Cross-Domain CNN for Hyperspectral Image Classification,"CROSS-DOMAIN CNN FOR HYPERSPECTRAL IMAGE CLASSIFICATION Hyungtae Lee†‡, Sungmin Eum†‡, Heesung Kwon‡ Booz Allen Hamilton Inc., McLean, Virginia, U.S.A. U.S. Army Research Laboratory, Adelphi, Maryland, U.S.A. lee eum" cf009a6b02fbef514a4bac9695a928080ceac764,COLUMBUS : Feature Selection on Data Analytics Systems,"COLUMBUS: Feature Selection on Data Analytics Systems Arun Kumar Pradap Konda Christopher R´e February 28, 2013" cf6eef2ac9ca1a76d0e70006ca9bc3cb3fb80b0b,Recognizing Open-Vocabulary Relations between Objects in Images,"Recognizing Open-Vocabulary Relations between Objects in Images Masayasu Muraoka∗ Kota Yamaguchi‡ Masaki Saito‡ Naoaki Okazaki† Takayuki Okatani‡ Kentaro Inui† Sumit Maharjan† IBM Research – Tokyo∗ Tohoku University†‡" cf34bda14a2f6148f330213e0ec0dbfe3062c959,Concatenative Resynthesis Using Twin Networks,"INTERSPEECH 2017 August 20–24, 2017, Stockholm, Sweden Concatenative Resynthesis using twin networks Soumi Maiti1, Michael I Mandel1,2 The Graduate Center, CUNY, USA Brooklyn College, CUNY, USA" cf86616b5a35d5ee777585196736dfafbb9853b5,Learning Multiscale Active Facial Patches for Expression Analysis,"This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. Learning Multiscale Active Facial Patches for Expression Analysis Lin Zhong, Qingshan Liu, Peng Yang, Junzhou Huang, and Dimitris N. Metaxas, Senior Member, IEEE" cf968e26add377a7edeae338629f2f4edb050b0d,"Project-Team PRIMA Perception , recognition and integration for interactive environments Rhône-Alpes","INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE Project-Team PRIMA Perception, recognition and integration for interactive environments Rhône-Alpes THEME COG tivitytepor2005" cf103f2fe5595a55f918ecbd9119800f4747fc8e,Human recognition based on ear shape images using PCA-Wavelets and different classification methods,"Human recognition based on ear shape images using PCA-Wavelets and different classification methods Ali Mahmoud Mayya1* and Mariam Mohammad Saii PhD student, Computer Engineering, Tishreen University, Syria" cf5bdf52cf269c9f3ebf548756146763f55e42d6,Title of Thesis: Contour Based 3d Face Modeling from Monocular Video Contour Based 3d Face Modeling from Monocular Video, cf280435c471ee099148c4eb9eb2e106ccb2b218,HoME: a Household Multimodal Environment,"HoME: a Household Multimodal Environment Simon Brodeur1, Ethan Perez2,3∗, Ankesh Anand2∗, Florian Golemo2,4∗, Luca Celotti1, Florian Strub2,5, Jean Rouat1, Hugo Larochelle6,7, Aaron Courville2,7 Université de Sherbrooke, 2MILA, Université de Montréal, 3Rice University, 4INRIA Bordeaux, 5Univ. Lille, Inria, UMR 9189 - CRIStAL, 6Google Brain, 7CIFAR Fellow {simon.brodeur, luca.celotti, {florian.golemo, {ankesh.anand," cf6527d8d42a9958eea7d8d1f90ea4c86d591408,Convolutional Neural Network-Based Classification of Driver’s Emotion during Aggressive and Smooth Driving Using Multi-Modal Camera Sensors,"Article Convolutional Neural Network-Based Classification of Driver’s Emotion during Aggressive and Smooth Driving Using Multi-Modal Camera Sensors Kwan Woo Lee, Hyo Sik Yoon, Jong Min Song and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (K.W.L.); (H.S.Y.); (J.M.S.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 20 February 2018; Accepted: 21 March 2018; Published: 23 March 2018" cf8f5cad6aa87a6364f6b5dd985116b902050acf,Slack and Margin Rescaling as Convex Extensions of Supermodular Functions,"Slack and Margin Rescaling as Convex Extensions of Supermodular Functions Matthew B. Blaschko Center for Processing Speech & Images Departement Elektrotechniek, KU Leuven Kasteelpark Arenberg 10 001 Leuven, Belgium" cf7b4fa0a8b58473b94496f353f3c8d0f9531b71,Recognition of 3 D Frontal Face Images Using Local Ternary Patterns and MLDA Algorithm,"International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Impact Factor (2012): 3.358 Recognition of 3D Frontal Face Images Using Local Ternary Patterns and MLDA Algorithm Dr. T. Karthikeyan1, T. K. Sumathi2 Associate Professor, PSG College of Arts & Science, Coimbatore Research Scholar, Karpagam University, Coimbatore identification" cf805d478aeb53520c0ab4fcdc9307d093c21e52,Finding Tiny Faces in the Wild with Generative Adversarial Network,"Finding Tiny Faces in the Wild with Generative Adversarial Network Yancheng Bai1 Yongqiang Zhang1 Mingli Ding2 Bernard Ghanem1 Visual Computing Center, King Abdullah University of Science and Technology (KAUST) School of Electrical Engineering and Automation, Harbin Institute of Technology (HIT) Institute of Software, Chinese Academy of Sciences (CAS) {zhangyongqiang, Figure1. The detection results of tiny faces in the wild. (a) is the original low-resolution blurry face, (b) is the result of re-sizing directly by a bi-linear kernel, (c) is the generated image by the super-resolution method, and our result (d) is learned y the super-resolution (×4 upscaling) and refinement network simultaneously. Best viewed in color and zoomed in." cffc94574c8796cbd8234422a979e57e67eca7b5,Multiracial Children's and Adults' Categorizations of Multiracial Individuals.,"Journal of Cognition and Development ISSN: 1524-8372 (Print) 1532-7647 (Online) Journal homepage: http://www.tandfonline.com/loi/hjcd20 Multiracial Children’s and Adults’ Categorizations of Multiracial Individuals Steven O. Roberts & Susan A. Gelman To cite this article: Steven O. Roberts & Susan A. Gelman (2017) Multiracial Children’s and Adults’ Categorizations of Multiracial Individuals, Journal of Cognition and Development, 18:1, -15, DOI: 10.1080/15248372.2015.1086772 To link to this article: http://dx.doi.org/10.1080/15248372.2015.1086772 Accepted author version posted online: 23 Feb 2016. Published online: 23 Feb 2016. Submit your article to this journal Article views: 75 View related articles View Crossmark data Citing articles: 2 View citing articles Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=hjcd20 Download by: [University of Michigan]" cf216fcd4cf537e53b9ed4f46e59c445e845cfc5,Nonnegative Restricted Boltzmann Machines for Parts-based Representations Discovery and Predictive Model Stabilization,"Noname manuscript No. (will be inserted by the editor) Nonnegative Restricted Boltzmann Machines for Parts-based Representations Discovery and Predictive Model Stabilization Tu Dinh Nguyen, Truyen Tran, Dinh Phung, Svetha Venkatesh the date of receipt and acceptance should be inserted later" cfc30ce53bfc204b8764ebb764a029a8d0ad01f4,Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization,"Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization Hyeonwoo Noh Tackgeun You Dept. of Computer Science and Engineering, POSTECH, Korea Jonghwan Mun Bohyung Han" cf875336d5a196ce0981e2e2ae9602580f3f6243,"7 What 1 s It Mean for a Computer to "" Have "" Emotions ?","7 What 1 Rosalind W. Picard It Mean for a Computer to ""Have"" Emotions? There is a lot of talk about giving machines emotions, some of it fluff. Recently at a large technical meeting, a researcher stood up nd talked of how a Bamey stuffed animal [the purple dinosaur for kids) ""has emotions."" He did not define what he meant by this, but fter repeating it several times, it became apparent that children ttributed emotions to Barney, and that Barney had deliberately expressive behaviors that would encourage the kids to think. Bar- ney had emotions. But kids have attributed emotions to dolls and stuffed animals for as long a s we know; and most of my technical olleagues would agree that such toys have never had and still do not have emotions. What is different now that prompts a researcher to make such a claim? Is the computational plush an example of a omputer that really does have emotions? If not Barney, then what would be an example of a computa- tional system that has emotions? I am not a philosopher, and this paper will not be a discussion of the meaning of this question in ny philosophical sense. However, as an engineer I am interested" cfc22c35ad191cf9d70f4a3655840748b0e1322c,Real-Time Dense Mapping for Self-driving Vehicles using Fisheye Cameras,"Real-Time Dense Mapping for Self-Driving Vehicles using Fisheye Cameras Zhaopeng Cui1, Lionel Heng2, Ye Chuan Yeo2, Andreas Geiger3, Marc Pollefeys1,4, and Torsten Sattler1" cf185d0d8fcad2c7f0a28b7906353d4eca5a098b,Improved gradient local ternary patterns for facial expression recognition,"Holder and Tapamo EURASIP Journal on Image and Video Processing (2017) 2017:42 DOI 10.1186/s13640-017-0190-5 EURASIP Journal on Image nd Video Processing RESEARCH Open Access Improved gradient local ternary patterns for facial expression recognition Ross P. Holder and Jules R. Tapamo*" cf2a313b039b8adfee2a14ca5e81f2f5da52b0f2,Learning Fashion Traits with Label Uncertainty,"Learning Fashion Traits with Label Uncertainty Gal Levi Eli Alshan Assaf Neuberger Amazon Lab 126 Herzliya, Israel 4672560 Amazon Lab 126 Herzliya, Israel 4672560 Amazon Lab 126 Herzliya, Israel 4672560 Sharon Alpert Amazon Lab 126 Herzliya, Israel 4672560 Eduard Oks Amazon Lab 126 Herzliya, Israel 4672560" 75522dfc1610c8765185c4344d97db33e1af5047,3D Human Body-Part Tracking and Action Classification Using A Hierarchical Body Model,"RASKIN, RUDZSKY, RIVLIN: BODY-PART TRACKING AND ACTION CLASSIFICATION D Human Body-Part Tracking and Action Classification Using a Hierarchical Body Model Leonid Raskin Michael Rudzsky Ehud Rivlin Computer Science Department Technion -Israel Institute of Technology Haifa, Israel, 3200" 758d7e1be64cc668c59ef33ba8882c8597406e53,"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","IEEE TRANSACTIONS ON AFFECTIVE COMPUTING AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild Ali Mollahosseini, Student Member, IEEE, Behzad Hasani, Student Member, IEEE, nd Mohammad H. Mahoor, Senior Member, IEEE" 758572c5779a47e898caff7232af76eda253163b,Csr: Medium: Collaborative Research: Architecture and System Support for Power-agile Computing,"CSR: MEDIUM: COLLABORATIVE RESEARCH: ARCHITECTURE AND SYSTEM SUPPORT FOR POWER-AGILE COMPUTING Co-PI: Geoffrey Challen (University at Buffalo), Co-PI: Mark Hempstead (Drexel University) NSF PROPOSAL 5 OCT 2013 As energy management on energy-constrained devices continues to challenge researchers and frustrate users, device designs are addressing the problem by integrating more hardware components that can trade off energy and performance. Dynamic voltage-and-frequency scaling (DVFS) allows CPUs and memory to trade off speed and energy, buffering and polling rates allow radios to trade off latency and energy, nd screen refresh rates allow displays to trade off quality and energy. And as the Dark Silicon utilization wall forces systems to choose what parts of the CPU to operate, the already-large configuration space will explode. This proposal refers to the emerging class of devices integrating multiple energy-proportional omponents as power-agile, reflecting their potential ability to adaptively reallocate energy usage between omponents to improve performance and save energy. But as energy-management features proliferate, new interfaces enabling coordination between applications, the operating system (OS), and hardware are urgently needed to realize the potential energy and performance benefits. INTELLECTUAL MERIT: Our proposal describes a new architecture for power-agile systems with both novel interfaces that cleanly separate energy management responsibilities and a new approach to energy llocation driven by differences in hardware energy efficiency. Applications use resource requests to allo- ate energy between hardware components, making their resource needs explicit. The OS manages energy" 75073faadb967823db48794e9cd54b681bb0729b,Thermal-Aware Task Allocation and Scheduling for Heterogeneous Multi-core Cyber-Physical Systems,"Thermal-Aware Task Allocation and Scheduling for Heterogeneous Multi-core Cyber-Physical Systems Department of Electrical and Computer Engineering University of Massachusetts Amherst, Amherst, MA, 01003 Shikang Xu, Israel Koren and C. M. Krishna" 75c3ba0c7e5b0d4a11e9d2e073ccd02ee688c0c9,"A Multimodal LDA Model integrating Textual, Cognitive and Visual Modalities","Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1146–1157, Seattle, Washington, USA, 18-21 October 2013. c(cid:13)2013 Association for Computational Linguistics" 750e567370fd8c37bab657207195517405727a71,Time Aware Task Delegation in Agent Interactions for Video-Surveillance,"Time aware task delegation in agent interactions for video-surveillance Paolo Sernani1, Matteo Biagiola2,3, Nicola Falcionelli1, Dagmawi Neway Mekuria1, Stefano Cremonini4, Aldo Franco Dragoni1 Dipartimento di Ingegneria dell’Informazione, Universit`a Politecnica delle Marche, Ancona, Italy {p.sernani, {n.falcionelli, Fondazione Bruno Kessler, Trento, Italy Universit`a degli Studi di Genova, Genova, Italy Site Spa, Bologna, Italy" 759a3b3821d9f0e08e0b0a62c8b693230afc3f8d,Attribute and simile classifiers for face verification,"Attribute and Simile Classifiers for Face Verification Neeraj Kumar Alexander C. Berg Peter N. Belhumeur Columbia University∗ Shree K. Nayar" 7538ad235caf4dbc64a8b94a6146e1212d4de1ff,Amygdala dysfunction in men with the fragile X premutation.,"doi:10.1093/brain/awl338 Brain (2007), 130, 404–416 Amygdala dysfunction in men with the fragile X premutation David Hessl,1,2 Susan Rivera,1,5 Kami Koldewyn,1,6 Lisa Cordeiro,1 John Adams,1 Flora Tassone,1,4 Paul J. Hagerman1,4 and Randi J. Hagerman1,3 Medical Investigation of Neurodevelopmental Disorders (MIND) Institute and Departments of 2Psychiatry and Behavioral Sciences, 3Pediatrics, University of California-Davis, Medical Center, Sacramento, 4Department of Biochemistry and Molecular Medicine, University of California-Davis, School of Medicine, 5Department of Psychology and 6Center for Neuroscience, University of California-Davis, Davis, CA, USA Correspondence to: David Hessl, PhD, Assistant Clinical Professor, MIND Institute, University of California, Davis Medical Center, 2825 50th Street, Sacramento, CA 95817, USA. E-mail: Premutation alleles (55–200 CGG repeats) of the fragile X mental retardation 1 (FMR1) gene are associated with autism spectrum disorder in childhood, premature ovarian failure, and the neurodegenerative disorder, fragile X-associated tremor/ataxia syndrome (FXTAS). FXTAS, and perhaps the other clinical presentations mong carriers, are thought to be due to toxic gain-of-function of elevated levels of the expanded-repeat FMR1 mRNA. Previous structural MRI studies have implicated the amygdala as a potential site of dysfunction underlying social deficits and/or risk for FXTAS. As a preliminary investigation of this possible association, adult males with the premutation, and male controls matched for IQ, age and education, completed three protocols" 7515dc37fd1e62a3c1e9bbe175c093c0c5cc7bed,Multi-Pose Face Recognition Using Fuzzy Ant Algorithm and Center of Gravity Search,"IJCSNS International Journal of Computer Science and Network Security, VOL.11 No.3, March 2011 Multi-Pose Face Recognition Using Fuzzy Ant Algorithm and Center of Gravity Search Supawee Makdee1, Chom Kimpan2 and Seri Pansang3 Faculty of Information Technology, Rangsit University, Bangkok, THAILAND Summary In this paper, we present the novel technique to solve the recognition errors and minimize memory size of invariant range image multi-pose face recognition. Range image face data (RIFD) was obtained from a laser range finder and was used in the model to generate multi-pose. The fuzzy ant clustering lgorithm is used to classify and find the number of clusters for reduced recognition time. RIFD will be transformed by the gradient transformation into significant feature and matching by using Membership Matching Score (MMS) and Center of Gravity (CG) search. The proposed method was tested using facial range images from 130 persons with normal facial expressions. The processing time of the recognition system is etter than 3LMS. Moreover, it is 6 times faster without any hange of recognition rate. Memory size of this experimental was" 75827a2021ac2ad2256144b2a2fe301948d39b51,AI Benchmark: Running Deep Neural Networks on Android Smartphones,"AI Benchmark: Running Deep Neural Networks on Android Smartphones Andrey Ignatov ETH Zurich Radu Timofte ETH Zurich William Chou Qualcomm, Inc. Ke Wang Huawei, Inc. Max Wu MediaTek, Inc. Tim Hartley Arm, Inc. Luc Van Gool ∗ ETH Zurich" 75d59ae0ed3ce51e37b383985cfff310251f591a,Cost-Sensitive Robustness against Adversarial Examples,"Cost-Sensitive Robustness against Adversarial Examples Xiao Zhang∗ nd David Evans†" 75249ebb85b74e8932496272f38af274fbcfd696,Face Identification in Large Galleries,"Face Identification in Large Galleries Rafael H. Vareto, Filipe Costa, William Robson Schwartz Smart Surveillance Interest Group, Department of Computer Science Universidade Federal de Minas Gerais, Belo Horizonte, Brazil" 75e9401e70c05c4d080e2d17f83ed2b61b44b3af,A distributed algorithm for partitioned robust submodular maximization,"A Distributed Algorithm for Partitioned Robust Submodular Maximization Ilija Bogunovic, Slobodan Mitrovi´c, Jonathan Scarlett, and Volkan Cevher École Polytechnique Fédérale de Lausanne (EPFL) {ilija.bogunovic, slobodan.mitrovic, jonathan.scarlett," 75503aff70a61ff4810e85838a214be484a674ba,Improved facial expression recognition via uni-hyperplane classification,"Improved Facial Expression Recognition via Uni-Hyperplane Classification S.W. Chew∗, S. Lucey†, P. Lucey‡, S. Sridharan∗, and J.F. Cohn‡" 75650bfc20036d99314f7ddae8f2baecde3d57e2,Concave Losses for Robust Dictionary Learning,"CONCAVE LOSSES FOR ROBUST DICTIONARY LEARNING Rafael Will M. de Araujo, R. Hirata Jr ∗ Alain Rakotomamonjy † University of S˜ao Paulo Institute of Mathematics and Statistics Rua do Mat˜ao, 1010 – 05508-090 – S˜ao Paulo-SP, Brazil Universit´e de Rouen Normandie LITIS EA 4108 76800 Saint- ´Etienne-du-Rouvray, France" 75df6bc2dd7225446f2a421d99e9db80b9c50837,Multithread Face Recognition in Cloud,"Publishing CorporationJournal of SensorsVolume 2016, Article ID 2575904, 21 pageshttp://dx.doi.org/10.1155/2016/2575904" 75a9d9ea6c1a5ee55fc0ccb347b263785b15ac0a,An Image Search Reranking Model based on attribute assisted hypergraph Miss,"International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 03 Issue: 05 | May-2016 www.irjet.net p-ISSN: 2395-0072 An Image Search Reranking Model based on ttribute assisted hypergraph Miss. Madhuri J.Mhaske1, Prof. Sachin P.Patil2 PG Scholar Computer Engineering , G. H. Raisoni College of Engineering and Management, Savitribai Phule Pune University , Chas, Ahmednagar.414001,Maharashtra, India. Assistant professor, computer engineering, G.H. Raisoni College of engineering and Management, Savitribai Phule Pune University, Wagholi, Pune 411015, Maharashtra, India. ---------------------------------------------------------------------***--------------------------------------------------------------------- user wants to search for a red image, the images cannot be" 75e02f14e9871a405d2d367dd7c77c730499fed6,Perceptual Generative Adversarial Networks for Small Object Detection,"Perceptual Generative Adversarial Networks for Small Object Detection Jianan Li Xiaodan Liang Yunchao Wei Tingfa Xu Jiashi Feng Shuicheng Yan" 75879ab7a77318bbe506cb9df309d99205862f6c,Analysis of emotion recognition from facial expressions using spatial and transform domain methods,"Analysis Of Emotion Recognition From Facial Expressions Using Spatial And Transform Domain Methods Ms. P. Suja* and Dr. Shikha Tripathi" 7543cf85a3fb56470b0020c0fc6db45e64f7ae5e,Object Proposals Estimation in Depth Image Using Compact 3D Shape Manifolds,"Object Proposal Estimation in Depth Images using Compact 3D Shape Manifolds Shuai Zheng1, Victor Adrian Prisacariu1, Melinos Averkiou2, Ming-Ming Cheng1,5, Niloy J. Mitra2, Jamie Shotton3, Philip H. S. Torr1, Carsten Rother4 University of Oxford†, 2University College London‡, 3Microsoft Research, 4TU Dresden, 5Naikai University §" 75308067ddd3c53721430d7984295838c81d4106,Rapid Facial Reactions in Response to Facial Expressions of Emotion Displayed by Real Versus Virtual Faces,"Article Rapid Facial Reactions in Response to Facial Expressions of Emotion Displayed by Real Versus Virtual Faces i-Perception 018 Vol. 9(4), 1–18 ! The Author(s) 2018 DOI: 10.1177/2041669518786527 journals.sagepub.com/home/ipe Leonor Philip, Jean-Claude Martin and Ce´ line Clavel LIMSI, CNRS, University of Paris-Sud, Orsay, France" 751e11880b54536a89bfcc4fd904b0989345a601,Hierarchical Adversarially Learned Inference,"HIERARCHICAL ADVERSARIALLY LEARNED INFERENCE Mohamed Ishmael Belghazi1, Sai Rajeswar1, Olivier Mastropietro1, Negar Rostamzadeh2, Jovana Mitrovic2 and Aaron Courville1† MILA, Université de Montréal, Element AI, DeepMind, CIFAR Fellow." 75d5e67e31cefa09ae46044fa1f9f7696e058c99,MRI based Techniques for Detection of Alzheimer: A Survey,"MRI based Techniques for Detection of Alzheimer: A Survey {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 159 Number 5 Year of Publication: 2017 Authors: Ruaa Adeeb Abdulmunem Al-falluji 10.5120/ijca2017912929 {bibtex}2017912929.bib{/bibtex}" 75976b1d3fae34f975374357eb9632ebb6c3a5f0,Binarising SIFT-Descriptors to Reduce the Curse of Dimensionality in Histogram-Based Object Recognition,"International Journal of Signal Processing, Image Processing and Pattern Recognition Vol. 3, No. 1, March, 2010 Binarising SIFT-Descriptors to Reduce the Curse of Dimensionality in Histogram-Based Object Recognition TZI Center for Computing and Communication Technologies University Bremen, Am Fallturm 1, 28359 Bremen, Germany Martin Stommel" 754ffd18b106e6ef3644e3670faf28d798b841cd,Momo: Monocular motion estimation on manifolds,"Momo: Monocular Motion Estimation on Manifolds Johannes Graeter1, Tobias Strauss1, and Martin Lauer1 Institute of Measurement and Control (MRT) , Karlsruhe Institute of Technology (KIT), Email: August 2, 2017" 75d8f2da0e9d80eef141c765254d7752445afb53,Violent video detection based on MoSIFT feature and sparse coding,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE Long Xu1, Chen Gong1, Jie Yang1(cid:3), Qiang Wu2, Lixiu Yao1 . INTRODUCTION" 75e4efae6de6d1ac787a6ca381fb49381fcb062b,Hierarchical Representation Learning for Kinship Verification,"IEEE TRANSACTIONS ON IMAGE PROCESSING Hierarchical Representation Learning for Kinship Verification Naman Kohli, Student Member, IEEE, Mayank Vatsa, Senior Member, IEEE, Richa Singh, Senior Member, IEEE, Afzel Noore, Senior Member, IEEE, and Angshul Majumdar, Senior Member, IEEE" 75cb21fa931e957941c0237a1030aa36209bae36,GAUSSIAN PROCESS FOR ACTIVITY MODELING AND ANOMALY DETECTION,"GAUSSIAN PROCESS FOR ACTIVITY MODELING AND ANOMALY DETECTION Wentong Liaoa, Bodo Rosenhahna, Michael Ying Yangb Institute for Information Processing, Leibniz University Hannover, Germany Computer Vision Lab, TU Dresden, Germany KEY WORDS: Gaussian Process regression, activity modeling, anomaly detection Commission WG III/3" 75b987f86af2bc7f68edc45be240dd30e1ef2699,Sampling Algorithms to Handle Nuisances in Large-Scale Recognition,"UNIVERSITY OF CALIFORNIA Los Angeles Sampling Algorithms to Handle Nuisances in Large-Scale Recognition A dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Computer Science Nikolaos Karianakis" cc5f4d5aa9c3ffa75a335f3305a1caf9cbdeb71f,LEARNING HIERARCHICAL REPRESENTATIONS FOR VIDEO ANALYSIS USING DEEP LEARNING,"LEARNING HIERARCHICAL REPRESENTATIONS FOR VIDEO ANALYSIS USING DEEP LEARNING YANG YANG B.S. Beijing University of Technology, 2008 A dissertation submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy in the Department of Electrical Engineering and Computer Science in the College of Engineering and Computer Science t the University of Central Florida Orlando, Florida Summer Term Major Professor: Mubarak Shah" ccbd7e417158e7ae0f9f61c3b6d1e5a3317cce34,Object Proposals in Computer Vision,"Object Proposals in Computer Vision Neelima Chavali Thesis submitted to the faculty of the Virginia Polytechnic Institute and State University in partial fulfillment of the requirements for the degree of Master of Science Electrical Engineering Dhruv Batra, Chair Devi Parikh Lynn Abbott 2nd July, 2015 Blacksburg, Virginia Keywords: Object proposals, evaluation, computer vision Copyright 2015, Neelima Chavali" cc4a2cab31ed06d0d8723df0bdf8cd0ece71bbe9,Analysis of Using Metric Access Methods for Visual Search of Objects in Video Databases,"Analysis of Using Metric Access Methods for Visual Search of Objects in Video Databases Henrique Batista da Silva 1 Zenilton Kleber Gonçalves do Patrocínio Júnior 2 Silvio Jamil Ferzoli Guimarães 2" cc5a62bd7c45a9ca479506acb572566331354fa3,Eye localization through multiscale sparse dictionaries,"Eye Localization through Multiscale Sparse Dictionaries Fei Yang, Junzhou Huang, Peng Yang and Dimitris Metaxas" cc09cf5831fcae802ed2905a61ab502956655bbe,Shape-based instance detection under arbitrary viewpoint,"Shape-based instance detection under arbitrary viewpoint Edward Hsiao and Martial Hebert" cc3c273bb213240515147e8be68c50f7ea22777c,Gaining Insight Into Films Via Topic Modeling & Visualization,"Gaining Insight Into Films Via Topic Modeling & Visualization MISHA RABINOVICH, MFA YOGESH GIRDHAR, PHD KEYWORDS Collaboration, computer vision, cultural nalytics, economy of abundance, interactive data visualization We moved beyond misuse when the software actually ecame useful for film analysis with the addition of audio nalysis, subtitle analysis, facial recognition, and topic modeling. Using multiple types of visualizations and back-and-fourth workflow between people and AI we arrived at an approach for cultural analytics that an be used to review and develop film criticism. Finally, we present ways to apply these techniques to Database Cinema and other aspects of film and video creation. PROJECT DATE 2014 URL http://misharabinovich.com/soyummy.html" cc91001f9d299ad70deb6453d55b2c0b967f8c0d,Performance Enhancement of Face Recognition in Smart TV Using Symmetrical Fuzzy-Based Quality Assessment,"OPEN ACCESS ISSN 2073-8994 Article Performance Enhancement of Face Recognition in Smart TV Using Symmetrical Fuzzy-Based Quality Assessment Yeong Gon Kim, Won Oh Lee, Ki Wan Kim, Hyung Gil Hong and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 26 Pil-dong 3-ga, Jung-gu, Seoul 100-715, Korea; E-Mails: (Y.G.K.); (W.O.L.); (K.W.K.); (H.G.H.) * Author to whom correspondence should be addressed; E-Mail: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735. Academic Editor: Christopher Tyler Received: 31 March 2015 / Accepted: 21 August 2015 / Published: 25 August 2015" cc2bb4318191a04e3fc82c008c649f5b90151e4d,Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering,"Published as a conference paper at ICLR 2018 BEYOND SHARED HIERARCHIES: DEEP MULTITASK LEARNING THROUGH SOFT LAYER ORDERING Elliot Meyerson & Risto Miikkulainen The University of Texas at Austin and Sentient Technologies, Inc. {ekm," cc7dd285ee25174f184c0f23a02bc23fb80ad573,Images Similarity Detection Based on Directional Gradient Angular Histogram,"Images Similarity Detection Based on Directional Gradient Angular Histogram Jinye Peng1,2, Bianzhang Yu2, Dakai Wang1 . Department of Electronics, Northwest University, Xi’an, 710069, P.R.China; . Department of Electrical Engineering, Northwestern Polytechnic University, Xi’an, 710072, P.R.China E-mail:" cce261b47bbeec42cf4036e89e2413e25f66ce61,Gender recognition from facial images : 2 D or 3 D ?,"Zhang, W., Smith, M., Smith, L. and Farooq, A. (2016) Gender recog- nition from facial images: 2D or 3D? Journal of the Optical Society of America A, 33 (3). pp. 333-344. ISSN 1084-7529 Available from: http://eprints.uwe.ac.uk/28147 We recommend you cite the published version. The publisher’s URL is: http://dx.doi.org/10.1364/JOSAA.33.000333 Refereed: Yes (no note) Disclaimer UWE has obtained warranties from all depositors as to their title in the material deposited and as to their right to deposit such material. UWE makes no representation or warranties of commercial utility, title, or fit- ness for a particular purpose or any other warranty, express or implied in respect of any material deposited. UWE makes no representation that the use of the materials will not infringe ny patent, copyright, trademark or other property or proprietary rights. UWE accepts no liability for any infringement of intellectual property rights in any material deposited but will remove such material from public view pend- ing investigation in the event of an allegation of any such infringement." cca228b47a603a9b9e2a1e3a1b278b35612d078d,Randomized Face Recognition on Partially Occluded Images,"Randomized Face Recognition on Partially Occluded Images Ariel Morelli Andres, Sebastian Padovani, Mariano Tepper, Marta Mejail, and Julio Jacobo Departamento de Computación, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Argentina." cc9f473584c1a7f224b42d4a3a3ea2864173cc28,Hephaestus: Data Reuse for Accelerating Scientific Discovery,"Hephaestus: Data Reuse for Accelerating Scientific Discovery Jennie Duggan Northwestern EECS" cca198ae698e7956992f2fb326c04965b2964a18,Learning Pain from Emotion: Transferred HoT Data Representation for Pain Intensity Estimation,"Learning Pain from Emotion: Transferred HoT Data Representation for Pain Intensity Estimation Corneliu Florea1, Laura Florea1, and Constantin Vertan1 Image Processing and Applications Laboratory, {corneliu.florea; laura.florea; constantin.vertan} University “Politehnica” of Bucharest," cc622a0ac114821be935ca9c66cc177b93e18876,Anomaly Detection Based on Trajectory Analysis Using Kernel Density Estimation and Information Bottleneck Techniques,"Anomaly Detection Based on Trajectory Analysis Using Kernel Density Estimation and Information Bottleneck Techniques Yuejun Guo, Qing Xu(cid:3), Yu Yang, Sheng Liang, Yu Liu, Mateu Sbert" cc96eab1e55e771e417b758119ce5d7ef1722b43,An Empirical Study of Recent Face Alignment Methods,"An Empirical Study of Recent Face Alignment Methods Heng Yang, Xuhui Jia, Chen Change Loy and Peter Robinson" cc3e1a6376928138dff5582b7a56d40cfb3b7367,Cost-Effective Features for Reidentification in Camera Networks,"Cost-effective features for re-identification in camera networks Syed Fahad Tahir and Andrea Cavallaro" cc246025ec8e1d32ecfbeefaba0727fdf73cd9cb,Vehicle Tracking by Simultaneous Detection and Viewpoint Estimation,"Vehicle Tracking by Simultaneous Detection and Viewpoint Estimation Ricardo Guerrero-G´omez-Olmedo1, Roberto L´opez-Sastre1, Saturnino Maldonado-Basc´on1, and Antonio Fern´andez-Caballero2 GRAM, Department of Signal Theory and Communications, UAH, Alcal´a de Henares, Spain. Department of Computing Systems, UCLM, Albacete, Spain." ccd5bd5ce40640ebc6665b97a86ba3d28e457d11,Contributions to a fast and robust object recognition in images. (Contributions à une reconnaissance d'objet rapide et robuste en images),"Contributions to a fast and robust object recognition in images J´erˆome Revaud To cite this version: J´erˆome Revaud. Contributions to a fast and robust object recognition in images. Other [cs.OH]. INSA de Lyon, 2011. English. . HAL Id: tel-00694442 https://tel.archives-ouvertes.fr/tel-00694442 Submitted on 4 May 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires" cca2bee0973e347efd7b3d145b6d23286c801bd1,VoCMex: a voice corpus in Mexican Spanish for research in speaker recognition,"Int J Speech Technol DOI 10.1007/s10772-012-9183-z VoCMex: a voice corpus in Mexican Spanish for research in speaker recognition José-Martín Olguín-Espinoza · Pedro Mayorga-Ortiz · Hugo Hidalgo-Silva · Luis Vizcarra-Corral · Mónica-Livier Mendiola-Cárdenas Received: 17 July 2012 / Accepted: 14 November 2012 © Springer Science+Business Media New York 2012" cc34b0ab84e82a6d8ebce08eff1b7556026b5352,Face Recognition using Gaussian Hermite Moments,"Special Issue of International Journal of Computer Applications (0975 – 8887) on Software Engineering, Databases and Expert Systems – SEDEXS, September 2012 D Face Recognition using Gaussian Hermite Moments Naouar Belghini Faculty of Technical Sciences B.P. 2202 – Road of Imouzzer Fez – Morocco Arsalane Zarghili Faculty of Technical Sciences B.P. 2202 – Road of Imouzzer Fez – Morocco Jamal Kharroubi Faculty of Technical Sciences B.P. 2202 – Road of Imouzzer Fez – Morocco" ccd99008d942b890cecd308a31ba61240eac9e54,Learning to Segment Every Thing,"Learning to Segment Every Thing Ronghang Hu1,2,∗ Piotr Doll´ar2 Kaiming He2 Trevor Darrell1 Ross Girshick2 BAIR, UC Berkeley Facebook AI Research (FAIR)" cc3bda396bb41face52cd1c7fd132b43a9ec426c,Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection,"Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection Dimity Miller, Feras Dayoub, Michael Milford, and Niko S¨underhauf" ccd2152c77ae65e4d3d0988990f6e243133a5efc,Learning Human Activities and Poses with Interconnected Data Sources,"Copyright Chao-Yeh Chen" 95e83661648ba6bf2f0fbbf436bc8304c3cf016f,The impact of empathy and reappraisal on emotional intensity recognition.,"Cognition and Emotion ISSN: 0269-9931 (Print) 1464-0600 (Online) Journal homepage: http://www.tandfonline.com/loi/pcem20 The impact of empathy and reappraisal on emotional intensity recognition Navot Naor, Simone G. Shamay-Tsoory, Gal Sheppes & Hadas Okon-Singer To cite this article: Navot Naor, Simone G. Shamay-Tsoory, Gal Sheppes & Hadas Okon-Singer (2017): The impact of empathy and reappraisal on emotional intensity recognition, Cognition and Emotion, DOI: 10.1080/02699931.2017.1372366 To link to this article: http://dx.doi.org/10.1080/02699931.2017.1372366 Published online: 11 Sep 2017. Submit your article to this journal View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pcem20 Download by: [Tel Aviv University] Date: 11 September 2017, At: 04:46" 95a9e256c8f8bbce0d86199cacea92b15004dd45,Using semantic similarity for multi-label zero-shot classification of text documents,"Using Semantic Similarity for Multi-Label Zero-Shot Classification of Text Documents Jinseok Nam2,3 Sappadla Prateek Veeranna1 Johannes F¨urnkranz2 ∗ Eneldo Loza Menc´ıa2 - Birla Institute of Technology and Science - Pilani - India - Knowledge Engineering Group - TU Darmstadt - Germany - Knowledge Discovery in Scientific Literature - DIPF - Germany" 9547a7bce2b85ef159b2d7c1b73dea82827a449f,Facial expression recognition using Gabor motion energy filters,"Facial Expression Recognition Using Gabor Motion Energy Filters Tingfan Wu Dept. Computer Science Engineering UC San Diego Marian S. Bartlett Javier R. Movellan Institute for Neural Computation UC San Diego" 95ed2269c4a13771cc8dfe0ff2d4d6a7f4d73033,Deep Learning for Domain Adaption: Engagement Recognition,"Engagement Recognition using Deep Learning and Facial Expression Omid Mohamad Nezami , Len Hamey , Deborah Richards , and Mark Dras Macquarie University, Sydney, NSW, Australia" 9501db000474dbd182579d311dfb1b1ab8fa871f,Supplementary of Multi-scale Deep Learning Architectures for Person Re-identification,"Supplementary of Multi-scale Deep Learning Architectures for Person Re-identification Xuelin Qian1 Yanwei Fu2,5,* Yu-Gang Jiang1,3 Tao Xiang4 Xiangyang Xue1,2 Shanghai Key Lab of Intelligent Info. Processing, School of Computer Science, Fudan University; School of Data Science, Fudan University; 3Tencent AI Lab; Queen Mary University of London; 5University of Technology Sydney; . Multi-scale stream layers Multi-scale-A layer (Fig. 1), analyses the data stream with the size 1 × 1, 3 × 3 and 5 × 5 of receptive field. Further- more, in order to increase both depth and width of this layer, we split the filter size of 5 × 5 into two 3 × 3 streams cas- aded (i.e. stream-4 and stream-3 in Tab 1 and Fig. 1). The weights of each stream are also tied with the corresponding stream in another branch. Such a design art is, in general, inspired by, and yet different from the inception architec- tures [11, 12, 10]. The key difference lies in the weights which are not tied between any two streams from the same ranch, but are tied between the two corresponding streams of different branches. Reduction layer (Fig. 2) further passes the data stream" 95a835cdb5dc46e4de071865f9dccdaf9ec944ad,Euclidean and geodesic distance between a facial feature points in two-dimensional face recognition system,"The International Arab Journal of Information Technology, Vol. 14, No. 4A, Special Issue 2017 565 Euclidean and Geodesic Distance between a Facial Feature Points in Two-Dimensional Face Recognition System Rachid Ahdid1,2, Said Safi1, and Bouzid Manaut2 Department of Mathematics and Informatics, Sultan Moulay Slimane University, Morocco Poladisciplinary Faculty, Sultan Moulay Slimane University, Morocco" 9595fa763c4f1d92c604a131cfc624b9edbd8b02,Integral Histogram Image Computing For Parallel Hardware Architecture,"Journal of Recent Research in Engineering and Technology, 4(6), June 2017, PP.31-39 ISSN (Online): 2349 –2252, ISSN (Print):2349 –2260 © Bonfay Publications, 2017 Integral Histogram Image Computing For Parallel Hardware Architecture J.Nandhini1, M. Vasanthakumar 2 (M.E, Department of Electronics and Communications Engineering, AVS Engineering College, Salem) (Assistant Professor, Department of Electronics and Communications Engineering, AVS Engineering Mail id: College, Salem) Mail id: Received 25 May 2017; Accepted 04 June 2017" 95deb62b82ede5c6732c5c498d3f9452866eaba7,Unsupervised Video Understanding by Reconciliation of Posture Similarities,"Unsupervised Video Understanding by Reconciliation of Posture Similarities Timo Milbich, Miguel Bautista, Ekaterina Sutter, Bj¨orn Ommer Heidelberg Collaboratory for Image Processing IWR, Heidelberg University, Germany {timo.milbich, miguel.bautista, ekaterina.sutter," 95de749dd1c3451d0842ecf33101244a1fa9d4af,Temporal Dynamics Underlying the Modulation of Social Status on Social Attention,"Temporal Dynamics Underlying the Modulation of Social Status on Social Attention Mario Dalmaso*, Giovanni Galfano, Carol Coricelli, Luigi Castelli Dipartimento di Psicologia dello Sviluppo e della Socializzazione, Universita` di Padova, Padova, Italy" 950cfcbaafad1e2aaae43728fe499d8a4c90f6ec,Object Instance Detection and Dynamics Modeling in a Long-Term Mobile Robot Context,"Object Instance Detection and Dynamics Modeling in Long-Term Mobile Robot Context NILS BORE Doctoral Thesis Stockholm, Sweden 2017" 95aef5184b89daebd0c820c8102f331ea7cae1ad,Recognising facial expressions in video sequences,"Recognising facial expressions in video sequences Jos´e M. Buenaposada1, Enrique Mu˜noz2⋆, Luis Baumela2 ESCET, Universidad Rey Juan Carlos C/Tulip´an s/n, 28933 M´ostoles, Spain Facultad Inform´atica, Universidad Polit´ecnica de Madrid Campus Montegancedo s/n, 28660 Boadilla del Monte, Spain http://www.dia.fi.upm.es/~pcr Received: 7 Jan 2007 / Accepted: 10 July 2007/ Online: 18 Oct 2007" 9590b09c34fffda08c8f54faffa379e478f84b04,Efficient Dual Approach to Distance Metric Learning,"An Efficient Dual Approach to Distance Metric Learning Chunhua Shen, Junae Kim, Fayao Liu, Lei Wang, Anton van den Hengel Experimental results Distance metric learning . . . . . UCI benchmark test . . IV-A1 Unconstrained face recognition IV-A2 IV-A3 Metric learning for action recognition . . . . . . . Maximum variance unfolding . . . IV-B1 Quantitative Assessment . Conclusion References" 95be490aef44da67ca1cef76b16df14b6e40c421,Learning Cross-View Binary Identities for Fast Person Re-Identification,"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16) Learning Cross-View Binary Identities for Fast Person Re-Identification Feng Zheng1, Ling Shao2 Department of Electronic and Electrical Engineering, The University of Sheffield. Department of Computer Science and Digital Technologies, Northumbria University." 9561c7ef4f89019eb7fb779a7b18ef810964b491,Real-Time Object Segmentation Using a Bag of Features Approach,"Real-Time Object Segmentation Using a Bag of Features Approach David ALDAVERT a,1, Arnau RAMISA c,b, Ramon LOPEZ DE MANTARAS b and Ricardo TOLEDO a Computer Vision Center, Dept. Ciencies de la Computació, Universitat Autonòma de Barcelona, Catalunya, Spain Institut d’Investigació d’Inteligencia Artificial (IIIA-CSIC), Campus UAB, Catalunya, Spain INRIA-Grenoble, LEAR Team, France" 958b761f1ebacbc38d4edc4b1bd5b42204fd91a1,Pattern Recognition for Ecological Science and Environmental Monitoring : An Initial Report,"Pattern Recognition for Ecological Science and Environmental Monitoring: An Initial Report Eric N. Mortensen, Enrique L. Delgado, Hongli Deng, David Lytle, Andrew Moldenke, Robert Paasch, Linda Shapiro, Pengcheng Wu, Wei Zhang, Thomas G. Dietterich" 95296302a7fc82edf782cece082d7319cfa584b7,Detection-free Bayesian Multi-object Tracking via Spatio-Temporal Video Bundles Grouping,"Detection-free Bayesian Multi-object Tracking via Spatio-Temporal Video Bundles Grouping Technical Report, November 2013 Yongyi Lu, Liang Lin, Yuanlu Xu, Zefeng Lai" 95029b1041a169e5b4e1ad79f60bfedb7a6844d0,Learning Superpixels with Segmentation-Aware Affinity Loss,"Learning Superpixels with Segmentation-Aware Affinity Loss Wei-Chih Tu1 Ming-Yu Liu2 Varun Jampani2 Deqing Sun2 Shao-Yi Chien1 Ming-Hsuan Yang2 Jan Kautz2 National Taiwan University 2NVIDIA 3UC Merced" 9513503867b29b10223f17c86e47034371b6eb4f,Comparison of Optimisation Algorithms for Deformable Template Matching,"Comparison of optimisation algorithms for deformable template matching Vasileios Zografos Link¨oping University, Computer Vision Laboratory ISY, SE-581 83 Link¨oping, SWEDEN" 95f990600abb9c8879e4f5f7cd03f3d696fcdec4,An Online Algorithm for Constrained Face Clustering in Videos,"Manuscript version: Author’s Accepted Manuscript The version presented in WRAP is the author’s accepted manuscript and may differ from the published version or Version of Record. Persistent WRAP URL: http://wrap.warwick.ac.uk/109574 How to cite: Please refer to published version for the most recent bibliographic citation information. If a published version is known of, the repository item page linked to above, will contain details on accessing it. Copyright and reuse: The Warwick Research Archive Portal (WRAP) makes this work by researchers of the University of Warwick available open access under the following conditions. Copyright © and all moral rights to the version of the paper presented here belong to the individual author(s) and/or other copyright owners. To the extent reasonable and practicable the material made available in WRAP has been checked for eligibility before eing made available. Copies of full items can be used for personal research or study, educational, or not-for-profit purposes without prior permission or charge. Provided that the authors, title and full ibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way." 951af0494e8812fdb7d578b68c342ab876acb27e,DOCTEUR DE L’ECOLE NORMALE SUPERIEURE DE CACHAN,"THÈSEDEDOCTORATDEL’ÉCOLENORMALESUPÉRIEUREDECACHANprésentéeparJULIENMAIRALpourobtenirlegradedeDOCTEURDEL’ÉCOLENORMALESUPÉRIEUREDECACHANDomaine:MATHÉMATIQUESAPPLIQUÉESSujetdelathèse:Représentationsparcimonieusesenapprentissagestatistique,traitementd’imageetvisionparordinateur—Sparsecodingformachinelearning,imageprocessingandcomputervisionThèseprésentéeetsoutenueàCachanle30novembre2010devantlejurycomposéde:FrancisBACHDirecteurderecherche,INRIAParis-RocquencourtDirecteurdethèseStéphaneMALLATProfesseur,EcolePolytechnique,New-YorkUniversityRapporteurEricMOULINESProfesseur,Télécom-ParisTechExaminateurBrunoOLSHAUSENProfesseur,UniversityofCalifornia,BerkeleyRapporteurJeanPONCEProfesseur,EcoleNormaleSupérieure,ParisDirecteurdethèseGuillermoSAPIROProfesseur,UniversityofMinnesotaExaminateurJean-PhilippeVERTDirecteurderecherche,EcolesdesMines-ParisTechExaminateurThèsepréparéeauseindel’équipeWillowdulaboratored’informatiquedel’ÉcoleNormaleSupérieure,Paris.(INRIA/ENS/CNRSUMR8548).23avenued’Italie,75214Paris." 95225bab187483e37823daab5c503f6b327fb008,Improved MinMax Cut Graph Clustering with Nonnegative Relaxation,"Improved MinMax Cut Graph Clustering with Nonnegative Relaxation Feiping Nie, Chris Ding, Dijun Luo, and Heng Huang Department of Computer Science and Engineering, University of Texas, Arlington, America" 95977c279c3c7c0a4368fb4f097e5002bbdce259,Application à la création d ’ un atlas probabiliste de perfusion cérébrale en imagerie médicale,"No d’ordre: 4616 TH(cid:18)ESE pr(cid:19)esent(cid:19)ee pour obtenir le grade de Docteur de l’Universit(cid:19)e Louis Pasteur - Strasbourg I (cid:19)Ecole doctorale : Sciences pour l’ing(cid:19)enieur Discipline Sp(cid:19)ecialit(cid:19)e (cid:19)Electronique, (cid:19)electrotechnique, automatique : Traitement d’images et vision par ordinateur Mod(cid:18)eles statistiques d’apparence non gaussiens. Application (cid:18)a la cr(cid:19)eation d’un atlas probabiliste de perfusion c(cid:19)er(cid:19)ebrale en imagerie m(cid:19)edicale English title: \Non-Gaussian Statistical Appearance Models. Application to the Creation of a Probabilistic Atlas of Brain Perfusion in Medical Imaging."" Soutenue publiquement le 21 septembre 2004 Torbj(cid:28)rn VIK Membres du jury: BLOCH Isabelle" 95aa80cf672771730393e1d7d263ab6f6d6e535d,Learning articulated body models for people re-identification,"Learning Articulated Body Models for People Re-identification Davide Baltieri, Roberto Vezzani, Rita Cucchiara University of Modena and Reggio Emilia Via Vignolese 905, 41125 Modena - Italy {davide.baltieri, roberto.vezzani," 95593fb20df8ce1273cebe0690cf2cdab054b9b5,Robust Multi-Image HDR Reconstruction for the Modulo Camera, 95ea564bd983129ddb5535a6741e72bb1162c779,Multi-Task Learning by Deep Collaboration and Application in Facial Landmark Detection,"Multi-Task Learning by Deep Collaboration and Application in Facial Landmark Detection Ludovic Trottier Philippe Giguère Brahim Chaib-draa Laval University, Québec, Canada" 955dc25def91eff6bfa5698249bb189ccfa83367,Geometric Model for Human Body Orientation Classification,"CommIT (Communication and Information Technology) Journal, Vol. 9 No. 1, pp. 29–33 GEOMETRIC MODEL FOR HUMAN BODY ORIENTATION CLASSIFICATION Igi Ardiyanto Department of Electrical Engineering and Information Technology, Faculty of Engineering, Gadjah Mada University Yogyakarta 55281, Indonesia Email:" 9588a42bff63fb36015e10fac9f3121154c3ab1d,Explaining Potential Risks in Traffic Scenes by Combining Logical Inference and Physical Simulation,"International Journal of Machine Learning and Computing, Vol. 6, No. 5, October 2016 Explaining Potential Risks in Traffic Scenes by Combining Logical Inference and Physical Simulation Ryo Takahashi, Naoya Inoue, Yasutaka Kuriya, Sosuke Kobayashi, and Kentaro Inui from observation and" c81b303005459285a5864ea4de71f77025cd5be5,Norm-Induced Entropies for Decision Forests,"Norm-induced entropies for decision forests Christoph Lassner Rainer Lienhart Multimedia Computing and Computer Vision Lab, University of Augsburg" c8ebe4c7d884c468d572a1ccf8583ac912215088,Emotion Dysregulation and Anxiety in Adults with ASD: Does Social Motivation Play a Role?,"J Autism Dev Disord DOI 10.1007/s10803-015-2567-6 S . I . : A S D I N A D U L T H O O D : C O M O R B I D I T Y A N D I N T E R V E N T I O N Emotion Dysregulation and Anxiety in Adults with ASD: Does Social Motivation Play a Role? Deanna Swain1 • Angela Scarpa1 • Susan White1 • Elizabeth Laugeson2 Ó Springer Science+Business Media New York 2015" c8e32484bbbc63908080284790edafc4b66008d2,Suivi par ré-identification dans un réseau de caméras à champs disjoints,"Suivi par r´e-identification dans un r´eseau de cam´eras `a hamps disjoints Boris Meden, Patrick Sayd, Fr´ed´eric Lerasle To cite this version: Boris Meden, Patrick Sayd, Fr´ed´eric Lerasle. Suivi par r´e-identification dans un r´eseau de am´eras `a champs disjoints. RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Jan 2012, Lyon, France. pp.978-2-9539515-2-3, 2012. HAL Id: hal-00656507 https://hal.archives-ouvertes.fr/hal-00656507 Submitted on 17 Jan 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" c8f216dbd43dda14783677f44bb336c92211cd46,Synthesis from 3 D Mesh Sequences Driven by Combined Speech Features,"VISUAL SPEECH SYNTHESIS FROM 3D MESH SEQUENCES DRIVEN BY COMBINED SPEECH FEATURES Felix Kuhnke and J¨orn Ostermann Institut f¨ur Informationsverarbeitung, Leibniz Universit¨at Hannover, Germany" c88a1d52d92a47704a797fce2202970bb1f2008c,RECOGNIZING FACE SKETCHES BY HUMAN VOLUNTEERS,"RECOGNIZING FACE SKETCHES BY HUMAN VOLUNTEERS Priyanka Reddy Gangam Submitted in Partial Fulfillment of the Requirements for the Degree of Master of Computing and Information Systems YOUNGSTOWN STATE UNIVERSITY August, 2010" c8ee4812c32b0ad4e26d53b99e1514514bbcaf14,A NEaT Design for Reliable and Scalable Network Stacks,"A NEaT Design for Reliable and Scalable Network Stacks Tomas Hruby Cristiano Giuffrida Lionel Sambuc Herbert Bos Andrew S. Tanenbaum Vrije Universiteit Amsterdam" c88b2a351e207698dae6a2b314b5f4fd25f2e9c1,A study in facial regions saliency: a fuzzy measure approach,"Soft Comput DOI 10.1007/s00500-013-1064-0 M E T H O D O L O G I E S A N D A P P L I C A T I O N A study in facial regions saliency: a fuzzy measure approach Paweł Karczmarek • Witold Pedrycz • Marek Reformat • Elaheh Akhoundi Ó The Author(s) 2013. This article is published with open access at Springerlink.com" c896502edcdec38466e7d66f38fb53a57c8e05db,Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks,"Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks Xianxu Hou and Guoping Qiu low-level" c81326a1ecb7e71ae38a665779b8d959d3938d1a,A Novel Neural Network Model Specified for Representing Logical Relations,"A Novel Neural Network Model Specified for Representing Logical Relations Gang Wang With computers to handle more and more complicated things in variable environments, it becomes an urgent requirement that the artificial intelligence has the ability of automatic judging and deciding according to numerous specific conditions so as to deal with the complicated and variable cases. ANNs inspired by brain is a good candidate. However, most of current numeric ANNs are not good at representing logical relations because these models still try to represent logical relations in the form of ratio based on functional approximation. On the other hand, researchers have been trying to design novel neural network models to make neural network model represent logical relations. In this work, a novel neural network model specified for representing logical relations is proposed and applied. New neurons and multiple kinds of links are defined. Inhibitory links are introduced besides exciting links. Different from current numeric ANNs, one end of an inhibitory link connects an exciting link rather than a neuron. Inhibitory model can simulate the operations of Boolean logic gates, and construct complex logical relations with the advantages of simpler neural network structures than recent works in this area. This work provides some ideas to make neural networks represent logical relations more directly and efficiently, and the model could be used as the complement to current numeric ANN to deal with logical issues and expand the application areas of ANN. Index Terms—Brain-inspired computing, logical representation, neural network structure, inhibitory link. I. INTRODUCTION With computers to handle more and more complicated things in variable environments like driverless car and ad- vanced medical diagnosis expert system, higher artificial intel-" c8855bebdaa985dfc4c1a07e5f74a0e29787e47e,Multi-label Object Attribute Classification using a Convolutional Neural Network,"Multi-label Object Attribute Classification using Convolutional Neural Network Soubarna Banik, Mikko Lauri, Simone Frintrop Department of Informatics, Universit¨at Hamburg" c8bcd8e0b2ab6cc00a565efbcf904235c33ac2dc,Unsupervised Person Image Synthesis in Arbitrary Poses,"Unsupervised Person Image Synthesis in Arbitrary Poses Albert Pumarola Antonio Agudo Alberto Sanfeliu Francesc Moreno-Noguer Institut de Rob`otica i Inform`atica Industrial (CSIC-UPC) 08028, Barcelona, Spain Figure 1: Given an original image of a person (left) and a desired body pose defined by a 2D skeleton (bottom-row), our model generates new photo-realistic images of the person under that pose (top-row). The main contribution of our work is to train this generative model with unlabeled data." c8e2582948d60d6363aa20208000f07c002c21cb,A STATE OF THE ART COMPARISON OF DATABASES FOR FACIAL OCCLUSION,"Jurnal Teknologi A STATE OF THE ART COMPARISON OF DATABASES FOR FACIAL OCCLUSION Abdulganiyu Abdu Yusufa,b*, Fatma Susilawati Mohamada, Zahraddeen Sufyanua Faculty of Informatics and Computing, 21300 Gong Badak Campus, Universiti Sultan Zainal Abidin (UniSZA), Terengganu, Malaysia National Biotechnology Development Agency (NABDA), Abuja, Nigeria Full Paper Article history Received 5 April 2015 Received in revised form 9 September 2015 Accepted 2 November 2015 *Corresponding author" c8b592fcf2ed2f75799b94c428d2ccdf1e82c5f7,"RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation","RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation Xirong Li(cid:63)1, Qin Jin(cid:63)1, Shuai Liao1, Junwei Liang1, Xixi He1, Yujia Huo1, Weiyu Lan1, Bin Xiao2, Yanxiong Lu2, Jieping Xu1 Multimedia Computing Lab, School of Information, Renmin University of China Pattern Recognition Center, WeChat Technical Architecture Department, Tencent" c840d85f6dce0fb69fb6113923f17e1e314c6134,Disparity Sliding Window: Object Proposals From Disparity Images,"Disparity Sliding Window: Object Proposals From Disparity Images Julian M¨uller1, Andreas Fregin2 and Klaus Dietmayer1" c8db8764f9d8f5d44e739bbcb663fbfc0a40fb3d,Modeling for part-based visual object detection based on local features,"Modeling for part-based visual object detection based on local features Von der Fakult¨at f¨ur Elektrotechnik und Informationstechnik der Rheinisch-Westf¨alischen Technischen Hochschule Aachen zur Erlangung des akademischen Grades eines Doktors der Ingenieurwissenschaften genehmigte Dissertation vorgelegt von Diplom-Ingenieur Mark Asbach us Neuss Berichter: Univ.-Prof. Dr.-Ing. Jens-Rainer Ohm Univ.-Prof. Dr.-Ing. Til Aach Tag der m¨undlichen Pr¨ufung: 28. September 2011 Diese Dissertation ist auf den Internetseiten der Hochschulbibliothek online verf¨ugbar." c85adcc3cc2f3ab27def7e1c615b52ac182dde80,Improving face gender classification by adding deliberately misaligned faces to the training data,"Improving Face Gender Classification By Adding Deliberately Misaligned Faces To The Training Data M. Mayo, E. Zhang Dept. of Computer Science, University of Waikato Hamilton, New Zealand. Email:" c83dba889132f0d2b909474e5e187f254bd09e29,Fourier Power Spectrum Characteristics of Face Photographs: Attractiveness Perception Depends on Low-Level Image Properties,"RESEARCH ARTICLE Fourier Power Spectrum Characteristics of Face Photographs: Attractiveness Perception Depends on Low-Level Image Properties Claudia Menzel1,2☯, Gregor U. Hayn-Leichsenring1,2☯*, Oliver Langner1,3, Holger Wiese1,4, Christoph Redies1,2 Person Perception Research Unit, Friedrich-Schiller-University Jena, Jena, Germany, 2 Experimental Aesthetics Group, Institute of Anatomy I, Jena University Hospital, Friedrich-Schiller-University Jena, Jena, Germany, 3 Department of Neurology, University of Lübeck, Lübeck, Germany, 4 Department of Psychology, Durham University, Durham, United Kingdom ☯ These authors contributed equally to this work." c866a2afc871910e3282fd9498dce4ab20f6a332,Surveillance Face Recognition Challenge,"Noname manuscript No. (will be inserted by the editor) Surveillance Face Recognition Challenge Zhiyi Cheng · Xiatian Zhu · Shaogang Gong Received: date / Accepted: date" c8a4b4fe5ff2ace9ab9171a9a24064b5a91207a3,Locating facial landmarks with binary map cross-correlations,"LOCATING FACIAL LANDMARKS WITH BINARY MAP CROSS-CORRELATIONS J´er´emie Nicolle K´evin Bailly Vincent Rapp Mohamed Chetouani Univ. Pierre & Marie Curie, ISIR - CNRS UMR 7222, F-75005, Paris - France {nicolle, bailly, rapp," c85aa12331bdeaba06d4c3e44b969e6060c3310c,Ensemble of Part Detectors for Simultaneous Classification and Localization,"Ensemble of Part Detectors for Simultaneous Classification and Localization Xiaopeng Zhang, Hongkai Xiong, Senior Member, IEEE, Weiyao Lin, Qi Tian, Fellow, IEEE" c82840923eeded245a8dab2dd102d8b0cf96758a,KDGAN: Knowledge Distillation with Generative Adversarial Networks,"KDGAN: Knowledge Distillation with Generative Adversarial Networks Xiaojie Wang University of Melbourne Yu Sun Twitter Inc. Rui Zhang∗ University of Melbourne Jianzhong Qi University of Melbourne" c8ddeeea803e50cab2d82f6d3c7f9e08b5f51f4b,Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps,"Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps N´ıcolas Rosa1, Vitor Guizilini2, and Valdir Grassi Jr1" c8dcb7b3c5ed43e61b90b50fedc76568d8e30675,GUARDING AGAINST ADVERSARIAL DOMAIN SHIFTS,"Under review as a conference paper at ICLR 2018 GUARDING AGAINST ADVERSARIAL DOMAIN SHIFTS WITH COUNTERFACTUAL REGULARIZATION Anonymous authors Paper under double-blind review" c8adbe00b5661ab9b3726d01c6842c0d72c8d997,Deep Architectures for Face Attributes,"Deep Architectures for Face Attributes Tobi Baumgartner, Jack Culpepper Computer Vision and Machine Learning Group, Flickr, Yahoo, {tobi," c8c035ff19fdea2b8053d781b999356110a43ff5,A Hierarchical Approach for Multi-task Logistic Regression,"A Hierarchical Approach for Multi-Task Logistic Regression (cid:18)Agata Lapedriza1, David Masip2 and Jordi Vitri(cid:18)a1 Computer Vision Center-Dept. Inform(cid:18)atica Universitat Aut(cid:18)onoma de Barcelona, 08193 Bellaterra, Spain fagata, Universitat de Barcelona (UB), 08007 Barcelona , Spain" c813413fc84be33d7c4ccdd4a1f025ccc73a77bd,Discriminative Bayesian Active Shape Models,"Discriminative Bayesian Active Shape Models Pedro Martins, Rui Caseiro, Jo˜ao F. Henriques, Jorge Batista Institute of Systems and Robotics - University of Coimbra, Portugal" c8f035510b72b84c21430a887ed03c8836eeddc2,Optical-inertial Synchronization of MoCap Suit with Single Camera Setup for Reliable Position Tracking, c84ca95638893700d8f806e844984a5b2c50b5e3,Automatic Facial Expression Recognition Using 3 D Faces,"Paper 071, ENG 101 Automatic Facial Expression Recognition Using 3D Faces Chao Li, Antonio Soares Florida A&M University hao.li," c867caf3f29abb2f3fd5c4c7e98e5f551a70be25,DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map,"DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map Peng Wang, Ruigang Yang, Binbin Cao, Wei Xu, Yuanqing Lin Baidu Research National Engineering Laboratory for Deep Learning Technology and Applications {wangpeng54, yangruigang, caobinbin, wei.xu," c8fc65c83473c633e2bf1c13031ccd10617cc8a2,Every Object Tells a Story,"Every Object Tells a Story James Pustejovsky Computer Science Department Brandeis University Waltham, MA 02453 Nikhil Krishnaswamy Computer Science Department Brandeis University Waltham, MA 02453" 694dda2a9f6d86c4bf3f57d85dfd376e2067ec62,CA : HOW MUCH FACE INFORMATION IS NEEDED ?,"HOW MUCH FACE INFORMATION IS NEEDED? P2CA: Davide Onofrio*, Antonio Rama+, Francesc Tarres+, Stefano Tubaro* *Dipartimento di Elettronica e Informazione - Politecnico di Milano +Department Teoria del Senyal i Comunicacions de la Universitat Politècnica de Catalunya" 6953911c6756ca70de1555df14a06f13305e1926,Author Profiling based on Text and Images: Notebook for PAN at CLEF 2018,"Author Profiling based on Text and Images Notebook for PAN at CLEF 2018 Luka Stout, Robert Musters, and Chris Pool Anchormen, The Netherlands" 6900bb437679dd0b0c5cea0acdaa9429d0127d38,Self-Erasing Network for Integral Object Attention,"Self-Erasing Network for Integral Object Attention Qibin Hou Peng-Tao Jiang Colledge of Computer Science, Nankai University Yunchao Wei Urbana-Champaign, IL, USA Colledge of Computer Science, Nankai University Ming-Ming Cheng ∗" 69a605b2ef38c59e0c8da284d6f27d33e3573620,AUTOMATED MULTI-MODAL SEARCH AND RESCUE USING BOOSTED HISTOGRAM OF ORIENTED GRADIENTS,"AUTOMATED MULTI-MODAL SEARCH AND RESCUE USING BOOSTED HISTOGRAM OF ORIENTED GRADIENTS A Thesis presented to the Faculty of California Polytechnic State University, San Luis Obispo In Partial Fulfillment of the Requirements for the Degree Master of Science in Electrical Engineering Matthew Lienemann December 2015" 698812f7d37e148c0a99e768f0a7d24e7b9605ab,Image Classification and Retrieval from User-Supplied Tags,"Image Classification and Retrieval from User-Supplied Tags Hamid Izadinia Univ. of Washington Ali Farhadi Univ. of Washington Aaron Hertzmann Adobe Research Matthew D. Hoffman Adobe Research" 693905c29feb7f9be3517308c8a9c2dc68aa8682,Self-supervised CNN for Unconstrained 3D Facial Performance Capture from an RGB-D Camera,"Self-supervised CNN for Unconstrained 3D Facial Performance Capture from an RGB-D Camera Yudong Guo, Juyong Zhang†, Lin Cai, Jianfei Cai and Jianmin Zheng" 699b6cbd72ee0274699b939863813499c377ea00,Enlightening Deep Neural Networks with Knowledge of Confounding Factors,"Enlightening Deep Neural Networks with Knowledge of Confounding Factors Yu Zhong Gil Ettinger {yu.zhong, Systems & Technology Research" 6957baa0db5576997aef9de43b93fe8fd4d07632,Identifica\c{c}\~ao autom\'atica de picha\c{c}\~ao a partir de imagens urbanas,"Identificac¸˜ao autom´atica de pichac¸˜ao a partir de imagens urbanas Eric K. Tokuda and Roberto M. Cesar-Jr. Institute of Mathematics and Statistics University of S˜ao Paulo (USP) Brazil Claudio Silva Tandon School of Engineering New York University (NYU)" 69dc87575b56ba7f60fa24bdd4fceabeeaf39a80,Decoding of nonverbal language in alcoholism: A perception or a labeling problem?,"tapraid5/ze6-adb/ze6-adb/ze600216/ze62965d15z xppws S⫽1 /8/16 6:36 Art: 2015-0668 APA NLM Psychology of Addictive Behaviors 016, Vol. 30, No. 2, 175–183 0893-164X/16/$12.00 © 2016 American Psychological Association http://dx.doi.org/10.1037/adb0000147 Decoding of Nonverbal Language in Alcoholism: A Perception or a Labeling Problem? Université Libre de Bruxelles and Centre Hospitalier Charles Kornreich Universitaire Brugmann Géraldine Petit and Heidi Rolin Université Libre de Bruxelles Elsa Ermer University of Maryland Baltimore Salvatore Campanella and Paul Verbanck" 695f56d6b1b294d1691c93d86a23e77016a42720,A Multimodal User Authentication System Using Faces and Gestures,"Hindawi Publishing Corporation BioMed Research International Volume 2015, Article ID 343475, 8 pages http://dx.doi.org/10.1155/2015/343475 Research Article A Multimodal User Authentication System Using Faces and Gestures Hyunsoek Choi1 and Hyeyoung Park2 School of Electrical Engineering and Computer Science, Kyungpook National University, Deagu 702-701, Republic of Korea School of Computer Science and Engineering, Kyungpook National University, Deagu 702-701, Republic of Korea Correspondence should be addressed to Hyeyoung Park; Received 26 September 2014; Accepted 19 November 2014 Academic Editor: Sabah Mohammed Copyright © 2015 H. Choi and H. Park. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. As a novel approach to perform user authentication, we propose a multimodal biometric system that uses faces and gestures obtained from a single vision sensor. Unlike typical multimodal biometric systems using physical information, the proposed system utilizes gesture video signals combined with facial images. Whereas physical information such as face, fingerprints, and iris is fixed nd not changeable, behavioral information such as gestures and signatures can be freely changed by the user, similar to a password. Therefore, it can be a countermeasure when the physical information is exposed. We aim to investigate the potential possibility of" 69c03f69ddf77586f83bf13d473abf53a70e6793,"EigenFaces Image normalization : rotation , scale and intensity Eye coordinates + input frame Voting method Person identity DCT HMM Face extraction Recognition Modules","Lemieux & Parizeau, Vision Interface 2003. Flexible multi-classifier architecture for face recognition systems Alexandre Lemieux and Marc Parizeau Laboratoire de vision et syst`emes num´eriques (LVSN), D´epartement de g´enie ´electrique et de g´enie informatique, Universit´e Laval, Ste-Foy (Qc), Canada, G1K 7P4." 694c7c7bf7ffad6caedb97aca425acfc08bd90ee,Aerial Detection in Maritime Scenarios Using Convolutional Neural Networks,"Aerial Detection in Maritime Scenarios Using Convolutional Neural Networks Gon¸calo Cruz1(B) and Alexandre Bernardino2 Portuguese Air Force, Sintra, Portugal Computer and Robot Vision Laboratory, Instituto de Sistemas e Rob´otica, Instituto Superior T´ecnico, Lisboa, Portugal" 69f49bae5b1c15adc644b47e6c3b6c3f7aa84171,Variational Bayesian Inference for Audio-Visual Tracking of Multiple Speakers,"Variational Bayesian Inference for Audio-Visual Tracking of Multiple Speakers Yutong Ban, Xavier Alameda-Pineda, Laurent Girin and Radu Horaud" 69ee78388e0f40941496ab92efe3e0fa065ad22e,Person Re-Identification with RGB-D Camera in Top-View Configuration through Multiple Nearest Neighbor Classifiers and Neighborhood Component Features Selection,"Article Person Re-Identification with RGB-D Camera in Top-View Configuration through Multiple Nearest Neighbor Classifiers and Neighborhood Component Features Selection Marina Paolanti * Emanuele Frontoni , Luca Romeo, Daniele Liciotti , Rocco Pietrini, Annalisa Cenci, nd Primo Zingaretti Department of Information Engineering, Universitá Politecnica delle Marche, I-60131 Ancona, Italy; (L.R.); (D.L.); (R.P.); (A.C.); (E.F.); (P.Z.) * Correspondence: Received: 30 August 2018 ; Accepted: 11 October 2018 ; Published: 15 October 2018" 699a7c88a6d226f59c7a5619b3cfad714415c31a,"Incorporating Luminance, Depth and Color Information by Fusion-based Networks for Semantic Segmentation","Incorporating Luminance, Depth and Color Information by Fusion-based Networks for Semantic Segmentation Shao-Yuan Lo Shang-Wei Hung National Chiao Ting University, UC San Diego National Chiao Ting University Figure 1: Flowchart of the proposed semantic segmentation system. Y: luminance information. omplexity. Lately, DenseNet [11] designs the invention of dding dense connections between each layer, which enhances the information flow in networks, and thus it previously outperforms many network rchitectures including ResNet [12]. proposed With the help of depth sensors such as Kinect, depth maps can be obtained along with RGB images. Since the depth channel provides complementary information to the RGB channels, containing the depth information is believed" 6997039127d9b262d4a9aa9467c4f4fa3d596085,Classification of Vehicle Types in Car Parks using Computer Vision Techniques,"Classification of Vehicle Types in Car Parks using Computer Vision Techniques Chadly Marouane Research & Development VIRALITY GmbH Rauchstraße 7 81679 Munich, Germany Lorenz Schauer Ludwig-Maximilians- Universität München Philipp Bauer Ludwig-Maximilians- Universität München Oettingenstraße 67 80538 München, Germany Oettingenstraße 67 80538 München, Germany" 69f638309fe692f7d57a72d2df8fe2bf1d81dff4,A Study of Artificial Personality from the Perspective of the Observer,"A Study of Artificial Personality from the Perspective of the Observer Sheryl Brahnam Computer Information Systems Department Southwest Missouri State University Springfield, MO 65804" 690d669115ad6fabd53e0562de95e35f1078dfbb,"Progressive versus Random Projections for Compressive Capture of Images, Lightfields and Higher Dimensional Visual Signals","Progressive versus Random Projections for Compressive Capture of Images, Lightfields and Higher Dimensional Visual Signals Rohit Pandharkar MIT Media Lab 75 Amherst St, Cambridge, MA Ashok Veeraraghavan 01 Broadway, Cambridge MA Ramesh Raskar MIT Media Lab 75 Amherst St, Cambridge, MA" 695f6dc7165aa3fca15d1b1deb4c496fc093ac19,Learning Discriminative Visual N-grams from Mid-level Image Features.,"GUPTA, PANDEY, CHIA: VISUAL N-GRAMS Learning Discriminative Visual N-grams from Mid-level Image Features Raj Kumar Gupta Megha Pandey Alex YS Chia Institute of High Performance Computing (A*STAR) Singapore Institute of Infocomm Research (A*STAR) Singapore Rakuten Institute of Technology Singapore" 69f27ca2f1280587004c8fae6b3b0021305e52eb,Title of dissertation : Scene and Video Understanding, 695b040a9550a46b5ffe31e4a6abbadfac02c1ad,Face recognition with illumination distinction description,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-1-6 ©2012 IAPR" 6937fe93e6238ee21904c172809bea0086da4570,Contour Grouping Based on Contour-Skeleton Duality,"Int J Comput Vis (2009) 83: 12–29 DOI 10.1007/s11263-009-0208-2 Contour Grouping Based on Contour-Skeleton Duality Nagesh Adluru · Longin Jan Latecki Received: 30 May 2008 / Accepted: 6 January 2009 / Published online: 27 January 2009 © Springer Science+Business Media, LLC 2009" 69ff40fd5ce7c3e6db95a2b63d763edd8db3a102,HUMAN AGE ESTIMATION VIA GEOMETRIC AND TEXTURAL FEATURES,"HUMAN AGE ESTIMATION VIA GEOMETRIC AND TEXTURAL FEATURES Merve KILINC1 and Yusuf Sinan AKGUL2 TUBITAK BILGEM UEKAE, Anibal Street, 41470, Gebze, Kocaeli, Turkey GIT Vision Lab, http://vision.gyte.edu.tr/, Department of Computer Engineering, Gebze Institute of Technology, 41400, Kocaeli, Turkey Keywords: Age estimation:age classification:geometric features:LBP:Gabor:LGBP:cross ratio:FGNET:MORPH" 695e44e9582f2bef78726e3c44f46b45ef12eab1,Using rapid visually evoked EEG activity for person identification,"1st Annual International Conference of the IEEE EMBS Minneapolis, Minnesota, USA, September 2-6, 2009 Using Rapid Visually Evoked EEG Activity for Person Identification Koel Das, Sheng Zhang, Barry Giesbrecht and Miguel P. Eckstein" 6911686f00c99c51c21f057c45d561c88027f676,Articulated pose estimation with parts connectivity using discriminative local oriented contours,"Articulated Pose Estimation with Parts Connectivity using Discriminative Local Oriented Contours Norimichi Ukita Nara Institute of Science and Technology" 69e1ccc3f9ac8410135cdd694135460440503d91,Recognition of quantized still face images,"Recognition of Quantized Still Face Images Tao Wu and Rama Chellappa" 6946acb595095407871992da62298254658f8d84,An Efficient Method for Face Recognition System In Various Assorted Conditions,"An Efficient Method for Face Recognition System In Various Assorted Conditions V.Karthikeyan K.Vijayalakshmi P.Jeyakumar finding" 692aecba13add2b8c1d82db303f5b2ec743ceb44,FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces.,"FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces Andreas R¨ossler1 Davide Cozzolino2 Luisa Verdoliva2 Christian Riess3 Justus Thies1 Matthias Nießner1 Technical University of Munich University Federico II of Naples University of Erlangen-Nuremberg" 6971bdac5119c4cc1b6d92adac605e13f1bcd80f,Limiting the reconstruction capability of generative neural network using negative learning,"LIMITING THE RECONSTRUCTION CAPABILITY OF GENERATIVE NEURAL NETWORK USING NEGATIVE LEARNING Asim Munawar, Phongtharin Vinayavekhin and Giovanni De Magistris IBM Research - Tokyo" 69aef3ce50967a00c568849fed630c573f6cd1eb,3-D Face Analysis and Identification Based on Statistical Shape Modelling,"-D Face Analysis and Identification Based on Statistical Shape Modelling Wei Quan*, Charlie Frowd † *School of Computing, Engineering and Physical Sciences University of Central Lancashire, Preston PR1 2HE, UK. Department of Psychology University of Winchester, Winchester SO22 4NR, UK. Keywords: shape modelling, face analysis, identification." 69d9b79757d76b73ed940754f4d05288b76eb8c3,Preschool Externalizing Behavior Predicts Gender-Specific Variation in Adolescent Neural Structure,"RESEARCH ARTICLE Preschool Externalizing Behavior Predicts Gender-Specific Variation in Adolescent Neural Structure Jessica Z. K. Caldwell1*¤, Jeffrey M. Armstrong2, Jamie L. Hanson1, Matthew J. Sutterer1, Diane E. Stodola1, Michael Koenigs2, Ned H. Kalin2, Marilyn J. Essex2☯, Richard J. Davidson1,2,3☯ Department of Psychology, University of Wisconsin–Madison, Madison, Wisconsin, United States of America, 2 Department of Psychiatry, University of Wisconsin–Madison, Madison, Wisconsin, United States of America, 3 Center for Investigating Healthy Minds, University of Wisconsin–Madison, Madison, Wisconsin, United States of America ☯ These authors contributed equally to this work. ¤. Current address: Marquette General Hospital/Michigan State University, Marquette, MI, United States of America" 699aa8b9b05f746b913bf86efdfa3bcab372f3e1,On Matching Forensic Sketches to Mugshot Photos,"On Matching Forensic Sketches to Mugshot Photos Under review TPAMI Brendan Klare, Zhifeng Li, and Anil K. Jain" 69526cdf6abbfc4bcd39616acde544568326d856,Face Verification Using Template Matching,"[17] B. Moghaddam, T. Jebara, and A. Pentland, “Bayesian face recogni- tion,” Pattern Recognit., vol. 33, no. 11, pp. 1771–1782, Nov. 2000. [18] A. Nefian, “A hidden Markov model-based approach for face detection nd recognition,” Ph.D. dissertation, Dept. Elect. Comput. Eng. Elect. Eng., Georgia Inst. Technol., Atlanta, 1999. [19] P. J. Phillips et al., “Overview of the face recognition grand challenge,” presented at the IEEE CVPR, San Diego, CA, Jun. 2005. [20] H. T. Tanaka, M. Ikeda, and H. Chiaki, “Curvature-based face surface recognition using spherical correlation-principal direction for curved object recognition,” in Proc. Int. Conf. Automatic Face and Gesture Recognition, 1998, pp. 372–377. [21] M. Turk and A. Pentland, “Eigenfaces for recognition,” J. Cognit. Sci., pp. 71–86, 1991. [22] V. N. Vapnik, Statistical Learning Theory. New York: Wiley, 1998. [23] W. Zhao, R. Chellappa, A. Rosenfeld, and P. Phillips, “Face recogni- tion: A literature survey,” ACM Comput. Surveys, vol. 35, no. 44, pp. 99–458, 2003. [24] W. Zhao, R. Chellappa, and P. J. Phillips, “Subspace linear discrimi- nant analysis for face recognition,” UMD TR4009, 1999. Face Verification Using Template Matching" 69d1b055807ef35a8f9490775348cce899421841,An improved ABC algorithm approach using SURF for face identification,"An Improved ABC Algorithm Approach Using SURF for Face Identification Chidambaram Chidambaram1,2, Marlon Subtil Mar¸cal2, Leyza Baldo Dorini2, Hugo Vieira Neto2, and Heitor Silv´erio Lopes2 State University of Santa Catarina-UDESC, Brazil Federal University of Technology - Paran´a - UTFPR, Brazil http://www.sbs.udesc.br http://www.utfpr.edu.br" d5fe9c84710b71a754676b2ee67cec63e8cd184b,FPGA Implementation of a HOG-based Pedestrian Recognition System,"Sebastian Bauer, Ulrich Brunsmann, Stefan Schlotterbeck-Macht Aschaffenburg University of Applied Sciences, Aschaffenburg, Germany Faculty of Engineering FPGA Implementation of a HOG-based Pedestrian Recognition System FPGA Implementation of a HOG-based Pedestrian Recognition System {sebastian.bauer, ulrich.brunsmann, stefan.schlotterbeck-macht} terms of With respect to road crash statistics, on-board pedestrian detection is a key task for future dvanced driver assistance systems. In this paper, we describe the implementation of a real- time pedestrian recognition system that combines FPGA-based extraction of image features with a CPU-based object localization and classification framework. features, we have implemented" d54703c366bce363130f1e633e033a0116c8a0da,Review on Emotion Recognition Databases,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,900 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." d55d6ccefe797317996805ebf58a74587b158950,Distribution-based Label Space Transformation for Multi-label Learning,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Distribution-based Label Space Transformation for Multi-label Learning Zongting Lyu, Yan Yan, and Fei Wu" d55cce6ecbad2c6ecccbaa1cb0d14ae3a46b1454,Multimodal representation learning with neural networks,"Multimodal representation learning with neural networks John Edilson Arevalo Ovalle National University of Colombia Engineering School, Systems and Industrial Engineering Departament Bogot´a, Colombia" d5de42d37ee84c86b8f9a054f90ddb4566990ec0,Asynchronous Temporal Fields for Action Recognition,"Asynchronous Temporal Fields for Action Recognition Gunnar A. Sigurdsson1∗ Santosh Divvala2,3 Ali Farhadi2,3 Abhinav Gupta1,3 Carnegie Mellon University 2University of Washington 3Allen Institute for Artificial Intelligence github.com/gsig/temporal-fields/" d5444f9475253bbcfef85c351ea9dab56793b9ea,BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance,"IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS BoxCars: Improving Fine-Grained Recognition of Vehicles using 3D Bounding Boxes in Traffic Surveillance Jakub Sochor, Jakub ˇSpaˇnhel, Adam Herout in contrast" d5ab6aa15dad26a6ace5ab83ce62b7467a18a88e,Optimized Structure for Facial Action Unit Relationship Using Bayesian Network,"World Journal of Computer Application and Technology 2(7): 133-138, 2014 DOI: 10.13189/wjcat.2014.020701 http://www.hrpub.org Optimized Structure for Facial Action Unit Relationship Using Bayesian Network Yee Koon Loh*, Shahrel A. Suandi Intelligent Biometric Group, School of Electrical and Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, Pulau *Corresponding Author: Pinang, Malaysia Copyright © 2014 Horizon Research Publishing All rights reserved." d56fe69cbfd08525f20679ffc50707b738b88031,Training of multiple classifier systems utilizing partially labeled sequential data sets,"Training of multiple classifier systems utilizing partially labelled sequences Martin Schels, Patrick Schillinger, and Friedhelm Schwenker Ulm University - Department of Neural Information Processing 89069 Ulm - Germany" d5de20cca347d6c5e6f662292e4d52e765ff5cee,Learning Tensors in Reproducing Kernel Hilbert Spaces with Multilinear Spectral Penalties, d50c6d22449cc9170ab868b42f8c72f8d31f9b6c,Dynamic MultiTask Learning with Convolutional Neural Network,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) d5bef023a7d1032a5c717109a9c1b600ee1e8a71,Autism Spectrum Disorder (ASD) and Fragile X Syndrome (FXS): Two Overlapping Disorders Reviewed through Electroencephalography—What Can be Interpreted from the Available Information?,"Brain Sci. 2015, 5, 92-117; doi:10.3390/brainsci5020092 OPEN ACCESS rain sciences ISSN 2076-3425 www.mdpi.com/journal/brainsci/ Review Autism Spectrum Disorder (ASD) and Fragile X Syndrome (FXS): Two Overlapping Disorders Reviewed through Electroencephalography—What Can be Interpreted from the Available Information? Niamh Mc Devitt 1,2,*, Louise Gallagher 1,3,4,5,6 and Richard B. Reilly 1,2,3,7 School of Medicine, Trinity College, the University of Dublin, Dublin, Ireland; E-Mails: (L.G.); (R.B.R.) Trinity Centre for Bioengineering, Trinity College Dublin, the University of Dublin, Dublin, Ireland Trinity College Institute for Neuroscience, Trinity College Dublin, the University of Dublin, Dublin, Ireland Department of Psychiatry, Trinity College Dublin, the University of Dublin, Dublin, Ireland 5 Institute of Molecular Medicine, Trinity Centre for Health Sciences, St James’ Hospital, Dublin, Ireland 6 Linn Dara Child and Adolescent Mental Health Services, Cherry Orchard Hospital Dublin 10," d5b5c63c5611d7b911bc1f7e161a0863a34d44ea,Extracting Scene-Dependent Discriminant Features for Enhancing Face Recognition under Severe Conditions,"Extracting Scene-dependent Discriminant Features for Enhancing Face Recognition under Severe Conditions Rui Ishiyama and Nobuyuki Yasukawa Information and Media Processing Research Laboratories, NEC Corporation 753, Shimonumabe, Nakahara-Ku, Kawasaki 211-8666 Japan" d5e5dc9bb068841ce2b0923d8250489426dc7ffe,Les modèles génératifs en classification supervisée et applications à la catégorisation d'images et à la fiabilité industrielle. (Generative models in supervised statistical learning with applications to digital image categorization and structural reliability),"Les modèles génératifs en classification supervisée et pplications à la catégorisation d’images et à la fiabilité industrielle Guillaume Bouchard To cite this version: Guillaume Bouchard. Les modèles génératifs en classification supervisée et applications à la catégorisa- tion d’images et à la fiabilité industrielle. Interface homme-machine [cs.HC]. Université Joseph-Fourier - Grenoble I, 2005. Français. HAL Id: tel-00541059 https://tel.archives-ouvertes.fr/tel-00541059 Submitted on 29 Nov 2010 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," d50e51d0a349dd904b85734083e59643ba99bd2c,A Robust Face Recognition method,"International Journal of Scientific & Engineering Research, Volume 5, Issue 5, May-2014 805 ISSN 2229-5518 A Robust Face Recognition method G.Seshikala,U.P.Kulakrni,M.N.GiriPrasad" d5579b2708a1c713e1b2feb8646533ce26085a3a,Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery,"Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery Ryuhei Hamaguchi Aito Fujita Keisuke Nemoto Tomoyuki Imaizumi Shuhei Hikosaka PASCO CORPORATION, Japan {riyhuc2734, aaitti6875, koetio8807, tiommu4352," d50a40f2d24363809a9ac57cf7fbb630644af0e5,End-to-End Trained CNN Encoder-Decoder Networks for Image Steganography,"END-TO-END TRAINED CNN ENCODER-DECODER NETWORKS FOR IMAGE STEGANOGRAPHY Atique ur Rehman, Rafia Rahim, Shahroz Nadeem, Sibt ul Hussain National University of Computer & Emerging Sciences (NUCES-FAST), Islamabad, Pakistan. Reveal.ai (Recognition, Vision & Learning) Lab" d510ed87dff0ac430974a44ccd4ef7cf265b0c56,Face Databases and Evaluation,"Face Databases and Evaluation? Dmitry O. Gorodnichy Laboratory and Scientific Services Directorate, Canada Border Services Agency, 79 Bentley Ave., Ottawa, ON, K1A 0L5, Canada Email: Synonyms Face Datasets; Face Recognition Performance Evaluation Definition Face Databases are imagery data that are used for testing face processing algorithms. In the contents of biometrics, face databases are collected and used to evaluate the performance of face recognition biometric systems. Face recognition evaluation is the procedure that is used to access the recognition quality of a face recognition system. It involves testing the system on a set of face databases and/or in a specific setup for the purpose of obtaining measurable statistics that can be used to compare systems to one another. Introduction: factors affecting face recognition performance While for humans recognizing a face in a photograph or in video is natural and easy, computerized face recognition is very hallenging. In fact, automated recognition of faces is known to be more difficult than recognition of other imagery data such s iris, vein, or fingerprint images due to the fact that the human face is a non-rigid 3D object which can be observed at different angles and which may also be partially occluded. Specifically, face recognition systems have to be evaluated with respect to the following factors [19]: . face image resolution – face images can be captured at different resolutions: face images scanned from documents may have very high resolution, while face images captured with a video camera will mostly be of very low resolution," d5d3c1b299e81b4ab96d052f8a37013305b731d9,Performance Evaluation of Human Detection Systems for Robot Safety,"J Intell Robot Syst DOI 10.1007/s10846-016-0334-3 Performance Evaluation of Human Detection Systems for Robot Safety William Shackleford · Geraldine Cheok · Tsai Hong · Kamel Saidi · Michael Shneier Received: 9 April 2015 / Accepted: 11 January 2016 © Springer Science+Business Media Dordrecht (outside the USA) 2016" d590ca357910532cc62eeacc56af8f86b9fe642b,Metric Spaces Library,"Metric Spaces Library www.sisap.org Karina Figueroa1,2, Gonzalo Navarro2, Edgar Ch´avez1 Escuela de Ciencias F´ısico-Matem´aticas, Universidad Michoacana, Mexico Center for Web Research, Department of Computer Science, University of Chile Bug reports, comments, and contributions to November 14, 2008 We describe a library to support similarity searching in metric spaces. It ontains various metric space and index implementations, as well as some tools to evaluate their performance for similarity searching. The library is is an integral part of the new conference Similarity Search and Applications (SISAP) created in 2008. It was defined and initially populated by the uthors, but we expect it to grow with other contributions over time. The goal of similarity searching is, given a finite set of objects U (called a database) drawn from a (possibly infinite) universe X, and a distance function d(·,·) defined among objects of X, preprocess U and build a data structure (called an index) so that similarity searches can be carried out on that set. The objects are seen as black boxes, on which the only operation one can perform is to compute distances, and nothing else should be assumed on" d5856f47fe117c114e8bcfbf2abc4e80691a512c,Interpreting Complex Scenes using a Hierarchy of Prototypical Scene Models,"Interpreting Complex Scenes using a Hierarchy of Prototypical Scene Models Dissertation zur Erlangung des akademischen Grades Doktor der Ingenieurwissenschaften (Dr.-Ing.) vorgelegt an der Technischen Fakult¨at der Universit¨at Bielefeld Sarah Bonnin 4.10.2014" d5d6b3959958adb1333fa1a72227378ad3f7c16d,Collaborative Contributions for Better Annotations, d5c6c0fb51947a2df1389f1aab7a635bf687ac1d,A Multiview Approach to Learning Articulated Motion Models,"A Multiview Approach to Learning Articulated Motion Models Andrea F. Daniele, Thomas M. Howard, and Matthew R. Walter" d51e4b2425c07cd26813b3af646762ff45682ef9,Image Features in Space - Evaluation of Feature Algorithms for Motion Estimation in Space Scenarios, d59a9d80e7d8c875d2b73241a8b02078ea6ad0a7,A Deep Learning Perspective on the Origin of Facial Expressions,"BREUER, KIMMEL: A DEEP LEARNING PERSPECTIVE ON FACIAL EXPRESSIONS A Deep Learning Perspective on the Origin of Facial Expressions Ran Breuer Ron Kimmel Department of Computer Science Technion - Israel Institute of Technology Technion City, Haifa, Israel Figure 1: Demonstration of the filter visualization process." d588dd4f305cdea37add2e9bb3d769df98efe880,Audio-Visual Authentication System over the Internet Protocol,"Audio-Visual Authentication System over the Internet Protocol Yee Wan Wong, Kah Phooi Seng, and Li-Minn Ang bandoned. illumination based is developed with the objective to" d5cf6a02f8308e948e3bcd1fd1ca660ea8ea8921,G ENERATIVE NETWORKS AS INVERSE PROBLEMS WITH SCATTERING TRANSFORMS,"Under review as a conference paper at ICLR 2018 GENERATIVE NETWORKS AS INVERSE PROBLEMS WITH SCATTERING TRANSFORMS Anonymous authors Paper under double-blind review" d56407072eb9847fa44d49969129b5a4d1ef9ceb,Gaussian Process Prior Variational Autoencoders,"Gaussian Process Prior Variational Autoencoders Francesco Paolo Casale†∗, Adrian V Dalca‡§, Luca Saglietti†¶, Jennifer Listgarten(cid:93), Nicolo Fusi† Microsoft Research New England, Cambridge (MA), USA Computer Science and Artificial Intelligence Lab, MIT, Cambridge (MA), USA § Martinos Center for Biomedical Imaging, MGH, HMS, Boston (MA), USA; ¶ Italian Institute for Genomic Medicine, Torino, Italy (cid:93) EECS Department, University of California, Berkeley (CA), USA." d53994f28deb2800120fab8a42852813b3b8c081,Does the Left Hair Part Look Better ( or Worse ) Than the Right ?,"Article Does the Left Hair Part Look Better (or Worse) Than the Right? Social Psychological and Personality Science ª The Author(s) 2018 Reprints and permission: sagepub.com/journalsPermissions.nav DOI: 10.1177/1948550618762500 journals.sagepub.com/home/spp Jeremy A. Frimer1" d53c5a974f9fccf18f3c8f7d73522d6ca7162115,X-GAN : Improving Generative Adversarial Networks with ConveX Combinations,"X-GAN: Improving Generative Adversarial Networks with ConveX Combinations Oliver Blum, Biagio Brattoli, and Bj¨orn Ommer Heidelberg University, HCI / IWR, Germany" d5813a4a0cca115b05e03d8d8c1ac8bf07176e96,Supplementary Material : Reinforced Video Captioning with Entailment Rewards,"Supplementary Material: Reinforced Video Captioning with Entailment Rewards Ramakanth Pasunuru and Mohit Bansal UNC Chapel Hill {ram, Attention-based Baseline Model (Cross-Entropy) Reinforcement Learning (Policy Gradient) Our attention baseline model is similar to the Bah- danau et al. (2015) architecture, where we encode input frame level video features to a bi-directional LSTM-RNN and then generate the caption using a single layer LSTM-RNN, with an attention mech- nism. Let {f1, f2, ..., fn} be the frame-level fea- tures of a video clip and {w1, w2, ..., wm} be the sequence of words forming a caption. The distri- ution of words at time step t given the previously generated words and input video frame-level fea- tures is given as follows:" d59404354f84ad98fa809fd1295608bf3d658bdc,Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs.,"International Journal of Computer Vision manuscript No. (will be inserted by the editor) Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs Xing Di · Vishal M. Patel Received: date / Accepted: date" d5b83d6b4a3c1093edc9138ab9dfe4e965a80261,Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates,"Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates Jun Liu, Amir Shahroudy, Dong Xu, Alex C. Kot, and Gang Wang" d58516957d376e1e682130825efd74a8d34e81d6,Pedestrian Detection Using Thermal Imaging for Night Driving Assistance,"International Journal of Multimed ia Technology IJMT Pedestrian Detection Using Thermal Imaging for Night Driving Assistance Ali Mahmoud *1, Ahmed EL-Barkouky 2, James Graham 3, Aly Farag 4 ,2,3,4Electrica l and Co mputer Engineering Depart ment, Un iversity Of Louisville, Kentucky, USA *1ali.mah isville.edu ; 3ja" d522c162bd03e935b1417f2e564d1357e98826d2,Weakly supervised object extraction with iterative contour prior for remote sensing images,"He et al. EURASIP Journal on Advances in Signal Processing 2013, 2013:19 http://asp.eurasipjournals.com/content/2013/1/19 RESEARCH Open Access Weakly supervised object extraction with iterative contour prior for remote sensing images Chu He1,2*, Yu Zhang1, Bo Shi1, Xin Su3, Xin Xu1 and Mingsheng Liao2" f23d4ed760a35fbfaeab47efde3d876c1818d3d1,Dynamicity and Durability in Scalable Visual Instance Search,"Dynamicity and Durability in Scalable Visual Instance Search Herwig Lejsek∗ Videntifier Technologies, Iceland Björn Þór Jónsson† Reykjavík University, Iceland ITU Copenhagen, Denmark Laurent Amsaleg IRISA–CNRS, France Friðrik Heiðar Ásmundsson∗ Videntifier Technologies, Iceland" f2e9494d0dca9fb6b274107032781d435a508de6,UNCONSTRAINED FACE RECOGNITION, f2d2dd3db244dcbc6fb32ff9c01ed0cdeb3fd437,Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging,"Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging Yong Xu, Qiang Huang, Wenwu Wang, Senior Member, IEEE, Peter Foster, Siddharth Sigtia, Philip J. B. Jackson, and Mark D. Plumbley, Fellow, IEEE" f2b2d50d6ca72666bab34e0f101ae1b18b434925,High-Fidelity Monocular Face Reconstruction based on an Unsupervised Model-based Face Autoencoder.,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 High-Fidelity Monocular Face Reconstruction based on an Unsupervised Model-based Face Autoencoder Ayush Tewari, Michael Zollh¨ofer, Florian Bernard, Pablo Garrido, Hyeongwoo Kim, Patrick P´erez, and Christian Theobalt (Invited Paper)" f20e0eefd007bc310d2a753ba526d33a8aba812c,Accurate and robust face recognition from RGB-D images with a deep learning approach,"Lee et al.: RGB-D FACE RECOGNITION WITH A DEEP LEARNING APPROACH Accurate and robust face recognition from RGB-D images with a deep learning pproach Yuancheng Lee http://cv.cs.nthu.edu.tw/php/people/profile.php?uid=150 Jiancong Chen http://cv.cs.nthu.edu.tw/php/people/profile.php?uid=153 Ching-Wei Tseng http://cv.cs.nthu.edu.tw/php/people/profile.php?uid=156 Computer Vision Lab, Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan Shang-Hong Lai http://www.cs.nthu.edu.tw/~lai/" f2b95f135b95c3df4f6ebe6015098a2e1667711d,Weakly Supervised Object Localization Using Things and Stuff Transfer,"Weakly Supervised Object Localization Using Things and Stuff Transfer Miaojing Shi1,2 Holger Caesar1 University of Edinburgh 2Tencent Youtu Lab Vittorio Ferrari1" f22058a3003cee6b17c6c25c8a635a653e78614c,Multimodal Attention in Recurrent Neural Networks for Visual Question Answering,"Global Journal of Computer Science and Technology: D Neural & Artificial Intelligence Volume 17 Issue 1 Version 1.0 Year 2017 Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Inc. (USA) Online ISSN: 0975-4172 & Print ISSN: 0975-4350 Multimodal Attention in Recurrent Neural Networks for Visual Question Answering By Lorena Kodra & Elinda Kajo Meçe Polytechnic University of Tirana" f26a8dcfbaf9f46c021c41a3545fcfa845660c47,Human Pose Regression by Combining Indirect Part Detection and Contextual Information,"Human Pose Regression by Combining Indirect Part Detection and Contextual Information Diogo C. Luvizon Hedi Tabia ETIS Lab., UMR 8051, Universit´e Paris Seine, Universit´e Cergy-Pontoise, ENSEA, CNRS. {diogo.luvizon, hedi.tabia, David Picard" f2bccfb12c1546bdf73b11904ac44b1cfa130072,RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement,"RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement Kiwoo Shin∗†, Youngwook Paul Kwon∗‡ and Masayoshi Tomizuka†" f2d95a5b29986a6a28746b30adfa43497b27ff02,Global Self-Similarity and Saliency Measures Based on Sparse Representations for Classification of Objects and Spatio-temporal Sequences,"Global Self-Similarity and Saliency Measures Based on Sparse Representations for Classification of Objects and Spatio-temporal Sequences. A DISSERTATION SUBMITTED TO THE FACULTY OF THE GRADUATE SCHOOL OF THE UNIVERSITY OF MINNESOTA Guruprasad Somasundaram IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF Doctor of Philosophy Nikolaos Papanikolopoulos November, 2012" f2efc85f9e20840c591b4590fd9ed202f727546a,Distributed signature fusion for person re-identification,"Distributed Signature Fusion for Person Re-Identification Niki Martinel University of Udine Udine, Italy Christian Micheloni University of Udine Udine, Italy Claudio Piciarelli University of Udine Udine, Italy" f2d215d25630b15122f8f773b00ac33bdf597c05,Real-Time Face Recognition Using Local Ternary Patterns with Collaborative Representation-Based Classification for Mobile Robots,"Real time Face Recognition using Local Ternary Patterns with Collaborative Representation based Classification for Mobile Robots Duc My Vo and Andreas Zell Chair of Cognitive Systems, Computer Science Department, University of T¨ubingen, Sand 1, D-72076 T¨ubingen, Germany http://www.cogsys.cs.uni-tuebingen.de" f218df397afb1f070ee093bb9a19616f61b562c4,A Neural Network Model of Face Detection for Active Vision Implementation,"International Journal of Modern Engineering Research (IJMER) www.ijmer.com Vol. 2, Issue. 5, Sept.-Oct. 2012 pp-2969-2974 ISSN: 2249-6645 A Neural Network Model of Face Detection for Active Vision Implementation Yasuomi D. Sato*, ** Yasutaka Kuriya* * Department of Brain Science and Engineering, Graduate School for Life Science and Systems Engineering, Kyushu ** Frankfurt Institute for Advanced Studies (FIAS), Goethe University Frankfurt, Germany Institute of Technology, Japan impaired" f20f93a5b2291283c0e40bd0418927efb06acb6a,A Tale of Two Encodings : Comparing Bag-of-Words and Word 2 vec for VQA,"A Tale of Two Encodings: Comparing Bag-of-Words and Word2vec for VQA Berthy Feng Princeton University ’19 Divya Thuremella Princeton University ’18" f2828ae81327276407504caab558c13362439476,"Modeling , Representing and Learning of Visual Categories","Modeling, Representing and Learning of Visual Categories A dissertation submitted to the TECHNISCHE UNIVERSIT¨AT DARMSTADT Fachbereich 20 for the degree of Dr. ing. presented by MARIO FRITZ Dipl.–Inf. orn 16th of January, 1978 in Adenau, Germany Prof. Dr. Bernt Schiele, examiner Prof. Dr. Pietro Perona, co-examiner Date of Submission: 12th of June, 2008 Date of Defense: 8th of August, 2008" f2889f3ab8e330e1ba6b23d493f8d727f49a9bc8,Recent Advances in Neural Program Synthesis,"Recent Advances in Neural Program Synthesis Neel Kant Machine Learning at Berkeley UC Berkeley" f21a8e372fa12d87fec77d3297afe1e566e229a7,"Nonnegative tensor factorization as an alternative Csiszar–Tusnady procedure: algorithms, convergence, probabilistic interpretations and novel probabilistic tensor latent variable analysis algorithms","Data Min Knowl Disc (2011) 22:419–466 DOI 10.1007/s10618-010-0196-4 Nonnegative tensor factorization as an alternative Csiszar–Tusnady procedure: algorithms, convergence, probabilistic interpretations and novel probabilistic tensor latent variable analysis algorithms Stefanos Zafeiriou · Maria Petrou Received: 1 May 2009 / Accepted: 8 July 2010 / Published online: 1 August 2010 © The Author(s) 2010" f29aae30c2cb4c73a3c814408ee5692e22176329,Pairwise Relational Networks using Local Appearance Features for Face Recognition,"Pairwise Relational Networks using Local Appearance Features for Face Recognition Bong-Nam Kang Yonghyun Kim, Daijin Kim Department of Creative IT Engineering Department of Computer Science and Engineering POSTECH, Korea POSTECH, Korea" f2b79ae191fc03a93ed50eea773279f67c8351e1,Annotating images with suggestions: user study of a tagging system,"Annotating images with suggestions — user study of a tagging system Michal Hradiˇs, Martin Kol´aˇr, Aleˇs L´an´ık, Jiˇr´ı Kr´al, Pavel Zemˇc´ık and Pavel Smrˇz Faculty of Information Technology VUT — Brno University of Technology Brno Czech Republic" f2fafa5d2c49034ba8f6318f869822b462b33a42,iQIYI-VID: A Large Dataset for Multi-modal Person Identification,"iQIYI-VID: A Large Dataset for Multi-modal Person Identification Yuanliu Liu, Peipei Shi, Bo Peng, He Yan, Yong Zhou, Bing Han, Yi Zheng, Chao Lin, Jianbin Jiang,Yin Fan, Tingwei Gao, Ganwen Wang, Jian Liu, Xiangju Lu, Danming Xie iQIYI, Inc." f2b547b0bbda1478cbecbd5c184c3c42c3db7e3c,Semi-parametric Image Synthesis, f26d34d8a8d082ce2c81937f61c28f3769c38372,Probability of Seeing Increases Saccadic Readiness,"Probability of Seeing Increases Saccadic Readiness The´ re` se Collins* Laboratoire Psychologie de la Perception, Universite´ Paris Descartes & CNRS, Paris, France" f2a7f9bd040aa8ea87672d38606a84c31163e171,Human Action Recognition without Human,"Human Action Recognition without Human Yun He, Soma Shirakabe, Yutaka Satoh, Hirokatsu Kataoka National Institute of Advanced Industrial Science and Technology (AIST) Tsukuba, Ibaraki, Japan {yun.he, shirakabe-s, yu.satou," f2877cdbffb0c9a4de1f562099d2f0597bcfec0b,"COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization","Zlatintsi et al. EURASIP Journal on Image and Video Processing (2017) 2017:54 DOI 10.1186/s13640-017-0194-1 EURASIP Journal on Image nd Video Processing RESEARCH Open Access COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization Athanasia Zlatintsi1* Niki Efthymiou1, Katerina Pastra4, Alexandros Potamianos1 and Petros Maragos1 , Petros Koutras1, Georgios Evangelopoulos2, Nikolaos Malandrakis3," c3bd3b9782dc504ee4f2b8a12bd9c562a5c0d7ad,Learning Complexity-Aware Cascades for Deep Pedestrian Detection,"Learning Complexity-Aware Cascades for Deep Pedestrian Detection Zhaowei Cai Mohammad Saberian Nuno Vasconcelos Yahoo Labs" c3293ef751d3fb041bd3016fbc3fa5cc16f962fa,Inferencing based on unsupervised learning of disentangled representations,"Accepted as a conference paper at the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2018 Inferencing Based on Unsupervised Learning of Disentangled Representations Tobias Hinz and Stefan Wermter ∗ Universit¨at Hamburg, Department of Informatics, Knowledge Technology Vogt-Koelln-Str. 30, 22527 Hamburg, Germany http://www.informatik.uni-hamburg.de/WTM/" c37a971f7a57f7345fdc479fa329d9b425ee02be,A Novice Guide towards Human Motion Analysis and Understanding,"A Novice Guide towards Human Motion Analysis and Understanding Dr. Ahmed Nabil Mohamed" c3599c91d0e3473178c1578b731b03e4be5d3ff1,Improving Resource Efficiency in Cloud Computing a Dissertation Submitted to the Department of Electrical Engineering and the Committee on Graduate Studies of Stanford University in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy,"IMPROVING RESOURCE EFFICIENCY IN CLOUD COMPUTING A DISSERTATION SUBMITTED TO THE DEPARTMENT OF ELECTRICAL ENGINEERING AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Christina Delimitrou August 2015" c3beae515f38daf4bd8053a7d72f6d2ed3b05d88,ACL 2014 52nd Annual Meeting of the Association for Computational Linguistics TACL Papers,"ACL201452ndAnnualMeetingoftheAssociationforComputationalLinguisticsTACLPapersJune23-25,2014Baltimore,Maryland,USA" c398684270543e97e3194674d9cce20acaef3db3,Chapter 2 Comparative Face Soft Biometrics for Human Identification,"Chapter 2 Comparative Face Soft Biometrics for Human Identification Nawaf Yousef Almudhahka, Mark S. Nixon and Jonathon S. Hare" c32f798663bd00268e3ceb8a855222dae877a58a,Anomaly detection from videos under sparse data and partial observations ∗,"Anomaly detection from videos under sparse data and partial observations∗ Sangmin Oh, Anthony Hoogs {sangmin.oh, Kitware Inc. 28 Corporate Dr., Clifton Park, NY Anomaly detection from videos is an important computer vision problem where the goal is to identify rare ctivity examples which significantly deviate from normal behaviors observed in scenes. For example, Fig 1 shows scene (a) and tracking results (b), where vehicles (blue) and people (green) are tracked over an extended period of time. An example anomaly is shown in Fig. 1(d) where a vehicle (red circle) is turning at a traf‌f‌ic intersection onfronting oncoming traf‌f‌ic. (a) Original Scene 1 (b) Tracking results 1 (c) Tracking results 2 (d) Abnormal vehicle turning (e) Functional scene elements 1 (f) Functional scene elements 2 (g) Activity words of vehicles (h) Fragmented tracks (i) Linked tracklets Figure 1: (a) Scene 1. (b) Tracking results in scene 1 with vehicles (blue) and people (green). (c) Tracking results" c33289788ca69a55c7eefe6e672c82a0cac5a299,Semantic Video CNNs Through Representation Warping,"Semantic Video CNNs through Representation Warping Raghudeep Gadde1,3, Varun Jampani1,4 and Peter V. Gehler1,2,3 MPI for Intelligent Systems, University of W¨urzburg Bernstein Center for Computational Neuroscience, NVIDIA" c390fb954a07ecee473e0704ac065875121f6137,Heterogeneous Tensor Decomposition for Clustering via Manifold Optimization,"IEEE TRANSACTIONS ON XXXX, VOL. XX, NO. X, APRIL 2015 Heterogeneous Tensor Decomposition for Clustering via Manifold Optimization Yanfeng Sun, Junbin Gao, Xia Hong, Bamdev Mishra and Baocai Yin" c33522fc5d2cf92c5a10f32ba9416365944cdb85,Scaling the Scattering Transform: Deep Hybrid Networks,"Scaling the Scattering Transform: Deep Hybrid Networks Edouard Oyallon D´epartement Informatique Ecole Normale Sup´erieure Eugene Belilovsky University of Paris-Saclay INRIA and KU Leuven Paris, France Sergey Zagoruyko Universit´e Paris-Est ´Ecole des Ponts ParisTech Paris, France" c3955d74f2a084a8ddcbd7e73952c326e81804b2,Mutual Information Neural Estimation,"Mutual Information Neural Estimation Mohamed Ishmael Belghazi 1 Aristide Baratin 1 2 Sai Rajeswar 1 Sherjil Ozair 1 Yoshua Bengio 1 3 4 Aaron Courville 1 3 R Devon Hjelm 1 4" c3dc704790e1a170919087baab0ad10d7df6c24e,Oxytocin in the socioemotional brain: implications for psychiatric disorders,"C l i n i c a l r e s e a r c h Oxytocin in the socioemotional brain: implications for psychiatric disorders Peter Kirsch, PhD Introduction During recent years, the neuropeptide oxytocin (OXT) has attracted enormous interest in neuroscien- tific research on social and emotional processes. Given the generally increased interest in social cognition in the area of psychiatric research, the number of publi- ations focusing on OXT in the context of mental dis- orders has also increased markedly in recent years. The role of OXT in the context of childbirth and lactation has long been studied; however, two lines of research have motivated investigation into the role of OXT in social behavior. First, animal research initiated by In- sel and Young1 on the role of OXT in maternal be- havior and bonding revealed that OXT in the central nervous system modulates social behavior. Second, in human research, a startling paper by Kosfeld et al2" c317181fa1de2260e956f05cd655642607520a4f,Objective Classes for Micro-Facial Expression Recognition,"Research Article Research Article for submission to journal Subject Areas: omputer vision, pattern recognition, feature descriptor Keywords: micro-facial expression, expression recognition, action unit Moi Hoon Yap e-mail: Objective Classes for Micro-Facial Expression Recognition Adrian K. Davison1, Walied Merghani2 and Moi Hoon Yap3 Centre for Imaging Sciences, University of Manchester, Manchester, United Kingdom Sudan University of Science and Technology, Khartoum, Sudan" c391029d67e5a0c352f9f328b838cb19528336fe,Responding to Other People’s Direct Gaze: Alterations in Gaze Behavior in Infants at Risk for Autism Occur on Very Short Timescales,"J Autism Dev Disord (2017) 47:3498–3509 DOI 10.1007/s10803-017-3253-7 ORIGINAL PAPER Responding to Other People’s Direct Gaze: Alterations in Gaze Behavior in Infants at Risk for Autism Occur on Very Short Timescales Pär Nyström1 · Sven Bölte2,3 · Terje Falck‑Ytter1,2 · The EASE Team Published online: 4 September 2017 © The Author(s) 2017. This article is an open access publication" c3a1a3d13bf1cb2b9c054857b857c3fb9d7176f6,Détection de marqueurs affectifs et attentionnels de personnes âgées en interaction avec un robot. (Audio-visual detection of emotional (laugh and smile) and attentional markers for elderly people in social interaction with a robot),"Détection de marqueurs affectifs et attentionnels de personnes âgées en interaction avec un robot Fan Yang To cite this version: Fan Yang. Détection de marqueurs affectifs et attentionnels de personnes âgées en interaction vec un robot. Intelligence artificielle [cs.AI]. Université Paris-Saclay, 2015. Français. . HAL Id: tel-01280505 https://tel.archives-ouvertes.fr/tel-01280505 Submitted on 29 Feb 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," c380aa240ebcdb8bf2cad4f30bcef2390fada091,Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space,"Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space Berta Bescos1, Jos´e Neira1, Roland Siegwart2 and Cesar Cadena2" c3b5ec36a29b320a576f6b9e58188b505becb4aa,Practical Gauss-Newton Optimisation for Deep Learning,"Practical Gauss-Newton Optimisation for Deep Learning Aleksandar Botev 1 Hippolyt Ritter 1 David Barber 1 2" c3dc4f414f5233df96a9661609557e341b71670d,Utterance independent bimodal emotion recognition in spontaneous communication,"Tao et al. EURASIP Journal on Advances in Signal Processing 2011, 2011:4 http://asp.eurasipjournals.com/content/2011/1/4 RESEARCH Utterance independent bimodal emotion recognition in spontaneous communication Jianhua Tao*, Shifeng Pan, Minghao Yang, Ya Li, Kaihui Mu and Jianfeng Che Open Access" c34911e9fefd987470edf8f620d9ce8f0030339d," Autism, Emotion Recognition and the Mirror Neuron System: The Case of Music ","Copyright © 2009 by MJM MJM 2009 12(2): 87-98 FoCuS rEViEW Autism, Emotion Recognition and the Mirror Neuron System: The Case of Music Istvan Molnar-Szakacs*, Martha J. Wang, Elizabeth A. Laugeson, Katie Overy, Wai-Ling Wu, Judith Piggot" c399c0089fb134d1476fadf5f0426e0e8b70eebd,The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses.,1EXPERIMENTALRESULTS1.1JaccardlossarXiv:1512.07797v2 [stat.ML] 15 May 2017 c338045f80ab3465bdc381f2b1791744b060fbb3,A Diffusion and Clustering-Based Approach for Finding Coherent Motions and Understanding Crowd Scenes,"A Diffusion and Clustering-based Approach for Finding Coherent Motions and Understanding Crowd Scenes Weiyao Lin, Yang Mi, Weiyue Wang, Jianxin Wu, Jingdong Wang, and Tao Mei" c3124b0491d479e8a869c61f059ffa08dad49362,A Generative Model for Zero Shot Learning Using Conditional Variational Autoencoders,"A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders Ashish Mishra1 , Shiva Krishna Reddy1, Anurag Mittal, and Hema A Murthy Indian Institute of Technology Madras" c30e4e4994b76605dcb2071954eaaea471307d80,Feature Selection for Emotion Recognition based on Random Forest, c32b5f8d400cdfd4459b0dfdeccf011744df0b4b,Object Tracking Using Local Multiple Features and a Posterior Probability Measure,"Article Object Tracking Using Local Multiple Features and a Posterior Probability Measure Wenhua Guo *, Zuren Feng and Xiaodong Ren Systems Engineering Institute, State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, China; (Z.F.); (X.R.) * Correspondence: Tel.: +86-29-8266-7771 Academic Editors: Xue-Bo Jin, Shuli Sun, Hong Wei and Feng-Bao Yang Received: 20 February 2017; Accepted: 28 March 2017; Published: 31 March 2017" c37de914c6e9b743d90e2566723d0062bedc9e6a,Joint and Discriminative Dictionary Learning for Facial Expression Recognition,"©2016 Society for Imaging Science and Technology DOI: 10.2352/ISSN.2470-1173.2016.11.IMAWM-455 Joint and Discriminative Dictionary Learning Expression Recognition for Facial Sriram Kumar, Behnaz Ghoraani, Andreas Savakis" c35724d227eb1e3d680333469fb9b94c677e871f,Multi-view Generative Adversarial Networks,"Under review as a conference paper at ICLR 2017 MULTI-VIEW GENERATIVE ADVERSARIAL NET- WORKS Mickaël Chen Sorbonne Universités, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005, Paris, France Ludovic Denoyer Sorbonne Universités, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005, Paris, France" c3ea346826467f04779e55679679c7c7e549c8a2,Learning Short-Cut Connections for Object Counting,"OÑORO-RUBIO, NIEPERT, LÓPEZ-SASTRE: LEARNING SHORT-CUT CONNECTIONS. . . Learning Short-Cut Connections for Object Counting Daniel Oñoro-Rubio1 Mathias Niepert1 Roberto J. López-Sastre2 SysML, NEC Lab Europe, Heidelberg, Germany GRAM, University of Alcalá, Alcalá de Henares, Spain" c36f933a46e1d1c51785295bb97154df9ceada36,"Optimizing Program Performance via Similarity, Using a Feature-Agnostic Approach","Optimizing Program Performance via Similarity, Using a Feature-agnostic Approach Rosario Cammarota, Laleh Aghababaie Beni Alexandru Nicolau, and Alexander V. Veidenbaum Department of Computer Science, University of California Irvine, Irvine, USA" c32b09f20badd9ce04309d7c5ebea88336a3345a,Token-level and sequence-level loss smoothing for RNN language models,"Token-level and sequence-level loss smoothing for RNN language models Maha Elbayad1,2 Laurent Besacier1 Jakob Verbeek2 Univ. Grenoble Alpes, CNRS, Grenoble INP, Inria, LIG, LJK, F-38000 Grenoble France" c3b037fd6fb4542f7ed18c194a03ae328bcca423,Random binary mappings for kernel learning and efficient SVM,"Random Decision Stumps for Kernel Learning and Efficient SVM Gemma Roig * Xavier Boix * Luc Van Gool Computer Vision Lab, ETH Zurich, Switzerland * Both first authors contributed equally." c3780c0fd7f6ee82339a974045eebbc9e5b61c75,User-specific Score Normalization and Fusion for Biometric Person Recognition,"User-specific Score Normalization and Fusion for Biometric Person Recognition Norman Poh" c34ec5dd51880acf72336e85e4e45da5fcfc75f4,LEGO: Learning Edge with Geometry all at Once by Watching Videos,"LEGO: Learning Edge with Geometry all at Once by Watching Videos Zhenheng Yang1 Peng Wang2 Yang Wang2 Wei Xu3 Ram Nevatia1 University of Southern California 2Baidu Research National Engineering Laboratory for Deep Learning Technology and Applications" c32f04ccde4f11f8717189f056209eb091075254,Analysis and Synthesis of Behavioural Specific Facial Motion,"Analysis and Synthesis of Behavioural Specific Facial Motion Lisa Nanette Gralewski A dissertation submitted to the University of Bristol in accordance with the requirements for the degree of Doctor of Philosophy in the Faculty of Engineering, Department of Computer Science. February 2007 71657 words" c3c73bb626efec988aadbac519c61810710282fe,Saccadic movements using eye-tracking technology in individuals with autism spectrum disorders: pilot study.,"Arq Neuropsiquiatr 2006;64(3-A):559-562 SACCADIC MOVEMENTS USING EYE-TRACKING TECHNOLOGY IN INDIVIDUALS WITH AUTISM SPECTRUM DISORDERS Pilot study Marcos T. Mercadante, Elizeu C. Macedo, Patrícia M. Baptista, Cristiane S. Paula, José S. Schwartzman" c3b3636080b9931ac802e2dd28b7b684d6cf4f8b,Face Recognition via Local Directional Pattern,"International Journal of Security and Its Applications Vol. 7, No. 2, March, 2013 Face Recognition via Local Directional Pattern Dong-Ju Kim*, Sang-Heon Lee and Myoung-Kyu Sohn Division of IT Convergence, Daegu Gyeongbuk Institute of Science & Technology 50-1, Sang-ri, Hyeonpung-myeon, Dalseong-gun, Daegu, Korea." c324986c8599fee2f6da7b59751e89ed9624afa3,Dual Quaternions as Constraints in 4D-DPM Models for Pose Estimation,"Article Dual Quaternions as Constraints in 4D-DPM Models for Pose Estimation Enrique Martinez-Berti *, Antonio-José Sánchez-Salmerón and Carlos Ricolfe-Viala Departamento de Ingeniería de Sistemas y Automática, Instituto de Automática e informática Industrial, Universitat Politècnica de València, València, 46022, Spain ; (A.-J.S.-S.); (C.R.-V.) * Correspondence: Received: 1 June 2017; Accepted: 13 August 2017; Published: 19 August 2017" c3fb2399eb4bcec22723715556e31c44d086e054,Face recognition based on SIGMA sets of image features,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE . INTRODUCTION" c32fb755856c21a238857b77d7548f18e05f482d,Multimodal Emotion Recognition for Human-Computer Interaction : A Survey,"Multimodal Emotion Recognition for Human- Computer Interaction: A Survey School of Computer and Communication Engineering, University of Science and Technology Beijing, 100083 Beijing, China. Michele Mukeshimana, Xiaojuan Ban, Nelson Karani, Ruoyi Liu" c3de7c38493cfe67654411d77f47069cfa7b077b,Multiple context mere exposure: Examining the limits of liking.,"ISSN: 1747-0218 (Print) 1747-0226 (Online) Journal homepage: http://www.tandfonline.com/loi/pqje20 Multiple context mere exposure: Examining the limits of liking Daniel de Zilva, Ben R. Newell & Chris J. Mitchell To cite this article: Daniel de Zilva, Ben R. Newell & Chris J. Mitchell (2015): Multiple context mere exposure: Examining the limits of liking, The Quarterly Journal of Experimental Psychology, DOI: 10.1080/17470218.2015.1057188 To link to this article: http://dx.doi.org/10.1080/17470218.2015.1057188 Accepted online: 29 Jun 2015.Published online: 06 Jul 2015. Submit your article to this journal Article views: 43 View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pqje20 Download by: [UNSW Library] Date: 05 October 2015, At: 22:09" c348118690d2e6544ec1e68f904dbf9e5b6397bd,Video-to-Video Synthesis,"Video-to-Video Synthesis Ting-Chun Wang1, Ming-Yu Liu1, Jun-Yan Zhu2, Guilin Liu1, Andrew Tao1, Jan Kautz1, Bryan Catanzaro1 NVIDIA, 2MIT CSAIL" c3285a1d6ec6972156fea9e6dc9a8d88cd001617,Extreme 3D Face Reconstruction: Seeing Through Occlusions, c141b7c4ccb4a0e5d2a327aa260b318c7c3bcfbb,Real-Time Adaptive Image Compression,"Real-Time Adaptive Image Compression Oren Rippel * 1 Lubomir Bourdev * 1" c1d98fca75c63fd5975fc2fcd3fe07ac02de4a5b,An End-to-End Traffic Vision and Counting System Using Computer Vision and Machine Learning: The Challenges in Real-Time Processing,"SIGNAL 2018 : The Third International Conference on Advances in Signal, Image and Video Processing An End-to-End Traffic Vision and Counting System Using Computer Vision and Machine Learning: The Challenges in Real-Time Processing Haiyan Wang, Mehran Mazari, Mohammad Pourhomayoun Computer Science Department California State University Los Angeles Los Angeles, USA Email: Janna Smith Department of Transportation City of Los Angeles Los Angeles, USA Email: Hunter Owens Data Science Federation City of Los Angeles Los Angeles, USA Email: William Chernicoff Toyota Mobility Foundation" c18e11d0578dc67e46160afa527e1a9e73b8fa15,Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets,"Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets Fang-Chieh Chou, Tsung-Han Lin, Henggang Cui, Vladan Radosavljevic, Thi Nguyen, Tzu-Kuo Huang, Matthew Niedoba, Jeff Schneider, Nemanja Djuric Uber Advanced Technologies Group {fchou, hanklin, hcui2, vradosavljevic, thi, tkhuang, mniedoba, jschneider," c1bd99083098cf8dbfed8d25514755bc5356bc06,Fly Page (This sheet is left blank and not counted) GENERALIZED DISCRIMINANT ANALYSIS IN CONTENT-BASED IMAGE RETRIEVAL APPROVED BY SUPERVISING COMMITTEE:,"Fly Page (This sheet is left blank and not counted)" c1bbcdf3b5901e3378a89808b07e53a502c295f0,Allostasis and the human brain: Integrating models of stress from the social and life sciences.,"Psychol Rev. Author manuscript; available in PMC 2011 January 1. Published in final edited form as: Psychol Rev. 2010 January; 117(1): 134–174. doi: 10.1037/a0017773 Allostasis and the human brain: Integrating models of stress from the social and life sciences Barbara L. Ganzel, Pamela A. Morris, and Elaine Wethington Author information ► Copyright and License information ► The publisher's final edited version of this article is available at Psychol Rev See other articles in PMC that cite the published article." c1100efda7c00d3181a6a065ab1474c2f864e267,Video visual analytics,"Video Visual Analytics Von der Fakultät Informatik, Elektrotechnik und Informationstechnik der Universität Stuttgart genehmigte Abhandlung zur Erlangung der Würde eines Doktors der Naturwissenschaften (Dr. rer. nat.) Vorgelegt von Markus Johannes Höferlin us Herrenberg Hauptberichter: Prof. Dr. Daniel Weiskopf Mitberichter: Prof. Dr. Gunther Heidemann Prof. Min Chen, BSc, PhD, FBCS, FEG, FLSW Tag der mündlichen Prüfung: 27. Mai 2013 Visualisierungsinstitut der Universität Stuttgart" c1ff88493721af1940df0d00bcfeefaa14f1711f,Subspace Regression: Predicting a Subspace from one Sample,"#1369 CVPR 2010 Submission #1369. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. #1369 Subspace Regression: Predicting a Subspace from one Sample Anonymous CVPR submission Paper ID 1369" c1130d5c7bb1311e04cffbaf2bf6cbe734adc2ac,DFNet: Semantic Segmentation on Panoramic Images with Dynamic Loss Weights and Residual Fusion Block,"DFNet: Semantic Segmentation on Panoramic Images with Dynamic Loss Weights and Residual Fusion Block Wei Jiang, Yan Wu∗ technique, moreover," c1b971cd7263e788e114cf8c4aa076a2e170990f,Establishing the fundamentals for an elephant early warning and monitoring system,"Establishing the fundamentals for an elephant early warning and monitoring system Zeppelzauer and Stoeger Zeppelzauer and Stoeger BMC Res Notes (2015) 8:409 DOI 10.1186/s13104-015-1370-y" c1dd69df9dfbd7b526cc89a5749f7f7fabc1e290,Unconstrained face identification with multi-scale block-based correlation,"Unconstrained face identification with multi-scale block-based orrelation Gaston, J., MIng, J., & Crookes, D. (2016). Unconstrained face identification with multi-scale block-based orrelation. In Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 1477-1481). [978-1-5090-4117-6/17] Institute of Electrical and Electronics Engineers (IEEE). Published in: Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy" c126f053855396f9e1ac1a408201d50d5280f79f,FPGA implementation of an embedded face detection system based on LEON 3,"FPGA implementation of an embedded face detection system based on LEON3 L. Acasandrei1 and A. Barriga2 IMSE-CNM-CSIC, Seville, Spain IMSE-CNM-CSIC/University of Seville, Seville, Spain" c175f1666f3444e407660c5935a05b2a53f346f0,Modifying the Memorability of Face,"Modifying the Memorability of Face Photographs The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Citation As Published Publisher Version Accessed Citable Link Terms of Use Detailed Terms Khosla, Aditya, Wilma A. Bainbridge, Antonio Torralba, and Aude Oliva. “Modifying the Memorability of Face Photographs.” 2013 IEEE International Conference on Computer Vision (December 013). http://dx.doi.org/10.1109/ICCV.2013.397 Institute of Electrical and Electronics Engineers (IEEE) Author's final manuscript Mon Nov 05 02:44:57 EST 2018 http://hdl.handle.net/1721.1/90986" c100cb3ee6326d4f420c3be27b1232de6cd3bc8d,Methods for vehicle detection and vehicle presence analysis for traffic applications,"Methods for vehicle detection and vehicle presence analysis for traffic applications Oliver Sidla*, Yuriy Lipetski SLR Engineering GmbH, Gartengasse 19, A-8010 Graz, Austria" c1c3e32ecf6da8e1372fab7d504cb8cd2c86fd93,ΓΨ Face recognition based on artificial immune networks and principal component analysis with single training image per person,"Face recognition based on artificial immune networks and principal omponent analysis with single training image per person , Department of Mechanical Engineering, Tatung University, Taiwan, ROC, Guan-Chun Luh" c1c8ea4b2118095bea55cf6b51c36dbf95cc7f2c,Learning 3D Segment Descriptors for Place Recognition,"Learning 3D Segment Descriptors for Place Recognition Andrei Cramariuc Renaud Dubé Hannes Sommer Roland Siegwart Igor Gilitschenski∗" c19845c84abc9e3afe17003fdcd545ed020d0624,A face biometric benchmarking review and characterisation,"A Face Biometric Benchmarking Review and Characterisation Sandra Mau Senior Research Engineer NICTA Advanced Surveillance BeFIT workshop – ICCV 2011" c1df441663f18ce608ad396b6bb77f6c2e585678,FACE CLASSIFICATION USING WIDROW-HOFF LEARNING PARALLEL LINEAR COLLABORATIVE DISCRIMINANT REGRESSION ( WH-PLCDRC ),"Journal of Theoretical and Applied Information Technology 31st July 2016. Vol.89. No.2 © 2005 - 2016 JATIT & LLS. All rights reserved. ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 FACE CLASSIFICATION USING WIDROW-HOFF LEARNING PARALLEL LINEAR COLLABORATIVE DISCRIMINANT REGRESSION (WH-PLCDRC) VISHWANATH P., 2Dr. V M VISWANATHA NIMS University, Jaipur(Rajasthan), Electronics and Communication Engineering S L N College of Engineering, Raichur, Electronics and Communication Engineering E-mail:" c1dfabe36a4db26bf378417985a6aacb0f769735,Describing Visual Scene through EigenMaps,"Journal of Computer Vision and Image Processing, NWPJ-201109-50 Describing Visual Scene through EigenMaps Shizhi Chen, Student Member, IEEE, and YingLi Tian, Senior Member, IEEE" c1643ad49ab52b7a38e416430583ca6adaaf5a9d,Face Recognition for Smart Environments Means of Identification Achieving Face Recognition,"C O V E R F E A T U R E Face Recognition for Smart Environments Computers of the future will interact with us more like humans. A key element of that interaction will be their ability to recognize our faces and even understand our expressions. Alex (Sandy) Pentland Tanzeem Choudhury MIT Media Laboratory Smart environments, wearable computers, and ubiquitous computing in general are the com- ing “fourth generation” of computing and information technology.1-3 These devices will e everywhere—clothes, home, car, and office—and their economic impact and cultural sig- nificance will dwarf those of the first three generations." c160bcbc8f0517a97e46042c84343bf3f0477478,A Dynamic Approach and a New Dataset for Hand-detection in First Person Vision,"A Dynamic Approach and a New Dataset for Hand-Detection in First Person Vision. Alejandro Betancourt1,2, Pietro Morerio1, Emilia I. Barakova2, Lucio Marcenaro1, Matthias Rauterberg2, Carlo S. Regazzoni1 Department of Naval, Electric, Electronic and Telecommunications Engineering - University Designed Intelligence Group, Department of Industrial Design - Eindhoven University of Technology, The Netherlands. of Genoa, Italy." c19ed5102ecd953d5c78d5a0b87eaa51658e07d8,Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera,"Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera Timo von Marcard1, Roberto Henschel1, Michael J. Black2, Bodo Rosenhahn1, nd Gerard Pons-Moll3 Leibniz Universit¨at Hannover, Germany MPI for Intelligent Systems, T¨ubingen, Germany MPI for Informatics, Saarland Informatics Campus, Germany" c11a2501204e9e7c4a53d8a3c87055b2b11c73df,Adaptive Learning Algorithms for Transferable Visual Recognition,"Adaptive Learning Algorithms for Transferable Visual Recognition Judy Hoffman Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2016-139 http://www.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-139.html August 8, 2016" c132a6e869cd171e403784c172961471733dce31,IN-VEHICLE PEDESTRIAN DETECTION USING STEREO VISION TECHNOLOGY,"IN-VEHICLE PEDESTRIAN DETECTION USING STEREO VISION TECHNOLOGY Wei Zhang, Ph.D., P.E. Highway Research Engineer, Office of Safety Research & Development, HRDS-10 Federal Highway Administration 6300 Georgetown Pike, McLean, VA 22101, USA, e-mail: Submitted to the 3rd International Conference on Road Safety and Simulation, September 14-16, 011, Indianapolis, USA" c1087c588960dd7c00a2b5feed57fbdb70d066f1,Quantifying cortical surface asymmetry via logistic discriminant analysis,"Quantifying Cortical Surface Asymmetry via Logistic Discriminant Analysis Moo K. Chung1,2, Daniel J. Kelley2, Kim M. Dalton2, Richard J. Davidon2,3 Department of Biostatistics and Medical Informatics Waisman Laboratory for Brain Imaging and Behavior Department of Psychology and Psychiatry University of Wisconsin, Madison, WI 53706, USA" c149626b93c8949fb8b181c6220d8e8e8a558f98,Robot Sequential Decision Making using LSTM-based Learning and Logical-probabilistic Reasoning,"Robot Sequential Decision Making using LSTM-based Learning and Logical-probabilistic Reasoning Saeid Amiri1 , Mohammad Shokrolah Shirazi2 , Shiqi Zhang1 SUNY Binghamton Cleveland State University" c1974d59d55b6ea57d4acb8fcdc4a10f19d3cfca,Dynamic Local Feature Analysis for Face Recognition,"Dynamic Local Feature Analysis for Face Recognition Johnny NG and Humphrey CHEUNG Titanium Technology Research Centre 0/F, Tianjin Building, 167 Connaught Road West, Hong Kong, PR China {Johnny.ng," c158009b33989c6677f1daa3f5926887c9471c5e,Controlling Complex Systems and Developing Dynamic Technology,"Electronic Thesis and Dissertations Peer Reviewed Title: Controlling Complex Systems and Developing Dynamic Technology Author: Avizienis, Audrius Victor Acceptance Date: Series: UCLA Electronic Theses and Dissertations Degree: Ph.D., Chemistry 0153UCLA Advisor(s): Gimzewski, James K Committee: Kodambaka, Suneel, Baugh, Delroy A Permalink: https://escholarship.org/uc/item/35c10822" c18d80d00f2a7107bfe780eeec21b51a634ea925,Computational perspectives on the other-race effect,"This article was downloaded by: [The University of Texas at Dallas], [Alice O'Toole] On: 25 July 2013, At: 12:46 Publisher: Routledge Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, Visual Cognition Publication details, including instructions for authors nd subscription information: http://www.tandfonline.com/loi/pvis20 Computational perspectives on the other-race effect Alice J. O'Toole a & Vaidehi Natu a School of Behavioural and Brain Sciences , University of Texas at Dallas , Richardson , TX , USA Published online: 14 Jun 2013. To cite this article: Visual Cognition (2013): Computational perspectives on the other- race effect, Visual Cognition, DOI: 10.1080/13506285.2013.803505 To link to this article: http://dx.doi.org/10.1080/13506285.2013.803505 PLEASE SCROLL DOWN FOR ARTICLE" c1b2668186fcd01b3c0e93a9a0a68e3eb88a09ab,Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360 ^\circ ∘ Panoramic Imagery,"Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 60◦ Panoramic Imagery Gr´egoire Payen de La Garanderie, Amir Atapour Abarghouei, nd Toby P. Breckon Department of Computer Science Durham University" c1c34a3ab7815af1b9bcaf2822e4b9da8505f915,Image transmorphing with JPEG,"IMAGE TRANSMORPHING WITH JPEG Lin Yuan and Touradj Ebrahimi Multimedia Signal Processing Group, EPFL, Lausanne, Switzerland" c1059a702f53c44bb26d3313964e811adf01d9b4,Low and mid-level features for target detection in satellite images,"ISSN: 2278 – 1323 International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) Volume 2, Issue 2, February 2013 Low and mid-level features for target detection in satellite images Rajani.D.C" c165003060eeb01e05800a5ee4cd327f1e0bf5e3,SDC-Net: Video Prediction Using Spatially-Displaced Convolution,"SDC-Net: Video prediction using spatially-displaced convolution Fitsum A. Reda, Guilin Liu, Kevin J. Shih, Robert Kirby, Jon Barker, David Tarjan, Andrew Tao, and Bryan Catanzaro Nvidia Corporation, Santa Clara CA 95051, USA Fig. 1. Frame prediction on a YouTube video frame featuring a panning camera. Left to right: Ground-truth, MCNet [34] result, and our SDC-Net result. The SDC-Net predicted frame is sharper and preserves fine image details, while color distortion and lurriness is seen in the tree and text in MCNet’s predicted frame." c1b90cf91837628c430a796e7b6be6d8c010cc43,Local Steerable Pyramid Binary Pattern Sequence LSPBPS for face recognition method,"World Academy of Science, Engineering and Technology International Journal of Electronics and Communication Engineering Vol:3, No:11, 2009 Local Steerable Pyramid Binary Pattern Sequence LSPBPS for face recognition method Mohamed El Aroussi, Mohammed El Hassouni, Sanaa Ghouzali, Mohammed Rziza, and Driss Aboutajdine" 1eb4ea011a3122dc7ef3447e10c1dad5b69b0642,Contextual Visual Recognition from Images and Videos,"Contextual Visual Recognition from Images and Videos Georgia Gkioxari Jitendra Malik Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2016-132 http://www.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-132.html July 19, 2016" 1e1334f76177ddf3ddc35f7359a1e04b65438dc4,What Is the Most Efficient Way to Select Nearest Neighbor Candidates for Fast Approximate Nearest Neighbor Search ?,"013 IEEE International Conference on Computer Vision 013 IEEE International Conference on Computer Vision What Is the Most Efficient Way to Select Nearest Neighbor Candidates for Fast Approximate Nearest Neighbor Search? Masakazu Iwamura, Tomokazu Sato and Koichi Kise Graduate School of Engineering, Osaka Prefecture University {masa," 1ecb56e7c06a380b3ce582af3a629f6ef0104457,View-invariant face detection method based on local PCA cells,"List of Contents Vol.8 Contents of Journal of Advanced Computational Intelligence and Intelligent Informatics Volume 8 Vol.8 No.1, January 2004 Editorial: o Special Issue on Selected Papers from Humanoid, Papers: o Dynamic Color Object Recognition Using Fuzzy Nano-technology, Information Technology, Communication and Control, Environment, and Management (HNICEM’03). Elmer P. Dadios Papers: o A New Way of Discovery of Belief, Desire and Intention in the BDI Agent-Based Software Modeling . Chang-Hyun Jo o Integration of Distributed Robotic Systems" 1e1a67a78badc619b2f9938e4a03922dcbee0fb6,Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model,"Food/Non-food Image Classification and Food Categorization using Pre-Trained GoogLeNet Model Ashutosh Singla Lin Yuan Touradj Ebrahimi Multimedia Signal Processing Group Ecole Polytechnique Fédérale de Lausanne Station 11, 1015 Lausanne, Switzerland" 1eda03469d860ac725122bd27faaae6b2cb47d0d,Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction,"Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction Hyeonwoo Noh Paul Hongsuck Seo Bohyung Han {shgusdngogo, hsseo, Department of Computer Science and Engineering, POSTECH, Korea" 1ef46f7bb7463ead4369a796435106da63578733,Shamann: Shared Memory Augmented Neural Networks,"Under review as a conference paper at ICLR 2019 SHAMANN: SHARED MEMORY AUGMENTED NEURAL NETWORKS Anonymous authors Paper under double-blind review" 1e8394cc9fe7c2392aa36fb4878faf7e78bbf2de,Zero-Shot Object Recognition System Based on Topic Model,"TO APPEAR IN IEEE THMS Zero-Shot Object Recognition System ased on Topic Model Wai Lam Hoo and Chee Seng Chan" 1e1a3ee9626c740be78f9c5f75f9c4d7edc45666,Estimating the Natural Illumination Conditions from a Single Outdoor Image,E-mail: 1e6a26deea0a38310368d9c2a6dadc317b50bdf8,Joint Attention in Autonomous Driving (JAAD),"Joint Attention in Autonomous Driving (JAAD) Iuliia Kotseruba, Amir Rasouli and John K. Tsotsos {yulia_k, aras," 1e82a8965f08e8d38b16f39412e6e3c456f6f22e,Social force model aided robust particle PHD filter for multiple human tracking,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 1e2087908e6ce34032c821c7fb6629f2d0733086,Affective Embodied Conversational Agents for Natural Interaction,"Affective Embodied Conversational Agents for Natural Interaction Eva Cerezo, Sandra Baldassarri, Isabelle Hupont and Francisco J. Seron Advanced Computer Graphics Group (GIGA) Computer Science Department, Engineering Research Institute of Aragon(I3A), University of Zaragoza, Spain . Introduction Human computer intelligent interaction is an emerging field aimed at providing natural ways for humans to use computers as aids. It is argued that for a computer to be able to interact with humans it needs to have the communication skills of humans. One of these skills is the affective aspect of communication, which is recognized to be a crucial part of human intelligence and has been argued to be more fundamental in human behaviour and success in social life than intellect (Vesterinen, 2001; Pantic, 2005). Embodied conversational agents, ECAs (Casell et al., 2000), are graphical interfaces capable of using verbal and non-verbal modes of communication to interact with users in computer- ased environments. These agents are sometimes just as an animated talking face, may be displaying simple facial expressions and, when using speech synthesis, with some kind of lip synchronization, and sometimes they have sophisticated 3D graphical representation, with complex body movements and facial expressions." 1e058b3af90d475bf53b3f977bab6f4d9269e6e8,Manifold Relevance Determination,"Manifold Relevance Determination Andreas C. Damianou Dept. of Computer Science & Sheffield Institute for Translational Neuroscience, University of Sheffield, UK Carl Henrik Ek KTH – Royal Institute of Technology, CVAP Lab, Stockholm, Sweden Michalis K. Titsias Wellcome Trust Centre for Human Genetics, Roosevelt Drive, Oxford OX3 7BN, UK Neil D. Lawrence Dept. of Computer Science & Sheffield Institute for Translational Neuroscience, University of Sheffield, UK" 1ed6a05a226cb0d09afd76ff9b7560c404d8eb49,D4g: Pre-completion report on exemplar,"D4g: Pre-completion report on exemplar Workpackage 4 Deliverable Date: 31th August 2007" 1e2b8778cfe44de4bbe4a099ee7cdff5c2ca5f38,Attention to Scale: Scale-Aware Semantic Image Segmentation,"Attention to Scale: Scale-aware Semantic Image Segmentation Liang-Chieh Chen∗ {yangyi05, wangjiang03, Yi Yang, Jiang Wang, Wei Xu Alan L. Yuille" 1efaa128378f988965841eb3f49d1319a102dc36,Hierarchical binary CNNs for landmark localization with limited resources,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Hierarchical binary CNNs for landmark localization with limited resources Adrian Bulat and Georgios Tzimiropoulos" 1eeca84f33079c6d7a95daf8994370b2d7a93443,Fingertip Detection and Tracking for Recognition of Air-Writing in Videos,"Fingertip Detection and Tracking for Recognition of Air-Writing in Videos Sohom Mukherjeea, Sk. Arif Ahmedb, Debi Prosad Dograc, Samarjit Kard and Partha Pratim Roye Department of Electrical Engineering, National Institute of Technology Durgapur, Durgapur-713209, Indiaa National Institute of Technology Durgapur, Durgapur-713209, Indiab,d Department of Mathematics, School of Electrical Science, Indian Institute of Technology Bhubaneswar, Bhubaneswar-751013, Indiac Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee-247667, Indiae Email addresses:" 1e5edbd39b4c61f785515e117a74e2d280aefbe7,The urrent tate and TRL ssessment of eople racking echnology for ideo urveillance pplications,"The Furrent Vtate and TRL Dssessment of Seople Wracking Wechnology for Yideo Vurveillance Dpplications Prepared by: Diego MacriniVafa Khoshaein, Ghazal Moradian, Chris Whitten,Dmitry O. Gorodnichy, Robert Laganiere Canada Border Services Agency %HQWOH\$YHQXH Ottawa ON Canada K1A 0L8 URMHFW3673%,20 Scientific Authority: Pierre Meunier DRDC Centre for Security Science 613-992-0753 The scientific or technical validity of this Contract Report is entirely the responsibility of the Contractor and the contents do not necessarily have the approval or endorsement of the Department of National Defence of Canada. Defence Research and Development Canada  &RQWUDFW5HSRUW" 1e7ae86a78a9b4860aa720fb0fd0bdc199b092c3,A Brief Review of Facial Emotion Recognition Based on Visual Information,"Article A Brief Review of Facial Emotion Recognition Based on Visual Information Byoung Chul Ko ID Department of Computer Engineering, Keimyung University, Daegu 42601, Korea; Tel.: +82-10-3559-4564 Received: 6 December 2017; Accepted: 25 January 2018; Published: 30 January 2018" 1e1dc91c2ac3ad0ae44941e711aed193231c3335,Universal Adversarial Perturbations Against Semantic Image Segmentation,"Universal Adversarial Perturbations Against Semantic Image Segmentation Bosch Center for Artificial Intelligence, Robert Bosch GmbH Jan Hendrik Metzen Mummadi Chaithanya Kumar University of Freiburg Thomas Brox University of Freiburg Bosch Center for Artificial Intelligence, Robert Bosch GmbH Volker Fischer" 1e02dfeb93e8fd8753d2e69baf705baf8996cb81,"Online Object Tracking, Learning and Parsing with And-Or Graphs","ARXIV VERSION Online Object Tracking, Learning and Parsing with And-Or Graphs Tianfu Wu, Yang Lu and Song-Chun Zhu" 1e64b2d2f0a8a608d0d9d913c4baee6973995952,Dominant and Complementary Multi-Emotional Facial Expression Recognition Using C-Support Vector Classification,"DOMINANT AND COMPLEMENTARY MULTI- EMOTIONAL FACIAL EXPRESSION RECOGNITION USING C-SUPPORT VECTOR CLASSIFICATION Christer Loob, Pejman Rasti, Iiris Lusi, Julio C. S. Jacques Junior, Xavier Baro, Sergio Escalera, Tomasz Sapinski, Dorota Kaminska and Gholamreza Anbarjafari" 1e2d9ea6fe9c50a5c26a629b94446250e1be4e7d,The Freiburg Groceries Dataset,"The Freiburg Groceries Dataset Philipp Jund, Nichola Abdo, Andreas Eitel, Wolfram Burgard" 1ea2a53a6cb9c08312276a2f0646935d5fab5ed3,Real-time Crowd Tracking using Parameter Optimized Mixture of Motion Models,"Noname manuscript No. (will be inserted by the editor) Real-time Crowd Tracking using Parameter Optimized Mixture of Motion Models Aniket Bera · David Wolinski · Julien Pettr´e · Dinesh Manocha Received: date / Accepted: date" 1ee9598f88f40dabb70965a74eed87aedb276171,Face recognition using Histogram of co-occurrence Gabor phase patterns,"978-1-4799-2341-0/13/$31.00 ©2013 IEEE ICIP 2013" 1ee27c66fabde8ffe90bd2f4ccee5835f8dedbb9,9 Entropy Regularization,"Entropy Regularization Yves Grandvalet Yoshua Bengio The problem of semi-supervised induction consists in learning a decision rule from labeled and unlabeled data. This task can be undertaken by discriminative methods, provided that learning criteria are adapted consequently. In this chapter, we moti- vate the use of entropy regularization as a means to bene(cid:12)t from unlabeled data in the framework of maximum a posteriori estimation. The learning criterion is derived from clearly stated assumptions and can be applied to any smoothly parametrized model of posterior probabilities. The regularization scheme favors low density sep- ration, without any modeling of the density of input features. The contribution of unlabeled data to the learning criterion induces local optima, but this problem an be alleviated by deterministic annealing. For well-behaved models of posterior probabilities, deterministic annealing EM provides a decomposition of the learning problem in a series of concave subproblems. Other approaches to the semi-supervised problem are shown to be close relatives or limiting cases of entropy regularization. A series of experiments illustrates the good behavior of the algorithm in terms of performance and robustness with respect to the violation of the postulated low den- sity separation assumption. The minimum entropy solution bene(cid:12)ts from unlabeled data and is able to challenge mixture models and manifold learning in a number of" 1ebcf5dbb37fcd369530b0ee4df5d4a60f756f3e,Unsupervised High-level Feature Learning by Ensemble Projection for Semi-supervised Image Classification and Image Clustering,"High-level Feature Learning by Ensemble Projection for Image Classification with Limited Annotations $ Dengxin Dai∗, Luc Van Gool Computer Vision Lab, ETH Z¨urich, CH-8092, Switzerland" 1e15c5cba95cbb475ddb67157fdd480f5253502e,Face Recognition under Varying Lighting Conditions : A Combination of Weber-face and Local Directional Pattern for Feature Extraction and Support Vector Machines for Classification,"Journal of Information Hiding and Multimedia Signal Processing Ubiquitous International ©2017 ISSN 2073-4212 Volume 8, Number 5, September 2017 Face Recognition under Varying Lighting Conditions: A Combination of Weber-face and Local Directional Pattern for Feature Extraction and Support Vector Machines for Classification Chin-Shiuh Shieh1,5, Liyun Chang4,∗, and Tsair-Fwu Lee1,3,5,∗ Chi-Kien Tran1,2, Chin-Dar Tseng1, Pei-Ju Chao1,3 Medical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Applied Sciences, Kaohsiung 80778, Taiwan, ROC Center for Information Technology, Hanoi University of Industry, Hanoi, Vietnam Department of Radiation Oncology, Kaohsiung Chang Gung Memorial Hospital, Department of Medical Imaging and Radiological Sciences, I-Shou University, Kaohsiung 83305,Taiwan, ROC Kaohsiung 82445,Taiwan, ROC 5 Graduate Institute of Clinical Medicine, Kaohsiung Medical University, Corresponding authors: Kaohsiung 807,Taiwan, ROC" 1e9c3d0d87e09ea359ce1e31114b677d627bf9e7,Rapid Stress System Drives Chemical Transfer of Fear from Sender to Receiver,"RESEARCH ARTICLE Rapid Stress System Drives Chemical Transfer of Fear from Sender to Receiver Jasper H. B. de Groot1*, Monique A. M. Smeets1, Gün R. Semin1,2,3 Department of Social and Organizational Psychology, Faculty of Social and Behavioral Sciences, Utrecht University, Utrecht, the Netherlands, 2 Department of Psychology, Koç University, Istanbul, Turkey, Instituto Superior de Psicologia Aplicada (ISPA), Instituto Universitário, Lisbon, Portugal 11111" 1e1e35284591b6a69569c48b3677b6f4409c5edc,Matrix Product State for Feature Extraction of Higher-Order Tensors,"Matrix Product State for Feature Extraction of Higher-Order Tensors Johann A. Bengua1, Ho N. Phien1, Hoang D. Tuan1 and Minh N. Do2 een applied in neuroscience, pattern analysis, image classifi- ation and signal processing [7], [8], [9]. The central concept of using the TD is to decompose a large multidimensional tensor into a set of common factor matrices and a single core tensor which is considered as reduced features of the original tensor in spite of its lower dimension [7]. In practice, the TD is often performed in conjunction with some constraints, e.g. nonnegativity, orthogonality, etc., imposed on the common factors in order to obtain a better feature core tensor [7]. However, constraints like orthogonality often leads to an NP- hard computational problem [10]. Practical application of the TD is normally limited to small-order tensors. This is due to the fact the TD core tensor preserves the higher- order structure of the original tensor, with its dimensionality remaining fairly large in order to capture relevant interactions etween components of the tensor [2]." 1e17202d6de18d5e1965edce5fee79744b717d0b,MIML-FCN+: Multi-Instance Multi-Label Learning via Fully Convolutional Networks with Privileged Information,"MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information Hao Yang*, Joey Tianyi Zhou**, Jianfei Cai*, and Yew Soon Ong* *School of Computer Science and Engineering, NTU, Singapore." 1e21b925b65303ef0299af65e018ec1e1b9b8d60,Unsupervised Cross-Domain Image Generation,"Under review as a conference paper at ICLR 2017 UNSUPERVISED CROSS-DOMAIN IMAGE GENERATION Yaniv Taigman, Adam Polyak & Lior Wolf Facebook AI Research Tel-Aviv, Israel" 1e5c6c9fa9ba089931cfb2bc81e4368a4db5dd2d,Multi- View Fusion for Action Recognition in Child-Robot Interaction,"978-1-4799-7061-2/18/$31.00 ©2018 IEEE ICIP 2018 #2Kinect #1Kinect #3Multi-view action recognition systemSenseActDecisionSpeakRec.ActionActFig.1:Multi-viewactionrecognitionsystemforchild-robotinteraction.presentspontaneousbehaviorandaninformalwayofcommunica-tion.Inaddition,thesameactionscanbeperformedinavarietyofwaysandawidespectrum,furthercomplicatingtherecognitionofactions.Althoughhumanactionrecognitionisapopularproblemwithmanyproposedmethods[8–13],therequirementsofmulti-viewac-tionrecognitiondiffersignificantlyasithastotakeintoaccountbothactionrecognitionthatresultsfromsingleviewsandalsothefusionamongtheresultinginformationfromthedifferentstreams[14,15].Incross-viewactionrecognitionworksitisattemptedtoshareknowledgefortheactionamongthedifferentsetupviews.Forexample,in[16]aspecificviewistreatedasthetargetdomainandtheotherviewsassourcedomainsinordertoformulateacross-viewlearningframework.Inotherapproaches,theknowledgeofactionsistransferredfromthedifferentviewsinasinglecanoni-calview[17].In[18]itisproposedtolearnview-invariantfeaturesrobusttoviewvariationsusingdeepmodels.Inthefieldofmulti-viewactionrecognition,anewglobalrepresentationthatiscalledmulti-viewsupervectorhasalsobeenproposedinordertoenhancerecognitionperformance[19].Finally,anotherinterestingapproachispresentedin[20]whereitisattemptedtotransferthelow-levelfeaturesintoahigh-levelsemanticspaceandamulti-tasklearningapproachforjointactionmodelingisexamined.Inthispaperwedevelopamulti-viewactionrecognitionsystemsuitableforCRI.Themaincontributionsofthispapercanbesum-marizedasfollows:1)Single-viewmethodsareexploredinordertocreaterobustactionrecognitionmodelsforparticularusers,i.e.children,underdifficulttaskswithfewtrainingdata.2)Methodsforthefusionofinformationfromdifferentstreamsinamulti-viewsys-temareproposedtoenhanceactionrecognitionduringCRI.3)Themulti-viewactionrecognitionsystemisintegratedinroboticplat-" 1e146982a7b088e7a3790d2683484944c3b9dcf7,Video Person Re-Identification for Wide Area Tracking based on Recurrent Neural Networks,"Video Person Re-Identification for Wide Area Tracking based on Recurrent Neural Networks McLaughlin, N., Martinez del Rincon, J., & Miller, P. (2017). Video Person Re-Identification for Wide Area Tracking based on Recurrent Neural Networks. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/TCSVT.2017.2736599 Published in: IEEE Transactions on Circuits and Systems for Video Technology Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights Copyright IEEE 2017. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to" 1ee3b4ba04e54bfbacba94d54bf8d05fd202931d,Celebrity Face Recognition using Deep Learning,"Indonesian Journal of Electrical Engineering and Computer Science Vol. 12, No. 2, November 2018, pp. 476~481 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v12.i2.pp476-481  476 Celebrity Face Recognition using Deep Learning Nur Ateqah Binti Mat Kasim1, Nur Hidayah Binti Abd Rahman2, Zaidah Ibrahim3, Nur Nabilah Abu Mangshor4 ,2,3Faculty of Computer and Mathematical Sciences, UniversitiTeknologi MARA (UiTM), Faculty of Computer and Mathematical Sciences, UniversitiTeknologi MARA (UiTM), Shah Alam, Selangor, Malaysia Campus Jasin, Melaka, Malaysia Article Info Article history: Received May 29, 2018 Revised Jul 30, 2018 Accepted Aug 3, 2018 Keywords: AlexNet Convolutional neural network Deep learning" 1e2d965df330a72b3426279f9327f77330c2ee64,Simultaneous Detection and Segmentation of Pedestrians using Top-down and Bottom-up Processing,"Simultaneous Detection and Segmentation of Pedestrians using Top-down and Bottom-up Processing ∗ Vinay Sharma James W. Davis Dept. of Computer Science and Engineering Ohio State University Columbus OH 43210 USA" 1e8a265ec741584e851b83b5efc00351048bbe3f,Real Time Human Detection and Localization Using Consumer Grade Camera and Commercial UAV,"Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 7 November 2018 doi:10.20944/preprints201811.0156.v1 Article Real Time Human Detection and Localization Using Consumer Grade Camera and Commercial UAV Nemi Bhattarai 1,*, Tai Nakamura 1 and Chitrini Mozumder 1,* Remote Sensing and Geographic Information Systems, School of Engineering and Technology, Asian Institute of Technology, Thailand; (T.N.) * Correspondence: (N.B); (C.M); Tel.: +66-099-421-7492" 1eec03527703114d15e98ef9e55bee5d6eeba736,Automatic identification of persons in TV series S UBMITTED,"UNIVERSITÄT KARLSRUHE (TH) FAKULTÄT FÜR INFORMATIK INTERACTIVE SYSTEMS LABS Prof. Dr. A. Waibel DIPLOMA THESIS Automatic identification of persons in TV series SUBMITTED BY Mika Fischer MAY 2008 ADVISORS M.Sc. Hazım Kemal Ekenel Dr.-Ing. Rainer Stiefelhagen" 1e4c717a8a5eed5c3385b77641ebe3d8c4ceb3ac,An efficient algorithm for maximal margin clustering,"J Glob Optim DOI 10.1007/s10898-011-9691-4 An efficient algorithm for maximal margin clustering Jiming Peng · Lopamudra Mukherjee · Vikas Singh · Dale Schuurmans · Linli Xu Received: 29 April 2009 / Accepted: 5 February 2011 © Springer Science+Business Media, LLC. 2011" 1ef1f33c48bc159881c5c8536cbbd533d31b0e9a,Identity-based Adversarial Training of Deep CNNs for Facial Action Unit Recognition,"Z. ZHANG ET AL.: ADVERSARIAL TRAINING FOR ACTION UNIT RECOGNITION Identity-based Adversarial Training of Deep CNNs for Facial Action Unit Recognition Zheng Zhang Shuangfei Zhai Lijun Yin Department of Computer Science State University of New York at Binghamton NY, USA." 1e1e66783f51a206509b0a427e68b3f6e40a27c8,Semi-supervised estimation of perceived age from face images,"SEMI-SUPERVISED ESTIMATION OF PERCEIVED AGE FROM FACE IMAGES VALWAY Technology Center, NEC Soft, Ltd., Tokyo, Japan Kazuya Ueki Masashi Sugiyama Keywords:" 1ebf201b34d9687fa17e336a608ab43e466ca13f,Detecting Parts for Action Localization.,"Nicolas Chesneau Grégory Rogez Karteek Alahari Cordelia Schmid CHESNEAU ET AL.: DETECTING PARTS FOR ACTION LOCALIZATION Detecting Parts for Action Localization Inria∗" 1eadafc27372b33a73eca062438a58d4280fd3a1,DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images,"DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images Wei Shen, Kai Zhao, Yuan Jiang, Yan Wang, Xiang Bai and Alan Yuille" 09dbdc05f0f093ed71f6f29abbc516c58c75ad2a,Zero Shot Hashing,"Zero Shot Hashing Shubham Pachori Electrical Engineering Shanmuganathan Raman Electrical Engineering & Indian Institute of Technology Gandhinagar Computer Science and Engineering Gandhinagar, Gujarat 382355 Indian Institute of Technology Gandhinagar Email: shubham Gandhinagar, Gujarat 382355 Email:" 096e68f8d632f4363056d54a7de9c59d66b806d8,Impaired visuocortical discrimination learning of socially conditioned stimuli in social anxiety.,"Impaired Visuocortical Discrimination Learning of Socially Conditioned Stimuli in Social Anxiety Lea M. Ahrens1, Andreas Mühlberger2, Paul Pauli1, & Matthias J. Wieser1 Department of Psychology I, University of Würzburg, Germany Department of Clinical Psychology and Psychotherapy, University of Regensburg, Germany Address for correspondence: Lea M. Ahrens, University of Würzburg, Department of Psychology, Biological Psychology, Clinical Psychology, and Psychotherapy, Marcusstr. 9-11, D-97070 Würzburg, Phone.: +49 931 31-81929, Fax: +49 931 31-82733, Running title: Social Conditioning in Social Anxiety Words: 4995 (+ 8 place marker) © The Author (2014). Published by Oxford University Press. For Permissions, please email:" 09750c9bbb074bbc4eb66586b20822d1812cdb20,Estimation of the neutral face shape using Gaussian Mixture Models,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 09a6261c3334471bb0bc1a173aff672afe963ae3,Key-Pose Prediction in Cyclic Human Motion,"Key-Pose Prediction in Cyclic Human Motion Multimedia Computing and Computer Vision Lab, University of Augsburg Dan Zecha Rainer Lienhart" 09251a324dc4865732e2ead50334bfb906f8ffb4,Beyond Text based sentiment analysis : Towards multi-modal systems,"Springer Cognitive Computation manuscript No. (will be inserted by the editor) Beyond Text based sentiment analysis: Towards multi-modal systems Soujanya Poria · Amir Hussain · Erik Cambria the date of receipt and acceptance should be inserted later" 09137e3c267a3414314d1e7e4b0e3a4cae801f45,Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN,"Noname manuscript No. (will be inserted by the editor) Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN Dan Ma · Bin Liu · Zhao Kang · Jiayu Zhou · Jianke Zhu · Zenglin Xu Received: date / Accepted: date" 09ba6b87736fa29aae88c5b4cf30f25188e4c6ef,Gaze Estimation in the 3 D Space Using RGB-D sensors Towards Head-Pose And User Invariance,"International Journal of Computer Vision (Accepted Manuscript) The final publication is available at Springer via http://dx.doi.org/10.1007/s11263-015-0863-4 Gaze Estimation in the 3D Space Using RGB-D sensors Towards Head-Pose And User Invariance Kenneth A. Funes-Mora · Jean-Marc Odobez Received: 19 November 2014 / Accepted: 23 September 2015" 09a99ca583b0eff0a34de32b4eed23d6d8ff14c2,Domain-Independent Captioning of Domain-Specific Images,"Proceedings of the NAACL HLT 2013 Student Research Workshop, pages 69–76, Atlanta, Georgia, 13 June 2013. c(cid:13)2013 Association for Computational Linguistics" 0965a62c9c354d2c7175e313ade9e38120f1bd4e,Efficient Face Detection Method using Modified Hausdorff Distance Method with C 4 . 5 Classifier and Canny Edge Detection,"International Journal of Computer Applications (0975 – 8887) Volume 123 – No.10, August 2015 Efficient Face Detection Method using Modified Hausdorff Distance Method with C4.5 Classifier and Canny Edge Detection Neelima Singh Research Scholar Computer Science and Engineering Department Samrat Ashok Technological Institute, Vidisha, M. P. Satish Pawar Assistant Professor Computer Science and Engineering Department Samrat Ashok Technological Institute, Vidisha, M. P. Yogendra Kumar Jain Head of Department Computer Science and" 09d78009687bec46e70efcf39d4612822e61cb8c,Consistent Re-identification in a Camera Network,"Consistent Re-identification in a Camera Network Abir Das(cid:2), Anirban Chakraborty(cid:2), and Amit K. Roy-Chowdhury(cid:2)(cid:2) Dept. of Electrical Engineering, University of California, Riverside, CA 92521, USA" 0994916f67fd15687dd5d7e414becb1cd77129ac,Multi Class Different Problem Solving Using Intelligent Algorithm,"SIVAKUMAR R, Dr.M.SRIDHAR / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 2, Issue4, July-August 2012, pp.1782-1785 Multi Class Different Problem Solving Using Intelligent Algorithm SIVAKUMAR R, 2Dr.M.SRIDHAR Research Scholar Dept of ECE BHARATH UNIVERSITY India Dept of ECE BHARATH UNIVERSITY India" 09d9d9d153119558e83643f0097ffb87e1037649,Face Recognition and Verification Using Artificial Neural Network,"©2010 International Journal of Computer Applications (0975 – 8887) Volume 1 – No. 14 Face Recognition and Verification Using Artificial Neural Network Ms. S. S.Ranawade Maharashtra Institute Technology, Pune 05 / nonface images. We solve" 09e15bb266da86d0a9525d2a94ac0b38f0b53b88,Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts,"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts Xianjie Chen1, Roozbeh Mottaghi2, Xiaobai Liu1, Sanja Fidler3, Raquel Urtasun3, Alan Yuille1 University of California, Los Angeles 2Stanford University 3University of Toronto" 09222c50d8ffcc74bbb7462400bd021772850bba,Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation,"Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez, and Stephen Gould" 09eaa332ddcd036b0f0950bbdb3624072f105a3b,When appearance does not match accent: neural correlates of ethnicity-related expectancy violations,"Social Cognitive and Affective Neuroscience, 2017, 507–515 doi: 10.1093/scan/nsw148 Advance Access Publication Date: 19 October 2016 Original article When appearance does not match accent: neural orrelates of ethnicity-related expectancy violations Karolina Hansen,1 Melanie C. Steffens,2 Tamara Rakic,3 and Holger Wiese4 University of Warsaw, Warsaw, Poland, 2University of Koblenz-Landau, Landau, Germany, 3Lancaster University, Lancaster, UK, and 4Durham University, Durham, UK Correspondence should be addressed to Karolina Hansen, Faculty of Psychology, University of Warsaw, Stawki 5/7, 00-183 Warszawa, Poland. E-mail:" 0917de8a3be50f2a813e7b77fc53b81125a58acb,Video based head detection and tracking surveillance system,978-1-4673-0024-7/10/$26.00 ©2012 IEEE 2832 09d08e543a9b2fc350cb37e47eb087935c12be16,"A Multimodal, Full-Surround Vehicular Testbed for Naturalistic Studies and Benchmarking: Design, Calibration and Deployment.","A Multimodal, Full-Surround Vehicular Testbed for Naturalistic Studies nd Benchmarking: Design, Calibration and Deployment Akshay Rangesh1, Kevan Yuen1, Ravi Kumar Satzoda1, Rakesh Nattoji Rajaram1, Pujitha Gunaratne2, and Mohan M. Trivedi1 Laboratory for Intelligent and Safe Automobiles (LISA), UC San Diego Toyota Collaborative Safety Research Center (CSRC) in autonomous" 092597b8e0f31be1671025cea1b9fd28a48e04bc,Supervised Person Re-ID based on Deep Hand-crafted and CNN Features, 09e3967a34cca8dc0f00c9ee7a476a96812a55e0,1 Machine Learning Methods for Social Signal Processing,"Machine Learning Methods for Social Signal Processing Ognjen Rudovic, Mihalis A. Nicolaou and Vladimir Pavlovic Introduction In this chapter we focus on systematization, analysis, and discussion of recent trends in machine learning methods for Social signal processing (SSP)(Pentland 007). Because social signaling is often of central importance to subconscious de- ision making that affects everyday tasks (e.g., decisions about risks and rewards, resource utilization, or interpersonal relationships) the need for automated un- derstanding of social signals by computers is a task of paramount importance. Machine learning has played a prominent role in the advancement of SSP over the past decade. This is, in part, due to the exponential increase of data avail- bility that served as a catalyst for the adoption of a new data-driven direction in ffective computing. With the dif‌f‌iculty of exact modeling of latent and complex physical processes that underpin social signals, the data has long emerged as the means to circumvent or supplement expert- or physics-based models, such as the deformable musculo-sceletal models of the human body, face or hands and its movement, neuro-dynamical models of cognitive perception, or the models of the human vocal production. This trend parallels the role and success of machine learning in related areas, such as computer vision, c.f., (Poppe 2010, Wright" 093b6af0e5f00f9578088a49822d8d500283cab0,Human visual behaviour for collaborative human-machine interaction,"Human Visual Behaviour for Collaborative Human-Machine Interaction Andreas Bulling Perceptual User Interfaces Group Max Planck Institute for Informatics Saarbr¨ucken, Germany Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components" 09f853ce12f7361c4b50c494df7ce3b9fad1d221,Random Forests for Real Time 3D Face Analysis,"myjournal manuscript No. (will be inserted by the editor) Random forests for real time 3D face analysis Gabriele Fanelli · Matthias Dantone · Juergen Gall · Andrea Fossati · Luc Van Gool Received: date / Accepted: date" 09da5ae17cf1bf382f69036a96ec953c18f676d4,Person Re-Identification using Deep Foreground Appearance Modelling,"Original citation: Watson, Gregory and Bhalerao, Abhir (2018) Person reidentification using deep foreground ppearance modeling.Journal of Electronic Imaging, 27 (05). 051215. doi:10.1117/1.jei.27.5.051215 Permanent WRAP URL: http://wrap.warwick.ac.uk/100807 Copyright and reuse: The Warwick Research Archive Portal (WRAP) makes this work by researchers of the University of Warwick available open access under the following conditions. Copyright © nd all moral rights to the version of the paper presented here belong to the individual uthor(s) and/or other copyright owners. To the extent reasonable and practicable the material made available in WRAP has been checked for eligibility before being made vailable. Copies of full items can be used for personal research or study, educational, or not-for profit purposes without prior permission or charge. Provided that the authors, title and full ibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way. Publisher’s statement: Citation format: Watson, Gregory and Bhalerao, Abhir Person reidentification using deep foreground" 09e64d9e0654fe5d472ef73b479364d31ab362f6,Automated Classification of Female Facial Beauty Using Learning Algorithms,"Automated Classification of Female Facial Beauty Using Learning Algorithms Hatice Gunes, Massimo Piccardi, Tony Jan Computer Vision Group -Faculty of Information Technology University of Technology, Sydney (UTS) PO Box 123 Broadway 2007 NSW - Australia e-mail:" 09f4e1064afffd8464e9fd558fc8ef7be5e33170,Spatial and Temporal Organization of the Individual Human Cerebellum,"Article Spatial and Temporal Organization of the Individual Human Cerebellum" 095ccb4e2e0f3934dc1aa51c685b2f54c8a6e588,Derivate-based Component-Trees for Multi-Channel Image Segmentation,"Derivate-based Component-Trees for Multi-Channel Image Segmentation Dominik Gutermuth+∗ Tobias B¨ottger+∗ +MVTec Software GmbH, Munich, Germany Technical University of Munich (TUM) April 20, 2018" 09df62fd17d3d833ea6b5a52a232fc052d4da3f5,Mejora de Contraste y Compensación en Cambios de la Iluminación,"ISSN: 1405-5546 Instituto Politécnico Nacional México Rivas Araiza, Edgar A.; Mendiola Santibañez, Jorge D.; Herrera Ruiz, Gilberto; González Gutiérrez, Carlos A.; Trejo Perea, Mario; Ríos Moreno, G. J. Mejora de Contraste y Compensación en Cambios de la Iluminación Instituto Politécnico Nacional Distrito Federal, México Disponible en: http://www.redalyc.org/articulo.oa?id=61509703 Cómo citar el artículo Número completo Más información del artículo Página de la revista en redalyc.org Sistema de Información Científica Red de Revistas Científicas de América Latina, el Caribe, España y Portugal Proyecto académico sin fines de lucro, desarrollado bajo la iniciativa de acceso abierto" 09ac8added26307b358b83884b55af29de8b5bf9,Learning to grasp objects with multiple contact points,"Learning to grasp objects with multiple contact points Quoc V. Le, David Kamm, Arda F. Kara, Andrew Y. Ng" 092f955f701b31f3e58adb57c57e39a4dcab9fcd,Weighted Additive Criterion for Linear Dimension Reduction,"Seventh IEEE International Conference on Data Mining Seventh IEEE International Conference on Data Mining Seventh IEEE International Conference on Data Mining Seventh IEEE International Conference on Data Mining Seventh IEEE International Conference on Data Mining Weighted Additive Criterion for Linear Dimension Reduction Jing Peng & Stefan Robila Computer Science Department, Montclair State University Montclair, NJ 07043" 09879f7956dddc2a9328f5c1472feeb8402bcbcf,Density estimation using Real NVP,"Published as a conference paper at ICLR 2017 DENSITY ESTIMATION USING REAL NVP Laurent Dinh∗ Montreal Institute for Learning Algorithms University of Montreal Montreal, QC H3T1J4 Jascha Sohl-Dickstein Google Brain Samy Bengio Google Brain" 092b64ce89a7ec652da935758f5c6d59499cde6e,Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments,"Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments Catalin Ionescu∗†‡, Dragos Papava∗‡, Vlad Olaru∗, Cristian Sminchisescu§∗" 098388c08ef7d23ab583819b793b0057c0396dc8,Low Rank Approximation using Error Correcting Coding Matrices,"Low Rank Approximation using Error Correcting Coding Matrices Shashanka Ubaru Arya Mazumdar Yousef Saad University of Minnesota-Twin Cities, MN USA" 09b0040ad09d61f3403c57c437c03271f8614add,HUMAN ACTIVITY RECOGNITION AND GYMNASTICS ANALYSIS THROUGH DEPTH IMAGERY by,"HUMAN ACTIVITY RECOGNITION AND GYMNASTICS ANALYSIS THROUGH DEPTH IMAGERY Brian J. Reily" 09fbfb566a8f2af9df4d3a1bf5df00d0693a22eb,Conformal Prediction for Automatic Face Recognition,"Proceedings of Machine Learning Research 60:1–20, 2017 Conformal and Probabilistic Prediction and Applications Conformal Prediction for Automatic Face Recognition Charalambos Eliades Harris Papadopoulos Computer Science and Engineering Department, Frederick University, 7 Y. Frederickou St., Palouriotisa, Nicosia 1036, Cyprus Editor: Alex Gammerman, Vladimir Vovk, Zhiyuan Luo, and Harris Papadopoulos" 09d954e980133014cb4dfe3f6b1444edaa099c97,Real-time self-adaptive deep stereo,"Real-time self-adaptive deep stereo Alessio Tonioni, Fabio Tosi, Matteo Poggi, Stefano Mattoccia and Luigi Di Stefano Department of Computer Science and Engineering (DISI) University of Bologna, Bologna, Italy" 09c019141b209401b76a35184c86bab6cd1fe6b9,3D Deformable Shape Reconstruction with Diffusion Maps,"TAO, MATUSZEWSKI: 3D RECONSTRUCTION WITH DIFFUSION MAPS D Deformable Shape Reconstruction with Diffusion Maps Lili Tao Bogdan J. Matuszewski Applied Digital Signal and Image Processing Research Centre University of Central Lancashire, UK" 091b4ad74ac5bec206604673506b19838d6a0c52,Person Re-identification by Saliency Learning,"|| Volume 2 ||Issue 10 ||MAY 2017||ISSN (Online) 2456-0774 INTERNATIONAL JOURNAL OF ADVANCE SCIENTIFIC RESEARCH AND ENGINEERING TRENDS Person Re-Identification By Saliency Learning Shaihenila P.G. Student, Computer Science & Engineering, Everest Educational Society's Group of Institutions, Aurangabad, India." 097f674aa9e91135151c480734dda54af5bc4240,Face Recognition Based on Multiple Region Features,"Proc. VIIth Digital Image Computing: Techniques and Applications, Sun C., Talbot H., Ourselin S. and Adriaansen T. (Eds.), 10-12 Dec. 2003, Sydney Face Recognition Based on Multiple Region Features Jiaming Li, Geoff Poulton, Ying Guo, Rong-Yu Qiao CSIRO Telecommunications & Industrial Physics Australia Tel: 612 9372 4104, Fax: 612 9372 4411, Email:" 09749e7b0ae6bd9ab37671fcc4f0e7a7bcf9ff2e,Perceptual enhancement of emotional mocap head motion: An experimental study,"Perceptual Enhancement of Emotional Mocap Head Motion: An Experimental Study Yu Ding Univeristy of Houston Houston, TX, USA Lei Shi Univeristy of Houston Houston, TX, USA Zhigang Deng Univeristy of Houston Houston, TX, USA" 0949f46d5db3169813ae23acafa345c6b8a37f08,When Slower Is Faster: On Heterogeneous Multicores for Reliable Systems,"When Slower is Faster: On Heterogeneous Multicores for Reliable Systems Tomas Hruby The Network Institute, VU University Amsterdam Herbert Bos Andrew S. Tanenbaum" 0956a3c628959afcf870f5d7ec581160a4aa5221,LIFEisGAME Prototype: A Serious Game about Emotions for Children with Autism Spectrum Disorders,"Volume 11, Number 3, 191 – 211 LIFEisGAME Prototype: A Serious Game about Emotions for Children with Autism Spectrum Disorders Samanta Alves1, António Marques2, Cristina Queirós∗1 and Verónica Orvalho3 Psychosocial Rehabilitation Laboratory, Faculty of Psychology and Educational Sciences, Porto University (Portugal) Psychosocial Rehabilitation Laboratory, School of Allied Health Sciences, Porto Polytechnic Institute (Portugal) Porto Interactive" 0971a5e835f365b6008177a867cfe4bae76841a5,Supervised Dictionary Learning by a Variational Bayesian Group Sparse Nonnegative Matrix Factorization,"Supervised Dictionary Learning by a Variational Bayesian Group Sparse Nonnegative Matrix Factorization Ivan Ivek" 0910a4c470a410fac446f4026f7c8ef512ae7427,Hierarchical Question-Image Co-Attention for Visual Question Answering,"Hierarchical Question-Image Co-Attention for Visual Question Answering Jiasen Lu∗, Jianwei Yang∗, Dhruv Batra∗† , Devi Parikh∗† Virginia Tech, † Georgia Institute of Technology {jiasenlu, jw2yang, dbatra," 09926ed62511c340f4540b5bc53cf2480e8063f8,Tubelet Detector for Spatio-Temporal Action Localization,"Action Tubelet Detector for Spatio-Temporal Action Localization Vicky Kalogeiton1,2 Philippe Weinzaepfel3 Vittorio Ferrari2 Cordelia Schmid1" 092d5bc60a21933abf98aa85ace8a9c85df16958,Implementing Randomized Matrix Algorithms in Parallel and Distributed Environments,"Implementing Randomized Matrix Algorithms in Parallel and Distributed Environments Jiyan Yang ∗ Xiangrui Meng † Michael W. Mahoney ‡" 092a02ed126f8151c03e15716b8c27d73533358b,MAD-Bayes: MAP-based Asymptotic Derivations from Bayes,"MAD-Bayes: MAP-based Asymptotic Derivations from Bayes Tamara Broderick UC Berkeley, Statistics Department Brian Kulis Ohio State University, CSE Department Michael I. Jordan UC Berkeley, Statistics Department and EECS Department" 09edf114f8764c82713f8dd35b1b32ad83ecaa17,Large-Margin Learning of Compact Binary Image Encodings,"MANUSCRIPT Large-margin Learning of Compact Binary Image Encodings Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Hengel" 094f5e36dae2602e179f2c1d95a616df3dbe967f,Bilinear classifiers for visual recognition,"Bilinear classifiers for visual recognition Hamed Pirsiavash Deva Ramanan Charless Fowlkes Department of Computer Science University of California at Irvine" 09cf3d036f84b6b3ac5244a2ecf8ac74f69de5d3,Integrating Graph Partitioning and Matching for Trajectory Analysis in Video Surveillance,"Integrating Graph Partitioning and Matching for Trajectory Analysis in Video Surveillance Liang Lin, Yongyi Lu, Yan Pan, Xiaowu Chen" 09e5f2f819a21162d833f356670a140cd555a740,Adaptive Algorithm and Platform Selection for Visual Detection and Tracking,"Adaptive Algorithm and Platform Selection for Visual Detection and Tracking Shu Zhang, Qi Zhu, and Amit K. Roy-Chowdhury" 09556420a7441bb5259fd6dc68af340f6ac15ade,Gradient boosting for distributional regression: faster tuning and improved variable selection via noncyclical updates,"Stat Comput DOI 10.1007/s11222-017-9754-6 Gradient boosting for distributional regression: faster tuning and improved variable selection via noncyclical updates Janek Thomas1 Adam Smith4 · Benjamin Hofner5 · Andreas Mayr2,3 · Bernd Bischl1 · Matthias Schmid3 · Received: 3 November 2016 / Accepted: 5 May 2017 © Springer Science+Business Media New York 2017" 096eb8b4b977aaf274c271058feff14c99d46af3,Multi-observation visual recognition via joint dynamic sparse representation,"REPORT DOCUMENTATION PAGE Form Approved OMB NO. 0704-0188 including for reviewing information, this collection of information is estimated to average 1 hour per response, the data needed, and completing and reviewing this collection of instructions, The public reporting burden Send comments searching existing data sources, gathering and maintaining to Washington regarding this burden estimate or any other aspect of Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA, 22202-4302. Headquarters Services, Directorate" 0930af7c2d6f02b5e81c2003f76451aaff957a65,A Comprehensive Analysis of Deep Regression,"DRAFT A Comprehensive Analysis of Deep Regression St´ephane Lathuili`ere, Pablo Mesejo, Xavier Alameda-Pineda, Member IEEE, and Radu Horaud" 17d84ca10607442a405f3c4c8b4572bdd79801c2,Expression robust 3D face recognition via mesh-based histograms of multiple order surface differential quantities,"EXPRESSION ROBUST 3D FACE RECOGNITION VIA MESH-BASED HISTOGRAMS OF MULTIPLE ORDER SURFACE DIFFERENTIAL QUANTITIES Huibin Li1,2, Di Huang1,2, Pierre Lemaire1,2, Jean-Marie Morvan1,3,4, Liming Chen1,2 Universit´e de Lyon, CNRS Ecole Centrale de Lyon, LIRIS UMR5205, F-69134, Lyon, France Universit´e Lyon 1, Institut Camille Jordan, 3 blvd du 11 Novembre 1918, F-69622 Villeurbanne - Cedex, France King Abdullah University of Science and Technology, GMSV Research Center, Bldg 1, Thuwal 23955-6900, Saudi Arabia" 171d7762137725839fe5292901fe90d91b74811d,SLAM Algorithm by using Global Appearance of Omnidirectional Images, 176bc3f528d3d87a7543e377f9b7e4c04b5a9408,Towards Estimating the Upper Bound of Visual-Speech Recognition: The Visual Lip-Reading Feasibility Database,"Towards Estimating the Upper Bound of Visual-Speech Recognition: The Visual Lip-Reading Feasibility Database Adriana Fernandez-Lopez, Oriol Martinez and Federico M. Sukno Department of Information and Communication Technologies, Pompeu Fabra University, Barcelona, Spain" 173657da03e3249f4e47457d360ab83b3cefbe63,HKU-Face : A Large Scale Dataset for Deep Face Recognition Final Report,"HKU-Face: A Large Scale Dataset for Deep Face Recognition Final Report Haicheng Wang 035140108 COMP4801 Final Year Project Project Code: 17007" 177cbeb83c3a0868b9a5c75cd74edf4b972cba80,Exact Primitives for Time Series Data Mining,"UNIVERSITY OF CALIFORNIA RIVERSIDE Exact Primitives for Time Series Data Mining A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Computer Science Abdullah Al Mueen March 2012 Dissertation Committee: Dr. Eamonn Keogh, Chairperson Dr. Vassilis Tsotras Dr. Stefano Lonardi" 17e769ef3d86e74c21f2616c7f7a6f20a4e2fbaa,Bag of Machine Learning Concepts for Visual Concept Recognition in Images,"Bag of Machine Learning Concepts for Visual Concept Recognition in Images vorgelegt vom Diplom-Mathematiker Alexander Binder us Berlin von der Fakult¨at IV – Elektrotechnik und Informatik der Technischen Universit¨at Berlin zur Erlangung des akademischen Grades Doktor der Naturwissenschaften – Dr. rer. nat. – genehmigte Dissertation Promotionsausschuss: Vorsitzender: . Gutachter: . Gutachter: . Gutachter: Prof. Dr. Olaf Hellwich Prof. Dr. Klaus-Robert M¨uller Prof. Dr. Volker Tresp" 174930cac7174257515a189cd3ecfdd80ee7dd54,Multi-view Face Detection Using Deep Convolutional Neural Networks,"Multi-view Face Detection Using Deep Convolutional Neural Networks Sachin Sudhakar Farfade Yahoo Mohammad Saberian inc.com Yahoo Li-Jia Li Yahoo" 17c5db2190e25a66ab7f4067f7f7b72893d01d3d,From the Lab to the Real World: Re-identification in an Airport Camera Network,"Real-World Re-Identification in an Airport Camera Network Yang Li Rensselaer Polytechnic Institute, Troy, NY Ziyan Wu Rensselaer Polytechnic Institute, Troy, NY Srikrishna Karanam Rensselaer Polytechnic Institute, Troy, NY Richard J. Radke Rensselaer Polytechnic Institute, Troy, NY" 1701ee9e9518a055e82e79f6425645c4797c19de,Supervised Hashing Using Graph Cuts and Boosted Decision Trees,"APPEARING IN IEEE TRANS. PATTERN ANALYSIS AND MACHINE INTELLIGENCE, FEB. 2015 Supervised Hashing Using Graph Cuts and Boosted Decision Trees Guosheng Lin, Chunhua Shen, Anton van den Hengel" 174b6d661b96840e27cd9435c2dbb8e538b2c8a6,Progressive Representation Adaptation for Weakly Supervised Object Localization,"Progressive Representation Adaptation for Weakly Supervised Object Localization Dong Li, Jia-Bin Huang, Yali Li, Shengjin Wang(cid:63) and Ming-Hsuan Yang" 17a995680482183f3463d2e01dd4c113ebb31608,Structured Label Inference for Visual Understanding,"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. X, NO. Y, MONTH Z Structured Label Inference for Visual Understanding Nelson Nauata, Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao and Greg Mori" 17dea513763c57dcd0e62085045fb5be6770c600,"Dynamic thread mapping for high-performance, power-efficient heterogeneous many-core systems","Summary: Dynamic Thread Mapping for High-Performance, Power-Efficient Heterogeneous Many-core Systems Guangshuo Liu, Jinpyo Park, Diana Marculescu I. OVERVIEW throughput for maximizing This paper investigates about the problem of dynamic thread mapping in heterogeneous many-core systems via an efficient lgorithm that maximizes performance under power constraints. The approach is to formulate the mapping problem as a 0-1 integer linear program (ILP), given any numbers of threads, ores and type of cores. An iterative O(n2/m) heuristic-based lgorithm for solving the 0-1 ILP thread mapping is proposed, thereby providing, a novel scalable approach for effective thread mapping on many-core heterogeneous systems. The paper considers multi-threaded workloads and assumes that each core runs at most one thread at a time thereby supporting single threaded execution, without simultaneous multithreading" 177c48590469c62d430cf74fee7b5bd28bfbbc1d,Articulated Motion Learning via Visual and Lingual Signals,"Learning Articulated Motion Models from Visual and Lingual Signals Zhengyang Wu Georgia Tech Atlanta, GA 30332 Mohit Bansal TTI-Chicago Chicago, IL 60637 Matthew R. Walter TTI-Chicago Chicago, IL 60637" 17dc9ca88bb8f36d167af1fe672278c8edd09713,Learning to Update for Object Tracking.,"Learning to Update for Object Tracking Bi Li, Wenxuan Xie, Wenjun Zeng, Fellow, IEEE, and Wenyu Liu, Senior Member, IEEE" 174cd8e98f17b3f5bda1c8e16cb39e3dec800f74,Multi-scale Context Intertwining for Semantic Segmentation,"Multi-Scale Context Intertwining for Semantic Segmentation Di Lin1, Yuanfeng Ji1, Dani Lischinski2, Daniel Cohen-Or1,3, and Hui Huang1(cid:63) Shenzhen University 2The Hebrew University of Jerusalem 3Tel Aviv University" 17ff59bb388b155f613f7566ba7cd71ec780cdec,Asymmetric Sparse Kernel Approximations for Large-Scale Visual Search,"Asymmetric sparse kernel approximations for large-scale visual search Damek Davis University of California Los Angeles, CA 90095 Jonathan Balzer University of California Los Angeles, CA 90095 Stefano Soatto University of California Los Angeles, CA 90095" 1742e6c347037d5d4ccbdf5c7a27dfbf0afedb91,A Unified Framework for Representation-Based Subspace Clustering of Out-of-Sample and Large-Scale Data,"JOURNAL OF LATEX CLASS FILES, VOL. 13, NO. 9, SEPTEMBER 2014 A Unified Framework for Representation-Based Subspace Clustering of Out-of-Sample and Large-Scale Data Xi Peng, Huajin Tang, Member IEEE, Lei Zhang, Member IEEE, Zhang Yi, Senior Member IEEE, Shijie Xiao Student Member IEEE," 179ca4195c90e032aa1e052bf6dfea62095e1006,A Review on a Person Cross Domain Re Identification Based Adaptive Ranking Support Vector Machines ( AdaRSVMs ),"International Journal of Engineering Research in Electronic and Communication Engineering (IJERECE) Vol 3, Issue 3, March 2016 A Review on a Person Cross Domain Re Identification Based Adaptive Ranking Support Vector Machines (AdaRSVMs) [1] V .Hemanth Kumar, [2] Y.Penchalaiah, [3] Pushpalatha [1] M.Tech Student [DSCE], [2][3] Assistant Professor Annamacharya Institute of Technology & Sciences (AITS) [1] [2] [3]" 17a85799c59c13f07d4b4d7cf9d7c7986475d01c,Extending Procrustes Analysis: Building Multi-view 2-D Models from 3-D Human Shape Samples,"ADVERTIMENT. La consulta d’aquesta tesi queda condicionada a l’acceptació de les següents ondicions d'ús: La difusió d’aquesta tesi per mitjà del servei TDX (www.tesisenxarxa.net) ha estat autoritzada pels titulars dels drets de propietat intel·lectual únicament per a usos privats emmarcats en activitats d’investigació i docència. No s’autoritza la seva reproducció amb finalitats de lucre ni la seva difusió i posada a disposició des d’un lloc aliè al servei TDX. No s’autoritza la presentació del seu contingut en una finestra o marc aliè a TDX (framing). Aquesta reserva de drets afecta tant al resum de presentació de la tesi com als seus continguts. En la utilització o cita de parts de la tesi és obligat indicar el nom de la persona autora. ADVERTENCIA. La consulta de esta tesis queda condicionada a la aceptación de las siguientes ondiciones de uso: La difusión de esta tesis por medio del servicio TDR (www.tesisenred.net) ha sido autorizada por los titulares de los derechos de propiedad intelectual únicamente para usos privados enmarcados en actividades de investigación y docencia. No se autoriza su reproducción on finalidades de lucro ni su difusión y puesta a disposición desde un sitio ajeno al servicio TDR. No se autoriza la presentación de su contenido en una ventana o marco ajeno a TDR (framing). Esta reserva de derechos afecta tanto al resumen de presentación de la tesis como a sus ontenidos. En la utilización o cita de partes de la tesis es obligado indicar el nombre de la persona autora. WARNING. On having consulted this thesis you’re accepting the following use conditions: Spreading this thesis by the TDX (www.tesisenxarxa.net) service has been authorized by the titular of the intellectual property rights only for private uses placed in investigation and teaching" 17cf838720f7892dbe567129dcf3f7a982e0b56e,Global-Local Face Upsampling Network,"Global-Local Face Upsampling Network Oncel Tuzel Yuichi Taguchi John R. Hershey Mitsubishi Electric Research Labs (MERL), Cambridge, MA, USA" 17c62bff70eb0919864f111df4930062aded729a,Encoding Spatial Context in Local Image Descriptors,"Universit¨at des Saarlandes Max-Planck-Institut f¨ur Informatik Encoding Spatial Context in Local Image Descriptors Masterarbeit im Fach Informatik Master’s Thesis in Computer Science von / by Dushyant Mehta ngefertigt unter der Leitung von / supervised by Dr. Roland Angst etreut von / advised by Dr. Roland Angst egutachtet von / reviewers Dr. Roland Angst Prof. Dr. Joachim Weickert Saarbr¨ucken, February 28, 2016" 179cab3d5a800f846225117e708e8d7c49754828,Toward Seamless Multiview Scene Analysis From Satellite to Street Level,"Towards seamless multi-view scene analysis from satellite to street-level S´ebastien Lef`evre, Devis Tuia, Senior Member, IEEE, Jan D. Wegner, Timoth´ee Produit, Ahmed Samy Nassar" 17127e17c00dda8d5cbad6ad126a5509ead8b284,Bayesian face recognition using Gabor features,"Bayesian Face Recognition Using Gabor Features Xiaogang Wang Department of Information Engineering The Chinese University if Hong Kong Shatin, Hong Kong Xiaoou Tang Department of Information Engineering The Chinese University if Hong Kong Shatin, Hong Kong (Email: (Email:" 174ddb6379b91a0e799e9988d0e522a5af18f91d,ChatPainter: Improving Text to Image Generation using Dialogue,"ChatPainter: Improving Text to Image Generation using Dialogue Shikhar Sharma 1 Dendi Suhubdy 2 3 Vincent Michalski 2 3 1 Samira Ebrahimi Kahou 1 Yoshua Bengio 2 3" 17605bec1ea7a55d87eb07a872858d86b703e9b3,Smile at Me ! Dogs Activate the Temporal Cortex Towards Smiling Human Faces,"ioRxiv preprint first posted online May. 4, 2017; http://dx.doi.org/10.1101/134080 The copyright holder for this preprint (which was not peer-reviewed) is the author/funder. It is made available under a CC-BY-NC-ND 4.0 International license Smile at Me! Dogs Activate the Temporal Cortex Towards Smiling Human Faces Laura V. Cuaya1,*, Ra ´ul Hern´andez-P´erez1, and Luis Concha1 Instituto de Neurobiolog´ıa, Universidad Nacional Aut´onoma de M´exico, Quer´etaro, M´exico." 178a82e3a0541fa75c6a11350be5bded133a59fd,BioHDD: a dataset for studying biometric identification on heavily degraded data,"Techset Composition Ltd, Salisbury {IEE}BMT/Articles/Pagination/BMT20140045.3d www.ietdl.org Received on 15th July 2014 Revised on 17th September 2014 Accepted on 23rd September 2014 doi: 10.1049/iet-bmt.2014.0045 ISSN 2047-4938 BioHDD: a dataset for studying biometric identification on heavily degraded data Gil Santos1, Paulo T. Fiadeiro2, Hugo Proença1 Department of Computer Science, IT – Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal Department of Physics, Remote Sensing Unit – Optics, Optometry and Vision Sciences Group, University of Beira Interior, Covilhã, Portugal E-mail:" 1750db78b7394b8fb6f6f949d68f7c24d28d934f,Detecting Facial Retouching Using Supervised Deep Learning,"Detecting Facial Retouching Using Supervised Deep Learning Aparna Bharati, Richa Singh, Senior Member, IEEE, Mayank Vatsa, Senior Member, IEEE, Kevin W. Bowyer, Fellow, IEEE" 17daa9ddaf524de914e7440157fc0314db171884,Data driven analysis of faces from images,"Data Driven Analysis of Faces from Images Dissertation zur Erlangung des Grades „Doktor der Ingenieurwissenschaften (Dr.-Ing.)” der Naturwissenschaftlich-Technischen Fakultäten der Universität des Saarlandes Kristina Scherbaum 8.05.2013 Universität des Saarlandes | Max-Planck-Institut für Informatik Saarbrücken – Germany" 17a9db524ddbeb5577a94924c2a7cca048dd19f9,Object Recognition with Multi-Scale Pyramidal Pooling Networks,"Object Recognition with Multi-Scale Pyramidal Pooling Networks Jonathan Masci1, Ueli Meier1, Gabriel Fricout2, and J¨urgen Schmidhuber1 IDSIA – USI – SUPSI, Manno – Lugano, Switzerland, http://idsia.ch/~masci/ ArcelorMittal, Maizi`eres Research, Measurement and Control Dept., France" 17635e22a73da3ff60a72715b7dd8837de6fee89,The ABBA study – approach bias modification in bulimia nervosa and binge eating disorder: study protocol for a randomised controlled trial,"Brockmeyer et al. Trials (2016) 17:466 DOI 10.1186/s13063-016-1596-6 ST UD Y P R O T O C O L Open Access The ABBA study – approach bias modification in bulimia nervosa and binge eating disorder: study protocol for a randomised controlled trial Timo Brockmeyer1,2*, Ulrike Schmidt2 and Hans-Christoph Friederich1,3" 17c0094c68d6efd19b80287c51d228fa50750f46,An efficient partial face detection method using AlexNet CNN,"SSRG International Journal of Electronics and Communication Engineering - (ICRTECITA-2017) - Special Issue - March 2017 An efficient partial face detection method using AlexNet CNN Prof Mr.Sivalingam.T, S.Kabilan , Dhanabal.M ,Arun.R ,Chandrabhagavan.K V.S.B Engineering College,Karur" 1748867e04ba16673ec5231f6a2ca0ae03835658,Fast Exact Search in Hamming Space With Multi-Index Hashing,"Fast Exact Search in Hamming Space with Multi-Index Hashing Mohammad Norouzi, Ali Punjani, David J. Fleet, {norouzi, alipunjani," 17db741725b9f8406f69b27a117e99bee1a9a323,Person Re-identification with a Body Orientation-Specific Convolutional Neural Network,"Person Re-identification with a Body Orientation-Specific Convolutional Neural Network Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt To cite this version: Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt. Person Re- identification with a Body Orientation-Specific Convolutional Neural Network. Advanced Concepts for Intelligent Vision systems, Sep 2018, Poitiers, France. HAL Id: hal-01895374 https://hal.archives-ouvertes.fr/hal-01895374 Submitted on 15 Oct 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 17dd242e6d7afb5d7fafcf9f8e8b201573ce4b89,An Extensive Review on Spectral Imaging in Biometric Systems: Challenges and Advancements,"An Extensive Review on Spectral Imaging in Biometric Systems: Challenges & Advancements Rumaisah Munira,∗, Rizwan Ahmed Khana,b,∗∗ Faculty of IT, Barrett Hodgson University, Karachi, Pakistan. LIRIS, Universite Claude Bernard Lyon1, France." 11be33019f591214c8f79dbcb24a50d8f7fa5c95,Salgan 360 : Visual Saliency Prediction on 360 Degree Images with Generative Adversarial Networks,"SALGAN360: VISUAL SALIENCY PREDICTION ON 360 DEGREE IMAGES WITH GENERATIVE ADVERSARIAL NETWORKS Fang-Yi Chao, Lu Zhang, Wassim Hamidouche, Olivier Deforges Univ Rennes, INSA Rennes, CNRS, IETR - UMR 6164, F-35000 Rennes, France {fang-yi.chao, lu.ge, wassim.hamidouche," 112cc60d3c6268b1563df4e716904d29a7feb466,Machine Learning for Spatiotemporal Sequence Forecasting: A Survey,"Machine Learning for Spatiotemporal Sequence Forecasting: A Survey Xingjian Shi, Dit-Yan Yeung, Senior Member, IEEE" 11691f1e7c9dbcbd6dfd256ba7ac710581552baa,SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos,"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos Silvio Giancola, Mohieddine Amine, Tarek Dghaily, Bernard Ghanem King Abdullah University of Science and Technology (KAUST), Saudi Arabia" 1174b869c325222c3446d616975842e8d2989cf2,CosFace: Large Margin Cosine Loss for Deep Face Recognition,"CosFace: Large Margin Cosine Loss for Deep Face Recognition Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li∗, and Wei Liu∗ Tencent AI Lab" 1172ce24f6e9242b9c26c84c6aa89a72ed8203d0,Find your own way: Weakly-supervised segmentation of path proposals for urban autonomy,"Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy Dan Barnes, Will Maddern and Ingmar Posner" 1114c2aba97a5782a48341817811df2438d0fdbf,Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling,"Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling Peng Zhang∗, Shujian Yu∗, Student Member, IEEE, Jiamiao Xu, Xinge You†, Senior Member, IEEE, Xiubao Jiang, Xiao-Yuan Jing, and Dacheng Tao, Fellow, IEEE. etc. On the other hand, pplications impedes the usage of overcomplicated models. the real-time requirement in real" 11f7f939b6fcce51bdd8f3e5ecbcf5b59a0108f5,Rolling Riemannian Manifolds to Solve the Multi-class Classification Problem,"Rolling Riemannian Manifolds to Solve the Multi-class Classification Problem Rui Caseiro1, Pedro Martins1, João F. Henriques1, Fátima Silva Leite1,2, and Jorge Batista1 Institute of Systems and Robotics - University of Coimbra, Portugal Department of Mathematics - University of Coimbra, Portugal , {ruicaseiro, pedromartins, henriques," 11467733103a3e58ae88cb238f620cf6cafd4420,Learning of Graphical Models and Efficient Inference for Object Class Recognition,"Learning of Graphical Models and Ef‌f‌icient Inference for Object Class Recognition Martin Bergtholdt, J¨org Kappes, and Christoph Schn¨orr Computer Vision, Graphics, and Pattern Recognition Group Department of Mathematics and Computer Science University of Mannheim, 68131 Mannheim, Germany" 11d36e1687fc2fc3e3cc9d06fedee7b0f8fb79bf,A Deep Structure of Person Re-Identification using Multi-Level Gaussian Models,"> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < A Deep Structure of Person Re-Identification using Multi-Level Gaussian Models Dinesh Kumar Vishwakarma, IEEE Member, Sakshi Upadhyay" 11ed823555aabf7e32df5b09a04111a686f8ebb6,Learning visual dictionaries and decision lists for object recognition,"CONFIDENTIAL. Limited circulation. For review only. Preprint submitted to 19th International Conference on Pattern Recognition. Received April 10, 2008." 11da2d589485685f792a8ac79d4c2e589e5f77bd,Show and tell: A neural image caption generator,"Show and Tell: A Neural Image Caption Generator Oriol Vinyals Google Alexander Toshev Google Samy Bengio Google Dumitru Erhan Google" 1149c6ac37ae2310fe6be1feb6e7e18336552d95,"Classification of Face Images for Gender, Age, Facial Expression, and Identity","Proc. Int. Conf. on Artificial Neural Networks (ICANN’05), Warsaw, LNCS 3696, vol. I, pp. 569-574, Springer Verlag 2005 Classification of Face Images for Gender, Age, Facial Expression, and Identity1 Torsten Wilhelm, Hans-Joachim B¨ohme, and Horst-Michael Gross Department of Neuroinformatics and Cognitive Robotics Ilmenau Technical University, P.O.Box 100565, 98684 Ilmenau, Germany" 110556d073a4d930877edc597a92995f0ff9d294,Application of Faster R-CNN model on Human Running Pattern Recognition,"Application of Faster R-CNN Model on Human Running Pattern Recognitions Kairan Yang, Feng Geng Lexington High School, KTByte Computer Science Academy" 11f17191bf74c80ad0b16b9f404df6d03f7c8814,Characteristics of Visual Categorization of Long-Concatenated and Object-Directed Human Actions by a Multiple Spatio-Temporal Scales Recurrent Neural Network Model,"Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks Haanvid Lee, Minju Jung, and Jun Tani" 11b00a4be68e9622d7b4698aca84da85aca3e288,Modeling Social Interactions in Real Work Environments,"Modeling Social Interactions in Real Work Environments Salvatore Vanini SUPSI-DTI via Cantonale 6928 Manno, Switzerland Silvia Giordano SUPSI-DTI via Cantonale 6928 Manno, Switzerland Dario Gallucci SUPSI-DTI via Cantonale 6928 Manno, Switzerland Kamini Garg SUPSI-DTI via Cantonale 6928 Manno, Switzerland Victoria Mirata FFHS-IFeL Überlandstrasse 12" 116261c74ad54646f7d1d6be38cb9930f1bf44f6,3D Twins and Expression Challenge,"D Twins and Expression Challenge Vipin Vijayan, Kevin W. Bowyer, and Patrick J. Flynn." 1169f3386a49daccbe199cccb518238a0130a537,"Analyzing Complex Events and Human Actions in ""in-the-wild"" Videos", 115724ce1ce9422dad095b301c7d096498ad50d3,The E2E Dataset: New Challenges For End-to-End Generation,"Saarbr¨ucken, Germany, 15-17 August 2017. c(cid:13)2017 Association for Computational Linguistics Proceedings of the SIGDIAL 2017 Conference, pages 201–206," 1151a81118368e7596843b8db2508e4974fd7435,A Testbed for Cross-Dataset Analysis,"A Testbed for Cross-Dataset Analysis Tatiana Tommasi and Tinne Tuytelaars ESAT-PSI/VISICS - iMinds, KU Leuven, Belgium" 1120e88663a38ed05120af378f57ecf557660160,Generic Object Crowd Tracking by Multi-Task Learning,"LUOETAL.:GENERICOBJECTCROWDTRACKINGBYMULTI-TASKLEARNING Generic Object Crowd Tracking by Multi-Task Learning Wenhan Luo http://www.iis.ee.ic.ac.uk/~whluo Tae-Kyun Kim http://www.iis.ee.ic.ac.uk/~tkkim Department of Electrical and Electronic Engineering, Imperial College, London, UK" 11155ee686bfb675816a2acdf5a8ddf06e67b65f,EmoDetect – Smart Emotion Detection from Facial Expressions,"EmoDetect – Smart Emotion Detection from Facial Expressions Rishabh Animesh Skand Hurkat Abhinandan Majumdar Aayush Saxena ra523 sh953 m2352 s2825" 1198572784788a6d2c44c149886d4e42858d49e4,Learning Discriminative Features using Encoder-Decoder type Deep Neural Nets,"Learning Discriminative Features using Encoder/Decoder type Deep Neural Nets Vishwajeet Singh1, Killamsetti Ravi Kumar2, K Eswaran3 ALPES, Bolarum, Hyderabad 500010, ALPES, Bolarum, Hyderabad 500010, SNIST, Ghatkesar, Hyderabad 501301," 111f2f1255fa9e5a82753bf5b3f2f0974e87f86d,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 111ff5420111751454a2f4f55b7bb75d837ed5f4,Automatic Annotation of Structured Facts in Images,"Proceedings of the 5th Workshop on Vision and Language, pages 1–9, Berlin, Germany, August 12 2016. c(cid:13)2016 Association for Computational Linguistics" 11a7c4aadb47753c8d30cbda4ab347c361e4c66a,How to collect high quality segmentations : use human or computer drawn object boundaries ?,"Boston University Computer Science Technical Report No. BUCS-TR-2013-20 How to Collect High Quality Segmentations: Use Human or Computer Drawn Object Boundaries? Danna Gurari, Zheng Wu, Brett Isenberg, Chentian Zhang, Alberto Purwada, Joyce Y. Wong, Margrit Betke" 1178beb48d666d7fc41b2d476f6a92450c0726c0,Challenges in multimodal gesture recognition,"Submitted 11/14; Revised 1/16; Published 4/16 Challenges in multimodal gesture recognition Sergio Escalera Computer Vision Center UAB and University of Barcelona Vassilis Athitsos University of Texas Isabelle Guyon ChaLearn, Berkeley, California Editors: Zhuowen Tu" 11feb48d2c4c8f8a5ed9054d49e7a13b0f75f2af,Chapter 1 Feature Representation and Extraction for Image Search and Video Retrieval,"Chapter 1 Feature Representation and Extraction for Image Search and Video Retrieval Qingfeng Liu, Yukhe Lavinia, Abhishek Verma, Joyoung Lee, Lazar Spasovic, and Chengjun Liu" 11f2e65a0cd4e27505f1306d39b5717b5c5c92a5,Gradient Feature Selection for Online Boosting,"Gradient Feature Selection for Online Boosting Visualization and Computer Vision Lab General Electric Global Research, Niskayuna, NY, 12309, USA Xiaoming Liu Ting Yu {liux,yut} AT research.ge.com" 1152b88194214d4ea0f85b727f4b120915ad8056,Exploiting feature dynamics for active object recognition,"Exploiting Feature Dynamics for Active Object Recognition Philipp Robbel and Deb Roy MIT Media Laboratory Cambridge, MA 02139, USA" 11f73583ba373487967225ae4797d723ff367c1c,"End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks","Article End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks The International Journal of Robotics Research © The Author(s) 2017 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/0278364917734298 journals.sagepub.com/home/ijr Sen Wang1,2, Ronald Clark3, Hongkai Wen4 and Niki Trigoni2" 11bfc54a64ca69786323551bbf88b85b216ae486,Exploring the Facial Expression Perception-Production Link Using Real-Time Automated Facial Expression Recognition,"Exploring the Facial Expression Perception-Production Link Using Real-Time Automated Facial Expression Recognition David M. Deriso1, Josh Susskind1, Jim Tanaka2, Piotr Winkielman3, John Herrington4, Robert Schultz4, and Marian Bartlett1 Machine Perception Laboratory, University of California, San Diego Department of Psychology, University of Victoria Department of Psychology, University of California, San Diego Center for Autism Research, Children’s Hospital of Philadelphia" 111d0b588f3abbbea85d50a28c0506f74161e091,Facial Expression Recognition from Visual Information using Curvelet Transform,"International Journal of Computer Applications (0975 – 8887) Volume 134 – No.10, January 2016 Facial Expression Recognition from Visual Information using Curvelet Transform Pratiksha Singh Surabhi Group of Institution Bhopal systems. Further applications" 11a3084768f035c824662a85a348f02466693d2a,Lifting Object Detection Datasets into 3D,"Lifting Object Detection Datasets into 3D Jo˜ao Carreira*, Sara Vicente*, Lourdes Agapito and Jorge Batista" 1171ec9250743c349e5218d4a01c4fdad94c7707,Low-Cost Transfer Learning of Face Tasks,"Low-Cost Transfer Learning of Face Tasks Thrupthi Ann John1, Isha Dua1, Vineeth N Balasubramanian2, and C. V. Jawahar1 IIIT Hyderabad IIT Hyderabad" 117b78d154309d87c4d84ffb64057c1dfcdb1dd7,Gender Classification with Jointing Multiple Models for Occlusion Images,"GENDER CLASSIFICATION WITH JOINTING MULTIPLE MODELS FOR OCCLUSION IMAGES CHIAO-WEN KAO1, HUI-HUI CHEN2, BOR-JIUNN HWANG2, YU-JU HUANG1, KUO-CHIN FAN1 Department of Computer Science and Information Engineering, National Central Department of Computer Communication and Engineering, Ming Chuan University, University, Taoyuan, Taiwan Taoyuan, Taiwan E-MAIL:" 11e79b96cc87794592c0aa8f573d440a70a9a941,Systematic Testing of Convolutional Neural Networks for Autonomous Driving,"Systematic Testing of Convolutional Neural Networks for Autonomous Driving Tommaso Dreossi 1 Shromona Ghosh 1 Alberto Sangiovanni-Vincentelli 1 Sanjit A. Seshia 1" 111a9645ad0108ad472b2f3b243ed3d942e7ff16,Facial Expression Classification Using Combined Neural Networks,"Facial Expression Classification Using Combined Neural Networks Rafael V. Santos, Marley M.B.R. Vellasco, Raul Q. Feitosa, Ricardo Tanscheit DEE/PUC-Rio, Marquês de São Vicente 225, Rio de Janeiro – RJ - Brazil" 1131088237aacddcc078547b4455e8572c61766b,Object Referring in Videos with Language and Human Gaze,"Object Referring in Videos with Language and Human Gaze Arun Balajee Vasudevan1, Dengxin Dai1, Luc Van Gool1,2 ETH Zurich1 KU Leuven 2" 116a7ac8891cd22f97df508e696e8280658c858c,"Discriminant Analysis via Joint Euler Transform and ℓ2, 1-Norm","IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. *, NO. *, * * Discriminant Analysis via Joint Euler Transform nd (cid:96)2,1-norm Shuangli Liao, Quanxue Gao, Zhaohua Yang, Fang Chen, Feiping Nie, and Jungong Han" 11f732fe8f127c393cc8404ee8db2b3e85dd3d59,Disentangling Latent Factors with Whitening,"DISENTANGLING LATENT FACTORS WITH WHITENING Sangchul Hahn, Heeyoul Choi School of Information Technology {schahn21, Handong Global University Pohang, South Korea" 11a34bda2daecad5f7c1caa309897cc9cc334480,Person re-identification using view-dependent score-level fusion of gait and color features,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-1-6 ©2012 IAPR" 2c883977e4292806739041cf8409b2f6df171aee,Are Haar-Like Rectangular Features for Biometric Recognition Reducible?,"Aalborg Universitet Are Haar-like Rectangular Features for Biometric Recognition Reducible? Nasrollahi, Kamal; Moeslund, Thomas B. Published in: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications DOI (link to publication from Publisher): 0.1007/978-3-642-41827-3_42 Publication date: Document Version Early version, also known as pre-print Link to publication from Aalborg University Citation for published version (APA): Nasrollahi, K., & Moeslund, T. B. (2013). Are Haar-like Rectangular Features for Biometric Recognition Reducible? In J. Ruiz-Shulcloper, & G. Sanniti di Baja (Eds.), Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications (Vol. 8259, pp. 334-341). Springer Berlin Heidelberg: Springer Publishing Company. Lecture Notes in Computer Science, DOI: 10.1007/978-3-642-41827-3_42 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research." 2cac8ab4088e2bdd32dcb276b86459427355085c,A Face-to-Face Neural Conversation Model,"A Face-to-Face Neural Conversation Model Hang Chu1 Daiqing Li1 Sanja Fidler1 University of Toronto 2Vector Institute {chuhang1122, daiqing," 2c564f5241b0905baafc3677e7ca15c27fd2c6e7,An Integrated Approach to Contextual Face Detection,"AN INTEGRATED APPROACH TO CONTEXTUAL FACE DETECTION. Santi Segu´ı1, Michal Drozdzal1,2, Petia Radeva1,2 and Jordi Vitri`a1,2 Computer Vision Center, Universitat Aut`onoma de Barcelona, Bellaterra, Spain Dept. Matem`atica Aplicada i An`alisi, Universitat de Barcelona, Barcelona, Spain {ssegui, michal, petia, Keywords: face detection, object detection." 2cad358676854505517307314728e8920fe53d77,Mixture of Ridge Regressors for Human Pose Estimation,"#1754 CVPR 2012 Submission #1754. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. #1754 Mixture of Ridge Regressors for Human Pose Estimation Anonymous CVPR submission Paper ID 1754" 2c48683c9663ea82fcbbd5891d892a884f1a32d0,Explore semantic pixel sets based local patterns with information entropy for face recognition,"Chai et al. EURASIP Journal on Image and Video Processing 2014, 2014:26 http://jivp.eurasipjournals.com/content/2014/1/26 RESEARCH Open Access Explore semantic pixel sets based local patterns with information entropy for face recognition Zhenhua Chai1*, Heydi Mendez-Vazquez2, Ran He1, Zhenan Sun1 and Tieniu Tan1" 2c9c597ab660815e07980e9655c3c5989402205b,Vision-Based Reacquisition for Task-Level Control,"Vision-based Reacquisition for Task-level Control Matthew R. Walter, Yuli Friedman, Matthew Antone, and Seth Teller" 2c8743089d9c7df04883405a31b5fbe494f175b4,Real-time full-body human gender recognition in (RGB)-D data,"Washington State Convention Center Seattle, Washington, May 26-30, 2015 978-1-4799-6922-7/15/$31.00 ©2015 IEEE" 2cf7383e238fe37516e2607c4741f79a230834bf,A new Sparse Coding Approach for Human Face and Action Recognition,"A new Sparse Coding Approach for Human Face and Action Recognition Mohsen Nikpour* Department of Electrical and Computer Engineering, Babol Noushirvani University of Technology, Babol, Iran Mohammad Reza Karami Molaei Department of Electrical and Computer Engineering, Babol Noushirvani University of Technology, Babol, Iran Reza Ghaderi Department of nuclear Engineering, Shahid Beheshti University of Tehran, Tehran, Iran Received: 27/Jul/2016 Revised: 07/Jan/2017 Accepted: 14/Jan/2017" 2c786b32a621a52fc7d00499e4b056f149a4fba7,Face Recognition with Decision Tree-Based Local Binary Patterns,"Face Recognition with Decision Tree-based Local Binary Patterns Daniel Maturana, Domingo Mery and ´Alvaro Soto Department of Computer Science, Pontificia Universidad Cat´olica de Chile" 2cdde47c27a8ecd391cbb6b2dea64b73282c7491,Order-aware Convolutional Pooling for Video Based Action Recognition,"ORDER-AWARE CONVOLUTIONAL POOLING FOR VIDEO BASED ACTION RECOGNITION Order-aware Convolutional Pooling for Video Based Action Recognition Peng Wang, Lingqiao Liu, Chunhua Shen, and Heng Tao Shen" 2cfdf540840a983907e957aacf68b405214c721c,Can We Predict the Scenic Beauty of Locations from Geo-tagged Flickr Images?,"Can We Predict the Scenic Beauty of Locations from Geo-tagged Flickr Images? Ch. Md. Rakin Haider Bangladesh University of Engineering and Technology, Dhaka, Bangladesh Mohammed Eunus Ali Bangladesh University of Engineering and Technology, Dhaka, Bangladesh" 2c92839418a64728438c351a42f6dc5ad0c6e686,Pose-Aware Face Recognition in the Wild,"Pose-Aware Face Recognition in the Wild Iacopo Masi1 Prem Natarajan2 USC Institute for Robotics and Intelligent Systems (IRIS), Los Angeles, CA G´erard Medioni1 Stephen Rawls2 USC Information Sciences Institute (ISI), Marina Del Rey, CA" 2cbb8de53759e75411bc528518947a3094fbce3a,Billion-scale similarity search with GPUs,"Billion-scale similarity search with GPUs Jeff Johnson Facebook AI Research New York Matthijs Douze Facebook AI Research Paris Herv´e J´egou Facebook AI Research Paris" 2c47ef6a9979cb51f7cdfe3bafdbaa2aec28da8b,A Lazy Man's Approach to Benchmarking: Semisupervised Classifier Evaluation and Recalibration,"UvA-DARE (Digital Academic Repository) A Lazy Man's Approach to Benchmarking: Semisupervised Classifier Evaluation and Recalibration Welinder, P.; Welling, M.; Perona, P. Published in: 013, Portland, Oregon, USA 0.1109/CVPR.2013.419 Link to publication Citation for published version (APA): Welinder, P., Welling, M., & Perona, P. (2013). A Lazy Man's Approach to Benchmarking: Semisupervised Classifier Evaluation and Recalibration. In Proceedings: 2013 IEEE Conference on Computer Vision and Pattern Recognition: CVPR 2013: 23-28 June 2013, Portland, Oregon, USA (pp. 3262-3269). Los Alamitos, CA: IEEE Computer Society Conference Publishing Services. DOI: 10.1109/CVPR.2013.419 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam," 2cdd5b50a67e4615cb0892beaac12664ec53b81f,Mirror mirror: crowdsourcing better portraits,"To appear in ACM TOG 33(6). Mirror Mirror: Crowdsourcing Better Portraits Jun-Yan Zhu1 Aseem Agarwala2 Alexei A. Efros1 Eli Shechtman2 Jue Wang2 University of California, Berkeley1 Adobe2 Figure 1: We collect thousands of portraits by capturing video of a subject while they watch movie clips designed to elicit a range of positive emotions. We use crowdsourcing and machine learning to train models that can predict attractiveness scores of different expressions. These models can be used to select a subject’s best expressions across a range of emotions, from more serious professional portraits to big smiles." 2c72096bbecd70000f919b1cec3f31a649c94fd5,Neural Network Interpretation via Fine Grained Textual Summarization,"Neural Network Interpretation via Fine-Grained Textual Summarization Pei Guo, Connor Anderson, Kolton Pearson, Ryan Farrell Brigham Young University" 2c2bf22e2f0a1817475aefb37e0c4e0404e8d479,Structured Prediction of 3D Human Pose with Deep Neural Networks,"TEKIN ET AL.: STRUCTURED PREDICTION OF 3D HUMAN POSE Structured Prediction of 3D Human Pose with Deep Neural Networks Bugra Tekin∗1 Isinsu Katircioglu∗1 Mathieu Salzmann1 Vincent Lepetit2 Pascal Fua1 CVLab EPFL, Lausanne, Switzerland CVARLab TU Graz, Graz, Austria" 2cd03c6e78d09bb98872bb34bb70e08c32dc5f7e,Pedestrian Alignment Network for Large-scale Person Re-identification,"Noname manuscript No. (will be inserted by the editor) Pedestrian Alignment Network for Large-scale Person Re-identification Zhedong Zheng · Liang Zheng · Yi Yang Received: date / Accepted: date" 2cf5f2091f9c2d9ab97086756c47cd11522a6ef3,MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation,"MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation Xucong Zhang, Yusuke Sugano∗, Mario Fritz, Andreas Bulling" 2c0a71b5e111d2c7d99c3f23989d317a0d845adc,N-best maximal decoders for part models,"N-best maximal decoders for part models Dennis Park Deva Ramanan UC Irvine" 2c2786ea6386f2d611fc9dbf209362699b104f83,Title of Dissertation Local Feature Representations for Facial Expression Recognition Based on Differences of Gray Color Values of Neighboring Pixels,1)LOCAL FEATURE REPRESENTATIONS FOR FACIAL EXPRESSION RECOGNITION BASED ON DIFFERENCES OF GRAY COLOR VALUES OF NEIGHBORING PIXELS Mohammad Shahidul Islam A Dissertation Submitted in Partial Fulfillment of the Requirement for the Degree of Doctor of Philosophy (Computer Science and Information Systems) School of Applied Statistics National Institute of Development Administration 2013 2c93c8da5dfe5c50119949881f90ac5a0a4f39fe,Advanced local motion patterns for macro and micro facial expression recognition,"Advanced local motion patterns for macro and micro facial expression recognition B. Allaerta,∗, IM. Bilascoa, C. Djerabaa Univ. Lille, CNRS, Centrale Lille, UMR 9189 - CRIStAL - Centre de Recherche en Informatique Signal et Automatique de Lille, F-59000 Lille, France" 2cdd9e445e7259117b995516025fcfc02fa7eebb,Temporal Exemplar-Based Bayesian Networks for Facial Expression Recognition,"Title Temporal Exemplar-based Bayesian Networks for facial expression recognition Author(s) Shang, L; Chan, KP Citation Proceedings - 7Th International Conference On Machine Learning And Applications, Icmla 2008, 2008, p. 16-22 Issued Date http://hdl.handle.net/10722/61208 Rights This work is licensed under a Creative Commons Attribution- NonCommercial-NoDerivatives 4.0 International License.; International Conference on Machine Learning and Applications Proceedings. Copyright © IEEE.; ©2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted omponent of this work in other works must be obtained from" 2ce2560cf59db59ce313bbeb004e8ce55c5ce928,Anthropometric 3D Face Recognition,"Int J Comput Vis DOI 10.1007/s11263-010-0360-8 Anthropometric 3D Face Recognition Shalini Gupta · Mia K. Markey · Alan C. Bovik Received: 3 July 2009 / Accepted: 20 May 2010 © Springer Science+Business Media, LLC 2010" 2cc8371c483f76fff65a5fb1c9cc89e974ce83ea,Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks,"Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks Michael Gygli gifs.com Zurich, Switzerland" 2cc0e431d7cc0bcb926b9a19e7be8a3592d670d4,NovaMedSearch: a multimodal search engine for medical case-based retrieval,"NovaMedSearch: A multimodal search engine for medical ase-based retrieval André Mourão Flávio Martins Faculdade de Ciências e Tecnologia Universidade Nova de Lisboa Departamento de Informática Caparica, Portugal" 2c1cd58790cf07d5fa7f1f1f096023a993a6ead3,"Improving 3 D perception for Object Detection , Classification and Localization using Fused Multi-modal Sensors","Improving 3D perception for Object Detection, Classification and Localization using Fused Multi-modal Sensors Saif Imran, Aaron Gonzalez, Mehmet Akif Alper February 21, 2017 Introduction Object perception in 3-D is a highly challenging problem in computer vision. The major concern in these tasks involves object occlusion, different object poses, appearance and limited perception of the environment by individual sensors in terms of range measurements. In this particular project, our goal is improving 3D perception of the environment by using fusion from lidars and cameras with focus to autonomous driving. The main reason for using lidars and cameras are to combine the complementary information from each of the modalities for ef‌f‌icient feature set extraction that leads to improved perception. Motivation/Related Work The main focus of this work involves autonomous driving of cars using improved 3D perception of the environment. The real challenge is how to fuse the information from both the modalities in order to learn useful patterns/features of objects. There are some real advances in semantic labelling of objects in 2D images through deep networks. But using fused data for object classification and recognition is still at premature stage. We would like to use lidar and camera for this purpose. Lidars are good in the sense that" 2c5ff99e7e9769677df3eeab9f198e3ead016c35,Registration of 3D facial surfaces using covariance matrix pyramids,"Anchorage Convention District May 3-8, 2010, Anchorage, Alaska, USA 978-1-4244-5040-4/10/$26.00 ©2010 IEEE" 2c98165dd72bac574ed463b00f1dd4c276808cb4,Efficient Object Pixel-Level Categorization Using Bag of Features,"Ef‌f‌icient Object Pixel-Level Categorization using Bag of Features David Aldavert1, Arnau Ramisa2, Ricardo Toledo1, and Ramon Lopez de Mantaras2 Computer Vision Center (CVC) Dept. Ci`encies de la Computaci´o Universitat Aut`onoma de Barcelona (UAB), 08193, Bellaterra, Spain Artificial Intelligence Research Institute (IIIA-CSIC) Campus de la UAB, 08193, Bellaterra, Spain" 2c848cc514293414d916c0e5931baf1e8583eabc,An automatic facial expression recognition system evaluated by different classifiers,"An automatic facial expression recognition system evaluated by different classifiers Caroline Silva∗, Andrews Sobral∗ and Raissa Tavares Vieira† Programa de P´os-Graduac¸˜ao em Mecatrˆonica Universidade Federal da Bahia, Email: Email: Department of Electrical Engineering - EESC/USP Email:" 2c7932c2096669113328a75d1ad1d1bfb8f86ad0,Multi30K: Multilingual English-German Image Descriptions,"Proceedings of the 5th Workshop on Vision and Language, pages 70–74, Berlin, Germany, August 12 2016. c(cid:13)2016 Association for Computational Linguistics" 2c7b72d0b66074bff2f0b3493673a51f6f094d5f,A biometric verification system based on the fusion of palmprint and face features,"A Biometric Verification System Based on the Fusion of Palmprint and Face Features Slobodan Ribaric, Ivan Fratric and Kristina Kis Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia" 2cc17e1ccb5f1f67f8ce882e683d8c66475330be,Multitarget tracking with the von Mises-Fisher filter and probabilistic data association,"JOURNAL OF ADVANCES IN INFORMATION FUSION Multitarget tracking with the von Mises-Fisher filter nd probabilistic data association Ivan Markovi´c, Mario Bukal, Josip ´Cesi´c and Ivan Petrovi´c" 2ce1b73cee6ddf4dbff391e29b73b35e3fb67685,TSDF Manifolds: A Scalable and Consistent Dense Mapping Approach,"TSDF Manifolds: A Scalable and Consistent Dense Mapping Approach Alexander Millane, Zachary Taylor, Helen Oleynikova, Juan Nieto, Roland Siegwart, C´esar Cadena" 2c4b96f6c1a520e75eb37c6ee8b844332bc0435c,Automatic Emotion Recognition in Robot-Children Interaction for ASD Treatment,"Automatic Emotion Recognition in Robot-Children Interaction for ASD Treatment Marco Leo, Marco Del Coco, Pierluigi Carcagn`ı, Cosimo Distante ISASI UOS Lecce Campus Universitario via Monteroni sn, 73100 Lecce Italy Massimo Bernava, Giovanni Pioggia ISASI UOS Messina Giuseppe Palestra Univerisita’ di Bari Marine Institute, via Torre Bianca, 98164 Messina Italy Via Orabona 4, 70126 Bari, Italy" 2c5c89103605c6f0ed8924778526133dfa064a16,Blurred face recognition algorithm guided by a no-reference blur metric,"Blurred face recognition algorithm guided by a no-reference blur metric Cécile Fiche, Patricia Ladret, Ngoc-Son Vu To cite this version: Cécile Fiche, Patricia Ladret, Ngoc-Son Vu. Blurred face recognition algorithm guided by a no- Image Processing: Machine Vision Applications reference blur metric. III, Jan 2010, San Jose, Californie, United States. 7538 (75380U), pp.75380U-75380U-9, 2010, <10.1117/12.840245>. SPIE Digital Library. HAL Id: hal-00522115 https://hal.archives-ouvertes.fr/hal-00522115 Submitted on 29 Oct 2010 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers." 2c9179fec33f69a5c1a453034dc7d3d3302839d3,Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking,"Exploiting Hierarchical Dense Structures on Hypergraphs for Multi-Object Tracking Longyin Wen, Zhen Lei, Siwei Lyu, Stan Z. Li, Fellow, IEEE, and Ming-Hsuan Yang" 83b700f0777a408eb36eef4b1660beb3f6dc1982,Violent behaviour detection using local trajectory response Conference,"See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/317628106 Violent behaviour detection using local trajectory response Conference Paper · January 2016 DOI: 10.1049/ic.2016.0082 CITATIONS authors, including: Paul L. Rosin Cardiff University READS David Marshall Cardiff University 31 PUBLICATIONS 7,739 CITATIONS 98 PUBLICATIONS 2,855 CITATIONS SEE PROFILE SEE PROFILE Simon Christopher Moore University of Wales 08 PUBLICATIONS 1,069 CITATIONS SEE PROFILE" 8377ac1b2dffb11cf48f456be2531c95d14aa6e5,Improving the Annotation of DeepFashion Images for Fine-grained Attribute Recognition,"Improving the Annotation of DeepFashion Images for Fine-grained Attribute Recognition Roshanak Zakizadeh, Michele Sasdelli, Yu Qian and Eduard Vazquez Cortexica Vision Systems, London, UK" 838a4bcfeb36dc7bdb4a38f776fc0a70ce8ae9f0,Face Presentation Attack Detection using Biologically-inspired Features, 837e99301e00c2244023a8a48ff98d7b521c93ac,Local Feature Evaluation for a Constrained Local Model Framework,"Local Feature Evaluation for a Constrained Local Model Framework Maiya Hori(B), Shogo Kawai, Hiroki Yoshimura, and Yoshio Iwai Graduate School of Engineering, Tottori University, 01 Minami 4-chome, Koyama-cho, Tottori 680-8550, Japan" 832aae00e16c647716f1be38de233c9c15af9a28,Author ' s Accepted Manuscript Feature fusion for facial landmark detection,"Author's Accepted Manuscript Feature fusion for facial landmark detection Panagiotis Perakis, Theoharis Theoharis, Ioan- nis A. Kakadiaris Reference: S0031-3203(14)00105-8 http://dx.doi.org/10.1016/j.patcog.2014.03.007 PR5053 www.elsevier.com/locate/pr To appear in: Pattern Recognition Received date: 10 March 2013 Revised date: 18 September 2013 Accepted date: 8 March 2014 Cite this article as: Panagiotis Perakis, Theoharis Theoharis, Kakadiaris, Feature fusion for facial landmark detection, Pattern Recognition, http://dx.doi.org/10.1016/j.patcog.2014.03.007 Ioannis A. This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of" 8397956c7ad3bd24c6c6c0b38866e165367327c0,Social Relation Trait Discovery from Visual LifeLog Data with Facial Multi-Attribute Framework, 83c00537e0c3e226d999a5abf02464e138867e96,Pedestrians and their phones - detecting phone-based activities of pedestrians for autonomous vehicles,"Windsor Oceanico Hotel, Rio de Janeiro, Brazil, November 1-4, 2016 978-1-5090-1889-5/16/$31.00 ©2016 IEEE" 830b48f210f3905117b335e305166df4ec092b8b,Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling,"Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling Jonas Uhrig1,2, Marius Cordts1,3, Uwe Franke1, Thomas Brox2 Daimler AG R&D, 2University of Freiburg, 3TU Darmstadt" 83e093a07efcf795db5e3aa3576531d61557dd0d,Facial Landmark Localization Using Robust Relationship Priors and Approximative Gibbs Sampling,"Facial Landmark Localization using Robust Relationship Priors and Approximative Gibbs Sampling Karsten Vogt, Oliver M¨uller and J¨orn Ostermann Institut f¨ur Informationsverarbeitung (tnt) Leibniz Universit¨at Hannover, Germany {vogt, omueller," 83e7c51c4d6f04049f5a3dbf4ac9e129ed96caee,Spatio-temporal Pain Recognition in CNN-Based Super-Resolved Facial Images,"Aalborg Universitet Spatio-Temporal Pain Recognition in CNN-based Super-Resolved Facial Images Bellantonio, Marco; Haque, Mohammad Ahsanul; Rodriguez, Pau; Nasrollahi, Kamal; Telve, Taisi; Guerrero, Sergio Escalera; Gonzàlez, Jordi; Moeslund, Thomas B.; Rasti, Pejman; Anbarjafari, Gholamreza Published in: Video Analytics DOI (link to publication from Publisher): 0.1007/978-3-319-56687-0_13 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Bellantonio, M., Haque, M. A., Rodriguez, P., Nasrollahi, K., Telve, T., Guerrero, S. E., ... Anbarjafari, G. (2017). Spatio-Temporal Pain Recognition in CNN-based Super-Resolved Facial Images. In Video Analytics: Face and Facial Expression Recognition and Audience Measurement Springer. Lecture Notes in Computer Science, Vol.. 0165 https://doi.org/10.1007/978-3-319-56687-0_13 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners" 833ada09759039b7c620b8930a50a0521d70b2c7,Attend in Groups: A Weakly-Supervised Deep Learning Framework for Learning from Web Data,"Attend in groups: a weakly-supervised deep learning framework for learning from web data Bohan Zhuang∗, Lingqiao Liu∗, Yao Li, Chunhua Shen, Ian Reid The University of Adelaide; and Australian Centre for Robotic Vision . Experiments . . . . . .1. Datasets . . . . . . . . . . . . . . .2. Implementation details . . . . . . . . . . . .3. Evaluation on the WebCars . . . . . . . . . . . . . . . . . . . .4. Analysis of group size . .5. Web Images re-ranking . . . . . . . . . . . .6. Evaluation on Web Images + ImageNet 5. Conclusion" 8309e8f27f3fb6f2ac1b4343a4ad7db09fb8f0ff,Generic versus Salient Region-Based Partitioning for Local Appearance Face Recognition,"Generic versus Salient Region-based Partitioning for Local Appearance Face Recognition Hazım Kemal Ekenel and Rainer Stiefelhagen Computer Science Depatment, Universit¨at Karlsruhe (TH) Am Fasanengarten 5, Karlsruhe 76131, Germany http://isl.ira.uka.de/cvhci" 831cbffbfe39a059b1212d49e8fdfd458d1d01c5,"Globally Maximizing, Locally Minimizing: Unsupervised Discriminant Projection with Applications to Face and Palm Biometrics","Globally Maximizing, Locally Minimizing: Unsupervised Discriminant Projection with Applications to Face and Palm Biometrics Jian Yang, David Zhang, Senior Member, IEEE, Jing-yu Yang, and Ben Niu" 83ca4cca9b28ae58f461b5a192e08dffdc1c76f3,Detecting emotional stress from facial expressions for driving safety,"DETECTING EMOTIONAL STRESS FROM FACIAL EXPRESSIONS FOR DRIVING SAFETY Hua Gao, Anil Y¨uce, Jean-Philippe Thiran Signal Processing Laboratory (LTS5), ´Ecole Polytechnique F´ed´erale de Lausanne, Switzerland" 83b7578e2d9fa60d33d9336be334f6f2cc4f218f,The S-HOCK dataset: Analyzing crowds at the stadium,"The S-HOCK Dataset: Analyzing Crowds at the Stadium Davide Conigliaro1,3, Paolo Rota2, Francesco Setti3, Chiara Bassetti3, Nicola Conci4, Nicu Sebe4, Marco Cristani1, University of Verona. 2Vienna Institute of Technology. 3ISTC–CNR (Trento). 4University of Trento. The topic of crowd modeling in computer vision usually assumes a sin- gle generic typology of crowd, which is very simplistic. In this paper we dopt a taxonomy that is widely accepted in sociology, focusing on a partic- ular category, the spectator crowd, which is formed by people “interested in watching something specific that they came to see” [1]. This can be found t the stadiums, amphitheaters, cinema, etc. In particular, we propose a novel dataset, the Spectators Hockey (S-HOCK), which deals with 4 hockey matches during an international tournament. The dataset is unique in the crowd literature, and in general in the surveillance realm. The dataset analyzes the crowd at different levels of detail. At the highest level, it models the network of social connections mong the public (who knows whom in the neighborhood), what is the sup- ported team and what has been the best action in the match; all of this has een obtained by interviews at the stadium. At a medium level, spectators re localized, and information regarding the pose of their heads and body is given. Finally, at a lowest level, a fine grained specification of all the actions" 83cd39c3a171dbf3e684899c79bb596652d32d91,TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents,"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents Yuexin Ma1,2, Xinge Zhu3, Sibo Zhang1, Ruigang Yang1, Wenping Wang2, Dinesh Manocha4 Baidu Research, Baidu Inc.1, The University of Hong Kong2, The Chinese University of Hong Kong3, University of Maryland at College Park4 http://gamma.cs.unc.edu/TPredict/TrafficPredict.html" 8395cf3535a6628c3bdc9b8d0171568d551f5ff0,Entropy Non-increasing Games for the Improvement of Dataflow Programming,"Entropy Non-increasing Games for the Improvement of Dataflow Programming Norbert B´atfai, Ren´at´o Besenczi, Gerg˝o Bogacsovics, Fanny Monori∗ February 16, 2017" 831fbef657cc5e1bbf298ce6aad6b62f00a5b5d9,Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning, 833f6ab858f26b848f0d747de502127406f06417,Learning weighted similarity measurements for unconstrained face recognition,"978-1-4244-5654-3/09/$26.00 ©2009 IEEE ICIP 2009" 83a4b9c9ae3f75bf7e4a3222c46d99be7b7998ab,A random forest approach to segmenting and classifying gestures,"A Random Forest Approach to Segmenting and Classifying Gestures Ajjen Joshi1, Camille Monnier2, Margrit Betke1 and Stan Sclaroff1 Department of Computer Science, Boston Univeristy, Boston, MA 02215 USA Charles River Analytics, Cambridge, MA 02138 USA" 83e71455ee2070617ea35c02f03b7451187985d1,Faces Recognition with Image Feature Weights and Least Mean Square Learning Approach,"Faces Recognition with Image Feature Weights and Least Mean Square Learning Approach Dept. of Electrical Engineering, National Taiwan Uni. of Sci. & Technology, Taipei, Taiwan Wei-Li Fang, Ying-Kuei Yang and Jung-Kuei Pan Email:" 834b15762f97b4da11a2d851840123dbeee51d33,Landmark-free smile intensity estimation,"Landmark-free smile intensity estimation J´ulio C´esar Batista, Olga R. P. Bellon and Luciano Silva IMAGO Research Group - Universidade Federal do Paran´a Fig. 1. Overview of our method for smile intensity estimation" 839e7491cd6032162ee4bb6d73b7122cc4af12f1,Improved Person Detection on Omnidirectional Images with Non-maxima Supression,"Improved Person Detection on Omnidirectional Images with Non-maxima Supression Roman Seidel, André Apitzsch, Gangolf Hirtz Department of Information Technology, Chemnitz University of Technology, Chemnitz, Germany {roman.seidel, andre.apitzsch, Keywords: Ambient Assisted Living, Convolutional Neural Networks, Object Detection, Non-maxima Supression, Omnidirectional Images" 833da007d1cb183287728b720a03237bee072cd7,A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection,"A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection Zhaowei Cai1, Quanfu Fan2, Rogerio S. Feris2, and Nuno Vasconcelos1 SVCL, UC San Diego IBM T. J. Watson Research" 8399c71abc9a820bacd9c4e21c85c461c0b830b3,"Adaboost with ""Keypoint Presence Features"" for Real-Time Vehicle Visual Detection","Author manuscript, published in ""16th World Congress on Intelligent Transport Systems (ITSwc'2009), Sweden (2009)""" 83b20fdd3eafd21a6971dacc73d85c484a093bfc,Interleaved Structured Sparse Convolutional Neural Networks,"Interleaved Structured Sparse Convolutional Neural Networks Guotian Xie1,2,∗ Jingdong Wang3† Ting Zhang3 Jianhuang Lai1,2 Richang Hong4 Guo-Jun Qi5 Sun Yat-Sen University 2Guangdong Key Laboratory of Information Security Technology Microsoft Research 4Hefei University of Technology 5University of Central Florida" 839a359df925e6b159c8402bc81c39790a26febb,Automatic Person Identification using Multiple Cues,"ICCAS2005 June 2-5, KINTEX, Gyeonggi-Do, Korea Automatic Person Identification using Multiple Cues Danuwat Swangpol and Thanarat Chalidabhongse Faculty of Information Technology, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand (Tel: +66-2-737-2551; E-mail: ," 838420cebfdad4e93221f8fe203c09155983141a,Subspace Alignment Based Domain Adaptation for RCNN Detector,"RAJ, NAMBOODIRI, TUYTELAARS: ADAPTING RCNN DETECTOR Subspace Alignment Based Domain Adaptation for RCNN Detector Anant Raj Vinay P. Namboodiri Department of Electrical Engineering, IIT Kanpur, Kanpur, India. Department of Computer Science and Engineering, IIT Kanpur, Kanpur, India. ESAT, PSI-VISICS KU Leuven, Heverlee, Belgium" 83cc0768927dfdac32f2d5753cf70ac23b7cddeb,BLACKFACE SURVEILLANCE CAMERA DATABASE FOR EVALUATING FACE RECOGNITION IN LOW QUALITY SCENARIOS,"ISSN: Print - 2277 - 0593 Online - 2315 - 7461 © FUNAAB 2016 BLACKFACE SURVEILLANCE CAMERA DATABASE FOR EVALUATING FACE RECOGNITION IN LOW QUALITY Journal of Natural Science, Engineering nd Technology SCENARIOS Y. AKINGBOYE *1A. ABAYOMI-ALLI, 2E. O. OMIDIORA, 3S. O. OLABIYISI, 4J. A. OJO AND 5A. Department of Computer Science, Federal University of Agriculture, Abeokuta, Nigeria. ,3Department of Computer Science and Engineering, Ladoke Akintola University of Technology, Ogbomoso, Nigeria. Department of Electrical and Electronic Engineering, Ladoke Akintola University of Technology, Ogbomoso, Nigeria. 5Department of Electrical and Computer Engineering, Igbinedion University Okada, Nigeria. *Corresponding author: Tel: +2347030672420" 833bdee366f1e6250dea59bdebdcad271c7cfddd,Bayesian non-parametrics for multi-modal segmentation,"Bayesian Non-Parametrics for Multi-Modal Segmentation Thesis for obtaining the title of Doctor of Engineering Science (Dr.-Ing.) of the Faculty of Natural Science and Technology I of Saarland University Wei-Chen Chiu, M.Sc. Saarbrücken September 2016" 833fbf0e4be3ba82e7a1efdbc16813ee849d9942,Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Cameras,"SUBMITTED TO IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Cameras Liuyuan Deng, Ming Yang, Hao Li, Tianyi Li, Bing Hu, Chunxiang Wang" 8373c162ae0574eac1239f075fafeda02de56e6a,Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose,"Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose Daniil Osokin Intel" 833cd4265bd8162d3cfb483ce8f31eaef28e7a2e,TOWARDS EFFECTIVE GANS,"Under review as a conference paper at ICLR 2018 TOWARDS EFFECTIVE GANS FOR DATA DISTRIBUTIONS WITH DIVERSE MODES Anonymous authors Paper under double-blind review" 83ce2c969ea323784b9098b9b170e015d559a1df,Detecting domestic objects with ensembles of view-tuned support vector machine cascades trained on Web images,"Detecting Domestic Objects with Ensembles of View-tuned Support Vector Machine Cascades Trained on Web Images Marco Kortkamp" 8306e384e7ca48445843bc025b08236cd181d7c6,Histogram of Oriented Gradients with Cell Average Brightness for Human Detection,"Metrol. Meas. Syst., Vol. XXIII (2016), No. 1, pp. 27–36. METROLOGY AND MEASUREMENT SYSTEMS Index 330930, ISSN 0860-8229 www.metrology.pg.gda.pl HISTOGRAM OF ORIENTED GRADIENTS WITH CELL AVERAGE BRIGHTNESS FOR HUMAN DETECTION Marek Wójcikowski Gdańsk University of Technology, Faculty of Electronics, Telecommunications and Informatics, G. Narutowicza 11/12, 80-233 Gdańsk, Poland ((cid:1) +48 58 347 1974)" 832e1d128059dd5ed5fa5a0b0f021a025903f9d5,Pairwise Conditional Random Forests for Facial Expression Recognition,"Pairwise Conditional Random Forests for Facial Expression Recognition Arnaud Dapogny1 Kevin Bailly1 S´everine Dubuisson1 Sorbonne Universit´es, UPMC Univ Paris 06, CNRS, ISIR UMR 7222, 4 place Jussieu 75005 Paris" 83c332971c4534907afc4865179c2de30f2792c4,Sparse and Dense Hybrid Representation via Dictionary Decomposition for Face Recognition,"Sparse And Dense Hybrid Representation via Dictionary Decomposition for Face Recognition Xudong Jiang, Senior Member, IEEE, and Jian Lai, Student Member, IEEE" 83686b88e989bc6c9b66302e16546bde23ee34da,Coarse to fine non-rigid registration: a chain of scale-specific neural networks for multimodal image alignment with application to remote sensing,"chain of scale-specific neural networks for multimodal image alignment Coarse to fine non-rigid registration: with application to remote sensing Armand Zampieri1, Guillaume Charpiat2, Yuliya Tarabalka1 Titane team, INRIA Sophia-Antipolis TAU team, LRI, INRIA Saclay, Universit´e Paris-Sud This project started early 2017 and this paper was sub- mitted for publication in November 2017. Introduction" 83e7254431486d24715d4170680c6cbc8bdb2328,Image retrieval using visual attention,"IMAGE RETRIEVAL USING VISUAL ATTENTION Liam M. Mayron A Dissertation Submitted to the Faculty of The College of Engineering and Computer Science in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy Florida Atlantic University Boca Raton, Florida May 2008" 8387c58a5a3fd847f9b03760842dd49fec7cbb0e,Two-year-olds with autism orient to nonsocial contingencies rather than biological motion,"Vol 459 | 14 May 2009 | doi:10.1038/nature07868 LETTERS Two-year-olds with autism orient to non-social ontingencies rather than biological motion Ami Klin1, David J. Lin1{, Phillip Gorrindo1{, Gordon Ramsay1,2 & Warren Jones1,3 Typically developing human infants preferentially attend to bio- logical motion within the first days of life1. This ability is highly onserved across species2,3 and is believed to be critical for filial ttachment and for detection of predators4. The neural under- pinnings of biological motion perception are overlapping with rain regions involved in perception of basic social signals such s facial expression and gaze direction5, and preferential attention to biological motion is seen as a precursor to the capacity for ttributing intentions to others6. However, in a serendipitous observation7, we recently found that an infant with autism failed to recognize point-light displays of biological motion, but was instead highly sensitive to the presence of a non-social, physical ontingency that occurred within the stimuli by chance. This observation raised the possibility that perception of biological motion may be altered in children with autism from a very early" 8322ed1a3db7c63af40280a782e39fb01bfe96dd,Class label autoencoder for zero-shot learning,"Class label autoencoder for zero-shot learning Guangfeng Lina,∗, Caixia Fana, Wanjun Chena, Yajun Chena, Fan Zhaoa Information Science Department, Xian University of Technology, 5 South Jinhua Road, Xi’an, Shaanxi Province 710048, PR China" 8331fb280f083767fe85ba476862e519e0275233,OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation,"Detection in the wild through dataset merging and soft distillation OMNIA Faster R-CNN: Alexandre Rame ∗ 1, Emilien Garreau † 1, Hedi Ben-Younes ‡ 1,2, and Charles Ollion § 1 Heuritech 2LIP6" 83d0b7100ddce32e37af72585f9aa4181e6447e3,Online Social Behavior Modeling for Multi-target Tracking,"Online Social Behavior Modeling for Multi-Target Tracking Shu Zhang1 Abir Das1 Chong Ding2 Amit K. Roy-Chowdhury1 University of California, Riverside, CA 92521 USA" 83acbf0bee402b0472ff101cee5942f4137d91c3,Semi-automatic Annotation on Image Segmentation Hierarchies,"Semi-automatic Annotation on Image Segmentation Hierarchies DIPLOMARBEIT zur Erlangung des akademischen Grades Diplom-Ingenieur im Rahmen des Studiums Visual Computing eingereicht von Georg M. Zankl Matrikelnummer 0625388 n der Fakultät für Informatik der Technischen Universität Wien Betreuung: Univ.Ass. Dipl.-Ing. Dr.techn. Yll Haxhimusa Mitwirkung: Ing. Dr. techn. Adrian Ion Wien, 12.10.2012 (Unterschrift Verfasser) (Unterschrift Betreuung) A-1040 Wien (cid:5) Karlsplatz 13 (cid:5) Tel. +43-1-58801-0 (cid:5) www.tuwien.ac.at Technische Universität Wien" 8323af714efe9a3cadb31b309fcc2c36c8acba8f,Automatic Real-Time Facial Expression Recognition for Signed Language Translation,"Automatic Real-Time Facial Expression Recognition for Signed Language Translation Jacob Richard Whitehill A thesis submitted in partial fulfillment of the requirements for the de- gree of Magister Scientiae in the Department of Computer Science, University of the Western Cape. May 2006" 834f5ab0cb374b13a6e19198d550e7a32901a4b2,Face Translation between Images and Videos using Identity-aware CycleGAN,"Face Translation between Images and Videos using Identity-aware CycleGAN Zhiwu Huang†, Bernhard Kratzwald†, Danda Pani Paudel†, Jiqing Wu†, Luc Van Gool†‡ Computer Vision Lab, ETH Zurich, Switzerland VISICS, KU Leuven, Belgium {zhiwu.huang, paudel, jwu," 83963d1454e66d9cc82e28ff4efc562f5fe6b7d3,"Automated detection of feeding strikes by larval fish using continuous high-speed digital video: a novel method to extract quantitative data from fast, sparse kinematic events.","© 2016. Published by The Company of Biologists Ltd | Journal of Experimental Biology (2016) 219, 1608-1617 doi:10.1242/jeb.133751 METHODS & TECHNIQUES Automated detection of feeding strikes by larval fish using ontinuous high-speed digital video: a novel method to extract quantitative data from fast, sparse kinematic events Eyal Shamur1,‡, Miri Zilka2,*,‡, Tal Hassner1, Victor China3,4, Alex Liberzon5 and Roi Holzman3,4,§ the observer and subject" 83ef7de2669bb2827208fd3a64ac910e276fbdb4,Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery,"Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery Jamie Sherrah Defence Science & Technology Group Edinburgh, South Australia email: https://au.linkedin.com/jsherrah June 9, 2016" 8380b8f4e36c993eef23af42ccb382ae60aceabf,"URBAN-i: From urban scenes to mapping slums, transport modes, and pedestrians in cities using deep learning and computer vision","URBAN-i: From urban scenes to mapping slums, transport modes, and pedestrians in cities using deep learning and computer vision Mohamed R. Ibrahim1, James Haworth2 and Tao Cheng3 Department of Civil, Environmental and Geomatic Engineering, University College London (UCL)" 83fd5c23204147844a0528c21e645b757edd7af9,USDOT number localization and recognition from vehicle side-view NIR images,"USDOT Number Localization and Recognition From Vehicle Side-View NIR Images Orhan Bulan, Safwan Wshah, Ramesh Palghat, Vladimir Kozitsky and Aaron Burry Palo Alto Research Center (PARC) 800 Phillips Rd. Webster NY 14580" 8326d3e57796dad294ab1c14a0688221550098b6,ABC-GAN: Adaptive Blur and Control for improved training stability of Generative Adversarial Networks,"Adaptive Blur and Control for improved training stability of Generative Adversarial Networks ABC-GAN: Igor Susmelj 3 Eirikur Agustsson 3 Radu Timofte 3" 832a9584e85af1675d49ee35fd13283b21ce3a3f,Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy,"Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy Daniel S´aez Trigueros, Li Meng School of Engineering and Technology University of Hertfordshire Hatfield AL10 9AB, UK Margaret Hartnett GBG plc London E14 9QD, UK" bb2944569a2b3d3b8340b36d4903c8cddf20047f,Improving Regression Performance with Distributional Losses,"Improving Regression Performance with Distributional Losses Ehsan Imani 1 Martha White 1" bb79bb04e569f9319fbc9d8e1f275bbb2cf8d32e,NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning,"NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning Álvaro Peris, Francisco Casacuberta Pattern Recognition and Human Language Technology Research Center, Universitat Politècnica de València, Spain" bb131650627cf2d1da570589f6c540041df1ae92,Improving the Intra Class Distance using RBSQI Technique for Facial Images with Illumination Variations,"Volume 2 Special Issue ISSN 2079-8407 Journal of Emerging Trends in Computing and Information Sciences ©2010-11 CIS Journal. All rights reserved. http://www.cisjournal.org Improving the Intra Class Distance using RBSQI Technique for Facial Images with Illumination Variations K. R. Singh1, M. A. Zaveri2, M.M. Raghuwanshi3 ,2Computer Engineering Department, S.V.National Institute of Technology, Surat, 329507, India. NYSS College of Engineering and Research, Nagpur, 441 110, India." bbf534b8ee9455b8e492a252bef26f9293d4f91a,Effects of cannabis use and subclinical depression on the P3 event-related potential in an emotion processing task,"Observational Study Medicine® Effects of cannabis use and subclinical depression on the P3 event-related potential in an emotion processing task Lucy J. Troup, PhD , Robert D. Torrence, MS, Jeremy A. Andrzejewski, BSc, Jacob T. Braunwalder, BSc" bb35ef89addbbc28d960bc0cab70d8a29fdf6eee,A Survey on Multi-Task Learning,"A Survey on Multi-Task Learning Yu Zhang and Qiang Yang" bb667cbbf050040fa39cd9e756cd5bf485fccf32,Effective Deterministic Initialization for $k$-Means-Like Methods via Local Density Peaks Searching,"Effective Deterministic Initialization for k-Means-Like Methods via Local Density Peaks Searching Fengfu Li, Hong Qiao, and Bo Zhang" bb021f58f8822d12f5747d583a46005ade4a0b10,Breaking Microsoft ’ s CAPTCHA,"Breaking Microsoft’s CAPTCHA Colin Hong Bokil Lopez-Pineda Karthik Rajendran Adri`a Recasens May 2015" bbc4bbf7aa80a8108d62644fea24e6f70a805df9,Inducing Wavelets into Random Fields via Generative Boosting,"Inducing Wavelets into Random Fields via Generative Boosting Jianwen Xie, Yang Lu, Song-Chun Zhu, and Ying Nian Wu∗ Department of Statistics, University of California, Los Angeles, USA" bb7c5a521607a02e7a291dca7fc33b595c3b7bff,Texture Classification using Local Binary Patterns and Modular PCA,"ISSN: 2278 – 1323 International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) Volume 5, Issue 5, May 2016 Texture Classification using Local Binary Patterns and Modular PCA Sayanshree Ghosh, Srimanta Kundu and Sayantari Ghosh www.ijarcet.org" bbf5575f0d20b79b61c8c0d8b7c2a57224c359de,Emotion Recognition from Decision Level Fusion of Visual and Acoustic Features using Hausdorff Classifier,"Emotion Recognition from Decision Level Fusion of Visual and Acoustic Features using Hausdorff Classifier H.D.Vankayallapati1, K.R.Anne2, and K. Kyamakya1 Institute of Smart System Technologies, Transportation Informatics Group University of Klagenfurt, Klagenfurt, Austria. Department of Information Technology, TIFAC-CORE in Telematics VR Siddhartha Engineering College, Vijayawada, India." bb893fac40eb901229567abb507a8cb82553d198,Will the Pedestrian Cross? Probabilistic Path Prediction Based on Learned Motion Features,"Will the Pedestrian Cross? Probabilistic Path Prediction Based on Learned Motion Features Christoph G. Keller1, Christoph Hermes2, and Dariu M. Gavrila3,4 Image & Pattern Analysis Group, Univ. of Heidelberg, Germany Applied Informatics Group, Univ. of Bielefeld, Germany Environment Perception, Group Research, Daimler AG, Ulm, Germany Intelligent Systems Lab, Fac. of Science, Univ. of Amsterdam, The Netherlands" bb980dd94463b03c6584513bcccf780e43f089b2,Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities,"Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities Matthias Rottmann∗, Pascal Colling∗, Thomas Paul Hack†, Fabian H¨uger‡, Peter Schlicht‡ and Hanno Gottschalk∗" bb4650130c460f413e97b0328624a485bf094967,Dynamic Lexicon Generation for Natural Scene Images,"Dynamic Lexicon Generation for Natural Scene Images Yash Patel1,2, Lluis Gomez2, Mar¸cal Rusi˜nol2, and Dimosthenis Karatzas2 Computer Vision Center, Universitat Aut`onoma de Barcelona. CVIT, IIIT Hyderabad, India." bb1dc1e9e9c20d99b55f37b9e635457af86a065f,Neural Ctrl-F: Segmentation-Free Query-by-String Word Spotting in Handwritten Manuscript Collections,"Neural Ctrl-F: Segmentation-free Query-by-String Word Spotting in Handwritten Manuscript Collections Tomas Wilkinson Department of Information Technology Uppsala University Jonas Lindstr¨om Department of History Uppsala University Anders Brun Department of Information Technology Uppsala University" bb06c12e83255b2c3afca1e3e115e721c53b46b3,Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features,"Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features Marius Leordeanu1 Martial Hebert1 Rahul Sukthankar2,1 Carnegie Mellon University 2Intel Research Pittsburgh" bb127015474fdc51d4cd6b4dda7176a8c778ea49,Examining the Impact of Blur on Recognition by Convolutional Networks.,"Examining the Impact of Blur on Recognition by Convolutional Networks Igor Vasiljevic University of Chicago Ayan Chakrabarti TTI-Chicago Gregory Shakhnarovich TTI-Chicago" bb288a5c653659411f95ef5db8e1ad652e0a8173,Learning Depth From Single Images With Deep Neural Network Embedding Focal Length,"Learning Depth from Single Images with Deep Neural Network Embedding Focal Length Lei He, Guanghui Wang (Senior Member, IEEE) and Zhanyi Hu" bba22e04fbe124bf58330e5d911d873a80afa0eb,Probabilistic Global Scale Estimation for MonoSLAM Based on Generic Object Detection,"Probabilistic Global Scale Estimation for MonoSLAM Based on Generic Object Detection Centro de Investigaci´on en Matem´aticas - Universidad de Guanajuato Jalisco S/N, Col. Valenciana CP: 36023 Guanajuato, Gto, Mxico Edgar Sucar, Jean-Bernard Hayet" bbab2c3d0ebc0957c5e962298ffd8c6d4bc25c5a,Have we met before? Neural correlates of emotional learning in women with social phobia.,"Research Paper Have we met before? Neural correlates of emotional learning in women with social phobia Inga Laeger, MA; Kati Keuper, MA; Carina Heitmann, MA; Harald Kugel, PhD; Christian Dobel, PhD; Annuschka Eden, MA; Volker Arolt, MD; Pienie Zwitserlood, PhD; Udo Dannlowski, MD, PhD*; Peter Zwanzger, MD* Laeger, Heitmann, Arolt, Dannlowski, Zwanzger — Department of Psychiatry, University of Muenster, Germany; Keuper, Dobel, Eden — Institute for Biomagnetism and Biosignalanalysis, University of Muenster, Germany; Kugel — Department of Clinical Radiology, University of Muenster, Germany; Zwitserlood — Institute for Psychology, University of Muenster, Ger- many; Dannlowski — Department of Psychiatry, University of Marburg, Germany Background: Altered memory processes are thought to be a key mechanism in the etiology of anxiety disorders, but little is known about the neural correlates of fear learning and memory biases in patients with social phobia. The present study therefore examined whether pa- tients with social phobia exhibit different patterns of neural activation when confronted with recently acquired emotional stimuli. Methods: Patients with social phobia and a group of healthy controls learned to associate pseudonames with pictures of persons displaying either a fearful or a neutral expression. The next day, participants read the pseudonames in the magnetic resonance imaging scanner. Afterwards, memory tests were carried out. Results: We enrolled 21 patients and 21 controls in our study. There were no group differences for learning performance, and results of the memory tests were mixed. On a neural level, patients showed weaker amygdala activation than ontrols for the contrast of names previously associated with fearful versus neutral faces. Social phobia severity was negatively related to mygdala activation. Moreover, a detailed psychophysiological interaction analysis revealed an inverse correlation between disorder severity and frontolimbic connectivity for the emotional > neutral pseudonames contrast. Limitations: Our sample included only women." bb1f4c8e4f310047e50b7dc41d87292025d42eb7,Intersubject Differences in False Nonmatch Rates for a Fingerprint-Based Authentication System,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2009, Article ID 896383, 9 pages doi:10.1155/2009/896383 Research Article Intersubject Differences in False Nonmatch Rates for Fingerprint-Based Authentication System Jeroen Breebaart, Ton Akkermans, and Emile Kelkboom Philips Research, HTC 34 MS61, 5656 AE Eindhoven, The Netherlands Correspondence should be addressed to Jeroen Breebaart, Received 4 September 2008; Accepted 7 July 2009 Recommended by Jonathon Phillips The intersubject dependencies of false nonmatch rates were investigated for a minutiae-based biometric authentication process using single enrollment and verification measurements. A large number of genuine comparison scores were subjected to statistical inference tests that indicated that the number of false nonmatches depends on the subject and finger under test. This result was also observed if subjects associated with failures to enroll were excluded from the test set. The majority of the population (about 90%) showed a false nonmatch rate that was considerably smaller than the average false nonmatch rate of the complete population. The remaining 10% could be characterized as “goats” due to their relatively high probability for a false nonmatch. The image quality reported by the template extraction module only weakly correlated with the genuine comparison scores. When multiple verification attempts were investigated, only a limited benefit was observed for “goats,” since the conditional probability for a false" bb489e4de6f9b835d70ab46217f11e32887931a2,Everything You Wanted to Know about Deep Learning for Computer Vision but Were Afraid to Ask,"Everything you wanted to know about Deep Learning for Computer Vision but were fraid to ask Moacir A. Ponti, Leonardo S. F. Ribeiro, Tiago S. Nazare ICMC – University of S˜ao Paulo S˜ao Carlos/SP, 13566-590, Brazil Tu Bui, John Collomosse CVSSP – University of Surrey Guildford, GU2 7XH, UK Email: [ponti, leonardo.sampaio.ribeiro, Email: [t.bui, tools," bb22104d2128e323051fb58a6fe1b3d24a9e9a46,Analyzing Facial Expression by Fusing Manifolds,")=OEC .=?E= -NFHAIIE >O .KIEC 9A;= +D=C1,2 +DK5C +DA1,3 ;E2EC 0KC1,2,3 1IJEJKJA B 1BH=JE 5?EA?A 5EE?= 6=EM= ,AFJ B +FKJAH 5?EA?A 1BH=JE -CEAAHEC =JE= 6=EM= 7ELAHIEJO IJEJKJA B AJMHEC =JE= 6=EM= 7ELAHIEJO {wychang, )>IJH=?J .A=JKHA HAFHAIAJ=JE ?=IIE?=JE =HA JM =H EIIKAI E B=?E= ANFHAIIE ==OIEI 1 JDA F=IJ IJ AEJDAH DEIJE? H ?= HAFHA IAJ=JE BH ==OIEI 1 AIIA?A ?= EBH=JE =EO B?KIAI  JDA IK>JA L=HE=JEI B ANFHAIIEI DEIJE? HAFHAIAJ=JE IJHAIIAI  C>= JEAI 6 J=A JDA B >JD = HAFHAIAJ=JE EI E JDEI F=FAH A=HEC EI J ?D=H=?JAHEA C>= ?= EBH= JE 7EA IA KIEC A=H EC =FFH=?DAI B JDA HAFHAIAJ=JE =HA >O = A=HEC JA?DEGKA 6 EJACH=JA JDAIA ABBA?JELAO = BKIE ?=IIEAH EI MDE?D ?= DAF J AFO IKEJ=>A ?>E=JE MAECDJI B B=?E= ?FAJI J = ANFHAIIE +FHADA IELA ?F=HEII  B=?E= ANFHAIIE HA?CEJE =HA J JDA ABBA?JELAAII B KH =CHEJD A=EEC DK= AJEI F=OI = EFHJ=J HA E DK= ?KE?=JE 6" bb08d1570685a20861e9b8c15c57aae9c01d3eac,Modeling cooperative navigation in dense human crowds,"Modeling Cooperative Navigation in Dense Human Crowds Anirudh Vemula1, Katharina Muelling1 and Jean Oh1" bbd1eb87c0686fddb838421050007e934b2d74ab,Look at Boundary: A Boundary-Aware Face Alignment Algorithm,"(68 points) COFW (29 points) AFLW (19 points) Figure1:Thefirstcolumnshowsthefaceimagesfromdifferentdatasetswithdifferentnumberoflandmarks.Thesecondcolumnillustratestheuniversallydefinedfacialboundariesestimatedbyourmethods.Withthehelpofboundaryinformation,ourapproachachieveshighaccuracylocalisationresultsacrossmultipledatasetsandannotationprotocols,asshowninthethirdcolumn.Differenttofacedetection[45]andrecognition[75],facealignmentidentifiesgeometrystructureofhumanfacewhichcanbeviewedasmodelinghighlystructuredout-put.Eachfaciallandmarkisstronglyassociatedwithawell-definedfacialboundary,e.g.,eyelidandnosebridge.However,comparedtoboundaries,faciallandmarksarenotsowell-defined.Faciallandmarksotherthancornerscanhardlyremainthesamesemanticallocationswithlargeposevariationandocclusion.Besides,differentannotationschemesofexistingdatasetsleadtoadifferentnumberoflandmarks[28,5,66,30](19/29/68/194points)andanno-tationschemeoffuturefacealignmentdatasetscanhardlybedetermined.Webelievethereasoningofauniquefacial" bbc8254b170918d619574496c138dac101dee61f,Context-aware robot navigation using interactively built semantic maps,"Research Article Akansel Cosgun* and Henrik I. Christensen Context-aware robot navigation using interactively built semantic maps Open Access" bba281fe9c309afe4e5cc7d61d7cff1413b29558,An unpleasant emotional state reduces working memory capacity: electrophysiological evidence,"Social Cognitive and Affective Neuroscience, 2017, 984–992 doi: 10.1093/scan/nsx030 Advance Access Publication Date: 11 April 2017 Original article An unpleasant emotional state reduces working memory capacity: electrophysiological evidence Jessica S. B. Figueira,1 Leticia Oliveira,1 Mirtes G. Pereira,1 Luiza B. Pacheco,1 Isabela Lobo,1,2 Gabriel C. Motta-Ribeiro,3 and Isabel A. David1 Laboratorio de Neurofisiologia do Comportamento, Departamento de Fisiologia e Farmacologia, Instituto Biome´dico, Universidade Federal Fluminense, Niteroi, Brazil, 2MograbiLab, Departamento de Psicologia, Pontifıcia Universidade Catolica do Rio de Janeiro, Rio de Janeiro, Brazil, and 3Laboratorio de Engenharia Pulmonar, Programa de Engenharia Biome´dica, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil Correspondence should be addressed to Isabel A. David, Departamento de Fisiologia e Farmacologia, Instituto Biome´dico, Universidade Federal Fluminense, Rua Hernani Pires de Mello, 101, Niteroi, RJ 24210-130, Brazil. E-mail:" bb6ac4e26499dea5bdedb05b269f40f56247b4c6,An Action Unit based Hierarchical Random Forest Model to Facial Expression Recognition, bb7f2c5d84797742f1d819ea34d1f4b4f8d7c197,From Images to 3D Shape Attributes.,"TO APPEAR IN TPAMI From Images to 3D Shape Attributes David F. Fouhey, Abhinav Gupta, Andrew Zisserman" 587f81ae87b42c18c565694c694439c65557d6d5,DeepFace : Face Generation using Deep Learning,"DeepFace: Face Generation using Deep Learning Hardie Cate Fahim Dalvi Zeshan Hussain" 581e920ddb6ecfc2a313a3aa6fed3d933b917ab0,Automatic Mapping of Remote Crowd Gaze to Stimuli in the Classroom,"Automatic Mapping of Remote Crowd Gaze to Stimuli in the Classroom Thiago Santini1, Thomas K¨ubler1, Lucas Draghetti1, Peter Gerjets2, Wolfgang Wagner3, Ulrich Trautwein3, and Enkelejda Kasneci1 University of T¨ubingen, T¨ubingen, Germany Leibniz-Institut f¨ur Wissensmedien, T¨ubingen, Germany Hector Research Institute of Education Sciences and Psychology, T¨ubingen, Germany" 58d16e23e1192be4acaf6a29c1f5995817146554,Bringing back simplicity and lightliness into neural image captioning,"Bringing back simplicity and lightliness into neural image captioning Jean-Benoit Delbrouck and St´ephane Dupont {jean-benoit.delbrouck, TCTS Lab, University of Mons, Belgium" 580054294ca761500ada71f7d5a78acb0e622f19,A Subspace Model-Based Approach to Face Relighting Under Unknown Lighting and Poses,"A Subspace Model-Based Approach to Face Relighting Under Unknown Lighting and Poses Hyunjung Shim, Student Member, IEEE, Jiebo Luo, Senior Member, IEEE, and Tsuhan Chen, Fellow, IEEE" 5865e824e3d8560e07840dd5f75cfe9bf68f9d96,Embodied conversational agents for multimodal automated social skills training in people with autism spectrum disorders,"RESEARCH ARTICLE Embodied conversational agents for multimodal automated social skills training in people with autism spectrum disorders Hiroki Tanaka1*, Hideki Negoro2, Hidemi Iwasaka3, Satoshi Nakamura1 Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma-shi, Nara, 630- 0101, Japan, 2 Center for Special Needs Education, Nara University of Education, Nara-shi, Nara, 630-8538, Japan, 3 Developmental Center for Child and Adult, Shigisan Hospital, Ikoma-gun, Nara, 636-0815, Japan" 58cb6677b77d5a79fc5b8058829693ca30b36ac5,Under Review as a Conference Paper at Iclr 2016 Learning Metrics by Learning Constrained Em- Beddings of Objects to R N,"Learning Similarity Metrics by Factorising Adjacency Matrices Henry Gouk† Bernhard Pfahringer† Michael Cree‡ Department of Computer Science, University of Waikato, Hamilton, New Zealand School of Engineering, University of Waikato, Hamilton, New Zealand" 581fb0f0405c7f0e60610d88ceaceb9af44d8569,Final Report : Smart Trash Net : Waste Localization and Classification,"Final Report: Smart Trash Net: Waste Localization and Classification Oluwasanya Awe Robel Mengistu Vikram Sreedhar December 15, 2017" 58081cb20d397ce80f638d38ed80b3384af76869,Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care,"Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care Hyunwoo Lee∗ Jooyoung Kim Dojun Yang Joon-Ho Kim Samsung Research, Samsung Electronics {hyun0772.lee, joody.kim, dojun.yang," 58fa85ed57e661df93ca4cdb27d210afe5d2cdcd,Facial expression recognition by re-ranking with global and local generic features,"Cancún Center, Cancún, México, December 4-8, 2016 978-1-5090-4847-2/16/$31.00 ©2016 IEEE" 587b607a176588b4646bcdb3d60b6204e98806fe,Extraction in Volumetric Bioimages A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy in Electrical Engineering,"UNIVERSITY OF CALIFORNIA RIVERSIDE Feature Extraction in Volumetric Bioimages A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Electrical Engineering Min Liu June 2012 Dissertation Committee: Professor Amit K. Roy-Chowdhury, Chairperson Professor Venugopala Gonehal Reddy Professor Ertem Tuncel" 58b80f0e484d32c9fe5b57648848e048270d435b,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 58888b30e9123c1b1709be1efa92898e090d7bd2,Person Re-Identification by Discriminative Selection in Video Ranking,"Person Re-Identification by Discriminative Selection in Video Ranking Taiqing Wang, Shaogang Gong, Xiatian Zhu, and Shengjin Wang" 5884eaf9f7c20d6d65892a9eb91020448262c5d8,Perceptual expectation evokes category-selective cortical activity.,"doi:10.1093/cercor/bhp188 Advance Access publication September 16, 2009 Perceptual Expectation Evokes Category- Selective Cortical Activity Michael Esterman and Steven Yantis Department of Psychological and Brain Sciences, Johns Hopkins University, Baltimore, MD 21218-2686, USA Selective visual attention directed to a location (even in the bsence of a stimulus) increases activity in the corresponding regions of visual cortex and enhances the speed and accuracy of target perception. We further explored top-down influences on perceptual representations by manipulating observers’ expectations bout the category of an upcoming target. Observers viewed display in which an object (either a face or a house) gradually emerged from a state of phase-scrambled noise; a cue established expectation about the object category. Observers were faster to ategorize faces (gender discrimination) or houses (structural discrimination) when the category of the partially scrambled object matched their expectation. Functional magnetic resonance imaging" 585efe3c8efd1a4fa2ed8221c278997521668bc1,Recognizing Face Images with Disguise Variations, 5801690199c1917fa58c35c3dead177c0b8f9f2d,Application of Object Based Classification and High Resolution Satellite Imagery for Savanna Ecosystem Analysis,"Remote Sens. 2010, 2, 2748-2772; doi:10.3390/rs2122748 OPEN ACCESS Article Application of Object Based Classification and High Resolution Satellite Imagery for Savanna Ecosystem Analysis ISSN 2072-4292 www.mdpi.com/journal/remotesensing Cerian Gibbes *, Sanchayeeta Adhikari, Luke Rostant, Jane Southworth, and Youliang Qiu Department of Geography & Land Use and Environmental Change Institute (LUECI), University of Florida, 3141 Turlington Hall, P. O. Box 117315, Gainesville, FL 32611, USA; E-Mails: (S.A.); (L.R.); (J.S.); (Y.Q.) * Author to whom correspondence should be addressed; E-Mail: Tel.: +1-352-392-0494; Fax: +1-352-392-8855. Received: 16 October 2010; in revised form: 7 December 2010 / Accepted: 8 December 2010 / Published: 10 December 2010" 589b30ebdb76659ce5d3a19cd9fa0e7a3466d85d,Very Low Resolution Face Recognition Problem,"Very Low Resolution Face Recognition Problem Wilman ZOU Pong C. Yuen" 58cbd5a31e92cff29e29e8b25ee79f30ff4e6d4b,Culture shapes spatial frequency tuning for face identification.,"Journal of Experimental Psychology: Human Perception and Performance 017, Vol. 43, No. 2, 294 –306 0096-1523/17/$12.00 © 2016 American Psychological Association http://dx.doi.org/10.1037/xhp0000288 Culture Shapes Spatial Frequency Tuning for Face Identification Université de Montréal and Université du Québec en Outaouais Jessica Tardif Daniel Fiset Université du Québec en Outaouais Ye Zhang Hangzhou Normal University Amanda Estéphan Université du Québec en Outaouais Qiuju Cai, Canhuang Luo, and Dan Sun Hangzhou Normal University Frédéric Gosselin Université de Montréal Caroline Blais" 5860cf0f24f2ec3f8cbc39292976eed52ba2eafd,COMPUTATION EvaBio : A TOOL FOR PERFORMANCE EVALUATION IN BIOMETRICS,"International Journal of Automated Identification Technology, 3(2), July-December 2011, pp. 51-60 COMPUTATION EvaBio: A TOOL FOR PERFORMANCE EVALUATION IN BIOMETRICS Julien Mahier, Baptiste Hemery, Mohamad El-Abed*, Mohamed T. El-Allam, Mohamed Y. Bouhaddaoui and Christophe Rosenberger GREYC Laboratory, ENSICAEN - University of Caen Basse Normandie - CNRS, 6 Boulevard Maréchal Juin, 14000 Caen Cedex - France" 58bf72750a8f5100e0c01e55fd1b959b31e7dbce,PyramidBox: A Context-assisted Single Shot Face Detector,"PyramidBox: A Context-assisted Single Shot Face Detector. Xu Tang∗, Daniel K. Du∗, Zeqiang He, and Jingtuo Liu† Baidu Inc." 58f7b9ebdb9b380cdfbef12b8abefceee0160a58,Public Document Document Evolution Executive Summary,"Project N° IST-2002-507634 - BioSecure D7.2.2 – Revision: b3 Contract Number: Project Acronym: Project Title: Instrument: Start Date of Project: Duration: Deliverable Number: Title of Deliverable: 8 April 2005 IST-2002-507634 BioSecure Biometrics for Secure Authentication Network of Excellence 01 June, 2004 6 months D7.2.2 Report on the face state of the art Contractual Due Date:" 580a39100e0d1466c914915a2a30ec0a57a94bcc,Voxblox: Building 3D Signed Distance Fields for Planning,"Voxblox: Building 3D Signed Distance Fields for Planning Helen Oleynikova, Zachary Taylor, Marius Fehr, Juan Nieto, and Roland Siegwart Autonomous Systems Lab, ETH Z¨urich" 58823377757e7dc92f3b70a973be697651089756,Automatic facial expression analysis,"Technical Report UCAM-CL-TR-861 ISSN 1476-2986 Number 861 Computer Laboratory Automatic facial expression analysis Tadas Baltrusaitis October 2014 5 JJ Thomson Avenue Cambridge CB3 0FD United Kingdom phone +44 1223 763500 http://www.cl.cam.ac.uk/" 5892f8367639e9c1e3cf27fdf6c09bb3247651ed,CASC Multimedia Information Retrieval Extract “ faces ” and,"Estimating Missing Features to Improve Multimedia Information Retrieval Abraham Bagherjeiran Nicole S. Love Chandrika Kamath (cid:3)" 5834555d239c27369e7a4167bb0c0fed725d761e,Improved illumination invariant homomorphic filtering using the dual tree complex wavelet transform,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 5808f5285bc60a73bc240621ad0fce606867ebc1,VAIN: Attentional Multi-agent Predictive Modeling,"VAIN: Attentional Multi-agent Predictive Modeling Yedid Hoshen Facebook AI Research, NYC" 587c48ec417be8b0334fa39075b3bfd66cc29dbe,Serial Dependence in the perception of attractiveness.,"Serial dependence in the perception of attractiveness Ye Xia Department of Psychology, University of California, Berkeley, CA, USA Allison Yamanashi Leib Department of Psychology, University of California, Berkeley, CA, USA David Whitney Department of Psychology, University of California, Berkeley, CA, USA Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA Vision Science Group, University of California, Berkeley, CA, USA The perception of attractiveness is essential for choices of food, object, and mate preference. Like perception of other visual features, perception of attractiveness is stable despite constant changes of image properties due to factors like occlusion, visual noise, and eye movements. Recent results demonstrate that perception" 58bb77dff5f6ee0fb5ab7f5079a5e788276184cc,Facial expression recognition with PCA and LBP features extracting from active facial patches,"Facial Expression Recognition with PCA and LBP Features Extracting from Active Facial Patches Yanpeng Liua, Yuwen Caoa, Yibin Lia, Ming Liu, Rui Songa Yafang Wang, Zhigang Xu , Xin Maa†" 58abb5001087f51dd2e9ab17b9fb8fb3567988e8,Array of Multilayer Perceptrons with No-class Resampling Training for Face Recognition,"Inteligencia Artificial 44(2009), 5-13 doi: 10.4114/ia.v13i44.1041 INTELIGENCIA ARTIFICIAL http://erevista.aepia.org/ Array of Multilayer Perceptrons with No-class Resampling Training for Face Recognition D. Capello1, C. Mart´ınez2,3, D. Milone2 and G. Stegmayer1 CIDISI-UTN-FRSF, CONICET, Lavaise 610 - Santa Fe (Argentina) Sinc(i)-FICH-UNL, CONICET, Ciudad Universitaria UNL - Santa Fe (Argentina) Laboratorio de Cibern´etica-FI-UNER, C.C. 47 Suc. 3-3100, Entre R´ıos (Argentina)" 5882e62866fe1fcf7f8458e0bd0bcb39057afce3,Attention to Head Locations for Crowd Counting,"Attention to Head Locations for Crowd Counting Youmei Zhang, Chunluan Zhou, Faliang Chang, and Alex C. Kot, Fellow Member, IEEE" 58a6eb3584b2f5df2f25d39a218904d510cae516,The UAVid Dataset for Video Semantic Segmentation,"The UAVid Dataset for Video Semantic Segmentation Ye Lyu1, George Vosselman1, Guisong Xia2, Alper Yilmaz3, Michael Ying Yang1∗" 0dccc881cb9b474186a01fd60eb3a3e061fa6546,Effective face frontalization in unconstrained images,"Effective Face Frontalization in Unconstrained Images Tal Hassner1, Shai Harel1 †, Eran Paz1 † and Roee Enbar2 The open University of Israel. 2Adience. Figure 1: Frontalized faces. Top: Input photos; bottom: our frontalizations, obtained without estimating 3D facial shapes. “Frontalization” is the process of synthesizing frontal facing views of faces ppearing in single unconstrained photos. Recent reports have suggested that this process may substantially boost the performance of face recogni- tion systems. This, by transforming the challenging problem of recognizing faces viewed from unconstrained viewpoints to the easier problem of rec- ognizing faces in constrained, forward facing poses. Previous frontalization methods did this by attempting to approximate 3D facial shapes for each query image. We observe that 3D face shape estimation from unconstrained photos may be a harder problem than frontalization and can potentially in- troduce facial misalignments. Instead, we explore the simpler approach of using a single, unmodified, 3D surface as an approximation to the shape of ll input faces. We show that this leads to a straightforward, efficient and easy to implement method for frontalization. More importantly, it produces esthetic new frontal views and is surprisingly effective when used for face recognition and gender estimation." 0d7cd7256784d29296065cce07e432142fd4cad2,Machine Learning Approach for Object Recognition,"Machine Learning Approach for Object Recognition V. N. Pawar and S. N. Talbar learning technique. The" 0d0041aefb16c5f7b1e593b440bb3df7b05b411c,Secure JPEG scrambling enabling privacy in photo sharing,"Secure JPEG Scrambling Enabling Privacy in Photo Sharing Lin Yuan, Pavel Korshunov, Touradj Ebrahimi Multimedia Signal Processing Group, EPFL De-ID workshop, Ljubljana, Slovenia 8/14/2015 Workshop on De-identification for Privacy Protection in Multimedia" 0dcc768631d9ede8a3679e980b37204b782781b2,Stating the Obvious: Extracting Visual Common Sense Knowledge,"San Diego, California, June 12-17, 2016. c(cid:13)2016 Association for Computational Linguistics Proceedings of NAACL-HLT 2016, pages 193–198," 0d0199e48d22ff4b80c983e3b28532f908467da7,Linear regression motion analysis for unsupervised temporal segmentation of human actions,"Linear Regression Motion Analysis for Unsupervised Temporal Segmentation of Human Actions Simon Jones, Ling Shao Department of Electronic and Electrical Engineering The University of Shef‌f‌ield, Mappin St, Shef‌f‌ield, S1 3JD, UK" 0d30066576c029cd888d7c759349379bdb0e88c2,"How Much Information Kinect Facial Depth Data Can Reveal About Identity, Gender and Ethnicity?","How Much Information Kinect Facial Depth Data Can Reveal about Identity, Gender and Ethnicity? Elhocine Boutellaaa;b, Messaoud Bengherabia, Samy Ait-Aoudiab, Abdenour Hadidc Centre de D(cid:19)eveloppement des Technologies Avanc(cid:19)ees (DZ), Ecole Nationale Sup(cid:18)erieure d’Informatique (DZ), University of Oulu (FI)" 0d96c9d14f079b7b8b6b56b4fa86f611a4ff237f,Semi-supervised low-rank mapping learning for multi-label classification,"Semi-supervised Low-Rank Mapping Learning for Multi-label Classification Liping Jing1, Liu Yang1, Jian Yu1, Michael K. Ng2 Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University. 2Department of Mathematics, Hong Kong Baptist University. With the rapid growth of online content such as images, videos, web pages, it is crucial to design a scalable and effective classification system to au- tomatically organize, store, and search the content. In conventional clas- sification, each instance is assumed to belong to exactly one class among finite number of candidate classes. However, in modern applications, an instance can have multiple labels. For example, an image can be annotated y many conceptual tags in semantic scene classification. Multi-label data have ubiquitously occurred in many application domains: multimedia infor- mation retrieval, tag recommendation, query categorization, gene function prediction, medical diagnosis, drug discovery and marketing. An important nd challenging research problem [1, 4] in multi-label learning is how to exploit and make use of label correlations. In this paper, we develop a novel method for multi-label learning when there is only a small number of labeled data. Our main idea is to design Semi-supervised Low-Rank Mapping (SLRM) from a feature space to a label space based on given multi-label data. More specifically, the SLRM model can be formularized as" 0da4c3d898ca2fff9e549d18f513f4898e960aca,The Headscarf Effect Revisited: Further Evidence for a Culture-Based Internal Face Processing Advantage.,"Wang, Y., Thomas, J., Weissgerber, S. C., Kazemini, S., Ul-Haq, I., & Quadflieg, S. (2015). The Headscarf Effect Revisited: Further Evidence for a 36. 10.1068/p7940 Peer reviewed version Link to published version (if available): 0.1068/p7940 Link to publication record in Explore Bristol Research PDF-document University of Bristol - Explore Bristol Research General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: http://www.bristol.ac.uk/pure/about/ebr-terms.html Take down policy Explore Bristol Research is a digital archive and the intention is that deposited content should not be removed. However, if you believe that this version of the work breaches copyright law please contact nd include the following information in your message: • Your contact details • Bibliographic details for the item, including a URL • An outline of the nature of the complaint" 0d760e7d762fa449737ad51431f3ff938d6803fe,LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems,"LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems Subarna Tripathi UC San Diego ∗ Gokce Dane Qualcomm Inc. Byeongkeun Kang UC San Diego Vasudev Bhaskaran Qualcomm Inc. Truong Nguyen UC San Diego" 0dd86ec40c90c436a1ec566501dc8429d85b9d88,Driver Gaze Zone Estimation Using Convolutional Neural Networks: A General Framework and Ablative Analysis,"Driver Gaze Zone Estimation using Convolutional Neural Networks: A General Framework and Ablative Analysis Sourabh Vora, Akshay Rangesh, and Mohan M. Trivedi" 0d4dbd59e42e615ccf6cd4f71203be97afac48fb,End-to-End Joint Semantic Segmentation of Actors and Actions in Video,"End-to-End Joint Semantic Segmentation of Actors and Actions in Video Jingwei Ji1, Shyamal Buch1, Alvaro Soto2, and Juan Carlos Niebles1 Stanford Vision and Learning Lab,2Pontificia Universidad Catlica de Chile {jingweij, shyamal," 0d8a2034bbdefa214d8debecc704cadc5b9ec6e8,SUBMITTED FOR THE DEGREE OF DOCTOR OF PHILOSOPHY AT THE UNIVERSITY OF SUSSEX,"A University of Sussex DPhil thesis Available online via Sussex Research Online: http://sro.sussex.ac.uk/ This thesis is protected by copyright which belongs to the author. This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the Author The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the Author When referring to this work, full bibliographic details including the uthor, title, awarding institution and date of the thesis must be given Please visit Sussex Research Online for more information and further details" 0d6008f2b2e198e9eac44e8ad68e590cf6b41c57,Human and chimpanzee face recognition in chimpanzees (Pan troglodytes): role of exposure and impact on categorical perception.,"007, Vol. 121, No. 6, 1145–1155 Copyright 2007 by the American Psychological Association 0735-7044/07/$12.00 DOI: 10.1037/0735-7044.121.6.1145 Human and Chimpanzee Face Recognition in Chimpanzees (Pan troglodytes): Role of Exposure and Impact on Categorical Perception Emory University and Yerkes National Primate Research Center Julie Martin-Malivel Kazunori Okada San Francisco State University The respective influences of exposure and inborn neural networks on conspecific and nonconspecific face processing remain unclear. Although the importance of exposure in the development of object and face recognition in general is well documented, studies explicitly comparing face recognition across species showed a species-specific effect. For instance, laboratory monkeys exposed daily to human faces were etter at discriminating monkeys than humans, suggesting that the role of exposure may not be the only factor affecting cross-species recognition. In the present study, the authors investigated conspecific and nonconspecific face recognition in chimpanzees (Pan troglodytes) from 2 primate centers that provided different exposure to chimpanzee and human faces. The authors showed that the chimpanzees from the enter providing more exposure to human faces than to chimpanzee faces were better at discriminating human faces than they were at discriminating chimpanzee faces. The chimpanzees from the other center did not show the same effect. A computational simulation was developed to evaluate the average" 0d82ac80275283c3dd26aca9e629ee6a9ca8a07a,An object-based semantic world model for long-term change detection and semantic querying,"An Object-Based Semantic World Model for Long-Term Change Detection and Semantic Querying Julian Mason and Bhaskara Marthi" 0dab1ab19a44b73ce0fdd15014b635eb7362af3c,Reinforcement Cutting-Agent Learning for Video Object Segmentation,"Reinforcement Cutting-Agent Learning for Video Object Segmentation Junwei Han1, Le Yang1, Dingwen Zhang1 , Xiaojun Chang3, Xiaodan Liang3 Northwestern Polytechincal University, 2Xidian University, 3Carnegie Mellon University" 0dcdef6b8d97483f4d4dab461e1cb5b3c4d1fe1a,Probabilistic Semantic Inpainting with Pixel Constrained CNNs,"Probabilistic Semantic Inpainting with Pixel Constrained CNNs Emilien Dupont Suhas Suresha Schlumberger Software Technology Innovation Center" 0df347f5e3118fac7c351917e3a497899b071d1e,Datasheets for Datasets,"Datasheets for Datasets Timnit Gebru 1 Jamie Morgenstern 2 Briana Vecchione 3 Jennifer Wortman Vaughan 1 Hanna Wallach 1 Hal Daumé III 1 4 Kate Crawford 1 5" 0d82013cbe9f65ddb34e5d99eab730fce4f0effe,A system based on sequence learning for event detection in surveillance video,"978-1-4799-2341-0/13/$31.00 ©2013 IEEE ICIP 2013" 0d90d046db16d3d5ce70590e6dab32cdd58928f6,A robust feature extraction algorithm based on class-Modular Image Principal Component Analysis for face verification,"978-1-4577-0539-7/11/$26.00 ©2011 IEEE ICASSP 2011" 0d130b5536bb1b909ff9a62737d768d4b4fab2f6,Semantic Segmentation with Scarce Data,"Semantic Segmentation with Scarce Data Isay Katsman * 1 Rohun Tripathi * 1 Andreas Veit 1 Serge Belongie 1" 0d0cee830772c3b2b274bfb5c3ad0ee42d8a0a57,Multimodal Convolutional Neural Networks for Matching Image and Sentence,"Multimodal Convolutional Neural Networks for Matching Image and Sentence Lin Ma Zhengdong Lu Lifeng Shang Hang Li {Lu.Zhengdong, Shang.Lifeng, Noah’s Ark Lab, Huawei Technologies" 0d6017c54d1f08d60d1423a3b84b01c387276387,Geometry meets semantics for semi-supervised monocular depth estimation,"Geometry meets semantics for semi-supervised monocular depth estimation Pierluigi Zama Ramirez, Matteo Poggi, Fabio Tosi, Stefano Mattoccia, and Luigi Di Stefano University of Bologna, Viale del Risorgimento 2, Bologna, Italy" 0d185e6de595bd3844909d3606e9218a498a9bd8,Trace optimization and eigenproblems in dimension reduction methods,"TRACE OPTIMIZATION AND EIGENPROBLEMS IN DIMENSION REDUCTION METHODS E. KOKIOPOULOU∗, J. CHEN†, AND Y. SAAD†" 0d1a87dad1e4538cc7bd3c923767c8bf1a9b779f,The Riemannian Geometry of Deep Generative Models,"The Riemannian Geometry of Deep Generative Models Hang Shao University of Utah Salt Lake City, UT Abhishek Kumar IBM Research AI Yorktown Heights, NY P. Thomas Fletcher University of Utah Salt Lake City, UT" 0dd151d003ac9b7f3d6936ccdd5ff38fce76c29f,A Review and Comparison of Measures for Automatic Video Surveillance Systems,"Hindawi Publishing Corporation EURASIP Journal on Image and Video Processing Volume 2008, Article ID 824726, 30 pages doi:10.1155/2008/824726 Research Article A Review and Comparison of Measures for Automatic Video Surveillance Systems Axel Baumann, Marco Boltz, Julia Ebling, Matthias Koenig, Hartmut S. Loos, Marcel Merkel, Wolfgang Niem, Jan Karl Warzelhan, and Jie Yu Corporate Research, Robert Bosch GmbH, D-70049 Stuttgart, Germany Correspondence should be addressed to Julia Ebling, Received 30 October 2007; Revised 28 February 2008; Accepted 12 June 2008 Recommended by Andrea Cavallaro Today’s video surveillance systems are increasingly equipped with video content analysis for a great variety of applications. However, reliability and robustness of video content analysis algorithms remain an issue. They have to be measured against ground truth data in order to quantify the performance and advancements of new algorithms. Therefore, a variety of measures have been proposed in the literature, but there has neither been a systematic overview nor an evaluation of measures for specific video analysis tasks yet. This paper provides a systematic review of measures and compares their effectiveness for specific spects, such as segmentation, tracking, and event detection. Focus is drawn on details like normalization issues, robustness, and representativeness. A software framework is introduced for continuously evaluating and documenting the performance of video" 0dca6aa1c0143aa190973fb2256c16d700992473,"An introduction to the good, the bad, & the ugly face recognition challenge problem","An Introduction to the Good, the Bad, & the Ugly Face Recognition Challenge Problem P. Jonathon Phillips, J. Ross Beveridge, Bruce A. Draper, Geof Givens, Alice J. O’Toole, David S. Bolme, Joseph Dunlop, Yui Man Lui, Hassan Sahibzada, and Samuel Weimer" 0dc34e186e8680336e88c3b5e73cde911a8774b8,Image Classification Using Naive Bayes Classifier With Pairwise Local Observations,"JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 32, XXXX-XXXX (2017) Image Classification Using Naive Bayes Classifier With Pairwise Local Observations SHIH-CHUNG HSU1, I-CHIEH CHEN1 AND CHUNG-LIN HUANG2 Department of Electrical Engineering, National Tsing-Hua University, Hsin-Chu, Taiwan Department of M-Commerce and Multimedia Applications, Asia Univ., Tai-Chung, Taiwan E-mail: We propose a pairwise local observation-based Naive Bayes (NBPLO) classifier for image classification. First, we find the salient regions (SRs) and the Keypoints (KPs) as the local observations. Second, we describe the discriminative pairwise local observations using Bag-of-features (BoF) histogram. Third, we train the object class models by using random forest to develop the NBPLO classifier for image classification. The two major ontributions in this paper are multiple pairwise local observations and regression object lass model training for NBPLO classifier. In the experiments, we test our method using Scene-15 and Caltech-101 database and compare the results with the other methods. Keywords: Local observation-based Naive Bayes classifier (NBPLO), Salient Region(SR), Keypoint(KP), Bag-of-feature(BoF). . INTRODUCTION Image classification has been a challenging unsolved problem due to the complexity of image contents. It has been a popular research subject of many recently published re-" 0d8e7cda7d8a2ff737c0ad72f31dfd4d80d3a09a,Network Structure & Information Advantage,"A research and education initiative at the MIT Sloan School of Management Network Structure & Information Advantage Paper 235 Sinan Aral Marshall Van Alstyne July 2007 For more information, please visit our website at http://digital.mit.edu or contact the Center directly at or 617-253-7054" 0d07db3510c7f9c2ceab65444cb8fc8ec49197b2,Learning-based Composite Metrics for Improved Caption Evaluation,"Learning-based Composite Metrics for Improved Caption Evaluation Naeha Sharif, Lyndon White, Mohammed Bennamoun and Syed Afaq Ali Shah, {naeha.sharif, nd {mohammed.bennamoun, The University of Western Australia. 5 Stirling Highway, Crawley, Western Australia" 0d3404530399eaa1f657d925a9a49c9e88a2e23b,Detection Evolution with Multi-order Contextual Co-occurrence,"Detection Evolution with Multi-Order Contextual Co-occurrence Guang Chen∗ Yuanyuan Ding† Epson Research and Development, Inc. San Jose, CA, USA Jing Xiao† Tony X. Han∗ Dept. of ECE, Univ. of Missouri Columbia, MO, USA" 0db787317ba0d63ec8f9918905e7db181a489026,Automatic Eye Localization in Color Images,"Automatic Eye Localization in Color Images José Gilvan Rodrigues Maia1, Fernando de Carvalho Gomes1, Osvaldo de Souza2 Departamento de Computação – Universidade Federal do Ceará (UFC) Depto de Engenharia de Teleinformática – Universidade Federal do Ceará (UFC) 60455-760 – Fortaleza – CE – Brasil {gilvan," 0d52f1ae438a395fadebf04990d0d1750cdd0218,Face Recognition in Various Illuminations,"Saurabh D. Parmar et al Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 4, Issue 5( Version 5), May 2014, pp.98-102 RESEARCH ARTICLE Face Recognition in Various Illuminations Saurabh D. Parmar, Vaishali J. Kalariya Research Scholar, CE/IT Department-School of Engineering, R.K. University, Rajkot Professor, CE/IT Department-School of Engineering, R.K. University, Rajkot OPEN ACCESS" 0dd72a3522b99aedea83b47c5d7b33a1df058fd0,A Set of Selected SIFT Features for 3D Facial Expression Recognition,"A Set of Selected SIFT Features for 3D Facial Expression Recognition Stefano Berretti, Alberto Del Bimbo, Pietro Pala, Boulbaba Ben Amor, Daoudi Mohamed To cite this version: Stefano Berretti, Alberto Del Bimbo, Pietro Pala, Boulbaba Ben Amor, Daoudi Mohamed. A Set of Selected SIFT Features for 3D Facial Expression Recognition. 20th International Conference on Pattern Recognition, Aug 2010, Istanbul, Turkey. pp.4125 - 4128, 2010. HAL Id: hal-00829354 https://hal.archives-ouvertes.fr/hal-00829354 Submitted on 3 Jun 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 0d371fcd99e321257a1b7f87a436c6cc5b8b7557,Stability Based Filter Pruning for Accelerating Deep CNNs,"Stability Based Filter Pruning for Accelerating Deep CNNs Pravendra Singh IIT Kanpur Vinay Sameer Raja Kadi Nikhil Verma Samsung R&D Institute, Delhi {k.raja, Vinay P. Namboodiri IIT Kanpur" 0d48c282737793b234c56382053cc69cdddeccb0,A Poodle or a Dog? Evaluating Automatic Image Annotation Using Human Descriptions at Different Levels of Granularity,"Proceedings of the 25th International Conference on Computational Linguistics, pages 38–45, Dublin, Ireland, August 23-29 2014." 0d7ddcf97b1341d8d4bbc4718f4ca3094e994a1f,Homographic Active Shape Models for View-Independent Facial Analysis,"Homographic Active Shape Models for View-Independent Facial Analysis Federico M. Sukno12 and Jos´e J. Guerrero32 and Alejandro F. Frangi1 Department of Technology, Pompeu Fabra University, Barcelona, Spain; Aragon Institute of Engineering Research, University of Zaragoza, Spain; Computer Science and System Engineering Department, University of Zaragoza, Spain" 0d3882b22da23497e5de8b7750b71f3a4b0aac6b,Context is routinely encoded during emotion perception.,"Research Article Context Is Routinely Encoded During Emotion Perception 1(4) 595 –599 © The Author(s) 2010 Reprints and permission: sagepub.com/journalsPermissions.nav DOI: 10.1177/0956797610363547 http://pss.sagepub.com Lisa Feldman Barrett1,2,3 and Elizabeth A. Kensinger1,3 Boston College; 2Psychiatric Neuroimaging Program, Massachusetts General Hospital, Harvard Medical School; and 3Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School" 0d2a9f3357717e0a44eb82d5eabfc047cc4d46f1,Classifier Ensembles with Trajectory Under-Sampling for Face Re-Identification,"Classifier Ensembles with Trajectory Under-Sampling for Face Re-Identification Roghayeh Soleymani1, Eric Granger1 and Giorgio Fumera2 Laboratoire d’imagerie, de vision et d’intelligence artificielle, École de technologie supérieure, Pattern Recognition and Applications Group, Dept. of Electrical and Electronic Engineering, University of Université du Québec, Montreal, Canada Cagliari,Cagliari, Italy Keywords: Person Re-Identification, Class Imbalance, Ensemble Methods." 0d30a662061a495e4b5aeb92a2edfac868b225ea,Chapter 7 Quantification of Emotions for Facial Expression : Generation of Emotional Feature Space Using Self-Mapping,"Chapter 7 Quantification of Emotions for Facial Expression: Generation of Emotional Feature Space Using Self- Mapping Masaki Ishii, Toshio Shimodate, Yoichi Kageyama, Tsuyoshi Takahashi and Makoto Nishida Additional information is available at the end of the chapter http://dx.doi.org/10.5772/51136 . Introduction Facial expression recognition for the purpose of emotional communication between humans nd machines has been investigated in recent studies [1-7]. The shape (static diversity) and motion (dynamic diversity) of facial components, such as the eyebrows, eyes, nose, and mouth, manifest expression. From the viewpoint of static di‐ versity, owing to the individual variation in facial configurations, it is presumed that a facial expression pattern due to the manifestation of a facial expression includes subject-specific features. In addition, from the viewpoint of dynamic diversity, because the dynamic hanges in facial expressions originate from subject-specific facial expression patterns, it is presumed that the displacement vector of facial components has subject-specific features. On the other hand, although an emotionally generated facial expression pattern of an indi‐ vidual is unique, internal emotions expressed and recognized by humans via facial expres‐" 0dc2fdf1b97c76de1e7380e8126f8acc7d87e23a,Robust PCA Via Nonconvex Rank Approximation,"Robust PCA via Nonconvex Rank Approximation Department of Computer Science, Southern Illinois University, Carbondale, IL 62901, USA Zhao Kang, Chong Peng, Qiang Cheng {zhao.kang, pchong," 0d076edd62e258316bc310fafcec88db3ab85434,Automatic detection and tracking of pedestrians from a moving stereo rig,"Automatic detection and tracking of pedestrians from a moving stereo rig Konrad Schindlera, Andreas Essb, Bastian Leibec, Luc Van Goolb,d Photogrammetry and Remote Sensing, ETH Z¨urich, Switzerland Computer Vision Lab, ETH Z¨urich, Switzerland UMIC research centre, RWTH Aachen, Germany dESAT/PSI–VISICS, IBBT, KU Leuven, Belgium" 0d538084f664b4b7c0e11899d08da31aead87c32,Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction,"Deformable Part Descriptors for Fine-grained Recognition and Attribute Prediction Ning Zhang1 Ryan Farrell1,2 Forrest Iandola1 ICSI / UC Berkeley 2Brigham Young University Trevor Darrell1" 0da611ca979327840161df87564fd07299c268b5,Bodyprint: Biometric User Identification on Mobile Devices Using the Capacitive Touchscreen to Scan Body Parts,"Bodyprint Biometric User Identification on Mobile Devices Using the Capacitive Touchscreen to Scan Body Parts Christian Holz Senaka Buthpitiya Marius Knaust" 0d2a1a3897d50ba490a2ffaaecc3135f573a7023,Discriminative training for object recognition using image patches,"Discriminative Training for Object Recognition Using Image Patches Thomas Deselaers, Daniel Keysers, and Hermann Ney Lehrstuhl f¨ur Informatik VI – Computer Science Department RWTH Aachen University – 52056 Aachen, Germany" b62486261104d5136aea782ee8596425b5f228da,Modelling perceptions of criminality and remorse from faces using a data-driven computational approach.,"Cognition and Emotion ISSN: 0269-9931 (Print) 1464-0600 (Online) Journal homepage: http://www.tandfonline.com/loi/pcem20 Modelling perceptions of criminality and remorse from faces using a data-driven computational pproach Friederike Funk, Mirella Walker & Alexander Todorov To cite this article: Friederike Funk, Mirella Walker & Alexander Todorov (2017) Modelling perceptions of criminality and remorse from faces using a data-driven computational approach, Cognition and Emotion, 31:7, 1431-1443, DOI: 10.1080/02699931.2016.1227305 To link to this article: http://dx.doi.org/10.1080/02699931.2016.1227305 View supplementary material Published online: 07 Sep 2016. Submit your article to this journal Article views: 235 View related articles View Crossmark data Citing articles: 1 View citing articles Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pcem20 Download by: [Princeton University]" b6b1b0632eb9d4ab1427278f5e5c46f97753c73d,Generalização cartográfica automatizada para um banco de dados cadastral,"UNIVERSIDADE FEDERAL DE SANTA CATARINA -UFSC DEPARTAMENTO DE ENGENHARIA CIVIL PROGRAMA DE PÓS-GRADUAÇÃO EM ENGENHARIA CIVIL - PPGEC AREA DE CONCENTRAÇÃO: CADASTRO TÉCNICO E GESTÃO TERRITORIAL GENERALIZAÇÃO CARTOGRÁFICA AUTOMATIZADA PARA UM BANCO DE DADOS CADASTRAL Tese submetida à Universidade Federal de Santa Catarina como requisito exigido pelo Programa de Pós-Graduação em Engenharia Civil - PPGEC, para a obtenção do Título de DOUTOR em Engenharia Civil. Mariane Alves Dal Santo Orientador: Prof. Dr. Carlos Loch Florianópolis, dezembro de 2007" b66a93884f80a243f50da97e33211693a317dc45,Deep Learning for Generic Object Detection: A Survey,"Deep Learning for Generic Object Detection: A Survey Li Liu 1,2 · Wanli Ouyang 3 · Xiaogang Wang 4 · Paul Fieguth 5 · Jie Chen 2 · Xinwang Liu 1 · Matti Pietik¨ainen 2 Received: 12 September 2018" b651814360e3899cd9206bfd23621aca6551e69c,Improving Feature Level Likelihoods using Cloud Features,"IMPROVING FEATURE LEVEL LIKELIHOODS USING CLOUD FEATURES Heydar Maboudi Afkham1, Stefan Carlsson1, Josephine Sullivan1 Computer Vision and Active Perception Lab., KTH, Stockholm, Sweden Keywords: Feature inference, Latent models, Clustering" b69badabc3fddc9710faa44c530473397303b0b9,Unsupervised Image-to-Image Translation Networks,"Unsupervised Image-to-Image Translation Networks Ming-Yu Liu, Thomas Breuel, Jan Kautz NVIDIA" b63411ed70ba315b87a716e1809faea48e70a982,"A Survey on Object Detect , Track and Identify Using Video Surveillance","IOSR Journal of Engineering (IOSRJEN) e-ISSN: 2250-3021, p-ISSN: 2278-8719, www.iosrjen.org Volume 2, Issue 10 (October 2012), PP 71-76 A Survey on Object Detect, Track and Identify Using Video Surveillance Chandrashekhar D.Badgujar1, Dipali P.Sapkal2 1,2(Computer Science and Engineering G.H.R.E.M, Jalgoan)" b67e2ccd0f05df5358464b9b38da3bcb9feda1ab,FaceID@home: cycle-sharing for facial recognition,"ycle-sharing for facial recognition FaceID-BOINC: adapta¸c˜ao de algoritmos de reconhecimento facial (eigenfaces) para execu¸c˜ao em m´aquinas multicore e GPUs integrado num cliente para plataforma BOINC Nuno Miguel Abreu Teixeira - 55397 Instituto Superior T´ecnico" b6aaef3be3e93a5429511011b3fcf1c768521efc,Car Detection and Tracking from a Vehicle Driving on a Roundabout,"Bachelor thesis Czech Technical University in Prague Faculty of Electrical Engineering Department of Cybernetics Car Detection and Tracking from Vehicle Driving on a Roundabout Libor Novák May 2014 Supervisor: prof. Ing. Jiří Matas, Ph.D." b6e3b42ea84bbb84658d34e7af49bff139616084,Low Cost and Usable Multimodal Biometric System Based on Keystroke Dynamics and 2 D Face Recognition,"Low Cost and Usable Multimodal Biometric System Based on Keystroke Dynamicsand 2D Face Recognition Romain Giot, Baptiste Hemery, Christophe Rosenberger To cite this version: Romain Giot, Baptiste Hemery, Christophe Rosenberger. Low Cost and Usable Multimodal Biometric System Based on Keystroke Dynamicsand 2D Face Recognition. The 20th Interna- tional Conference on Pattern Recognition, Aug 2010, Istanbul, Turkey. pp.4, 2010, . HAL Id: hal-00503103 https://hal.archives-ouvertes.fr/hal-00503103 Submitted on 16 Aug 2010 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" b61b4eb2e28b9cf35578498e1bbcc35ec0a07651,Backtracking ScSPM Image Classifier for Weakly Supervised Top-Down Saliency,"Backtracking ScSPM Image Classifier for Weakly Supervised Top-down Saliency Hisham Cholakkal Jubin Johnson Deepu Rajan Multimedia Lab, School of Computer Science and Engineering Nanyang Technological University Singapore {hisham002, jubin001," b648d73edd1a533decd22eec2e7722b96746ceae,weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming,"weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming Inkyu Sa1, Zetao Chen2, Marija Popovi´c1, Raghav Khanna1, Frank Liebisch3, Juan Nieto1, Roland Siegwart1" b6ecc8d34ebc8895378abe2b8f35e3a0691f5d26,Annotation Methodologies for Vision and Language Dataset Creation,"Annotation Methodologies for Vision and Language Dataset Creation Gitit Kehat Computer Science Department Brandeis University Waltham, MA. 02453 USA James Pustejovsky Computer Science Department Brandeis University Waltham, MA. 02453 USA" b691463de5e30e7efd18b9d02cbf83c805834fe7,EVALUATION OF PENALTY FUNCTIONS FOR SEMI-GLOBAL MATCHING COST AGGREGATION,"EVALUATION OF PENALTY FUNCTIONS FOR SEMI-GLOBAL MATCHING COST AGGREGATION Christian Banz, Peter Pirsch, and Holger Blume Institute of Microelectronic Systems Leibniz Universität Hannover, Hannover, Germany KEY WORDS: Stereoscopic, Quality, Matching, Vision, Reconstruction, Camera, Disparity Estimation, Semi-Global Matching" b6dc1cd3cabdfea7363d41773a315a0d241dc836,Local Context Priors for Object Proposal Generation,"Local Context Priors for Object Proposal Generation Marko Ristin1, Juergen Gall2, and Luc Van Gool1,3 ETH Zurich MPI for Intelligent Systems KU Leuven" b632d47eb7421a3d622b0f1ceb009e4415ccc84d,Deep Perceptual Mapping for Cross-Modal Face Recognition,"(will be inserted by the editor) Deep Perceptual Mapping for Cross-Modal Face Recognition M. Saquib Sarfraz · Rainer Stiefelhagen the date of receipt and acceptance should be inserted later" b68dfa8723be662e6af76bef159ed929bf8a1a2f,Distance weighted discrimination of face images for gender classification,"Distance weighted discrimination of face images for gender classification Mónica Benito1, Eduardo García-Portugués1,4, J. S. Marron2, and Daniel Peña1,3" b6fd905efd5da32bd32047896074a821477cb564,An Human Perceptive Model for Person Re-identification,"An Human Perceptive Model for Person Re-identification Angelo Cardellicchio1, Tiziana D’Orazio1, Tiziano Politi2 and Vito Ren`o1 National Research Council, Institute of Intelligent Systems for Automation, Bari, Italia Politecnico di Bari, Bari, Italia Keywords: Color Analysis, Feature Extraction, Histograms." b66418ecc37ea0c79da5425e9ceac939ca9075ae,EFFICIENT GAIT-BASED GENDER CLASSIFICATION THROUGH FEATURE SELECTION,"EFFICIENT GAIT-BASED GENDER CLASSIFICATION THROUGH FEATURE SELECTION∗ Ra´ul Mart´ın-F´elez, Javier Ortells, Ram´on A. Mollineda and J. Salvador S´anchez Institute of New Imaging Technologies and Dept. Llenguatges i Sistemes Inform`atics Universitat Jaume I. Av. Sos Baynat s/n, 12071, Castell´o de la Plana, Spain {martinr, jortells, mollined, Keywords: Gender classification, Gait, ANOVA, Feature selection." b6ef46621d8660eb53836202fa58f04fa20adfd7,Disgust and Anger Relate to Different Aggressive Responses to Moral Violations,"692000 PSSXXX10.1177/0956797617692000Molho et al.Moral Emotions and Aggressive Tactics research-article2017 Research Article Disgust and Anger Relate to Different Aggressive Responses to Moral Violations Catherine Molho1, Joshua M. Tybur1, Ezgi Güler2, Daniel Balliet1, and Wilhelm Hofmann3 Department of Experimental and Applied Psychology, Vrije Universiteit Amsterdam; Department of Political and Social Sciences, European University Institute; and 3Social Cognition Center Cologne, University of Cologne Psychological Science 017, Vol. 28(5) 609 –619 © The Author(s) 2017 Reprints and permissions: sagepub.com/journalsPermissions.nav DOI: 10.1177/0956797617692000 https://doi.org/10.1177/0956797617692000 www.psychologicalscience.org/PS" b6aa94b81b2165e492cc2900e05dd997619bfe7a,Automatic temporal segment detection via bilateral long short-term memory recurrent neural networks,"Automatic temporal segment detection via bilateral long short- term memory recurrent neural networks Bo Sun Siming Cao Jun He Lejun Yu Liandong Li Bo Sun, Siming Cao, Jun He, Lejun Yu, Liandong Li, “Automatic temporal segment detection via bilateral long short-term memory recurrent neural networks,” J. Electron. Imaging 26(2), 020501 (2017), doi: 10.1117/1.JEI.26.2.020501. Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 03/03/2017 Terms of Use: http://spiedigitallibrary.org/ss/termsofuse.aspx" b64cc1f0772e9620ecf916019de85b7adb357b7a,Fast Face-Swap Using Convolutional Neural Networks,"Fast Face-swap Using Convolutional Neural Networks Iryna Korshunova1,2 Wenzhe Shi1 {iryna.korshunova, Twitter Joni Dambre2 Lucas Theis1 IDLab, Ghent University {wshi," b69a7be6ae438090b7ed458662abcbde5871c4ff,Vehicle Motion Detection using CNN,"Vehicle Motion Detection using CNN Yaqi Zhang∗ Billy Wan∗ Wenshun Liu∗" b6dd4057bdeef69148ee22e9ca31b44434c0e89f,FIDA : Face Recognition using Descriptive Input Semantics,"FIDA: Face Recognition using Descriptive Input Semantics Nipun Bhatia, Rakshit Kumar, Samir Menon Department of Computer Science, Stanford University. December 14, 2007" b67e0ae9d64ec06b3e1c25c7f7e8b86020612d33,VOCABULARY-INFORMED VISUAL FEATURE AUGMEN-,"Under review as a conference paper at ICLR 2018 VOCABULARY-INFORMED VISUAL FEATURE AUGMEN- TATION FOR ONE-SHOT LEARNING" b6b9d29d25de42d78f09217c9cc457247d90fc70,Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints from Limited Training Data,"Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints from Limited Training Data Yutong Bai1∗, Qing Liu2∗, Lingxi Xie2, Yan Zheng3, Weichao Qiu2, Alan Yuille2 Northwestern Polytechnical University 2Johns Hopkins University 3Beihang University {198808xc, yan.zheng.mat," b63041d05b78a66724fbcb2803508999bf885d6b,Deep Sets,"Deep Sets Manzil Zaheer 1 2 Satwik Kottur 2 Siamak Ravanbhakhsh 2 Barnabas Poczos 2 Ruslan Ssalakhutdinov 2 Alexander Smola 1 2" b6f682648418422e992e3ef78a6965773550d36b,"CBMM Memo No . 061 February 8 , 2017 Full interpretation of minimal images","February 8, 2017" b62628ac06bbac998a3ab825324a41a11bc3a988,Xm2vtsdb: the Extended M2vts Database,"SecondInternationalConferenceonAudioandVideo-basedBiometricPersonAuthentication(AVBPA' ),WashingtonD.C, XMVTSDB:TheExtendedMVTSDatabase K.Messer,J.Matas,J.Kittler J.Luettin,G.Maitre UniversityofSurrey IDIAP Guildford,Surrey,GUXH,UK. CP , Martigny,Switzerland. ofvideoandaudiosignalsisintheorderofTBytes (GBytes);technologyallowingmanipulationand" b6ff7ead669e67ddf46bd2955b7cc0af0fa24ad7,Anticipation in Human-Robot Cooperation: A Recurrent Neural Network Approach for Multiple Action Sequences Prediction,"Anticipation in Human-Robot Cooperation: A Recurrent Neural Network Approach for Multiple Action Sequences Prediction Paul Schydlo1, Mirko Rakovic1,2, Lorenzo Jamone3 and Jos´e Santos-Victor1" b640c36acc0e748553f78280fce7a840965c5cec,Detection from Natural Image using MSER and BOW 1,"International Journal of Emerging Engineering Research and Technology Volume 3, Issue 11, November 2015, PP 152-156 ISSN 2349-4395 (Print) & ISSN 2349-4409 (Online) Text Detection from Natural Image using MSER and BOW K.Sowndarya Lahari, 2M.Haritha, 3P.Prasanna Murali Krishna (M.Tech), DECS, DR.Sgit, Markapur, India. Associate Professor, Department of ECE, DR.Sgit, Markapur, India. .3H.O.D Department of ECE, DR.Sgit, Markapur, India." b610e52b0a8fa11af3d01944c0383f015cade9c0,Multimodal 2 D-3 D Face Recognition,"International Journal of Future Computer and Communication, Vol. 2, No. 6, December 2013 Multimodal 2D-3D Face Recognition Gawed M. Nagi, Rahmita Rahmat, Muhamad Taufik, and Fatimah Khalid technology" b61ae8216a7c3a5a3202478cd6f18bf3014e2342,Robust Pedestrian Detection by Combining Visible and Thermal Infrared Cameras,"Sensors 2015, 15, 10580-10615; doi:10.3390/s150510580 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article Robust Pedestrian Detection by Combining Visible and Thermal Infrared Cameras Ji Hoon Lee, Jong-Suk Choi, Eun Som Jeon, Yeong Gon Kim, Toan Thanh Le, Kwang Yong Shin, Hyeon Chang Lee and Kang Ryoung Park * Department of Electronics and Electrical Engineering, Dongguk University, 26 Pil-dong 3-ga, Jung-gu, Seoul 100-715, Korea; E-Mails: (J.H.L.); (J.-S.C.); (E.S.J.); (Y.G.K.); (T.T.L.); (K.Y.S.); (H.C.L.) * Author to whom correspondence should be addressed; E-Mail: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735. Academic Editor: Vittorio M.N. Passaro Received: 12 February 2015 / Accepted: 27 April 2015 / Published: 5 May 2015" 2e8b08c8df95d2ef8c0d03820094608e9cf456ab,License Plate Detection and Recognition in Unconstrained Scenarios,"License Plate Detection and Recognition in Unconstrained Scenarios S´ergio Montazzolli Silva[0000−0003−2444−3175] and Cl´audio Rosito Jung[0000−0002−4711−5783] Institute of Informatics - Federal University of Rio Grande do Sul Porto Alegre, Brazil" 2e56209ed179be641e6df5efd11be8b3d54a62e9,Combining Deep and Handcrafted Image Features for Presentation Attack Detection in Face Recognition Systems Using Visible-Light Camera Sensors,"Article Combining Deep and Handcrafted Image Features for Presentation Attack Detection in Face Recognition Systems Using Visible-Light Camera Sensors Dat Tien Nguyen, Tuyen Danh Pham, Na Rae Baek and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (D.T.N.); (T.D.P.); (N.R.B.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 30 January 2018; Accepted: 24 February 2018; Published: 26 February 2018" 2e0481def73dbd3e6dfb447c1c3c8afdfaf9b7ec,UPC System for the 2015 MediaEval Multimodal Person Discovery in Broadcast TV task,"UPC System for the 2015 MediaEval Multimodal Person Discovery in Broadcast TV task M. India, D. Varas, V. Vilaplana, J.R. Morros, J. Hernando Universitat Politecnica de Catalunya, Spain" 2e091b311ac48c18aaedbb5117e94213f1dbb529,Collaborative Facial Landmark Localization for Transferring Annotations Across Datasets,"Collaborative Facial Landmark Localization for Transferring Annotations Across Datasets Brandon M. Smith and Li Zhang University of Wisconsin – Madison http://www.cs.wisc.edu/~lizhang/projects/collab-face-landmarks/" 2e708431df3e7a9585a338e1571f078ddbe93a71,Deep Pain: Exploiting Long Short-Term Memory Networks for Facial Expression Classification.,"Aalborg Universitet Deep Pain Rodriguez, Pau; Cucurull, Guillem; Gonzàlez, Jordi; M. Gonfaus, Josep ; Nasrollahi, Kamal; Moeslund, Thomas B.; Xavier Roca, F. Published in: I E E E Transactions on Cybernetics DOI (link to publication from Publisher): 0.1109/TCYB.2017.2662199 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Rodriguez, P., Cucurull, G., Gonzàlez, J., M. Gonfaus, J., Nasrollahi, K., Moeslund, T. B., & Xavier Roca, F. (2017). Deep Pain: Exploiting Long Short-Term Memory Networks for Facial Expression Classification. I E E E Transactions on Cybernetics, 1-11. DOI: 10.1109/TCYB.2017.2662199 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research." 2ea8029283e6bbb03c023070d042cb19647f06af,Neurobiological mechanisms associated with facial affect recognition deficits after traumatic brain injury,"Neurobiological mechanisms associated with facial affect recognition deficits after traumatic brain injury Dawn Neumann, PhD Indiana University School of Medicine Department of Physical Medicine and Rehabilitation Rehabilitation Hospital of Indiana 141 Shore Drive Indianapolis, IN 46254 Email: Phone: 317-329-2188 Brenna C. McDonald, PsyD, MBA Indiana University School of Medicine Department of Radiology and Imaging Sciences Indiana University Center for Neuroimaging 55 W. 16th St., GH Suite 4100 Indianapolis, IN 46202 Email: John West, MS Indiana University School of Medicine Department of Radiology and Imaging Sciences" 2e80ce889fa47bae8583f89d501a41e283c1551b,FlowNet: Learning Optical Flow with Convolutional Networks,"FlowNet: Learning Optical Flow with Convolutional Networks Philipp Fischer∗‡, Alexey Dosovitskiy‡, Eddy Ilg‡, Philip H¨ausser, Caner Hazırbas¸, Vladimir Golkov∗ University of Freiburg Technical University of Munich Patrick van der Smagt Daniel Cremers Thomas Brox Technical University of Munich Technical University of Munich University of Freiburg" 2eefaa9c278346b9e0eb51085cff490b0a43688f,TEMPO: Feature-Endowed Teichmüller Extremal Mappings of Point Clouds,"Vol. 9, No. 4, pp. 1922–1962 (cid:13) 2016 Society for Industrial and Applied Mathematics TEMPO: Feature-Endowed Teichm¨uller Extremal Mappings of Point Clouds∗ Ting Wei Meng† , Gary Pui-Tung Choi‡ , and Lok Ming Lui†" 2ebc35d196cd975e1ccbc8e98694f20d7f52faf3,Towards Wide-angle Micro Vision Sensors,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Towards Wide-angle Micro Vision Sensors Sanjeev J. Koppal* Ioannis Gkioulekas* Travis Young+ Hyunsung Park* Kenneth B. Crozier* Geoffrey L. Barrows+ Todd Zickler*" 2e8d0f1802e50cccfd3c0aabac0d0beab3a7846e,3DPeS: 3D people dataset for surveillance and forensics,"DPeS: 3D People Dataset for Surveillance and Forensics Davide Baltieri, Roberto Vezzani, Rita Cucchiara {davide.baltieri, roberto.vezzani, rita.cucchiara} University of Modena and Reggio Emilia, Italy (Dipartimento di Ingegneria dell’Informazione) A new Dataset for People Tracking and Reidentification 600 videos, 200 people, 8 cameras Calibration and 3D scene reconstruction taken The dataset contains hundreds of video sequences of from a multi-camera distributed 00 people surveillance system over several days, with different light onditions; each person is detected multiple times and from different points of view. The dataset The starting point of our dataset is a real surveillance setup, composed by 8 different surveillance cameras, monitoring a section of the ampus of the University of Modena and Reggio" 2ed9a69ee6509c0b3fe5a51d1116dccc877653ba,Reconstruction and Analysis of Shapes from 3D Scans,"Reconstruction and Analysis of Shapes from 3D Scans" 2e1add06cc82d139348056fe43282f1ca1832e5b,Local 3 D Shape Analysis for Facial Expression Recognition,"Local 3D Shape Analysis for Facial Expression Recognition Ahmed Maalej, Boulbaba Ben Amor, Mohamed Daoudi, Anuj Srivastava, Stefano Berretti To cite this version: Ahmed Maalej, Boulbaba Ben Amor, Mohamed Daoudi, Anuj Srivastava, Stefano Berretti. Local 3D Shape Analysis for Facial Expression Recognition. 20th International Conference on Pattern Recognition (ICPR 2010), Aug 2010, Istanbul, Turkey. pp.4129 - 4132, 2010. HAL Id: hal-00662321 https://hal.archives-ouvertes.fr/hal-00662321 Submitted on 23 Jan 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," 2e0f5e72ad893b049f971bc99b67ebf254e194f7,Apparel classification with style,"Apparel Classification with Style Lukas Bossard1, Matthias Dantone1, Christian Leistner1,2, Christian Wengert1,3, Till Quack3, Luc Van Gool1,4 ETH Z¨urich, Switzerland 2Microsoft, Austria 3Kooaba AG, Switzerland KU Leuven, Belgium" 2eb9f1dbea71bdc57821dedbb587ff04f3a25f07,Face for ambient interface,"Face for Ambient Interface Maja Pantic Imperial College, Computing Department, 180 Queens Gate, London SW7 2AZ, U.K." 2e082232eb37c98052e62eec76e674a491082544,Virtual Scenarios : Achievements and Current Work,"Virtual Scenarios: Achievements and Current Work Javier Mar´ın, David V´azquez and Antonio M. L´opez ADAS, Computer Vision Center, Universitat Autonoma de Barcelona, Spain e-mail:{ jmarin, dvazquez, antonio" 2ef51b57c4a3743ac33e47e0dc6a40b0afcdd522,Leveraging Billions of Faces to Overcome Performance Barriers in Unconstrained Face Recognition,"Leveraging Billions of Faces to Overcome Performance Barriers in Unconstrained Face Recognition Yaniv Taigman and Lior Wolf face.com {yaniv," 2e2935a7489ae55fe36af6980523f8d587c18935,On testing methods for biometric authentication, 2e6c3557cb90f472e6798fcaa8ecc9dff3557f11,Towards Perspective-Free Object Counting with Deep Learning,"Towards perspective-free object counting with deep learning Daniel O˜noro-Rubio and Roberto J. L´opez-Sastre GRAM, University of Alcal´a, Alcal´a de Henares, Spain" 2efc6f98720b804345c030e22aef6c9f4a53023e,Soft-biometrics evaluation for people re-identification in uncontrolled multi-camera environments,"Moctezuma et al. EURASIP Journal on Image and Video Processing (2015) 2015:28 DOI 10.1186/s13640-015-0078-1 RESEARCH Open Access Soft-biometrics evaluation for people re-identification in uncontrolled multi-camera environments Daniela Moctezuma1*, Cristina Conde2, Isaac Martín De Diego2 and Enrique Cabello2" 2e1415a814ae9abace5550e4893e13bd988c7ba1,Dictionary Based Face Recognition in Video Using Fuzzy Clustering and,"International Journal of Engineering Trends and Technology (IJETT) – Volume 21 Number 3 – March 2015 Dictionary Based Face Recognition in Video Using Fuzzy Clustering and Fusion Neeraja K.C.#1, RameshMarivendan E.#2, #1IInd year M.E. Student, #2Assistant Professor #1#2ECE Department, Dhanalakshmi Srinivasan College of Engineering, Coimbatore,Tamilnadu,India. Anna University." 2e68190ebda2db8fb690e378fa213319ca915cf8,Generating Videos with Scene Dynamics,"Generating Videos with Scene Dynamics Carl Vondrick Hamed Pirsiavash Antonio Torralba" 2e53a5dbadfd30b834feea80c365ffff3925eb76,The role of alexithymia in reduced eye-fixation in Autism Spectrum Conditions.,"23Journal of Autism andDevelopmental Disorders ISSN 0162-3257Volume 41Number 11 J Autism Dev Disord (2011)41:1556-1564DOI 10.1007/s10803-011-1183-3The Role of Alexithymia in Reduced Eye-Fixation in Autism Spectrum ConditionsGeoffrey Bird, Clare Press & DanielC. Richardson" 2e475f1d496456831599ce86d8bbbdada8ee57ed,Groupsourcing: Team Competition Designs for Crowdsourcing,"Groupsourcing: Team Competition Designs for Crowdsourcing Markus Rokicki, Sergej Zerr, Stefan Siersdorfer L3S Research Center, Hannover, Germany" 2eef20a11324686099ee6f9b1a7613444b0d2112,Dual-Path Convolutional Image-Text Embedding with Instance Loss,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Dual-Path Convolutional Image-Text Embeddings with Instance Loss Zhedong Zheng, Liang Zheng, Michael Garrett, Yi Yang, Yi-Dong Shen" 2e927d0a2dc4b69fc03124ad876329b22a61f1b0,Temporal Reasoning in Videos using Convolutional Gated Recurrent Units,"Temporal Reasoning in Videos using Convolutional Gated Recurrent Units Debidatta Dwibedi∗ Pierre Sermanet Jonathan Tompson Google Brain {debidatta, sermanet," 2ea78e128bec30fb1a623c55ad5d55bb99190bd2,Residual vs. Inception vs. Classical Networks for Low-Resolution Face Recognition,"Residual vs. Inception vs. Classical Networks for Low-Resolution Face Recognition Christian Herrmann1,2, Dieter Willersinn2, and J¨urgen Beyerer1,2 Vision and Fusion Lab, Karlsruhe Institute of Technology KIT, Karlsruhe, Germany Fraunhofer IOSB, Karlsruhe, Germany {christian.herrmann,dieter.willersinn," 2e10560579f2bdeae0143141f26bd9f0a195b4b7,Mixed Precision Training,"Published as a conference paper at ICLR 2018 MIXED PRECISION TRAINING Sharan Narang∗, Gregory Diamos, Erich Elsen† Baidu Research {sharan, Paulius Micikevicius∗, Jonah Alben, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, Hao Wu NVIDIA {pauliusm, alben, dagarcia, bginsburg, mhouston, okuchaiev, gavenkatesh," 2e55fd3f5138e55250aed84a7dc17adfc34970d3,The implications of social neuroscience for social disability.,"J Autism Dev Disord (2012) 42:1256–1262 DOI 10.1007/s10803-012-1514-z O R I G I N A L P A P E R The Implications of Social Neuroscience for Social Disability James C. McPartland • Kevin A. Pelphrey Published online: 29 March 2012 Ó Springer Science+Business Media, LLC 2012" 2e62b4f2f5a8e6c1bf6a21ebb860c40463d72917,Adversarial background augmentation improves object localisation using convolutional neural networks,"Master Thesis Computing Science Adversarial background ugmentation improves object localisation using convolutional neural networks Author: Ing. Harm Berntsen Supervisor Radboud University: Prof. Dr. Tom Heskes Supervisors Nedap: Daan van Beek, MSc. Dr. Wouter Kuijper August 2015" 2ea46531f7d837c1e4b9e6a8d8fc084c6e526545,Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction,"Just look at the image: viewpoint-specific surface normal prediction for improved multi-view reconstruction Silvano Galliani Konrad Schindler Photogrammetry and Remote Sensing, ETH Zurich" 2eae02d59a3f455f3714ce674d85d3f073c9d7a2,All in the first glance: first fixation predicts individual differences in valence bias.,"Cognition and Emotion ISSN: 0269-9931 (Print) 1464-0600 (Online) Journal homepage: http://www.tandfonline.com/loi/pcem20 All in the first glance: first fixation predicts individual differences in valence bias Maital Neta, Tien T. Tong, Monica L. Rosen, Alex Enersen, M. Justin Kim & Michael D. Dodd To cite this article: Maital Neta, Tien T. Tong, Monica L. Rosen, Alex Enersen, M. Justin Kim & Michael D. Dodd (2016): All in the first glance: first fixation predicts individual differences in valence bias, Cognition and Emotion, DOI: 10.1080/02699931.2016.1152231 To link to this article: http://dx.doi.org/10.1080/02699931.2016.1152231 View supplementary material Published online: 10 Mar 2016. Submit your article to this journal View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pcem20 Download by: [University of Nebraska, Lincoln] Date: 10 March 2016, At: 09:04" 2e1a1deb7dccff41fca7447364d6748bf362fb70,A topographical nonnegative matrix factorization algorithm,"A Topographical Nonnegative Matrix Factorization lgorithm Rogovschi Nicoleta Lazhar Labiod Mohamed Nadif LIPADE, Paris Descartes University LIPADE, Paris Descartes University LIPADE, Paris Descartes University 5, rue des Saints P`eres 75006 Paris, France 5, rue des Saints P`eres 75006 Paris, France 5, rue des Saints P`eres 75006 Paris, France" 2e832d5657bf9e5678fd45b118fc74db07dac9da,"Recognition of Facial Expressions of Emotion: The Effects of Anxiety, Depression, and Fear of Negative Evaluation","Running head: RECOGNITION OF FACIAL EXPRESSIONS OF EMOTION Recognition of Facial Expressions of Emotion: The Effects of Anxiety, Depression, and Fear of Negative Evaluation Rachel Merchak Wittenberg University Rachel Merchak, Psychology Department, Wittenberg University. Author Note This research was conducted in collaboration with Dr. Stephanie Little, Psychology Department, Wittenberg University, and Dr. Michael Anes, Psychology Department, Wittenberg University. Correspondence concerning this article should be addressed to Rachel Merchak, 10063 Fox Chase Drive, Loveland, OH 45140. E‐mail:" 2e1822bf06d80f5ad07a79a4bfff98c1c18fb573,Knowing who to listen to: Prioritizing experts from a diverse ensemble for attribute personalization,"KNOWING WHO TO LISTEN TO: PRIORITIZING EXPERTS FROM A DIVERSE ENSEMBLE FOR ATTRIBUTE PERSONALIZATION Shrenik Lad1, Bernardino Romera Paredes2, Julien Valentin2, Philip Torr2, Devi Parikh1 . Virginia Tech 2. University of Oxford" 2efc4eee3953f6b52e23989bbcc2598a91e18ba0,External Cameras and a Mobile Robot for Enhanced Multi-person Tracking,"RFAntennas2D SICKLaserFirewire Cameraon PTU LaptopCamera 1Flea RGB Camera 2Flea RGBHubFirewireFigure1:Perceptualplatform;staticcameras(withroughpositionsandfieldsofview)andthemobilerobotRackham.Thispaperisstructuredasfollows:architectureofthecooperativesystemispresentedinsection2.Sec-tion3describesthedifferentdetectionmodalitiesthatdrivethemulti-persontracker(presentedinsection4).Evaluationsandresultsarepresentedinsection5fol-lowedbyconcludingremarksinsection6.2ARCHITECTUREOurcooperativeframeworkismadeupofamobilerobotandtwofixedviewwall-mountedRGBflea2cameras(figure1).Thecamerashaveamaximumres-olutionof640x480pixelsandareconnectedtoadual-coreIntelCentrinoLaptopviaafire-wirecable.Therobot,calledRackham,isaniRobotB21rmobileplat-form.Ithasvarioussensors,ofwhichitsSICKLaserRangeFinder(LRF)isutilizedinthiswork.Commu-nicationbetweenthemobilerobotandthecomputer" 2e64682caf77309db573ee439d988233f71e88ad,Establishing Good Benchmarks and Baselines for Face Recognition,"Author manuscript, published in ""Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recognition, Marseille : France (2008)""" 2edf55ebc88e89c4caff0c49c6b8e79f46407d19,Pruning Deep Neural Networks using Partial Least Squares,"Pruning Deep Neural Networks using Partial Least Squares Artur Jordao, Ricardo Kloss∗, Fernando Yamada and William Robson Schwartz Smart Sense Laboratory, Computer Science Department Universidade Federal de Minas Gerais, Brazil Email: {arturjordao, rbk, fernandoakio," 2e491c8e3d1d3314ea5e50943c0bdf2aa57b99b7,Weighted joint sparse representation-based classification method for robust alignment-free face recognition,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 12/17/2017 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use Weightedjointsparserepresentation-basedclassificationmethodforrobustalignment-freefacerecognitionBoSunFengXuGuoyanZhouJunHeFengxiangGe" 2e5cfa97f3ecc10ae8f54c1862433285281e6a7c,Generative Adversarial Networks for Improving Face Classification,"Generative Adversarial Networks for Improving Face Classification JONAS NATTEN SUPERVISOR Morten Goodwin, PhD University of Agder, 2017 Faculty of Engineering and Science Department of ICT" 2e0d56794379c436b2d1be63e71a215dd67eb2ca,Improving precision and recall of face recognition in SIPP with combination of modified mean search and LSH,"Improving precision and recall of face recognition in SIPP with combination of modified mean search and LSH Xihua.Li" 2e7874ec37df91db1934d61d9e1181de5e4efb36,COCO-Stuff: Thing and Stuff Classes in Context,"COCO-Stuff: Thing and Stuff Classes in Context Holger Caesar1 Jasper Uijlings2 Vittorio Ferrari1 2 University of Edinburgh1 Google AI Perception2" 2ec393b4fa5739c54ac9f61e583f5e41cfb2687c,Face Recognition using Spherical Wavelets,"Face Recognition using Spherical Wavelets Christian Lessig∗" 2ed4973984b254be5cba3129371506275fe8a8eb,Victoria Ovsyannikova THE EFFECTS OF MOOD ON EMOTION RECOGNITION AND ITS RELATIONSHIP WITH THE GLOBAL VS LOCAL INFORMATION PROCESSING,"Victoria Ovsyannikova THE EFFECTS OF MOOD ON EMOTION RECOGNITION AND ITS RELATIONSHIP WITH THE GLOBAL VS LOCAL INFORMATION PROCESSING STYLES BASIC RESEARCH PROGRAM WORKING PAPERS SERIES: PSYCHOLOGY WP BRP 60/PSY/2016 This Working Paper is an output of a research project implemented at the National Research University Higher School of Economics (HSE). Any opinions or claims contained in this Working Paper do not necessarily reflect the views of HSE" e27301701e4d2d7da4171e6c560c4fb3f974bf2d,Comparative Evaluations of Selected Tracking-by-Detection Approaches,"Comparative Evaluations of Selected Tracking-by-Detection Approaches Alhayat Ali Mekonnen, Frédéric Lerasle To cite this version: Alhayat Ali Mekonnen, Frédéric Lerasle. Comparative Evaluations of Selected Tracking-by-Detection Approaches. IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical nd Electronics Engineers, 2018, <10.1109/TCSVT.2018.2817609>. HAL Id: hal-01815850 https://hal.laas.fr/hal-01815850 Submitted on 14 Jun 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" e20daf69526c5da9cffb252d043fdc765f37a89e,Relating images and 3D models with convolutional neural networks. (Mise en relation d'images et de modèles 3D avec des réseaux de neurones convolutifs),"Relating images and 3D models with convolutional neural networks Francisco Vitor Suzano Massa To cite this version: Francisco Vitor Suzano Massa. Relating images and 3D models with convolutional neural networks. Signal and Image Processing. Université Paris-Est, 2017. English. . HAL Id: tel-01762533 https://pastel.archives-ouvertes.fr/tel-01762533 Submitted on 10 Apr 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" e27ef52c641c2b5100a1b34fd0b819e84a31b4df,SARC3D: A New 3D Body Model for People Tracking and Re-identification,"SARC3D: a new 3D body model for People Tracking and Re-identification Davide Baltieri, Roberto Vezzani, and Rita Cucchiara Dipartimento di Ingegneria dell’Informazione - University of Modena and Reggio Emilia, Via Vignolese, 905 - 41125 Modena - Italy" e21b1c10bee6a984971dcba414c22078dcfd21c2,Recent progress in semantic image segmentation,"Artificial Intelligence Review https://doi.org/10.1007/s10462-018-9641-3 Recent progress in semantic image segmentation Xiaolong Liu1 · Zhidong Deng1 · Yuhan Yang2 © The Author(s) 2018" e282bf5a679ca4e8b7d9a2ed56d3b40dc440ab53,Referenceless Quality Estimation for Natural Language Generation,"Referenceless Quality Estimation for Natural Language Generation Ondˇrej Duˇsek 1 Jekaterina Novikova 1 Verena Rieser 1" e21cdb56c23e2a834a611d51abce545d2e8d01a2,Gender and Identity Classification for a Naive and Evolving System,"Gender and Identity Classification for a Naive and Evolving System M. Castrill´on-Santana, O. D´eniz-Su´arez, J. Lorenzo-Navarro and M. Hern´andez-Tejera IUSIANI - Edif. Ctral. del Parque Cient´ıfico Tecnol´ogico Universidad de Las Palmas de Gran Canaria, Spain" e2edc7e7a2832e2f6014945afce4f76643cab02c,Augsburg An annotated data set for pose estimation of swimmers,"Universit¨at Augsburg An annotated data set for pose estimation of swimmers Thomas Greif and Rainer Lienhart Report 2009-18 Januar 2010 Institut f¨ur Informatik D-86135 Augsburg" e2c122bea06dfa067712cdb58ce474144f93af07,Phrase-based Image Captioning with Hierarchical LSTM Model,"ACCV2016 EXTENSION Phrase-based Image Captioning with Hierarchical LSTM Model Ying Hua Tan and Chee Seng Chan" e2baf990bc60ef0d24b7556d238e40566ad23d2f,Modified Gabor Filter based Vehicle Verification,"International Journal of Computer Applications® (IJCA) (0975 – 8887) National Conference cum Workshop on Bioinformatics and Computational Biology, NCWBCB- 2014 Modified Gabor Filter based Vehicle Verification Amrutha Ramachandran Mtech,AE&C, Dept. of EC, NCERC,Kerala. towards ollision voidance ccess,potential" e2fc290a245d9f5c545e2e92ee8fcaff4908b97f,Picture-to-Identity linking of social network accounts based on Sensor Pattern Noise,"Picture-to-Identity linking of social network accounts based on Sensor Pattern Noise Riccardo Satta∗ and Pasquale Stirparo∗+ Institute for the Protection and Security of the Citizen, Joint Research Centre (JRC), European Commission, Ispra (VA), Italy +Royal Institute of Technology (KTH), Stockholm, Sweden {riccardo.satta, Keywords: linking, digital image forensics social network, Sensor Pattern Noise, identity," e2afea1a84a5bdbcb64d5ceadaa2249195e1fd82,DOOM Level Generation Using Generative Adversarial Networks,"DOOM Level Generation using Generative Adversarial Networks Edoardo Giacomello Dipartimento di Elettronica, Informazione e Bioinformatica Politecnico di Milano Pier Luca Lanzi Dipartimento di Elettronica, Informazione e Bioinformatica Politecnico di Milano Daniele Loiacono Dipartimento di Elettronica, Informazione e Bioinformatica Politecnico di Milano" e21c45b14d75545d40ed07896f26ec6f766f6a4b,Fisher GAN,"Fisher GAN Youssef Mroueh∗, Tom Sercu∗ Equal Contribution AI Foundations, IBM Research AI IBM T.J Watson Research Center" e260847323b48a79bd88dd95a1499cd3053d3645,Reconstructing perceived faces from brain activations with deep adversarial neural decoding,"PDF hosted at the Radboud Repository of the Radboud University Nijmegen The following full text is a publisher's version. For additional information about this publication click this link. http://hdl.handle.net/2066/179505 Please be advised that this information was generated on 2018-07-04 and may be subject to hange." e295f31df11ec700851c2413b9bba644a91b0629,3D face reconstruction in a binocular passive stereoscopic system using face properties,"D FACE RECONSTRUCTION IN A BINOCULAR PASSIVE STEREOSCOPIC SYSTEM USING FACE PROPERTIES Amel AISSAOUI, Jean MARTINET and Chaabane DJERABA LIFL UMR Lille1-CNRS n 8022, IRCICA, 50 avenue Halley, 59658 Villeneuve d’Ascq, France" e24294adfcdb0334c310823c591f15e8829dc224,Deep Neural Networks and Regression Models for Object Detection and Pose estimation, e2059946b69e0854f21919c1cf13c3f618f48d12,Deep Architectures and Ensembles for Semantic Video Classification,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2018 Deep Architectures and Ensembles for Semantic Video Classification Eng-Jon Ong, Sameed Husain, Mikel Bober-Irizar, Miroslaw Bober∗" e2e8db754b1ab4cd8aa07f5c5940f6921a1b7187,Interpretable visual models for human perception-based object retrieval,"Interpretable Visual Models for Human Perception-Based Object Retrieval Ahmed Rebai, Alexis Joly, Nozha Boujemaa To cite this version: Ahmed Rebai, Alexis Joly, Nozha Boujemaa. Based Object Retrieval. trieval, Apr 2011, Trento, <10.1145/1991996.1992017>. Italy. Interpretable Visual Models for Human Perception- ICMR’11 - First ACM International Conference on Multimedia Re- ACM, pp.21:1–21:8, 2011, . HAL Id: hal-00642232 https://hal.inria.fr/hal-00642232 Submitted on 17 Nov 2011 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or" e2279676b01e477b5e7333bab276678f4ad34753,SEARCHING IMAGE WITH HASH CODE GENERATIONS 1,"International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 02 Issue: 05 | Aug-2015 www.irjet.net p-ISSN: 2395-0072 SEARCHING IMAGE WITH HASH CODE GENERATIONS R.Lawanya,*2Mrs.G.Sangeetha Lakshmi, 3Ms.A.Sivasankari ,*2,3Department of Computer Science,DKM College for Women, Vellore, Tamil Nadu, India. ----------------------------------------------------------------------------------------------------------------------" e2945f1b10a52dd5336015363af892ad97cdeb83,Learning to Segment Moving Objects,"Noname manuscript No. (will be inserted by the editor) Learning to Segment Moving Objects Pavel Tokmakov · Cordelia Schmid · Karteek Alahari Received: date / Accepted: date" e23ed8642a719ff1ab08799257d9566ed3bba403,Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks,"Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks Taeksoo Kim, Byoungjip Kim, Moonsu Cha, Jiwon Kim SK T-Brain" e27acf161f569aa876e46ffae2058bb275f12a60,Interactive learning of heterogeneous visual concepts with local features,"Interactive Learning of Heterogeneous Visual Concepts with Local Features Wajih Ouertani INRIA − IMEDIA project nd INRA, France Michel Crucianu INRIA − IMEDIA project nd CEDRIC − CNAM, France Nozha Boujemaa INRIA − IMEDIA project 78153 Le Chesnay, France" e2d265f606cd25f1fd72e5ee8b8f4c5127b764df,Real-Time End-to-End Action Detection with Two-Stream Networks,"Real-Time End-to-End Action Detection with Two-Stream Networks Alaaeldin El-Nouby∗†, Graham W. Taylor∗†‡ School of Engineering, University of Guelph Vector Institute for Artificial Intelligence Canadian Institute for Advanced Research" e278218ba1ff1b85d06680e99b08e817d0962dab,Tracking Persons-of-Interest via Unsupervised Representation Adaptation,"Tracking Persons-of-Interest via Unsupervised Representation Adaptation Shun Zhang, Jia-Bin Huang, Jongwoo Lim, Yihong Gong, Jinjun Wang, Narendra Ahuja, and Ming-Hsuan Yang" e20e06ea1aa6e94721638ffc8e3bdcc0ef574b64,Secure Face Authentication Framework in Open Networks,"Secure Face Authentication Framework in Open Networks Yongjin Lee, Yongki Lee, Yunsu Chung, and Kiyoung Moon knowledge In response to increased security concerns, biometrics is ecoming more focused on overcoming or complementing onventional possession-based uthentication. However, biometric authentication requires special care since the loss of biometric data is irrecoverable. In this paper, we present a biometric authentication framework, where several novel techniques are applied to provide security and privacy. First, a biometric template is saved in a transformed form. This makes it possible for a template to be canceled upon its loss while the original iometric information is not revealed. Second, when a user is registered with a server, a biometric template is stored in special form, named a ‘soft vault’. This technique prevents impersonation attacks even if data in a server is disclosed to an attacker. Finally, a one-time template" e22cf1ca10c11991c2a43007e37ca652d8f0d814,A Biologically Inspired Visual Working Memory,"Under review as a conference paper at ICLR 2019 A BIOLOGICALLY INSPIRED VISUAL WORKING MEMORY FOR DEEP NETWORKS Anonymous authors Paper under double-blind review" e2af85dc41269bc7c50fcf2fb35bfeb75e3d6ee4,xytocin Improves “ Mind-Reading ” in Humans,"PRIORITY COMMUNICATION Oxytocin Improves “Mind-Reading” in Humans Gregor Domes, Markus Heinrichs, Andre Michel, Christoph Berger, and Sabine C. Herpertz Background: The ability to “read the mind” of other individuals, that is, to infer their mental state by interpreting subtle social cues, is indispensable in human social interaction. The neuropeptide oxytocin plays a central role in social approach behavior in nonhuman mammals. Methods: In a double-blind, placebo-controlled, within-subject design, 30 healthy male volunteers were tested for their ability to infer the affective mental state of others using the Reading the Mind in the Eyes Test (RMET) after intranasal administration of 24 IU oxytocin. Results: Oxytocin improved performance on the RMET compared with placebo. This effect was pronounced for difficult compared with easy items. Conclusions: Our data suggest that oxytocin improves the ability to infer the mental state of others from social cues of the eye region. Oxytocin might play a role in the pathogenesis of autism spectrum disorder, which is characterized by severe social impairment. Key Words: Emotion, oxytocin, peptide, social cognition, theory of T he ability to infer the internal state of another person to dapt one’s own behavior is a cornerstone of all human social interactions. Humans have to infer internal states from external cues such as facial expressions in order to make sense of or predict another person’s behavior, an ability that is referred to as “mind-reading” (Siegal and Varley 2002; Stone et al 998). In particular, individuals with autism have distinct diffi-" e25e07cfd0818a499033caf9d7aa8ef4feec981b,Semantic Segmentation for Real-World Data by Jointly Exploiting Supervised and Transferrable Knowledge,"Pages 84.1-84.12 DOI: https://dx.doi.org/10.5244/C.30.84" e2b8ba13586bb9a96e4813472d1f763d37ead47d,Media Content Access : Image-Based Filtering,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 9, No. 3, 2018 Media Content Access: Image-Based Filtering Rehan Ullah Khan1, Ali Alkhalifah2 Information Technology Department Qassim University, Al-Qassim, KSA" 7e25544be9ba701c8cf02c841e0bbadb36fa0e29,Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Network,"Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks Long Chen1 Hanwang Zhang2 Jun Xiao1∗ Wei Liu3 Shih-Fu Chang4 Zhejiang University 2Nanyang Technological University 3Tencent AI Lab 4Columbia University {longc, {wliu, Figure 1: (a) Attribute variance heat maps of the 312 attributes in CUB birds [60] and the 102 attributes in SUN scenes [47] (lighter color indicates lower variance, i.e., lower discriminability) and the t-SNE [35] visualizations of the test images represented by all attributes (left) and only the high-variance ones (right). Some of the low-variance attributes (the lighter part to the left of the cut-off line) discarded at training are still needed in discriminating unseen test classes. (b) Comparison of reconstructed images using SAE [25] and our proposed SP-AEN method, which is shown to retain sufficient semantics for photo-realistic reconstruction." 7e7e4af2a79288fd2e391020edff8552ea1ece9a,Trimming Prototypes of Handwritten Digit Images with Subset Infinite Relational Model,"Trimming Prototypes of Handwritten Digit Images with Subset Infinite Relational Model Tomonari Masada1 and Atsuhiro Takasu2 Nagasaki University, 1-14 Bunkyo-machi, Nagasaki-shi, Nagasaki, 852-8521 Japan, National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo, 101-8430 Japan," 7e7b4b4a84c2aa0ee69b5cea3a4da7f62a0a37d5,GraSp: Combining Spatially-aware Mobile Devices and a Display Wall for Graph Visualization and Interaction,"Eurographics Conference on Visualization (EuroVis) 2017 J. Heer, T. Ropinski and J. van Wijk (Guest Editors) Volume 36 (2017), Number 3 GRASP: Combining Spatially-aware Mobile Devices nd a Display Wall for Graph Visualization and Interaction U. Kister1, K. Klamka1, C. Tominski2 and R. Dachselt1 Interactive Media Lab Dresden, Technische Universität Dresden, Germany Institute for Computer Science, University of Rostock, Germany Figure 1: Mobile devices support graph visualization and interaction on wall-sized displays close to the display wall and further away (A). The GRASP system provides a mobile toolbox with selections, alternative representations, lenses, and filtering close to the user (B)." 7e654380bd0d1f4c00e85da71a3081d3ada432ef,MGAN: TRAINING GENERATIVE ADVERSARIAL NETS,"Under review as a conference paper at ICLR 2018 MGAN: TRAINING GENERATIVE ADVERSARIAL NETS WITH MULTIPLE GENERATORS Anonymous authors Paper under double-blind review" 7e3367b9b97f291835cfd0385f45c75ff84f4dc5,Improved local binary pattern based action unit detection using morphological and bilateral filters,"Improved Local Binary Pattern Based Action Unit Detection Using Morphological and Bilateral Filters Anıl Y¨uce1, Matteo Sorci2 and Jean-Philippe Thiran1 Signal Processing Laboratory (LTS5) ´Ecole Polytechnique F´ed´erale de Lausanne, Switzerland nViso SA Lausanne, Switzerland" 7e8edc45fa80cb0f7bc2c20e8eb893dcadde2c8c,COMBINING SPEEDED-UP ROBUST FEATURES WITH PRINCIPAL COMPONENT ANALYSIS IN FACE RECOGNITION SYSTEM,"International Journal of Innovative Computing, Information and Control Volume 8, Number 12, December 2012 ICIC International c(cid:13)2012 ISSN 1349-4198 pp. 8545{8556 COMBINING SPEEDED-UP ROBUST FEATURES WITH PRINCIPAL COMPONENT ANALYSIS IN FACE RECOGNITION SYSTEM Shinfeng D. Lin(cid:3), Bo-Feng Liu and Jia-Hong Lin Department of Computer Science and Information Engineering National Dong Hwa University No. 1, Sec. 2, Da Hsueh Rd., Shoufeng, Hualien 97401, Taiwan Corresponding author: (cid:3) Received October 2011; revised March 2012" 7e463877264e70d53c844cf4b1bf3b15baec8cfb,ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks,"ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks Francesco Visin(cid:63) Politecnico di Milano Kyle Kastner(cid:63) University of Montreal Kyunghyun Cho(cid:63) University of Montreal Matteo Matteucci Politecnico di Milano Aaron Courville University of Montreal Yoshua Bengio University of Montreal CIFAR Senior Fellow" 7eba8590558148759b0aeebb0772e19ae50edb3c,Facial Recognition and Its Applications in Distance Learning Environment,Weidong Liao & Chad Vanorsdale1 7ed9913de03dd2990b68751842306c2636852647,VQABQ: Visual Question Answering by Basic Questions,"VQABQ: Visual Question Answering by Basic Questions Jia-Hong Huang King Abdullah University of Science and Technology {jiahong.huang, modar.alfadly, Modar Alfadly Bernard Ghanem" 7e55dab6f23f8e0f9587f76ec1dd66e2dbba436a,Pilgrims Face Recognition Dataset -- HUFRD,"Pilgrims Face Recognition Dataset – HUFRD Salah A. Aly Center of Research Excellence in Hajj and Umrah (HajjCore), College of Computers and Information Systems, Umm Al-Qura University, Makkah, KSA Email:" 7ed6ff077422f156932fde320e6b3bd66f8ffbcb,State of 3 D Face Biometrics for Homeland Security Applications,"State of 3D Face Biometrics for Homeland Security Applications Anshuman Razdan1, Gerald Farin2, Myung Soo-Bae3 and Mahesh Chaudhari4" 7ebd323ddfe3b6de8368c4682db6d0db7b70df62,Location-based Face Recognition Using Smart Mobile Device Sensors,"Proceedings of the International Conference on Computer and Information Science and Technology Ottawa, Ontario, Canada, May 11 – 12, 2015 Paper No. 111 Location-based Face Recognition Using Smart Mobile Device Sensors Nina Taherimakhsousi, Hausi A. Müller Department of Computer Science University of Victoria, Victoria, Canada" 7ea7c073d13e80ec5015f41f1d57f0674502cc5e,An Implementation of Face Emotion Identification System using Active Contour Model and PCA,"IJSRD - International Journal for Scientific Research & Development| Vol. 3, Issue 04, 2015 | ISSN (online): 2321-0613 An Implementation of Face Emotion Identification System using Active Contour Model and PCA Namita Rathore1 Mr.Rohit Miri2 P.G. Student 2Assistant Professor ,2Department of Computer Science and Engineering ,2DR C V Raman Institute of Science and Technology Kota, bilaspur systems, surveillance" 7e7430b5b6ffc470284b8fa94840797610d450ad,Free-space detection using online disparity-supervised color modeling,"Free-space detection using online disparity-supervised olor modeling Sanberg, W.P.; Dubbelman, G.; de With, P.H.N. Published in: Proceedings of the 7th Workshop on Planning, Perception and Navigation for Intelligent Vehicles (PPNIV) Published: 28/09/2015 Document Version Publisher’s PDF, also known as Version of Record (includes final page, issue and volume numbers) Please check the document version of this publication: • A submitted manuscript is the author's version of the article upon submission and before peer-review. There can be important differences etween the submitted version and the official published version of record. People interested in the research are advised to contact the uthor for the final version of the publication, or visit the DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication Citation for published version (APA): Sanberg, W. P., Dubbelman, G., & de With, P. H. N. (2015). Free-space detection using online disparity- supervised color modeling. In Proceedings of the 7th Workshop on Planning, Perception and Navigation for Intelligent Vehicles (PPNIV): at IEEE/RSJ IROS (pp. 105-110) General rights" 7e507370124a2ac66fb7a228d75be032ddd083cc,Dynamic Pose-Robust Facial Expression Recognition by Multi-View Pairwise Conditional Random Forests,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TAFFC.2017.2708106, IEEE Transactions on Affective Computing Dynamic Pose-Robust Facial Expression Recognition by Multi-View Pairwise Conditional Random Forests Arnaud Dapogny1 and Kevin Bailly1 and S´everine Dubuisson1 Sorbonne Universit´es, UPMC Univ Paris 06 CNRS, UMR 7222, F-75005, Paris, France" 7e157fb05614a158397bc2a3bf7b7962b1a123ce,Deep Network Embedding for Graph Representation Learning in Signed Networks,"This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. Deep Network Embedding for Graph Representation Learning in Signed Networks Xiao Shen nd Fu-Lai Chung" 7ebc96b4b7886b263808c2cd62b21158ebf6297c,"Crowd Motion Analysis: Segmentation, Anomaly Detection, and Behavior Classification","CROWD MOTION ANALYSIS: SEGMENTATION, ANOMALY DETECTION, AND BEHAVIOR CLASSIFICATION Habib Ullah Advisor: Nicola Conci, PhD February 2015" 7e5414277148c8fdf9903068b001887225b69868,Perceptive Parallel Processes Coordinating Geometry and Texture,"Perceptive Parallel Processes Coordinating Geometry and Texture Marco A. Gutierrez1, Rafael E. Banchs2 and Luis F. D'Haro2" 7e3693fffef8d83ac109309a77f2545d32c10fc3,The effect of Ramadan fasting on spatial attention through emotional stimuli,"Psychology Research and Behavior Management Open access Full Text article Dovepress open access to scientific and medical research O Ri g i n a l R e s e aRc h The effect of Ramadan fasting on spatial attention through emotional stimuli Maziyar Molavi Jasmy Yunus nugraha P Utama Department of clinical sciences, Faculty of Biosciences and Medical engineering (FBMe), Universiti Teknologi Malaysia (UTM), Johor Bahru, Johor, Malaysia orrespondence: nugraha P Utama Department of clinical sciences, Faculty of Biosciences and Medical engineering, Universiti Teknologi Malaysia (UTM), 81310 Johor Bahru, Johor, Malaysia" 7e53ab07d0ce28484830329036a1fc018b9644dd,Online multiple people tracking-by-detection in crowded scenes,"Journal of Advances in Computer Engineering and Technology, 1(2) 2015 Online multiple people tracking-by-detection in rowded scenes Sahar Rahmatian1, Reza Safabakhsh2 Received (2015-01-23) Accepted (2015-03-19)" 7e59d2d3416537dd958ff71b7a0bff87e639dad9,Feature-Based Pose Estimation,"Feature-based Pose Estimation Cristian Sminchisescu1,2, Liefeng Bo3, Catalin Ionescu4, Atul Kanaujia5" 7ee53d931668fbed1021839db4210a06e4f33190,What If We Do Not have Multiple Videos of the Same Action? — Video Action Localization Using Web Images,"What if we do not have multiple videos of the same action? — Video Action Localization Using Web Images Center for Research in Computer Vision (CRCV), University of Central Florida (UCF) Waqas Sultani, Mubarak Shah" 7ed241bcf77552889850640ca9782993fa78c1a9,The HCI Benchmark Suite: Stereo and Flow Ground Truth with Uncertainties for Urban Autonomous Driving,"The HCI Benchmark Suite: Stereo And Flow Ground Truth With Uncertainties for Urban Autonomous Driving Daniel Kondermann∗ Rahul Nair∗ Katrin Honauer∗ Karsten Krispin∗ Jonas Andrulis† Alexander Brock∗ Burkhard G¨ussefeld∗ Mohsen Rahimimoghaddam∗ Sabine Hofmann‡ Claus Brenner‡ Bernd J¨ahne∗ Heidelberg Collaboratory for Image Processing, Pallas Ludens GmbH, Institute of Cartography and Geoinformatics, Ruprecht-Karls Universit¨at Heidelberg, Germany Heidelberg, Germany Leibniz Universit¨at Hannover, Germany" 7ea07b7b27d59300840df17e5881dbe3a4769872,Detection driven adaptive multi-cue integration for multiple human tracking,"Detection Driven Adaptive Multi-cue Integration for Multiple Human Tracking Ming Yang, Fengjun Lv, Wei Xu, Yihong Gong NEC Laboratories America, Inc. 0080 North Wolfe Road, SW-350, Cupertino, CA 95014" 7e2602f7572add68636863504bfe9ff271f3796a,Asymmetric Bilateral Phase Correlation for Optical Flow Estimation in the Frequency Domain,"Flow Estimation in the Frequency Domain Vasileios Argyriou Kingston University London London, UK" 7e3b5d30b83a20c7cffdacf53b3ffbaf81002b54,People Transitioning Across Places : A Multimethod Investigation of How People Go to Football Games,"12589 EABXXX10.1177/0013916511412589 © The Author(s) 2011 Reprints and permission: http://www. sagepub.com/journalsPermissions.nav Environment and Behavior XX(X) 1 –28 © 2011 SAGE Publications Reprints and permission: http://www. sagepub.com/journalsPermissions.nav DOI: 10.1177/0013916511412589 http://eab.sagepub.com People Transitioning Across Places: A Multimethod Investigation of How People Go to Football Games R. Barry Ruback1, Robert T. Collins1, Sarah Koon-Magnin1, Weina Ge2, Luke Bonkiewicz1, and Clifford E. Lutz1" 7ef0cc4f3f7566f96f168123bac1e07053a939b2,Triangular Similarity Metric Learning: a Siamese Architecture Approach. ( L'apprentissage de similarité triangulaire en utilisant des réseaux siamois),"Triangular Similarity Metric Learning: a Siamese Architecture Approach Lilei Zheng To cite this version: Lilei Zheng. Triangular Similarity Metric Learning: a Siamese Architecture Approach. Com- puter Science [cs]. UNIVERSITE DE LYON, 2016. English. . HAL Id: tel-01314392 https://hal.archives-ouvertes.fr/tel-01314392 Submitted on 11 May 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" fd9286f0e465deffad59123f46fa4f66cb15c3e4,Learning Answer Embeddings for Visual Question Answering,"Learning Answer Embeddings for Visual Question Answering Hexiang Hu∗ U. of Southern California Los Angeles, CA Wei-Lun Chao∗ Los Angeles, CA U. of Southern California U. of Southern California Fei Sha Los Angeles, CA" fd0a1a2ecf69a6c1a6efcb18b8f23e4d5402f601,"ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events","ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events Evan Racah1,2, Christopher Beckham1,3, Tegan Maharaj1,3, Samira Ebrahimi Kahou4, Prabhat2, Christopher Pal1,3 MILA, Université de Montréal, Lawrence Berkeley National Lab, Berkeley, CA, École Polytechnique de Montréal, Microsoft Maluuba," fdebde7926e87dbfb6e73dd4f8324ad2ec45d7a6,Image Segmentation for Biometric Identification Systems,"Image Segmentation for Biometric Identification Systems Eyad Haj Said Dissertation submitted to the College of Engineering and Mineral Resources t West Virginia University in partial fulfillment of the requirements for the degree of Doctor of Philosophy Computer Engineering Hany H. Ammar Ph.D, Committee Chairperson Arun Ross, Ph.D Xin Li, Ph.D Sam Mukdadi , Ph.D Mohamed Abdel-Mottaleb, Ph.D Lane Department of Computer Science and Electrical Engineering Morgantown, West Virginia Keywords: Biometrics, Image Segmentation, Automated Segmentation Evaluation, ADIS, AEIS Copyright 2007 Eyad Haj Said" fdf533eeb1306ba418b09210387833bdf27bb756,Exploiting Unrelated Tasks in Multi-Task Learning, fdf31db5aa8cf8a7f9ac84fcc7b0949e8e000a41,MODELING FASHION Anonymous ICME submission,"MODELING FASHION Anonymous ICME submission" fd8b1715ad34858bf8650ac549c4249d86edbb7c,A survey of techniques for human segmentation from static images,"International Association of Scientific Innovation and Research (IASIR) (An Association Unifying the Sciences, Engineering, and Applied Research) ISSN (Print): 2279-0063 ISSN (Online): 2279-0071 International Journal of Software and Web Sciences (IJSWS) www.iasir.net A survey of techniques for human segmentation from static images Ms.Ashwini T. Magar, Prof.J.V.Shinde Late G.N.Sapkal College of Engineering, Computer Engineering Department, Nashik, University of Pune, India. __________________________________________________________________________________________" fde0180735699ea31f6c001c71eae507848b190f,Face Detection and Sex Identification from Color Images using AdaBoost with SVM based Component Classifier,"International Journal of Computer Applications (0975 – 8887) Volume 76– No.3, August 2013 Face Detection and Sex Identification from Color Images using AdaBoost with SVM based Component Classifier Tonmoy Das Lecturer, Department of EEE University of Information Technology and Sciences (UITS) Dhaka, Bangladesh Manamatha Sarnaker B.Sc. in EEE International University of Business Agriculture and Technology (IUBAT) Dhaka-1230, Bangladesh Md. Hafizur Rahman Lecturer, Department of EEE International University of Business Agriculture and" fd4ac1da699885f71970588f84316589b7d8317b,Supervised Descent Method for Solving Nonlinear Least Squares Problems in Computer Vision,"JOURNAL OF LATEX CLASS FILES, VOL. 6, NO. 1, JANUARY 2007 Supervised Descent Method for Solving Nonlinear Least Squares Problems in Computer Vision Xuehan Xiong, and Fernando De la Torre" fd4c46bfd3bb00ed93b0bb5b28ef0336f59f0c15,Expressing emotions through vibration for perception and control,"Expressing Emotions through Vibration for Perception and Control Shafiq ur Réhman Doctoral Thesis, April 2010 Department of Applied Physics and Electronics Umeå University, Sweden UNIVERSITETSSERVICEProfil & CopyshopÖppettider:Måndag - fredag 10-16Tel. 786 52 00 alt 070-640 52 01Universumhuset" fdb956c7705b7f57f56f944a0f3f4ede1d6f77fa,Does Fast Fashion Increase the Demand for Premium Brands ?,"Does Fast Fashion Increase the Demand for Premium Brands? A Structural Analysis Zijun (June) Shi1, Param Vir Singh, Dokyun Lee, Kannan Srinivasan (Preliminary draft. Please do not cite without the authors’ permission.)" fdb0472af94a726897c20b6b181c6d71ee293e71,Quality assessment of image-based biometric information,"El-Abed et al. EURASIP Journal on Image and Video Processing (2015) 2015:3 DOI 10.1186/s13640-015-0055-8 RESEARCH Open Access Quality assessment of image-based biometric information Mohamad El-Abed1*, Christophe Charrier2,3,4 and Christophe Rosenberger2,3,4" fd23502287ae4ca8db63e4e5080c359610398be5,Real-Time Pedestrian Detection with Deep Network Cascades,"ANGELOVA ET AL.: REAL-TIME PEDESTRIAN DETECTION WITH DEEP CASCADES Real-Time Pedestrian Detection With Deep Network Cascades Anelia Angelova1 Alex Krizhevsky1 Vincent Vanhoucke1 Abhijit Ogale2 Dave Ferguson2 Google Research 600 Amphitheatre Parkway Mountain View, CA, USA Google X 600 Amphitheatre Parkway Mountain View, CA, USA" fdfaf46910012c7cdf72bba12e802a318b5bef5a,Computerized Face Recognition in Renaissance Portrait Art,"Computerized Face Recognition in Renaissance Portrait Art Ramya Srinivasan, Conrad Rudolph and Amit Roy-Chowdhury" fdf9c636f79f146f116bbca392dcad3b535cecb2,Statistical Approaches to Inferring Object Shape from Single Images,"Statistical Approaches to Inferring Object Shape from Single Images Ashwini Shikaripur Nadig Submitted to the Department of Electrical Engineering and Computer Science and the Graduate Faculty of the University of Kansas in partial fulllment of the requirements for the degree of Doctor of Philosophy Committee members Dr. Bo Luo, Chairperson Dr. Brian Potetz, Co-chair Dr. Luke Huan Dr. James Miller Dr. Paul Selden Date defended: May 20, 2014" fd069af1ede370625703f7984e52f282fcd6342e,Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents,"Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents Haonan Yu†, Xiaochen Lian†, Haichao Zhang†, and Wei Xu‡ Baidu Research, Sunnyvale CA USA Horizon Robotics, Cupertino CA USA" fdd94d77377df6e55d14e41a28141dc241d8b5d6,Current Status and Future Prospects of Clinical Psychology: Toward a Scientifically Principled Approach to Mental and Behavioral Health Care.,"Current Status and Future Prospects of Clinical Psychology: Toward a Scientifically Principled Approach to Mental and Behavioral Health Care Author(s): Timothy B. Baker, Richard M. McFall and Varda Shoham Source: Psychological Science in the Public Interest, Vol. 9, No. 2 (November 2008), pp. 67- Published by: Sage Publications, Inc. on behalf of the Association for Psychological Science Stable URL: http://www.jstor.org/stable/20697320 Accessed: 07-02-2017 15:41 UTC REFERENCES Linked references are available on JSTOR for this article: http://www.jstor.org/stable/20697320?seq=1&cid=pdf-reference#references_tab_contents You may need to log in to JSTOR to access the linked references. JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at http://about.jstor.org/terms Sage Publications, Inc., Association for Psychological Science are collaborating with JSTOR to digitize, preserve and extend access to Psychological Science in the Public Interest This content downloaded from 129.133.179.122 on Tue, 07 Feb 2017 15:41:42 UTC All use subject to http://about.jstor.org/terms" fdca08416bdadda91ae977db7d503e8610dd744f,The Ksera Project (http://www.ksera under the 7th Framework Programme (fp7) for Research and Technological Development under Grant Human Robot Interaction Ksera Project (http://www.ksera-project.eu) Has Received Funding from the European Commission under the 7th Framework Programme (fp7) for Researc,"ICT-2009.7.1 KSERA Project 010-248085 Deliverable D3.1 Deliverable D3.1 Human Robot Interaction Human Robot Interaction 8 October 2010 Public Document The KSERA project (http://www.ksera KSERA project (http://www.ksera-project.eu) has received funding from the European Commission project.eu) has received funding from the European Commission under the 7th Framework Programme (FP7) for Research and Technological Development under grant under the 7th Framework Programme (FP7) for Research and Technological Development under grant under the 7th Framework Programme (FP7) for Research and Technological Development under grant greement n°2010-248085." fd4537b92ab9fa7c653e9e5b9c4f815914a498c0,One-Sided Unsupervised Domain Mapping, fde3f34a1accadb73269e4beef487611f682b781,"Before A Computer Can Draw, It Must First Learn To See","Before A Computer Can Draw, It Must First Learn To See Derrall Heath and Dan Ventura Computer Science Department Brigham Young University Provo, UT 84602 USA" fdee0cf79e9a2695857afeee6526352918c9f315,Quantization for Rapid Deployment of Deep Neural Networks,"Quantization for Rapid Deployment of Deep Neural Networks Jun Haeng Lee∗, Sangwon Ha∗, Saerom Choi, Won-Jo Lee, Seungwon Lee Samsung Advanced Institute of Technology Samsung-ro 130, Suwon-si, Republic of Korea {junhaeng2.lee," fdb33141005ca1b208a725796732ab10a9c37d75,A connectionist computational method for face recognition,"Int.J.Appl. Math. Comput.Sci.,2016,Vol. 26,No. 2,451–465 DOI: 10.1515/amcs-2016-0032 A CONNECTIONIST COMPUTATIONAL METHOD FOR FACE RECOGNITION FRANCISCO A. PUJOL a, HIGINIO MORA a,∗ , JOS ´E A. GIRONA-SELVA a Department of Computer Technology University of Alicante, 03690, San Vicente del Raspeig, Alicante, Spain e-mail: In this work, a modified version of the elastic bunch graph matching (EBGM) algorithm for face recognition is introduced. First, faces are detected by using a fuzzy skin detector based on the RGB color space. Then, the fiducial points for the facial graph are extracted automatically by adjusting a grid of points to the result of an edge detector. After that, the position of the nodes, their relation with their neighbors and their Gabor jets are calculated in order to obtain the feature vector defining each face. A self-organizing map (SOM) framework is shown afterwards. Thus, the calculation of the winning neuron and the recognition process are performed by using a similarity function that takes into account both the geometric and texture information of the facial graph. The set of experiments carried out for our SOM-EBGM method shows the accuracy of our proposal when compared with other state-of the-art methods. Keywords: pattern recognition, face recognition, neural networks, self-organizing maps. Introduction libraries, In recent years, there has been intensive research carried" fd4f9955ec28b63443039cb9d4e15bae796defe4,Predictably Angry - Facial Cues Provide a Credible Signal of Destructive Behavior,"Predictably Angry Facial cues provide a credible signal of destructive behavior Boris van Leeuwen1, Charles N. Noussair2, Theo Offerman3, Sigrid Suetens4, Matthijs van Veelen5, and Jeroen van de Ven6 November 2016" fd51665efe2520a55aa58b2f1863a3bd9870529f,Understanding Compressive Adversarial Privacy,"Understanding Compressive Adversarial Privacy Xiao Chen, Peter Kairouz, Ram Rajagopal" fd4b5766a8ace0d89676deb26a098949a96089a3,Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos,"Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos Naman Kohli, Student Member, IEEE, Daksha Yadav, Student Member, IEEE, Mayank Vatsa, Senior Member, IEEE, Richa Singh, Senior Member, IEEE, and Afzel Noore, Senior Member, IEEE." fdfff58f62ffe7ab76c2b2cc32ea20099d197194,On the Nonlinear Statistics of Optical Flow,"ON THE NONLINEAR STATISTICS OF OPTICAL FLOW HENRY ADAMS, JOHNATHAN BUSH, BRITTANY CARR, LARA KASSAB, AND JOSHUA MIRTH" fd96432675911a702b8a4ce857b7c8619498bf9f,Improved Face Detection and Alignment using Cascade Deep Convolutional Network,"Improved Face Detection and Alignment using Cascade Deep Convolutional Network Weilin Cong†, Sanyuan Zhao†, Hui Tian‡, and Jianbing Shen† Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science,Beijing Institute of Technology, Beijing 100081, P.R.China China Mobile Research Institute, Xuanwu Men West Street, Beijing" fd615118fb290a8e3883e1f75390de8a6c68bfde,Joint Face Alignment with Non-parametric Shape Models,"Joint Face Alignment with Non-Parametric Shape Models Brandon M. Smith and Li Zhang University of Wisconsin – Madison http://www.cs.wisc.edu/~lizhang/projects/joint-align/" fd0e1fecf7e72318a4c53463fd5650720df40281,End-to-End Comparative Attention Networks for Person Re-Identification,"End-to-End Comparative Attention Networks for Person Re-identification Hao Liu, Jiashi Feng, Meibin Qi, Jianguo Jiang and Shuicheng Yan, Fellow, IEEE" fd63df88af4b4a30b315904de22995b3da798b09,Generative Modeling of Multimodal Multi-Human Behavior,"Generative Modeling of Multimodal Multi-Human Behavior Boris Ivanovic1 Edward Schmerling2 Karen Leung3 Marco Pavone3" fdaf65b314faee97220162980e76dbc8f32db9d6,Face recognition using both visible light image and near-infrared image and a deep network,"Accepted Manuscript Face recognition using both visible light image and near-infrared image and a deep network Kai Guo, Shuai Wu, Yong Xu Reference: S2468-2322(17)30014-8 0.1016/j.trit.2017.03.001 TRIT 41 To appear in: CAAI Transactions on Intelligence Technology Received Date: 30 January 2017 Accepted Date: 28 March 2017 Please cite this article as: K. Guo, S. Wu, Y. Xu, Face recognition using both visible light image and near-infrared image and a deep network, CAAI Transactions on Intelligence Technology (2017), doi: 0.1016/j.trit.2017.03.001. This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo opyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain." fdda5852f2cffc871fd40b0cb1aa14cea54cd7e3,Im2Flow: Motion Hallucination from Static Images for Action Recognition,"Im2Flow: Motion Hallucination from Static Images for Action Recognition Ruohan Gao UT Austin Bo Xiong UT Austin Kristen Grauman UT Austin" fd1b917476b114919de0ae1b6a4b96a52a410c20,A Memory Based Face Recognition Method,"A Memory Based Face Recognition Method Alex Pappachen James B. Tech. (Hons), M. Tech. Grif‌f‌ith School of Engineering Science, Environment, Engineering and Technology Grif‌f‌ith University Submitted in fulfilment of the requirements of the degree of Doctor of Philosophy November 2008" fdc60fe4654b5efe0752acabef0ec6258062be0f,Multi-Sensor Fusion Adopted 2-D Laser Rangefinder and Camera for Pedestrian Detection,"2nd ITS World Congress, Bordeaux, France, 5–9 October 2015 Paper number ITS-1576 Multi-Sensor Fusion Adopted 2-D Laser Rangefinder and Camera for Pedestrian Detection Kuo-Ching Chang*, Chi-Kuo Chen, Pao-Kai Tseng Automotive Research & Testing Center, Taiwan +886-4-7811222 Ext. 2323," fdbe7c520568d9a32048270d2c87113c635dc7e6,Live Stream Oriented Age and Gender Estimation using Boosted LBP Histograms Comparisons,"Live Stream Oriented Age and Gender Estimation using Boosted LBP Histograms Comparisons LAMIA, University of the French West Indies and Guiana, Campus de Fouillole, BP 250, 97157 Pointe `a Pitre, France Lionel Prevost1, Philippe Phothisane2 and Erwan Bigorgne2 Eikeo, 11 rue L´eon Jouhaux, 75010 Paris, France Keywords: Face Analysis, Boosting, Gender Estimation, Age Estimation." 5c1fcee7c31fb2dd54a35670b63cdb2af5726ae6,TUNIR : A Multi-Modal Database for Person Authentication under Near Infrared Illumination,"TUNIR: A Multi-Modal Database for Person Authentication under Near Infrared Illumination Shuyan Zhao and Ralph Kricke and Rolf-Rainer Grigat TUHH Vision Systems (E-2) Harburger Schloßstr. 20, 21079 Hamburg, Germany Tel: +49 40 42878-3125, Fax: +49 40 42878-2911 http://www.ti1.tu-harburg.de in: 6th WSEAS International Conference on Signal Processing, Robotics and Automation (ISPRA 007). See also BIBTEX entry below. BIBTEX: uthor = {Shuyan Zhao and Ralph Kricke and Rolf-Rainer Grigat}, title = {TUNIR: A Multi-Modal Database for Person Authentication under Near Infrared Illumination}, ooktitle = {6th WSEAS International Conference on Signal Processing, Robotics nd Automation (ISPRA 2007)}, year = {2007}, month = {feb}, url = {http://www.ti1.tu-harburg.de/Publikationen} © copyright by the author(s)" 5c8ad080ccb3f5e3c999c2948029f0bd005d5635,Engaging Image Captioning,"ENGAGING IMAGE CAPTIONING VIA PERSONALITY Kurt Shuster, Samuel Humeau, Hexiang Hu, Antoine Bordes, Jason Weston Facebook AI Research" 5c6ccca19179fd217a74ccb954a4c4370e4203e2,Correspondences of Persistent Feature Points on Near-Isometric Surfaces,"Correspondences of Persistent Feature Points on Near-Isometric Surfaces Ying Yang1,2, David G¨unther1,3, Stefanie Wuhrer3,1, Alan Brunton3,4 Ioannis Ivrissimtzis2, Hans-Peter Seidel1, Tino Weinkauf1 (cid:63) MPI Informatik 2Durham University 3Saarland University 4University of Ottawa" 5c48f97a8a8217025abafeababaef6288fd7ded6,Model syndromes for investigating social cognitive and affective neuroscience: a comparison of Autism and Williams syndrome.,"doi:10.1093/scan/nsl035 SCAN (2006) 1of 8 Model syndromes for investigating social cognitive nd affective neuroscience: a comparison of utism and Williams syndrome Helen Tager-Flusberg, Daniela Plesa Skwerer, and Robert M. Joseph Boston University School of Medicine, Boston, MA, USA Autism and Williams syndrome are genetically based neurodevelopmental disorders that present strikingly different social phenotypes. Autism involves fundamental impairments in social reciprocity and communication, whereas people with Williams syndrome are highly sociable and engaging. This article reviews the behavioral and neuroimaging literature that has explored the neurocognitive mechanisms that underlie these contrasting social phenotypes, focusing on studies of face processing. The article oncludes with a discussion of how the social phenotypes of both syndromes may be characterized by impaired connectivity etween the amygdala and other critical regions in the ’social brain’. Keywords: autism; Williams syndrome; face processing; emotion processing; amygdala INTRODUCTION For the past two decades autism, (ASD)1 and Williams syndrome (WMS) have captured the interest and imagina- tion of cognitive neuroscientists. These neurodevelopmental disorders present striking phenotypes that hold out the promise of advancing our understanding of the biological" 5cd34abb1e96e0c11f427364e40b1e87d6fc62c2,Greedy Part-Wise Learning of Sum-Product Networks,"Greedy Part-Wise Learning of Sum-Product Networks Robert Peharz, Bernhard C. Geiger and Franz Pernkopf {robert.peharz, geiger, Signal Processing and Speech Communication Laboratory Graz, University of Technology" 5c02bd53c0a6eb361972e8a4df60cdb30c6e3930,Multimedia stimuli databases usage patterns: a survey report,"Multimedia stimuli databases usage patterns: a survey report M. Horvat1, S. Popović1 and K. Ćosić1 University of Zagreb, Faculty of Electrical Engineering and Computing Department of Electric Machines, Drives and Automation Zagreb, Croatia" 5c435c4bc9c9667f968f891e207d241c3e45757a,"""How old are you?"" : Age Estimation with Tensors of Binary Gaussian Receptive Maps","RUIZ-HERNANDEZ, CROWLEY, LUX: HOW OLD ARE YOU? ""How old are you?"" : Age Estimation with Tensors of Binary Gaussian Receptive Maps John A. Ruiz-Hernandez James L. Crowley Augustin Lux INRIA Grenoble Rhones-Alpes Research Center and Laboratoire d’Informatique de Grenoble (LIG) 655 avenue de l’Europe 8 334 Saint Ismier Cedex, France" 5cebc83001ea0737cc46360850fd294327c82013,MEMORY-BASED GAIT RECOGNITION 1 Memory-based Gait Recognition,"DANLIUet al.:MEMORY-BASEDGAITRECOGNITION Memory-based Gait Recognition Dan Liu Mao Ye∗ Xudong Li Feng Zhang Lan Lin School of Computer Science and Engineering, Center for Robotics, Key Laboratory for NeuroInformation of Ministry of Education, University of Electronic Science and Technology of China, Chengdu 611731, P.R. China" 5c81048593a6729b2d0b948a1129a97bdbf82f11,Moving Object Localization Using Optical Flow for Pedestrian Detection from a Moving Vehicle,"Hindawi Publishing Corporation e Scientific World Journal Volume 2014, Article ID 196415, 8 pages http://dx.doi.org/10.1155/2014/196415 Research Article Moving Object Localization Using Optical Flow for Pedestrian Detection from a Moving Vehicle Joko Hariyono, Van-Dung Hoang, and Kang-Hyun Jo Graduate School of Electrical Engineering, University of Ulsan, Ulsan 680-749, Republic of Korea Correspondence should be addressed to Kang-Hyun Jo; Received 9 April 2014; Revised 7 June 2014; Accepted 8 June 2014; Published 10 July 2014 Academic Editor: Yu-Bo Yuan Copyright © 2014 Joko Hariyono et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This paper presents a pedestrian detection method from a moving vehicle using optical flows and histogram of oriented gradients (HOG). A moving object is extracted from the relative motion by segmenting the region representing the same optical flows after ompensating the egomotion of the camera. To obtain the optical flow, two consecutive images are divided into grid cells 14 × 14 pixels; then each cell is tracked in the current frame to find corresponding cell in the next frame. Using at least three corresponding ells, affine transformation is performed according to each corresponding cell in the consecutive images, so that conformed optical flows are extracted. The regions of moving object are detected as transformed objects, which are different from the previously" 5c1e0e94d6cb74448c7b3c1e0db42121be4e9bd6,Saliency Detection using regression trees on hierarchical image segments,"SALIENCY DETECTION USING REGRESSION TREES ON HIERARCHICAL IMAGE SEGMENTS G¨okhan Yildirim, Appu Shaji, Sabine S¨usstrunk School of Computer and Communication Sciences ´Ecole Polytechnique F´ed´erale de Lausanne" 5c6de2d9f93b90034f07860ae485a2accf529285,Compensating for pose and illumination in unconstrained periocular biometrics,"Int. J. Biometrics, Vol. X, No. Y, xxxx Compensating for pose and illumination in unconstrained periocular biometrics Chandrashekhar N. Padole and Hugo Proença* Department of Computer Science, IT – Instituto de Telecomunicações, University of Beira Interior, 6200-Covilhã, Portugal Fax: +351-275-319899 E-mail: E-mail: *Corresponding author" 5cc9fdd3a588f6e62e46d7884c1dbeef92a782f2,Spontaneous attention to faces in Asperger syndrome using ecologically valid static stimuli.,"Durham Research Online Deposited in DRO: 6 December 2014 Version of attached le: Accepted Version Peer-review status of attached le: Peer-reviewed Citation for published item: Hanley, M. and McPhillips, M. and Mulhern, G. and Riby, D. M. (2013) 'Spontaneous attention to faces in Asperger Syndrome using ecologically valid static stimuli.', Autism., 17 (6). pp. 754-761. Further information on publisher's website: http://dx.doi.org/10.1177/1362361312456746 Publisher's copyright statement: Use policy The full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that: • a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders." 5c0dc4dff1dfb5e27b19bef0713bccd9f85ce3b2,Joint probabilistic pedestrian head and body orientation estimation,"014 IEEE Intelligent Vehicles Symposium (IV) June 8-11, 2014. Dearborn, Michigan, USA 978-1-4799-3637-3/14/$31.00 ©2014 IEEE" 5cead7ba087ebe7314f96d875f3d3dbb8dbed1c7,Automatic Food Intake Assessment Using Camera Phones,"Michigan Technological University Digital Commons Michigan Dissertations, Master's Theses and Master's Reports - Open Dissertations, Master's Theses and Master's Reports Automatic Food Intake Assessment Using Camera Phones Fanyu Kong Michigan Technological University Copyright 2012 Fanyu Kong Recommended Citation Kong, Fanyu, ""Automatic Food Intake Assessment Using Camera Phones"", Dissertation, Michigan Technological University, 2012. http://digitalcommons.mtu.edu/etds/494 Follow this and additional works at: http://digitalcommons.mtu.edu/etds Part of the Computer Engineering Commons" 5c35ac04260e281141b3aaa7bbb147032c887f0c,Face Detection and Tracking Control with Omni Car,"Face Detection and Tracking Control with Omni Car Jheng-Hao Chen, Tung-Yu Wu CS 231A Final Report June 31, 2016" 5c315aae464602115674716a7f976c4992fcb98e,Teachers’ Perception in the Classroom,"Teachers’ Perception in the Classroom ¨Omer S¨umer1 Patricia Goldberg1 Kathleen St¨urmer1 Tina Seidel3 Peter Gerjets2 Ulrich Trautwein1 Enkelejda Kasneci1 University of T¨ubingen, Germany Leibniz-Institut f¨ur Wissensmedien, Germany Technical University of Munich, Germany" 5c4f8972ff0df23161cbdf1d70ea91f0e545d52d,Machine Learning with Dual Process Models, 5c2e264d6ac253693469bd190f323622c457ca05,Improving large-scale face image retrieval using multi-level features,"978-1-4799-2341-0/13/$31.00 ©2013 IEEE ICIP 2013" 5ca2e14f91dffb4784c443fe5cfe7838c3f3713c,Convolutional Recurrent Predictor: Implicit Representation for Multi-target Filtering and Tracking,"Convolutional Recurrent Predictor: Implicit Representation for Multi-target Filtering and Tracking Mehryar Emambakhsh, Alessandro Bay and Eduard Vazquez {mehryar.emambakhsh, alessandro.bay, Cortexica Vision Systems London, UK" 5c271b5f96cfce1b4fdacc728ae8f8ebcbc738f9,A framework for implicit human-centered image tagging inspired by attributed affect,"Vis Comput (2013) O R I G I NA L A RT I C L E A framework for implicit human centered image tagging inspired by attributed affect Konstantinos C. Apostolakis · Petros Daras Published online: © Springer-Verlag Berlin Heidelberg 2013" 5c09d905f6d4f861624821bf9dfe2aae29137e9c,Women Also Snowboard: Overcoming Bias in Captioning Models,"Women also Snowboard: Overcoming Bias in Captioning Models Lisa Anne Hendricks * 1 Kaylee Burns * 1 Kate Saenko 2 Trevor Darrell 1 Anna Rohrbach 1" 5c45a1abc51fe059987bcfba19b1d5076a8d9afb,Autonomous Object Category Learning for Service Robots Using Internet Resources,"Autonomous Object Category Learning for Service Robots Using Internet Resources Md Reaz Ashraful Abedin November 20, 2016 Master’s Thesis in Computing Science, 30 credits Supervisor at CS-UmU: Thomas Hellstr¨om Examiner: Ola Ringdahl Ume˚a University Department of Computing Science SE-901 87 UME˚A SWEDEN" 5cf12787b9ee536817c0429700c75b98f04192ba,A Self-Supervised Bootstrap Method for Single-Image 3D Face Reconstruction,"A Self-Supervised Bootstrap Method for Single-Image 3D Face Reconstruction Yifan Xing Rahul Tewari Paulo R. S. Mendonc¸a Amazon Web Services" 5c3fd194ba96c5eea41c0772ad0b2292dedcd197,Understanding the Energy Saving Potential of Smart Scale Selection in the Viola and Jones Facial Detection Algorithm, 5cdc02ed9f456219369fe3115321564c9955b9ae,Real-time Analysis and Visualization of the YFCC 100 m Dataset,"Real-time Analysis and Visualization of the YFCC100m Dataset Firstname Lastname Institute City, Country" 5c5dbca68946434afb201f0df90011104c85e4c4,Robust 3D Patch-Based Face Hallucination,"Robust 3D Patch-Based Face Hallucination Chengchao Qu1,2 Christian Herrmann1,2 Eduardo Monari2 Tobias Schuchert2 J¨urgen Beyerer2,1 Vision and Fusion Laboratory (IES), Karlsruhe Institute of Technology (KIT) Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (Fraunhofer IOSB)" 5cff58d081a4732b11e6da498196ed6fbb54d15b,Adversarial Examples for Semantic Segmentation and Object Detection,"Adversarial Examples for Semantic Segmentation and Object Detection Cihang Xie1*, Jianyu Wang2*, Zhishuai Zhang1∗, Yuyin Zhou1, Lingxi Xie1, Alan Yuille1 Department of Computer Science, The Johns Hopkins University, Baltimore, MD 21218 USA {cihangxie306, wjyouch, zhshuai.zhang, zhouyuyiner, 198808xc, Baidu Research USA, Sunnyvale, CA 94089 USA" 5c44807fb7a38d4c9c3ef3bdfb950b44c4a02a3f,Viewpoints and keypoints,"Viewpoints and Keypoints Shubham Tulsiani and Jitendra Malik University of California, Berkeley - Berkeley, CA 94720" 5c7db2907c586f4f2d6ae5937b0dc0f4d1bc834a,DELIVERABLE D 2 . 1 AUDIO-VISUAL ALGORITHMS FOR PERSON TRACKING AND CHARACTERIZATION ( BASELINE ),"MULTIMODAL MALL ENTERTAINMENT ROBOT mummer-project.eu Grant No. 688147. Project started 2016-03-01. Duration 48 months. DELIVERABLE D2.1 AUDIO-VISUAL ALGORITHMS FOR PERSON TRACKING AND CHARACTERIZATION (BASELINE) Jean-Marc Odobez (Idiap), Natalia Lyubova (SBRE), Olivier Can´evet (Idiap), Kenneth Funes Mora (Idiap), Weipeng He (Idiap), Angel Martinez Gonzalez (Idiap), Jean-Marc Montanier (SBRE), Marc Moreaux (SBRE) Beneficiaries: Workpackage: Idiap Research Institute (lead), SoftBank Robotics Europe Active Multimodal Sensing and Perception Version: Nature: Dissemination level: Pages: 017-3-3 Draft" 5c9c153f705a02e157adcf49dccf4f1eeb70cf93,Learning Appearance Transfer for Person Re-identification,"Learning Appearance Transfer for Person Re-identification Tamar Avraham and Michael Lindenbaum" 5cb343e447c7fd933ff8f57fc9c99c5673cad97d,MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild,"MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild Grégory Rogez Cordelia Schmid Inria Grenoble Rhône-Alpes, Laboratoire Jean Kuntzmann, France" 5c717afc5a9a8ccb1767d87b79851de8d3016294,A novel eye region based privacy protection scheme,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 5cd11d6b6cb7a2b8c00fcb535879edbd6b008a01,Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras,"Large-Scale Direct Sparse Visual Odometry with Stereo Cameras Stereo DSO: Rui Wang∗, Martin Schw¨orer∗, Daniel Cremers Technical University of Munich {wangr, schwoere," 5ce40105e002f9cb428a029e8dec6efe8fad380e,Co-design of architectures and algorithms for mobile robot localization and model-based detection of obstacles. (Co-conception d'architectures et d'algorithmes pour la localisation de robots mobiles et la détection d'obstacles basée sur des modèles),"Co-design of architectures and algorithms for mobile robot localization and model-based detection of obstacles Daniel Törtei To cite this version: Daniel Törtei. Co-design of architectures and algorithms for mobile robot localization and model-based detection of obstacles. Embedded Systems. Université Paul Sabatier - Toulouse III, 2016. English. . HAL Id: tel-01477662 https://tel.archives-ouvertes.fr/tel-01477662v2 Submitted on 16 Feb 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 5c562ed8d58522d28ac2d749de0bce8de07c1733,A Wavelet-Based Facial Ageing Synthesis Method,"ISSN 1000-9825, CODEN RUXUEW Journal of Software, Vol.18, No.2, February 2007, pp.469−476 DOI: 10.1360/jos180469 © 2007 by Journal of Software. All rights reserved. E-mail: http://www.jos.org.cn Tel/Fax: +86-10-62562563 一种基于小波的人脸衰老化合成方法 刘剑毅+, 郑南宁, 游屈波 (西安交通大学 人工智能与机器人研究所,陕西 西安 710049) A Wavelet-Based Facial Ageing Synthesis Method LIU Jian-Yi+, ZHENG Nan-Ning, YOU Qu-Bo (Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China) + Corresponding author: Phn: +86-29-82668802 ext 8002, E-mail: http://www.xjtu.edu.cn Liu JY, Zheng NN, You QB. A wavelet-based facial ageing synthesis method. Journal of Software, 2007,18(2): 69−476. http://www.jos.org.cn/1000-9825/18/469.htm" 5c879f9e2e79d6c6af8d4c821575e73876240a83,DeepFaceLIFT: Interpretable Personalized Models for Automatic Estimation of Self-Reported Pain,"Journal of Machine Learning Research 66 (2017) 1-16 Submitted 5/17; Published 08/17 DeepFaceLIFT: Interpretable Personalized Models for Automatic Estimation of Self-Reported Pain Dianbo Liu*2,3 Fengjiao Peng*1 Andrew Shea*3 Ognjen (Oggi) Rudovic1 Rosalind Picard1 Media Lab, MIT, Cambridge, MA, USA Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, MA, USA Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, USA" 7f4bc8883c3b9872408cc391bcd294017848d0cf,The Multimodal Focused Attribute Model : A Nonparametric Bayesian Approach to Simultaneous Object Classification and Attribute Discovery,"Computer Sciences Department The Multimodal Focused Attribute Model: A Nonparametric Bayesian Approach to Simultaneous Object Classification and Attribute Discovery Jake Rosin Charles R. Dyer Xiaojin Zhu Technical Report #1697 January 2012" 7f217ff1f3c21c84ed116d32e3b8d1509a306fbd,Direct Optimization through arg max for Discrete Variational Auto-Encoder,"Direct Optimization through arg max for Discrete Variational Auto-Encoder Guy Lorberbom (Technion), Andreea Gane (MIT), Tommi Jaakkola (MIT), Tamir Hazan (Technion)." 7f9cacb5fc126f87dbf53dd547a9fb9f58ded557,RoadNet-v2: A 10 ms Road Segmentation Using Spatial Sequence Layer,"RoadNet-v2: A 10 ms Road Segmentation Using Spatial Sequence Layer Yecheng Lyu and Xinming Huang Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester, MA 01609, USA" 7f44f8a5fd48b2d70cc2f344b4d1e7095f4f1fe5,Sparse Output Coding for Scalable Visual Recognition,"Int J Comput Vis (2016) 119:60–75 DOI 10.1007/s11263-015-0839-4 Sparse Output Coding for Scalable Visual Recognition Bin Zhao1 · Eric P. Xing1 Received: 15 May 2013 / Accepted: 16 June 2015 / Published online: 26 June 2015 © Springer Science+Business Media New York 2015" 7ff83f10e49e81ce6f66270e8f3f42dd2c6eb3ed,PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report,"PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report Andrey Ignatov, Radu Timofte, Thang Van Vu, Tung Minh Luu, Trung X Pham, Cao Van Nguyen, Yongwoo Kim, Jae-Seok Choi, Munchurl Kim, Jie Huang, Jiewen Ran, Chen Xing, Xingguang Zhou, Pengfei Zhu, Mingrui Geng, Yawei Li, Eirikur Agustsson, Shuhang Gu, Luc Van Gool, Etienne de Stoutz, Nikolay Kobyshev, Kehui Nie, Yan Zhao, Gen Li, Tong Tong, Qinquan Gao, Liu Hanwen, Pablo Navarrete Michelini, Zhu Dan, Hu Fengshuo, Zheng Hui, Xiumei Wang, Lirui Deng, Rang Meng, Jinghui Qin, Yukai Shi, Wushao Wen, Liang Lin, Ruicheng Feng, Shixiang Wu, Chao Dong, Yu Qiao, Subeesh Vasu, Nimisha Thekke Madam, Praveen Kandula, A. N. Rajagopalan, Jie Liu, Cheolkon Jung ∗" 7f04b65f2c6f96c7ce000f537fb691a93f61db52,Geometrical and Visual Feature Quantization for 3D Face Recognition, 7f6061c83dc36633911e4d726a497cdc1f31e58a,YouTube-8M: A Large-Scale Video Classification Benchmark,"YouTube-8M: A Large-Scale Video Classification Benchmark Sami Abu-El-Haija George Toderici Nisarg Kothari Joonseok Lee Paul Natsev Balakrishnan Varadarajan Sudheendra Vijayanarasimhan Google Research" 7fdcb6638a9e01986cd8fb4133b4448700087faf,Expression-Invariant Multispectral Face Recognition : You Can Smile Now !,"Expression-Invariant Multispectral Face Recognition: You Can Smile Now! Ioannis A. Kakadiarisa, George Passalisa, George Todericia, Yunliang Lua, Nikos Karampatziakisa, Najam Murtuzaa, Theoharis Theoharisa Computational Biomedicine Lab, Dept. of Computer Science, Univ. of Houston, TX, USA" 7fa41631cdef8f7fba7e1289dd4c5f3723b172ab,A robust and isotropic curved surface representation for 3D faces description,"A robust and isotropic curved surface representation for 3D faces description Majdi Jribi and Faouzi Ghorbel" 7fc5ab3743e6e9a2f4fe70152440e13a673e239b,Improved Face Recognition Rate Using HOG Features and SVM Classifier,"IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-ISSN: 2278-2834,p- ISSN: 2278-8735.Volume 11, Issue 4, Ver. I (Jul.-Aug .2016), PP 34-44 www.iosrjournals.org Improved Face Recognition Rate Using HOG Features and SVM Classifier Harihara Santosh Dadi, Gopala Krishna Mohan Pillutla" 7f3da52c13c70fd5b93c2ccebdd4a4527fa597fa,Deep Multi-task Learning to Recognise Subtle Facial Expressions of Mental States,"Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States Hu, G., Liu, L., Yuan, Y., Yu, Z., Hua, Y., Zhang, Z., ... Yang, Y. (2018). Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States. In European Conference on Computer Vision 2018: Proceedings (pp. 106-123). (Lecture Notes in Computer Science; Vol. 11216). https://doi.org/10.1007/978-3-030-01258-8_7 Published in: European Conference on Computer Vision 2018: Proceedings Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights © 2018 Springer Publishing. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to" 7f9c3ee2d3a3db9922203cbd19f03708067a42ab,A Comparative Analysis of Face Recognition Algorithms,"Gagan Kumar et al. International Journal of Recent Research Aspects ISSN: 2349-7688, Vol. 3, Issue , June 2016, pp. 201-204 A Comparative Analysis of Face Recognition Algorithms Gagan kumar1, Sumit Saurabh2 Assistant Professor, Modern Institute of engineering & technology Research scholar, Modern Institute of engineering & technology" 7f533bd8f32525e2934a66a5b57d9143d7a89ee1,Audio-Visual Identity Grounding for Enabling Cross Media Search,"Audio-Visual Identity Grounding for Enabling Cross Media Search Kevin Brady, MIT Lincoln Laboratory Paper ID 22" 7fd97bc23c85213b8b2e4d28264f04ce6dc84e74,Optimal Transformation Estimation with Semantic Cues,"Optimal Transformation Estimation with Semantic Cues Danda Pani Paudel Computer Vision Laboratory D-ITET, ETH Zurich Adlane Habed ICube Laboratory CNRS, University of Strasbourg Luc Van Gool Computer Vision Laboratory D-ITET, ETH Zurich" 7f3a73babe733520112c0199ff8d26ddfc7038a0,Robust Face Identification with Small Sample Sizes using Bag of Words and Histogram of Oriented Gradients, 7f6cd03e3b7b63fca7170e317b3bb072ec9889e0,A Face Recognition Signature Combining Patch-based Features with Soft Facial Attributes,"A Face Recognition Signature Combining Patch-based Features with Soft Facial Attributes L. Zhang, P. Dou, I.A. Kakadiaris Computational Biomedicine Lab, 4849 Calhoun Rd, Rm 373, Houston, TX 77204" 7ff42ee09c9b1a508080837a3dc2ea780a1a839b,Data Fusion for Real-time Multimodal Emotion Recognition through Webcams and Microphones in E-Learning,"Data Fusion for Real-time Multimodal Emotion Recognition through Webcams nd Microphones in E-Learning Kiavash Bahreini*, Rob Nadolski*, Wim Westera* *Welten Institute, Research Centre for Learning, Teaching and Technology, Faculty of Psychology and Educational Sciences, Open University of the Netherlands, Valkenburgerweg 77, 6419 AT Heerlen, The Netherlands {kiavash.bahreini, rob.nadolski," 7fa62c091a14830ae256dc00b512f7d4b4cf5b94,Stabilizing GAN Training with Multiple Random Projections,"Under review as a conference paper at ICLR 2018 Stabilizing GAN Training with Multiple Random Projections Anonymous authors Paper under double-blind review" 7fbff9fa2ba7a7ff57a433e8bb19cfd99d52132d,A probabilistic framework for car detection in images using context and scale,"RiverCentre, Saint Paul, Minnesota, USA May 14-18, 2012 978-1-4673-1405-3/12/$31.00 ©2012 IEEE" 7f6a527a3dc2e526aa59a57cadb20ff727124973,A comparison of adaptive matchers for screening of faces in video surveillance,"012 IEEE Symposium on Computational Intelligence for Security and Defence Applications (CISDA 2012) Ottawa, Ontario, Canada 1 – 13 July 2012 IEEE Catalog Number: ISBN: CFP12SDA-PRT 978-1-4673-1416-9" 7ff636c82898a35d3239573f8e3a29da89c73ed4,Automatic Detection of the Uterus and Fallopian Tube Junctions in Laparoscopic Images,"Automatic Detection of the Uterus and Fallopian Tube Junctions in Laparoscopic Images Kristina Prokopetc, Toby Collins, and Adrien Bartoli Image Science for Interventional Techniques (ISIT), UMR 6284 CNRS, Universit´e d(cid:48)Auvergne, France" 7f3c6bf191a8633d10fad32e23fa06a3c925ffee,The benefits of simply observing: mindful attention modulates the link between motivation and behavior.,"015, Vol. 108, No. 1, 148 –170 0022-3514/15/$12.00 © 2014 American Psychological Association http://dx.doi.org/10.1037/a0038032 The Benefits of Simply Observing: Mindful Attention Modulates the Link Between Motivation and Behavior Esther K. Papies Utrecht University Mike Keesman Utrecht University Tila M. Pronk Tilburg University Lawrence W. Barsalou Emory University Mindful attention, a central component of mindfulness meditation, can be conceived as becoming aware of one’s thoughts and experiences and being able to observe them as transient mental events. Here, we present a series of studies demonstrating the effects of applying this metacognitive perspective to one’s spontaneous reward responses when encountering attractive stimuli. Taking a grounded cognition perspective, we argue that reward simulations in response to attractive stimuli contribute to appetitive ehavior and that motivational states and traits enhance these simulations. Directing mindful attention at" 7f97a36a5a634c30de5a8e8b2d1c812ca9f971ae,Incremental Classifier Learning with Generative Adversarial Networks,"Incremental Classifier Learning with Generative Adversarial Networks Yue Wu1 Yinpeng Chen2 Lijuan Wang2 Yuancheng Ye3 Zicheng Liu2 Yandong Guo2 Zhengyou Zhang2 Yun Fu1 Northeastern University 2Microsoft Research 3City University of New York" 7f7c3a99923549601c81cd5e9659ca01e8a42f47,Zero-Shot Learning of Language Models for Describing Human Actions Based on Semantic Compositionality of Actions,"PACLIC 28 Zero-Shot Learning of Language Models for Describing Human Actions Based on Semantic Compositionality of Actions Hideki ASOH National Institute of Graduate School of Humanities and Sciences, Ichiro KOBAYASHI Ochanomizu University Bunkyo-ku, Tokyo 112-8610 Japan Advanced Industrial Science and Technology Tsukuba, Ibaraki 305-8568 Japan" 7fb143927b616726f065a55b4455b822b4cc8d86,Structured Learning for Cell Tracking,"Structured Learning for Cell Tracking Xinghua Lou, Fred A. Hamprecht Heidelberg Collaboratory for Image Processing (HCI) Interdisciplinary Center for Scientific Computing (IWR) University of Heidelberg, Heidelberg 69115, Germany" 7f92ace1683979018b87f2e472857e152503cc24,Regressor Based Estimation of the Eye Pupil Center,"Regressor Based Estimation of the Eye Pupil Center Necmeddin Said Karakoc, Samil Karahan, Yusuf Sinan Akgul Gebze Technical University, Gebze, Kocaeli 41400, Turkey, GTU Vision Lab: http://vision.gyte.edu.tr" 7f36dd9ead29649ed389306790faf3b390dc0aa2,MOVEMENT DIFFERENCES BETWEEN DELIBERATE AND SPONTANEOUS FACIAL EXPRESSIONS: ZYGOMATICUS MAJOR ACTION IN SMILING.,"MOVEMENT DIFFERENCES BETWEEN DELIBERATE AND SPONTANEOUS FACIAL EXPRESSIONS: ZYGOMATICUS MAJOR ACTION IN SMILING Karen L. Schmidt, Zara Ambadar, Jeffrey F. Cohn, and L. Ian Reed" 7fc70f6dbbbc9221552c8547cd10ffc13d11b276,Respectful cameras: detecting visual markers in real-time to address privacy concerns,"Respectful Cameras: Detecting Visual Markers in Real-Time to Address Privacy Concerns Jeremy Schiff, Marci Meingast, Deirdre K. Mulligan, Shankar Sastry, Ken Goldberg" 3347d3e9f8a2da66e1c00f6a1e56bb37d27145ae,devant le jury composé de:,"Spécialité: Informatique et Télécommunications Ecole doctorale: Informatique, Télécommunications et Electronique de Paris Présentée par Raluca-Diana ŞAMBRA-PETRE Pour obtenir le grade de DOCTEUR DE TELECOM SUDPARIS MODELISATION ET INFERENCE 2D/3D DE CONNAISSANCES POUR L'ACCES INTELLIGENT AUX CONTENUS VISUELS ENRICHIS Soutenue le 18 Juin 2013 à Paris devant le jury composé de : Président de jury: Madame le Maître de Conférences, HDR Catherine ACHARD Rapporteur: Monsieur le Professeur Marc ANTONINI Rapporteur: Monsieur le Professeur Constantin VERTAN Examinateur: Monsieur le Professeur Miroslaw BOBER Examinateur: Monsieur le Docteur Olivier MARTINOT Directeur de thèse: Monsieur le Professeur Titus ZAHARIA Thèse n°: 2013TELE0012 THESE DE DOCTORAT CONJOINT TELECOM SUDPARIS et L'UNIVERSITE PIERRE ET MARIE CURIE" 33919313bb3cf09b00f9fa2253b30af33a52bc51,Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs,"Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs Anton Osokin∗,1 Jean-Baptiste Alayrac∗,1 Isabella Lukasewitz1 Puneet K. Dokania2 Simon Lacoste-Julien1 INRIA – ´Ecole Normale Sup´erieure, Paris, France Both authors contributed equally. INRIA – CentraleSup´elec, Chˆatenay-Malabry, France" 338d0087fbd3bb768e637b4538e6581220387fff,Distributed Averages of Gradients (DAG): A Fast Alternative for Histogram of Oriented Gradients,"Distributed Averages of Gradients (DAG): A Fast Alternative for Histogram of Oriented Gradients M. Hossein Mirabdollah, Mahmoud A. Mohamed, and B¨arbel Mertsching GET Lab, University of Paderborn, 33098 Paderborn, Germany {mirabdollah, mahmoud, http://getwww.upb.de" 3387805b752dadfa34cb8eb63d9dc86aff49934a,"Exploration of Contextual Relationships for Robust Video Analysis: Applications in Camera Networks, Bio-image Analysis and Activity Forecasting","UNIVERSITY OF CALIFORNIA RIVERSIDE Exploration of Contextual Relationships for Robust Video Analysis: Applications in Camera Networks, Bio-image Analysis and Activity Forecasting A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Electrical Engineering Anirban Chakraborty August 2014 Dissertation Committee: Dr. Amit K. Roy-Chowdhury, Chairperson Dr. Ertem Tuncel Dr. Stefano Lonardi" 33d045b39bc4645ff2a8bffd83a49697631ff968,Learning Discrete Representations via Information Maximizing Self Augmented Training,"Learning Discrete Representations via Information Maximizing Self Augmented Training Weihua Hu 1 Takeru Miyato 2 3 Seiya Tokui 2 1 Eiichi Matsumoto 2 1 Masashi Sugiyama 4 1" 331b2520b0eda715270134ac2ee2a3cbb329aaa1,3D non-rigid reconstruction with prior shape constraints,"D Non-Rigid Reconstruction with Prior Shape Constraints Lili Tao A thesis submitted in partial fulfilment for the requirements for the degree of Doctor of Philosophy the University of Central Lancashire May 2014" 335486cb9bb326e2b33fb03a74d0f9d671490ae7,Real-time pedestrian detection with deformable part models,"Real-time Pedestrian Detection with Deformable Part Models Hyunggi Cho, Paul E. Rybski, Aharon Bar-Hillel and Wende Zhang" 3389fa2f292b72320f4554261eae34d57e2db7b6,Morphable Reflectance Fields for enhancing face recognition,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Morphable Reflectance Fields for Enhancing Face Recognition Ritwik Kumar, Michael Jones, Tim Marks TR2010-039 July 2010" 333be4858994e6d9364341aeb520f7800a0f6a07,Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks,"Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks Konstantinos Bousmalis Google Brain San Francisco, CA Nathan Silberman Google Research New York, NY David Dohan Google Brain Mountain View, CA Dumitru Erhan Google Brain San Francisco, CA Dilip Krishnan Google Research Cambridge, MA" 3393459600368be2c4c9878a3f65a57dcc0c2cfa,Eigen-PEP for Video Face Recognition,"Eigen-PEP for Video Face Recognition Haoxiang Li†, Gang Hua†, Xiaohui Shen‡, Zhe Lin‡, Jonathan Brandt‡ Stevens Institute of Technology ‡Adobe Systems Inc." 33e5d1c93e4195a1bfd303a94f0fc3f1c5e233bd,3D Face Recognition Under Expression Variations using Similarity Metrics Fusion,"(cid:176)2007 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for ad- vertising or promotional purposes or for creating new collec- tive works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE." 33ef644ef5085237b4f529251d6c895d32d6052f,TasselNet: counting maize tassels in the wild via local counts regression network,"Lu et al. RESEARCH ARTICLES TasselNet: Counting maize tassels in the wild via local counts regression network Hao Lu1, Zhiguo Cao1*, Yang Xiao1, Bohan Zhuang2 and Chunhua Shen2 Part of this work was done when the first author was visiting The University of Adelaide, Australia." 3355aff37b5e4ba40fc689119fb48d403be288be,Deep Private-Feature Extraction,"Deep Private-Feature Extraction Seyed Ali Osia, Ali Taheri, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Hamid R. Rabiee" 339937141ffb547af8e746718fbf2365cc1570c8,Facial Emotion Recognition in Real Time,"Facial Emotion Recognition in Real Time Dan Duncan Gautam Shine Chris English" 33f843eaab92cc04ba6dec0ff8c72026e37cfdb2,Genetic Programming for Multibiometrics,"Genetic Programming for Multibiometrics Romain Giot∗, Christophe Rosenberger GREYC Laboratory ENSICAEN - University of Caen - CNRS 6 Boulevard Mar´echal Juin 14000 Caen Cedex - France" 33d30ab798e518eedbebe7e7569737362fdcefdb,Effect of Purposeful Feature Extraction inHigh-dimensional Kinship Verification Problem,"July 2016, Volume 3, Number 3 (pp. 183–191) http://www.jcomsec.org Journal of Computing and Security Effect of Purposeful Feature Extraction in High-dimensional Kinship Verification Problem Pendar Alirezazadeh a, Abdolhossein Fathi a,∗, Fardin Abdali-Mohammadi a Department of Computer Engineering and Information Technology, Razi University, Kermanshah, Iran. A R T I C L E I N F O. A B S T R A C T Article history: Received: 31 July 2017 Revised: 20 November 2017 Accepted: 07 January 2018 Published Online: 10 February 2018 Keywords: Kinship Verification, Purposeful Feature Extraction, Redundancy, Feature Selection. Recently, researchers have shown an increased interest in kinship verification via facial images in the field of computer vision. The matter of fact is that" 33548dec33abfc66bba40ac3f9651c0605d6b537,CMML : a New Metric Learning Approach for Cross Modal Matching,"CMML: a New Metric Learning Approach for Cross Modal Matching Alexis Mignon and Fr´ed´eric Jurie GREYC, CNRS UMR 6072, Universit´e de Caen Basse-Normandie, France first name.last" 33ea400ca2105b9a3cd0e3c7c147e06c2d3c6d79,Vision based Decision-Support and Safety Systems for Robotic Surgery,"Vision based Decision-Support and Safety Systems for Robotic Surgery Suren Kumar PhD Candidate Madusudanan Sathia Narayanan* PhD Candidate Sukumar Misra Surgical Intern Sudha Garimella Assistant Professor Pankaj Singhal Director of Robotic Surgery Jason J. Corso Assistant Professor" 33c485b59249af2d763d6951cd11e4080f3bbb3d,Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation,"Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation Bugra Tekin Pablo M´arquez-Neila Mathieu Salzmann Pascal Fua EPFL, Switzerland" 336fe31c25c9128f43f2dfe454041e7c608557d1,H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis.,"H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis Tianjia Shao, Yin Yang, Yanlin Weng, Qiming Hou, Kun Zhou" 3333b35ddb698be76dd27bffad131c1daa694bf2,Comparing Robustness of Two-Dimensional PCA and Eigenfaces for Face Recognition,"Comparing Robustness of Two-Dimensional PCA and Eigenfaces for Face Recognition Muriel Visani, Christophe Garcia, and Christophe Laurent France Telecom R&D - DIH/HDM , rue du Clos Courtel 5512 Cesson-S´evign´e Cedex - France" 33695e0779e67c7722449e9a3e2e55fde64cfd99,Riemannian coding and dictionary learning: Kernels to the rescue,"Riemannian Coding and Dictionary Learning: Kernels to the Rescue Mehrtash Harandi, Mathieu Salzmann Australian National University & NICTA While sparse coding on non-flat Riemannian manifolds has recently become increasingly popular, existing solutions either are dedicated to specific man- ifolds, or rely on optimization problems that are difficult to solve, especially when it comes to dictionary learning. In this paper, we propose to make use of kernels to perform coding and dictionary learning on Riemannian man- ifolds. To this end, we introduce a general Riemannian coding framework with its kernel-based counterpart. This lets us (i) generalize beyond the spe- ial case of sparse coding; (ii) introduce efficient solutions to two coding schemes; (iii) learn the kernel parameters; (iv) perform unsupervised and supervised dictionary learning in a much simpler manner than previous Rie- mannian coding approaches. i=1, di ∈ M, be a dictionary on a Rie- mannian manifold M, and x ∈ M be a query point on the manifold. We (cid:17) define a general Riemannian coding formulation as More specifically, let D = {di}N (cid:93)N" 334d6c71b6bce8dfbd376c4203004bd4464c2099,Biconvex Relaxation for Semidefinite Programming in Computer Vision,"BICONVEX RELAXATION FOR SEMIDEFINITE PROGRAMMING IN COMPUTER VISION SOHIL SHAH*, ABHAY KUMAR*, DAVID JACOBS, CHRISTOPH STUDER, AND TOM GOLDSTEIN" 33236cd0b9454ab88ec9deddfb8ce8e492056770,Salient social cues are prioritized in autism spectrum disorders despite overall decrease in social attention.,"J Autism Dev Disord DOI 10.1007/s10803-012-1710-x O R I G I N A L P A P E R Salient Social Cues are Prioritized in Autism Spectrum Disorders Despite Overall Decrease in Social Attention Coralie Chevallier • Pascal Huguet • Francesca Happe´ • Nathalie George • Laurence Conty Ó Springer Science+Business Media New York 2012" 332339c32d41cc8176d360082b4d9faa90dadffa,"UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory","UberNet : Training a ‘Universal’ Convolutional Neural Network for Low-, Mid-, nd High-Level Vision using Diverse Datasets and Limited Memory Iasonas Kokkinos CentraleSup´elec - INRIA" 330a34b8dfb3f6adaf6401c3ececf9f4127505a0,Feature selection for pose invariant lip biometrics,"INTERSPEECH 2010 Feature Selection for Pose Invariant Lip Biometrics Adrian Pass, Jianguo Zhang, Darryl Stewart School of Electronics, Electrical Engineering and Computer Science Queens University Belfast Belfast BT7 1NN, UK {apass01, jianguo.zhang," 330dda431e0343a96f9d630a0b4ee526bd93ad11,Domain Adaptation for Visual Applications: A Comprehensive Survey,"Domain Adaptation for Visual Applications: A Comprehensive Survey Gabriela Csurka" 3369692338841f14ce032fc5d0b5b4fe7cc79f1a,Visualising mental representations : A primer on noise-based reverse correlation in social psychology,"European Review of Social Psychology ISSN: 1046-3283 (Print) 1479-277X (Online) Journal homepage: http://www.tandfonline.com/loi/pers20 Visualising mental representations: A primer on noise-based reverse correlation in social psychology L. Brinkman, A. Todorov & R. Dotsch To cite this article: L. Brinkman, A. Todorov & R. Dotsch (2017) Visualising mental representations: A primer on noise-based reverse correlation in social psychology, European Review of Social Psychology, 28:1, 333-361, DOI: 10.1080/10463283.2017.1381469 To link to this article: http://dx.doi.org/10.1080/10463283.2017.1381469 © 2017 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. Published online: 16 Oct 2017. Submit your article to this journal View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pers20 Download by: [Princeton University]" 33891ca0f8fab0eab503f4b4bcee009a1cf3b880,A video database of human faces under near Infra-Red illumination for human computer interaction applications,"A Video Database of Human Faces under Near Infra-Red Illumination for Human Computer Interaction Aplications S L Happy, Anirban Dasgupta, Anjith George, and Aurobinda Routray Department of Electrical Engineering Indian Institute of Technology Kharagpur" 33e7bc26047de3c1b607f04a644c2c03920201fd,Learning to Navigate Autonomously in Outdoor Environments : MAVNet,"Learning to Navigate Autonomously in Outdoor Environments : MAVNet Saumya Kumaar2, Arpit Sangotra3, Sudakshin Kumar3, Mayank Gupta3, Navaneethkrishnan B2 and S N Omkar1" 330bcf952a5a20aac0e334aad1de4cd6ba6ed6eb,Pedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison,"Article Pedestrian Detection at Day/Night Time with Visible nd FIR Cameras: A Comparison Alejandro González 1,2,*, Zhijie Fang 1,2, Yainuvis Socarras 1,2, Joan Serrat 1,2, David Vázquez 1,2, Jiaolong Xu 1,2 and Antonio M. López 1,2 Autonomous University of Barcelona, Cerdanyola, Barcelona 08193, Spain; (Z.F.); (Y.S.); (J.S.); (D.V.); (J.X.); (A.M.L.) Computer Vision Center, Cerdanyola, Barcelona 08193, Spain * Correspondence: Tel.: +34-622-605-455 Academic Editor: Vittorio M. N. Passaro Received: 17 March 2016; Accepted: 30 May 2016; Published: 4 June 2016" 330126c9dd71b3b0319d6429737186f1f20057a7,Deep Ordinal Regression Based on Data Relationship for Small Datasets,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 33e20449aa40488c6d4b430a48edf5c4b43afdab,The Faces of Engagement: Automatic Recognition of Student Engagementfrom Facial Expressions,"TRANSACTIONS ON AFFECTIVE COMPUTING The Faces of Engagement: Automatic Recognition of Student Engagement from Facial Expressions Jacob Whitehill, Zewelanji Serpell, Yi-Ching Lin, Aysha Foster, and Javier R. Movellan" 33691b7e8c980ea2dea5b5d3d7bee661e9623715,Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM,"Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM Ra´ul Mur-Artal and Juan D. Tard´os Instituto de Investigaci´on en Ingenier´ıa de Arag´on (I3A), Universidad de Zaragoza, Spain {raulmur," 3323a905a3960a663a9884540e8c3586cf362ba9,Face Hallucination Using Sparse Representation Algorithm,"International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) Volume 4 Issue 9, September 2015 Face Hallucination Using Sparse Representation Algorithm Sudhir Kumar Vikram Mutneja" 3361ddc93a6d9f451c1b94cc488c52fd0bdf5c83,Deep Generative Models of Urban Mobility,"Deep Generative Models of Urban Mobility Ziheng Lin∗ Mogeng Yin† Civil Systems, CEE, UC Berkeley Transportation, CEE, UC Berkeley Civil Systems, CEE, UC Berkeley Madeleine Sheehan Transportation, CEE, UC Berkeley Jean-Francois Paiement AT&T Research Sidney Feygin‡ Alexei Pozdnoukhov CEE, UC Berkeley" 334355b4c82ad477a2f44ba61dd04c68048e78d3,Applications of kernel machines to structured data,"Applications of Kernel Machines to Structured Data Vorgelegt von Diplom-Physiker Jan Eichhorn us Weimar Von der Fakult¨at IV - Elektrotechnik und Informatik der Technischen Universit¨at Berlin zur Erlangung des akademischen Grades Doktor der Naturwissenschaften (Dr. rer. nat.) genehmigte Dissertation Promotionsausschuß: Vorsitzender: Prof. Dr. H. Ehrig Berichter: Berichter: Berichter: Prof. Dr. K.-R. M¨uller Prof. Dr. K. Obermayer Prof. Dr. B. Sch¨olkopf Tag der wissenschaftlichen Aussprache: 27.11.2006 Berlin 2007" 33a9076d5d48208960feebff9d5efdaa2203f872,Face De-Identification,"Face De-identification Ralph Gross, Latanya Sweeney, Jeffrey Cohn, Fernando de la Torre nd Simon Baker" 33ae696546eed070717192d393f75a1583cd8e2c,Subspace selection to suppress confounding source domain information in AAM transfer learning, 8d9067da4ba5c57643ee7a84cd5c5d5674384937,Sorting out Lipschitz function approximation,"SORTING OUT LIPSCHITZ FUNCTION APPROXIMATION Cem Anil ∗ James Lucas∗ Roger Grosse University of Toronto; Vector Institute {cemanil, jlucas," 8d40150c7ec59daba7d1a34eba291ff2eac6388c,Overcoming Dataset Bias : An Unsupervised Domain Adaptation Approach,"Overcoming Dataset Bias: An Unsupervised Domain Adaptation Approach Boqing Gong Dept. of Computer Science U. of Southern California Los Angeles, CA 90089 Fei Sha Dept. of Computer Science U. of Southern California Los Angeles, CA 90089 Kristen Grauman Dept. of Computer Science U. of Texas at Austin Austin, TX 78701" 8d384e8c45a429f5c5f6628e8ba0d73c60a51a89,Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection,"Temporal Dynamic Graph LSTM for Action-driven Video Object Detection Yuan Yuan1 Xiaodan Liang2 Xiaolong Wang2 Dit-Yan Yeung1 Abhinav Gupta2 The Hong Kong University of Science and Technology 2 Carneige Mellon University" 8d44861cfcb5159e0a1afb9d50f3d2c6083f605a,3 D SUPER-RESOLUTION APPROACH FOR SPARSE LASER SCANNER DATA,"D SUPER-RESOLUTION APPROACH FOR SPARSE LASER SCANNER DATA S. Hosseinyalamdarya∗, A. Yilmaza Photogrammetric Computer Vision (PCV) Lab 070 Neil avenue, Columbus, OH 43212, Commission VI, WG VI/4 KEY WORDS: 3D Super-resolution, Geometric Surface Reconstruction, Diffusion Equations, isotropic and anisotropic" 8de2dbe2b03be8a99628ffa000ac78f8b66a1028,Action Recognition in Videos,"´Ecole Nationale Sup´erieure dInformatique et de Math´ematiques Appliqu´ees de Grenoble INP Grenoble – ENSIMAG UFR Informatique et Math´ematiques Appliqu´ees de Grenoble Rapport de stage de Master 2 et de projet de fin d’´etudes Effectu´e au sein de l’´equipe LEAR, I.N.R.I.A., Grenoble Action Recognition in Videos Gaidon Adrien e ann´ee ENSIMAG – Option I.I.I. M2R Informatique – sp´ecialit´e I.A. 04 f´evrier 2008 – 04 juillet 2008 LEAR, I.N.R.I.A., Grenoble 655 avenue de l’Europe 8 334 Montbonnot France Responsable de stage Mme. Cordelia Schmid Tuteur ´ecole M. Augustin Lux M. Roger Mohr" 8de9380536a5f7f29cfe59578041efe7c8ea20bd,Facial image-based gender classification using Local Circular Patterns,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-1-6 ©2012 IAPR" 8d3114a3236ec9adabcf0c40613a23f00c272a1c,From 3D Point Clouds to Pose-Normalised Depth Maps,"Int J Comput Vis (2010) 89: 152–176 DOI 10.1007/s11263-009-0297-y From 3D Point Clouds to Pose-Normalised Depth Maps Nick Pears · Tom Heseltine · Marcelo Romero Received: 30 September 2008 / Accepted: 14 September 2009 / Published online: 25 September 2009 © Springer Science+Business Media, LLC 2009" 8d6d0fdf4811bc9572326d12a7edbbba59d2a4cc,SchiNet: Automatic Estimation of Symptoms of Schizophrenia from Facial Behaviour Analysis,"SchiNet: Automatic Estimation of Symptoms of Schizophrenia from Facial Behaviour Analysis Mina Bishay, Petar Palasek, Stefan Priebe, and Ioannis Patras" 8d3fbdb9783716c1832a0b7ab1da6390c2869c14,Discriminant Subspace Analysis for Uncertain Situation in Facial Recognition,"Discriminant Subspace Analysis for Uncertain Situation in Facial Recognition Pohsiang Tsai, Tich Phuoc Tran, Tom Hintz and Tony Jan School of Computing and Communications – University of Technology, Sydney Australia . Introduction Facial analysis and recognition have received substential attention from researchers in iometrics, pattern recognition, and computer vision communities. They have a large number of applications, such as security, communication, and entertainment. Although a great deal of efforts has been devoted to automated face recognition systems, it still remains challenging uncertainty problem. This is because human facial appearance has potentially of very large intra-subject variations of head pose, illumination, facial expression, occlusion due to other objects or accessories, facial hair and aging. These misleading variations may ause classifiers to degrade generalization performance. It is important for face recognition systems to employ an effective feature extraction scheme to enhance separability between pattern classes which should maintain and enhance features of the input data that make distinct pattern classes separable (Jan, 2004). In general, there exist a number of different feature extraction methods. The most common feature extraction methods are subspace analysis methods such as principle component analysis (PCA) (Kirby & Sirovich, 1990) (Jolliffe, 1986) (Turk & Pentland, 1991b), kernel principle" 8dc198bcd54ab73936711165a52c6ecc842edc90,Playing for Depth,"Playing for Depth Mohammad M. Haji-Esmaeili Gholamali Montazer Figure 1: Images and Depths extracted from the game Grand Theft Auto V" 8d09c8c6b636ef70633a3f1bb8ff6b4d4136b5cf,3D Twins Expression Challenge,"D Twins Expression Challenge Vipin Vijayan, Kevin Bowyer, Patrick Flynn Department of Computer Science and Engineering, University of Notre Dame. 84 Fitzpatrick Hall, Notre Dame, IN 46556, USA. {vvijayan, kwb, . Introduction We describe the 3D Twins Expression Challenge (“3D TEC”) problem in the area of 3D face recognition. The supporting dataset contains 3D scans of pairs of identical twins taken with two different facial expressions, neutral nd smiling. The dataset is smaller than the FRGC v2 [1] dataset by approximately a factor of ten, but is still more hallenging than the FRGC v2 dataset due to it containing twins with different expressions. This challenge problem will help to push the frontiers of 3D face recognition. Three dimensional face recognition is an active research topic in biometrics [2, 3]. While 2D pictures can be cap- tured quickly, non-intrusively, and easily by widely avail-" 8db43d306a70e23e2a0e6eb2fda60f14b73f65d0,Multi-Commodity Network Flow for Tracking Multiple People,"Multi-Commodity Network Flow for Tracking Multiple People Horesh Ben Shitrit, J´erˆome Berclaz, Franc¸ois Fleuret, and Pascal Fua, Fellow, IEEE" 8d2459ada191d496eeee70f1e817d0ba92075160,The evaluation of different approaches towards using Kinect sensor as a Laser scanner,"The evaluation of different approaches towards using Kinect sensor as a Laser scanner Bachelor of Science Thesis Software Engineering and Management KHASHAYAR ABDOLI ZLATAN HABUL University of Gothenburg Chalmers University of Technology Department of Computer Science and Engineering Göteborg, Sweden, June 2014" 8d5945ef2361511a17719c9efe9e2d005247029e,Merced Proceedings of the Annual Meeting of the Cognitive Science Society Title Look Ma ! No Network ! : PCA of Gabor Filters Models the Development of Face Discrimination Permalink,"PCA of Gabor Filters Models the Development of Face Discrimination Look Ma! No Network!: Lingyun Zhang and Garrison W. Cottrell UCSD Computer Science and Engineering 9500 Gilman Dr., La Jolla, CA 92093-0114 USA" 8de06a584955f04f399c10f09f2eed77722f6b1c,Facial Landmarks Localization Estimation by Cascaded Boosted Regression,"Author manuscript, published in ""International Conference on Computer Vision Theory and Applications (VISAPP 2013) (2013)""" 8d9f793bbf6a36285308fdaf2886c9c377f40413,Optimizing process for tracking people in video-camera network. (Optimisation du suivi de personnes dans un réseau de caméras),"Universit´e Nice Sophia Antipolis – UFR Sciences ´Ecole Doctorale STIC TH`ESE Pr´esent´ee pour obtenir le titre de : Docteur en Sciences de l’Universit´e Nice Sophia Antipolis Sp´ecialit´e : INFORMATIQUE Julien BADIE ´Equipe d’accueil : STARS – INRIA Sophia Antipolis OPTIMIZING PROCESS FOR TRACKING PEOPLE IN VIDEO-CAMERA NETWORK Th`ese dirig´ee par Franc¸ois BR´EMOND Soutenance `a l’INRIA le 17 novembre 2015, `a 10h00 devant le jury compos´e de : Pr´esident : Fr´ed´eric PRECIOSO Directeur : Franc¸ois BR´EMOND Professeur, Universit´e Nice Sophia Antipolis DR2, INRIA Sophia Antipolis - M´editerran´ee Rapporteurs : Xavier ROCA MARVA Directeur du d´epartement des sciences Laure" 8d4f0517eae232913bf27f516101a75da3249d15,Event-based Dynamic Face Detection and Tracking Based on Activity.,"ARXIV SUBMISSION, MARCH 2018 Event-based Dynamic Face Detection and Tracking Based on Activity Gregor Lenz, Sio-Hoi Ieng and Ryad Benosman" 8d97e0102b5d89c62e5c6697eeaaefc82b36c809,Bottom-up attention orienting in young children with autism.,"J Autism Dev Disord (2014) 44:664–673 DOI 10.1007/s10803-013-1925-5 O R I G I N A L P A P E R Bottom-Up Attention Orienting in Young Children with Autism Dima Amso • Sara Haas • Elena Tenenbaum • Julie Markant • Stephen J. Sheinkopf Published online: 1 September 2013 Ó Springer Science+Business Media New York 2013" 8dffbb6d75877d7d9b4dcde7665888b5675deee1,Emotion Recognition with Deep-Belief Networks,"Emotion Recognition with Deep-Belief Networks Tom McLaughlin, Mai Le, Naran Bayanbat Introduction For our CS229 project, we studied the problem of reliable computerized emotion recognition in images of human faces. First, we performed a preliminary exploration using SVM classifiers, and then developed an pproach based on Deep Belief Nets. Deep Belief Nets, or DBNs, are probabilistic generative models composed of multiple layers of stochastic latent variables, where each “building block” layer is a Restricted Boltzmann Machine (RBM). DBNs have a greedy layer-wise unsupervised learning algorithm as well as a discriminative fine-tuning procedure for optimizing performance on classification tasks. [1]. We trained our classifier on three databases: the Cohn-Kanade Extended Database (CK+) [2], the Japanese Female Facial Expression Database (JAFFE) [3], and the" 8d8afef13a8f6195d3b874231e5e767cf62f3c50,Deep Ranking for Person Re-Identification via Joint Representation Learning,"Deep Ranking for Person Re-identification via Joint Representation Learning Shi-Zhe Chen, Chun-Chao Guo, Student Member, IEEE, and Jian-Huang Lai, Senior Member, IEEE" 8d1adf0ac74e901a94f05eca2f684528129a630a,Facial Expression Recognition Using Facial Movement Features,"Facial Expression Recognition Using Facial Movement Features" 8df3bef321cd1b259cf6fb1ef264a2e885610044,Interactively Learning Visually Grounded Word Meanings from a Human Tutor,"Proceedings of the 5th Workshop on Vision and Language, pages 48–53, Berlin, Germany, August 12 2016. c(cid:13)2016 Association for Computational Linguistics" 8d7a55d184659ac97d02061a660ae4e30604185b,Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation,"Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation Xinge Zhu1, Hui Zhou2, Ceyuan Yang1, Jianping Shi2, Dahua Lin1 CUHK-SenseTime Joint Lab, CUHK SenseTime Research" 8db9f32b0de29cfb7fd8e3d225be47b801cc9848,Vision-based deep execution monitoring,"Vision-based deep execution monitoring Francesco Puja, Simone Grazioso, Antonio Tammaro, Valsmis Ntouskos, Marta Sanzari, Fiora Pirri" 4ab87f509fd5c6d4b8c28d1ee6acbb59cd6ce4d8,"MetaStyle: Three-Way Trade-Off Among Speed, Flexibility and Quality in Neural Style Transfer","MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer Chi Zhang and Yixin Zhu and Song-Chun Zhu International Center for AI and Robot Autonomy (CARA)" 4a303369828d9334022a0f5e8ad2b1a715d1c0c9,Deep Metric Learning by Online Soft Mining and Class-Aware Attention,"Deep Metric Learning by Online Soft Mining and Class-Aware Attention Xinshao Wang1,2, Yang Hua1,2, Elyor Kodirov2, Guosheng Hu1,2, Neil M. Robertson1,2 School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, UK {xwang39, y.hua, {elyor, Anyvision Research Team, UK" 4aeb87c11fb3a8ad603311c4650040fd3c088832,Self-paced Mixture of Regressions,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) SamplesSelected SamplesOutliersMoRSPMoR (ours)6361242024Figure1:Inter-componentimbalanceandintra-componentoutliersinMixtureofRegression(MoR)approaches.StandardMoRcannotlearnaccurateregressors(denotedbythedashedlines).Byintroduc-inganovelself-pacedscheme,ourSPMoRapproach(denotedbythesolidlines)selectsbalancedandconfidenttrainingsamplesfromeachcomponent,whilepreventlearningfromtheoutliersthroughoutthetrainingprocedure.theywillbeinevitablybiasedbydatadistribution:lowre-gressionerrorindenselysampledspacewhilehigherrorineverywhereelse.Foraddressingtheissuesofthedatadiscontinuityandheterogeneity,thedivide-and-conquerapproacheswerepro-posedlately.Thecoreideaistolearntocombinemultiplelocalregressors.Forinstance,thehierarchical-based[Hanetal.,2015]andtree-basedregression[HaraandChellappa,2014]makehardpartitionsrecursively,andthesubsetsofsam-plesmaynotbehomogeneousforlearninglocalregressors.WhileMixtureofRegressions(MoR)[Jacobsetal.,1991;JordanandXu,1995]distributesregressionerroramonglocalregressorsbymaximizinglikelihoodinthejointinput-outputspace.Theseapproachesreduceoverallerrorbyfittingre-gressionlocallyandreliefsthebiasbydiscontinuousdatadistribution.Unfortunately,theaforementionedapproachesstillcannotachievesatisfactoryperformancewhenapplyinginsomereal-worldapplications.Themainreasonisthattheseapproachestendtobesensitivetotheintra-componentoutliers(i.e.,thenoisytrainingdataresidingincertaincomponents)andtheinter-componentimbalance(i.e.,thedifferentamountsoftrain-" 4a869781d074f6be7a5001c59e41b25145bdd830,DeltaPhish: Detecting Phishing Webpages in Compromised Websites,"DeltaPhish: Detecting Phishing Webpages in Compromised Websites∗ Igino Corona1,2, Battista Biggio1,2, Matteo Contini2, Luca Piras1,2, Roberto Corda2, Mauro Mereu2, Guido Mureddu2, Davide Ariu1,2, and Fabio Roli1,2 Pluribus One, via Bellini 9, 09123 Cagliari, Italy DIEE, University of Cagliari, Piazza d’Armi 09123, Cagliari, Italy" 4a0f152a07a9becb986b516a1281a4482b38db81,Video Compression for Object Detection Algorithms,"CONFIDENTIAL. Limited circulation. For review only. Preprint submitted to 24th International Conference on Pattern Recognition. Received January 22, 2018." 4afd11632db090f518c2591f46523bc7be95ba2e,Exploring outdoor appearance changes with transient scene attributes,"Exploring outdoor appearance changes with transient scene attributes Pierre-Yves Laffont, James Hays Brown University∗ Figure 1: Each image in a photo collection is represented as a point in attribute space, where each dimension corresponds to a scene property which can vary with time, weather, or lighting conditions. Left: projection of all images on the dominant plane of attribute space; each image is represented as a dot, color-coded according to its value of the “sunniness” attribute. Right: values of a few transient attributes for three photographs. The scene appearance and its attributes vary widely between the three images, despite the fixed viewpoint. The appearance of outdoor scenes changes dramatically with light- ing and weather conditions, time of day, and season. We relate visual changes to scene attributes, which are human-nameable con- epts used for high-level description of scenes. They carry semantic meaning and are more flexible than a categorical representation of scenes. While the discriminative scene attributes proposed in [Pat- terson and Hays 2012] distinguish scenes from each other, we fo- us on transient attributes which describe changes in appearance within each scene under real-world conditions. Using online webcams to gather many photographs of outdoor scenes, crowdsourcing to collect human annotations, and machine learning to train classifiers, we: • discover which attributes are likely to vary among images of" 4af36d3ce93f7ed82a7dc321fca926d540691b33,ADVISE: Symbolism and External Knowledge for Decoding Advertisements,[cs.CV] 29 Jul 2018 4abaf7d4b9577131cb2f93e913f8bd83f924da4c,Towards learning through robotic interaction alone: the joint guided search task,"Towards learning through robotic interaction alone: the joint guided search task Nick DePalma and Cynthia Breazeal 0 Ames Str. Cambridge MA Personal Robots Group MIT Media Lab" 4a4da3d1bbf10f15b448577e75112bac4861620a,"Face, Expression, and Iris Recognition Using Learning-based Approaches Face, Expression, and Iris Recognition Using Learning-based Approaches Special Thanks Are Due to Professors Table of Contents","FACE, EXPRESSION, AND IRIS RECOGNITION USING LEARNING-BASED APPROACHES Guodong Guo A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy (Computer Sciences) t the UNIVERSITY OF WISCONSIN–MADISON" 4a53ac7f99a42da17a7f1ba04f5c6d6831e31151,Beyond Bilinear: Generalized Multi-modal Factorized High-order Pooling for Visual Question Answering,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Beyond Bilinear: Generalized Multi-modal Factorized High-order Pooling for Visual Question Answering Zhou Yu, Jun Yu Member, IEEE, Chenchao Xiang, Jianping Fan, Dacheng Tao Fellow, IEEE" 4a0eb83e1c2b7afbf6d20c7775492764bd039141,Improving a Discriminative Approach to Object Recognition Using Image Patches,"Improving a Discriminative Approach to Object Recognition using Image Patches Thomas Deselaers, Daniel Keysers, and Hermann Ney Lehrstuhl f˜ur Informatik VI { Computer Science Department, RWTH Aachen University { D-52056 Aachen, Germany fdeselaers, keysers," 4a2d54ea1da851151d43b38652b7ea30cdb6dfb2,Direct recognition of motion-blurred faces,"Direct Recognition of Motion Blurred Faces Kaushik Mitra, Priyanka Vageeswaran and Rama Chellappa" 4a4a3effdfffb51a0f82d3b0904c017086996ac6,Conceptual and methodological challenges for neuroimaging studies of autistic spectrum disorders,"Mazzone and Curatolo Behavioral and Brain Functions 2010, 6:17 http://www.behavioralandbrainfunctions.com/content/6/1/17 REVIEW Conceptual and methodological challenges for neuroimaging studies of autistic spectrum disorders Luigi Mazzone1*, Paolo Curatolo2 Open Access" 4a855d86574c9bd0a8cfc522bc1c77164819c0bc,PixelCNN Models with Auxiliary Variables for Natural Image Modeling,"PixelCNN Models with Auxiliary Variables for Natural Image Modeling Alexander Kolesnikov 1 Christoph H. Lampert 1" 4abd49538d04ea5c7e6d31701b57ea17bc349412,Recognizing Fine-Grained and Composite Activities Using Hand-Centric Features and Script Data,"Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data Marcus Rohrbach · Anna Rohrbach · Michaela Regneri · Sikandar Amin · Mykhaylo Andriluka · Manfred Pinkal · Bernt Schiele" 4af25075729aa4d0fa4ecf6c948f59ec15bf9565,Analysis and Evaluation of Alternatives and Advanced Solutions for System Elements Contractual Document Evolution Executive Summary,"Project N° IST-2002-507634 - BioSecure D 9.1.2 - Revision: b3 4 June 2005 Contract Number : Project Acronym : Project Title : Instrument : Start Date of Project : Duration : Deliverable Number : Title of Deliverable : Contractual Due Date : Actual Date of Completion : IST-2002-507634 BioSecure Biometrics for Secure Authentication Network of Excellence 01 June, 2004 6 months D 9.1.2" 4a1f7905a2d6f218bd39172fb6247ffa9cfe0640,Liveness detection in remote biometrics based on gaze direction estimation,"Proceedings of the Federated Conference on Computer Science and Information Systems pp. 225–230 DOI: 10.15439/2015F307 ACSIS, Vol. 5 Liveness detection in remote biometrics based on gaze direction estimation Krzysztof Adamiak, Dominik ˙Zurek, Krzysztof ´Slot Lodz University of Technology ul. Stefanowskiego 18/22, 90-924 Łód´z, Poland Email:" 4af89578ac237278be310f7660a408b03f12d603,Large-scale geo-facial image analysis,"Islam et al. EURASIP Journal on Image and Video Processing (2015) 2015:17 DOI 10.1186/s13640-015-0070-9 RESEARCH Open Access Large-scale geo-facial image analysis Mohammad T. Islam1, Connor Greenwell1, Richard Souvenir2 and Nathan Jacobs1*" 4a8085987032e85ac8017d9977a4b76b0d8fa4ac,Object Recognition using Template Matching,"Object Recognition using Template Matching Nikhil Gupta, Rahul Gupta, Amardeep Singh, Matt Wytock December 12, 2008 Introduction Building 3D models Object Recognition is inherently a hard problem in omputer vision. Current standard object recogni- tion techniques require small training data sets of images and apply sophisticated algorithms. These methods tend to perform poorly because the small data set does not reflect the true distribution (selec- tion bias). Recently, Torralba et al [1] have proposed to de- velop a large data set of images (80 million images) nd apply simple algorithms for object recognition. Their method performs relatively well for some cer- tain classes of objects. Nevertheless, their data sets require very large storage and are noisy. In this project, we develop precise 3D models of objects and use these to apply simple learning al-" 4a5b2d5892f630a10b136eab25a1406de81b586b,Adaptive low bit rate facial feature enhanced residual image coding method using SPIHT for compressing personal ID images,"This article appeared in a journal published by Elsevier. The attached opy is furnished to the author for internal non-commercial research nd education use, including for instruction at the authors institution nd sharing with colleagues. Other uses, including reproduction and distribution, or selling or licensing copies, or posting to personal, institutional or third party websites are prohibited. In most cases authors are permitted to post their version of the rticle (e.g. in Word or Tex form) to their personal website or institutional repository. Authors requiring further information regarding Elsevier’s archiving and manuscript policies are encouraged to visit: http://www.elsevier.com/copyright" 4ac3cd8b6c50f7a26f27eefc64855134932b39be,Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network,"Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network Daniel Merget Matthias Rock Gerhard Rigoll Technical University of Munich" 4a56d5e483ddea93f14bfbe350a3063b2b9126cb,Iterative Action and Pose Recognition Using Global-and-Pose Features and Action-Specific Models,"Iterative Action and Pose Recognition using Global-and-Pose Features and Action-specific Models Norimichi Ukita Nara Institute of Science and Technology" 4a95dacb1d38a07e73007082b8ed7651a4b5277c,Region labelling using a Point-Based Coherence Criterion,"Region labelling using a Point-Based Coherence Criterion Hichem Houissa(cid:2) and Nozha Boujemaa(cid:2) (cid:2)INRIA Rocquencourt, BP 105,78153, Le Chesnay Cedex-France" 4a3d96b2a53114da4be3880f652a6eef3f3cc035,A Dictionary Learning-Based 3D Morphable Shape Model,"A Dictionary Learning-Based D Morphable Shape Model Claudio Ferrari , Giuseppe Lisanti, Stefano Berretti , Senior Member, IEEE, and Alberto Del Bimbo" 4ada5b80a032f3daa4e97e9f716a5cba7cf80d85,Learning a priori constrained weighted majority votes,"Noname manuscript No. (will be inserted by the editor) Learning A Priori Constrained Weighted Majority Votes Aur´elien Bellet · Amaury Habrard · Emilie Morvant · Marc Sebban Received: date / Accepted: date" 4a1a5316e85528f4ff7a5f76699dfa8c70f6cc5c,Face Recognition using Local Features based on Two-layer Block Model,"MVA2005 IAPR Conference on Machine VIsion Applications, May 16-18, 2005 Tsukuba Science City, Japan Face Recognition using Local Features based on Two-layer Block M odel W onjun Hwang1 Ji-Yeun Kim Seokcheol Kee Computing Lab., Samsung Advanced Institute of Technology ombined by Yang and etc [7]. The sparsification of LFA helps the reduction of dimension of image in LDA scheme nd local topological property is more useful than holistic property of PCA in recognition, but there is still structural problem because the method to select the features is designed for minimization of reconstruction error, not for increasing discriminability in face model. In this paper, we proposed the novel recognition lgorithm to merge LFA and LDA method. We do not use the existing sparsification method for selecting features but dopt the two-layer block model to make several groups with topographic local features in similar position. Each local block, flocked local features, can represent its own local property and at time holistic face" 4a31ca27b987606ae353b300488068b5240633ee,WSABIE: scaling up to large vocabulary image annotation,"WSABIE: Scaling Up To Large Vocabulary Image Annotation Jason Weston1 and Samy Bengio1 and Nicolas Usunier2 Google, USA Universit´e Paris 6, LIP6, France" 4a1b67d1f30abeeecb270666605025d9d78971ff,Energy-based adaptive skin segmentation for hand and head detection,"Noname manuscript No. (will be inserted by the editor) Energy-based adaptive skin segmentation for hand and head detection Michal Kawulok Received: date / Accepted: date" 4afd04db8eeb6a4cacb616b0dd193819bad8c2b6,Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking,"JOURNAL OF LATEX CLASS FILES, DOI 10.1109/TCSVT.2018.2825679 Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking Hui Zhou, Wanli Ouyang, Jian Cheng, Xiaogang Wang, and Hongsheng Li" 4a2062ba576ca9e9a73b6aa6e8aac07f4d9344b9,Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification,"Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification Hilal Ergun and Mustafa SertB Department of Computer Engineering Bas¸kent University 06810 Ankara, TURKEY" 4af133c49d39c8b7aa9d82c17f1fd2c70e36233f,Recognition of Facial Gestures using Gabor Filter,"Recognition of Facial Gestures using Gabor Filter {tag} {/tag} International Journal of Computer Applications © 2011 by IJCA Journal Number 8 - Article 2 Year of Publication: 2011 Authors: Subhashini Ramalingam Dr Ilango Paramasivam Mangayarkarasi Ramiah 10.5120/3153-3990" 4adca62f888226d3a16654ca499bf2a7d3d11b71,Models of Semantic Representation with Visual Attributes,"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 572–582, Sofia, Bulgaria, August 4-9 2013. c(cid:13)2013 Association for Computational Linguistics" 4a9831e5fec549edee454709048a51997ef60fb7,Did the Model Understand the Question?,"Did the Model Understand the Question? Pramod K. Mudrakarta University of Chicago Ankur Taly Google Brain Mukund Sundararajan Kedar Dhamdhere Google Google" 4a75d59c9c57da420441190071ba545eb4a75e1e,Deep Mixture of Diverse Experts for Large-Scale Visual Recognition,"Deep Mixture of Diverse Experts for Large-Scale Visual Recognition Tianyi Zhao, Jun Yu, Zhenzhong Kuang, Wei Zhang, Jianping Fan" 4a5014c23e2adb640f4b07b9b47ca2f2a5d427e6,On the Estimation of Face Recognition System Performance using Image Variabil- ity Information,"Accepted Manuscript Title: On the estimation of face recognition system performance using image variability information Authors: Muhammad Aurangzeb Khan, Costas Xydeas, Hassan Ahmed Reference: To appear in: Received date: Revised date: Accepted date: S0030-4026(17)30206-1 http://dx.doi.org/doi:10.1016/j.ijleo.2017.02.063 IJLEO 58879 8-8-2016 7-2-2017 7-2-2017 Please cite this article as: Muhammad Aurangzeb Khan, Costas Xydeas, Hassan Ahmed, On the estimation of face recognition system performance using image variability information, Optik - International Journal for Light and Electron Optics http://dx.doi.org/10.1016/j.ijleo.2017.02.063" 4a0267f6e840d6632122a60e8fad1f8740eba8ca,Comparative study: face recognition on unspecific persons using linear subspace methods,"Comparative Study: Face Recognition on Unspeci(cid:2)c Persons using Linear Subspace Methods Dahua Lin Shuicheng Yan Xiaoou Tang Dept. of Information Engineering Dept. of Information Engineering Dept. of Information Engineering The Chinese University of The Chinese University of The Chinese University of Hong Kong Shatin, Hong Kong SAR Email: Hong Kong Shatin, Hong Kong SAR Email: Hong Kong Shatin, Hong Kong SAR Email:" 4a227881f5763d2bda2e545eac346389b2b2017a,Model based image interpretation with application to facial expression recognition,"d d d d d d d ddd ddd ddd ddd Institut für Informatik der Technischen Universität München Model-based Image Interpretation with Application to Facial Expression Recognition Dissertation Matthias Wimmer" 4aa18f3a1c85f7a09d3b0d6b28c0339199892d60,The Application of Neural Networks for Facial Landmarking on Mobile Devices, 4a45b8f8decc178305af06d758ac7428a9070fad,Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data,"Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data Amjad Almahairi 1 † Sai Rajeswar 1 Alessandro Sordoni 2 Philip Bachman 2 Aaron Courville 1 3" 4a6fcf714f663618657effc341ae5961784504c7,Scaling Up Class-Specific Kernel Discriminant Analysis for Large-Scale Face Verification,"Scaling up Class-Specific Kernel Discriminant Analysis for large-scale Face Verification Alexandros Iosifidis, Senior Member, IEEE, and Moncef Gabbouj, Fellow, IEEE" 4ae3cdba121dec886a84eff146e438a55513002c,Interactive Hausdorff distance computation for general polygonal models,"Interactive Hausdorff Distance Computation for General Polygonal Models Min Tang∗ Minkyoung Lee† Ewha Womans University, Seoul, Korea Young J. Kim‡ http://graphics.ewha.ac.kr/HDIST Figure 1: Interactive Hausdorff Distance Computation. Our algorithm can compute Hausdorff distance between complicated models at interactive rates (the first three figures). Here, the green line denotes the Hausdorff distance. This algorithm can also be used to find penetration depth (PD) for physically-based animation (the last two figures). It takes only a few milli-seconds to run on average." 4a70c6e14bcd7a44838fdabdcdb33bc026c907b4,Allocentric Pose Estimation,"Allocentric Pose Estimation Jos´e Oramas M. Luc De Raedt Tinne Tuytelaars KU Leuven, ESAT-PSI, iMinds KU Leuven, CS-DTAI KU Leuven, ESAT-PSI, iMinds" 4a88237199595feaa3f0e3289cbdd201a3ce28ff,Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking,"Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking Hengkai Guo1(cid:63), Tang Tang1, Guozhong Luo1, Riwei Chen1, Yongchen Lu1, nd Linfu Wen1 ByteDance AI Lab" 4a3a9d02999fcf0895db31d644f40c98254ac4b1,Vision-based 3D bicycle tracking using deformable part model and Interacting Multiple Model filter,"Vision-based 3D Bicycle Tracking using Deformable Part Model nd Interacting Multiple Model Filter Hyunggi Cho, Paul E. Rybski and Wende Zhang" 4ad51a99e489939755f1d4f5d1f5bc509c49e96d,Preferences for facially communicated big five personality traits and their relation to self-reported big five personality,"Personality and Individual Differences 134 (2018) 195–200 Contents lists available at ScienceDirect Personality and Individual Differences journal homepage: www.elsevier.com/locate/paid Preferences for facially communicated big five personality traits and their relation to self-reported big five personality Donald F. Sacco⁎, Mitch Brown The University of Southern Mississippi, United States of America A R T I C L E I N F O A B S T R A C T Keywords: Personality Face perception Big five Similarity Complementarity A growing body of research has begun to document that core personality traits are associated with specific facial structures, and that individuals are sensitive to these facial cues, as indexed by preferences for faces commu- nicating higher or lower levels of specific traits. We explored how self-reported Big Five personality traits in- fluence preferences for facially-communicated Big Five personality in targets. Participants selected among pairs" 1bc23c771688109bed9fd295ce82d7e702726327,C 2011 Jianchao Yang Sparse Modeling of High-dimensional Data for Learning and Vision,(cid:13) 2011 Jianchao Yang 1b0f11db30e9184da63decbd7711db196753054c,The iNaturalist Species Classification and Detection Dataset-Supplementary Material,"The iNaturalist Species Classification and Detection Dataset - Supplementary Material Grant Van Horn1 Oisin Mac Aodha1 Yang Song2 Yin Cui3 Chen Sun2 Alex Shepard4 Hartwig Adam2 Pietro Perona1 Serge Belongie3 Caltech Google Cornell Tech iNaturalist . Additional Classification Results We performed an experiment to understand if there was ny relationship between real world animal size and pre- diction accuracy. Using existing records for bird [4] and mammal [2] body sizes we assigned a mass to each of the lasses in iNat2017 that overlapped with these datasets. For given species, mass will vary due to the life stage or gen- der of the particular individual. Here, we simply take the verage value. This resulted in data for 795 species, from the small Allen’s hummingbird (Selasphorus sasin) to the" 1b4424e06ac29b72535727b92f261f39d065e858,3D Pictorial Structures Revisited: Multiple Human Pose Estimation,"D Pictorial Structures Revisited: Multiple Human Pose Estimation Vasileios Belagiannis, Sikandar Amin, Mykhaylo Andriluka, Bernt Schiele, Nassir Navab, and Slobodan Ilic" 1b1d9b528c69e082dc5685089090bd2d849d887d,STD-PD: Generating Synthetic Training Data for Pedestrian Detection in Unannotated Videos,"MixedPeds: Pedestrian Detection in Unannotated Videos using Synthetically Generated Human-agents for Training Ernest Cheung, Anson Wong, Aniket Bera, Dinesh Manocha Department of Computer Science Project Webpage: http://gamma.cs.unc.edu/MixedPeds The University of North Carolina at Chapel Hill Email: {ernestc, ahtsans, ab," 1ba61a4fedc217f7bd052d1b2904567c9985dc44,Person Re-identification for Improved Multi-person Multi-camera Tracking by Continuous Entity Association,"Person Re-identification for Improved Multi-person Multi-camera Tracking by Continuous Entity Association Neeti Narayan, Nishant Sankaran, Devansh Arpit, Karthik Dantu, Srirangaraj Setlur, Venu Govindaraju University at Buffalo" 1b9472907f5b7a1815c98b4562dce6c46dd2cf34,Consistent Rank Logits for Ordinal Regression with Convolutional Neural Networks,"Consistent Rank Logits for Ordinal Regression with Convolutional Neural Networks Wenzhi Cao 1 Vahid Mirjalili 2 Sebastian Raschka 1" 1bc783d6bc137b7fabcb5cfc9c4542c500a5c3ba,Fast Human Detection Algorithm for High-Resolution CCTV Camera,"Journal of the Korea Academia-Industrial ooperation Society Vol. 15, No. 8 pp. 5263-5268, 2014 http://dx.doi.org/10.5762/KAIS.2014.15.8.5263 ISSN 1975-4701 / eISSN 2288-4688 고해상도 CCTV 카메라를 위한 빠른 사람 검출 알고리즘 박인철1* 호원대학교 국방기술학부 Fast Human Detection Algorithm for High-Resolution CCTV Camera In-Cheol Park1* Division of Defence Technology, Howon University 본 논문은 사람 검출 알고리즘을 고해상도 CCTV 카메라에 적용할 수 있도록 빠른 사람 검출 알고리즘을 제안한다. HOG 디텍터를 이용한 사람 검출 알고리즘은 영상처리 분야의 최신 기술로 높은 성능을 보인다. 그러나 HOG 특징 추출 과정에서 연산 속도가 느려 실시간 고해상도 영상에 적용하기 어렵다. 이러한 문제를 해결하기 위해 2단계 검출 방법을 제안 한다. 먼저 전처리 과정으로 배경 차감법(Background subtraction)을 이용하여 사람 후보 영역을 찾는다. 이후 사람 후보 영역에서만 HOG 디텍터를 이용하여 사람/비사람 구분을 수행한다. 이러한 두 단계의 실험 결과 약 2.5배의 검출 속도 향상을 보였으며, 성능 저하는 거의 없음을 확인할 수 있었다." 1b1323b4677c640ae8835a9ccab611ca1e9652e3,Robust object tracking with a hierarchical ensemble framework,"Robust Object Tracking with a Hierarchical Ensemble Framework Mengmeng Wang1, Yong Liu2 and Rong Xiong2" 1b4bc7447f500af2601c5233879afc057a5876d8,Facial Action Unit Classification with Hidden Knowledge under Incomplete Annotation,"Facial Action Unit Classification with Hidden Knowledge under Incomplete Annotation Jun Wang University of Science and Technology of China Hefei, Anhui Shangfei Wang University of Science and Technology of China Hefei, Anhui Rensselaer Polytechnic Qiang Ji Institute Troy, NY P.R.China, 230027 P.R.China, 230027 USA, 12180" 1b2568de7363a9f46094b9cac82f4fe2ec1a4f56,Detection of Fragmented Rectangular Enclosures in Very High Resolution Remote Sensing Images,"Detection of Fragmented Rectangular Enclosures in Very High Resolution Remote Sensing Images Igor Zingman, Dietmar Saupe, Otávio A. B. Penatti, and Karsten Lambers" 1b807b6abaeef68edfbdc4200e198bf4e9613198,Image Processing Pipeline for Facial Expression Recognition under Variable Lighting,"Image Processing Pipeline for Facial Expression Recognition under Variable Lighting Ralph Ma, Amr Mohamed" 1b0548e52a1ffc7ebffe5200e2111525c9f7fd4a,Novel Views of Objects from a Single Image,"Novel Views of Objects from a Single Image Konstantinos Rematas, Chuong Nguyen, Tobias Ritschel, Mario Fritz, and Tinne Tuytelaars" 1ba8acf75d84bccc14590251353b369cdd3bd500,Computationally efficient dense moving object detection based on reduced space disparity estimation,"Computationally ef‌f‌icient dense moving object detection based on reduced space disparity estimation Goran Popovi´c, Antea Hadviger, Ivan Markovi´c, Ivan Petrovi´c ∗ University of Zagreb Faculty of Electrical Engineering and Computing, Laboratory for Autonomous Systems and Mobile Robotics, Zagreb, Croatia (e-mail:" 1bb14ddc0326a8e5b44eafd915738c2b1342f392,Title On color texture normalization for active appearance models,"Provided by the author(s) and NUI Galway in accordance with publisher policies. Please cite the published version when available. Title On color texture normalization for active appearance models Author(s) Ionita, Mircea C.; Corcoran, Peter M.; Buzuloiu, Vasile Publication 009-05-12 Publication Information Ionita, M. C., Corcoran, P., & Buzuloiu, V. (2009). On Color Texture Normalization for Active Appearance Models. Image Processing, IEEE Transactions on, 18(6), 1372-1378. Publisher Link to publisher's version http://dx.doi.org/10.1109/TIP.2009.2017163 Item record http://hdl.handle.net/10379/1350" 1b150248d856f95da8316da868532a4286b9d58e,Analyzing 3D Objects in Cluttered Images,"Analyzing 3D Objects in Cluttered Images Mohsen Hejrati UC Irvine Deva Ramanan UC Irvine" 1b457646a300c744bf098f0bfde641042602262a,Holistic and Gabor-local Feature-fusion for Face Recognition using Canonical Correlation Analysis ( CCA ),"Holistic and Gabor-local Feature-fusion for Face Recognition using Canonical Correlation Analysis (CCA) Hendra Kusuma1), Wirawan2), Adi Soeprijanto3) Department of Electrical Engineering, Faculty of Industrial Technology ITS Surabaya Indonesia 60111 e-mail : Abstrak – In this paper, we propose a feature fusion method based on Canonical Correlation Analysis (CCA) for combining two feature extractors to increase robustness of face recognition against pose nd illumination changes. At first holistic features, eigenfaces (PCA) and Gabor phase congruency image (GPCI) features are extracted from facial images respectively and then CCA finds the transformation for each extractor dataset and maximizes orrelation between them. Experiments results on Yale face image and ORL databases have shown that the fusion of exhibit better performance. Keywords: Feature-fusion, Local features, Holistic" 1b2297ba37fece76568c8b53369e6fd34d63175a,High-Resolution 3 D Layout from a Single View,"High-Resolution 3D Layout from a Single View M. Zeeshan Zia1, Michael Stark2, and Konrad Schindler1 Photogrammetry and Remote Sensing, ETH Z¨urich, Switzerland Stanford University and Max Planck Institute for Informatics" 1b2e50412ec151486912f0bfd01703c8ec46b5a7,A geometric approach to face detector combining,"A Geometric Approach to Face Detector Combining⋆ Nikolay Degtyarev and Oleg Seredin Tula State University http://lda.tsu.tula.ru" 1b7a0fffb5ee96adece2f6079f5e9ab79c3bc50e,Spigan: Privileged Adversarial Learning,"Under review as a conference paper at ICLR 2019 SPIGAN: PRIVILEGED ADVERSARIAL LEARNING FROM SIMULATION Anonymous authors Paper under double-blind review" 1bfc74bad04b407d1792a70d73a3f5dc0be0506d,Cross-Dataset Adaptation for Visual Question Answering,"Cross-Dataset Adaptation for Visual Question Answering Wei-Lun Chao∗ Hexiang Hu∗ Fei Sha U. of Southern California U. of Southern California U. of Southern California Los Angeles, CA Los Angeles, CA Los Angeles, CA" 1b3d5d95e1fcded017f193f5cf9772bf8a1ed108,Using Keystroke Analytics to Improve Pass – Fail Classifiers,"(2017). Using nalytics http://dx.doi.org/10.18608/jla.2017.42.14 keystrokes improve pass-fail lassifiers. Journal Learning Analytics, (2), 89–211. Using Keystroke Analytics to Improve Pass–Fail Classifiers Kevin Casey Maynooth University, Ireland" 1bea531e8271202462c7907f60a8458fa5aec00d,"Ein generisches System zur automatischen Detektion, Verfolgung und Wiedererkennung von Personen in Videodaten","Ein generisches System zur automatischen Detektion, Verfolgung und Wiedererkennung von Personen in Videodaten Zur Erlangung des akademischen Grades eines Doktor-Ingenieurs von der Fakult¨at f¨ur Bauingenieur-, Geo- und Umweltwissenschaften des Karlsruher Instituts f¨ur Technologie (KIT) (Institut f¨ur Photogrammetrie und Fernerkundung) genehmigte Dissertation Dipl.-Inform. Kai J¨ungling us Adenau Tag der m¨undlichen Pr¨ufung: 24.01.2011 Referent: Prof. Dr.-Ing. Stefan Hinz Korreferent: Prof. Dr. rer. nat. Maurus Tacke Korreferent: Prof. Dr.-Ing. Christoph Stiller Karlsruhe 2011" 1bbec7190ac3ba34ca91d28f145e356a11418b67,Explorer Action Recognition with Dynamic Image Networks,"Action Recognition with Dynamic Image Networks Citation for published version: Bilen, H, Fernando, B, Gravves, E & Vedaldi, A 2017, 'Action Recognition with Dynamic Image Networks' IEEE Transactions on Pattern Analysis and Machine Intelligence. DOI: 10.1109/TPAMI.2017.2769085 Digital Object Identifier (DOI): 0.1109/TPAMI.2017.2769085 Link: Link to publication record in Edinburgh Research Explorer Document Version: Peer reviewed version Published In: IEEE Transactions on Pattern Analysis and Machine Intelligence General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) nd / or other copyright owners and it is a condition of accessing these publications that users recognise and bide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer ontent complies with UK legislation. If you believe that the public display of this file breaches copyright please ontact providing details, and we will remove access to the work immediately and" 1b1173a3fb33f9dfaf8d8cc36eb0bf35e364913d,Registration Invariant Representations for Expression Detection,"DICTA DICTA 2010 Submission #147. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. Registration Invariant Representations for Expression Detection Anonymous DICTA submission Paper ID 147" 1bdef21f093c41df2682a07f05f3548717c7a3d1,Towards Automated Classification of Emotional Facial Expressions,"Towards Automated Classification of Emotional Facial Expressions Lewis J. Baker Vanessa LoBue Elizabeth Bonawitz & Patrick Shafto Department of Mathematics and Computer Science, 2Department of Psychology Rutgers University – Newark, 101 Warren St., Newark, NJ, 07102 USA" 1b3b01513f99d13973e631c87ffa43904cd8a821,HMM recognition of expressions in unrestrained video intervals,"HMM RECOGNITION OF EXPRESSIONS IN UNRESTRAINED VIDEO INTERVALS José Luis Landabaso, Montse Pardàs, Antonio Bonafonte Universitat Politècnica de Catalunya, Barcelona, Spain" 1b793cc5dceb98c95e816aebc2252205bfd71569,ADNet: A Deep Network for Detecting Adverts,"ADNet: A Deep Network for Detecting Adverts Murhaf Hossari(cid:63)1, Soumyabrata Dev(cid:63)1, Matthew Nicholson1, Killian McCabe1, Atul Nautiyal1, Clare Conran1, Jian Tang3, Wei Xu3, and Fran¸cois Piti´e1,2 The ADAPT SFI Research Centre, Trinity College Dublin Department of Electronic & Electrical Engineering, Trinity College Dublin Huawei Ireland Research Center, Dublin" 1b6d2f8f9cbbf5e20e445a60cb7840a30975f297,Learning from Noisy Web Data with Category-level Supervision,"Learning from Noisy Web Data with Category-level Supervision Li Niu, Qingtao Tang, Ashok Veeraraghavan, and Ashu Sabharwal" 1ba55051d3957895d77257cc9a5885068fb2e43a,High-Resolution Face Verification Using Pore-Scale Facial Features,"High-Resolution Face Verification Using Pore-Scale Facial Features Dong Li, Huiling Zhou, and Kin-Man Lam" 1bd80812c58de8cb0127aea915a45ebbff42dc3b,Twins 3D face recognition challenge,"Twins 3D Face Recognition Challenge Vipin Vijayan 1, Kevin W. Bowyer 1, Patrick J. Flynn 1, Di Huang 2, Liming Chen 2, Mark Hansen 3, Omar Ocegueda 4, Shishir K. Shah 4, Ioannis A. Kakadiaris 4" 1b2183c2b9608b7f815551c9ba602f22205126b1,Facial Reenactment Project Plan,"Facial Reenactment Project Plan Student: Li Wing Yee Supervisor: Dr. Dirk Scheiders" 1b6394178dbc31d0867f0b44686d224a19d61cf4,EPML: Expanded Parts Based Metric Learning for Occlusion Robust Face Verification,"EPML: Expanded Parts based Metric Learning for Occlusion Robust Face Verification Gaurav Sharma, Fr´ed´eric Jurie, Patrick P´erez To cite this version: Gaurav Sharma, Fr´ed´eric Jurie, Patrick P´erez. EPML: Expanded Parts based Metric Learning for Occlusion Robust Face Verification. Asian Conference on Computer Vision, Nov 2014, -, Singapore. pp.1-15, 2014. HAL Id: hal-01070657 https://hal.archives-ouvertes.fr/hal-01070657 Submitted on 2 Oct 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 1b4f6f73c70353869026e5eec1dd903f9e26d43f,Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels,"Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Jiechao Xiong, Shaogang Gong, Yizhou Wang, and Yuan Yao" 1b300a7858ab7870d36622a51b0549b1936572d4,Dynamic Facial Expression Recognition With Atlas Construction and Sparse Representation,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TIP.2016.2537215, IEEE Transactions on Image Processing Dynamic Facial Expression Recognition with Atlas Construction and Sparse Representation Yimo Guo, Guoying Zhao, Senior Member, IEEE, and Matti Pietik¨ainen, Fellow, IEEE" 1be498d4bbc30c3bfd0029114c784bc2114d67c0,Age and Gender Estimation of Unfiltered Faces,"Age and Gender Estimation of Unfiltered Faces Eran Eidinger, Roee Enbar, Tal Hassner*" 1b3ee5455956a40c6e9e09ccda0f4fb162838629,The Recognition of License Plate Restrictions Based on Faster R-CNN,"017 2nd International Conference on Manufacturing Science and Information Engineering (ICMSIE 2017) ISBN: 978-1-60595-516-2 The Recognition of License Plate Restrictions Based on Faster R-CNN Xi Wang, Lina Xun, Yi Xia, Fenglin Du, Yun Ding, Yuanyuan Li nd Zhi Yang" 1b90507f02967ff143fce993a5abbfba173b1ed0,Gradient-DCT (G-DCT) descriptors,"Image Processing Theory, Tools and Applications Gradient-DCT (G-DCT) Descriptors Radovan Fusek, Eduard Sojka Technical University of Ostrava, FEECS, Department of Computer Science, 7. listopadu 15, 708 33 Ostrava-Poruba, Czech Republic e-mail:" 1b92973843c3a791bb5ca5a68405c3ecb3473ded,Grassmann Learning To perform discriminant learning on Grassmann manifolds,"Building Deep Networks on Grassmann Manifolds Zhiwu Huang†, Jiqing Wu†, Luc Van Gool†‡ Computer Vision Lab, ETH Zurich, Switzerland VISICS, KU Leuven, Belgium {zhiwu.huang, jiqing.wu," 1ba20398e3b0154730590217a0988fbbab19e927,Doubly weighted nonnegative matrix factorization for imbalanced face recognition,"978-1-4244-2354-5/09/$25.00 ©2009 IEEE ICASSP 2009" 1bed38bc216f80a50617afa5c6d9cc4b2db72519,Face recognition using early biologically inspired features,"Face Recognition Using Early Biologically Inspired Features Min Li, Shenghua Bao, Weihong Qian, and Zhong Su IBM China Research Lab, PRC fminliml,baoshhua,qianwh, Nalini K. Ratha IBM Watson Research Center, USA" 1be18a701d5af2d8088db3e6aaa5b9b1d54b6fd3,ENHANCEMENT OF FAST FACE DETECTION ALGORITHM BASED ON A CASCADE OF DECISION TREES,"ENHANCEMENT OF FAST FACE DETECTION ALGORITHM BASED ON A CASCADE OF DECISION TREES V. V. Khryashchev a, *, A. A. Lebedev a, A. L. Priorov a YSU, Yaroslavl, Russia - (vhr, Commission II, WG II/5 KEY WORDS: Face Detection, Cascade Algorithm, Decision Trees." 1b2dd300a43d0553f1deb578d9aea45d99472136,Fast Approximation of Distance Between Elastic Curves using Kernels, 1bf0b5186af083117af136dfcb08ed28828664d0,"Deep Filter Banks for Texture Recognition, Description, and Segmentation","Int J Comput Vis DOI 10.1007/s11263-015-0872-3 Deep Filter Banks for Texture Recognition, Description, nd Segmentation Mircea Cimpoi1 · Subhransu Maji2 · Iasonas Kokkinos3 · Andrea Vedaldi1 Received: 4 June 2015 / Accepted: 20 November 2015 © The Author(s) 2015. This article is published with open access at Springerlink.com" 1bb73d8f1224a846473d0a2ddc4289ae3e21b61c,A joint particle filter to track the position and head orientation of people using audio visual cues,"© EURASIP, 2010 ISSN 2076-1465 8th European Signal Processing Conference (EUSIPCO-2010) INTRODUCTION" 1b224ad99c42e696b6d98c05a87f1738e28c6c5e,A Markov Random Field Groupwise Registration Framework for Face Recognition,"A Markov Random Field Groupwise Registration Framework for Face Recognition Shu Liao, Dinggang Shen, and Albert C.S. Chung" 1b7a7d291235e4b6e5f97722124070feb26f3cc1,Learning Two-Branch Neural Networks for Image-Text Matching Tasks,"Learning Two-Branch Neural Networks for Image-Text Matching Tasks Liwei Wang, Yin Li, Jing Huang, Svetlana Lazebnik" 1b0a071450c419138432c033f722027ec88846ea,Looking at faces in a vehicle: A deep CNN based approach and evaluation,"Windsor Oceanico Hotel, Rio de Janeiro, Brazil, November 1-4, 2016 978-1-5090-1889-5/16/$31.00 ©2016 IEEE" 1b55c4e804d1298cbbb9c507497177014a923d22,Incremental Class Representation Learning for Face Recognition,"Incremental Class Representation Learning for Face Recognition Degree’s Thesis Audiovisual Systems Engineering Author: Advisors: Elisa Sayrol, Josep Ramon Morros Eric Presas Valga Universitat Politècnica de Catalunya (UPC) 016 - 2017" 1b71d3f30238cb6621021a95543cce3aab96a21b,Fine-grained Video Classification and Captioning,"Fine-grained Video Classification and Captioning Farzaneh Mahdisoltani1,2, Guillaume Berger2, Waseem Gharbieh2 David Fleet1, Roland Memisevic2 {farzaneh, University of Toronto1, Twenty Billion Neurons2" 1b3505018e39a794eab032e7e313784b21be42e9,Saliency based Person Re-Identification in Video using Colour Features,"GRD Journals- Global Research and Development Journal for Engineering | Volume 1 | Issue 10 | September 2016 ISSN: 2455-5703 Saliency based Person Re-Identification in Video using Colour Features Srujy Krishna A U PG Student Shimy Joseph Assistant Professor Department of Computer Science and Engineering Department of Computer Science and Engineering Federal Institute Of Science and Technology Federal Institute Of Science and Technology" 1b3587363d37dd197b6adbcfa79d49b5486f27d8,Multimodal Grounding for Language Processing,"Multimodal Grounding for Language Processing Lisa Beinborn◦∗3 Teresa Botschen∗(cid:52) Iryna Gurevych (cid:52) Language Technology Lab, University of Duisburg-Essen (cid:52) Ubiquitous Knowledge Processing Lab (UKP) and Research Training Group AIPHES Department of Computer Science, Technische Universit¨at Darmstadt www.ukp.tu-darmstadt.de" 1b74479f6e597a33703a63161527d55cc5d3096f,Self-Supervised Model Adaptation for Multimodal Semantic Segmentation,"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation Abhinav Valada · Rohit Mohan · Wolfram Burgard" 1b8508c6e341dcc803e52ed02968ae944c744f68,Face detection evaluation: a new approach based on the golden ratio $${\Phi}$$,"SIViP manuscript No. (will be inserted by the editor) Face Detection Evaluation: A New Approach Based on the Golden Ratio (cid:8) M. Hassaballah (cid:1) Kenji Murakami (cid:1) Shun Ido Received: 1 Jan. 2011 /Revised: 9 March 2011/ Accepted: date" 1b7b95ee13d91e9c768de6417a8919f2a3384599,A Probabilistic U-Net for Segmentation of Ambiguous Images,"A Probabilistic U-Net for Segmentation of Ambiguous Images Simon A. A. Kohl1∗,2,, Bernardino Romera-Paredes1, Clemens Meyer1, Jeffrey De Fauw1, Joseph R. Ledsam1, Klaus H. Maier-Hein2, S. M. Ali Eslami1, Danilo Jimenez Rezende1, and Olaf Ronneberger1 Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany DeepMind, London, UK" d488dad9fa81817c85a284b09ebf198bf6b640f9,FCHD: A fast and accurate head detector,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 FCHD: A fast and accurate head detector Aditya Vora, Johnson Controls Inc." d4a7259340ece685b9dacb390eea10c6684a05b3,Object Detection based on Region Decomposition and Assembly,"Object Detection based on Region Decomposition and Assembly Computer Vision Lab., Department of Computer Science and Engineering Incheon National University, 119 Academy-ro, Yeonsu-gu, Incheon, 22012, Korea Seung-Hwan Bae" d4343b3c7122f57ecc0bb39887406dad5214dd57,Effective and Efficient Optimization Methods for Kernel Based Classification Problems,"Effective and Efficient Optimization Methods for Kernel Based Classification Problems Aditya Tayal A thesis presented to the University of Waterloo in fulfilment of the thesis requirement for the degree of Doctor of Philosophy Computer Science Waterloo, Ontario, Canada, 2014 ©Aditya Tayal 2014" d4e4369babdba158bfdce1b605f92d6b1b665be4,The amygdala and the relevance detection theory of autism: an evolutionary perspective,"REVIEW ARTICLE published: 30 December 2013 doi: 10.3389/fnhum.2013.00894 The amygdala and the relevance detection theory of autism: n evolutionary perspective Tiziana Zalla1* and Marco Sperduti 2,3 Institut Jean Nicod, Centre National de la Recherche Scientifique, Ecole Normale Supérieure, Paris, France Laboratoire Mémoire et Cognition, Institut de Psychologie, Université Paris Descartes, Boulogne-Billancourt, France Inserm U894, Centre de Psychiatrie et Neurosciences, Université Paris Descartes, Paris, France Edited by: Corrado Corradi-Dell’Acqua, University of Geneva, Switzerland Reviewed by: Sebastian B. Gaigg, City University London, UK Bhismadev Chakrabarti, University of Reading, UK Danilo Bzdok, Research Center Jülich, Germany *Correspondence:" d45fbd818f032566e9e8f8bdc0f658cdd6873e8f,Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks,"Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, and Yusuke Uchida DeNA Co., Ltd., Tokyo, Japan" d4207e8fdb053e81f4570ca2da9f6e7b73656ccf,Image Saliency Applied to Infrared Images for Unmanned Maritime Monitoring,"Image Saliency Applied to Infrared Images for Unmanned Maritime Monitoring Gon¸calo Cruz1 and Alexandre Bernardino2 Research Center, Portuguese Air Force Academy, Sintra, Portugal Computer and Robot Vision Laboratory, Instituto de Sistemas e Rob´otica, Instituto Superior T´ecnico, Lisboa, Portugal" d4b88be6ce77164f5eea1ed2b16b985c0670463a,A Survey of Different 3 D Face Reconstruction Methods,"TECHNICAL REPORT JAN.15.2016 A Survey of Different 3D Face Reconstruction Methods Amin Jourabloo Department of Computer Science and Engineering" d4a44459849ec8fcd51f9b5eee196e197d15e005,Novel Simulation Framework of Three-Dimensional Skull BioMetric Measurement,"Shibab A. Hameed et al / International Journal on Computer Science and Engineering Vol.1(3), 2009, 269-274 Novel Simulation Framework of Three-Dimensional Skull Bio-Metric Measurement Shihab A. Hameed, B.B.Zaidan, A.A.Zaidan, A.W. Naji and Omar Faroq" d4901683e2c2552fc2d62d4eb3b1f5d5fa60a5ff,ScaleNet: Scale Invariant Network for Semantic Segmentation in Urban Driving Scenes, d458c49a5e34263c95b3393386b5d76ba770e497,A Comparative Analysis of Gender Classification Techniques,"Middle-East Journal of Scientific Research 20 (1): 01-13, 2014 ISSN 1990-9233 © IDOSI Publications, 2014 DOI: 10.5829/idosi.mejsr.2014.20.01.11434 A Comparative Analysis of Gender Classification Techniques Sajid Ali Khan, Maqsood Ahmad, Muhammad Nazir and Naveed Riaz Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad, Pakistan" d4ced2086ccd9259ade8fabdba14e0e4d9fc0c40,A Mobile Imaging System for Medical Diagnostics,"A Mobile Imaging System for Medical Diagnostics Sami Varjo and Jari Hannuksela The Center for Machine Vision Research Department of Computer Science and Engineering P.O. Box 4500, FI-90014 University of Oulu" d48bd355d091e7ae75ade4e878fe346741e7da1a,Can You Spot the Semantic Predicate in this Video ?,"Can You Spot the Semantic Predicate in this Video? Christopher Reale, Claire Bonial, Heesung Kwon and Clare R. Voss U.S. Army Research Lab, Adelphi, Maryland 20783 {claire.n.bonial.civ, heesung.kwon.civ," d41c11ebcb06c82b7055e2964914b9af417abfb2,CDI-Type I : Unsupervised and Weakly-Supervised Discovery of Facial Events 1,"CDI-Type I: Unsupervised and Weakly-Supervised Introduction Discovery of Facial Events The face is one of the most powerful channels of nonverbal communication. Facial expression has been a focus of emotion research for over a hundred years [12]. It is central to several leading theories of emotion [18, 31, 54] and has been the focus of at times heated debate about issues in emotion science [19, 24, 50]. Facial expression figures prominently in research on almost every aspect of emotion, including psychophys- iology [40], neural correlates [20], development [11], perception [4], addiction [26], social processes [30], depression [49] and other emotion disorders [55], to name a few. In general, facial expression provides cues bout emotional response, regulates interpersonal behavior, and communicates aspects of psychopathology. Because of its importance to behavioral science and the emerging fields of computational behavior science, perceptual computing, and human-robot interaction, significant efforts have been applied toward developing algorithms that automatically detect facial expression. With few exceptions, previous work on facial expression relies on supervised approaches to learning (i.e. event categories are defined in advance in labeled training data). While supervised learning has important advantages, two critical limitations may e noted. One, because labeling facial expression is highly labor intensive, progress in automated facial expression recognition and analysis is slowed. For the most detailed and comprehensive labeling or coding systems, such as Facial Action Coding System (FACS), three to four months is typically required to train coder (’coding’ refers to the labeling of video using behavioral descriptors). Once trained, each minute of video may require 1 hour or more to code [9]. No wonder relatively few databases are yet available," d42142285c46207a16bd4294e437d504e419a9b7,Varying image description tasks : spoken versus written descriptions,"Varying image description tasks: spoken versus written descriptions Emiel van Miltenburg Vrije Universiteit Amsterdam Ruud Koolen Tilburg University Emiel Krahmer Tilburg University" d44ca9e7690b88e813021e67b855d871cdb5022f,"Selecting, Optimizing and Fusing `Salient' Gabor Features for Facial Expression Recognition","QUT Digital Repository: http://eprints.qut.edu.au/ Zhang, Ligang and Tjondronegoro, Dian W. (2009) Selecting, optimizing and fusing ‘salient’ Gabor features for facial expression recognition. In: Neural Information Processing (Lecture Notes in Computer Science), 1-5 December 009, Hotel Windsor Suites Bangkok, Bangkok. © Copyright 2009 Springer-Verlag GmbH Berlin Heidelberg" d46b790d22cb59df87f9486da28386b0f99339d3,Learning Face Deblurring Fast and Wide,"Learning Face Deblurring Fast and Wide Meiguang Jin University of Bern Switzerland Michael Hirsch† Amazon Research Germany Paolo Favaro University of Bern Switzerland" d4712c75a1a51ecbc74e362747926a16a2cd36ed,Automated Human Recognition by Gait using Neural Network,"Image Processing Theory, Tools & Applications Automated Human Recognition by Gait using Neural Network Jang-Hee Yoo Information Security Research Division, ETRI S. Korea Ki-Young Moon Information Security Research Division, ETRI S. Korea" d497b9e50dc2aacfb1693ca4de6ebf904404d98d,Patch Based Approaches for the Recognition of Visual Object Classes - A Survey,"ALBERT-LUDWIGS-UNIVERSIT ¨AT FREIBURG INSTITUT F ¨UR INFORMATIK Lehrstuhl f¨ur Mustererkennung und Bildverarbeitung Patch Based Approaches for the Recognition of Visual Object Classes - A Survey Internal Report 2/06 Alexandra Teynor November, 2006" d444368421f456baf8c3cb089244e017f8d32c41,CNN for IMU assisted odometry estimation using velodyne LiDAR,"CNN for IMU Assisted Odometry Estimation using Velodyne LiDAR Martin Velas, Michal Spanel, Michal Hradis, and Adam Herout" d4f8168242f688af29bcbbe1cc5aec7cd12a601c,Edinburgh Research Explorer Visually Grounded Meaning Representations,"Visually Grounded Meaning Representations Citation for published version: Silberer, C, Ferrari, V & Lapata, M 2016, 'Visually Grounded Meaning Representations' IEEE Transactions on Pattern Analysis and Machine Intelligence. DOI: 10.1109/TPAMI.2016.2635138 Digital Object Identifier (DOI): 0.1109/TPAMI.2016.2635138 Link: Link to publication record in Edinburgh Research Explorer Document Version: Peer reviewed version Published In: IEEE Transactions on Pattern Analysis and Machine Intelligence General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) nd / or other copyright owners and it is a condition of accessing these publications that users recognise and bide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer ontent complies with UK legislation. If you believe that the public display of this file breaches copyright please ontact providing details, and we will remove access to the work immediately and" d4dd4600e8f4ecfd11fa4a4a702b1f08bc9ec6f7,Combining intention and emotional state inference in a dynamic neural field architecture for human-robot joint action,"Special issue on Grounding Emotions in Robots Combining intention and emotional state inference in a dynamic neural field architecture for human-robot joint action Adaptive Behavior 016, Vol. 24(5) 350–372 Ó The Author(s) 2016 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/1059712316665451 db.sagepub.com Rui Silva1, Luı´s Louro1, Tiago Malheiro1, Wolfram Erlhagen2 and Estela Bicho1" d409d8978034de5e5e8f9ee341d4a00441e3d05f,Annual research review: re-thinking the classification of autism spectrum disorders.,"Journal of Child Psychology and Psychiatry 53:5 (2012), pp 490–509 doi:10.1111/j.1469-7610.2012.02547.x Annual Research Review: Re-thinking the lassification of autism spectrum disorders Center for Autism and the Developing Brain, Weill-Cornell Medical College and New York Presbyterian Hospital/ Westchester Division, White Plains, NY, USA Catherine Lord and Rebecca M. Jones Background: The nosology of autism spectrum disorders (ASD) is at a critical point in history as the field seeks to better define dimensions of social-communication deficits and restricted/repetitive ehaviors on an individual level for both clinical and neurobiological purposes. These different dimensions also suggest an increasing need for quantitative measures that accurately map their dif- ferences, independent of developmental factors such as age, language level and IQ. Method: Psycho- metric measures, clinical observation as well as genetic, neurobiological and physiological research from toddlers, children and adults with ASD are reviewed. Results: The question of how to conceptu- lize ASDs along dimensions versus categories is discussed within the nosology of autism and the proposed changes to the DSM-5 and ICD-11. Differences across development are incorporated into the new classification frameworks. Conclusions: It is crucial to balance the needs of clinical practice in ASD diagnostic systems, with neurobiologically based theories that address the associations between social-communication and restricted/repetitive dimensions in individuals. Clarifying terminology," d8af6a45eaea68adda8597ae65f91ece152f7b21,Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation,"Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation Maximilian Jaritz1, 2, Raoul de Charette1, Emilie Wirbel2, Xavier Perrotton2, Fawzi Nashashibi1 {maximilian.jaritz, raoul.de-charette, Inria RITS Team {emilie.wirbel, Valeo" d809c0ab068861c139a544e5d8eeaa73cc8a3f6b,Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks,"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks Chenyang Lu1, Ren´e van de Molengraft2, and Gijs Dubbelman1" d8b568392970b68794a55c090c4dd2d7f90909d2,PDA Face Recognition System Using Advanced Correlation Filters,"PDA Face Recognition System Using Advanced Correlation Filters Chee Kiat Ng Advisor: Prof. Khosla/Reviere" d850aff9d10a01ad5f1d8a1b489fbb3998d0d80e,Recognizing and Segmenting Objects in the Presence of Occlusion and Clutter,"UNIVERSITY OF CALIFORNIA, IRVINE Recognizing and Segmenting Objects in the Presence of Occlusion and Clutter DISSERTATION submitted in partial satisfaction of the requirements for the degree of DOCTOR OF PHILOSOPHY in Computer Science Golnaz Ghiasi Dissertation Committee: Professor Charless Fowlkes, Chair Professor Deva Ramanan Professor Alexander Ihler" d8b3bebe39f5f69d68cdb5c04b44aba3f9b5ae02,Active Vision System with Human Detection Using RGB-D images and machine learning algorithms,"Active Vision System with Human Detection Using RGB-D images and machine learning algorithms Master’s thesis in Applied Physics and in Biomedical Engineering ANDREAS BERGGREN ERIC BJ ¨ORKLUND Department of Applied Mechanics Division of Vehicle Engineering and Autonomous Systems CHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2012 Master’s thesis 2012:28" d8c04365ed0627a5043996cdd26c1a56b5a630b8,Learning Monocular Depth Estimation with Unsupervised Trinocular Assumptions,"Learning monocular depth estimation with unsupervised trinocular assumptions Matteo Poggi, Fabio Tosi, Stefano Mattoccia University of Bologna, Department of Computer Science and Engineering Viale del Risorgimento 2, Bologna, Italy {m.poggi, fabio.tosi5," d8f0bda19a345fac81a1d560d7db73f2b4868836,Activity Understanding and Labeling in Natural Videos,"UNIVERSITY OF CALIFORNIA RIVERSIDE Online Activity Understanding and Labeling in Natural Videos A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Computer Science Md Mahmudul Hasan August 2016 Dissertation Committee: Dr. Amit K. Roy-Chowdhury, Chairperson Dr. Eamonn Keogh Dr. Evangelos Christidis Dr. Christian Shelton" d861c658db2fd03558f44c265c328b53e492383a,Automated face extraction and normalization of 3D Mesh Data,"Automated Face Extraction and Normalization of 3D Mesh Data Jia Wu1, Raymond Tse2, Linda G. Shapiro1" d881a59d00971c754e02bfaaf4c48ec6dfbc1343,Neighborhood Sensitive Mapping for Zero-Shot Classification using Independently Learned Semantic Embeddings,"Neighborhood Sensitive Mapping for Zero-Shot Classification using Independently Learned Semantic Embeddings Gaurav Singh1, Fabrizio Silvestri2, and John Shawe-Taylor1 UCL, UK Yahoo, UK" d813ec3a3442f2885b76ac0133c4c5d76f9f8065,Panoptic Studio: A Massively Multiview System for Social Interaction Capture,"Panoptic Studio: A Massively Multiview System for Social Interaction Capture Hanbyul Joo, Tomas Simon, Xulong Li, Hao Liu, Lei Tan, Lin Gui, Sean Banerjee, Timothy Godisart, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, and Yaser Sheikh" d88eb94d7054d2668b1a8dfa311721f37ae1f059,Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering,"Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering Medhini Narasimhan, Alexander G. Schwing University of Illinois Urbana-Champaign" d8b8e165279ca2091d5af1440ed974db4792250f,Mean Response-Time Minimization of a Soft-Cascade Detector, d83ae5926b05894fcda0bc89bdc621e4f21272da,Frugal Forests : Learning a Dynamic and Cost Sensitive Feature Extraction Policy for Anytime Activity Classification,"The Thesis committee for Joshua Allen Kelle certifies that this is the approved version of the following thesis: Frugal Forests: Learning a Dynamic and Cost Sensitive Feature Extraction Policy for Anytime Activity Classification APPROVED BY SUPERVISING COMMITTEE: Kristen Grauman, Supervisor Peter Stone" d81dbc2960e527e91c066102aabdaf9eb8b15f85,Deep Directed Generative Models with Energy-Based Probability Estimation,"Deep Directed Generative Models with Energy-Based Probability Estimation Taesup Kim, Yoshua Bengio∗ Department of Computer Science and Operations Research Université de Montréal Montréal, QC, Canada" d8671247f6188620c6e382ffcd15d3e909647c63,Multicamera human detection and tracking supporting natural interaction with large-scale displays,"DOI 10.1007/s00138-012-0408-6 ORIGINAL PAPER Multicamera human detection and tracking supporting natural interaction with large-scale displays Xenophon Zabulis · Dimitris Grammenos · Thomas Sarmis · Konstantinos Tzevanidis · Pashalis Padeleris · Panagiotis Koutlemanis · Antonis A. Argyros Received: 8 March 2011 / Revised: 9 January 2012 / Accepted: 17 January 2012 © Springer-Verlag 2012" d8904955fa93ad434f5156235ac94452eec57f64,Facial expression recognition in the wild based on multimodal texture features,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 4/20/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use FacialexpressionrecognitioninthewildbasedonmultimodaltexturefeaturesBoSunLiandongLiGuoyanZhouJunHeBoSun,LiandongLi,GuoyanZhou,JunHe,“Facialexpressionrecognitioninthewildbasedonmultimodaltexturefeatures,”J.Electron.Imaging25(6),061407(2016),doi:10.1117/1.JEI.25.6.061407." d827c72d6c9e35066b40bd205bbd71ce487a1c39,ENSEMBLE OF FACE / EYE DETECTORS FOR ACCURATE AUTOMATIC FACE DETECTION 1,"International Journal of Latest Research in Science Volume 4, Issue 3: Page No.8-18, May-June 2015 http://www.mnkjournals.com/ijlrst.htm nd Technology ISSN (Online):2278-5299 ENSEMBLE OF FACE/EYE DETECTORS FOR ACCURATE AUTOMATIC FACE DETECTION Loris Nanni, 2Alessandra Lumini, 3Sheryl Brahnam Department of Information Engineering at the University of Padua, Padua, Italy DISI, University of Bologna, Cesena, Italy Computer Information Systems, Missouri State University, USA" d853f490cd3d552d3a6d4a90d1b76c84e746a061,Hierarchically grouped 2D local features applied to edge contour localisation,"Liu, Yuan (2016) Hierarchically grouped 2D local features applied to edge contour localisation. PhD thesis http://theses.gla.ac.uk/7335/ Copyright and moral rights for this thesis are retained by the author A copy can be downloaded for personal non-commercial research or study, without prior permission or charge This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the Author The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the Author When referring to this work, full bibliographic details including the uthor, title, awarding institution and date of the thesis must be given. Glasgow Theses Service http://theses.gla.ac.uk/" d89cfed36ce8ffdb2097c2ba2dac3e2b2501100d,Robust Face Recognition via Multimodal Deep Face Representation,"Robust Face Recognition via Multimodal Deep Face Representation Changxing Ding, Student Member, IEEE, Dacheng Tao, Fellow, IEEE" d8f7b26d25a026fe43487b6f77993e11b8b333e0,Photo Indexing and Retrieval based on Content and Context,"PhD Dissertation International Doctorate School in Information and Communication Technologies DISI - University of Trento Photo Indexing and Retrieval ased on Content and Context Mattia Broilo Advisor: Prof. Francesco G. B. De Natale Universit`a degli Studi di Trento February 2011" d80564cea654d11b52c0008891a0fd2988112049,Semi-supervised Conditional GANs,"Semi-supervised Conditional GANs Kumar Sricharan∗1, Raja Bala1, Matthew Shreve1, Hui Ding1, Kumar Saketh2, and Jin Sun1 Interactive and Analytics Lab, Palo Alto Research Center, Palo Alto, CA Verizon Labs, Palo Alto, CA August 22, 2017" d8cfc7d9b13a5e1b21fc81e9f14697ac445c3698,Dynamic and Robust Object Tracking for Activity Recognition. (Suivi dynamique et robuste d'objets pour la reconnaissance d'activités),"Dynamic and Robust Object Tracking for Activity Recognition Duc Phu Chau To cite this version: Duc Phu Chau. Dynamic and Robust Object Tracking for Activity Recognition. Computer Vision nd Pattern Recognition [cs.CV]. Institut National de Recherche en Informatique et en Automatique (INRIA), 2012. English. HAL Id: tel-00695567 https://tel.archives-ouvertes.fr/tel-00695567 Submitted on 22 Nov 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" d888895cd56d336aa1367fac8072da782bdbc0fb,AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks,"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks Tao Xu∗1, Pengchuan Zhang2, Qiuyuan Huang2, Han Zhang3, Zhe Gan4, Xiaolei Huang1, Xiaodong He2 Lehigh University 2Microsoft Research 3Rutgers University 4Duke University {tax313, {penzhan, qihua," d8e8730231dc0e77f3ad61385f918df3d93bd266,Efficient face detection method with eye region judgment,"Lin and Lin EURASIP Journal on Image and Video Processing 2013, 2013:34 http://jivp.eurasipjournals.com/content/2013/1/34 R ES EAR CH Efficient face detection method with eye region judgment Chun-Fu Lin1,2 and Sheng-Fuu Lin1* Open Access" d84568d42a02b6d365889451f208f423edb1f0f3,Age Synthesis and Estimation From Face Image Ms,"www.ijecs.in International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 3 Issue 4 April, 2014 Page No. 5462-5466 Age Synthesis and Estimation From Face Image Ms. Deepali R. gadbail1, Prof. S.S. Dhande2, Prof.Kanchan M. Pimple3 M s. Deepali R Gadbail, Computer Science and Engineering Department, Sipna COET,Amravati. Prof. S. S. Dhande, Computer Science and Engineering Department, Sipna COET,Amravati. Prof.Kanchan M . Pimple, IBSS College of engg. & tech.,Amravati" d833c48334e906537f21757b6f9fa44da66f6c76,MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement,"MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang" d865c5e85191cfc0da714290d8583a2fb1179fd4,"Learning Hierarchical Space Tiling for Scene Modeling, Parsing and Attribute Tagging","Learning Hierarchical Space Tiling for Scene Modeling, Parsing and Attribute Tagging Shuo Wang, Yizhou Wang, and Song-Chun Zhu" d83c5c0fa648de9ea0f8f6f92ce2096d5fa04808,Multi-appearance segmentation and extended 0-1 programming for dense small object tracking,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, JULY 2016 Multi-appearance Segmentation and Extended 0-1 Program for Dense Small Object Tracking Longtao Chen, Jing Lou, Wei Zhu, Qingyuan Xia, Mingwu Ren" d87ccfc42cf6a72821d357aab0990e946918350b,Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search,"Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search Masanori Suganuma 1 2 Mete Ozay 1 Takayuki Okatani 1 2" d88d43504f2be7e26ab1ec731dfc8af6e407aa59,"Model-based Optical Flow: Layers, Learning, and Geometry","Model-based Optical Flow: Layers, Learning, and Geometry Dissertation der Mathematisch-Naturwissenschaftlichen Fakult¨at der Eberhard Karls Universit¨at T¨ubingen zur Erlangung des Grades eines Doktors der Naturwissenschaften (Dr. rer. nat.) vorgelegt von Dipl.-Ing. Jonas Wulff us Warburg (Westfalen) T¨ubingen" d84263e22c7535cb1a2a72c88780d5a407bd9673,Stability of Scattering Decoder For Nonlinear Diffractive Imaging,"Stability of Scattering Decoder for Nonlinear Diffractive Imaging Yu Sun1 and Ulugbek S. Kamilov1,2 Department of Computer Science & Engineering, Washington University in St Louis. Department of Electrical & Systems Engineering, Washington University in St. Louis" d88e3d5ca820cb240de4b662f0a6fd1172a678c7,Image Quality-based Adaptive Illumination Normalisation for Face Recognition,"Harin Sellahewa and Sabah A. Jassim, ""Image quality-based adaptive illumination normalisation for face recognition"", Proc. SPIE 7306, Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI, 73061V (May 05, 2009); doi:10.1117/12.819087; http://dx.doi.org/10.1117/12.819087 Copyright 2009 Society of Photo Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for ommercial purposes, or modification of the content of the paper are prohibited.” (http://spie.org/x1125.xml)" d86478cb6c79d8b6c74e6caeb20c7456266cf50e,Statistical Transformation Techniques for Face Verification Using Faces Rotated in Depth,"STATISTICAL TRANSFORMATION TECHNIQUES FOR FACE VERIFICATION USING FACES ROTATED IN DEPTH Conrad Sanderson (a) Samy Bengio (b) IDIAP–RR 04-04 FEBRUARY 2004 SUBMITTED FOR PUBLICATION D a l l e M o l l e I n s t i t u t e f o r P e r c e p t u a l A r t i f i c i a l Intelligence • P.O.Box 592 • Martigny • Valais • Switzerland phone +41 − 27 − 721 77 11 +41 − 27 − 721 77 12 e-mail internet http://www.idiap.ch" d8b58c5b403dc28437af8244ec812efdfbc6b2e0,MVOR: A Multi-view RGB-D Operating Room Dataset for 2D and 3D Human Pose Estimation,"MVOR: A Multi-view RGB-D Operating Room Dataset for 2D and 3D Human Pose Estimation Vinkle Srivastav1, Thibaut Issenhuth1, Abdolrahim Kadkhodamohammadi1, Michel de Mathelin1, Afshin Gangi1,2, and Nicolas Padoy1 ICube, University of Strasbourg, CNRS, IHU Strasbourg, France Radiology Department, University Hospital of Strasbourg, France" d8abf01fce0d44665949e7a73716fff7731fa6da,Places: An Image Database for Deep Scene Understanding,"Places: An Image Database for Deep Scene Understanding Bolei Zhou, Aditya Khosla, Agata Lapedriza, Antonio Torralba and Aude Oliva" d8db46f1775641051d8596dad3d37d1d731558f7,Survey on Deep Learning Techniques for Person Re-Identification Task, 5bfc32d9457f43d2488583167af4f3175fdcdc03,ijsr . net Local Gray Code Pattern ( LGCP ) : A Robust Feature Descriptor for Facial Expression Recognition,"International Journal of Science and Research (IJSR), India Online ISSN: 2319-7064 Local Gray Code Pattern (LGCP): A Robust Feature Descriptor for Facial Expression Recognition Mohammad Shahidul Islam Atish Dipankar University of Science & Technology, School, Department of Computer Science and Engineering, Dhaka, Bangladesh." 5bed19eaba0a6667e16859de8b78173e99568e1f,Deep Neural Networks In Fully Connected CRF For Image Labeling With Social Network Metadata,"Deep Neural Networks In Fully Connected CRF For Image Labeling With Social Network Metadata Chengjiang Long Kitware Inc. Roddy Collins Eran Swears Anthony Hoogs {chengjiang.long, roddy.collins, eran.swears, 8 Corporate Drive, Clifton Park, NY 12065" 5b01d4338734aefb16ee82c4c59763d3abc008e6,A Robust Face Recognition Algorithm Based on Kernel Regularized Relevance-Weighted Discriminant Analysis,"DI WU: A ROBUST FACE RECOGNITION ALGORITHM BASED ON KERNEL REGULARIZED RELEVANCE … A Robust Face Recognition Algorithm Based on Kernel Regularized Relevance-Weighted Discriminant Analysis Di WU 1, 2 2 Hunan Provincial Key Laboratory of Wind Generator and Its Control, Hunan Institute of Engineering, Xiangtan, China. College of Electrical and Information Engineering, [e-mail: I. INTRODUCTION interface and security recognition their this paper, we propose an effective" 5b14abbea83270282ef94fcf3f3a73e7d8fee023,Experiments about the Generalization Ability of Common Vector based methods for Face Recognition,"Experiments about the Generalization Ability of Common Vector based methods for Face Recognition ? Marcelo Armengot, Francesc J. Ferri, and Wladimiro D´ıaz Dept. d’Inform`atica, Universitat de Val`encia Dr Moliner, 50 46100 Burjassot, Spain" 5b25b9053ceafe1cf8258d8daa818a2da80c800f,Assigning affinity-preserving binary hash codes to images,"Assigning af‌f‌inity-preserving inary hash codes to images Jason Filippou Varun Manjunatha June 10, 2014" 5bb87c7462c6c1ec5d60bde169c3a785ba5ea48f,Targeting Ultimate Accuracy: Face Recognition via Deep Embedding,"Targeting Ultimate Accuracy: Face Recognition via Deep Embedding Jingtuo Liu Yafeng Deng Tao Bai Zhengping Wei Chang Huang Baidu Research – Institute of Deep Learning" 5b3dc81a490b1d9e69d7be20c4e8e1de886b5ca3,Improving Object Localization with Fitness NMS and Bounded IoU Loss,"Improving Object Localization with Fitness NMS and Bounded IoU Loss Lachlan Tychsen-Smith, Lars Petersson CSIRO (Data61) CSIRO-Synergy Building, Acton, ACT, 2601" 5bc5cfc2622f6b0a0003d7b115726d075205a2cc,AUTO LANDING PROCESS FOR AUTONOMOUS FLYING ROBOT BY USING IMAGE PROCESSING BASED ON EDGE DETECTION,"AUTO LANDING PROCESS FOR AUTONOMOUS FLYING ROBOT BY USING IMAGE PROCESSING BASED ON EDGE DETECTION Bahram Lavi Sefidgari1 and Sahand Pourhassan Shamchi2 Department of Computer Engineering, EMU, Famagusta, Cyprus Department of Mechanical Engineering, EMU, Famagusta, Cyprus" 5b516862b93052cc2335d78a832641a38304beed,Foresee: Attentive Future Projections of Chaotic Road Environments with Online Training,"Foresee: Attentive Future Projections of Chaotic Road Environments with Online Training Indraprastha Institute of Information Technology, Delhi Anil Sharma and Prabhat Kumar {anils," 5b73bc1660b7eef0c12694db935854dba0829f9e,A Probabilistic Model for Face Transformation with Application to Person Identification,"EURASIP Journal on Applied Signal Processing 2004:4, 510–521 (cid:1) 2004 Hindawi Publishing Corporation A Probabilistic Model for Face Transformation with Application to Person Identification Florent Perronnin Multimedia Communications Department, Institut Eur´ecom, BP 193, 06904 Sophia Antipolis Cedex, France Email: Jean-Luc Dugelay Multimedia Communications Department, Institut Eur´ecom, BP 193, 06904 Sophia Antipolis Cedex, France Email: Kenneth Rose Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA 93106-9560, USA Email: Received 30 October 2002; Revised 23 June 2003 A novel approach for content-based image retrieval and its specialization to face recognition are described. While most face recog- nition techniques aim at modeling faces, our goal is to model the transformation between face images of the same person. As a global face transformation may be too complex to be modeled directly, it is approximated by a collection of local transforma- tions with a constraint that imposes consistency between neighboring transformations. Local transformations and neighborhood onstraints are embedded within a probabilistic framework using two-dimensional hidden Markov models (2D HMMs). We fur- ther introduce a new ef‌f‌icient technique, called turbo-HMM (T-HMM) for approximating intractable 2D HMMs. Experimental" 5bcff482bd9652420f8f6b0e6e58ab59a562046e,Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-Identification,"Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification Ruimao Zhang, Liang Lin, Rui Zhang, Wangmeng Zuo, and Lei Zhang" 5b818c73ce5681e523d6fe9ed8603c7afc0a9089,Improving Shape Retrieval by Spectral Matching and Meta Similarity,"Improving Shape retrieval by Spectral Matching and Meta Similarity Amir Egozi (BGU), Yosi Keller (BIU) nd Hugo Guterman (BGU) Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev / 21" 5b3eee498ba40423536c3ca487f7ac10d94092d2,Multimodal fusion of polynomial classifiers for automatic person recognition,"Multimodal fusion of polynomial classifiers for automatic person recognition Charles C. Brouna and Xiaozheng Zhangb Motorola Labs – Human Interface Lab, Phoenix, Arizona The Georgia Institute of Technology, Atlanta, Georgia" 5b9d9f5a59c48bc8dd409a1bd5abf1d642463d65,An evolving spatio-temporal approach for gender and age group classification with Spiking Neural Networks,"(will be inserted by the editor) An evolving spatio-temporal approach for gender and age group classification with Spiking Neural Networks Fahad Bashir Alvi, Russel Pears, Nikola Kasabov Received: date / Accepted: date" 5bae9822d703c585a61575dced83fa2f4dea1c6d,MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking,"MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking Laura Leal-Taix´e∗, Anton Milan∗, Ian Reid, Stefan Roth, and Konrad Schindler" 5be74c6fa7f890ea530e427685dadf0d0a371fc1,Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification,"Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification Lin Wu, Yang Wang, Junbin Gao, Dacheng Tao, Fellow, IEEE" 5b6c603fba0a66fb3c037632079bdca82ec3bf91,Alternating Co-Quantization for Cross-Modal Hashing,"Alternating Co-Quantization for Cross-modal Hashing Go Irie Hiroyuki Arai Yukinobu Taniguchi NTT Corporation {irie.go, arai.hiroyuki," 5bfde88767331eee8f06b296791d21e2260deee0,Les modèles génératifs en classification supervisée et applications à la catégorisation d'images et à la fiabilité industrielle. (Generative models in supervised statistical learning with applications to digital image categorization and structural reliability),"Universit´e Joseph Fourier – Grenoble 1 Les mod`eles g´en´eratifs en classification supervis´ee et applications `a la at´egorisation d’images et `a la fiabilit´e industrielle. TH`ESE Soutenance en 2005 pour l’obtention du Doctorat de l’universit´e Joseph Fourier – Grenoble 1 (sp´ecialit´e math´ematiques appliqu´ees) Guillaume Bouchard Composition du jury Directeur de thèse : Gilles Celeux INRIA Co-directeur de thèse : William Triggs CNRS Institut National Recherche en Informatique et Automatique" 5bf9493564d1ed173aee4dc701d4e62d5f926fe3,Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics using CNNs,"Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics using CNNs Andres Milioto Cyrill Stachniss" 5b7870359b8b9934453f8e772ab7c3f9df3a5035,LF Indoor Location and Identification System,"LF Indoor Location and Identification System Antti Ropponen, Matti Linnavuo, Raimo Sepponen Helsinki University of Technology Department of Electronics PL 3340, 02015 TKK Finland Emails:" 5b94093939ac42aba54ab41eb1725aeba1bd5c34,Aalborg Universitet RGB-D Segmentation of Poultry,"Aalborg Universitet RGB-D Segmentation of Poultry Entrails Philipsen, Mark Philip; Jørgensen, Anders; Guerrero, Sergio Escalera; Moeslund, Thomas B. Published in: IX International Conference on Articulated Motion and Deformable Objects DOI (link to publication from Publisher): 0.1007/978-3-319-41778-3_17 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Philipsen, M. P., Jørgensen, A., Guerrero, S. E., & Moeslund, T. B. (2016). RGB-D Segmentation of Poultry Entrails. In IX International Conference on Articulated Motion and Deformable Objects (pp. 168-174). Springer. (Lecture Notes in Computer Science, Vol. 9756). DOI: 10.1007/978-3-319-41778-3_17 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain" 5b0552a8e0ffdf1b6e7f2573640f888815391dec,Part-level fully convolutional networks for pedestrian detection,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" 5ba51674897afa2a1bc0646fddada7510bd9c0ce,Video-based face recognition evaluation in the CHIL project - Run 1,"Video-Based Face Recognition Evaluation in the CHIL Project – Run 1 Hazım Kemal Ekenel Universität Karlsruhe (TH) Interactive Systems Labs 76131, Karlsruhe, Germany Aristodemos Pnevmatikakis Athens Information Technology Autonomic and Grid Computing Group 9002, Peania, Athens, Greece" 5b9c849c2acbdea6e3cfc730def4f083f169521c,A Method for Face Detection based on Wavelet Transform and optimised feature selection using Ant Colony Optimisation in Support Vector Machine,"ISSN (Print) : 2320 – 9798 ISSN (Online) : 2320 – 9801 International Journal of Innovative Research in Computer and Communication Engineering Vol. 1, Issue 2, April 2013 A Method for Face Detection based on Wavelet Transform and optimised feature selection using Ant Colony Optimisation in Support Vector Machine Sanjay Kumar Pal1, Uday Chourasia 2 and Manish Ahirwar3 Department of CSE, University Institute of Technology, RGPV, Bhopal, India1,2,3" 5b1d78b160560db5f581e65289ce5e2f99eb9b1f,Twitter100k: A Real-World Dataset for Weakly Supervised Cross-Media Retrieval,"Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval Yuting Hu, Liang Zheng, Yi Yang, and Yongfeng Huang" 5b3725c8b5e058ec3a383b621aa9316b90738b2e,Gaussian Conditional Random Field Network for Semantic Segmentation,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Gaussian Conditional Random Field Network for Semantic Segmentation Vemulapalli, R.; Tuzel, C.O.; Liu, M.-Y.; Chellappa, R. TR2016-078 June 2016" 5bf4f97b631937b2176db9c80dee965e2e2286be,From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process,"From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process Yannick Le Cacheux Herv´e Le Borgne CEA LIST CEA LIST Michel Crucianu CEDRIC Lab – CNAM September 27, 2018" 5be3cc1650c918da1c38690812f74573e66b1d32,Relative Parts: Distinctive Parts for Learning Relative Attributes,"Relative Parts: Distinctive Parts for Learning Relative Attributes Ramachandruni N. Sandeep Yashaswi Verma C. V. Jawahar Center for Visual Information Technology, IIIT Hyderabad, India - 500032" 5b7c0f8ae03e23573049e71329a4ba4166d016c9,Learning Context For Semantic Segmentation and Applications,"Dissertation Learning Context For Semantic Segmentation And Applications Vladimir Haltakov Technische Universit¨at M ¨unchen Department of Computer Science Chair for Computer Aided Medical Procedures and Augmented Reality ampar.cs.tum.edu" 5bca2c751526665469e9e405d6143d13e7472f7d,Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors,"Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors Rico Jonschkowski, Divyam Rastogi, and Oliver Brock Robotics and Biology Laboratory, Technische Universit¨at Berlin, Germany" 5be6340c55d4a45e96e811bdeac3972328ca9247,People Identification and Tracking Through Fusion of Facial and Gait Features,"Original citation: Guan, Yu (Researcher in Computer Science), Wei, Xingjie, Li, Chang-Tsun and Keller, Y. (2014) People identification and tracking through fusion of facial and gait features. In: Cantoni, Virginio and Dimov, Dimo and Tistarell, Massimo, (eds.) Biometric Authentication : First International Workshop, BIOMET 2014, Sofia, Bulgaria, June 23- 4, 2014. Revised Selected Papers. Lecture Notes in Computer Science . Springer International Publishing, pp. 209-221. ISBN 9783319133850 Permanent WRAP url: http://wrap.warwick.ac.uk/65110 Copyright and reuse: The Warwick Research Archive Portal (WRAP) makes this work by researchers of the University of Warwick available open access under the following conditions. Copyright © nd all moral rights to the version of the paper presented here belong to the individual uthor(s) and/or other copyright owners. To the extent reasonable and practicable the material made available in WRAP has been checked for eligibility before being made vailable. Copies of full items can be used for personal research or study, educational, or not-for profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way." 5b6bdf478860b1e3f797858e71abd14f98684b61,Distributed neural computation for the visual perception of motion. (Calcul neuronal distribué pour la perception visuelle du mouvement),"Distributed neural computation for the visual perception of motion Mauricio Cerda To cite this version: Mauricio Cerda. Distributed neural computation for the visual perception of motion. Computer science. Universit´e Nancy II, 2011. English. HAL Id: tel-00642818 https://tel.archives-ouvertes.fr/tel-00642818 Submitted on 18 Nov 2011 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires" 5ba7882700718e996d576b58528f1838e5559225,Predicting Personalized Image Emotion Perceptions in Social Networks,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TAFFC.2016.2628787, IEEE Transactions on Affective Computing IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, VOL. X, NO. X, OCTOBER 2016 Predicting Personalized Image Emotion Perceptions in Social Networks Sicheng Zhao, Hongxun Yao, Yue Gao, Senior Member, IEEE, Guiguang Ding and Tat-Seng Chua" 5b6f0a508c1f4097dd8dced751df46230450b01a,Finding lost children,"Finding Lost Children Ashley Michelle Eden Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2010-174 http://www.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-174.html December 20, 2010" 5ba1db56bccc090ce5eceb13f46f2cd15ba3aa55,Interpretable Counting for Visual Question Answering,"Under review as a conference paper at ICLR 2018 INTERPRETABLE COUNTING IN VISUAL QUESTION ANSWERING Anonymous authors Paper under double-blind review" 5bb14bba7510c590164007d7e3aa1bf88cb3faec,Learning to Match Appearances by Correlations in a Covariance Metric Space,"Learning to Match Appearances by Correlations in a Covariance Metric Space Sªawomir B¡k, Guillaume Charpiat, Etienne Corvée, François Brémond, Monique Thonnat INRIA Sophia Antipolis, STARS group 004, route des Lucioles, BP93 06902 Sophia Antipolis Cedex - France" f5083b4e28e42a2da7bafd2a742ab8e21c12559f,Deep Learning for Automated Image Classification of Seismic Damage to Built Infrastructure,"Eleventh U.S. National Conference on Earthquake Engineering Integrating Science, Engineering & Policy June 25-29, 2018 Los Angeles, California DEEP LEARNING FOR AUTOMATED IMAGE CLASSIFICATION OF SEISMIC DAMAGE TO BUILT INFRASTRUCTURE B. Patterson1 , G. Leone1, M. Pantoja1, and A. Behrouzi2" f580b0e1020ad67bdbb11e8d99a59c21a8df1e7d,Compressed Sensing using Generative Models,"Compressed Sensing using Generative Models Ashish Bora∗ Ajil Jalal† Eric Price‡ Alexandros G. Dimakis§" f553f8022b1417bc7420523220924b04e3f27b8e,Finding your Lookalike: Measuring Face Similarity Rather than Face Identity,"Finding your Lookalike: Measuring Face Similarity Rather than Face Identity Amir Sadovnik, Wassim Gharbi, Thanh Vu Lafayette College Easton, PA Andrew Gallagher Google Research Mountain View, CA" f5770dd225501ff3764f9023f19a76fad28127d4,Real Time Online Facial Expression Transfer with Single Video Camera,"Real Time Online Facial Expression Transfer with Single Video Camera" f5748711db00d82469ff60e05f62319f1eac90c5,Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset,"Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset Zachary Pezzementi∗ Trenton Tabor∗ Peiyun Hu† Jonathan K. Chang∗ Deva Ramanan† Carl Wellington∗ Benzun P. Wisely Babu∗ Herman Herman∗" f5c83679b73ab59c2ada2b72610acdd63669b226,2D-3D Pose Invariant Face Recognition System for Multimedia Applications,"D-3D POSE INVARIANT FACE RECOGNITION SYSTEM FOR MULTIMEDIA APPLICATIONS Authors: Antonio Rama1, Francesc Tarrés1 Jürgen Rurainsky2 {tonirama, Department of Signal Theory and Communications Universitat Politècnica de Catalunya (UPC) Image Processing Department Fraunhofer Institute for Telecommunications Heinrich-Hertz-Institut (HHI) Automatic Face recognition of people is a challenging problem which has re- eived much attention during the recent years due to its potential multimedia ap- plications in different fields such as 3D videoconference, security applications or video indexing. However, there is no technique that provides a robust solution to ll situations and different applications, yet. Face recognition includes a set of hallenges like expression variations, occlusions of facial parts, similar identities, resolution of the acquired images, aging of the subjects and many others. Among ll these challenges, most of the face recognition techniques have evolved in order to overcome two main problems: illumination and pose variation. Either of these" f541dac9d0d49cadb3cfd018e87b26e03e3f13aa,Trio Constrained Adaptive Noise Removal ( TCANR ) Mechanism for Salt and Pepper Noise in Image Classification,"International Journal of Advanced Research in Computer and Communication Engineering IJARCCE ISSN (Online) 2278-1021 ISSN (Print) 2319 5940 ISO 3297:2007 Certified Vol. 6, Issue 3, March 2017 Trio Constrained Adaptive Noise Removal (TCANR) Mechanism for Salt and Pepper Noise in Image Classification G Muthu Krishnan1, Capt.Dr.S.Santhosh Baboo2 Research Scholar, Dravidian University, Kuppam1 Associate Professor, P.G. & Research Department of Computer science, D.G. Vaishnav College, Chennai2" f5050ffebf973d4d848049dcf661891acd950b82,"Face and object discrimination in autism, and relationship to IQ and age.","J Autism Dev Disord DOI 10.1007/s10803-013-1955-z O R I G I N A L P A P E R Face and Object Discrimination in Autism, and Relationship to IQ nd Age Pamela M. Pallett • Shereen J. Cohen • Karen R. Dobkins Ó Springer Science+Business Media New York 2013 faces, yet" f5adb841e30eb635b91e95c03575f3b8767c9ed5,Learning Optimal Parameters For Multi-target Tracking,"WANG, FOWLKES: LEARNING MULTI-TARGET TRACKING Learning Optimal Parameters For Multi-target Tracking Shaofei Wang Charless Fowlkes Dept of Computer Science University of California Irvine, CA, USA" f51771c6cd9061acc9c468e7b44d5d3b6c552b32,"Sparse Representation, Discriminative Dictionaries and Projections for Visual Classification", f558a3812106764fb1af854a02da080cc42c197f,Amygdala volume and nonverbal social impairment in adolescent and adult males with autism.,"ORIGINAL ARTICLE Amygdala Volume and Nonverbal Social Impairment in Adolescent and Adult Males With Autism Brendon M. Nacewicz, BS; Kim M. Dalton, PhD; Tom Johnstone, PhD; Micah T. Long, BS; Emelia M. McAuliff, BS; Terrence R. Oakes, PhD; Andrew L. Alexander, PhD; Richard J. Davidson, PhD Background: Autism is a syndrome of unknown cause, marked by abnormal development of social behavior. At- tempts to link pathological features of the amygdala, which plays a key role in emotional processing, to autism have shown little consensus. Objective: To evaluate amygdala volume in individu- ls with autism spectrum disorders and its relationship to laboratory measures of social behavior to examine whether variations in amygdala structure relate to symp- tom severity. Design: We conducted 2 cross-sectional studies of amyg- dala volume, measured blind to diagnosis on high- resolution, anatomical magnetic resonance images. Par- ticipants were 54 males aged 8 to 25 years, including 23 with autism and 5 with Asperger syndrome or pervasive" f5bd11c5c5a455df04b171e37acd1fbdbf3dacd5,African American and Caucasian males ' evaluation of racialized female facial averages,"UNLV Theses, Dissertations, Professional Papers, and Capstones 5-2010 African American and Caucasian males' evaluation of racialized female facial averages Rhea M. Watson University of Nevada Las Vegas Follow this and additional works at: http://digitalscholarship.unlv.edu/thesesdissertations Part of the Cognition and Perception Commons, Race and Ethnicity Commons, and the Social Psychology Commons Repository Citation Watson, Rhea M., ""African American and Caucasian males' evaluation of racialized female facial averages"" (2010). UNLV Theses, Dissertations, Professional Papers, and Capstones. 366. http://digitalscholarship.unlv.edu/thesesdissertations/366 This Thesis is brought to you for free and open access by Digital It has been accepted for inclusion in UNLV Theses, Dissertations, Professional Papers, and Capstones by an authorized administrator of Digital For more information, please contact" f56674e6a4d89bf8855499eea0a043fa14fead70,Prediction of Pedestrian Trajectories Final Report,"Prediction of Pedestrian Trajectories Final Report Mingchen Li (limc), Yiyang Li (yiyang7), Gendong Zhang (zgdsh29) December 15, 2017 Introduction As the industry of automotive vehicles growing rapidly, the ability of those vehicles to predict trajectories of pedestrians becomes more crucial than ever. Any autonomous vehicle navigating such a scene should e able to foresee the future positions of pedestrians and accordingly adjust its path to avoid collisions [1]. As stated in [1], this trajectory prediction problem can be viewed as a sequence generation task, where we are interested in predicting the future trajectory of people based on their past positions. In this project, we present comparisons among the performances of different machine learning models. The input to our algorithm is arbitrary number of people’s previous positions in x-y coordinates and the output is the people’s next position. The methods been applied are K-Nearest Neighbors (KNN) ombined with linear regression, Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU). The latter two are different cell types of Recurrent Neural Network (RNN). Related Works The problem of predicting pedestrian trajectories has been studied by many research groups around the world for decades and many models have been proposed. Some groups used traditional machine learning algorithms by fitting data into different models, such as Gaussian mixture model [2], Mixed Markov-chain model [3], and Gaussian process regression [4]. Other groups considered the social forces etween pedestrians. Helbing et. al. [5] modeled pedestrian motions with attractive and repulsive forces." f56edb6f2bf4f5bc9d54284289212b8d4a437c1b,Detection and Localization of Texture-less Objects with Deep Neural Networks,"Bachelor Thesis Czech Technical University in Prague Faculty of Electrical Engineering Department of Cybernetics Detection and Localization of Texture-less Objects with Deep Neural Networks Pavel Haluza Supervisor: Ing. Tomáš Hodaň May 2017" f5c99652c4c89e56156faf2bed361a15de6162d5,Towards Large-Scale Multimedia Retrieval Enriched by Knowledge about Human Interpretation Retrospective Survey,"Noname manuscript No. (will be inserted by the editor) Towards Large-Scale Multimedia Retrieval Enriched y Knowledge about Human Interpretation Retrospective Survey Kimiaki Shirahama · Marcin Grzegorzek Received: date / Accepted: date" f565ac8e175e4659fadd3b5b6507ebac2d90a2b7,Interpretable Visual Question Answering by Reasoning on Dependency Trees,"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. X, NO. X, XXX Interpretable Visual Question Answering by Reasoning on Dependency Trees Qingxing Cao, Xiaodan Liang, Bailin Li and Liang Lin" b8a5839f6b1e051f430f2b89d5a1a7e49a10655a,DCFNet: Deep Neural Network with Decomposed Convolutional Filters,"DCFNet: Deep Neural Network with Decomposed Convolutional Filters Qiang Qiu 1 Xiuyuan Cheng 1 Robert Calderbank 1 Guillermo Sapiro 1" b8a53daa97fb917a89c351c47f0b197573e20023,Recognizing Faces---An Approach Based on Gabor Wavelets,"Recognizing Faces --- An Approach Based on Gabor Wavelets By LinLin Shen, BSc, MSc Thesis submitted to the University of Nottingham for the degree of Doctor of Philosophy July 2005" b86d16c9df3791ed29ae8219ac419447fde82270,PART-BASED PEDESTRIAN DETECTION AND TRACKING USING HOG-SVM CLASSIFICATION Miss .,"A. Sanofer Nisha et al, International Journal of Computer Science and Mobile Applications, Vol.2 Issue. 1, January- 2014, pg. 142-155 ISSN: 2321-8363 PART-BASED PEDESTRIAN DETECTION AND TRACKING USING HOG-SVM CLASSIFICATION Miss. A. Sanofer Nisha(1) Mrs. K. Thulasimani(2) ME II Year AP/CSE Department of Computer Science and Department of Computer Science and Engineering Engineering Government College of Engineering Government College of Engineering Tirunelveli Tirunelveli" b8ad1f7e5753473e3d5231a08c980fc2bae3af0b,Image Background Matching for Identifying Suspects,"Chapter 24 IMAGE BACKGROUND MATCHING FOR IDENTIFYING SUSPECTS Paul Fogg, Gilbert Peterson and Michael Veth" b8969d6e5658b360111f33d3f85eac63afcd7252,WESPE: Weakly Supervised Photo Enhancer for Digital Cameras,"WESPE: Weakly Supervised Photo Enhancer for Digital Cameras Andrey Ignatov, Nikolay Kobyshev, Kenneth Vanhoey, Radu Timofte, Luc Van Gool ETH Zurich {andrey, nk, vanhoey, timofter," b87eeb3b873d27c68a5a1cdfd9409c14db352d92,Hierarchical Cellular Automata for Visual Saliency,"Noname manuscript No. (will be inserted by the editor) Hierarchical Cellular Automata for Visual Saliency Yao Qin* · Mengyang Feng* · Huchuan Lu · Garrison W. Cottrell Received: date / Accepted: date" b8abc0573208786550e0bfbce4bbcac9d048537e,Context-Patch for Difficult Face Recognition Anonymous ICB 2012 submission,"CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. Context-Patch for Difficult Face Recognition Anonymous ICB 2012 submission" b8f09ff53e5a1700492100b8cd1b9e9783485376,Clustered Multitask Feature Learning for Attribute Prediction Anonymous CVPR submission,"#1105 CVPR 2016 Submission #1105. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. #1105 Clustered Multi-task Feature Learning for Attribute Prediction Anonymous CVPR submission Paper ID 1105" b8612b5c1aa0970b5d99340ad19d7fcede1b0854,"Fusion of Speech, Faces and Text for Person Identification in TV Broadcast","Fusion of speech, faces and text for person identification in TV broadcast Herv´e Bredin1, Johann Poignant2, Makarand Tapaswi3, Guillaume Fortier4, Viet Bac Le5, Thibault Napoleon6, Hua Gao3, Claude Barras1, Sophie Rosset1, Laurent Besacier2, Jakob Verbeek4, Georges Qu´enot2, Fr´ed´eric Jurie6, and Hazim Kemal Ekenel3 Univ Paris-Sud / CNRS-LIMSI UPR 3251, BP 133, F-91403 Orsay, France UJF-Grenoble 1 / UPMF-Grenoble 2 / Grenoble INP / CNRS-LIG UMR 5217, F-38041 Grenoble, France Karlsruher Institut fur Technologie, Karlsruhe, Germany INRIA Rhone-Alpes, 655 Avenue de lEurope, F-38330 Montbonnot, France 5 Vocapia Research, 3 rue Jean Rostand, Parc Orsay Universit´e, F-91400 Orsay, 6 Universit´e de Caen / GREYC UMR 6072, F-14050 Caen Cedex, France France" b800f6b02c32c54cb07e6b8655171bbb2ca5cc0e,Computer Vision : Visual Extent of an Object,"IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661, p- ISSN: 2278-8727Volume 14, Issue 4 (Sep. - Oct. 2013), PP 22-27 www.iosrjournals.org Computer Vision: Visual Extent of an Object Akshit Chopra1, Ayushi Sharma2 (Department Of Computer Science, Maharaja Surajmal Institute Of Technology – Guru Gobind Singh (Department Of Computer Science, Maharaja Surajmal Institute Of Technology – Guru Gobind Singh Indraprastha University, India) Indraprastha University, India)" b85901174fa83c76ae994603228ba5b4f299a1af,"SOS, LOST IN A HIGH DIMENSIONAL SPACE","SOS, LOST IN A HIGH DIMENSIONAL SPACE Anne Hendrikse" b85580ff2d8d8be0a2c40863f04269df4cd766d9,HCMUS team at the Multimodal Person Discovery in Broadcast TV Task of MediaEval 2016,"HCMUS team at the Multimodal Person Discovery in Broadcast TV Task of MediaEval 2016 Vinh-Tiep Nguyen, Manh-Tien H. Nguyen, Quoc-Huu Che, Van-Tu Ninh, Tu-Khiem Le, Thanh-An Nguyen, Minh-Triet Tran Faculty of Information Technology University of Science, Vietnam National University-Ho Chi Minh city {nhmtien, cqhuu, nvtu," b8b46df1b013c30d791972ee109425a94e3adc06,"Automaticity , Control , and the Social Brain","C H A P T E R 1 9 Automaticity, Control, nd the Social Brain Robert P. Spunt and Matthew D. Lieberman The social world is good at keeping the human brain busy, posing cognitive chal- lenges that are complex, frequent, and enor- mously important to our well-being. In fact, the computational demands of the social world may be the principal reason why the human brain has evolved to its present form and function relative to other primates (Dunbar, 1993). Importantly, the human rain is often able to make sense of the social world without having to do too much work. This is because many of its processes re automatically initiated by the presence of relevant social stimuli and run to comple- tion without much, if any, conscious inter- vention (Bargh & Chartrand, 1999; Gilbert," b878518814fee31ce8cb61040301e7a921892156,A Gaussian Feature Adaptive Integrated PCA-ICA Approach for Facial Recognition,"Vaishali et al, International Journal of Computer Science and Mobile Computing, Vol.4 Issue.5, May- 2015, pg. 401-406 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 5, May 2015, pg.401 – 406 RESEARCH ARTICLE ISSN 2320–088X A Gaussian Feature Adaptive Integrated PCA-ICA Approach for Facial Recognition Student, Dept. of ECE, ITM University Gurgaon Haryana Vaishali Dr. Rekha Vig Asstt. Prof, Dept. of ECE, ITM University Gurgaon Haryana" b856c493c2e5cbb71791f56763886e5e0d40295c,Unsupervised Domain Adaptive Re-Identification: Theory and Practice,"Unsupervised Domain Adaptive Re-Identification: Theory and Practice Liangchen Song12∗ Cheng Wang23∗ Lefei Zhang1 Bo Du1 Qian Zhang2 Chang Huang2 Xinggang Wang3 Wuhan University 2Horizon Robotics Huazhong Univ. of Science and Technology" b86bcc153e097838fdb31ffa6c363f1d883512ae,ON-LINE UNSUPERVISED ADAPTATION FOR FACE VERIFICATION USING GAUSSIAN MIXTURE MODELS WITH MULTIPLE USER MODELS,"ON-LINE UNSUPERVISED ADAPTATION FOR FACE VERIFICATION USING GAUSSIAN MIXTURE MODELS WITH MULTIPLE USER MODELS Niklas Johansson Chris McCool Sébastien Marcel Idiap-RR-07-2011 MARCH 2011 Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" b89862f38fff416d2fcda389f5c59daba56241db,A Web Survey for Facial Expressions Evaluation,"A Web Survey for Facial Expressions Evaluation Matteo Sorci Gianluca Antonini Jean-Philippe Thiran Ecole Polytechnique Federale de Lausanne Signal Processing Institute Ecublens, 1015 Lausanne, Switzerland Ecole Polytechnique Federale de Lausanne, Operation Research Group Michel Bierlaire Ecublens, 1015 Lausanne, Switzerland June 9, 2008" b8471908880c916ebc70ac900e9446705ed258f4,Transitional and translational studies of risk for anxiety.,"Review TRANSITIONAL AND TRANSLATIONAL STUDIES OF RISK FOR ANXIETY B. J. Casey Ph.D., Erika J. Ruberry B.S., Victoria Libby B.A., Charles E. Glatt M.D., Ph.D., Todd Hare Ph.D., Fatima Soliman M.D., Ph.D., Stephanie Duhoux Ph.D., Helena Frielingsdorf M.D., Ph.D., and Nim Tottenham Ph.D. Adolescence reflects a period of increased rates of anxiety, depression, and suicide. Yet most teens emerge from this period with a healthy, positive outcome. In this article, we identify biological factors that may increase risk for some individuals during this developmental period by: (1) examining changes in neural circuitry underlying core phenotypic features of anxiety as healthy individuals transition into and out of adolescence; (2) examining genetic factors that may enhance the risk for psychopathology in one individual over another using translation from mouse models to human neuroimaging and behavior; nd (3) examining the effects of early experiences on core phenotypic features of nxiety using human neuroimaging and behavioral approaches. Each of these pproaches alone provides only limited information on genetic and environ- mental influences on complex human behavior across development. Together, they reflect an emerging field of translational developmental neuroscience in" b856c0eb039effce7da9ff45c3f5987f18928bef,Pedestrian Alignment Network for Large-scale Person Re-identification,"Noname manuscript No. (will be inserted by the editor) Pedestrian Alignment Network for Large-scale Person Re-identification Zhedong Zheng · Liang Zheng · Yi Yang Received: date / Accepted: date" b8b202fa955801da840afc9f523d439d14d87cc1,A Novel Approach for Monocular 3 D Object Tracking in Cluttered Environment 853 Monocular Video Sequences,"International Journal of Computational Intelligence Research ISSN 0973-1873 Volume 13, Number 5 (2017), pp. 851-864 © Research India Publications http://www.ripublication.com A Novel Approach for Monocular 3D Object Tracking in Cluttered Environment Navneet S. Ghedia Research scholar, Gujarat Technological University, Gujarat, India. Dr. C.H. Vithalani Professor and Head of EC Dept., Government Engineering College, Rajkot, India. Dr. Ashish Kothari Associate Professor and Head of EC Dept., Atmiya Institute of Technology and Science, Rajkot, Gujarat, India." b8da30e8f6149baf1201e98b2ecbe847cf49a872,Open Framework for Combined Pedestrian Detection,"Open Framework for Combined Pedestrian Detection Floris De Smedt and Toon Goedem´e EAVISE, KU Leuven, Sint-Katelijne-Waver, Belgium Keywords: Pedestrian Detection, Real-time, Framework." b8ccc5341a1b0214e9d155b019962023f344c2ee,Incremental Learning of Object Detectors without Catastrophic Forgetting,"Incremental Learning of Object Detectors without Catastrophic Forgetting Konstantin Shmelkov Cordelia Schmid Karteek Alahari Inria∗" b88771387d5c0f09ea9a2ccc743b11471fb257b4,An interactive facial-expression training platform for individuals with autism spectrum disorder,"An Interactive Facial-Expression Training Platform for Individuals with Autism Spectrum Disorder Christina Tsangouri*, Wei Li+, Zhigang Zhu* * Dept. of Comp. Sci.. and +Dept of Electrical Eng.. City College of New York, New York, USA" b8d361d45f6fe4d8dc6129d205b0ae8c8e615939,2 FACE SKETCH SYNTHESIS USING THE MULTISCALE MARKOV RANDOM FIELDS MODEL,"IEEE TRANS. ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Face Photo-Sketch Synthesis and Recognition Xiaogang Wang, Student Member, IEEE, and Xiaoou Tang, Senior Member, IEEE" b8aef59bac4035013bcdaa9b56d665fc8b4e187d,Optimal Bayes Classification of High Dimensional Data in Face Recognition,"Optimal Bayes Classification of High Dimensional Data in Face Recognition GRIFT Research Group, CRISTAL Laboratory, National School of Computer Sciences, University of Manouba, Wissal Drira and Faouzi Ghorbel Manouba, Tunisia Keywords: Face Classification, Bayes, Feature Extraction, Reduction Dimension, L2 Probabilistic Dependence Measure." b8053da77bf1a5b4c87fddf6140be0a612cfc164,Multi-Pose Face Recognition Using Hybrid Face Features Descriptor,"MULTI-POSE FACE RECOGNITION USING HYBRID FACE FEATURES DESCRIPTOR I Gede Pasek Suta WIJAYA[1,2], Keiichi UCHIMURA[2] and Gou KOUTAKI[2]" b8a4e7c21c3163b7595dac0cb00cf518e2dd82b5,Coupling Fall Detection and Tracking in Omnidirectional Cameras,"Coupling Fall Detection and Tracking in Omnidirectional Cameras removed for blind review No Institute Given" b8a829b30381106b806066d40dd372045d49178d,A Probabilistic Framework for Joint Pedestrian Head and Body Orientation Estimation,"A Probabilistic Framework for Joint Pedestrian Head nd Body Orientation Estimation Fabian Flohr, Madalin Dumitru-Guzu, Julian F. P. Kooij, and Dariu M. Gavrila" b871d1b8495025ff8a6255514ed39f7765415935,Application of Completed Local Binary Pattern for Facial Expression Recognition on Gabor Filtered Facial Images,"Application of Completed Local Binary Pattern for Facial Expression Recognition on Gabor Filtered Facial Images Tanveer Ahsan, 2Rifat Shahriar, *3Uipil Chong Dept. of Electrical and Computer Engineering, University of Ulsan, Ulsan, Republic of Korea" b8f3f6d8f188f65ca8ea2725b248397c7d1e662d,Selfie Detection by Synergy-Constraint Based Convolutional Neural Network,"Selfie Detection by Synergy-Constriant Based Convolutional Neural Network Yashas Annadani, Vijaykrishna Naganoor, Akshay Kumar Jagadish and Krishnan Chemmangat Electrical and Electronics Engineering, NITK-Surathkal, India." b8e35566129299c3591af0fd4f127e5e0d0b5774,3D Facial Image Comparison using Landmarks,"D Facial Image Comparison using Landmarks A study to the discriminating value of the characteristics of 3D facial landmarks and their automated detection. Alize Scheenstra Master thesis: INF/SCR-04-54 Netherlands Forensic Institute Institute of Information and Computing Sciences Utrecht University February 2005" b8dba0504d6b4b557d51a6cf4de5507141db60cf,Comparing Performances of Big Data Stream Processing Platforms with RAM3S,"Comparing Performances of Big Data Stream Processing Platforms with RAM3S" b8e76cadc9ad20c242718be4dd3c5af0e34b29bf,Fusing Body Posture with Facial Expressions for Joint Recognition of Affect in Child-Robot Interaction,"Fusing Body Posture with Facial Expressions for Joint Recognition of Affect in Child-Robot Interaction Panagiotis P. Filntisis 1,3 Niki Efthymiou 1,3 Petros Koutras 1,3 Gerasimos Potamianos 2,3 Petros Maragos 1,3 School of E.C.E., NTUA, Greece E.C.E. Department, UTH, Greece Athena RC, Maroussi, Greece" 4106c49eb96b506ea1125c27e2b2f32ad79f8c48,"Markovian Tracking-by-Detection from a Single , Uncalibrated Camera","Markovian Tracking-by-Detection from a Single, Uncalibrated Camera Michael D. Breitenstein1 Fabian Reichlin1 Bastian Leibe1,2 Esther Koller-Meier1 Luc Van Gool1,3 ETH Zurich RWTH Aachen KU Leuven" 4129e1075c7856d8bebbf0655ae00a4843109429,A Tale of Two Losses : Discriminative Deep Feature Learning for Person Re-Identification,"A Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-Identification Borgia, A., Hua, Y., & Robertson, N. (2017). A Tale of Two Losses: Discriminative Deep Feature Learning for Person Re-Identification. In Irish Machine Vision and Image Processing Conference 2017: Proceedings Published in: Irish Machine Vision and Image Processing Conference 2017: Proceedings Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights © 2017 National University of Ireland Maynooth. This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to ensure that content in the Research Portal does not infringe any person's rights, or applicable UK laws. If you discover content in the" 41a6196f88beced105d8bc48dd54d5494cc156fb,Using facial images for the diagnosis of genetic syndromes: A survey,"015 International Conference on Communications, Signal Processing, and their Applications (ICCSPA 2015) Sharjah, United Arab Emirates 7-19 February 2015 IEEE Catalog Number: ISBN: CFP1574T-POD 978-1-4799-6533-5" 41ed93fd97aa76b4abfda7a09168ad1799f34664,Video Event Detection: From Subvolume Localization to Spatiotemporal Path Search,"This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore. Title Video event detection : from subvolume localization to spatio-temporal path search Author(s) Tran, Du; Yuan, Junsong; Forsyth, David Citation Tran, D., Yuan, J., & Forsyth, D. (2014). Video Event Detection: From Subvolume Localization to Spatiotemporal Path Search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(2), 404- http://hdl.handle.net/10220/19322 Rights © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any" 41235b815a3a69eb5ef48199e7ea7e98495e56a9,Learning Discriminative Local Patterns with Unrestricted Structure for Face Recognition,"Learning discriminative local patterns with unrestricted structure for face recognition Author Brown, Douglas, Gao, Yongsheng, Zhou, Jun Published Conference Title 013 International Conference on Digital Image Computing: Techniques and Applications (DICTA) https://doi.org/10.1109/DICTA.2013.6691504 Copyright Statement © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Downloaded from http://hdl.handle.net/10072/56813 Link to published version http://www.aprs.org.au/dicta13/ Griffith Research Online" 41de109bca9343691f1d5720df864cdbeeecd9d0,Facial Emotion Recognition: A Survey and Real-World User Experiences in Mixed Reality,"Article Facial Emotion Recognition: A Survey and Real-World User Experiences in Mixed Reality Dhwani Mehta, Mohammad Faridul Haque Siddiqui and Ahmad Y. Javaid * ID EECS Department, The University of Toledo, Toledo, OH 43606, USA; (D.M.); (M.F.H.S.) * Correspondence: Tel.: +1-419-530-8260 Received: 10 December 2017; Accepted: 26 January 2018; Published: 1 Febuary 2018" 4156b7e88f2e0ab0a7c095b9bab199ae2b23bd06,Nighttime Face Recognition at Long Distance: Cross-Distance and Cross-Spectral Matching,"Nighttime Face Recognition at Long Distance: Cross-distance and Cross-spectral Matching Hyunju Maenga, Shengcai Liaob, Dongoh Kanga, Seong-Whan Leea, Anil K. Jaina;b Dept. of Brain and Cognitive Eng. Korea Univ., Seoul, Korea Dept. of Comp. Sci. & Eng. Michigan State Univ., E. Lansing, MI, USA 48824" 4180978dbcd09162d166f7449136cb0b320adf1f,Real-time head pose classification in uncontrolled environments with Spatio-Temporal Active Appearance Models,"Real-time head pose classification in uncontrolled environments with Spatio-Temporal Active Appearance Models Miguel Reyes∗ and Sergio Escalera+ and Petia Radeva + Matematica Aplicada i Analisi ,Universitat de Barcelona, Barcelona, Spain + Matematica Aplicada i Analisi, Universitat de Barcelona, Barcelona, Spain + Matematica Aplicada i Analisi, Universitat de Barcelona, Barcelona, Spain" 41ddd29d9e56bb87b9f988afc75cd597657b2600,R 4-A . 3 : Human Detection & Re-Identification for Mass Transit Environments,"R4-A.3: Human Detection & Re-Identification for Mass Transit Environments PARTICIPANTS Rich Radke Title Faculty/Staff Institution Graduate, Undergraduate and REU Students Srikrishna Karanam Eric Lam Degree Pursued Institution Email Month/Year of Graduation 5/2017 5/2017 PROJECT DESCRIPTION Project Overview The computer vision research problem of human re-identification or “re-id” is generally posed as follows: Given a cropped rectangle of pixels representing a human in one view, a re-id algorithm produces a similarity" 4189aa74550c1761dd5927442d0a98ff3d3d1134,Residual Conv-Deconv Grid Network for Semantic Segmentation,"FOURURE ET AL.: RESIDUAL CONV-DECONV GRIDNET Residual Conv-Deconv Grid Network for Semantic Segmentation Univ Lyon, UJM Saint-Etienne, CNRS UMR 5516, Hubert Curien Lab, F-42023 Saint-Etienne, France INSA-Lyon, LIRIS UMR CNRS 5205, F-69621, France Damien Fourure1 Rémi Emonet1 Elisa Fromont1 Damien Muselet1 Alain Tremeau1 Christian Wolf2" 4152d2c8585f7e3f85d3b3d84036171de104cbd7,Rethinking ImageNet Pre-training,"Rethinking ImageNet Pre-training Kaiming He Ross Girshick Piotr Doll´ar Facebook AI Research (FAIR)" 41fafb5392ad5e33e5169d870812ab5edca301a1,Tree-Structured Stick Breaking Processes for Hierarchical Data,"TREE-STRUCTURED STICK BREAKING PROCESSES FOR HIERARCHICAL DATA By Ryan P. Adams, Zoubin Ghahramani and Michael I. Jordan Many data are naturally modeled by an unobserved hierarchical structure. In this paper we propose a flexible nonparametric prior over processes to allow for trees of unbounded width and depth, where data an live at any node and are infinitely exchangeable. One can view our model as providing infinite mixtures where the components have a dependency structure corresponding to an evolutionary diffusion down tree. By using a stick-breaking approach, we can apply Markov chain Monte Carlo methods based on slice sampling to perform Bayesian inference and simulate from the posterior distribution on trees. We pply our method to hierarchical clustering of images and topic modeling of text data. . Introduction. Structural aspects of models are often critical to ob- taining flexible, expressive model families. In many cases, however, the structure is unobserved and must be inferred, either as an end in itself or to assist in other estimation and prediction tasks. This paper addresses an important instance of the structure learning problem: the case when the data arise from a latent hierarchy. We take a direct nonparametric Bayesian" 414715421e01e8c8b5743c5330e6d2553a08c16d,PoTion : Pose MoTion Representation for Action Recognition,"PoTion: Pose MoTion Representation for Action Recognition Philippe Weinzaepfel2 Inria∗ NAVER LABS Europe J´erˆome Revaud2 Cordelia Schmid1 Vasileios Choutas1,2" 41367bca49675d0dd078dcd9a140b92d05379900,Survey on Emotional Body Gesture Recognition,"JOURNAL OF IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, VOL. XX, NO. X, XXX 201X Survey on Emotional Body Gesture Recognition Fatemeh Noroozi, Ciprian Adrian Corneanu, Dorota Kami´nska, Tomasz Sapi´nski, Sergio Escalera, nd Gholamreza Anbarjafari," 4131aa28d640d17e1d63ca82e55cc0b280db0737,COULOMB GANS: PROVABLY OPTIMAL NASH EQUI-,"Under review as a conference paper at ICLR 2018 COULOMB GANS: PROVABLY OPTIMAL NASH EQUI- LIBRIA VIA POTENTIAL FIELDS Anonymous authors Paper under double-blind review" 41a174c27f0b431d62d0f50051bce7f5b3b4ce64,A System for Object Class Detection,"A system for object class detection Daniela Hall INRIA Rh^one-Alpes, 655, ave de l’Europe, 8320 St. Ismier, France" 41b541ff747817dade4653fe6ffcdc50e7b3135b,A Stochastic Graph Evolution Framework for Robust Multi-target Tracking,"A Stochastic Graph Evolution Framework for Robust Multi-Target Tracking Bi Song, Ting-Yueh Jeng, Elliot Staudt, and Amit K. Roy-Chowdhury (cid:63) Dept. of Electrical Engineering, University of California, Riverside, CA 92521, USA" 416c647cd9f8c1d77db8676195dff7ae5dfc1fd8,Grammatical Facial Expressions Recognition with Machine Learning,"Grammatical Facial Expressions Recognition with Machine Learning Fernando de Almeida Freitas Incluir Tecnologia Itajub´a, MG, Brazil Universidade de S˜ao Paulo S˜ao Paulo, SP, Brazil Clodoaldo Aparecido de Moraes Lima Sarajane Marques Peres Felipe Venˆancio Barbosa Universidade de S˜ao Paulo S˜ao Paulo, SP, Brazil" 41a5e043d499967f405e823b959e2ac4fdf9ff71,Extending Recognition in a Changing Environment,"Extending Recognition in a Changing Environment Department of Computer Science and Applied Mathematics, The Weizmann Institue of Science, Rehovot, Israel Daniel Harari and Shimon Ullman {danny.harari, Keywords: Object Recognition, Video Analysis, Dynamic Model Update, Unsupervised Learning, Bayesian Model." 418b468b804379e8a600bca0395e01bffb7e08de,Class-specific kernel linear regression classification for face recognition under low-resolution and illumination variation conditions,"Chou et al. EURASIP Journal on Advances in Signal Processing (2016) 2016:28 DOI 10.1186/s13634-016-0328-0 Open Access R ES EAR CH Class-specific kernel linear regression lassification for face recognition under low-resolution and illumination variation onditions Yang-Ting Chou, Shih-Ming Huang and Jar-Ferr Yang*" 4196e0b77f88ea01cd868c535befb52c2722454f,3D Facial similarity: Automatic assessment versus perceptual judgments,"D Facial Similarity: Automatic Assessment versus Perceptual Judgments Anush K. Moorthy, Anish Mittal, Sina Jahanbin, Kristen Grauman and Alan C. Bovik" 41308edf82ae645923efea2d6979d076b975ee25,Convolutional Scale Invariance for Semantic Segmentation,"Convolutional Scale Invariance for Semantic Segmentation Ivan Kre(cid:20)so, Denis (cid:20)Cau(cid:20)sevi(cid:19)c, Josip Krapac and Sini(cid:20)sa (cid:20)Segvi(cid:19)c Faculty of Electrical Engineering and Computing University of Zagreb, Croatia" 41f8dd3de3380d49ed3809c582b139d9be5176e9,The Price of Fair PCA: One Extra dimension,"The Price of Fair PCA: One Extra Dimension Samira Samadi Georgia Tech Uthaipon Tantipongpipat Georgia Tech Jamie Morgenstern Georgia Tech Mohit Singh Georgia Tech Santosh Vempala Georgia Tech" 418b106e1f072c4da400b516079f429d84cd7305,Model-based Face Computation Project Role in Support of Imsc Strategic Plan Discussion of Methodology Used,"Model-Based Face Computation Research Team Project Leader: Prof. Ulrich Neumann, IMSC and Computer Science Post Doc(s): John P. Lewis Graduate Students: Hea-juen Hwang, Zhenyao Mo, Gordon Thomas Statement of Project Goals Prior knowledge of the canonical structure of the human face can aid in various automated face- processing tasks. In this project we have developed a statistical appearance model for faces and re exploring its application to several problems: stylized face rendering, caricature, and reconstruction of occluded face images. Project Role in Support of IMSC Strategic Plan Model-Based Face computation is part of the general IMSC effort towards expressive human interaction in virtual and augmented reality environments. While this project involves processing based on the structure of the face, the complementary Data-Driven Facial Animation project is directed toward deriving models of facial movement (including non-speech gestures) directly from data. Discussion of Methodology Used" 41690be86b39c55a26ea056261513ddd726d6601,Heterogeneous microarchitectures trump voltage scaling for low-power cores,"Heterogeneous Microarchitectures Trump Voltage Scaling for Low-Power Cores Andrew Lukefahr, Shruti Padmanabha, Reetuparna Das, Ronald Dreslinski Jr., Thomas F. Wenisch, and Scott Mahlke Advanced Computer Architecture Laboratory Ann Arbor, MI, USA {lukefahr, shrupad, reetudas, rdreslin, twenisch," 41e6dfe1a87f49c8539f725daa44256c19f31004,Audio-visual speaker identification using the CUAVE database,"COVER SHEET Dean, David and Lucey, Patrick and Sridharan, Sridha (2005) Audio-visual speaker identification using the CUAVE database. In Vatikiotis-Bateson, Eric and Burnham, Denis and Fels, Sidney, Eds. Proceedings Auditory-Visual Speech Processing 2005, British Columbia, Canada. Accessed from http://eprints.qut.edu.au Copyright 2005 the authors" 413160257096b9efcd26d8de0d1fa53133b57a3d,Customer satisfaction measuring based on the most significant facial emotion,"Customer satisfaction measuring based on the most significant facial emotion Mariem Slim, Rostom Kachouri, Ahmed Atitallah To cite this version: Mariem Slim, Rostom Kachouri, Ahmed Atitallah. Customer satisfaction measuring based on the most significant facial emotion. 15th IEEE International Multi-Conference on Systems, Signals Devices (SSD 2018), Mar 2018, Hammamet, Tunisia. HAL Id: hal-01790317 https://hal-upec-upem.archives-ouvertes.fr/hal-01790317 Submitted on 11 May 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 41dd2ca8929bfdae49a4bf85de74df4723ef9c3b,Correction by Projection: Denoising Images with Generative Adversarial Networks.,"WITH GENERATIVE ADVERSARIAL NETWORKS Subarna Tripathi Zachary C. Lipton Truong Q. Nguyen UC San Diego UC San Diego UC San Diego" 414722ddd809b460d5b397eaf454fbb697cfb881,Dimensionality Reduction and Classification through PCA and LDA,"International Journal of Computer Applications (0975 – 8887) Volume 122 – No.17, July 2015 Dimensionality Reduction and Classification through PCA and LDA Telgaonkar Archana H. PG Student Department of CS and IT Dr. BAMU, Aurangabad" 417890cc6d43a3082a6ab2ac64527f8db5b0125b,Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction,"microwavetake foodput into microwaveParse TreeFuture prediction...Sequenceinput dataClassifierraw outputFinal outputGrammarGeneralized Earley algorithmmicrowave foodFigure1.TheinputofthegeneralizedEarleyparserisamatrixofprobabilitiesofeachlabelforeachframe,givenbyanarbitraryclassifier.Theparsersegmentsandlabelsthesequencedataintoalabelsentenceinthelanguageofagivengrammar.Futurepredictionsarethenmadebasedonthegrammar.grammarstoparseandlabelsequencedata.Traditionalgrammarparserstakesymbolicsentencesasinputsinsteadofnoisysequencedatalikevideosoraudios.Thedatahastobei)segmentedandii)labeledtoapplyexistinggram-marparsersto.Onenaivesolutionistofirstsegmentandlabelthedatausingaclassifierandthusgeneratingalabelsentence.Thengrammarparserscanbeappliedontopofitforprediction.Butthisisapparentlynon-optimal,sincethegrammarrulesarenotconsideredintheclassificationpro-cess.Itmaynotevenbepossibletoparsethislabelsentence,becausetheyareveryoftengrammaticallyincorrect.Inthispaper,wedesignagrammar-basedparsingalgorithmthatdirectlyoperatesonsequenceinputdata,whichgoesbeyondthescopeofsymbolicstringinputs.Specifically,weproposeageneralizedEarleyparserbasedontheEarleyparser(Earley,1970).Thealgorithmfindstheoptimalseg-mentationandlabelsentenceaccordingtobothasymbolicgrammarandaclassifieroutputofprobabilitiesoflabelsforeachframeasshowninFigure1.Optimalityheremeansmaximizingtheprobabilityofthelabelsentenceaccordingtotheclassifieroutputwhilebeinggrammaticallycorrect.Thedifficultyofachievingthisoptimalityliesinthejointoptimizationofboththegrammarstructureandtheparsinglikelihoodoftheoutputlabelsentence.Forexample,anexpectation-maximization-typealgorithmwillnotworkwell" 41ea92251c668a99d2b9a31935fc71e6b6d82b6d,Canonical Correlation Analysis of Datasets With a Common Source Graph,"Canonical Correlation Analysis of Datasets with a Common Source Graph Jia Chen, Gang Wang, Student Member, IEEE, Yanning Shen, Student Member, IEEE, and Georgios B. Giannakis, Fellow, IEEE" 413a184b584dc2b669fbe731ace1e48b22945443,Human Pose Co-Estimation and Applications,"Human Pose Co-Estimation and Applications Marcin Eichner and Vittorio Ferrari" 41f7c03519a2b108c064a2126daf627edde14c1e,Generic Object Detection using AdaBoost,"Generic Object Detection using AdaBoost Ben Weber Department of Computer Science University of California, Santa Cruz Santa Cruz, CA 95064" 419a6fca4c8d73a1e43003edc3f6b610174c41d2,A component based approach improves classification of discrete facial expressions over a holistic approach,"A Component Based Approach Improves Classification of Discrete Facial Expressions Over a Holistic Approach Kenny Hong, and Stephan K. Chalup, Senior Member, IEEE and Robert A.R. King" 41d9a240b711ff76c5448d4bf4df840cc5dad5fc,Image Similarity Using Sparse Representation and Compression Distance,"JOURNAL DRAFT, VOL. X, NO. X, APR 2013 Image Similarity Using Sparse Representation nd Compression Distance Tanaya Guha, Student Member, IEEE, and Rabab K Ward, Fellow, IEEE" 41f6368bc4ec5e334c81a9d16185205b3acecee3,Machine Learning Methods from Group to Crowd Behaviour Analysis,"Machine learning methods from group to crowd ehaviour analysis Luis Felipe Borja-Borja1, Marcelo Saval-Calvo2, and Jorge Azorin-Lopez2 Universidad Central del Ecuador, Ciudadela Universitaria Av. Am´erica, Quito, Ecuador Computer Technology Department, University of Alicante, Carretera San Vicente s/n, 03690, San Vicente del Raspeig (Spain)" 410017a1810308564dc54cb986b12f079428f966,A functional pipeline framework for landmark identification on 3D surface extracted from volumetric data,"RESEARCH ARTICLE A functional pipeline framework for landmark identification on 3D surface extracted from volumetric data Pan Zheng1,2*, Bahari Belaton2*, Iman Yi Liao3, Zainul Ahmad Rajion4,5 Faculty of Engineering, Computing and Science, Swinburne University of Technology Sarawak Campus, Kuching, Malaysia, 2 School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia, 3 School of Computer Science, The University of Nottingham Malaysia Campus, Semenyih, Malaysia, 4 School of Dental Sciences, Universiti Sains Malaysia, Kubang Kerian, Malaysia, 5 College of Dentistry, King Saud bin Abdulaziz University for Health Sciences, Riyadh, Kingdom of Saudi Arabia * (PZ); (BB)" 413a1a00f0eab2fcc3dcc0d821fb2f34e85f5d7a,Pedestrian detection by scene dependent classifiers with generative learning,"June 23-26, 2013, Gold Coast, Australia 978-1-4673-2754-1/13/$31.00 ©2013 IEEE" 413c960e57ec3fe713e7b3e070cb6072726874bd,A Search Space Strategy for Pedestrian Detection and Localization in World Coordinates, 41ab4939db641fa4d327071ae9bb0df4a612dc89,Interpreting Face Images by Fitting a Fast Illumination-Based 3D Active Appearance Model,"Interpreting Face Images by Fitting a Fast Illumination-Based 3D Active Appearance Model Salvador E. Ayala-Raggi, Leopoldo Altamirano-Robles, Janeth Cruz-Enriquez Instituto Nacional de Astrof´ısica, ´Optica y Electr´onica, Luis Enrique Erro #1, 72840 Sta Ma. Tonantzintla. Pue., M´exico Coordinaci´on de Ciencias Computacionales {saraggi, robles," 41b2c5ad11a3f55d72def07d44cb32a44701ecd1,Weighted Self-Incremental Transfer Learning for 3 D-Semantic Segmentation,"Weighted Self-Incremental Transfer Learning for D-Semantic Segmentation Anonymous Author(s) Affiliation Address email" 8458efc65d0b2ef9b23c0f4f2a41f206fcaa787c,Indexing of the CNN features for the large scale image search,"Noname manuscript No. (will be inserted by the editor) Indexing of the CNN Features for the Large Scale Image Search Ruoyu Liu · Shikui Wei · Yao Zhao · Yi Received: date / Accepted: date" 843f873c08df64431baefd79e83e4b70236427de,Exploring and Understanding the High Dimensional and Sparse Image Face Space : a Self-Organized Manifold Mapping,"Exploring and Understanding the High Dimensional and Sparse Image Face Space: Self-Organized Manifold Mapping Edson C. Kitani1, Emilio M. Hernandez1, Gilson A. Giraldi2 and Carlos E. Thomaz3 Universidade de São Paulo, São Paulo, São Paulo, Laboratório Nacional de Computação Científica, Petrópolis, Rio de Janeiro, Centro Universitário da FEI, São Bernardo do Campo, São Paulo, Brazil . Introduction Face recognition has motivated several research studies in the last years owing not only to its applicability and multidisciplinary inherent characteristics, but also to its important role in human relationship. Despite extensive studies on face recognition, a number of related problems has still remained challenging in this research topic. It is well known that humans an overcome any computer program in the task of face recognition when artefacts are present such as changes in pose, illumination, occlusion, aging and etc. For instance, young hildren can robustly identify their parents, friends and common social groups without any previous explicit teaching or learning. Some recent research in Neuroscience (Kandel et al., 2000; Bakker et al., 2008) has shown that there is some new information about how humans deal with such high dimensional and" 84adff86191a1942ec165654fa1d484555d1e6f2,Implementation of an Intentional Vision System to Support Cognitive Architectures,"Implementation of an Intentional Vision System to Support Cognitive Architectures Ignazio Infantino, Carmelo Lodato, Salvatore Lopes and Filippo Vella Istituto di Calcolo e Reti ad Alte Prestazioni edif. 11, Viale delle Scienze, 90128, Palermo, Italy Consiglio Nazionale delle Ricerche ICAR-CNR sede di Palermo" 84fd7c00243dc4f0df8ab1a8c497313ca4f8bd7b,Perceived Age Estimation from Face Images,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 84a69f6357b137028e3aa51376ce2dffad5e0179,"UPSALIENSIS UPPSALA 2018 Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Social Sciences 152 Visual Attention to Faces , Eyes and Objects Studies of Typically and Atypically Developing Children JOHAN","Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Social Sciences 152 Visual Attention to Faces, Eyes and Objects Studies of Typically and Atypically Developing Children JOHAN L. KLEBERG ISSN 1652-9030 ISBN 978-91-513-0244-7 urn:nbn:se:uu:diva-342578 UNIVERSITATIS UPSALIENSIS UPPSALA" 84124eba5ccd5a25d2275c3dd6d2f15e30225ef7,People counting with image retrieval using compressed sensing,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 Crown Homa Foroughi, Nilanjan Ray, Hong Zhang Index Terms— compressed sensing, people counting, . INTRODUCTION" 8468af265ef8c296764d26a69a7d35e6ccd68fa5,Adaptive Regression Splines Models for Predicting Facial Image Verification and Quality Assessment Scores,"BALKAN JOURNAL OF ELECTRICAL & COMPUTER ENGINEERING, 2015, Vol.3, No.1 Adaptive Regression Splines Models for Predicting Facial Image Verification and Quality Assessment Scores A. A. Abayomi-Alli, E. O. Omidiora, S. O. Olabiyisi and J. A. Ojo" 84f6f20496fadb975922b47528fd94c71e872950,Dissimilarity-based people re-identification and search for intelligent video surveillance,"Ph.D. in Electronic and Computer Engineering Dept. of Electrical and Electronic Engineering University of Cagliari Dissimilarity-based people re-identification and search for intelligent video surveillance Riccardo Satta Advisor: Prof. Fabio Roli Co-advisor: Prof. Giorgio Fumera Curriculum: ING-INF/05 - Sistemi di Elaborazione delle Informazioni XXV Cycle April 2013" 84c8b29103480cf6f2b93e2fd4225b0d9d535ed6,Playing hide and seek with a mobile companion robot,"Playing Hide and Seek with a Mobile Companion Robot Michael Volkhardt, Steffen Mueller, Christof Schroeter, Horst-Michael Gross Neuroinformatics and Cognitive Robotics Lab Ilmenau University of Technology 98684 Ilmenau, Germany Email:" 84c8eb2db35f7fd38c906ced741e2c5470ba7544,Deep Control - a simple automatic gain control for memory efficient and high performance training of deep convolutional neural networks,"Deep Control - a simple automatic gain control for memory efficient and high performance training of deep onvolutional neural networks Brendan Ruff Submitted to BMVC 2017, 2nd May 2017 Patent application GB1619779.0, 23rd Nov 2016" 84508e846af3ac509f7e1d74b37709107ba48bde,Use of the Septum as a Reference Point in a Neurophysiologic Approach to Facial Expression Recognition,"Use of the Septum as a Reference Point in a Neurophysiologic Approach to Facial Expression Recognition Igor Stankovic and Montri Karnjanadecha Department of Computer Engineering, Faculty of Engineering, Prince of Songkla University, Hat Yai, Songkhla, 90112 Thailand Telephone: (66)080-7045015, (66)074-287-357 E-mail:" 8411fe1142935a86b819f065cd1f879f16e77401,Facial Recognition using Modified Local Binary Pattern and Random Forest,"International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 4, No. 6, November 2013 Facial Recognition using Modified Local Binary Pattern and Random Forest Brian O’Connor and Kaushik Roy Department of Computer Science, North Carolina A&T State University, Greensboro, NC 27411" 84e4b7469f9c4b6c9e73733fa28788730fd30379,Projective complex matrix factorization for facial expression recognition,"Duong et al. EURASIP Journal on Advances in Signal Processing (2018) 2018:10 DOI 10.1186/s13634-017-0521-9 EURASIP Journal on Advances in Signal Processing R ES EAR CH Projective complex matrix factorization for facial expression recognition Viet-Hang Duong1, Yuan-Shan Lee1, Jian-Jiun Ding2, Bach-Tung Pham1, Manh-Quan Bui1, Pham The Bao2 nd Jia-Ching Wang1,3* Open Access" 84968d6488e87c99b8560ab33110a5bf85aa5761,Object category learning and retrieval with weak supervision,"Object category learning and retrieval with weak supervision Steven Hickson, Anelia Angelova, Irfan Essa, Rahul Sukthankar Google Brain / Google Research (shickson, anelia, irfanessa," 84187adc5e6412123405102bb3c2f0428713593c,Quad-Tree based Image Encoding Methods for Data-Adaptive Visual Feature Learning,"IPSJ SIG Technical Report Quad-Tree based Image Encoding Methods for Data-Adaptive Visual Feature Learning Cuicui Zhang1,a) Xuefeng Liang1,b) Takashi Matsuyama1,c)" 844568d9e49ec34536502bb8c66d5578c962abd6,From Virtual to Real World Visual Perception using Domain Adaptation - The DPM as Example,"Invited book chapter to appear in Domain Adaptation in Computer Vision Applications, Springer Series: Advances in Computer Vision and Pattern Recognition, Edited by Gabriela Csurka. Written during Summer 2016. From Virtual to Real World Visual Perception using Domain Adaptation – The DPM as Example Computer Vision Center (CVC) and Dpt. Ci`encies de la Computaci´o (DCC), Antonio M. L´opez Universitat Aut`onoma de Barcelona (UAB) Jiaolong Xu Jos´e L. G´omez David V´azquez CVC and DCC, UAB CVC and DCC, UAB CVC and DCC, UAB Germ´an Ros CVC and DCC, UAB December 30, 2016" 84c35fc21db3bcd407a4ffb009912b6ac5a47e3c,MGAN: TRAINING GENERATIVE ADVERSARIAL NETS,"Under review as a conference paper at ICLR 2018 MGAN: TRAINING GENERATIVE ADVERSARIAL NETS WITH MULTIPLE GENERATORS Anonymous authors Paper under double-blind review" 847a1fc7c29ca91282a676fc6381056b8dec65a6,People as Sensors: Imputing Maps from Human Actions,"People as Sensors: Imputing Maps from Human Actions Oladapo Afolabi*, Katherine Driggs-Campbell*, Roy Dong, Mykel J. Kochenderfer, and S. Shankar Sastry" 845c03910c7cfd02de7df9622a9973e8b085c0d8,Interactive Generation of Realistic Facial Wrinkles from Sketchy Drawings,"EUROGRAPHICS 2015 / O. Sorkine-Hornung and M. Wimmer (Guest Editors) Volume 34 (2015), Number 2 Interactive Generation of Realistic Facial Wrinkles from Sketchy Drawings Hyeon-Joong Kim 1,3, A. Cengiz Öztireli2, Il-Kyu Shin1, Markus Gross2, Soo-Mi Choi†1 Sejong University, Korea 2 ETH Zurich, Switzerland 3 3D Systems, Korea Figure 1: We use statistics extracted from example faces to augment interactively drawn concept sketches for synthesizing realistic facial wrinkles." 84f911432ba8a3356013b3abfbf1947f1145c953,Online Object Tracking with Proposal Selection,"Online Object Tracking with Proposal Selection Yang Hua Karteek Alahari Inria∗ Cordelia Schmid" 84a20d0a47c0d826b77f73075530d618ba7573d2,Look at Boundary: A Boundary-Aware Face Alignment Algorithm,"(68 points) COFW (29 points) AFLW (19 points) Figure1:Thefirstcolumnshowsthefaceimagesfromdifferentdatasetswithdifferentnumberoflandmarks.Thesecondcolumnillustratestheuniversallydefinedfacialboundariesestimatedbyourmethods.Withthehelpofboundaryinformation,ourapproachachieveshighaccuracylocalisationresultsacrossmultipledatasetsandannotationprotocols,asshowninthethirdcolumn.Differenttofacedetection[45]andrecognition[75],facealignmentidentifiesgeometrystructureofhumanfacewhichcanbeviewedasmodelinghighlystructuredout-put.Eachfaciallandmarkisstronglyassociatedwithawell-definedfacialboundary,e.g.,eyelidandnosebridge.However,comparedtoboundaries,faciallandmarksarenotsowell-defined.Faciallandmarksotherthancornerscanhardlyremainthesamesemanticallocationswithlargeposevariationandocclusion.Besides,differentannotationschemesofexistingdatasetsleadtoadifferentnumberoflandmarks[28,5,66,30](19/29/68/194points)andanno-tationschemeoffuturefacealignmentdatasetscanhardlybedetermined.Webelievethereasoningofauniquefacial" 842e42d30dc31de1833047c268f0a5cdff16f2ce,Face Compression and Recognition using Spherical Wavelet Parametrization,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 3, No.9, 2012 D Face Compression and Recognition using Spherical Wavelet Parametrization Rabab M. Ramadan College of Computers and Information Technology University of Tabuk Tabuk, KSA into multi-resolution sub" 84fa126cb19d569d2f0147bf6f9e26b54c9ad4f1,Improved Boosting Performance by Explicit Handling of Ambiguous Positive Examples,"Improved Boosting Performance by Explicit Handling of Ambiguous Positive Examples Miroslav Kobetski and Josephine Sullivan" 84be05dd82a7208a6e7b3d238df27b123cc917ce,Revisiting Visual Question Answering Baselines,"Revisiting Visual Question Answering Baselines Allan Jabri, Armand Joulin, and Laurens van der Maaten Facebook AI Research" 42ecfc3221c2e1377e6ff849afb705ecd056b6ff,Pose Invariant Face Recognition Under Arbitrary Unknown Lighting Using Spherical Harmonics,"Pose Invariant Face Recognition under Arbitrary Lei Zhang and Dimitris Samaras Department of Computer Science, SUNY at Stony Brook, NY, 11790 {lzhang," 42b56c77e4b154364763d4024baa8129da75151f,Deep Detection of People and their Mobility Aids for a Hospital Robot,"Deep Detection of People and their Mobility Aids for a Hospital Robot Andres Vasquez Marina Kollmitz Andreas Eitel Wolfram Burgard" 42f4653f0693f16e087e4b913407d9b0278154c9,3D Human Action Recognition with Siamese-LSTM Based Deep Metric Learning,"D Human Action Recognition with Siamese- LSTM Based Deep Metric Learning VisLab, Department of Computer Engineering, Gebze Technical University, Kocaeli, Turkey Seyma Yucer and Yusuf Sinan Akgul Email: {syucer," 42e793b1dd6669b74ad106071c432aa5015b8631,How do people think about interdependence? A multidimensional model of subjective outcome interdependence.,"tapraid5/z2g-perpsy/z2g-perpsy/z2g99917/z2g4623d17z xppws S⫽1 8/10/17 :53 Art: 2016-0710 APA NLM 017, Vol. 0, No. 999, 000 0022-3514/17/$12.00 © 2017 American Psychological Association http://dx.doi.org/10.1037/pspp0000166 How Do People Think About Interdependence? A Multidimensional Model of Subjective Outcome Interdependence Fabiola H. Gerpott, Daniel Balliet, Simon Columbus, and Catherine Molho Vrije Universiteit Amsterdam Reinout E. de Vries Vrije Universiteit Amsterdam and University of Twente Interdependence is a fundamental characteristic of social interactions. Interdependence Theory states that 6 dimensions describe differences between social situations. Here we examine if these 6 dimensions describe how people think about their interdependence with others in a situation. We find that people (in situ and ex situ) can reliably differentiate situations according to 5, but not 6, dimensions of interde-" 424e918134ed7c70fa73450bd6af1bd982071a27,Final Report : Localized object detection with Convolutional Neural Networks,"Final Report: Localized object detection with Convolutional Computer Vision Neural Networks Bardia Doosti Vijay Hareesh Avula May 5, 2016" 423aacfe7467961e32f012bc6de10d636ebc0236,Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Breaking the Interactive Bottleneck in Multi-Class Classification with Active Selection and Binary Feedback Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoulos TR2010-037 July 2010" 4264342722c48bb334d19b993400c5a133819e51,Nasal Patches and Curves for Expression-Robust 3D Face Recognition,"Nasal Patches and Curves for Expression-robust 3D Face Recognition Mehryar Emambakhsh and Adrian Evans" 4209783b0cab1f22341f0600eed4512155b1dee6,Accurate and Efficient Similarity Search for Large Scale Face Recognition,"Accurate and Efficient Similarity Search for Large Scale Face Recognition Ce Qi Zhizhong Liu Fei Su" 4213502d0f226b9845b00c2882851ba4c57742ab,Does Rabbit Antithymocyte Globulin (Thymoglobuline®) Have a Role in Avoiding Delayed Graft Function in the Modern Era of Kidney Transplantation?,"Hindawi Journal of Transplantation Volume 2018, Article ID 4524837, 11 pages https://doi.org/10.1155/2018/4524837 Review Article Does Rabbit Antithymocyte Globulin (ThymoglobulineD) Have a Role in Avoiding Delayed Graft Function in the Modern Era of Kidney Transplantation? Lluís Guirado Department of Renal Transplantation, Fundaci´o Puigvert, Barcelona, Spain Correspondence should be addressed to Llu´ıs Guirado; Received 12 April 2018; Accepted 20 June 2018; Published 12 July 2018 Academic Editor: Andreas Zuckermann Copyright © 2018 Llu´ıs Guirado. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Delayed graft function (DGF) increases the risk of graft loss by up to 40%, and recent developments in kidney donation have increased the risk of its occurrence. Lowering the risk of DGF, however, is challenging due to a complicated etiology in which ischemia-reperfusion injury (IRI) leads to acute tubular necrosis. Among various strategies explored, the choice of induction therapy is one consideration. Rabbit antithymocyte globulin (rATG [Thymoglobuline]) has complex immunomodulatory effects that are relevant to DGF. In addition to a rapid and profound T-cell depletion, rATG inhibits leukocyte migration and adhesion." 42ab6c438bf5a6e0e74cc2dd9192a12f2406ca33,Nonlinear Dimensionality Reduction by Manifold Unfolding,"Nonlinear Dimensionality Reduction y Manifold Unfolding Pooyan Khajehpour Tadavani A thesis presented to the University of Waterloo in fulfillment of the thesis requirement for the degree of Doctor of Philosophy Computer Science Waterloo, Ontario, Canada, 2013 (cid:13) Pooyan Khajehpour Tadavani 2013" 428017f7a6df4d667275c7ac9b3feba39b70e4ae,CNN-RNN: A Unified Framework for Multi-label Image Classification,"CNN-RNN: A Unified Framework for Multi-label Image Classification Jiang Wang1 Yi Yang1 Junhua Mao2 Zhiheng Huang3∗ Chang Huang4∗ Wei Xu1 Baidu Research University of California at Los Angles Facebook Speech Horizon Robotics" 42cc8637a5e7b8203722ba0dca995814f6dfd525,PETS 2016: Dataset and Challenge,"PETS 2016: Dataset and Challenge Luis Patino*, Tom Cane**, Alain Vallee*** and James Ferryman* *University of Reading, Computational Vision Group, Reading RG6 6AY, United Kingdom, {j.l.patinovilchis, **BMT Group Ltd., Teddington TW11 8LZ. United Kingdom, ***SAGEM, 92659 Boulogne-Billancourt, France," 429b8d5bb05e1a580fad0222b9e9496985465e40,"See No Evil, Say No Evil: Description Generation from Densely Labeled Images","Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM 2014), pages 110–120, Dublin, Ireland, August 23-24 2014. (Count:3) Isa: ride, vehicle,… Doing: parking,… Has: steering wheel,… Attrib: black, shiny,… children (Count:2) Isa: kids, children … Doing: biking, riding … Has: pants, bike … Attrib: young, small … bike (Count:1) Isa: bike, bicycle,… Doing: playing,… Has: chain, pedal,… Attrib: silver, white,… women(Count:3) Isa: girls, models,… Doing: smiling,... Has: shorts, bags,… Attrib: young, tan,… purses(Count:3) Isa: accessory,… Doing: containing,… Has: body, straps,… Attrib: black, soft,… sidewalk(Count:1) Isa: sidewalk, street,… Doing: laying,… Has: stone, cracks,… Attrib: flat, wide,… woman(Count:1) Isa: person, female,… Doing: pointing,… Has: nose, legs,… Attrib: tall, skinny,… tree(Count:1) Isa: plant,… Doing: growing,… Has: branches,… Attrib: tall, green,… kids(Count:5) Isa: group, teens,… Doing: walking,… Has: shoes, bags,… Attrib: young,… Fiveyoungpeopleonthestreet,twosharingabicycle.Severalyoungpeoplearewalkingnearparkedvehicles.Threegirlswithlargehandbagswalkingdownthesidewalk.Threewomenwalkdownacitystreet,asseenfromabove.Threeyoungwomanwalkingdownasidewalklookingup.Figure1:Anannotatedimagewithhumangeneratedsen-tencedescriptions.Eachboundingpolygonencompassesoneormoreobjectsandisassociatedwithacountandtextla-bels.Thisimagehas9highlevelobjectsannotatedwithover250textuallabels.tomuchofthevisualcontentneededtogeneratecomplete,human-likesentences.Inthispaper,weinsteadstudygenerationwithmorecompletevisualsupport,asprovidedbyhu-manannotations,allowingustodevelopmorecomprehensivemodelsthanpreviouslyconsid-ered.Suchmodelshavethedualbenefitof(1)providingnewinsightsintohowtoconstructmorehuman-likesentencesand(2)allowingustoper-formexperimentsthatsystematicallystudythecontributionofdifferentvisualcuesingeneration,suggestingwhichautomaticdetectorswouldbemostbeneficialforgeneration.Inanefforttoapproximaterelativelycompletevisualrecognition,wecollectedmanuallylabeledrepresentationsofobjects,parts,attributesandac-tivitiesforabenchmarkcaptiongenerationdatasetthatincludesimagespairedwithhumanauthored" 4263630a35c5ee34ccf9dbd81c0541d92d0c7d5b,Shape Variation-Based Frieze Pattern for Robust Gait Recognition,"Shape Variation-Based Frieze Pattern for Robust Gait Recognition Seungkyu Lee* Yanxi Liu* Robert Collins Dept. of Computer Science and Eng. *Dept. of Electrical Eng. The Penn State University" 42cc9ea3da1277b1f19dff3d8007c6cbc0bb9830,Coordinated Local Metric Learning,"Coordinated Local Metric Learning Shreyas Saxena Jakob Verbeek Inria∗" 421387011b5cdd2cb4a1fdf04728d350741a0ac1,Incidental memory for faces in children with different genetic subtypes of Prader-Willi syndrome,"Social Cognitive and Affective Neuroscience, 2017, 918–927 doi: 10.1093/scan/nsx013 Advance Access Publication Date: 17 February 2017 Original article Incidental memory for faces in children with different genetic subtypes of Prader-Willi syndrome Alexandra P. Key,1,2 and Elisabeth M. Dykens1,3 Vanderbilt Kennedy Center for Research on Human Development, 2Department of Hearing and Speech Sciences, Vanderbilt University Medical Center, and 3Department of Psychology and Human Development, Vanderbilt University, Nashville, TN 37203, USA Correspondence should be addressed to Alexandra P. Key, Vanderbilt Kennedy Center, Peabody Box 74, Vanderbilt University, Nashville, TN 37203, USA. E-mail:" 421b3a33ec70af2d733310f6c83ad713a314951d,Using nasal curves matching for expression robust 3D nose recognition,"Emambakhsh, M., Evans, A. and Smith, M. (2013) Using nasal curves matching for expression robust 3D nose recognition. In: IEEE Con- ference on Biometrics: Theory, Applications and Systems (BTAS2013), Washington DC, USA, September 29th - October 2, 2013. Available from: http://eprints.uwe.ac.uk/20812 We recommend you cite the published version. The publisher’s URL is: http://eprints.uwe.ac.uk/20812/ Refereed: Yes (no note) Disclaimer UWE has obtained warranties from all depositors as to their title in the material deposited and as to their right to deposit such material. UWE makes no representation or warranties of commercial utility, title, or fit- ness for a particular purpose or any other warranty, express or implied in respect of any material deposited. UWE makes no representation that the use of the materials will not infringe ny patent, copyright, trademark or other property or proprietary rights. UWE accepts no liability for any infringement of intellectual property rights in any material deposited but will remove such material from public view pend-" 426b47af132293e9ffe6071a3ede59cfdc1aa3fb,Promoting social behavior with oxytocin in high-functioning autism spectrum disorders.,"Promoting social behavior with oxytocin in high- functioning autism spectrum disorders Elissar Andaria, Jean-René Duhamela, Tiziana Zallab, Evelyn Herbrechtb, Marion Leboyerb, and Angela Sirigua,1 Centre de Neuroscience Cognitive, Unité Mixte de Recherche 5229, Centre National de la Recherche Scientifique, 69675 Bron, France; and bInstitut National de la Santé et de la Recherche Médicale U 841, Department of Psychiatry, Hôpital Chenevier-Mondor, 94000 Créteil, France Edited by Leslie G. Ungerleider, National Institute of Mental Health, Bethesda, MD, and approved January 7, 2010 (received for review September 8, 2009) Social adaptation requires specific cognitive and emotional compe- tences. Individuals with high-functioning autism or with Asperger syndrome cannot understand or engage in social situations despite preserved intellectual abilities. Recently, it has been suggested that oxytocin, a hormone known to promote mother-infant bonds, may e implicated in the social deficit of autism. We investigated the ehavioral effects of oxytocin in 13 subjects with autism. simulated ball game where participants interacted with fictitious partners, we found that after oxytocin inhalation, patients exhibited stronger interactions with the most socially cooperative partner and reported enhanced feelings of trust and preference. Also, during free viewing of pictures of faces, oxytocin selectively increased patients’ gazing time on the socially informative region of the face, namely the eyes. Thus, under oxytocin, patients respond" 423cfa55a14cd92ada32245b416b587ef9c29308,Visually-Grounded Bayesian Word Learning,"Visually-Grounded Bayesian Word Learning Yangqing Jia Joshua Abbott Joseph Austerweil Thomas Griffiths Trevor Darrell Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2012-202 http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-202.html October 17, 2012" 422d352a7d26fef692a3cd24466bfb5b4526efea,Pedestrian interaction in tracking : the social force model and global optimization methods,"Pedestrian interaction in tracking: the social force model and global optimization methods Laura Leal-Taix´e and Bodo Rosenhahn" 42d8a6b1ef5acaaf4640a8974c6f99d60b56090c,Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation,"SUBMIT TO IEEE TRANS. PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. XX, NO. XX, AUGUST 2012 Markerless Motion Capture of Multiple Characters Using Multi-view Image Segmentation Yebin Liu, Juergen Gall Member, IEEE, Carsten Stoll, Qionghai Dai Senior Member, IEEE, Hans-Peter Seidel, and Christian Theobalt" 42afe5fd3f7b1d286a20e9306c6bc8624265f658,FACE DETECTION USING THE 3×3 BLOCK RANK PATTERNS OF GRADIENT MAGNITUDE IMAGES,"Signal & Image Processing : An International Journal (SIPIJ) Vol.4, No.5, October 2013 FACE DETECTION USING THE 3×3 BLOCK RANK PATTERNS OF GRADIENT MAGNITUDE IMAGES Kang-Seo Park, Young-Gon Kim, and Rae-Hong Park Department of Electronic Engineering, School of Engineering, Sogang University, 5 Baekbeom-ro (Sinsu-dong), Mapo-gu, Seoul 121-742, Korea" 4297deda7ea77fb90de2509c763738584b2353de,Beyond one billion time series: indexing and mining very large time series collections with $$i$$ SAX2+,"Knowl Inf Syst DOI 10.1007/s10115-012-0606-6 REGULAR PAPER Beyond one billion time series: indexing and mining very large time series collections with iSAX2+ Alessandro Camerra · Jin Shieh · Themis Palpanas · Thanawin Rakthanmanon · Eamonn Keogh Received: 23 March 2012 / Revised: 23 September 2012 / Accepted: 28 December 2012 © Springer-Verlag London 2013" 428e42f8d5cbffc068e2e5fe8f697c9c9ee113a9,Deep Multimodal Subspace Clustering Networks,"IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, VOL. X, NO. X, SEPTEMBER 21, 2018 Deep Multimodal Subspace Clustering Networks Mahdi Abavisani, Student Member, IEEE and Vishal M. Patel, Senior Member, IEEE" 42f8ef9d5ebf969a7e2b4d1eef4b332db562e5d4,Which Training Methods for GANs do actually Converge?,"Which Training Methods for GANs do actually Converge? Lars Mescheder 1 Andreas Geiger 1 2 Sebastian Nowozin 3" 42d9cb791b8aa3a8658e3ac34e41a1bad1935610,Tracking Sports Players with Context-Conditioned Motion Models,"Tracking Sports Players with Context-Conditioned Motion Models Jingchen Liu1 The Pennsylvania State University Peter Carr2" 423e8cc1a7501066b7e0e5bb1beb5b9592337023,Accurate eye center localization using Snakuscule,"Accurate Eye Center Localization using Snakuscule Abhinav Tripathi Microsoft Research India Edward Cutrell Microsoft Research India Sanyam Garg Microsoft Research India" 4275ef99c717c5dedd88f2e0b578df5216da2183,Facial Face Recognition Method using Fourier Transform Filters,"International Conference on Intelligent Systems and Data Processing (ICISD) 2011 Proceedings published by International Journal of Computer Applications® (IJCA) Facial Face Recognition Method using Fourier Transform Filters Gabor and R_LDA Anissa Bouzalmat Arsalane Zarghili Jamal Kharroubi Sidi Mohamed Ben Abdellah Sidi Mohamed Ben Abdellah Sidi Mohamed Ben Abdellah University University University Department of Computer Department of Computer Department of Computer Science Faculty of Science and Science Faculty of Science and Science Faculty of Science and Technology" 42966f6d506f09f990a42fe422f69895235f9bee,Video-Based Face Recognition and Tracking from a Robot Companion,"1st October 2008 0:25 WSPC/INSTRUCTION FILE Video-based Face Recognition and Tracking from a Robot Companion T.Germa†, F.Lerasle†, T.Simon¶ LAAS-CNRS, Universit´e de Toulouse, Toulouse, FRANCE ¶ IUT Figeac, LRPmip-Perceval, avenue de Nayrac, 46100 Figeac, France http://www.laas.fr/∼tgerma/hri This paper deals with video-based face recognition and tracking from a camera mounted on a mobile robot companion. All persons must be logically identified before being uthorized to interact with the robot while continuous tracking is compulsory in order to estimate the person’s approximate position. A first contribution relates to experiments of still-image-based face recognition methods in order to check which image projection nd classifier associations give the highest performance of the face database acquired from our robot. Our approach, based on Principal Component Analysis (PCA) and Support Vector Machines (SVM) improved by genetic algorithm optimization of the free- parameters, is found to outperform conventional appearance-based holistic classifiers (eigenface and Fisherface) which are used as benchmarks. Relative performances are nalyzed by means of Receiver Operator Characteristics which systematically provide optimized classifier free-parameter settings. Finally, for the SVM-based classifier, we propose a non-dominated sorting genetic algorithm to obtain optimized free-parameter" 4265269bc894caa97efbfcfe5b83da7413f86a30,Asymmetric Tri-training for Unsupervised Domain Adaptation,"Asymmetric Tri-training for Unsupervised Domain Adaptation Kuniaki Saito 1 Yoshitaka Ushiku 1 Tatsuya Harada 1" 426c39358d592be673b72d26dad4560b06ec5d89,Human Trajectory Prediction using Spatially aware Deep Attention Models,"Human Trajectory Prediction using Spatially aware Deep Attention Models Daksh Varshneya IIIT-B∗ G. Srinivasaraghavan IIIT-B ∗" 4273a9d1605a69ac66440352b92ebeb230fd34f6,Simple Test Procedure for Image-based Biometric Veriication Systems,"SimpleTestProcedureforImage-BasedBiometric Veri(cid:12)cationSystems C.L.Wilson,R.M.McCabe InformationTechnologyLaboratory NationalInstituteofStandardsandTechnology Gaithersburg,MD" 429d4848d03d2243cc6a1b03695406a6de1a7abd,"Identification Mode, it is process of one-to-many comparison of the test set with database to identify an unknown","Face Recognition based on Logarithmic Fusion International Journal of Soft Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-3, July 2012 of SVD and KT Ramachandra A C, Raja K B, Venugopal K R, L M Patnaik" 42a6ae6827f8cc92e15191e53605b0aa4f875fb9,Challenges in Autonomous Vehicle Testing and Validation,"Preprint: 2016 SAE World Congress 016-01-0128 / 16AE-0265 Challenges in Autonomous Vehicle Testing and Validation Philip Koopman & Michael Wagner Carnegie Mellon University; Edge Case Research LLC" 424e52158b43e40f356af7eafb35c91a9e13db30,"Impact Factor : 3 . 449 ( ISRA ) , Impact Factor : 2 .","[Randive, 4(1): January, 2015] ISSN: 2277-9655 Scientific Journal Impact Factor: 3.449 (ISRA), Impact Factor: 2.114 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY AN INNOVATIVE APPROACH FOR PLASTIC SURGERY FACE RECOGNITION-A Mahendra P. Randive *, Prof. Umesh W. Hore REVIEW *Student of M.E. Department of Electronics & Telecommunication Engineering, P. R. Patil College of Engineering, Amravati Maharashtra – India." 42e898ca773dbd9e085ffa824c21d0bfda245345,LOTS about attacking deep features,"This is a pre-print of the original paper accepted at the International Joint Conference on Biometrics (IJCB) 2017. LOTS about Attacking Deep Features Andras Rozsa, Manuel G¨unther, and Terrance E. Boult Vision and Security Technology (VAST) Lab University of Colorado, Colorado Springs, USA" 4270460b8bc5299bd6eaf821d5685c6442ea179a,"Partial Similarity of Objects, or How to Compare a Centaur to a Horse","Int J Comput Vis (2009) 84: 163–183 DOI 10.1007/s11263-008-0147-3 Partial Similarity of Objects, or How to Compare a Centaur to a Horse Alexander M. Bronstein · Michael M. Bronstein · Alfred M. Bruckstein · Ron Kimmel Received: 30 September 2007 / Accepted: 3 June 2008 / Published online: 26 July 2008 © Springer Science+Business Media, LLC 2008" 42e155ea109eae773dadf74d713485be83fca105,Sparse reconstruction of facial expressions with localized gabor moments, 42c645df49106b68a71abe757ac13245db4be394,A New Method of Illumination Normalization for Robust Face Recognition,"A New Method of Illumination Normalization for Robust Face Recognition Young Kyung Park, Bu Cheon Min, and Joong Kyu Kim School of Information and Communication Engineering, SungKyunKwan University. 00, Chun-Chun-Dong, Chang-An-Ku, Suwon, Korea 440-746 {multipym," 4212a93f011aa47c6344c0cdc3e991740d8c7c04,Zero-Shot Kernel Learning,"Zero-Shot Kernel Learning Hongguang Zhang∗,2,1 Piotr Koniusz∗,1,2 Data61/CSIRO, 2Australian National University nu.edu.au2}" 42832bcb36ee3f69327c38d0d17e6e2a73aaa2a6,SUN Database: Exploring a Large Collection of Scene Categories,"Int J Comput Vis DOI 10.1007/s11263-014-0748-y SUN Database: Exploring a Large Collection of Scene Categories Jianxiong Xiao · Krista A. Ehinger · James Hays · Antonio Torralba · Aude Oliva Received: 9 June 2013 / Accepted: 2 July 2014 © Springer Science+Business Media New York 2014" 42dadeee13686e555435f9426cb9840fc085b23a,Challenges in Designing Datasets and Validation for Autonomous Driving,"CHALLENGES IN DESIGNING DATASETS AND VALIDATION FOR AUTONOMOUS DRIVING Michal Uˇriˇc´aˇr1, David Hurych1, Pavel Kˇr´ıˇzek1 and Senthil Yogamani2 Valeo R&D DVS, Prague, Czech Republic {michal.uricar, david.hurych, Valeo Vision Systems, Tuam, Ireland Keywords: Visual Perception, Design of Datasets, Validation Scheme, Automated Driving." 42e0d7fe2039b075ac2372d883fa994eb0a68b48,Learning human actions in video,"Learning human actions in video Alexander Klaser To cite this version: Alexander Klaser. Learning human actions in video. Modeling and Simulation. Institut Na- tional Polytechnique de Grenoble - INPG, 2010. English. HAL Id: tel-00514814 https://tel.archives-ouvertes.fr/tel-00514814 Submitted on 3 Sep 2010 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires publics ou priv´es." 42954bb6babed6fc16646c6f34083b720593cce9,Bringing Order in the Bag of Words,"BRINGING ORDER IN THE BAG OF WORDS Shihong Zhang, Rahat Khan, Damien Muselet and Alain Tr´emeau Universit´e de Lyon, F-42023, Saint- ´Etienne, France CNRS, UMR 5516, Laboratoire Hubert Curien, F-42000, Saint- ´Etienne, France Universit´e de Saint- ´Etienne, Jean-Monnet, F-42000, Saint- ´Etienne, France Keywords: Bag-of-words, Object Categorization, Spatial Information." 42df75080e14d32332b39ee5d91e83da8a914e34,Illumination Compensation Using Oriented Local Histogram Equalization and its Application to Face Recognition,"Illumination Compensation Using Oriented Local Histogram Equalization and Its Application to Face Recognition Ping-Han Lee, Szu-Wei Wu, and Yi-Ping Hung" 426840ccf74bbd8b087cf357efdb80ecc85ea2ab,Reduced Analytic Dependency Modeling: Robust Fusion for Visual Recognition,"Noname manuscript No. (will be inserted by the editor) Reduced Analytic Dependency Modeling: Robust Fusion for Visual Recognition Andy J Ma · Pong C Yuen Received: date / Accepted: date" 42dc36550912bc40f7faa195c60ff6ffc04e7cd6,Visible and Infrared Face Identification via Sparse Representation,"Hindawi Publishing Corporation ISRN Machine Vision Volume 2013, Article ID 579126, 10 pages http://dx.doi.org/10.1155/2013/579126 Research Article Visible and Infrared Face Identification via Sparse Representation Pierre Buyssens1 and Marinette Revenu2 LITIS EA 4108-QuantIF Team, University of Rouen, 22 Boulevard Gambetta, 76183 Rouen Cedex, France GREYC UMR CNRS 6072 ENSICAEN-Image Team, University of Caen Basse-Normandie, 6 Boulevard Mar´echal Juin, 4050 Caen, France Correspondence should be addressed to Pierre Buyssens; Received 4 April 2013; Accepted 27 April 2013 Academic Editors: O. Ghita, D. Hernandez, Z. Hou, M. La Cascia, and J. M. Tavares Copyright © 2013 P. Buyssens and M. Revenu. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly ited. We present a facial recognition technique based on facial sparse representation. A dictionary is learned from data, and patches extracted from a face are decomposed in a sparse manner onto this dictionary. We particularly focus on the design of dictionaries that play a crucial role in the final identification rates. Applied to various databases and modalities, we show that this approach" fab0d19c58815eccb0db7215fe45d6a32066ca1c,Inferring Human Attention by Learning Latent Intentions,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) the mug's statuschecking the book's statuslocating the dispenserFigure1:Humanattentionandintentionsina3Dscene.thedispenser,hisattentionsweepsfromthetabletothedis-penser;whilefetchingwaterfromthedispenser,hisintentionistocheckifthemugisfullandhisattentionsteadilyfocusesonthemug.Thedrivingrulesofintentionsactingonattentioncanbeindependentofactivitycategories.Forexample,inFigure1,theattentiondrivenbytheintentioncheckingstatusalwayspresentsassteadilyfocusing,evenindifferentactivities.Thisphenomenonmakesitpossibletoinfertheattentionwiththesamerulesacrossdifferentactivities.However,thesedrivingrulesarehiddenandshouldbelearnedfromdata.Thispaperproposesaprobabilisticmethodtoinfer3Dhu-manattentionbyjointlymodelingattention,intentions,andtheirinteractions.Theattentionandintentionarerepresent-edwithfeaturesextractedfromhumanskeletonsandscenevoxels.Humanintentionsaretakenaslatentvariableswhichguidethemotionsandformsofhumanattention.Conversely,thehumanattentionrevealstheintentionfeatures.Attentioninferenceismodeledasajointoptimizationwithlatenthu-manintentions.WeadoptanEM-based[Bishop,2006]approachtolearnthemodelparametersandminethelatentintentions.Giv-enanRGB-DvideowithhumanskeletonscapturedbytheKinectcamera,ajoint-statedynamicprogrammingalgorithm" fa08a4da5f2fa39632d90ce3a2e1688d147ece61,Supplementary material for “ Unsupervised Creation of Parameterized Avatars ” 1 Summary of Notations,"Supplementary material for “Unsupervised Creation of Parameterized Avatars” Summary of Notations Tab. 1 itemizes the symbols used in the submission. Fig. 2,3,4 of the main text illustrate many of these symbols. DANN results Fig. 1 shows side by side samples of the original image and the emoji generated by the method of [1]. As can be seen, these results do not preserve the identity very well, despite considerable effort invested in finding suitable architectures. Multiple Images Per Person Following [4], we evaluate the visual quality that is obtained per person and not just per image, by testing TOS on the Facescrub dataset [3]. For each person p, we considered the set of their images Xp, and selected the emoji that was most similar to their source image, i.e., the one for which: ||f (x) − f (e(c(G(x))))||. rgmin Fig. 2 depicts the results obtained by this selection method on sample images form the Facescrub dataset (it is an extension of Fig. 7 of the main text). The figure also shows, for comparison, the DTN [4] result for the same image. Detailed Architecture of the Various Networks In this section we describe the architectures of the networks used in for the emoji and avatar experiments." faf40ce28857aedf183e193486f5b4b0a8c478a2,Automated Human Identification Using Ear Imaging,"Imperial Journal of Interdisciplinary Research (IJIR) Vol.2, Issue-1 , 2016 ISSN : 2454-1362 , www.onlinejournal.in Automated Human Identification Using Ear Imaging Priya Thakare SITS.Narhe Abhijit Patil SITS, Narhe. Priya More SITS, Narhe. Vivek Patil SITS, Narhe. Akshay Shende SITS, Narhe. Reliability in human authentication from airport surveillance important aspect for the security requirements in various pplications ranging electronic banking. Many physical characteristics of" fab83bf8d7cab8fe069796b33d2a6bd70c8cefc6,Draft : Evaluation Guidelines for Gender Classification and Age Estimation,"Draft: Evaluation Guidelines for Gender Classification and Age Estimation Tobias Gehrig, Matthias Steiner, Hazım Kemal Ekenel {tobias.gehrig, July 1, 2011 Introduction In previous research on gender classification and age estimation did not use a standardised evaluation procedure. This makes comparison the different ap- proaches dif‌f‌icult. Thus we propose here a benchmarking and evaluation protocol for gender lassification as well as age estimation to set a common ground for future re- search in these two areas. The evaluations are designed such that there is one scenario under controlled labratory conditions and one under uncontrolled real life conditions. The datasets were selected with the criteria of being publicly available for research purposes. File lists for the folds corresponding to the individual benchmarking proto- ols will be provided over our website at http://face.cs.kit.edu/befit. We will provide two kinds of folds for each of the tasks and conditions: one set of folds using the whole dataset and one set of folds using a reduced dataset, which" fae4185a5fc540b057ea9e0402223e653327d0f9,Structured Edge Detection for Improved Object Localization using the Discriminative Generalized Hough Transform, fa11590fea86049fff1eb412642753422738c584,Depression-related difficulties disengaging from negative faces are associated with sustained attention to negative feedback during social evaluation and predict stress recovery,"RESEARCH ARTICLE Depression-related difficulties disengaging from negative faces are associated with sustained attention to negative feedback during social evaluation and predict stress recovery Alvaro Sanchez*, Nuria Romero, Rudi De Raedt Department of Experimental Clinical and Health Psychology, Ghent University, Ghent, Belgium" fa60521dabd2b64137392b4885e4d989f4b86430,Physics-Based Generative Adversarial Models for Image Restoration and Beyond,"Physics-Based Generative Adversarial Models for Image Restoration and Beyond Jinshan Pan, Yang Liu, Jiangxin Dong, Jiawei Zhang, Jimmy Ren, Jinhui Tang, Yu-Wing Tai and Ming-Hsuan Yang" faccce1a55c0c0ac767b74782c862a3eed0d1065,SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception,"SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception Yue Meng1 Yongxi Lu1 Tara Javidi1 Aman Raj1 Gaurav Bansal2 Samuel Sunarjo1 Dinesh Bharadia1 Rui Guo2 UC San Diego Toyota InfoTechnology Center {yum107, yol070, amraj, ssunarjo, tjavidi," fabbc7f921d77b5aa9157310df29ad81367fe92d,Efficient Image and Video Representations for Retrieval, fad895771260048f58d12158a4d4d6d0623f4158,Audio-visual emotion recognition for natural human-robot interaction,"Audio-Visual Emotion Recognition For Natural Human-Robot Interaction Dissertation zur Erlangung des akademischen Grades Doktor der Ingenieurwissenschaften (Dr.-Ing.) vorgelegt von Ahmad Rabie n der Technischen Fakultät der Universität Bielefeld 5. März 2010" fafa7bbd6b37dc97237155654e1a4d1f1aba70f8,Radial Basis Function Neuroscaling Algorithms for Efficient Facial Image Recognition,"Machine Learning Research 017; 2(4): 152-168 http://www.sciencepublishinggroup.com/j/mlr doi: 10.11648/j.mlr.20170204.16 Radial Basis Function Neuroscaling Algorithms for Efficient Facial Image Recognition Vincent A. Akpan1, *, Joshua B. Agbogun2, Michael T. Babalola3, Bamidele A. Oluwade4 Department of Biomedical Technology, The Federal University of Technology, Akure, Nigeria Department of Computer Science, Kogi State University, Anyigba, Nigeria Department of Physics Electronics, Afe Babalola University, Ado-Ekiti, Nigeria Department of Computer Science, University of Ilorin, Ilorin, Nigeria Email address: (V. A. Akpan), (J. B. Agbogun), (M. T. Babalola), (B. A. Oluwade) *Corresponding author To cite this article: Vincent A. Akpan, Joshua B. Agbogun, Michael T. Babalola, Bamidele A. Oluwade. Radial Basis Function Neuroscaling Algorithms for Efficient Facial Image Recognition. Machine Learning Research. Vol. 2, No. 4, 2017, pp. 152-168. doi: 10.11648/j.mlr.20170204.16 Received: September 30, 2017; Accepted: November 9, 2017; Published: December 28, 2017" facdb71e8175c33ec54c2248fa6cfc319e27cfa5,Accelerating Machine Learning Research with MI-Prometheus,"Accelerating Machine Learning Research with MI-Prometheus Tomasz Kornuta Vincent Marois Ryan L. McAvoy Younes Bouhadjar Alexis Asseman Vincent Albouy IBM Research AI, Almaden Research Center, San Jose, USA T.S. Jayram Ahmet S. Ozcan {tkornut, vmarois, mcavoy, byounes, jayram, {alexis.asseman," fa307dac56600e8fe8a0ee03830ed72b014208e3,Descripteurs d ’ images locaux et méthodes par noyaux pour la classification de textures et de catégories d ’ objets : une étude approfondie,"INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study Jianguo Zhang — Marcin Marszałek — Svetlana Lazebnik — Cordelia Schmid N° 5737 Octobre 2005 Th`eme COG p p o r t (cid:13) (cid:13) d e r e c h e r c h e (cid:13)" fafe69a00565895c7d57ad09ef44ce9ddd5a6caa,Gaussian Mixture Models for Human Face Recognition under Illumination Variations,"Applied Mathematics, 2012, 3, 2071-2079 http://dx.doi.org/10.4236/am.2012.312A286 Published Online December 2012 (http://www.SciRP.org/journal/am) Gaussian Mixture Models for Human Face Recognition under Illumination Variations Information Systems and Decision Sciences Department, Mihaylo College of Business and Economics, California State University, Fullerton, USA Email: Sinjini Mitra Received August 18, 2012; revised September 18, 2012; accepted September 25, 2012" fac36fa1b809b71756c259f2c5db20add0cb0da0,Transferring GANs: Generating Images from Limited Data,"Transferring GANs: generating images from limited data Yaxing Wang, Chenshen Wu, Luis Herranz, Joost van de Weijer, Abel Gonzalez-Garcia, Bogdan Raducanu {yaxing, chenshen, lherranz, joost, agonzgarc, Computer Vision Center Universitat Aut`onoma de Barcelona, Spain" fa2603efaf717974c77162c93d800defae61a129,Face recognition/detection by probabilistic decision-based neural network,"Face Recognition/Detection by Probabilistic Decision-Based Neural Network Shang-Hung Lin, Sun-Yuan Kung, Fellow, IEEE, and Long-Ji Lin" faca1c97ac2df9d972c0766a296efcf101aaf969,Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition,"Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition C´esar Roberto de Souza1,2, Adrien Gaidon1, Eleonora Vig3, Antonio Manuel L´opez2 Computer Vision Group, Xerox Research Center Europe, Meylan, France Centre de Visi´o per Computador, Universitat Aut`onoma de Barcelona, Bellaterra, Spain German Aerospace Center, Wessling, Germany {cesar.desouza," facf25e1880d23eb993d4ad507256ebbc7e0d82d,CURE-OR: Challenging Unreal and Real Environments for Object Recognition,"Citation D. Temel, J. Lee, and G. AlRegib, “CURE-OR: Challenging unreal and real environments for object recognition,” 2018 17th IEEE International Conference on Machine Learning nd Applications (ICMLA), Orlando, Florida, USA, 2018. Dataset https://ghassanalregib.com/cure-or/ ICMLA, uthor={D. Temel and J. Lee and G. AlRegib}, ooktitle={2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)}, title={CURE-OR: Challenging unreal and real environments for object recognition}, year=2018,} Copyright c(cid:13)2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Contact https://ghassanalregib.com/ http://cantemel.com/" fa24bf887d3b3f6f58f8305dcd076f0ccc30272a,Interval Insensitive Loss for Ordinal Classification,"JMLR: Workshop and Conference Proceedings 39:189–204, 2014 ACML 2014 Interval Insensitive Loss for Ordinal Classification Kostiantyn Antoniuk Vojtˇech Franc V´aclav Hlav´aˇc Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Technick´a 2, 166 27 Prague 6 Czech Republic Editor: Dinh Phung and Hang Li" fa496716a5b8520e94a0126b5baa4f636623c997,Revisiting Knowledge Transfer for Training Object Class Detectors,"Revisiting knowledge transfer for training object class detectors Jasper R. R. Uijlings S. Popov V. Ferrari Google AI Perception" fad721b7af838964c98bbb3ebb3f6265b83f950d,Adult Image Content Classification Using Global Features and Skin Region Detection,"Adult Image Content Classification Using Global Features and Skin Region Detection Hakan Sevimli1,2, Ersin Esen1,3, Tuğrul K. Ateş1,3, Ezgi C. Ozan1,3, Mashar Tekin1,2, K. Berker Loğoğlu1,4, Ayça Müge Sevinç1,4, Ahmet Saracoğlu1,3, Adnan Yazıcı2 and A. Aydın Alatan3 TÜBİTAK Space Technologies Research Institute Department of Computer Engineering, M.E.T.U. Department of Electrical and Electronics Engineering, M.E.T.U. Graduate School of Informatics, M.E.T.U. {hakan.sevimli, ersin.esen, tugrul.ates, ezgican.ozan, mashar.tekin, berker.logoglu, muge.sevinc," faa111d749eb228c686643e4667dd1bc21c724f2,Condensed from Video Sequences for Place Recognition,"Boosting Descriptors Condensed from Video Sequences for Place Recognition Tat-Jun Chin, Hanlin Goh and Joo-Hwee Lim Institute for Infocomm Research 1 Heng Mui Keng Terrace, Singapore 119613. {tjchin, hlgoh," fac0151ed0494caf10c7d778059f176ba374e29c,Recognising Complex Mental States from Naturalistic Human-Computer Interactions,"Copyright and use of this thesis This thesis must be used in accordance with the provisions of the Copyright Act 1968. Reproduction of material protected by copyright may be an infringement of copyright and opyright owners may be entitled to take legal action against persons who infringe their opyright. Section 51 (2) of the Copyright Act permits n authorized officer of a university library or rchives to provide a copy (by communication or otherwise) of an unpublished thesis kept in the library or archives, to a person who satisfies the authorized officer that he or she requires the reproduction for the purposes of research or study. The Copyright Act grants the creator of a work number of moral rights, specifically the right of ttribution, the right against false attribution and the right of integrity." fa23122db319440fb5a7253e19709f992b4571b9,Human Age Estimation via Geometric and Textural Features,"HUMAN AGE ESTIMATION VIA GEOMETRIC AND TEXTURAL FEATURES Merve Kilinc1 and Yusuf Sinan Akgul2 TUBITAK BILGEM UEKAE, Anibal Street, 41470, Gebze, Kocaeli, Turkey GIT Vision Lab∗, Department of Computer Engineering, Gebze Institute of Technology, 41400, Kocaeli, Turkey Keywords: Age Estimation, Age Classification, Geometric Features, LBP, Gabor, LGBP, Cross Ratio, FGNET, MORPH." fa4ff855ca125b986bcb2bc6b71bef2ae8fde1cf,"3d Integral Invariant Signatures and Their Application on Face Recognition Dedication I Am Grateful for the Support and Guidance I Have Received from Dr. Irina A. Kogan, and I Also Express My Gratitude To", fa4544e5dce135c3d0517304ec9e620c78267891,LIDAR-based driving path generation using fully convolutional neural networks,"LIDAR-based Driving Path Generation Using Fully Convolutional Neural Networks Luca Caltagirone∗, Mauro Bellone, Lennart Svensson, Mattias Wahde" fab7f1af3d67c7b7cf76ec1d8dfcb265da61a572,Towards Recommender Systems for Police Photo Lineup,"Towards Recommender Systems for Police Photo Lineup Ladislav Peska Department of Software Engineering Hana Trojanova Department of Psychology Faculty of Mathematics and Physics, Charles University, Prague Faculty of Arts, Charles University, Prague Czech Republic Czech Republic" fab6e12a913223b69e1b9f0672df6c89275b1ed0,Initial Development of a Learners ’ Ratified Acceptance of Multibiometrics Intentions Model ( RAMIM ),"Interdisciplinary Journal of E-Learning and Learning Objects IJELLO special series of Chais Conference 2009 best papers Volume 5, 2009 Initial Development of a Learners’ Ratified Acceptance of Multibiometrics Intentions Model (RAMIM) Yair Levy GSCIS, Nova Southeastern University, Ft. Lauderdale, FL, USA Michelle M. Ramim Nova Southeastern University, Huizenga School of Business, Ft. Lauderdale, FL, USA" fa4e1906e120c07116858f059c17abfbfa7f145b,Face Recognition Using Chain Codes,"Journal of Signal and Information Processing, 2013, 4, 154-157 doi:10.4236/jsip.2013.43B027 Published Online August 2013 (http://www.scirp.org/journal/jsip) Face Recognition Using Chain Codes Nazmeen B. Boodoo-Jahangeer, Sunilduth Baichoo Department of Computer Science, University of Mauritius, Reduit, Mauritius. Email: Received May, 2013." fa9f1b236d0a252d4a56e26e8a9a41d496803413,Face Recognition Method with Two-Dimensional HMM,"FACE RECOGNITION METHOD WITH TWO-DIMENSIONAL HMM Janusz Bobulski1 Czestochowa University of Technology Institute of Computer and Information Science Dabrowskiego Street 73, 42-200 Czestochowa, Poland." fa95ce52d821499547a68048d35f35a0dd171a25,Forecast the Plausible Paths in Crowd Scenes,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 670637d0303a863c1548d5b19f705860a23e285c,Face swapping: automatically replacing faces in photographs,"Face Swapping: Automatically Replacing Faces in Photographs Dmitri Bitouk Neeraj Kumar Samreen Dhillon∗ Columbia University† Peter Belhumeur Shree K. Nayar Figure 1: We have developed a system that automatically replaces faces in an input image with ones selected from a large collection of face images, obtained by applying face detection to publicly available photographs on the internet. In this example, the faces of (a) two people are shown after (b) automatic replacement with the top three ranked candidates. Our system for face replacement can be used for face de-identification, personalized face replacement, and creating an appealing group photograph from a set of “burst” mode images. Original images in (a) used with permission from Retna Ltd. (top) and Getty Images Inc. (bottom). Rendering, Computational Photography Introduction Advances in digital photography have made it possible to cap- ture large collections of high-resolution images and share them on the internet. While the size and availability of these col- lections is leading to many exciting new applications, lso creating new problems. One of the most important of" 67c30688bd46d305c610a83a0b28e86e10ef5cc4,Ship Detection in Harbour Surveillance based on Large-Scale Data and CNNs, 67dca0d4b87ab2a4f18b5a1ef76f6ba17b599245,Top-Down Regularization of Deep Belief Networks,"Top-Down Regularization of Deep Belief Networks Hanlin Goh∗, Nicolas Thome, Matthieu Cord Laboratoire d’Informatique de Paris 6 UPMC – Sorbonne Universit´es, Paris, France Joo-Hwee Lim† Institute for Infocomm Research A*STAR, Singapore" 6740f4918d594094f5eca3c0c65006c9c6d6c1d4,Class Room Attendance System Using Facial Recognition System,"The International Journal of Mathematics, Science, Technology and Management (ISSN : 2319-8125) Vol. 2 Issue 3 Class Room Attendance System Using Facial Recognition System Abhishek Jha ABES Engineering College, Ghaziabad" 67751b7ce7f934ffadcf095f4189b31f890e9fdc,Pilot Comparative Study of Different Deep Features for Palmprint Identification in Low-Quality Images,"Ninth Hungarian Conference on Computer Graphics and Geometry, Budapest, 2018 Pilot Comparative Study of Different Deep Features for Palmprint Identification in Low-Quality Images A.S. Tarawneh1, D. Chetverikov1,2 and A.B. Hassanat3 Eötvös Loránd University, Budapest, Hungary Institute for Computer Science and Control, Budapest, Hungary Mutah University, Karak, Jordan" 677585ccf8619ec2330b7f2d2b589a37146ffad7,A flexible model for training action localization with varying levels of supervision,"A flexible model for training action localization with varying levels of supervision Guilhem Chéron∗ 1 2 Jean-Baptiste Alayrac∗ 1 Ivan Laptev1 Cordelia Schmid2" 67126ad0af544740c455311d08cb180aec830a6c,Generating Descriptions of Spatial Relations between Objects in Images,"Proceedings of the 15th European Workshop on Natural Language Generation (ENLG), pages 100–104, Brighton, September 2015. c(cid:13)2015 Association for Computational Linguistics" 67484723e0c2cbeb936b2e863710385bdc7d5368,Anchor Cascade for Efficient Face Detection,"Anchor Cascade for Efficient Face Detection Baosheng Yu and Dacheng Tao, Fellow, IEEE" 6737a429dd615a0d9ac78d836c6b65bfd9ec36e8,Image Classification by Transfer Learning Based on the Predictive Ability of Each Attribute,"Image Classification by Transfer Learning Based on the Predictive Ability of Each Attribute Masahiro Suzuki, Haruhiko Sato, Satoshi Oyama, and Masahito Kurihara" 6733adb12458678c606759233f6f55782bace372,Photogenic Facial Expression Discrimination,"PHOTOGENIC FACIAL EXPRESSION DISCRIMINATION Luana Bezerra Batista and Herman Martins Gomes Departamento de Sistemas e Computação João Marques de Carvalho Departamento de Engenharia Elétrica Universidade Federal de Campina Grande Campina Grande, Paraíba, Brasil, 58.109-970 Keywords: Facial Expression Recognition, Photogeny, Principal Component Analysis, Multi-Layer Perceptron." 67490b6f34c827f107b046adeef0f5476132d4f8,"How good are detection proposals, really?","J. HOSANG ET AL.: HOW GOOD ARE DETECTION PROPOSALS, REALLY? How good are detection proposals, really? Jan Hosang http://mpi-inf.mpg.de/~jhosang Rodrigo Benenson http://mpi-inf.mpg.de/~benenson Bernt Schiele http://mpi-inf.mpg.de/~schiele MPI Informatics Saarbrücken, Germany" 675b2caee111cb6aa7404b4d6aa371314bf0e647,AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions,"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions Chunhui Gu∗ Yeqing Li∗ Chen Sun∗ David A. Ross∗ Sudheendra Vijayanarasimhan∗ Carl Vondrick∗ George Toderici∗ Caroline Pantofaru∗ Susanna Ricco∗ Rahul Sukthankar∗ Cordelia Schmid† ∗ Jitendra Malik‡ ∗" 679aded003bce19aa7821295117693b9a5b4f0ef,Fluid Annotation: A Human-Machine Collaboration Interface for Full Image Annotation,"Fluid Annotation: A Human-Machine Collaboration Interface for Full Image Annotation Mykhaylo Andriluka∗ Jasper R. R. Uijlings∗ Google Research Z¨urich, Switzerland Vi(cid:138)orio Ferrari" 67bf0b6bc7d09b0fe7a97469f786e26f359910ef,Abnormal use of facial information in high-functioning autism.,"J Autism Dev Disord DOI 10.1007/s10803-006-0232-9 O R I G I N A L P A P E R Abnormal Use of Facial Information in High-Functioning Autism Michael L. Spezio Æ Ralph Adolphs Æ Robert S. E. Hurley Æ Joseph Piven Ó Springer Science+Business Media, LLC 2006" 678b367b2d5250f278c994238bbf816098252d9d,IrisDenseNet: Robust Iris Segmentation Using Densely Connected Fully Convolutional Networks in the Images by Visible Light and Near-Infrared Light Camera Sensors,"Article IrisDenseNet: Robust Iris Segmentation Using Densely Connected Fully Convolutional Networks in the Images by Visible Light and Near-Infrared Light Camera Sensors Muhammad Arsalan, Rizwan Ali Naqvi, Dong Seop Kim, Phong Ha Nguyen, Muhammad Owais nd Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (M.A.); (R.A.N.); (D.S.K.); (P.H.N.); (M.O.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 2 April 2018; Accepted: 8 May 2018; Published: 10 May 2018" 67e00f7e928e6eab0faf1917252778b36bf64e39,Sparse radial sampling LBP for writer identification,"Sparse Radial Sampling LBP for Writer Identification Anguelos Nicolaou∗, Andrew D. Bagdanov∗, Marcus Liwicki†, and Dimosthenis Karatzas∗ Computer Vision Center, Edifici O, Universitad Autonoma de Barcelona,Bellaterra, Spain DIVA research group, Department of Informatics, University of Fribourg, Switzerland Email:" 67bee729d046662c6ebd9d3d695823c9d820343a,Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus,"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 588–598, Berlin, Germany, August 7-12, 2016. c(cid:13)2016 Association for Computational Linguistics" 674fcadf1b895e3a79380d3ac5afb43d406fd31a,Facial Asymmetry Assessment from 3D Shape Sequences: The Clinical Case of Facial Paralysis, 6769cfbd85329e4815bb1332b118b01119975a95,Tied Factor Analysis for Face Recognition Across Large Pose Changes,"Tied factor analysis for face recognition across large pose changes" 67f88f37e4853b870debef2bd29b257b5b19f255,EgoSampling: Wide View Hyperlapse from Single and Multiple Egocentric Videos,"EgoSampling: Wide View Hyperlapse from Single and Multiple Egocentric Videos Tavi Halperin Yair Poleg Chetan Arora Shmuel Peleg" 67a6bd37e91f2c334b1092fd9e9b16be93f82377,Data Driven Visual Recognition,"Data Driven Visual Recognition OMID AGHAZADEH Doctoral Thesis Stockholm, Sweden, 2014" 6768b558cc58e113096540c123ef3b2c2d2469a1,Maximum Margin Linear Classifiers in Unions of Subspaces,"LYU, ZEPEDA, PÉREZ: US-SVM Maximum Margin Linear Classifiers in Unions of Subspaces Xinrui Lyu1,2 Joaquin Zepeda1 Patrick Pérez1 Technicolor 5576, Cesson-Sevigne, France École Polytechnique Fédérale de Lausanne (EPFL) CH-1015, Lausanne, Switzerland" 67da607541b8e380c1665c2158e5e0dd4a6f0e49,Learning to Localize Sound Source in Visual Scenes, 6752b59da83c03e64c73f9248a67304713b6efa9,Chapter 3 Re-identification by Covariance Descriptors,"Chapter 3 Re-identification by Covariance Descriptors Sławomir B ˛ak and François Brémond" 67f42733a8d147bc432bc79171a7c976e99374b3,Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks,"Short-term Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks Nemanja Djuric, Vladan Radosavljevic, Henggang Cui, Thi Nguyen, Fang-Chieh Chou, Tsung-Han Lin and Jeff Schneider1" 67c78fbef7ebcde1b8c4e42415e595fb78317133,Optimization of Face Recognition Algorithms for Smartphone Environment,"International Journal of Security and Its Applications Vol.7, No.6 (2013), pp.303-308 http://dx.doi.org/10.14257/ijsia.2013.7.6.31 Optimization of Face Recognition Algorithms for Smartphone Environment Kanghun Jeong, Dongil Han and Hyeonjoon Moon School of Computer Science and Engineering, Sejong University, Seoul, Korea E-mail:" 67c703a864aab47eba80b94d1935e6d244e00bcb,Face Retrieval Based On Local Binary Pattern and Its Variants : A Comprehensive Study,"(IJACSA) International Journal of Advanced Computer Science and Applications Vol. 7, No. 6, 2016 Face Retrieval Based On Local Binary Pattern and Its Variants: A Comprehensive Study Department of Computer Vision and Robotics, University of Science, VNU-HCM, Viet Nam Phan Khoi, Lam Huu Thien, Vo Hoai Viet face searching," 6720edcea05b31a9b9a6db98ee71e8ed31efdc38,Practices in source code sharing in astrophysics,"Practices source sharing astrophysics Shamir1, Wallin2, Alice Allen3, Bruce Berriman4, Peter Teuben5, Robert Nemiroff6, Jessica Mink7, Robert Hanisch8, Kimberly DuPrie3" 6757254d27b761ada5dbd88642bd0112fcb962cf,Gait Recognition Using Wearable Motion Recording Sensors,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2009, Article ID 415817, 16 pages doi:10.1155/2009/415817 Research Article Gait Recognition Using Wearable Motion Recording Sensors Davrondzhon Gafurov and Einar Snekkenes Norwegian Information Security Laboratory, Gjøvik University College, P.O. Box 191, 2802 Gjøvik, Norway Correspondence should be addressed to Davrondzhon Gafurov, Received 1 October 2008; Revised 26 January 2009; Accepted 26 April 2009 Recommended by Natalia A. Schmid This paper presents an alternative approach, where gait is collected by the sensors attached to the person’s body. Such wearable sensors record motion (e.g. acceleration) of the body parts during walking. The recorded motion signals are then investigated for person recognition purposes. We analyzed acceleration signals from the foot, hip, pocket and arm. Applying various methods, the best EER obtained for foot-, pocket-, arm- and hip- based user authentication were 5%, 7%, 10% and 13%, respectively. Furthermore, we present the results of our analysis on security assessment of gait. Studying gait-based user authentication (in case of hip motion) under three attack scenarios, we revealed that a minimal effort mimicking does not help to improve the acceptance hances of impostors. However, impostors who know their closest person in the database or the genders of the users can be a threat to gait-based authentication. We also provide some new insights toward the uniqueness of gait in case of foot motion. In particular, we revealed the following: a sideway motion of the foot provides the most discrimination, compared to an up-down or" 67a56dd94906a5460c263e1a1b87fa3a52c4b453,FACE ANALYSIS BY LOCAL DIRECTIONAL NUMBER PATTERN,"International Journal of Engineering Research and General Science Volume 3, Issue 1, January-February, 2015 ISSN 2091-2730 FACE ANALYSIS BY LOCAL DIRECTIONAL NUMBER PATTERN Manjunatha S B, Guruprasad A M, Vineesh P Coorg Institute of Technology, Ponnampet, Coorg-District, Karnataka, 9611962024" 67ba3524e135c1375c74fe53ebb03684754aae56,A compact pairwise trajectory representation for action recognition,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" ebabf19e66ef1253fda8d39a0569787c65e60a9e,Multi-person Tracking with Sparse Detection and Continuous Segmentation,"Multi-Person Tracking with Sparse Detection and Continuous Segmentation Dennis Mitzel1, Esther Horbert1, Andreas Ess2, Bastian Leibe1 UMIC Research Centre RWTH Aachen University, Germany Computer Vision Laboratory, ETH Zurich, Switzerland" ebd5df2b4105ba04cef4ca334fcb9bfd6ea0430c,Fast Localization of Facial Landmark Points,"Fast Localization of Facial Landmark Points Nenad Markuˇs*, Miroslav Frljak*, Igor S. Pandˇzi´c*, J¨orgen Ahlberg†, and Robert Forchheimer† * University of Zagreb, Faculty of Electrical Engineering and Computing, Unska 3, 10000 Zagreb, Croatia Link¨oping University, Department of Electrical Engineering, SE-581 83 Link¨oping, Sweden March 28, 2014" eb33adf3f8eb5c07b58a1433734ab1fee5d77c93,"Singleton, C. J., Ashwin, C. and Brosnan, M. (2014) Physiological Responses to Social and Nonsocial Stimuli in Neurotypical Adults With High and Low Levels of Autistic Traits:Implications for Understanding Nonsocial Drive in Autism Spectrum","Singleton, C. J., Ashwin, C. and Brosnan, M. (2014) Physiological Responses to Social and Nonsocial Stimuli in Neurotypical Adults With High and Low Levels of Autistic Traits:Implications for Understanding Nonsocial Drive in Autism Spectrum Disorders. Autism Research, 7 (6). pp. 695-703. ISSN 1939-3792 Link to official URL (if available): http://dx.doi.org/10.1002/aur.1422 Opus: University of Bath Online Publication Store http://opus.bath.ac.uk/ This version is made available in accordance with publisher policies. Please cite only the published version using the reference above. See http://opus.bath.ac.uk/ for usage policies. Please scroll down to view the document." eba31ad9871c6dd5c2e7c62a121bbb417dcb1223,Adaptive Ensemble Selection for Face Re-identification under Class Imbalance,"Adaptive Ensemble Selection for Face Re-Identification Under Class Imbalance(cid:63) Paulo Radtke1, Eric Granger1, Robert Sabourin1 and Dmitry Gorodnichy2 . Laboratoire d’imagerie, de vision et d’intelligence artificielle ´Ecole de technologie sup´erieure, Universit´e du Qu´ebec, Montreal, Canada {eric.granger, . Science and Engineering Directorate, Canada Border Services Agency Ottawa, Canada," eb0e5db282f88d47b65f98df70c2e7c78b8647a6,Image Provenance Analysis at Scale,"Image Provenance Analysis at Scale Daniel Moreira, Aparna Bharati, Student Member, IEEE, Joel Brogan, Student Member, IEEE, Allan Pinto, Student Member, IEEE, Michael Parowski, Kevin W. Bowyer, Fellow, IEEE, Patrick J. Flynn, Fellow, IEEE, Anderson Rocha, Senior Member, IEEE, nd Walter J. Scheirer, Senior Member, IEEE" eb566490cd1aa9338831de8161c6659984e923fd,From Lifestyle Vlogs to Everyday Interactions,"From Lifestyle Vlogs to Everyday Interactions David F. Fouhey, Wei-cheng Kuo, Alexei A. Efros, Jitendra Malik EECS Department, UC Berkeley" ebc2643567b1c614727cd7ecf1d0604972572568,Robust Subspace Estimation Using Low-rank,"ROBUST SUBSPACE ESTIMATION USING LOW-RANK OPTIMIZATION. THEORY AND APPLICATIONS IN SCENE RECONSTRUCTION, VIDEO DENOISING, AND ACTIVITY RECOGNITION. OMAR OREIFEJ B.S. University of Jordan, 2006 M.S. University of Central Florida, 2009 A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Department of Electrical Engineering and Computer Science in the College of Engineering and Computer Science t the University of Central Florida Orlando, Florida Spring Term Major Professor: Mubarak Shah" eb0e0a40372db32d30ceaefad046b213fac977f4,SCENE UNDERSTANDING USING BACK PROPAGATION BY NEURAL NETWORK,"Scene Understanding Using Back Propagation by Neural Network SCENE UNDERSTANDING USING BACK PROPAGATION BY NEURAL NETWORK ARTI TIWARI1 & JAGVIR VERMA2 ,2Department of Elex & Telecomm. Engg.Chouksey Engg. College,Bilaspur intelligent human-computer" eb526174fa071345ff7b1fad1fad240cd943a6d7,Deeply vulnerable: a study of the robustness of face recognition to presentation attacks,"Deeply Vulnerable – A Study of the Robustness of Face Recognition to Presentation Attacks Amir Mohammadi, Sushil Bhattacharjee, and S´ebastien Marcel ∗†" ebf877db5fb6aadbc09d74325f4f9d29a192018a,Embedding Model for Stereo Matching Costs,"A Deep Visual Correspondence Embedding Model for Stereo Matching Costs Zhuoyuan Chen, Xun Sun, Liang Wang, Baidu Research – Institute of Deep Learning Yinan Yu, Chang Huang Horizon Robotics" eb90ebf766dc36c3eca3f85b12d4b8fdd2ddbf1e,Modelling Uncertainty in Representation of Facial Features for Face Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." eb716dd3dbd0f04e6d89f1703b9975cad62ffb09,Visual Object Category Discovery in Images and Videos,"Copyright Yong Jae Lee" ebcd23bf99ead285b9f064bc47e713cd6e5dd599,On Demand Video Sharing System,"Imperial Journal of Interdisciplinary Research (IJIR) Vol-2, Issue-11, 2016 ISSN: 2454-1362, http://www.onlinejournal.in On Demand Video Sharing System Tejas Benke1, Pratik Wakchaure2, Vaibhav Deshmukh3 Amol Sonawane4 & Prof. Kahate S. A.5 2,3,4 Student, SPCOE, Department Of Computer Engineering, Dumbarwadi, Otur 5 Assistant Professor, SPCOE, Department Of Computer Engineering, Dumbarwadi, Otur" eb69f89588e9538194750f12bf8c8df6d5301f3b,Object Tracking by a Combination of Discriminative Global and Generative Multi-Scale Local Models,"Article Object Tracking by a Combination of Discriminative Global and Generative Multi-Scale Local Models Zhiguo Song *, Jifeng Sun and Jialin Yu Wushan Road, Tianhe District, Guangzhou 510640, China; (J.S.); (J.Y.) * Correspondence: Academic Editor: Willy Susilo Received: 6 February 2017; Accepted: 5 April 2017; Published: 11 April 2017" ebf204e0a3e137b6c24e271b0d55fa49a6c52b41,Visual Tracking Using Deep Motion Features,"Master of Science Thesis in Electrical Engineering Department of Electrical Engineering, Linköping University, 2016 Visual Tracking Using Deep Motion Features Susanna Gladh" eb4edbec8cb122de07951e3cf54c33fc30dd1c19,Examining the Effects of Supervision for Transfer from Synthetic to Real Driving Domains Vashisht Madhavan,"Examining the Effects of Supervision for Transfer from Synthetic to Real Driving Domains Vashisht Madhavan" eb3f47ed113752eaa4c989bb92aa0e3e4e0bf339,Tracking of dolphins in a basin using a constrained motion model,"Tracking of Dolphins in a Basin Using a Constrained Motion Model Clas Veibäck, Gustaf Hendeby and Fredrik Gustafsson Linköping University Post Print N.B.: When citing this work, cite the original article. Original Publication: Clas Veibäck, Gustaf Hendeby and Fredrik Gustafsson, Tracking of Dolphins in a Basin Using Constrained Motion Model, 2015, Proceedings of the 18th International Conference of Information Fusion. Copyright: The Authors. Preprint ahead of print available at: Linköping University Electronic Press http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-120373" eb4d2ec77fae67141f6cf74b3ed773997c2c0cf6,A new soft biometric approach for keystroke dynamics based on gender recognition,"Int. J. Information Technology and Management, Vol. 11, Nos. 1/2, 2012 A new soft biometric approach for keystroke dynamics based on gender recognition Romain Giot* and Christophe Rosenberger GREYC Research Lab, ENSICAEN – Université de Caen Basse Normandie – CNRS, 4000 Caen, France Fax: +33-231538110 E-mail: E-mail: *Corresponding author" eb2ab9caa61b021c1cd7aff6d08163768faba99e,Cleaning Up Multiple Detections Caused by Sliding Window Based Object Detectors,"Cleaning Up Multiple Detections Caused y Sliding Window Based Object Detectors Arne Ehlers, Bj¨orn Scheuermann, Florian Baumann, and Bodo Rosenhahn Institut f¨ur Informationsverarbeitung (TNT) Leibniz Universit¨at Hannover, Germany" eb48a58b873295d719827e746d51b110f5716d6c,Face Alignment Using K-Cluster Regression Forests With Weighted Splitting,"Face Alignment Using K-cluster Regression Forests With Weighted Splitting Marek Kowalski and Jacek Naruniec" 529baf1a79cca813f8c9966ceaa9b3e42748c058,Triangle wise Mapping Technique to Transform one Face Image into Another Face Image,"Triangle Wise Mapping Technique to Transform one Face Image into Another Face Image {tag} {/tag} International Journal of Computer Applications © 2014 by IJCA Journal Volume 87 - Number 6 Year of Publication: 2014 Authors: Rustam Ali Ahmed Bhogeswar Borah 10.5120/15209-3714 {bibtex}pxc3893714.bib{/bibtex}" 524890eef6beaeb2e206c7b1bf51b58298eb55ec,Florian et al_ICMCSSE 2012_3,"Efficient and Effective Gabor Feature Representation for Face Detection Yasuomi D. Sato, Yasutaka Kuriya" 526ce5c72af5e1f93b8029a26e2eed7d1ac009f5,0 Constructing Kernel Machines in the Empirical Kernel Feature Space,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 520e4b21302b99e5f289075541f9fe4959a639a4,Framewise approach in multimodal emotion recognition in OMG challenge,"Framewise approach in multimodal emotion recognition in OMG challenge Grigoriy Sterling1, 2, Andrey Belyaev1, 3, and Maxim Ryabov1 Institute for Information Transmission Problems, Moscow, Russian Federation Moscow State Univercity, Moscow, Russian Federation Neurodata Lab LLC, USA May 4, 2018" 527d596a56aa238dfc450c3ebfdae31e82c6c175,Face detection methods,"Face Detection Methods ZYAD SHAABAN Department of Information Technology College of Computers and Information Technology University of Tabuk Tabuk 71491 KINGDOM OF SAUDI ARABIA" 5209758096819efee15751c8875121bd27f2ee78,Finding Person Relations in Image Data of the Internet Archive,"Finding Person Relations in Image Data of the Internet Archive Eric M¨uller-Budack1,2[0000−0002−6802−1241], Kader Pustu-Iren1[0000−0003−2891−9783], Sebastian Diering1, and Ralph Ewerth1,2[0000−0003−0918−6297] Leibniz Information Centre for Science and Technology (TIB), Hannover, Germany L3S Research Center, Leibniz Universit¨at Hannover, Germany" 52012b4ecb78f6b4b9ea496be98bcfe0944353cd,Using Support Vector Machine and Local Binary Pattern for Facial Expression Recognition,"JOURNAL OF COMPUTATION IN BIOSCIENCES AND ENGINEERING Journal homepage: http://scienceq.org/Journals/JCLS.php Research Article Using Support Vector Machine and Local Binary Pattern for Facial Expression Recognition Open Access Ayeni Olaniyi Abiodun 1, Alese Boniface Kayode1, Dada Olabisi Matemilayo2 1. Department of Computer Science, Federal University Technology Akure, PMB 704, Akure, Nigeria. . Department of computer science, Kwara state polytechnic Ilorin, Kwara-State, Nigeria. . *Corresponding author: Ayeni Olaniyi Abiodun Mail Id: Received: September 22, 2015, Accepted: December 14, 2015, Published: December 14, 2015." 5265be9c7b8b22f4e06a01736bbedf171caee74e,Covariance of Motion and Appearance Featuresfor Spatio Temporal Recognition Tasks,"Covariance of Motion and Appearance Features for Human Action and Gesture Recognition Subhabrata Bhattacharya, Nasim Souly and Mubarak Shah" 5223f3485b96bffe7dd4b3aa71e63fd2b049fcf0,Is the Pedestrian going to Cross? Answering by 2D Pose Estimation,"Is the Pedestrian going to Cross? Answering by 2D Pose Estimation Zhijie Fang and Antonio M. L´opez" 5251cb5349e37495b3ca29b06e6ed7422f12d126,A Pedestrian Detector Using Histograms of Oriented Gradients and a Support Vector Machine Classifier,"Proceedings of the 2007 IEEE Intelligent Transportation Systems Conference Seattle, WA, USA, Sept. 30 - Oct. 3, 2007 MoD2.2 -4244-1396-6/07/$25.00 ©2007 IEEE." 5293960de53b0118ef3c8b410d27b23b9cec9bf7,Online Multi-Object Tracking with Dual Matching Attention Networks,"Online Multi-Object Tracking with Dual Matching Attention Networks Ji Zhu1,2, Hua Yang1(cid:63), Nian Liu3, Minyoung Kim4, Wenjun Zhang1, and Ming-Hsuan Yang5,6 Northwestern Polytechnical University 4Massachusetts Institute of Technology Shanghai Jiao Tong University 2Visbody Inc 5University of California, Merced 6Google Inc {jizhu1023," 529341eb910ca5125b4aa6aa83bfc5fc8bf44fe3,V&L Net 2014 The 3rd Annual Meeting Of The EPSRC Network On Vision & Language and The 1st Technical Meeting of the European Network on Integrating Vision and Language,"V&LNet2014The3rdAnnualMeetingOfTheEPSRCNetworkOnVision&LanguageandThe1stTechnicalMeetingoftheEuropeanNetworkonIntegratingVisionandLanguageAWorkshopofthe25thInternationalConferenceonComputationalLinguistics(COLING2014)ProceedingsAugust23,2014Dublin,Ireland" 52f60abde42428d4aa8c5824a749398a1aa73be8,3D Skull Recognition Using 3D Matching Technique,"JOURNAL OF COMPUTING, VOLUME 2, ISSUE 1, JANUARY 2010, ISSN 2151-9617 HTTPS://SITES.GOOGLE.COM/SITE/JOURNALOFCOMPUTING/ D Skull Recognition Using 3D Matching Technique Hamdan.O.Alanazi, B.B Zaidan, A.A Zaidan" 52f71cc9c312aa845867ad1695c25a6d1d94ba0e,The invariance assumption in process-dissociation models: an evaluation across three domains.,"Journal of Experimental Psychology: General 015, Vol. 144, No. 1, 198 –221 0096-3445/15/$12.00 © 2014 American Psychological Association http://dx.doi.org/10.1037/xge0000044 The Invariance Assumption in Process-Dissociation Models: An Evaluation Across Three Domains Karl Christoph Klauer, Kerstin Dittrich, nd Christine Scholtes Albert-Ludwigs-Universität Freiburg Andreas Voss Universität Heidelberg The class of process-dissociation models, a subset of the class of multinomial processing-tree models, is one of the best understood classes of models used in experimental psychology. A number of prominent debates have addressed fundamental assumptions of process-dissociation models, leading, in many cases, to conceptual clarifications and extended models that address identified issues. One issue that has so far defied empirical clarification is how to evaluate the invariance assumption for the dominant process. Violations of the invariance assumption have, however, the potential to bias conventional process- dissociation analyses in different ways, and they can cause misleading theoretical interpretations and onclusions. Based on recent advances in multinomial modeling, we propose new approaches to examine" 52884a0c7913be319c1a2395f009cea47b03f128,Explorer Learning Grounded Meaning Representations with Autoencoders,"Learning Grounded Meaning Representations with Autoencoders Citation for published version: Silberer, C & Lapata, M 2014, 'Learning Grounded Meaning Representations with Autoencoders'. in Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Baltimore, Maryland, pp. 721-732. Link: Link to publication record in Edinburgh Research Explorer Document Version: Publisher final version (usually the publisher pdf) Published In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) nd / or other copyright owners and it is a condition of accessing these publications that users recognise and bide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer ontent complies with UK legislation. If you believe that the public display of this file breaches copyright please ontact providing details, and we will remove access to the work immediately and" 52ed30920f2f96970c4f79d6768436ed855dad42,Active image pair selection for continuous person re-identification,"ACTIVE IMAGE PAIR SELECTION FOR CONTINUOUS PERSON RE-IDENTIFICATION Abir Das, Rameswar Panda, Amit Roy-Chowdhury Electrical and Computer Engineering Department, University of California, Riverside, USA" 52c9617414f29551dca35fb7a7ba18b58640a4eb,The Multimedia Satellite Task at MediaEval 2018,"The Multimedia Satellite Task at MediaEval 2018 Emergency Response for Flooding Events Benjamin Bischke1, 2, Patrick Helber1, 2, Zhengyu Zhao3, Jens de Bruijn4, Damian Borth1 German Research Center for Artificial Intelligence (DFKI), Germany TU Kaiserslautern, Germany Radboud University, The Netherlands VU University Amsterdam, The Netherlands" 522fab628aab972f39835521e31564b4b6c64fe5,Vehicle Classification on Low-resolution and Occluded images : A low-cost labeled dataset for augmentation,"Vehicle Classification on Low-resolution and Occluded images: A low-cost labeled dataset for ugmentation Anonymous Author(s) Affiliation Address email" 52e0c03dd661d032865dfedd91ca49542ccfc2a3,Improving Human Action Recognition Using Score Distribution and Ranking,"Improving Human Action Recognition using Score Distribution and Ranking Minh Hoai1,2 and Andrew Zisserman1 Visual Geometry Group, Dept. Engineering Science, University of Oxford. Department of Computer Science, Stony Brook University." 52b6df1fe810d36fd615eb7c47aa1fd29376e769,Graph Mining for Object Tracking in Videos,"Graph Mining for Object Tracking in Videos Fabien Diot, Elisa Fromont, Baptiste Jeudy, Emmanuel Marilly, Olivier Martinot To cite this version: Fabien Diot, Elisa Fromont, Baptiste Jeudy, Emmanuel Marilly, Olivier Martinot. Graph Mining for Object Tracking in Videos. European Conference on Machine Learning and Prin- iples and Practice of Knowledge Discovery in Databases, Sep 2012, Bristol, United Kingdom. Springer, LNCS (LNAI 6321), pp.394-409, 2012. HAL Id: hal-00714705 https://hal.archives-ouvertes.fr/hal-00714705v2 Submitted on 20 Sep 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," 52cd3eb77a5e259289d2442205f1731eafd581f9,Human Detection Based on the Generation of a Background Image and Fuzzy System by Using a Thermal Camera,"Article Human Detection Based on the Generation of Background Image and Fuzzy System by Using Thermal Camera Eun Som Jeon, Jong Hyun Kim, Hyung Gil Hong, Ganbayar Batchuluun and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (E.S.J.); (J.H.K.); (H.G.H.); (G.B.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Academic Editors: Vincenzo Spagnolo and Dragan Indjin Received: 3 January 2016; Accepted: 24 March 2016; Published: 30 March 2016" 52417b0406886154f0b4e2343ad6ac18c0484ec4,Ecological legacies of civil war : 35-year increase in savanna tree cover following wholesale large-mammal declines,"Journal of Ecology 2016, 104, 79–89 doi: 10.1111/1365-2745.12483 Ecological legacies of civil war: 35-year increase in savanna tree cover following wholesale large-mammal declines Joshua H. Daskin1*, Marc Stalmans2 and Robert M. Pringle1 Department of Ecology and Evolutionary Biology, 106A Guyot Hall, Princeton University Princeton, NJ 08540, USA; nd 2Department of Scientific Services, Gorongosa National Park, Sofala Province, Mozambique Summary . Large mammalian herbivores (LMH) exert strong effects on plants in tropical savannas, and many wild LMH populations are declining. However, predicting the impacts of these declines on vegetation structure remains challenging. . Experiments suggest that tree cover can increase rapidly following LMH exclusion. Yet it is unclear whether these results scale up to predict ecosystem-level impacts of LMH declines, which often alter fire regimes, trigger compensatory responses of other herbivores and accompany anthro- pogenic land-use changes. Moreover, theory predicts that grazers and browsers should have oppos- ing effects on tree cover, further complicating efforts to forecast the outcomes of community-wide declines. . We used the near-extirpation of grazing and browsing LMH from Gorongosa National Park dur- ing the Mozambican Civil War (1977–1992) as a natural experiment to test whether megafaunal col-" 52969cdd2c5eaccb534fe1296a61517b7ec42a54,Human Identification based on Ear Recognition,"Human Identification based on Ear Recognition S. Gangaram1, and S. Viriri1,2" 524634e1055637b7c22b29e7e36437f4ba80df04,Thermal to Visible Synthesis of Face Images Using Multiple Regions,"Thermal to Visible Synthesis of Face Images using Multiple Regions Benjamin S. Riggan1,* Nathaniel J. Short1,2 Shuowen Hu1 U.S. Army Research Laboratory, 2800 Powder Mill Rd., Adelphi, MD 20783 Booz Allen Hamilton, 8283 Grennsboro Dr., McLean, VA 22102 *Corresponding author:" 5293df3b1543e79f88eea70b8766dc34e1f406e0,A Comparative Evaluation of Fusion Strategies for Multimodal Biometric Verification,"A Comparative Evaluation of Fusion Strategies for Multimodal Biometric Verification J. Fierrez-Aguilar, J. Ortega-Garcia, D. Garcia-Romero and J. Gonzalez-Rodriguez www.atvs.diac.upm.es Universidad Politecnica de Madrid, Spain Biometrics Research Lab., ATVS" 5232a1ab263e4feaa4989b8b257830650403dfa5,On Finding Differences Between Faces,"On Finding Differences Between Faces Manuele Bicego1, Enrico Grosso1, and Massimo Tistarelli2 DEIR - University of Sassari, via Sardegna 58 - 07100 Sassari - Italy DAP - University of Sassari, piazza Duomo 6 - 07041 Alghero (SS) - Italy" 527ed756eba3bc77eb58d22d4cfe27da04d3bbbb,Adaptive skew-sensitive fusion of ensembles and their application to face re-identification,"Adaptive Skew-Sensitive Fusion of Ensembles and their Application to Face Re-Identification Miguel De-la-Torre∗†, Eric Granger∗, Robert Sabourin∗ ´Ecole de technologie sup´erieure, Universit´e du Qu´ebec, Montr´eal, Canada Centro Universitario de Los Valles, Universidad de Guadalajara, Ameca, M´exico" 52887969107956d59e1218abb84a1f834a314578,Travel Recommendation by Mining People Attributes and Travel Group Types From Community-Contributed Photos,"Travel Recommendation by Mining People Attributes and Travel Group Types From Community-Contributed Photos Yan-Ying Chen, An-Jung Cheng, and Winston H. Hsu, Senior Member, IEEE" 521120c3907677e17708c17c5b6bab9087e61c5b,"l2, 1-Norm Regularized Discriminative Feature Selection for Unsupervised Learning","(cid:2)2,1-Norm Regularized Discriminative Feature Selection for Unsupervised Learning Yi Yang1, Heng Tao Shen1, Zhigang Ma2, Zi Huang1, Xiaofang Zhou1 School of Information Technology & Electrical Engineering, The University of Queensland. Department of Information Engineering & Computer Science, University of Trento. yangyi {huang," 52a723061175ad141d73cb3979788e8afb7291db,Canonical Correlation Analysis of Datasets With a Common Source Graph,"Canonical Correlation Analysis of Datasets with a Common Source Graph Jia Chen, Gang Wang, Student Member, IEEE, Yanning Shen, Student Member, IEEE, and Georgios B. Giannakis, Fellow, IEEE" bd2d7c7f0145028e85c102fe52655c2b6c26aeb5,Attribute-based People Search: Lessons Learnt from a Practical Surveillance System,"Attribute-based People Search: Lessons Learnt from a Practical Surveillance System Rogerio Feris IBM Watson http://rogerioferis.com Russel Bobbitt IBM Watson Lisa Brown IBM Watson Sharath Pankanti IBM Watson" bd96c3af9c433b4eaf95c8a28f072e1b0fc2de1a,A Study on Facial Expression Recognition Model using an Adaptive Learning Capability,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." bd37ff771acd72ebdf4024043cb62fcacdd3a82b,Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval,"Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval Lin Wu, Yang Wang and Ling Shao Senior Member, IEEE" bd86306ccb6698e17f00f208cf4fbc7a0aae39a9,An incremental nonparametric Bayesian clustering-based traversable region detection method,"Auton Robot DOI 10.1007/s10514-016-9588-7 An incremental nonparametric Bayesian clustering-based traversable region detection method Honggu Lee1 · Kiho Kwak2 · Sungho Jo1 Received: 23 October 2015 / Accepted: 23 June 2016 © Springer Science+Business Media New York 2016" bda61e9bcf02d02f61882790dbbdad8e4fed0986,Face Recognition through Combined SVD and LBP Features,"Face Recognition through Combined SVD and LBP International Journal of Computer Applications (0975 – 8887) Volume 88 – No.9, February 2014 Features Rahul Kumar Mittal M.Tech. Scholar BGIET, Sangrur Punjab (India) Anupam Garg Assistant Professor BGIET, Sangrur Punjab (India)" bd76a71c6b1f414ada026ba82726024fbd58e9fe,DEEPSTEREOBRUSH : INTERACTIVE DEPTH MAP CREATION,"DEEPSTEREOBRUSH: INTERACTIVE DEPTH MAP CREATION Sebastian Knorr1,3,∗, Matis Hudon1,∗, Julian Cabrera2,∗, Thomas Sikora3, Aljosa Smolic1 † Trinity College Dublin, 2Universidad Polit´ecnica de Madrid, 3Technische Universit¨at Berlin" bd0a6bea1985ece3388b1dae47fa76aab3562d6d,One Deep Music Representation to Rule Them All? : A comparative analysis of different representation learning strategies,"Noname manuscript No. (will be inserted by the editor) One Deep Music Representation to Rule Them All? A comparative analysis of different representation learning strategies Jaehun Kim · Juli´an Urbano · Cynthia C. S. Liem · Alan Hanjalic Received: date / Accepted: date" bd95446d4b1423b9f9c9243d8b5dddfbd045a30d,Cosy Cognitive Systems for Cognitive Assistants Dr.4.2 System for Supervised Mapping Executive Summary Role of (topic of Deliverable) in Cosy Relation to the Demonstrators Cosy Fp6-004250 1 Introduction Cosy Fp6-004250,"FP6-004250 Cognitive Systems for Cognitive Assistants Integrated Project Information Society Technologies DR.4.2 System for Supervised Mapping Due date of deliverable: 31/8/2005 Actual submission date: 16/10/2005 Start date of project: September 1st, 2004 Duration: 48 months Organisation name of lead contractor for this deliverable: Revision: draft V.1., final, etc... Dissemination Level: PU" bdb74f1b633b2c48d5e9d101e09bad2db8d68be6,Medical Image Annotation 1,"Chapter 1 Medical image annotation 1 Thanks to the rapid development of modern medical devices and the use of digital systems, more and more medical images are being generated. This has lead to an increase in the demand for automatic methods to index, com- pare, analyze and annotate them. Until 2005, automatic categorization of medical images was often restricted to a small number of classes. The Image- CLEF medical image annotation challenge was born in this scenario, propos- ing a task reflecting real life constraints of content based image classification in medical applications. In this chapter we report about our experience first s participants, then as co-organizers. This research activity started in 2007, supported by a 1-year IM2 fellowship. By leveraging over the initial IM2 support, in 2008 a 4-year project started (EMMA, Enhanced Multimodal Medical data Access), sponsored by the Halser foundation. Since 2009, B. Caputo has been an ImageCLEF task organizers, respectively for the medi- al annotation and robot vision tasks. Since 2013, she is main organizer of ImageCLEF. Introduction This chapter presents the algorithms and results of the Idiap team partici- pation to the ImageCLEFmed annotation task in 2007, 2008 and 2009. The" bd17d6ba5525dec8762dbaacf6cc3e0cc3f5ff90,Necst: Neural Joint Source-channel Coding,"Under review as a conference paper at ICLR 2019 NECST: NEURAL JOINT SOURCE-CHANNEL CODING Anonymous authors Paper under double-blind review" bdfb5f11d497b44b17d0315c3b6892f835723832,Object Captioning and Retrieval with Natural Language,"Object Captioning and Retrieval with Natural Language Anh Nguyen1, Thanh-Toan Do2, Ian Reid2, Darwin G. Caldwell1, Nikos G. Tsagarakis1" bd3a3884718015cde3eb8b0fdeae94eb1702a233,Hierarchical Compositional Model for Representation and Sketching of High-Resolution Human Images,"UNIVERSITY OF CALIFORNIA Los Angeles A Hierarchical Compositional Model for Representation and Sketching of High-Resolution Human Images A dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Statistics Zijian Xu" bd07d1f68486052b7e4429dccecdb8deab1924db,Face representation under different illumination conditions, bd74c7b6d17e2515583cc26f26933a785045690f,Navigation assistance and guidance of older adults across complex public spaces: the DALi approach,"Intel Serv Robotics (2015) 8:77–92 DOI 10.1007/s11370-015-0169-y ORIGINAL RESEARCH PAPER Navigation assistance and guidance of older adults across complex public spaces: the DALi approach Luigi Palopoli1 · Antonis Argyros2 · Josef Birchbauer3 · Alessio Colombo1 · Daniele Fontanelli1 · Axel Legay4 · Andrea Garulli5 · Antonello Giannitrapani5 · David Macii1 · Federico Moro1 · Payam Nazemzadeh1 · Pashalis Padeleris2 · Roberto Passerone1 · Georg Poier3 · Domenico Prattichizzo5 · Tizar Rizano1 · Luca Rizzon1 · Stefano Scheggi5 · Sean Sedwards4 Received: 26 November 2014 / Accepted: 5 March 2015 / Published online: 22 March 2015 © Springer-Verlag Berlin Heidelberg 2015" bdbba95e5abc543981fb557f21e3e6551a563b45,Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks,"Vol. 17, No. 2 (2018) 1850008 (15 pages) #.c The Author(s) DOI: 10.1142/S1469026818500086 Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks Tobias Hinz*, Nicolas Navarro-Guerrero†, Sven Magg‡ nd Stefan Wermter§ Knowledge Technology, Department of Informatics Universit€at Hamburg Vogt-K€olln-Str. 30, Hamburg 22527, Germany Received 15 August 2017 Accepted 23 March 2018 Published 18 June 2018 Most learning algorithms require the practitioner to manually set the values of many hyper- parameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional represen- tation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher- dimensional data. We compare this approach with the standard procedure of optimizing the" bd2752acf6821282655933d1946f43bb4ac5e901,Flexible Network Binarization with Layer-Wise Priority,"Flexible Network Binarization with Layer-wise Priority Lixue Zhuang*, Yi Xu*, Bingbing Ni*, Hongteng Xu† Shanghai Jiao Tong University*, Duke University† {qingliang, xuyi," bd67c08fae1d32f605585b0f375ad17c9695c9bd,Real Time Face Tracking and Recognition ( RTFTR,"Real Time Face Tracking and Recognition (RTFTR) http://rtftr.sourceforge.net http://collaborate.d2labs.org/projects/rtftr Open Software Challenge Nepal(OSCN) - 2009 Submitted to July 01, 2009 Abhishek Dutta Anjan Nepal Bibek Shrestha Lakesh Kansakar { adutta.np, anjan.nepal, bibekshrestha, lakesh.kansakar } gmail.com Institute of Engineering - Pulchowk Campus Tribhuvan University, Nepal" bd88bb2e4f351352d88ee7375af834360e223498,HDA dataset-DRAFT 1 A Multi-camera video data set for research on High-Definition surveillance,"HDA dataset - DRAFT A Multi-camera video data set for research on High-Definition surveillance Athira Nambiar, Matteo Taiana, Dario Figueira, Jacinto Nascimento and Alexandre Bernardino Computer and Robot Vision Lab, Institute for Systems and Robotics Instituto Superior Técnico Lisbon, Portugal" bd13f50b8997d0733169ceba39b6eb1bda3eb1aa,Occlusion Coherence: Detecting and Localizing Occluded Faces,"Occlusion Coherence: Detecting and Localizing Occluded Faces Golnaz Ghiasi, Charless C. Fowlkes University of California at Irvine, Irvine, CA 92697" bd0e100a91ff179ee5c1d3383c75c85eddc81723,Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection,"Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection∗ Mohammadamin Barekatain1, Miquel Mart´ı2,3, Hsueh-Fu Shih4, Samuel Murray2, Kotaro Nakayama5, Yutaka Matsuo5, Helmut Prendinger6 Technical University of Munich, Munich, 2KTH Royal Institute of Technology, Stockholm, Polytechnic University of Catalonia, Barcelona, 4National Taiwan University, Taipei, 5University of Tokyo, Tokyo, 6National Institute of Informatics, Tokyo" a56c1331750bf3ac33ee07004e083310a1e63ddc,Efficient Point-to-Subspace Query in ℓ1 with Application to Robust Object Instance Recognition,"Vol. xx, pp. x (cid:13) xxxx Society for Industrial and Applied Mathematics Ef‌f‌icient Point-to-Subspace Query in (cid:96)1 with Application to Robust Object Instance Recognition Ju Sun∗, Yuqian Zhang†, and John Wright‡" a511463a423f842bdb524009f6ce6c6b0ffa0f77,Kernel diff-hash,"Kernel diff-hash Michael M. Bronstein Institute of Computational Science Faculty of Informatics, Universit`a della Svizzera Italiana Via G. Buf‌f‌i 13, Lugano 6900, Switzerland November 3, 2011" a5c33de108cf7903a0f7d20daf22fb0794adba43,Study and Analysis of Convolutional Neural Networks for Pedestrian Detection in Autonomous Vehicles,"UPTEC F 18020 Examensarbete 30 hp Juni 2018 Study and Analysis of Convolutional Neural Networks for Pedestrian Detection in Autonomous Vehicles Louise Augustsson" a565990d6b176bf9c82eec9354b0936fb141e631,Scheduling on Heterogeneous Multi-core Processors Using Stable Matching Algorithm,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 7, No. 6, 2016 Scheduling on Heterogeneous Multi-core Processors Using Stable Matching Algorithm Muhammad Rehman Zafar Department of Computer Science Bahria University Islamabad, Pakistan Muhammad Asfand-e-Yar Department of Computer Science Bahria University Islamabad, Pakistan" a5006c29b0609296b5c1368ff1113eeb12b119ad,In-flight launch of unmanned aerial vehicles,"In-flight launch of unmanned aerial vehicles Niels Nauwynck, Haris Balta, Geert De Cubber, and Hichem Sahli" a588d38ec81c0337b445931eadf6f443aea13380,Functional Map of the World,"Functional Map of the World Gordon Christie1 Neil Fendley1 The Johns Hopkins University Applied Physics Laboratory James Wilson2 Ryan Mukherjee1 DigitalGlobe" a52d6daf72281521ee99dabd82cd80093e8d6f4a,Person re-identification across different datasets with multi-task learning,"Person re-identification across different datasets with multi-task learning Matthieu Ospici, Antoine Cecchi Atos BDS R&D" a5ae7fe2bb268adf0c1cd8e3377f478fca5e4529,Exemplar Hidden Markov Models for classification of facial expressions in videos,"Exemplar Hidden Markov Models for Classification of Facial Expressions in Videos Univ. of California San Diego Univ. of Canberra, Australian Univ. of California San Diego Abhinav Dhall Marian Bartlett Karan Sikka California, USA National University Australia California, USA" a5dd647ff98d8ac9642a884c501de9a7aaf9a1b7,ICANet : a simple cascade linear convolution network for face recognition,"Zhang et al. EURASIP Journal on Image and Video Processing (2018) 2018:51 https://doi.org/10.1186/s13640-018-0288-4 EURASIP Journal on Image nd Video Processing RESEARCH Open Access ICANet: a simple cascade linear onvolution network for face recognition Yongqing Zhang1,2, Tianyu Geng3*, Xi Wu1, Jiliu Zhou1 and Dongrui Gao1" a50b4d404576695be7cd4194a064f0602806f3c4,Efficiently Estimating Facial Expression and Illumination in Appearance-based Tracking,"In Proceedings of BMVC, Edimburgh, UK, September 2006 Efficiently estimating facial expression and illumination in appearance-based tracking Jos´e M. Buenaposada†, Enrique Mu˜noz‡, Luis Baumela‡ ESCET, U. Rey Juan Carlos C/ Tulip´an, s/n 8933 M´ostoles, Spain Facultad Inform´atica, UPM Campus de Montegancedo s/n 8660 Boadilla del Monte, Spain http://www.dia.fi.upm.es/~pcr" a55efc4a6f273c5895b5e4c5009eabf8e5ed0d6a,"Continuous Head Movement Estimator for Driver Assistance: Issues, Algorithms, and On-Road Evaluations","Continuous Head Movement Estimator for Driver Assistance: Issues, Algorithms, nd On-Road Evaluations Ashish Tawari, Student Member, IEEE, Sujitha Martin, Student Member, IEEE, and Mohan Manubhai Trivedi, Fellow, IEEE" a52d9e9daf2cb26b31bf2902f78774bd31c0dd88,Understanding and Designing Convolutional Networks for Local Recognition Problems,"Understanding and Designing Convolutional Networks for Local Recognition Problems Jonathan Long Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2016-97 http://www.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-97.html May 13, 2016" a51d5c2f8db48a42446cc4f1718c75ac9303cb7a,Cross-validating Image Description Datasets and Evaluation Metrics,"Cross-validating Image Description Datasets and Evaluation Metrics Josiah Wang and Robert Gaizauskas Department of Computer Science University of Sheffield, UK {j.k.wang," a5d77dd6ed07bd9688d13eac9d7848d19fdfb39b,PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud,"PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud Yuan Wang1 Tianyue Shi2 Peng Yun1 Lei Tai1 Ming Liu1" a55ec6bade29f23f8cb1337edf417b2da2f48695,Deep Asymmetric Networks with a Set of Node-wise Variant Activation Functions,"Deep Asymmetric Networks with a Set of Node-wise Variant Activation Functions Jinhyeok Jang, Hyunjoong Cho, Jaehong Kim, Jaeyeon Lee, and Seungjoon Yang" a5fd72b3bdda02c1d706167e98d088ffbdfefae4,RSR2015: Database for Text-Dependent Speaker Verification using Multiple Pass-Phrases,"The RSR2015: Database for Text-Dependent Speaker Verification using Multiple Pass-Phrases Anthony Larcher, Kong Aik Lee, Bin Ma, Haizhou Li Institute for Infocomm Research (I2R) A(cid:63)STAR, Singapore" a5ad7ce9b8bba0a6bd8e6c26ccc5d6133d748c44,NEAREST-NEIGHBOR BASED METRIC FUNCTIONS FOR INDOOR SCENE RECOGNITION,"NEAREST-NEIGHBOR BASED METRIC FUNCTIONS FOR INDOOR SCENE RECOGNITION thesis submitted to the department of computer engineering nd the graduate school of engineering and science of b˙Ilkent university in partial fulfillment of the requirements for the degree of master of science Fatih C¸ akır July, 2011" a5da6a6d4243a89e974a6467cb5c6df6d914a946,Static and Dynamic Approaches for Pain Intensity Estimation using Facial Expressions, a55dea7981ea0f90d1110005b5f5ca68a3175910,"Are 1, 000 Features Worth A Picture? Combining Crowdsourcing and Face Recognition to Identify Civil War Soldiers","Combining Crowdsourcing and Face Recognition to Identify Civil War Soldiers Are 1,000 Features Worth A Picture? Vikram Mohanty, David Thames, Kurt Luther Department of Computer Science and Center for Human-Computer Interaction Virginia Tech, Arlington, VA, USA" a5625cfe16d72bd00e987857d68eb4d8fc3ce4fb,VFSC: A Very Fast Sparse Clustering to Cluster Faces from Videos,"VFSC: A Very Fast Sparse Clustering to Cluster Faces from Videos Dinh-Luan Nguyen, Minh-Triet Tran University of Science, VNU-HCMC, Ho Chi Minh city, Vietnam" a5d525d27a55c38879c4becda7af7ad04406708e,Feature Multi-Selection among Subjective Features,"Feature Multi-Selection among Subjective Features Sivan Sabato Adam Kalai Microsoft Research New England, 1 Memorial Dr., Cambridge, MA" a54e0f2983e0b5af6eaafd4d3467b655a3de52f4,Face Recognition Using Convolution Filters and Neural Networks.,"Face Recognition Using Convolution Filters and Neural Networks V. Rihani Head, Dept. of E&E,PEC Sec-12, Chandigarh – 160012 Amit Bhandari Department of CSE & IT, PEC Sec-12, Chandigarh – 160012 C.P. Singh Physics Department, CFSL, Sec-36, Chandigarh - 160036 to: (a) potential method" a546fd229f99d7fe3cf634234e04bae920a2ec33,Fast Fight Detection,"RESEARCH ARTICLE Fast Fight Detection Ismael Serrano Gracia1*, Oscar Deniz Suarez1*, Gloria Bueno Garcia1*, Tae-Kyun Kim2 Department of Systems Engineering and Automation, E.T.S.I. Industriales, Ciudad Real, Castilla-La Mancha, Spain, 2 Department of Electrical and Electronic Engineering, Imperial College, London, UK * (ISG); (ODS); (GBG)" a5be204b71d1daaf6897270f2373d1a5e37c3010,Improving Spatiotemporal Self-supervision by Deep Reinforcement Learning,"Improving Spatiotemporal Self-Supervision y Deep Reinforcement Learning Uta B¨uchler(cid:63), Biagio Brattoli(cid:63), and Bj¨orn Ommer Heidelberg University, HCI / IWR, Germany" a5e5094a1e052fa44f539b0d62b54ef03c78bf6a,Detection without Recognition for Redaction,"Detection without Recognition for Redaction Shagan Sah1, Ram Longman1, Ameya Shringi1, Robert Loce2, Majid Rabbani1, and Raymond Ptucha1 Rochester Institute of Technology - 83 Lomb Memorial Drive, Rochester, NY USA, 14623 Conduent, Conduent Labs - US, 800 Phillips Rd, MS128, Webster, NY USA, 14580 Email:" a5a44a32a91474f00a3cda671a802e87c899fbb4,Moments in Time Dataset: one million videos for event understanding,"Moments in Time Dataset: one million videos for event understanding Mathew Monfort, Bolei Zhou, Sarah Adel Bargal, Alex Andonian, Tom Yan, Kandan Ramakrishnan, Lisa Brown, Quanfu Fan, Dan Gutfruend, Carl Vondrick, Aude Oliva" a5531b5626c1ee3b6f9aed281a98338439d06d12,Multichannel Attention Network for Analyzing Visual Behavior in Public Speaking,"Multichannel Attention Network for Analyzing Visual Behavior in Public Speaking Rahul Sharma, Tanaya Guha and Gaurav Sharma IIT Kanpur {rahus, tanaya," a59e338fec32adee012e31cdb0513ec20d6c8232,Phase Retrieval Under a Generative Prior,"Phase Retrieval Under a Generative Prior Paul Hand∗, Oscar Leong∗, and Vladislav Voroninski† July 12, 2018" e018c7f468a9b61cd6e7dcbc40b332a8a25808ae,Face Recognition by Face Bunch Graph Method,"Face Recognition by Face Bunch Graph Method JIRI STASTNY*, VLADISLAV SKORPIL** * Department of Automation and Computer Science, ** Department of Telekommunications, Brno University of Technology, Purkynova 118, 612 00 Brno, CZECH REPUBLIC," e0181f7596b475f7c7d31fd1eccad8e9b7379180,Facial Expression Recognition for Traumatic Brain Injured Patients, e076f818b090e42036821c69727cfa3b7da49373,Social Groups Detection in Crowd through Shape-Augmented Structured Learning,"Social Groups Detection in Crowd Through Shape-Augmented Structured Learning Francesco Solera and Simone Calderara DIEF University of Modena and Reggio Emilia, Italy" e000dd1aec1c7b1e9e781ec7ea66f2bde72faa5e,Ear Recognition : A Complete System,"Ear Recognition: A Complete System Ayman Abazaa,b and MaryAnn F. Harrisona West Virginia High Tech Foundation, 1000 Technology Drive, Fairmont, USA; Cairo University, Cairo, Egypt" e0739088d578b2abf583e30953ffa000620cca98,Efficient Pedestrian Detection in Urban Traffic Scenes,"Efficient Pedestrian Detection in Urban Traffic Scenes Dissertation Erlangung des Doktorgrades (Dr. rer. nat.) Mathematisch-Naturwissenschaftlichen Fakult¨at Rheinischen Friedrich-Wilhelms-Universit¨at Bonn vorgelegt von Shanshan Zhang Jiangxi, V.R. China Bonn, 2014" e013c650c7c6b480a1b692bedb663947cd9d260f,Robust Image Analysis With Sparse Representation on Quantized Visual Features,"Robust Image Analysis With Sparse Representation on Quantized Visual Features Bing-Kun Bao, Guangyu Zhu, Jialie Shen, and Shuicheng Yan, Senior Member, IEEE" e00bdb0b046c4d21517ca808a4233a6fd5f3faee,Efficient Retina-like Resampling from Cartesian Images,"VII Workshop de Vis˜ao Computacional – WVC 2011 Efficient Retina-like Resampling from Cartesian Images Hugo Vieira Neto, Diogo Rosa Kuiaski and Gustavo Benvenutti Borba Graduate School of Electrical Engineering and Applied Computer Science Federal University of Technology - Paran´a, Brazil" e065a2cb4534492ccf46d0afc81b9ad8b420c5ec,SFace: An Efficient Network for Face Detection in Large Scale Variations,"SFace: An Ef‌f‌icient Network for Face Detection in Large Scale Variations Jianfeng Wang12∗, Ye Yuan 1†, Boxun Li†, Gang Yu† and Sun Jian† College of Software, Beihang University∗ Megvii Inc. (Face++)†" e0f3b8cbf90096bb0d4b36324c6fe7db89f580b9,Ré-identification de personnes : Application aux réseaux de caméras à champs disjoints,"Ré-identification de personnes : Application aux réseaux de caméras à champs disjoints Boris Meden To cite this version: Boris Meden. Ré-identification de personnes : Application aux réseaux de caméras à champs disjoints. Robotique [cs.RO]. Université Paul Sabatier - Toulouse III, 2013. Français. HAL Id: tel-00822779 https://tel.archives-ouvertes.fr/tel-00822779 Submitted on 15 May 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" e0082ae9e466f7c855fb2c2300215ced08f61432,Generative Temporal Models with Spatial Memory for Partially Observed Environments,"Generative Temporal Models with Spatial Memory for Partially Observed Environments Marco Fraccaro 1 * Danilo Jimenez Rezende 2 Yori Zwols 2 Alexander Pritzel 2 S. M. Ali Eslami 2 Fabio Viola 2" e04a5a6860b80e3a7fc293d495f3b9a822c3f98d,Exploration of the Influence of Smiling on Initial Reactions Across Levels of Facial Attractiveness,"American Journal of Undergraduate Research (cid:90)(cid:90)(cid:90)(cid:17)(cid:68)(cid:77)(cid:88)(cid:85)(cid:82)(cid:81)(cid:79)(cid:76)(cid:81)(cid:72)(cid:17)(cid:82)(cid:85)(cid:74) Exploration of the Influence of Smiling on Initial Reactions Across Levels of Facial Attractiveness Stephanie M. Shields* a, Caitlin E. Morse a, Paige Arringtonb, and David F. Nicholsa Department of Psychology, Roanoke College, Salem, VA Graduate Program in Liberal Arts, Hollins University, Roanoke, VA Students: Mentor:" e0939b4518a5ad649ba04194f74f3413c793f28e,Mind-reading machines : automated inference of complex mental states Rana,"Technical Report UCAM-CL-TR-636 ISSN 1476-2986 Number 636 Computer Laboratory Mind-reading machines: utomated inference of complex mental states Rana Ayman el Kaliouby July 2005 5 JJ Thomson Avenue Cambridge CB3 0FD United Kingdom phone +44 1223 763500 http://www.cl.cam.ac.uk/" e0aa9ab8f00b2bf0dd1b6ffd5c00e5a15b6a67e1,Robust Visual Tracking via Hierarchical Convolutional Features,"Robust Visual Tracking via Hierarchical Convolutional Features Chao Ma, Jia-Bin Huang, Xiaokang Yang, and Ming-Hsuan Yang" e0a57676ca5f7fced9dcf885a60a1967cc21070c,Development of a Computer Interface for People with Disabilities based on Computer Vision, e05444e51d292bda871388c22b97400ed4cf73a8,An Overview of Recent Approaches in Person Re-Identification,An Overview of Recent Approaches in Person Re-Identification e0eb1d66f244456063409264ed795d9893565011,Inhibited Softmax for Uncertainty Estimation in Neural Networks,"Electronic Preprint INHIBITED SOFTMAX FOR UNCERTAINTY ESTIMATION IN NEURAL NETWORKS Marcin Mo˙zejko, Mateusz Susik & Rafał Karczewski Sigmoidal" e0ad3408ed47261a9d0fbc2f037b395fb41b88bf,MOTION VECTOR FIELD ESTIMATION USING BRIGHTNESS CONSTANCY ASSUMPTION AND EPIPOLAR GEOMETRY CONSTRAINT,"ISPRS Technical Commission I Symposium, Sustaining Land Imaging: UAVs to Satellites 7 – 20 November 2014, Denver, Colorado, USA, MTSTC1-109" e0e511a5d58a8d090ad169be4fcfdbeaef097a70,Leveraging Cognitive Computing for Gender and Emotion Detection,"Leveraging Cognitive Computing for Gender and Emotion Detection Andrea Corriga1, Simone Cusimano1, Francesca M. Malloci1, Lodovica Marchesi1 and Diego Reforgiato Recupero1 Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari" e0515dc0157a89de48e1120662afdd7fe606b544,Perception Science in the Age of Deep Neural Networks,"SPECIALTY GRAND CHALLENGE published: 02 February 2017 doi: 10.3389/fpsyg.2017.00142 Perception Science in the Age of Deep Neural Networks Rufin VanRullen 1, 2* Centre National de la Recherche Scientifique, UMR 5549, Faculté de Médecine Purpan, Toulouse, France, 2 Université de Toulouse, Centre de Recherche Cerveau et Cognition, Université Paul Sabatier, Toulouse, France Keywords: perception, neuroscience, psychology, neural networks, deep learning, artificial intelligence For decades, perception was considered a unique ability of biological systems, little understood in its inner workings, and virtually impossible to match in artificial systems. But this status quo was upturned in recent years, with dramatic improvements in computer models of perception brought bout by “deep learning” approaches. What does all the ruckus about a “new dawn of artificial intelligence” imply for the neuroscientific and psychological study of perception? Is it a threat, an opportunity, or maybe a little of both? WHILE WE WERE SLEEPING... My personal journey in the field of perception science started about 20 years ago. For as long as I can remember, we perception scientists have exploited in our papers and grant proposals the lack of human-level artificial perception systems, both as a justification for scientific inquiry, and s a convenient excuse for using a cautious, methodical approach—i.e., “baby steps.” Visual object" e01058388d139e027482a7d89a2997606f7ef4fd,Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) Input (b) FCN Based Model (c) GRN (d) Input (f) LRN (e) FCN Based Model Figure1:ResultofFCNbasedmodel(b)hasinconsistentlabelsinwall,curtainandbedsidetable,whichcanberefinedbytheproposedGRN(c).ResultofFCNbasedmodel(e)hasimpreciseanddiscon-tinuousobjectboundariesofcabinet,tableandchairs,whichcanberefinedbytheproposedLRN(f).stepinmanypracticalframeworks.Forexample,inobjectdetection,bounding-boxrefinement[GidarisandKomodakis,2015]iswidelyusedin[Heetal.,2016][Belletal.,2016][Shrivastavaetal.,2016],bringingsignificantimprovementofbounding-boxlocalizationandscoring.Inspiredbyitssuccess,wedesigntwonewrefinementnetworksparticularlyforrectifyingtheparsingpredictions,frombothglobalandlocalviewsrespectively.Eachofthetwonetworkscanbeemployedaftertheexistingparsingframeworksindividually.Moreover,cascadingthemtogetherforrefinementcangainmorepreciseparsingresults.Firstly,weconsiderperformingrefinementfromtheglobalview.Inconsistentparsingresultsareverycommoninpre-dictionsofexistingsceneparsingframeworks,asshowninFigure1(b).Toaddressthisproblem,wedesigntheGlobal-residualRefinementNetwork(GRN)throughexploit-ingglobalcontextualinformationandspatiallayoutrelation-shipsduringrefining.ThisnetworktakestheoriginalimagesandtheKconfidencemaps(i.e.,theoutputofthelastlayerbeforeSoftMaxlayer,eachforoneoftheKsemanticclasses)asinput.Thenoutputstheglobalparsingresidual,whichwillbeaddedtotheinputconfidencemapstoobtaintheglobalrectifyingresults.Thisnetworkeffectivelycapturesglobalcontextualinformationbyiterativelyusingadeepneuralnet-workwithlargereceptivefields.AfterglobalrefinementbyGRN,somemislabelingcanbecorrectedandsomeinconsis-" e09c7bbf1bef602018928acb395f09448a0366b8,Learning beautiful (and ugly) attributes.,"MARCHESOTTI, PERRONNIN: LEARNING BEAUTIFUL (AND UGLY) ATTRIBUTES Learning beautiful (and ugly) attributes Luca Marchesotti Florent Perronnin Xerox Research Centre Europe Meylan, France" e096b11b3988441c0995c13742ad188a80f2b461,DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers,"Noname manuscript No. (will be inserted by the editor) DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers Amir Ghodrati · Ali Diba · Marco Pedersoli · Tinne Tuytelaars · Luc Van Gool Received: date / Accepted: date" e0e71b59a34c97d15e5ff148fb9a43b892d45bd5,Facial Expression Emotion Detection for Real-Time Embedded Systems †,"Article Facial Expression Emotion Detection for Real-Time Embedded Systems † Saeed Turabzadeh 1, Hongying Meng 1,* ID , Rafiq M. Swash 1 ID , Matus Pleva 2 ID and Jozef Juhar 2 ID Department of Electronic and Computer Engineering, Brunel University London, Uxbridge UB8 3PH, UK; (S.T.); (R.M.S.) Department of Electronics and Multimedia Telecommunications, Technical University of Kosice, Letna 9, 04001 Kosice, Slovakia; (M.P.); (J.J.) * Correspondence: Tel.: +44-1895-265496 This paper is an extended version of our paper in Proceedings of Innovative Computing Technology (INTECH 2017), Luton, UK, 16–18 August 2017; with permission from IEEE. Received: 15 December 2017; Accepted: 22 January 2018; Published: 26 January 2018" e0152a4e30f4ce73fd7a3d56f9d796da6dad4bdc,Indexation audio-visuelle des personnes dans un contexte de télévision. (Audio-visual indexing of people in TV-context),"Indexation audio-visuelle des personnes dans un ontexte de télévision Meriem Bendris To cite this version: Meriem Bendris. Indexation audio-visuelle des personnes dans un contexte de télévision. Traitement du signal et de l’image. Télécom ParisTech, 2011. Français. HAL Id: pastel-00661662 https://pastel.archives-ouvertes.fr/pastel-00661662 Submitted on 20 Jan 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" e043d79f4dc41c9decaf637d8ffdd11f8ed59f2b,Distance metric learning for image and webpage comparison. (Apprentissage de distance pour la comparaison d'images et de pages Web),"Distance metric learning for image and webpage omparison Marc Teva Law To cite this version: Marc Teva Law. Distance metric learning for image and webpage comparison. Image Processing. Uni- versité Pierre et Marie Curie - Paris VI, 2015. English. . HAL Id: tel-01135698 https://tel.archives-ouvertes.fr/tel-01135698v2 Submitted on 18 Mar 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" e01ac06aa1f0b193a620bf70c5dad91128a1bc90,CAPTAIN: Comprehensive Composition Assistance for Photo Taking,"International Journal on Computer Vision manuscript No. (will be inserted by the editor) CAPTAIN: Comprehensive Composition Assistance for Photo Taking Farshid Farhat · Mohammad Mahdi Kamani · James Z. Wang Received: date / Accepted: date" e0cac58f3855cd84b9d28f508b2f7711e0d7e44a,3 A : A PERSON RE-IDENTIFICATION SYSTEM VIA ATTRIBUTE AUGMENTATION AND AGGREGATION,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" e00526ff149bd61f6811ba2f2145ed22d9306319,Personal Space Regulation in Childhood Autism Spectrum Disorders,"Personal Space Regulation in Childhood Autism Spectrum Disorders Erica Gessaroli1,2, Erica Santelli3, Giuseppe di Pellegrino1,4*, Francesca Frassinetti1,2* Department of Psychology, University of Bologna, Bologna, Italy, 2 Fondazione Salvatore Maugeri, Clinica del Lavoro e della Riabilitazione, Istituto di Ricovero e Cura a Carattere Scientifico, Mantova, Castel Goffredo, Italy, 3 Centro Autismo, Reggio Emilia, Italy, 4 Center for Studies and Research in Cognitive Neuroscience, Cesena, Italy" 6898b0934d2bc34acc61a3c63fbb20337d7b9a95,Learning Styles and Emotion Recognition in a Fuzzy Expert System,"Learning Styles and Emotion Recognition in a Fuzzy Expert System Ramón Zatarain-Cabada, M. Lucía Barrón-Estrada, Rosalío Zatarain-Cabada Instituto Tecnológico de Culiacán, Juan de Dios Bátiz s/n, Col. Guadalupe, Culiacán Sinaloa, 80220, Mexico {rzatarain," 68ba19afe924699b4a0c84af91c05deb5b03e3bd,Do Characteristics of Faces That Convey Trustworthiness and Dominance Underlie Perceptions of Criminality?,"Do Characteristics of Faces That Convey Trustworthiness nd Dominance Underlie Perceptions of Criminality? Heather D. Flowe* College of Medicine, Biological Sciences and Psychology, University of Leicester, Leicester, United Kingdom" 683260bf133c282439b91ac4427d42d73a5988b5,"Optimizing Program Performance via Similarity, Using Feature-aware and Feature-agnostic Characterization Approaches","UNIVERSITY OF CALIFORNIA, IRVINE Optimizing Program Performance via Similarity, Using Feature-aware and Feature-agnostic Characterization Approaches DISSERTATION submitted in partial satisfaction of the requirements for the degree of DOCTOR OF PHILOSOPHY in Information and Computer Science Rosario Cammarota Dissertation Committee: Professor Alexander V. Veidenbaum, Chair Professor Alexandru Nicolau Professor Nikil Dutt" 6821a3fa67d9d58655c26e24b568fda1229ac5be,Fast and robust object segmentation with the Integral Linear Classifier,"Fast and Robust Object Segmentation with the Integral Linear Classifier David Aldavert Computer Vision Center Dept. Computer Science Arnau Ramisa INRIA-Grenoble Artificial Intelligence Research Univ. Aut`onoma de Barcelona Institute (IIIA-CSIC) Ramon Lopez de Mantaras Artificial Intelligence Research Institute (IIIA-CSIC) Campus UAB Ricardo Toledo Computer Vision Center Dept. Computer Science Univ. Aut`onoma de Barcelona" 68ee4a2a4aecff38598cf99e72bc21a6ecbbcd1f,Approximating Discrete Probability Distribution of Image Emotions by Multi-Modal Features Fusion,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 6888f3402039a36028d0a7e2c3df6db94f5cb9bb,CLASSIFIER-TO-GENERATOR ATTACK: ESTIMATION,"Under review as a conference paper at ICLR 2018 CLASSIFIER-TO-GENERATOR ATTACK: ESTIMATION OF TRAINING DATA DISTRIBUTION FROM CLASSIFIER Anonymous authors Paper under double-blind review" 68d08ed9470d973a54ef7806318d8894d87ba610,Drive Video Analysis for the Detection of Traffic Near-Miss Incidents,"Drive Video Analysis for the Detection of Traffic Near-Miss Incidents Hirokatsu Kataoka1, Teppei Suzuki1 , Shoko Oikawa3, Yasuhiro Matsui4 and Yutaka Satoh1" 68e4ed4daa2ae94c789443ed222601a4a47f9a45,BUILDING EXTRACTION FROM POLARIMETRIC INTERFEROMETRIC SAR DATA USING BAYESIAN NETWORK,"BUILDING EXTRACTION FROM POLARIMETRIC INTERFEROMETRIC SAR DATA USING BAYESIAN NETWORK Wenju He and Olaf Hellwich Berlin University of Technology {wenjuhe, . INTRODUCTION Many researches have been done to extract buildings from high resolution Synthetic Aperture Radar (SAR) data. The extraction problem is far from solved due to many constraints, e.g. SAR side-look imaging, speckle, and lack of object extent in SAR images. Building detection algorithms usually use intensity information or textures. Layovers and shadows can be discriminated from other objects since they have distinct appearances. The detection is hindered by the small geometric extent of buildings in SAR images and the orientation dependency of reflections. Many buildings are occluded with surrounding environments. The interactions between radar and various buildings are hard to model. Polarimetric SAR data can resolve some ambiguities ecause polarimetry can be used to analyze physical scattering properties. Scatterers formed by buildings have strong double- ounce reflections. Polarimetric SAR data also allow us to extract rich features for object detection. Polarimetric interferometric SAR (PolinSAR) data are more promising since they are able to provide object height information. Furthermore, coherent scatterer and permanent scatterer analysis using interferometric SAR (InSAR) data are powerful in urban change detection pplications. As to building localization, a height map retrieved from PolinSAR data is very advantageous. PolinSAR data are expected to further resolve ambiguities in building detection problems. For meter-resolution PolinSAR data, however, it is hard to retrieve phases of building roofs from interferometric phase ecause of complex scattering mechanisms and building geometries. Building height image was derived from InSAR digital" 6889d649c6bbd9c0042fadec6c813f8e894ac6cc,Analysis of Robust Soft Learning Vector Quantization and an application to Facial Expression Recognition,"Analysis of Robust Soft Learning Vector Quantization and an application to Facial Expression Recognition" 68484ae8a042904a95a8d284a7f85a4e28e37513,Spoofing Deep Face Recognition with Custom Silicone Masks,"Spoofing Deep Face Recognition with Custom Silicone Masks Sushil Bhattacharjee Amir Mohammadi S´ebastien Marcel Idiap Research Institute. Centre du Parc, Rue Marconi 19, Martigny (VS), Switzerland {sushil.bhattacharjee; amir.mohammadi;" 68b44eb4c7440046783146064ae9e715a72766dc,An Investigation of Physiological Arousal in Children with Autism and Co-morbid Challenging Behaviour,"An Investigation of Physiological Arousal in Children with Autism and Co-morbid Challenging Behaviour Sinéad Lydon A thesis submitted to Trinity College Dublin, the University of Dublin, in partial fulfillment of the requirements for the Degree of Doctor of Philosophy (PhD) in Psychology Supervisors: Dr. Olive Healy (Trinity College Dublin) and Professor Brian Hughes (National University of Ireland, Galway)." 68333b73613c59914bfe1264a440b3cf854dc15c,Mugeetion: Musical Interface Using Facial Gesture and Emotion,"Mugeetion: Musical Interface Using Facial Gesture and Emotion Eunjeong Stella Koh Music Department UC San Diego" 688f5cb02dc6c779fa9fd18f44b792f9626bdcd0,Visual pattern discovery in image and video data: a brief survey,"Visual Pattern Discovery in Image and Video Data: A Brief Survey Hongxing Wang, Gangqiang Zhao and Junsong Yuan" 68b01afed57ed7130d993dffc03dcbfa36d4e038,Adversarial Learning with Local Coordinate Coding,"Adversarial Learning with Local Coordinate Coding Jiezhang Cao * 1 Yong Guo * 1 Qingyao Wu * 1 Chunhua Shen 2 Junzhou Huang 3 Mingkui Tan 1" 68d40176e878ebffbc01ffb0556e8cb2756dd9e9,Locality Repulsion Projection and Minutia Extraction Based Similarity Measure for Face Recognition,"International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 International Conference on Humming Bird ( 01st March 2014) RESEARCH ARTICLE OPEN ACCESS Locality Repulsion Projection and Minutia Extraction Based Similarity Measure for Face Recognition Agnel AnushyaP.1,RamyaP.2 AgnelAnushya P. is currently pursuing M.E (Computer Science and engineering) at Vins Christian college of Ramya P. is currently working as an Asst. Professor in the dept. of Information Technology at Vins Christian Engineering. ollege of Engineering." 688cb9fd33769b152806c04ef6fc276629a9f300,LocNet: Improving Localization Accuracy for Object Detection,"LocNet: Improving Localization Accuracy for Object Detection Spyros Gidaris Universite Paris Est, Ecole des Ponts ParisTech Nikos Komodakis Universite Paris Est, Ecole des Ponts ParisTech" 68a05a845b6ace756d51c5bbce927479c9b9ab95,A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity,"A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity Hoda Heidari ETH Z¨urich Krishna P. Gummadi MPI-SWS Michele Loi University of Z¨urich Andreas Krause ETH Z¨urich" 687ef116d7115498f12dff1b3338d959f164ef6b,Using Thought-Provoking Children's Questions to Drive Artificial Intelligence Research,"Using Thought-Provoking Children’s Questions to Drive Artificial Intelligence Research Erik T. Mueller and Henry Minsky Minsky Institute for Artificial Intelligence http://minskyinstitute.org/ September 14, 2015 00:09" 68c279d4fcc02710056e73a3b0d0d564a7615cad,Unified framework for fast exact and approximate search in dissimilarity spaces,"Unified Framework for Fast Exact and Approximate Search in Dissimilarity Spaces TOM´AˇS SKOPAL Charles University in Prague In multimedia systems we usually need to retrieve DB objects based on their similarity to a query object, while the similarity assessment is provided by a measure which defines a (dis)similarity score for every pair of DB objects. In most existing applications, the similarity measure is required to be a metric, where the triangle inequality is utilized to speedup the search for relevant objects y use of metric access methods (MAMs), e.g. the M-tree. A recent research has shown, however, that non-metric measures are more appropriate for similarity modeling due to their robustness and ease to model a made-to-measure similarity. Unfortunately, due to the lack of triangle inequality, the non-metric measures cannot be directly utilized by MAMs. From another point of view, some sophisticated similarity measures could be available in a black-box non-analytic form (e.g. as an lgorithm or even a hardware device), where no information about their topological properties is provided, so we have to consider them as non-metric measures as well. From yet another point of view, the concept of similarity measuring itself is inherently imprecise and we often prefer fast ut approximate retrieval over an exact but slower one. To date, the mentioned aspects of similarity retrieval have been solved separately, i.e. exact vs. approximate search or metric vs. non-metric search. In this paper we introduce a similarity retrieval framework which incorporates both of the aspects into a single unified model. Based on" 6872615b0298aa01affa3b8d71e4d5547244278f,WEIGHTED FOURIER IMAGE ANALYSIS AND MODELING,"WEIGHTED FOURIER IMAGE ANALYSIS AND MODELING Shubing Wang A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy (Statistics) t the UNIVERSITY OF WISCONSIN – MADISON" 688680d9902f688b9ac2d47c399ceebd1014d785,GIS-supported people tracking re-acquisition in a multi-camera environment,"GIS-supported People Tracking Re-Acquisition in a Multi-Camera Environment Anastasios Dimou1, Vasileios Lovatsis1, Andreas Papadakis2, Stelios Pantelopoulos2 and Petros Daras1 CERTH-ITI, 6th kilometer Harilaou-Thermi, Thessaloniki, Greece SingularLogic, Athens, Greece Keywords: GIS, Re-Identification, Multi-camera." 6844a700aee36bd809d1188f6f9e81707c513f19,Interactive model-based reconstruction of the human head using an RGB-D sensor,"Interactive Model-based Reconstruction of the Human Head using an RGB-D Sensor M. Zollh¨ofer, J. Thies, M. Colaianni, M. Stamminger, G. Greiner Computer Graphics Group, University Erlangen-Nuremberg, Germany" 68becbe61cf30ef93b2679866d3a511e919ffb2f,"Motor, emotional, and cognitive empathy in children and adolescents with autism spectrum disorder and conduct disorder.","J Abnorm Child Psychol (2013) 41:425–443 DOI 10.1007/s10802-012-9689-5 Motor, Emotional, and Cognitive Empathy in Children nd Adolescents with Autism Spectrum Disorder nd Conduct Disorder Danielle Bons & Egon van den Broek & Floor Scheepers & Pierre Herpers & Nanda Rommelse & Jan K. Buitelaaar Published online: 25 October 2012 # Springer Science+Business Media New York 2012" 68df1f746a3434ee8bcc8918d46809ddaad38b12,Subspace learning in minimax detection,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE Email: {raja.fazliza, david.mary, SUBSPACE LEARNING IN MINIMAX DETECTION Raja Fazliza R. Suleiman, David Mary and Andr´e Ferrari Campus Valrose, 06108 Nice Cedex 02, FRANCE Laboratoire J.-L. Lagrange, UMR7293, . INTRODUCTION AND PRIOR WORKS (cid:26) H0" 68caf5d8ef325d7ea669f3fb76eac58e0170fff0,Long-term face tracking in the wild using deep learning, 68d4056765c27fbcac233794857b7f5b8a6a82bf,Example-Based Face Shape Recovery Using the Zenith Angle of the Surface Normal,"Example-Based Face Shape Recovery Using the Zenith Angle of the Surface Normal Mario Castel´an1, Ana J. Almaz´an-Delf´ın2, Marco I. Ram´ırez-Sosa-Mor´an3, nd Luz A. Torres-M´endez1 CINVESTAV Campus Saltillo, Ramos Arizpe 25900, Coahuila, M´exico Universidad Veracruzana, Facultad de F´ısica e Inteligencia Artificial, Xalapa 91000, ITESM, Campus Saltillo, Saltillo 25270, Coahuila, M´exico Veracruz, M´exico" 683fbd7593cf5c22ef54004bb89c469eab2f656e,URJC&UNED at ImageCLEF 2013 Photo Annotation Task,"URJCyUNED at ImageCLEF 2012 Photo Annotation task⋆ Jes´us S´anchez-Oro1, Soto Montalvo1, Antonio S. Montemayor1, Ra´ul Cabido1, Juan J. Pantrigo1, Abraham Duarte1, V´ıctor Fresno2, and Raquel Mart´ınez2 Universidad Rey Juan Carlos, M(cid:19)ostoles, Spain Universidad Nacional de Educaci(cid:19)on a Distancia, Madrid, Spain" 6848a0993b0754b27750a78196fa91e3cf2bbebb,Accurate and Robust Neural Networks for Security Related Applications Exampled by Face Morphing Attacks,"Accurate and Robust Neural Networks for Security Related Applications Exampled by Face Morphing Attacks Clemens Seibold1, Wojciech Samek1, Anna Hilsmann1 and Peter Eisert1,2 Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany Humboldt University Berlin, Unter den Linden 6, 10099 Berlin, Germany" 68ae4db6acf5361486f153ee0c0d540e0823682a,FlashReport Memory conformity for con fi dently recognized items : The power of social in fl uence on memory reports,"Journal of Experimental Social Psychology 48 (2012) 783–786 Contents lists available at SciVerse ScienceDirect Journal of Experimental Social Psychology j o u r n a l h o m e pa ge : w ww . e l s e v i e r . c o m/ l o c a t e / j e s p FlashReport Memory conformity for confidently recognized items: The power of social influence on memory reports Ruth Horry ⁎, Matthew A. Palmer 1, Michelle L. Sexton, Neil Brewer Flinders University, Australia r t i c l e i n f o b s t r a c t Article history: Received 14 September 2011 Revised 9 December 2011 Available online 22 December 2011 Keywords: Memory conformity Confidence Face recognition" 682f735ef796370f510218eb7afb4d2a36cd1256,On Offline Evaluation of Vision-Based Driving Models, 68f61154a0080c4aae9322110c8827978f01ac2e,"Recognizing blurred , non-frontal , illumination and expression variant partially occluded faces","Research Article Journal of the Optical Society of America A Recognizing blurred, non-frontal, illumination and expression variant partially occluded faces ABHIJITH PUNNAPPURATH1* AND AMBASAMUDRAM NARAYANAN RAJAGOPALAN1 Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai 600036, India. *Corresponding author: Compiled June 26, 2016 The focus of this paper is on the problem of recognizing faces across space-varying motion blur, changes in pose, illumination, and expression, as well as partial occlusion, when only a single image per subject is available in the gallery. We show how the blur incurred due to relative motion between the camera and the subject during exposure can be estimated from the alpha matte of pixels that straddle the boundary etween the face and the background. We also devise a strategy to automatically generate the trimap re- quired for matte estimation. Having computed the motion via the matte of the probe, we account for pose variations by synthesizing from the intensity image of the frontal gallery, a face image that matches the pose of the probe. To handle illumination and expression variations, and partial occlusion, we model the probe as a linear combination of nine blurred illumination basis images in the synthesized non-frontal pose, plus a sparse occlusion. We also advocate a recognition metric that capitalizes on the sparsity of the occluded pixels. The performance of our method is extensively validated on synthetic as well as real face data. © 2016 Optical Society of America" 68c17aa1ecbff0787709be74d1d98d9efd78f410,GENDER CLASSIFICATION FROM FACE IMAGES USING MUTUAL INFORMATION AND FEATURE FUSION,"International Journal of Optomechatronics, 6: 92–119, 2012 Copyright # Taylor & Francis Group, LLC ISSN: 1559-9612 print=1559-9620 online DOI: 10.1080/15599612.2012.663463 GENDER CLASSIFICATION FROM FACE IMAGES USING MUTUAL INFORMATION AND FEATURE FUSION Claudio Perez, Juan Tapia, Pablo Este´vez, and Claudio Held Department of Electrical Engineering and Advanced Mining Technology Center, Universidad de Chile, Santiago, Chile In this article we report a new method for gender classification from frontal face images using feature selection based on mutual information and fusion of features extracted from intensity, shape, texture, and from three different spatial scales. We compare the results of three different mutual information measures: minimum redundancy and maximal relevance (mRMR), normalized mutual information feature selection (NMIFS), and conditional mutual information feature selection (CMIFS). We also show that by fusing features extracted from six different methods we significantly improve the gender classification results relative to those previously published, yielding 99.13% of the gender classification rate on the FERET database. Keywords: Feature fusion, feature selection, gender classification, mutual information, real-time gender" 688ae87c5e40583ecf9ec6d06d4d15a3e62f5556,A New Angle on L2 Regularization,"A New Angle on L2 Regularization (interactive version available at https://thomas-tanay.github.io/post--L2-regularization/) Thomas Tanay Lewis D Grif‌f‌in CoMPLEX, UCL CoMPLEX, UCL Deep neural networks have been shown to be vulnerable to the dversarial example phenomenon: all models tested so far can have their lassifications dramatically altered by small image perturbations [1, 2]. The following predictions were for instance made by a state-of-the-art network trained to recognize celebrities [3]:" 684c8acd49148020e9bf9c4f4aefc03708a6dac0,Video-Based Person Re-Identification With Accumulative Motion Context,"Video-based Person Re-identification with Accumulative Motion Context Hao Liu, Zequn Jie, Karlekar Jayashree, Meibin Qi, Jianguo Jiang and Shuicheng Yan, Fellow, IEEE, Jiashi Feng" 68b6ec13d06facacf5637f90828ab5b6e352be60,Neural Proximal Gradient Descent for Compressive Imaging,"Neural Proximal Gradient Descent for Compressive Imaging Morteza Mardani1,2, Qingyun Sun4, Shreyas Vasawanala2, Vardan Papyan3, Hatef Monajemi3, John Pauly1, and David Donoho3 Depts. of Electrical Eng., Radiology, Statistics, and Mathematics; Stanford University" 6864b089c8586b0e3f6bd6736cabea96b1c4a28a,Robust classification for occluded ear via Gabor scale feature-based non-negative sparse representation,"Robust classification for occluded ear via Gabor scale feature-based non-negative sparse representation Baoqing Zhang Zhichun Mu Chen Li Hui Zeng Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 01/02/2016 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx" 685f8df14776457c1c324b0619c39b3872df617b,Face Recognition with Preprocessing and Neural Networks,"Master of Science Thesis in Electrical Engineering Department of Electrical Engineering, Linköping University, 2016 Face Recognition with Preprocessing and Neural Networks David Habrman" 68eb5404a22fcca595cc6360e9a77a4b09156eb2,Appearance-based person reidentification in camera networks: problem overview and current approaches,"J Ambient Intell Human Comput (2011) 2:127–151 DOI 10.1007/s12652-010-0034-y O R I G I N A L R E S E A R C H Appearance-based person reidentification in camera networks: problem overview and current approaches Gianfranco Doretto • Thomas Sebastian • Peter Tu • Jens Rittscher Received: 30 January 2010 / Accepted: 4 October 2010 / Published online: 14 January 2011 Ó Springer-Verlag 2011" c9bbe64ae797b8d522eac5cc115ac31e8e5491bf,Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction,"Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction E. Jared Shamwell1, Sarah Leung2, William D. Nothwang3" c9c3ba7bebee553490a9ddbc6840292ed5aed90b,SCHOOL OF COMPUTER ENGINEERING PhD Confirmation Report on Object Detection in Real Images,"SCHOOL OF COMPUTER ENGINEERING PhD Confirmation Report Object Detection in Real Images Submitted by: Dilip Kumar Prasad Research Student (PhD) School of Computer Engineering E-mail: Supervisor: Dr. Maylor K. H. Leung Associate Professor, School of Computer Engineering E-mail: August 2010" c94c2cf52fef0503c09268c7d1faee60465ee08e,BenchIP: Benchmarking Intelligence Processors,"BENCHIP: Benchmarking Intelligence Processors Jinhua Tao1, Zidong Du1,2, Qi Guo1,2, Huiying Lan1, Lei Zhang1 Shengyuan Zhou1, Lingjie Xu3, Cong Liu4, Haifeng Liu5, Shan Tang6 Allen Rush7,Willian Chen7, Shaoli Liu1,2, Yunji Chen1, Tianshi Chen1,2 ICT CAS,2Cambricon,3Alibaba Infrastructure Service, Alibaba Group IFLYTEK,5JD,6RDA Microelectronics,7AMD" c9ea71631540dfc13079338fb534c6eb78198d4e,Automatic Visual Integration: Defragmenting the Face,"Automatic Visual Integration: Defragmenting the Face Electrical & Computer Engineering Department, University of California, San Diego Luke Barrington La Jolla, CA 92093 USA Computer Science & Engineering Department, University of California, San Diego Garrison W. Cottrell La Jolla, CA 92093 USA" c9b13a5d5c7a688b567e08d933a8098724c75325,Motion in action : optical flow estimation and action localization in videos. (Le mouvement en action : estimation du flot optique et localisation d'actions dans les vidéos),"Motion in action : optical flow estimation and action localization in videos Philippe Weinzaepfel To cite this version: Philippe Weinzaepfel. Motion in action : optical flow estimation and action localization in videos. Computer Vision and Pattern Recognition [cs.CV]. Université Grenoble Alpes, 2016. English. . HAL Id: tel-01407258 https://tel.archives-ouvertes.fr/tel-01407258 Submitted on 1 Dec 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" c97774191be232678a45d343a25fcc0c96c065e7,Co-Training of Audio and Video Representations from Self-Supervised Temporal Synchronization,"Co-Training of Audio and Video Representations from Self-Supervised Temporal Synchronization Undergraduate Thesis written by Bruno Korbar under the supervision of Professor Lorenzo Torresani and Du Tran, and submitted to the Committee as a culminating experience for the degree of Bachelor of Arts in Computer Science t Dartmouth College. Date of the public presentation: Members of the Thesis Committee: May 29, 2018 Prof Lorenzo Torresani Prof Saeed Hassanpour Prof Venkatramanan Siva Subrahmanian Dartmouth Computer Science Technical Report TR2018-849" c9d9e91bec48a13048a2a0626892e00575e236f5,A Two Dimensional Facial Features Analysis for Gender-based Comparison Using Morphometrics Approach,"International Journal of Engineering & Technology, 7 (4.31) (2018) 214-219 International Journal of Engineering & Technology Website: www.sciencepubco.com/index.php/IJET Research paper A Two Dimensional Facial Features Analysis for Gender-based Comparison Using Morphometrics Approach Olalekan Agbolade1*, Azree Shahrel Ahmad Nazri2 Faculty of Computer Science & Information Technology, Universiti Putra Malaysia, Serdang, Selangor, Malaysia *Corresponding author E-mail:" c9876861cc0e33fffe8c3ce7484ae27d3b2eeb75,A Corpus for Analyzing Linguistic and Paralinguistic Features in Multi-Speaker Spontaneous Conversations – EVA Corpus,"A Corpus for Analyzing Linguistic and Paralinguistic Features in Multi-Speaker Spontaneous Conversations – EVA Corpus IZIDOR MLAKAR, ZDRAVKO KAČIČ, MATEJ ROJC Faculty of Electrical Engineering and Computer Science, University of Maribor SLOVENIA" c93996cb126589b30c04bf1256c97a4431c0e8b6,Robustness Analysis of Pedestrian Detectors for Surveillance,"Robustness Analysis of Pedestrian Detectors for Surveillance Yuming Fang, Senior Memmber, IEEE, Guanqun Ding, Yuan Yuan, Weisi Lin, Fellow, IEEE, nd Haiwen Liu, Senior Memmber, IEEE" c924137ca87e8b4e1557465405744f8b639b16fc,Seeding Deep Learning using Wireless Localization,"ADDRESSING TRAINING BIAS VIA AUTOMATED IMAGE ANNOTATION Zhujun Xiao 1 Yanzi Zhu 2 Yuxin Chen 1 Ben Y. Zhao 1 Junchen Jiang 1 Haitao Zheng 1" c91103e6612fa7e664ccbc3ed1b0b5deac865b02,Automatic facial expression recognition using statistical-like moments,"Automatic facial expression recognition using statistical-like moments Roberto D’Ambrosio, Giulio Iannello, and Paolo Soda {r.dambrosio, g.iannello, Integrated Research Center, Universit`a Campus Bio-Medico di Roma, Via Alvaro del Portillo, 00128 Roma, Italy" c933c4bef57be3585abb13bacb74aca29588a6ac,People Detection in Color and Infrared Video Using HOG and Linear SVM,"People Detection in Color and Infrared Video using HOG and Linear SVM Pablo Tribaldos1, Juan Serrano-Cuerda1, Mar´ıa T. L´opez1;2, Antonio Fern´andez-Caballero1;2, and Roberto J. L´opez-Sastre3 Instituto de Investigaci(cid:19)on en Inform(cid:19)atica de Albacete (I3A), 02071-Albacete, Spain Universidad de Castilla-La Mancha, Departamento de Sistemas Inform(cid:19)aticos, 02071-Albacete, Spain Universidad de Alcal(cid:19)a, Dpto. de Teor(cid:19)(cid:16)a de la se~nal y Comunicaciones, 8805-Alcal(cid:19)a de Henares (Madrid), Spain" c9d7219d54eccb9e49b72044d805e103fe17ba80,Towards Information-Seeking Agents,"Under review as a conference paper at ICLR 2017 TOWARDS INFORMATION-SEEKING AGENTS Philip Bachman∗ phil.bachman Alessandro Sordoni∗ lessandro.sordoni Adam Trischler dam.trischler Maluuba Research Montréal, QC, Canada" c99a23a5bb5d5b10098395f59e9f8f79c79a75bd,Prediction Using Audience Chat Reactions,"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 972–978 Copenhagen, Denmark, September 7–11, 2017. c(cid:13)2017 Association for Computational Linguistics" c90b109301244e59771fec431a8d50a78e395956,Alternative face models for 3 D face registration,"Alternative face models for 3D face registration Albert Ali Salah, Ne¸se Aly¨uz, Lale Akarun Bo˘gazi¸ci University, 34342 Bebek, ˙Istanbul, Turkey" c9bbf31afbec278ca735e91cf5e9c70dd3aa41a4,Enhancing 3D Face Recognition By Mimics Segmentation,"Enhancing 3D Face Recognition By Mimics Segmentation Boulbaba Ben Amor, Mohsen Ardabilian, and Liming Chen MI Department, LIRIS Laboratory, CNRS 5205 Ecole Centrale de Lyon, 36 av. Guy de Collongue, 69134 Lyon , France {Boulbaba.Ben-Amor, Mohsen.Ardabilian," c94ae3d1c029a70cabdab906fe1460d84fd42acd,"Comparison of wavelet , Gabor and curvelet transform for face recognition","Optica Applicata, Vol. XLI, No. 1, 2011 Comparison of wavelet, Gabor and curvelet transform for face recognition JIULONG ZHANG, YINGHUI WANG, ZHIYU ZHANG, CHUNLI XIA Computer Science and Engineering School, Xian University of Technology, Xi'an, 710048, P.R. China There has been much research about using Gabor wavelet for face recognition. Other multiscale geometrical tools, such as curvelet and contourlet, have also been used for face recognition, thus it is interesting to know which method performs best, especially under illumination and expression hanges. In this paper, we make a systematic comparison of wavelet, Gabor and curvelet for recognition, and find the best subband irrelevant to expression and illumination changes. We ombine the multiscale analysis with subspace decomposition as our algorithm. Experiments show that for expression changes, the properties of the coarse layer of curvelet and wavelet are very good. Whilst for illumination changes, the low frequency parts of the two methods are similarly influenced, but the detail coefficients of curvelet and the high frequency of wavelet work fine with PCA, with the former outperforming the latter. When these two factors change simultaneously, the detail layer of curvelet is better relative to the others. Keywords: wavelet transform, Gabor wavelet, curvelet transform, face recognition, multiscale analysis. . Introduction Among the so many popular methods for face recognition, the wavelet transform is" c92e701c908908bda407f12edf6984b283e8c258,Where Should You Attend While Driving?,"Where Should You Attend While Driving? Simone Calderara Stefano Alletto Andrea Palazzi∗ Francesco Solera∗ Rita Cucchiara University of Modena and Reggio Emilia" c9b139b78e5337580047138d7fc2dff3b8fcf31f,Offline Face Recognition System Based on Gabor- Fisher Descriptors and Hidden Markov Models,"Offline Face Recognition System Based on Gabor- Fisher Descriptors and Hidden Markov Models Zineb Elgarrai1, Othmane Elmeslouhi2, Mustapha Kardouchi3, Hakim Allali1, Sid-Ahmed Selouani4 FST of Hassan 1st University Settat /LAVETTE Laboratory, FPO of Ibnou Zohr University /LabSIE Laboratory Université de Moncton /Département d’Informatique, Université de Moncton/Département de Gestion de l’Information" c936b9a958a67cdd5665b923569d9d786c934029,Software Specification Document For,"Software Specification Document Crowd_Count++ Version 1.0 November 2015 Juan Mejia      Michael Safdieh      Rosario Antunez Prepared by:" c9311a0c5045d86a617bd05a5cc269f44e81508d,Accurate Eye Centre Localisation by Means of Gradients,"ACCURATE EYE CENTRE LOCALISATION BY MEANS OF GRADIENTS Institute for Neuro- and Bioinformatics, University of L¨ubeck, Ratzeburger Allee 160, D-23538 L¨ubeck, Germany Pattern Recognition Company GmbH, Innovations Campus L¨ubeck, Maria-Goeppert-Strasse 1, D-23562 L¨ubeck, Germany {timm, Fabian Timm and Erhardt Barth Keywords:" c96f012f4915398259e7e223810c57898b5e1a76,Fast LIDAR-based Road Detection Using Convolutional Neural Networks,"Fast LIDAR-based Road Detection Using Convolutional Neural Networks Luca Caltagirone1, Samuel Scheidegger2, Lennart Svensson3, Mattias Wahde4 {luca.caltagirone, samsch, lennart.svensson," c95d8b9bddd76b8c83c8745747e8a33feedf3941,Image Ordinal Classification and Understanding: Grid Dropout with Masking Label,"label:(1, 0, 1, 0, 1, 1, 1, 1, 1)Masking label:(0, 1, 1, 1, 0, 1, 1, 1, 1)Entire imageInput imageNeuron dropout’s gradCAMGrid dropout’s gradCAMFig.1.Above:imageordinalclassificationwithrandomlyblackoutpatches.Itiseasyforhumantorecognizetheageregardlessofthemissingpatches.Themaskinglabelisalsousefultoimageclassification.Bottom:griddropout’sgrad-CAMisbetterthanthatofneurondropout.Thatistosay,griddropoutcanhelplearningfeaturerepresentation.problem[1].Withtheproliferationofconvolutionalneuralnetwork(CNN),workshavebeencarriedoutonordinalclas-sificationwithCNN[1][2][3].Thoughgoodperformanceshavebeenloggedwithmoderndeeplearningapproaches,therearetwoproblemsinimageordinalclassification.Ononehand,theamountofordinaltrainingdataisverylim-itedwhichprohibitstrainingcomplexmodelsproperly,andtomakemattersworse,collectinglargetrainingdatasetwithordinallabelisdifficult,evenharderthanlabellinggenericdataset.Therefore,insufficienttrainingdataincreasestheriskofoverfitting.Ontheotherhand,lessstudiesareconductedtounderstandwhatdeepmodelshavelearnedonordinaldata978-1-5386-1737-3/18/$31.00c(cid:13)2018IEEE" c95c30fb990576704f2ccb3dc3335aaf43208856,CS 231 A Project report,"CS231A Project report Cecile Foret March 19, 2014." c9b90cf9cdd901bd3072d6dfd8ddc523c55944b1,Adversarial Generator-Encoder Networks,"Adversarial Generator-Encoder Networks Dmitry Ulyanov 1 2 Andrea Vedaldi 3 Victor Lempitsky 1" e810ddd9642db98492bd6a28b08a8655396c1555,Facing facts: neuronal mechanisms of face perception.,"Review Acta Neurobiol Exp 2008, 68: 229–252 Facing facts: Neuronal mechanisms of face perception Monika Dekowska1, Michał Kuniecki2, and Piotr Jaśkowski3* Kazimierz Wielki University of Bydgoszcz, Poland; 2Department of Psychophysiology, Jagiellonian University, Kraków, Poland; 3Department of Cognitive Psychology, University of Finance and Management, Warszawa, Poland, *Email: The face is one of the most important stimuli carrying social meaning. Thanks to the fast analysis of faces, we are able to judge physical attractiveness and features of their owners’ personality, intentions, and mood. From one’s facial expression we can gain information about danger present in the environment. It is obvious that the ability to process efficiently one’s face is crucial for survival. Therefore, it seems natural that in the human brain there exist structures specialized for face processing. In this article, we present recent findings from studies on the neuronal mechanisms of face perception and recognition in the light of current theoretical models. Results from brain imaging (fMRI, PET) and electrophysiology (ERP, MEG) show that in face perception particular regions (i.e. FFA, STS, IOA, AMTG, prefrontal and orbitofrontal cortex) are involved. These results are confirmed by behavioral data and clinical observations as well as by animal studies. The developmental findings reviewed in this article lead us to suppose that the ability to analyze face-like stimuli is hard-wired nd improves during development. Still, experience with faces is not sufficient for an individual to become an expert in face perception. This thesis is supported by the investigation of individuals with developmental disabilities, especially with utistic spectrum disorders (ASD). Key words: face perception, emotion perception" e8691980eeb827b10cdfb4cc402b3f43f020bc6a,Segmentation Guided Attention Networks for Visual Question Answering,"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics- Student Research Workshop, pages 43–48 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics- Student Research Workshop, pages 43–48 Vancouver, Canada, July 30 - August 4, 2017. c(cid:13)2017 Association for Computational Linguistics Vancouver, Canada, July 30 - August 4, 2017. c(cid:13)2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-3008 https://doi.org/10.18653/v1/P17-3008" e811550cc83a3650bee8764d5fab4bd26109ee73,Discriminant Phase Component for Face Recognition,"Hindawi Publishing Corporation Journal of Electrical and Computer Engineering Volume 2012, Article ID 718915, 12 pages doi:10.1155/2012/718915 Research Article Discriminant Phase Component for Face Recognition Naser Zaeri Faculty of Computer Studies, Arab Open University, P.O. Box 3322, Safat 13033, Kuwait Correspondence should be addressed to Naser Zaeri, Received 1 September 2011; Revised 14 December 2011; Accepted 14 December 2011 Academic Editor: Somaya Al-Maadeed Copyright © 2012 Naser Zaeri. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Numerous face recognition techniques have been developed owing to the growing number of real-world applications. Most of urrent algorithms for face recognition involve considerable amount of computations and hence they cannot be used on devices onstrained with limited speed and memory. In this paper, we propose a novel solution for ef‌f‌icient face recognition problem for systems that utilize small memory capacities and demand fast performance. The new technique divides the face images into omponents and finds the discriminant phases of the Fourier transform of these components automatically using the sequential floating forward search method. A thorough study and comprehensive experiments relating time consumption versus system performance are applied to benchmark face image databases. Finally, the proposed technique is compared with other known" e8f753208fc354fa9aeb3fa9c6acb3d45e7eac7b,Definite Description Lexical Choice: taking Speaker's Personality into account,"Definite Description Lexical Choice: taking Speaker’s Personality into account Alex Gwo Jen Lan, Ivandr´e Paraboni University of S˜ao Paulo, School of Arts, Sciences and Humanities S˜ao Paulo, Brazil" e8039e1531dd86da960be26d59718d2452f9943b,Scene Parsing and Fusion-Based Continuous Traversable Region Formation,"Scene parsing and fusion-based continuous traversable region formation Xuhong Xiao, Gee Wah Ng, Yuan Sin Tan, Yeo Ye Chuan 0 Science Park Drive, DSO national Laboratories, Singapore 118230" e8af37ac6e0a5b7f04b6824bb1f74e4f363b99b5,On the replication of CycleGAN,"Bachelor thesis Computer Science Radboud University On the replication of CycleGAN Author: Robin Elbers s4225678 First supervisor/assessor: MSc. Jacopo Acquarelli Second assessor: Prof. Tom Heskes August 10, 2018" e855856d4b61b6a732005418f543c49195cb1542,Novel Method for Eyeglasses Detection in Frontal Face Images,"Novel Method for Eyeglasses Detection in Frontal Face Images R. L. Parente, L. V. Batista Centro de Inform´atica - CI Universidade Federal da Para´ıba - UFPB Jo˜ao Pessoa, Brazil I. Andreza, E. Borges, R. Marques VSoft Research Group VSoft Technology Jo˜ao Pessoa, Brazil {igorlpa90, erickvagnerr," e8bcef31648bcde5a97c770dddbbcd1e09086930,A direct approach for object detection with catadioptric omnidirectional cameras,"Noname manuscript No. (will be inserted by the editor) A Direct Approach for Object Detection with Catadioptric Omnidirectional Cameras Ibrahim Cinaroglu · Yalin Bastanlar Received: date / Accepted: date" e8dda897372e6b4cf903234c7a9c40117711d8d8,What do you think of my picture? Investigating factors of influence in profile images context perception,"What do you think of my picture? Investigating factors of influence in profile images context perception Filippo Mazza, Matthieu Perreira da Silva, Patrick Le Callet, Ingrid Heynderickx To cite this version: Filippo Mazza, Matthieu Perreira da Silva, Patrick Le Callet, Ingrid Heynderickx. What do you think of my picture? Investigating factors of influence in profile images context perception. Human Vision and Electronic Imaging XX, Mar 2015, San Francisco, United States. Proc. SPIE 9394, Hu- man Vision and Electronic Imaging XX, 9394, . <10.1117/12.2082817>. HAL Id: hal-01149535 https://hal.archives-ouvertes.fr/hal-01149535 Submitted on 7 May 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est" e819a577c57c83a133a0a0e81180d14dc13b82e9,Pyramid Histogram of Oriented Gradients based Human Ear Identification,"Pyramid Histogram of Oriented Gradients based Human Ear Identification Pyramid Histogram of Oriented Gradients based Human Ear Identification Partha Pratim Sarangi1, B.S.P. Mishra1 and Sachidanada Dehuri2 School of Computer Engineering KIIT University, Bhubaneswar , Emails: Department of ICT FM University, Balasore, Email:" e825811cfd92a8be5be2caee67fc7a48ed2f5df0,Meta-Analysis of Face Recognition Algorithms,"Meta-Analysis of Face Recognition Algorithms P. Jonathon Phillips 00 Bureau Dr., STOP 8940 Gaithersburg, Md. 20899-8940 Elaine M. Newton 01 N. Craig St., Suite 102 Pittsburgh, Pa. 15213" e8acbe49ecf7e0a77f4f5874674ac40b1e35bf8a,EXPERIMENTAL EVALUATION OF TEXT-INDEPENDENT SPEAKER VERIFICATION ON LABORATORY AND FIELD TEST DATABASES IN THE M2VTS PROJECT,"EXPERIMENTAL EVALUATION OF TEXT-INDEPENDENT SPEAKER VERIFICATION ON LABORATORY AND FIELD TEST DATABASES IN THE M2VTS PROJECT L. Besacie , J. Luett , G. Maîtr , E. Meurv (1) IMT, Neuchâtel (CH) - (2) IDIAP, Martigny (CH) - (3) now at EIV, Sion (CH) - (4) now at EPFL, Lausanne (CH) -" e8304700fd89461ec9ecf471179ad87f08f3c2f7,Learning to Learn New Models of Human Activities in Indoor Settings 1 1.1 Introduction,"Chapter 1 Learning to learn new models of human activities in indoor settings1 Introduction Biological cognitive systems have the great capability to recognize and in- easily within their existing knowledge base. Autonomous artificial agents to large extent still lack such capacities. In this paper, we work towards this direction, as we do not only detect abnormal situations, but are also able to learn new concepts during runtime. We aim at the interpretation of human behavior in indoor environments. Possible applications go from the main IM2 scenario, i.e. analysis and un- derstanding of meetings, to monitoring of elderly or handicapped people in their homes in order to ensure their well-being. The indoor setting triggers interesting issues, such as the adaptation of pre-trained knowledge to a par- with an individual behavior style, whereas real abnormalities must still be detected. One main limitation of automated surveillance approaches is their need for an of‌f‌line prior training with many labeled data. Furthermore, no train- ing sequence contains a comprehensive set of all the situations to expect" e8e43abbc8bee64a53af64ceca90bfb687f7bb9d,Fast Object Class Labelling via Speech,"Fast Object Class Labelling via Speech Michael Gygli Google Research Z¨urich, Switzerland Vittorio Ferrari Google Research Z¨urich, Switzerland" e8686663aec64f4414eba6a0f821ab9eb9f93e38,Improving shape-based face recognition by means of a supervised discriminant Hausdorff distance,"IMPROVING SHAPE-BASED FACE RECOGNITION BY MEANS OF A SUPERVISED DISCRIMINANT HAUSDORFF DISTANCE J.L. Alba , A. Pujol , A. L´opez nd J.J. Villanueva Signal Theory and Communications Department, University of Vigo, Spain Centre de Visio per Computador, Universitat Autonoma de Barcelona, Spain Digital Pointer MVT" e8867f819f39c1838bba7d446934258035d4101c,Face recognition performance with superresolution.,"Face recognition performance with superresolution Shuowen Hu,1,* Robert Maschal,1 S. Susan Young,1 Tsai Hong Hong,2 nd P. Jonathon Phillips2 United States Army Research Laboratory, 2800 Powder Mill Road, Adelphi, Maryland 20783, USA NIST, 100 Bureau Drive, Gaithersburg, Maryland 20899, USA *Corresponding author: Received 29 September 2011; revised 19 April 2012; accepted 24 April 2012; posted 30 April 2012 (Doc. ID 155384); published 20 June 2012 With the prevalence of surveillance systems, face recognition is crucial to aiding the law enforcement com- munity and homeland security in identifying suspects and suspicious individuals on watch lists. However, face recognition performance is severely affected by the low face resolution of individuals in typical sur- veillance footage, oftentimes due to the distance of individuals from the cameras as well as the small pixel ount of low-cost surveillance systems. Superresolution image reconstruction has the potential to improve face recognition performance by using a sequence of low-resolution images of an individual’s face in the same pose to reconstruct a more detailed high-resolution facial image. This work conducts an extensive performance evaluation of superresolution for a face recognition algorithm using a methodology and ex- perimental setup consistent with real world settings at multiple subject-to-camera distances. Results show that superresolution image reconstruction improves face recognition performance considerably at the examined midrange and close range. OCIS codes:" e8ffef3d4d74720e766e506e175e533bdc8ee705,Object Detection Networks on Convolutional Feature Maps,"Object Detection Networks on Convolutional Feature Maps Shaoqing Ren, Kaiming He, Ross Girshick, Xiangyu Zhang, and Jian Sun" e8a5800db4b7609e3a55ec4b904b263cd359df2e,Face Recognition using Neural Network and Eigenvalues with Distinct Block Processing,"International Journal of Scientific & Engineering Research Volume 2, Issue 5, May-2011 1 ISSN 2229-5518 Face Recognition using Neural Network nd Eigenvalues with Distinct Block Processing Prashant Sharma, Amil Aneja, Amit Kumar, Dr.Shishir Kumar" e80635b9b48df5ad263c51ecec62d7d4bd7327fd,"Playful Robot for Research , Therapy , and Entertainment","Int J Soc Robot (2009) 1: 3–18 DOI 10.1007/s12369-008-0009-8 O R I G I N A L PA P E R Keepon A Playful Robot for Research, Therapy, and Entertainment Hideki Kozima · Marek P. Michalowski · Cocoro Nakagawa Accepted: 28 October 2008 / Published online: 19 November 2008 © Springer 2008" e81705e6100759b75eb71839ea61abc257b0b6a9,Enhanced Spatial Pyramid Matching Using Log-Polar-Based Image Subdivision and Representation,"Enhanced Spatial Pyramid Matching Using Log-Polar-Based Image Subdivision nd Representation Edmond Zhang, Michael Mayo Department of Computer Science The University of Waikato Hamilton, New Zealand" e862577cb654c33c4817c31b445264614485413c,Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning,"Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning Jiayao Zhang, Guangxu Zhu, Robert W. Heath Jr., and Kaibin Huang Modern machine learning algorithms have been adopted in range of signal-processing applications spanning computer vision, natural language processing, and artificial intelligence. Many relevant problems involve subspace-structured features, orthogonality constrained or low-rank constrained objective functions, or subspace distances. These mathematical charac- teristics are expressed naturally using the Grassmann manifold. Unfortunately, this fact is not yet explored in many traditional learning algorithms. In the last few years, there have been growing interests in studying Grassmann manifold to tackle new learning problems. Such attempts have been reassured by substantial performance improvements in both classic learning nd learning using deep neural networks. We term the former s shallow and the latter deep Grassmannian learning. The aim of this paper is to introduce the emerging area of Grassman- nian learning by surveying common mathematical problems nd primary solution approaches, and overviewing various" e8fdacbd708feb60fd6e7843b048bf3c4387c6db,Deep Learning,"Deep Learning Andreas Eilschou Hinnerup Net A/S www.hinnerup.net July 4, 2014 Introduction Deep learning is a topic in the field of artificial intelligence (AI) and is a relatively new research area although based on the popular artificial neural networks (supposedly mirroring brain function). With the development of the perceptron in the 1950s and 960s by Frank RosenBlatt, research began on artificial neural networks. To further mimic the architectural depth of the brain, researchers wanted to train a deep multi- layer neural network – this, however, did not happen until Geoffrey Hinton in 2006 introduced Deep Belief Networks [1]. Recently, the topic of deep learning has gained public interest. Large web companies such s Google and Facebook have a focused research on AI and an ever increasing amount of compute power, which has led to researchers finally being able to produce results that are of interest to the general public. In July 2012 Google trained a deep learning network on YouTube videos with the remarkable result that the network learned to recognize humans as well as cats [6], and in January this year Google successfully used deep learning on Street View images to automatically recognize house numbers with" e8d898a6adcd526874e0a41840b69760506a98a1,Computer Vision Methods as an Aid to Visually Impaired Users Title: Computer Vision Methods as an Aid to Visually Impaired Users,"Dipartimento di Informatica, Bioingegneria, Robotica ed Ingegneria dei Sistemi Computer Vision methods as an aid to visually impaired users Giovanni Fusco Theses Series DIBRIS-TH-2013-03 DIBRIS, Universit`a di Genova Via Opera Pia, 13 16145 Genova, Italy http://www.dibris.unige.it/" e8632e5bf43f7c59f4e1978833db8aa405c76c58,Saliency and Gist Features for Target Detection in Satellite Images,"Saliency and Gist Features for Target Detection in Satellite Images Zhicheng Li and Laurent Itti" e82693e9e7b1176ecb48a775cf2548e3d68ffd3a,Linear versus nonlinear neural modeling for 2-D pattern recognition,"IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART A: SYSTEMS AND HUMANS, VOL. 35, NO. 6, NOVEMBER 2005 [7] X. J. Li et al., “CAD-vision-range-based self-localization for mobile robot using one landmark,” J. Intell. Robot. Syst., vol. 35, no. 1, pp. 61–82, 002. [8] J. M. Perez, C. Urdiales, A. Bandera, and F. Sandoval, “A Hough-based solution to the simultaneous localization and map building problem,” in Proc. 1st Eur. Conf. Mobile Robots (ECMR), Radziejowice, Poland, 003, pp. 53–58. [9] A. Bonci, G. Ippoliti, L. Jetto, T. Leo, and S. Longhi, “Methods and lgorithms for sensor data fusion aimed at improving the autonomy of mobile robot,” in Advances in Control of Articulated Mobile Robots, B. Siciliano et al., Eds. Heidelberg, Germany: Springer-Verlag, Springer Tracts in Advanced Robotics (STAR), 2004, pp. 191–222. [10] P. V. C. Hough, “Methods and means for recognising complex patterns,” U.S. Patent 3 069 654, Dec. 18, 1962. [11] R. O. Duda and P. E. Hart, “Use of the Hough Transform to detect lines and curves in pictures,” Commun. ACM, vol. 15, no. 1, pp. 11–15, Jan. 1972. [12] F. O’Gorman and M. B. Clowes, “Finding picture edges through collinear- ity of feature points,” IEEE Trans. Comput., vol. C-25, no. 4, pp. 449–454," e8e8f40ceff8b71d5dafa6b680d40690dfae940c,title : Guidelines for studying developmental prosopagnosia in adults and children,"Article type: Focus Article Article title: Guidelines for studying developmental prosopagnosia in adults nd children First author: Full name and affiliation; plus email address if orresponding author Kirsten A. Dalrymple* Institute of Child Development, University of Minnesota, Minneapolis, USA Second author: Full name and affiliation; plus email address if orresponding author Romina Palermo* School of Psychology, and ARC Centre of Excellence in Cognition and its Disorders University of Western Australia, Crawley, Australia Please note that both authors would like to be listed as “corresponding authors”." e84e49c9530897fad7927a06ac4a48ddaf0adf0f,Searching for Efficient Multi-Scale Architectures for Dense Image Prediction,"Searching for Efficient Multi-Scale Architectures for Dense Image Prediction Liang-Chieh Chen Maxwell D. Collins Barret Zoph Florian Schroff Yukun Zhu Hartwig Adam George Papandreou Jonathon Shlens Google Inc." 2a7b7de7488211471a001044a3a249a117af488a,Physical Attribute Prediction Using Deep Residual Neural Networks,"Physical Attribute Prediction Using Deep Residual Neural Networks st Rashidedin Jahandideh dept. Computer Science Shahid Beheshti University Tehran, Iran nd Alireza Tavakoli Targhi dept. Computer Science Shahid Beheshti University Tehran, Iran rd Maryam Tahmasbi dept. Computer Science Shahid Beheshti University Tehran, Iran" 2a259fd1b4442a71cd127afac417a650ffc379d9,Human upper body posture recognition and upper limbs motion parameters estimation,"Human Upper Body Posture Recognition and Upper Limbs Motion Parameters Estimation Jun-Yang Huang1 Shih-Chung Hsu1and Chung-Lin Huang1,2 . Department Of Electrical Engineering, National Tsing-Hua University, Hsin-Chu, Taiwan . Department of Applied Informatics and Multimedia, Asia Univeristy, Tai-Chung, Taiwan. Email:" 2ad2af8e3bdeb0302de07defc3fec9b387414a27,Don ' t Look Back : Post-hoc Category Detection via Sparse Reconstruction,"Don't Look Back: Post-hoc Category Detection via Sparse Reconstruction Hyun Oh Song Mario Fritz Tim Althoff Trevor Darrell Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2012-16 http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-16.html January 24, 2012" 2a86bc520586f611771c2052b50ac52239414dd2,CrowdHuman: A Benchmark for Detecting Human in a Crowd,"CrowdHuman: A Benchmark for Detecting Human in a Crowd Shuai Shao∗ Zijian Zhao∗ Boxun Li Tete Xiao Gang Yu Xiangyu Zhang Jian Sun {shaoshuai, zhaozijian, liboxun, xtt, yugang, zhangxiangyu, Megvii Inc. (Face++)" 2ab9c36e19090ed9ac5295b3704708bdce80462d,Zero-Shot Learning via Category-Specific Visual-Semantic Mapping and Label Refinement,"Zero-Shot Learning via Category-Specific Visual-Semantic Mapping Li Niu, Jianfei Cai, and Ashok Veeraraghavan" 2aa08ab3d6c227e3b071dc470a2f36dc5d4a2403,Ensembling Visual Explanations for VQA,"To Appear In Proceedings of the NIPS 2017 workshop on Visually-Grounded Interaction and Language (ViGIL), December 2017." 2a7bca56e2539c8cf1ae4e9da521879b7951872d,Exploiting Unrelated Tasks in MultiTask Learning,"Exploiting Unrelated Tasks in Multi-Task Learning Anonymous Author 1 Anonymous Author 2 Anonymous Author 3" 2a6c7d5aa087233ff8a09bdaa34d5f76f3330a4f,A Survey of Efficient Regression of General-Activity Human Poses from Depth Images,"A Survey of Efficient Regression of General-Activity Hu- man Poses from Depth Images Wenye He This paper presents a comprehensive review on regression-based method for human pose es- timation. The problem of human pose estimation has been intensively studied and enabled many application from entertainment to training. Traditional methods often rely on color im- ge only which cannot completely ambiguity of joint’s 3D position, especially in the complex ontext. With the popularity of depth sensors, the precision of 3D estimation has significant improvement. In this paper, we give a detailed analysis of state-of-the-art on human pose estimation, including depth image based and RGB-D based approaches. The experimental results demonstrate their advantages and limitation for different scenarios. Introduction Human pose estimation from images has been studied for decades in computer vision. As recent development in cameras and sensors, depth images receive a wide spread of notice from researchers from body pose estimation 1 to 3D reconstruction 2. Girshick et al.1 present an approach to find the joints position in human body from depth images. They address the problem of general-activity pose estimation. Their regression-based approach sucessfully computes the joint positions even with occlusion. Their method can be view as a new combination of two existing works, implicit shape models3 and Hough forest4. The following sections cover related works, explanation on the method from testing to training, and result and comparison." 2ae139b247057c02cda352f6661f46f7feb38e45,Combining modality specific deep neural networks for emotion recognition in video,"Combining Modality Specific Deep Neural Networks for Emotion Recognition in Video Samira Ebrahimi Kahou1, Christopher Pal1, Xavier Bouthillier2, Pierre Froumenty1, Ça˘glar Gülçehre2,∗ , Roland Memisevic2, Pascal Vincent2, Aaron Courville2, & Yoshua Bengio2 École Polytechique de Montréal, Université de Montréal, Montréal, Canada Laboratoire d’Informatique des Systèmes Adaptatifs, Université de Montréal, Montréal, Canada {samira.ebrahimi-kahou, christopher.pal, {bouthilx, gulcehrc, memisevr, vincentp, courvila," 2a218c17944d72bfdc7f078f0337cab67536e501,Detection bank: an object detection based video representation for multimedia event recognition,"Detection Bank: An Object Detection Based Video Representation for Multimedia Event Recognition Tim Althoff, Hyun Oh Song, Trevor Darrell UC Berkeley EECS/ICSI Multimedia Event Detection Birthday Party vs Wedding Ceremony ● ObjectBank omits the following steps that are standard in a detection pipeline: ● Thresholding of score maps ● Non-maximum suppression ● Pooling across all scales ● We compute different detection count statistics to apture e.g. max number of detections, sum of detection scores, probablity of detection based on the detection images from a large number of windowed object detectors. Detection Count Statistics Look for: Balloon, Candle, Birthday Cake vs. Bride, Groom, Wedding Gown, Wedding Cake Illustration" 2a152dae1ba70d0cc605b0f7418392ed1a294a4a,Head pose detection using Fast Robust PCA for Side Active Appearance Models under Occlusion,"Head Pose Detection Using Fast Robust PCA for Side Active Appearance Models Under Occlusion Anıl Yüce1, Matteo Sorci2, and Jean-Philippe Thiran1 Signal Processing Laboratory (LTS5) École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland nViso Sàrl, Lausanne, Switzerland" 2a83a51c9596ed796da52bdac49ca30e4eb04345,Eclectic Genetic Algorithm for Holistic Face Recognition in L ∞ Space,"Eclectic Genetic Algorithm for Holistic Face Recognition in L∞ Space C. Villegas, J. Climent, C.R. Murillo, A. Otero, C.R. Villegas" 2a93ce4284c7f8605e1d9bc0a8b86036073ebf61,Learning and Detection of Multiple Objects in Video Sequences,"Master Thesis Czech Technical University in Prague Faculty of Electrical Engineering Department of Cybernetics Tracking, Learning and Detection of Multiple Objects in Video Sequences Filip Naiser Supervisor: prof. Ing. Jiří Matas, Ph.D. January 2017" 2acf7e58f0a526b957be2099c10aab693f795973,Bosphorus Database for 3D Face Analysis,"Bosphorus Database for 3D Face Analysis Arman Savran1, Neşe Alyüz2, Hamdi Dibeklioğlu2, Oya Çeliktutan1, Berk Gökberk3, Bülent Sankur1, and Lale Akarun2 Boğaziçi University, Electrical and Electronics Engineering Department Boğaziçi University, Computer Engineering Department Philips Research, Eindhoven, The Netherlands" 2a2232f2972191a0606d588aa4f13c9f27d1972d,InstanceCut: From Edges to Instances with MultiCut,"InstanceCut: from Edges to Instances with MultiCut Alexander Kirillov1 Evgeny Levinkov2 Bjoern Andres2 Bogdan Savchynskyy1 Carsten Rother1 TU Dresden, Dresden, Germany MPI for Informatics, Saarbr¨ucken, Germany" 2a2b99fc9583419931681acfd83ac953a3df3270,Estimating the quality of face localization for face verification,"ESTIMATING THE QUALITY OF FACE LOCALIZATION FOR FACE VERIFICATION Yann Rodriguez Fabien Cardinaux Samy Bengio Johnny Mari´ethoz IDIAP CP 592, rue du Simplon 4 920 Martigny, Switzerland" 2aec012bb6dcaacd9d7a1e45bc5204fac7b63b3c,Robust Registration and Geometry Estimation from Unstructured Facial Scans,"Robust Registration and Geometry Estimation from Unstructured Facial Scans Maxim Bazik1 and Daniel Crispell2" 2a067874fc1ec318b6d23f34bdb13ea4e95d5ca6,An Evaluation of Image-Based Verb Prediction Models against Human Eye-Tracking Data,"New Orleans, Louisiana, June 1 - 6, 2018. c(cid:13)2018 Association for Computational Linguistics Proceedings of NAACL-HLT 2018, pages 758–763" 2a1d3e1baf323e61da517a054b9571559815a651,Temporal normalization of videos using visual speech,"Temporal Normalization of Videos Using Visual Speech Usman Saeed EURECOM Sophia Antipolis 229 Route Des Cretes Sophia Antipolis, France +33(0)493008248 Jean-Luc Dugelay EURECOM Sophia Antipolis 229 Route Des Cretes Sophia Antipolis, France +33(0)493008141" 2ac986ec18c3572ee4f922ba9a90ae374563491c,A New Approach of Human Segmentation from Photo Images,"International Journal of Scientific and Research Publications, Volume 5, Issue 1, January 2015 ISSN 2250-3153 A New Approach of Human Segmentation from Photo Images Ashwini Magar*, Prof.J.V.Shinde** * Computer Department, Late G .N. Sapkal College Of Engineering, Savitribai Phule Pune University ** Computer Department, Late G .N .Sapkal College Of Engineering, Savitribai Phule Pune University" 2ae1c0d4898cf7d5446039e639d95a7e27f4d957,Visual place recognition with probabilistic voting, 2aca60ee8a43d88be24ab9dad373dd555fd080a7,Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Prediction,"Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Prediction Nelly Elsayed, Anthony S. Maida, and Magdy Bayoumi" 2acf319c5eac89cc9e0ed24633e4408dbd4a8a5b,The Effect of Distance Measures on the Recognition Rates of PCA and LDA Based Facial Recognition,"The Effect of Distance Measures on the Recognition Rates of PCA nd LDA Based Facial Recognition Philip Miller, Jamie Lyle Digitial Image Processing Clemson Universtiy {pemille," 2a6b5b8afee8289e454db9447fdaebc1282c1fea,Automatic Face Recognition and Identification Tools in the Forensic Science Domain,"Automatic Face Recognition and Identification Tools in the Forensic Science Domain Angelo Salici(✉) and Claudio Ciampini Raggruppamento Carabinieri Investigazioni Scientifiche, RIS di Messina, S.S.114 Km 6,400, 98128 Messina, Italy" 2a08147bf88041c6e0354e26762b4e4d65d5163f,Trimmed Event Recognition ( Moments in Time ) : Submission to ActivityNet Challenge 2018,"Trimmed Event Recognition (Moments in Time): Submission to ActivityNet Challenge 2018 Dongyang Cai" 2a06341b40b3fd27483b2a8d8cbf86fddf45e423,Automatic generation of ground truth for the evaluation of obstacle detection and tracking techniques,"Automatic generation of ground truth for the evaluation of obstacle detection nd tracking techniques Hatem Hajri∗, Emmanuel Doucet∗†, Marc Revilloud∗, Lynda Halit∗, Benoit Lusetti∗, Mohamed-Cherif Rahal∗ Automated Driving Research Team, Institut VEDECOM, Versailles, France InnoCoRe Team, Valeo, Bobigny, France" 2a1deffc67ccb5f8ca5897ac3f31dac09af70f05,Robust Subspace Clustering via Tighter Rank Approximation,"Robust Subspace Clustering via Tighter Rank Approximation Zhao Kang Computer Science Dept. Southern Illinois University Carbondale, IL, USA Chong Peng Computer Science Dept. Southern Illinois University Carbondale, IL, USA Qiang Cheng Computer Science Dept. Southern Illinois University Carbondale, IL, USA" 2a87f95e36938ca823b33c72a633d8d902d5cb86,Oxytocin Improves “Mind-Reading” in Humans,"PRIORITY COMMUNICATION Oxytocin Improves “Mind-Reading” in Humans Gregor Domes, Markus Heinrichs, Andre Michel, Christoph Berger, and Sabine C. Herpertz Background: The ability to “read the mind” of other individuals, that is, to infer their mental state by interpreting subtle social cues, is indispensable in human social interaction. The neuropeptide oxytocin plays a central role in social approach behavior in nonhuman mammals. Methods: In a double-blind, placebo-controlled, within-subject design, 30 healthy male volunteers were tested for their ability to infer the affective mental state of others using the Reading the Mind in the Eyes Test (RMET) after intranasal administration of 24 IU oxytocin. Results: Oxytocin improved performance on the RMET compared with placebo. This effect was pronounced for difficult compared with easy items. Conclusions: Our data suggest that oxytocin improves the ability to infer the mental state of others from social cues of the eye region. Oxytocin might play a role in the pathogenesis of autism spectrum disorder, which is characterized by severe social impairment. Key Words: Emotion, oxytocin, peptide, social cognition, theory of T he ability to infer the internal state of another person to dapt one’s own behavior is a cornerstone of all human social interactions. Humans have to infer internal states from external cues such as facial expressions in order to make sense of or predict another person’s behavior, an ability that is referred to as “mind-reading” (Siegal and Varley 2002; Stone et al 998). In particular, individuals with autism have distinct diffi-" 2a8aedea2031128868f1c6dd44329c5bb7afc419,A Convex Duality Framework for GANs,"A Convex Duality Framework for GANs Farzan Farnia∗ David Tse∗" 2aa362740ac9a2b304a74122da820e3829689842,"Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age","Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age Cesar Cadena, Luca Carlone, Henry Carrillo, Yasir Latif, Davide Scaramuzza, Jos´e Neira, Ian Reid, John J. Leonard" 2a5efa83ea5c4733757b838b84ba6519f873b826,A Continuous Learning for Solving a Face Recognition Problem,"International Journal of Computer Information Systems and Industrial Management Applications. ISSN 2150-7988 Volume 4 (2012) pp. 570-577 © MIR Labs, www.mirlabs.net/ijcisim/index.html A Continuous Learning for Solving a Face Recognition Problem Aldo Franco Dragoni, Germano Vallesi and Paola Baldassarri Università Politecnica delle Marche, Italy {a.f.dragoni, g.vallesi," 2a7e2cda27807d24b845f5b5080fb1296c302bfe,Personal Authentication Using Signature Recognition,"Personal Authentication Using Signature Recognition Diana Kalenova Department of Information Technology, Laboratory of Information Processing, Lappeenranta University of Technology" 2a4f3536cd21fb7193662faef2612384f429c6a7,1 Performance Evaluation of Photometric Normalization Techniques for Illumination Invariant Face Recognition,"Performance Evaluation of Photometric Normalization Techniques for Illumination Invariant Face Recognition Avtor: Vitomir Štruc Internal Report: LUKS" 2af2aa21538783e46911fb857a23dbb88ed90c2b,A Study on Deep Learning Based Sauvegrain Method for Measurement of Puberty Bone Age,"A Study on Deep Learning Based Sauvegrain Method for Measurement of Puberty Bone Age Keum Gang Cha∗ Seung Bin Baik∗ Plani Inc. Plani Inc. September 20, 2018" 2a56a51490f6ccfaf6fcbdf546a5515bef5203a1,"Attention, please!: Comparing Features for Measuring Audience Attention Towards Pervasive Displays","Attention, please! Comparing Features for Measuring Audience Attention Towards Pervasive Displays Florian Alta, Andreas Bullingb, Lukas Meckea, Daniel Buscheka LMU Munich Munich, Germany" cef6cffd7ad15e7fa5632269ef154d32eaf057af,Emotion Detection Through Facial Feature Recognition,"Emotion Detection Through Facial Feature Recognition James Pao through consistent" cee700093d6672df48d169ef194861026fe31e8e,Hashing on Nonlinear Manifolds,"Hashing on Nonlinear Manifolds Fumin Shen, Chunhua Shen, Qinfeng Shi, Anton van den Hengel, Zhenmin Tang, Heng Tao Shen in the Hamming space. This means that many algorithms which are based on such pairwise comparisons can be made more efficient, and applied to much larger datasets. Due to the flexibility of hash codes, hashing techniques can be applied in many ways. one can, for example, efficiently perform similarity search by exploring only those data points falling into the close-by buckets to the query by the Hamming distance, or use the binary representations for other tasks like image classification." cea85314294f9731661a419f627cb99331ad9c50,Race recognition using local descriptors,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" ce9799830a24412f4bd9ad30a9d6e2a50215f8f8,Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network,"Aram Ter-Sarkisov1 John Kelleher1 Bernadette Earley2 Michael Keane2 Robert Ross1 TER-SARKISOV ET AL.: BEEF CATTLE INSTANCE SEGMENTATION USING FCN Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network School of Computing Dublin Institute of Technology Dublin, Ireland TEAGASC Grange, Dunsany, Co. Meath, Ireland" cef092bf9beed65e379ab48ef2b43498d4aaea92,Process Monitoring in the Intensive Care Unit: Assessing Patient Mobility Through Activity Analysis with a Non-Invasive Mobility Sensor,"Process Monitoring in the Intensive Care Unit: Assessing Patient Mobility Through Activity Analysis with a Non-Invasive Mobility Sensor Austin Reiter1(B), Andy Ma1, Nishi Rawat2, Christine Shrock2, nd Suchi Saria1 The Johns Hopkins University, Baltimore, MD, USA Johns Hopkins Medical Institutions, Baltimore, MD, USA" ceee9ba72a021ae5604db04a93fdcff421d60216,Encoder Based Lifelong Learning,"Encoder Based Lifelong Learning Amal Rannen Triki ∗† Rahaf Aljundi∗ Mathew B. Blaschko Tinne Tuytelaars KU Leuven KU Leuven, ESAT-PSI, iMinds, Belgium" ce391bcdb64f7659ddc5a0c2e5c73854c1e8031c,Zur Erlangung Des Grades Des,"FILTERING AND OPTIMIZATION STRATEGIES FOR MARKERLESS HUMAN MOTION CAPTURE WITH SKELETON-BASED SHAPE MODELS. DISSERTATION ZUR ERLANGUNG DES GRADES DES DOKTORS DER INGENIEURWISSENSCHAFTEN (DR.-ING.) DER NATURWISSENSCHAFTLICH-TECHNISCHEN FAKULT ¨ATEN DER UNIVERSIT ¨AT DES SAARLANDES VORGELEGT VON JUERGEN GALL SAARBR ¨UCKEN" cebf73d590e0c0021f09bdbd59778bd574e96da7,First Impressions and the Reference Encounter : The In fl uence of Affect and Clothing on Librarian Approachability,"The University of Maine Library Staff Publications Fogler Library First Impressions and the Reference Encounter: The Influence of Affect and Clothing on Librarian Approachability Jennifer Bonnet University of Maine - Main, Ben McAlexander Trihydro Corporation, Follow this and additional works at: https://digitalcommons.library.umaine.edu/lib_staffpub Part of the Library and Information Science Commons Repository Citation Bonnet, Jennifer and McAlexander, Ben, ""First Impressions and the Reference Encounter: The Influence of Affect and Clothing on Librarian Approachability"" (2013). Library Staff Publications. 16. https://digitalcommons.library.umaine.edu/lib_staffpub/16 This Article is brought to you for free and open access by It has been accepted for inclusion in Library Staff Publications by n authorized administrator of For more information, please contact" ce0dbe6b1abecb54dcc98dbe652aa63d190dbc94,Part-Based Models for Finding People and Estimating Their Pose,"Part-based models for finding people and estimating their pose Deva Ramanan" ce54e891e956d5b502a834ad131616786897dc91,Face Recognition Using LTP Algorithm,"International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013): 6.14 | Impact Factor (2014): 5.611 Face Recognition Using LTP Algorithm Richa Sharma1, Rohit Arora2 ECE & KUK Assistant Professor (ECE) Volume 4 Issue 12, December 2015 Licensed Under Creative Commons Attribution CC BY www.ijsr.net  Variation in luminance: Third main challenge that ppears in face recognition process is the luminance. Due to variation in the luminance the representation get varied from the original image. The person with same poses expression and seen from same viewpoint can be appear very different due to variation in lightening." ceba512cd64951fa49ca2ee19295561cd2493f18,Visual and Semantic Knowledge Transfer for Large Scale Semi-Supervised Object Detection,"Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection Yuxing Tang, Josiah Wang, Xiaofang Wang, Boyang Gao, Emmanuel Dellandr´ea, Robert Gaizauskas nd Liming Chen Senior Member," cee5e1a4e5a79ed93a3f5a6cc0b22e38f1c8d389,Occluded Facial Image Retrieval Based on a Similarity Measurement,"Publishing CorporationMathematical Problems in EngineeringVolume 2015, Article ID 217568, 11 pageshttp://dx.doi.org/10.1155/2015/217568" ce06015fc0eb2add064ef93c9b97ad063c03aef4,Person Re-identification in Surveillance Videos using Multi-part Color Descriptor,"International Journal of Computer Applications (0975 – 8887) Volume 121 – No.16, July 2015 Person Re-identification in Surveillance Videos using Multi-part Color Descriptor P.K. Sathish S. Balaji Computer Science and Engineering Dept. Centre for Emerging Technologies, Jain University Christ University Bengaluru- 560074" ce12bbb8ce974df4b64f18e478d7fa99b722de03,A Hybrid Data Association Framework for Robust Online Multi-Object Tracking,"A Hybrid Data Association Framework for Robust Online Multi-Object Tracking Min Yang, Yuwei Wu∗, and Yunde Jia Member, IEEE," ce20f81374e2058b01910a4d028b79c07ce7e994,Discriminating Characteristics of Gabor Phase-Face and Improved Methods for Face Recognition,"Noname manuscript No. (will be inserted by the editor) Discriminating Characteristics of Gabor Phase-Face and Improved Methods for Face Recognition Iqbal Nouyed · Bruce Poon · M. Ashraful Amin · Hong Yan the date of receipt and acceptance should be inserted later" cea50611ba73b5775cc2fe1e9c27990a0bb20cf8,Gabor Feature Based Sparse Representation for Face Recognition with Gabor Occlusion Dictionary,"Gabor Feature based Sparse Representation for Face Recognition with Gabor Occlusion Dictionary Meng Yang, Lei Zhang ⋆ Biometric Research Center, Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong," ce6f459462ea9419ca5adcc549d1d10e616c0213,A Survey on Face Identification Methodologies in Videos,"A Survey on Face Identification Methodologies in Videos Student, M.Tech CSE ,Department of Computer Science & Engineering ,G.H.Raisoni College of Engineering & Technology for Women, Nagpur, Maharashtra, India. Deepti Yadav" ce3ee08f4d937a6dcb2d6dd0a1ca100920f312e6,Literature Survey On Contactless Palm Vein Recognition,"International Journal of Computer Science Trends and Technology (IJCST) – Volume 3 Issue 5, Sep-Oct 2015 RESEARCH ARTICLE Literature Survey On Contactless Palm Vein Recognition Roshni C Rahul [1], Merin Cherian [2], Manu Mohan C M [3] Department of Computer Science [1], Department of Science [2], Department of Electronics [3] OPEN ACCESS Mahatma Gandhi University Kerala - India" ce13aaf9ab0d3ec3dd9637b2dd5122b4aa711fd7,Local Feature-based Person Re-Identification in Video,"UNIVERSITÄT KARLSRUHE (TH) FAKULTÄT FÜR INFORMATIK INSTITUT FÜR ANTHROPOMATIK Prof. Dr. Rainer Stiefelhagen DIPLOMA THESIS Local Feature-based Person Re-Identification in Video SUBMITTED BY Martin Bäuml MAY 2009 ADVISORS Prof. Dr. Rainer Stiefelhagen Dipl. Inf. Keni Bernardin Dr. Jie Yang" ced4853617ba6af27f5447f9c4de07c3e05e8c3b,Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations,"Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations Vladimir Nekrasov1, Thanuja Dharmasiri2, Andrew Spek2, Tom Drummond2, Chunhua Shen1 and Ian Reid1" ce316d2366ec1b95ee91a98b4f426e6c00cdcdc4,Hierarchical Energy-transfer Features,"Hierarchical Energy-Transfer Features Radovan Fusek, Eduard Sojka, Karel Mozdˇreˇn and Milan ˇSurkala Technical University of Ostrava, FEECS, Department of Computer Science 7. listopadu 15, 708 33 Ostrava-Poruba, Czech Republic {radovan.fusek, eduard.sojka, karel.mozdren, Keywords: Object Detection, Recognition, SVM, Image Descriptors, Feature Selection." ce57cc478421adf85a9058a0cc8fad8ebfd81c52,Multimodal Attribute Extraction,"Multimodal Attribute Extraction Robert L. Logan IV University of California Irvine, CA Samuel Humeau Diffbot Mountain View, CA Sameer Singh University of California Irvine, CA Introduction Given the large collections of unstructured and semi-structured data available on the web, there is a rucial need to enable quick and efficient access to the knowledge content within them. Traditionally, the field of information extraction has focused on extracting such knowledge from unstructured text documents, such as job postings, scientific papers, news articles, and emails. However, the content on the web increasingly contains more varied types of data, including semi-structured web pages, tables that do not adhere to any schema, photographs, videos, and audio. Given a query by a user, the appropriate information may appear in any of these different modes, and thus there’s a crucial need for methods to construct knowledge bases from different types of data, and more importantly, Motivated by this goal, we introduce the task of multimodal attribute extraction. Provided contextual" ce6d23894f88349443e7c9fe512ca81291bb2e00,VIENA2: A Driving Anticipation Dataset,"VIENA2: A Driving Anticipation Dataset Mohammad Sadegh Aliakbarian1,2,4, Fatemeh Sadat Saleh1,4, Mathieu Salzmann3, Basura Fernando2, Lars Petersson1,4, and Lars Andersson4 ANU, 2ACRV, 3CVLab, EPFL, 4Data61-CSIRO" ceaa5eb51f761b5f84bd88b58c8f484fcd2a22d6,UC San Diego UC San Diego Electronic Theses and Dissertations Title Interactive learning and prediction algorithms for computer vision applications,"UC San Diego UC San Diego Electronic Theses and Dissertations Title Inhibitions of ascorbate fatty acid derivatives on three rabbit muscle glycolytic enzymes Permalink https://escholarship.org/uc/item/8x33n1gj Author Pham, Duyen-Anh Publication Date 011-01-01 Peer reviewed|Thesis/dissertation eScholarship.org Powered by the California Digital Library University of California" cef2b5ab841568755233994b12cf046c408f881e,TECHNIQUES FOR STATISTICAL SHAPE MODEL BUILDING AND FUSION,"TECHNIQUES STATISTICAL SHAPE MODEL BUILDING AND FUSION Constantine Butakoff (Kostantyn Butakov)" ce073cb70eec80d87c9e07a4ec2d4162d91e23a6,Positive Definite Matrices : Data Representation and Applications to Computer Vision,"Positive Definite Matrices: Data Representation nd Applications to Computer Vision Anoop Cherian and Suvrit Sra" ce4853f2214ee1f4c47a97ff45d4e53f6ffd5087,MODELS AND METHODS FOR BAYESIAN OBJECT MATCHING,"Helsinki University of Technology Laboratory of Computational Engineering Publications Teknillisen korkeakoulun Laskennallisen tekniikan laboratorion julkaisuja Espoo 2005 REPORT B52 MODELS AND METHODS FOR BAYESIAN OBJECT MATCHING Toni Tamminen AB TEKNILLINEN KORKEAKOULU TEKNISKA H(cid:214)GSKOLAN HELSINKI UNIVERSITY OF TECHNOLOGY TECHNISCHE UNIVERSIT˜T HELSINKI UNIVERSITE DE TECHNOLOGIE D’HELSINKI" ce6d34010f04afa4cf3018f51bad8f480ebc759c,"ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras","DOI: 10.1109/TRO.2017.2705103 IEEE Xplore: http://ieeexplore.ieee.org/document/7946260/ (cid:13)2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any urrent or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new ollective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works." ceac97de889ed2f65af62f61a007651d03b36b6c,Diagnostic Accuracy of Content Based Dermatoscopic Image Retrieval with Deep Classification Features,"Diagnostic Accuracy of Content Based Dermatoscopic Image Retrieval with Deep Classification Features Tschandl P, Argenziano G, Razmara M, Yap J Final version available at https://doi.org/10.1111/bjd.17189 Citation: tschandl cbir2018, Author=”Tschandl, P. and Argenziano, G. and Razmara, M. and Yap, J. ”, Title=”Diagnostic Accuracy of Content Based Dermatoscopic Image Retrieval with Deep Classification Features”, Journal=”Br J Dermatol”, Year=”2018”" ce933821661a0139a329e6c8243e335bfa1022b1,Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding,"Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding Fu Li, Chuang Gan, Xiao Liu, Yunlong Bian, Xiang Long, Yandong Li, Zhichao Li, Jie Zhou, Shilei Wen Baidu IDL & Tsinghua University" cefd107b19201cd9f403e2f9332c690e81f770b5,A Survey on Databases for Facial Expression Analysis, ced61099a0306d555486162670f1213f2c72b020,Multi-Vehicle Trajectories Generation for Vehicle-to-Vehicle Encounters,"Multi-Vehicle Trajectories Generation for Vehicle-to-Vehicle Encounters Wenhao Ding, Wenshuo Wang, and Ding Zhao" ceedb191328ac4d968853b948a32b5689c2ac2a2,Semisupervised Dimensionality Reduction and Classification Through Virtual Label Regression,"IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, VOL. 41, NO. 3, JUNE 2011 Semisupervised Dimensionality Reduction and Classification Through Virtual Label Regression Feiping Nie, Dong Xu, Xuelong Li, Senior Member, IEEE, and Shiming Xiang" cebfafea92ed51b74a8d27c730efdacd65572c40,Matching 2.5D face scans to 3D models,"JANUARY 2006 Matching 2.5D Face Scans to 3D Models Xiaoguang Lu, Student Member, IEEE, Anil K. Jain, Fellow, IEEE, and Dirk Colbry, Student Member, IEEE" ce8c8e9fdbdd84adc096018bb0edb49b6913b946,Learning Discriminative Features for Speaker Identification and Verification,"Interspeech 2018 -6 September 2018, Hyderabad 0.21437/Interspeech.2018-1015" ce0cc5f078c5224b9599caf518d74ae3023be0a6,Review on computer vision techniques in emergency situations,"(will be inserted by the editor) Review on Computer Vision Techniques in Emergency Situations Laura Lopez-Fuentes · Joost van de Weijer · Manuel Gonz´alez-Hidalgo · Harald Skinnemoen · Andrew D. Bagdanov Received: date / Accepted: date" fc1e37fb16006b62848def92a51434fc74a2431a,A Comprehensive Analysis of Deep Regression,"DRAFT A Comprehensive Analysis of Deep Regression St´ephane Lathuili`ere, Pablo Mesejo, Xavier Alameda-Pineda, Member IEEE, and Radu Horaud" fc2f12bacd3714c02a52ba183309d1f5dd8b292e,Generalization Abilities of Appearance-Based Subspace Face Recognition Algorithms,"2th Int. Workshop on Systems, Signals & Image Processing, 22-24 September 2005, Chalkida, Greece Generalization Abilities of Appearance-Based Subspace Face Recognition Algorithms Kresimir Delac *, Mislav Grgic and Sonja Grgic Department of Wireless Communications, Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia E-mail: * Corresponding author" fcf8bb1bf2b7e3f71fb337ca3fcf3d9cf18daa46,Feature Selection via Sparse Approximation for Face Recognition,"MANUSCRIPT SUBMITTED TO IEEE TRANS. PATTERN ANAL. MACH. INTELL., JULY 2010 Feature Selection via Sparse Approximation for Face Recognition Yixiong Liang, Lei Wang, Yao Xiang, and Beiji Zou" fc74e14a3195fdf91157d5ea86d35c576fcf01d6,Detection and Handling of Occlusion in an Object Detection System,"Detection and Handling of Occlusion in an Object Detection System R.M.G. Op het Velda, R.G.J. Wijnhovenb, Y. Bondarauc and Peter H.N. de Withd ,bViNotion B.V., Horsten 1, 5612 AX, Eindhoven, The Netherlands; ,c,dEindhoven University of Technology, Den Dolech 2, 5612 AZ, Eindhoven, The Netherlands" fcd3d69b418d56ae6800a421c8b89ef363418665,Effects of Aging over Facial Feature Analysis and Face Recognition,"Effects of Aging over Facial Feature Analysis and Face Recognition Bilgin Esme & Bulent Sankur Bogaziçi Un. Electronics Eng. Dept. March 2010" fcbedf2113c91fb71fe7bfcf9644a2f7f74ddff3,Street Viewer: An Autonomous Vision Based Traffic Tracking System,"Article Street Viewer: An Autonomous Vision Based Traffic Tracking System Andrea Bottino, Alessandro Garbo, Carmelo Loiacono and Stefano Quer * Dipartimento di Automatica ed Informatica, Politecnico di Torino, Torino 10129, Italy; (A.B.); (A.G.); (C.L.) * Correspondence: Tel.: +39-011-090-7076 Academic Editor: Andrea Zanella Received: 8 March 2016; Accepted: 27 May 2016; Published: 3 June 2016" fc30d7dbf4c3cdd377d8cd4e7eeabd5d73814b8f,Multiple Object Tracking by Efficient Graph Partitioning,"Multiple Object Tracking y Ef‌f‌icient Graph Partitioning Ratnesh Kumar, Guillaume Charpiat, Monique Thonnat STARS Team, INRIA, Sophia Antipolis, France" fcb64ef4421cebb80eb33f62c7726f339eb2bb62,Deep View-Aware Metric Learning for Person Re-Identification,Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) fc068f7f8a3b2921ec4f3246e9b6c6015165df9a,Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline),"Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline) Yifan Sun†, Liang Zheng‡, Yi Yang‡, Qi Tian§, Shengjin Wang†∗ Tsinghua University ‡University of Technology Sydney §University of Texas at San Antonio {liangzheng06," fc49b2b0bfc81df697aebf704f8bb68e5fa3cc44,Implementation of Gabor Filters Combined with Binary Features for Gender Recognition,"International Journal of Electrical and Computer Engineering (IJECE) Vol. 4, No. 1, Feburary 2014, pp. 108~115 ISSN: 2088-8708  108 Implementation of Gabor Filters Combined with Binary Features for Gender Recognition Milad Jafari Barani*, Karim Faez**, Fooad Jalili*** * Department of Electrical Computer and Biomedical Engineering Qazvin Branch, Islamic Azad University Qazvin, Iran ** Electrical Engineering Department, Amirkabir University of Technology (Tehran Polytechnic), Hafez Avenue, Tehran **Department of Electrical Computer and Biomedical Engineering Qazvin Branch, Islamic Azad University Qazvin, Iran Article Info Article history: Received Sep 8, 2013 Revised Nov 25, 2013 Accepted Dec 21, 2013 Keyword: Gender classification Self-organizing networks Geometric characteristics Gabor filters" fca14b3ad0efa7bdc6ab7c1f1d58016d2be634dc,Combining vocal and visual cues in an identity verification system using k-NN based classifiers,"COMBININGVOCALANDVISUALCUES INANIDENTITYVERIFICATIONSYSTEM USINGK-NNBASEDCLASSIFIERS G(cid:19)erardChollet PatrickVerlinde CNRSURA- SignalandImageCenter ENST/TSIDepartment RoyalMilitaryAcademy Paris,France Brussels,Belgium" fcabf1c0f4a26431d4df95ddeec2b1dff9b3e928,Semantic Segmentation using Adversarial Networks, fc73090889036a0e42ea40827ac835cd5e135b16,Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce,"Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce Devashish Shankar, Sujay Narumanchi, Ananya H A, Pramod Kompalli, Krishnendu Chaudhury Flipkart Internet Pvt. Ltd., Bengaluru, India." fc50c9392fd23b6c88915177c6ae904a498aacea,Scaling Egocentric Vision: The EPIC-KITCHENS Dataset,"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset Dima Damen1, Hazel Doughty1, Giovanni Maria Farinella2, Sanja Fidler3, Antonino Furnari2, Evangelos Kazakos1, Davide Moltisanti1, Jonathan Munro1, Toby Perrett1, Will Price1, and Michael Wray1 Uni. of Bristol, UK 2Uni. of Catania, Italy, Uni. of Toronto, Canada" fc4b50b96761f1746efe286ec1b27b0d44d5fc75,ILLUMINATION INVARIANT FACE RECOGNITION SYSTEM,"International Journal For Technological Research In Engineering Volume 1, Issue 10, June-2014 ISSN (Online): 2347 - 4718 ILLUMINATION INVARIANT FACE RECOGNITION SYSTEM Chande Anita1, Shah Khushbu2 Computer Engineering Department, L.J.I.E.T, G.T.U, Ahmedabad, Gujarat, India." fc04a50379e08ddde501816eb1f9560c36d01a39,Image Pre-processing Using OpenCV Library on MORPH-II Face Database,"Image Pre-processing Using OpenCV Library on MORPH-II Face Database B. Yip, R. Towner, T. Kling, C. Chen, and Y. Wang" fc27c2c8a2486f5918451fbef198f46b5bf45d2c,Robust Real-Time Multi-View Eye Tracking,"IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. XX, NO. XX, 2018 Robust Real-Time Multi-View Eye Tracking Nuri Murat Arar, Student Member, IEEE, and Jean-Philippe Thiran, Senior Member, IEEE" fcd77f3ca6b40aad6edbd1dab9681d201f85f365,Machine Learning Based Attacks and Defenses in Computer Security : Towards Privacy and Utility Balance in Sensor Environments,"(cid:13)Copyright 2014 Miro Enev" fcd9221f8ef306155f59817a3b0bdae05e9e0ae2,GEFeWS: A Hybrid Genetic-Based Feature Weighting and Selection Algorithm for Multi-Biometric Recognition,"GEFeWS: A Hybrid Genetic-Based Feature Weighting and Selection Algorithm for Multi-Biometric Recognition Aniesha Alford+, Khary Popplewell#, Gerry Dozier#, Kelvin Bryant#, John Kelly+, Josh Adams#, Tamirat Abegaz^, and Joseph Shelton# Center for Advanced Studies in Identity Sciences +Electrical and Computer Engineering Department, #Computer Science Department ^Computational Science and Engineering Department North Carolina A & T State University 601 E Market St., Greensboro, NC 27411" fcbf808bdf140442cddf0710defb2766c2d25c30,Unsupervised Semantic Action Discovery from Video Collections,"IJCV manuscript No. (will be inserted by the editor) Unsupervised Semantic Action Discovery from Video Collections Ozan Sener · Amir Roshan Zamir · Chenxia Wu · Silvio Savarese · Ashutosh Saxena Received: date / Accepted: date" fc9e60f370252bc9a6120a6b2c39703ac1fee810,Critical Points to Determine Persistence Homology,"Critical Points to Determine Persistence Homology Charmin Asirimath, Jayampathy Ratnayake, and Chathuranga Weeraddana" fcc6fd9b243474cd96d5a7f4a974f0ef85e7ddf7,InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity,"Improving Face Attribute Detection with Race and Gender Diversity InclusiveFaceNet: Hee Jung Ryu 1 Hartwig Adam * 1 Margaret Mitchell * 1" fc5fb5d0fb7c654e8fda140e5bc53f4f422a5d6e,Computationally Efficient Invariant Facial Expression Recognition,"Research Journal of Recent Sciences _________________________________________________ ISSN 2277-2502 Vol. 3(2), 61-68, February (2014) Res.J.Recent Sci. Computationally Efficient Invariant Facial Expression Recognition Muhammad Hussain, Sajid Ali Khan, Nadeem Ullah, Naveed Riaz and Muhammad Nazir Department of Computer Science, Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad, PAKISTAN Available online at: www.isca.in, www.isca.me Received 28th June 2013, revised 12th July 2013, accepted 13th August 2013" fc3e097ea7dd5daa7d314ecebe7faad9af5e62fb,Variational Inference and Model Selection with Generalized Evidence Bounds,"Variational Inference and Model Selection with Generalized Evidence Bounds Chenyang Tao * Liqun Chen * Ruiyi Zhang Ricardo Henao Lawrence Carin" fc7627e57269e7035e4d56105358211076fe4f04,The Association of Quantitative Facial Color Features with Cold Pattern in Traditional East Asian Medicine,"Hindawi Evidence-Based Complementary and Alternative Medicine Volume 2017, Article ID 9284856, 9 pages https://doi.org/10.1155/2017/9284856 Research Article The Association of Quantitative Facial Color Features with Cold Pattern in Traditional East Asian Medicine Sujeong Mun, Ilkoo Ahn, and Siwoo Lee Mibyeong Research Center, Korea Institute of Oriental Medicine, 1672 Yuseong-daero, Yuseong-gu, Daejeon 305-811, Republic of Korea Correspondence should be addressed to Siwoo Lee; Received 30 June 2017; Accepted 13 September 2017; Published 17 October 2017 Academic Editor: Kenji Watanabe Copyright © 2017 Sujeong Mun et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Introduction. Facial diagnosis is a major component of the diagnostic method in traditional East Asian medicine. We investigated the association of quantitative facial color features with cold pattern using a fully automated facial color parameterization system. Methods. The facial color parameters of 64 participants were obtained from digital photographs using an automatic color correction nd color parameter calculation system. Cold pattern severity was evaluated using a questionnaire. Results. The 𝑎∗ values of the whole face, lower cheek, and chin were negatively associated with cold pattern score (CPS) (whole face: 𝐵 = −1.048, 𝑃 = 0.021; lower cheek: 𝐵 = −0.494, 𝑃 = 0.007; chin: 𝐵 = −0.640, 𝑃 = 0.031), while 𝑏∗ value of the lower cheek was positively associated" 90e994a802a0038f24c8e3735d7619ebb40e6e93,Semantic Foggy Scene Understanding with Synthetic Data,"Noname manuscript No. (will be inserted by the editor) Semantic Foggy Scene Understanding with Synthetic Data Christos Sakaridis · Dengxin Dai · Luc Van Gool Received: date / Accepted: date" 90e56a8515c8c2ff16f5c79c69811e283be852c7,Boosting face recognition via neural Super-Resolution,"Boosting face recognition via neural Super-Resolution Guillaume Berger, Cl´ement Peyrard and Moez Baccouche Orange Labs - 4 rue du Clos Courtel, 35510 Cesson-S´evign´e - France" 90fb58eeb32f15f795030c112f5a9b1655ba3624,OF RESEARCH IN COMPUTER APPLICATIONS AND ROBOTICS ISSN 2320-7345 FACE AND IRIS RECOGNITION IN A VIDEO SEQUENCE USING DBPNN AND ADAPTIVE HAMMING DISTANCE,"INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND ROBOTICS www.ijrcar.com Vol.4 Issue 6, Pg.: 12-27 June 2016 INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND ROBOTICS ISSN 2320-7345 FACE AND IRIS RECOGNITION IN A VIDEO SEQUENCE USING DBPNN AND ADAPTIVE HAMMING DISTANCE S. Revathy, 2Mr. L. Ramasethu PG Scholar, Hindusthan College of Engineering and Technology, Coimbatore, India. Assistant Professor, Hindusthan College of Engineering and Technology, Coimbatore, India. Email id:" 904b322a61d9be9c0b1023946320f9245533085e,Multi-Residual Networks,"Multi-Residual Networks Masoud Abdi and Saeid Nahavandi*" 90ce227ec08053ea6acf9f9f9f53d8b7169574f2,An Introduction to Evaluating Biometric Systems,"C O V E R F E A T U R E An Introduction to Evaluating Biometric Systems O n the basis of media hype alone, you might onclude that biometric passwords will soon replace their alphanumeric counterparts with versions that cannot be stolen, forgot- ten, lost, or given to another person. But what if the performance estimates of these systems are far more impressive than their actual performance? P. Jonathon Phillips Alvin Martin C.L. Wilson Przybocki National Institute of Standards and" 9043df1de4f6e181875011c1379d1a7f68a28d6c,People Detection from Overhead Cameras,"People Detection from Overhead Cameras A study of impact of occlusion on performance Lu Liu in partial fulfillment of the requirements for the degree of Master of Science t the Delft University of Technology, to be defended publicly on Friday August 31, 2018 at 01:00 PM. Student number: Thesis committee: Dr. Hayley Hung (supervisor) 621832 EEMCS Laura Cabrera-Quiros (mentor) EEMCS EEMCS Prof. Marcel Reinders, Dr. Julian Kooij," 90c26eca18194e23cfd3c3bbf341b133e4bf5f6b,Localization from semantic observations via the matrix permanent,"Article Localization from semantic observations via the matrix permanent The International Journal of Robotics Research Ó The Author(s) 2015 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/0278364915596589 ijr.sagepub.com Nikolay Atanasov, Menglong Zhu, Kostas Daniilidis and George J. Pappas" 90cb074a19c5e7d92a1c0d328a1ade1295f4f311,Fully Automatic Upper Facial Action Recognition,"MIT. Media Laboratory Affective Computing Technical Report #571 Appears in IEEE International Workshop on Analysis and Modeling of Faces and Gestures , Oct 2003 Fully Automatic Upper Facial Action Recognition Ashish Kapoor Yuan Qi Rosalind W. Picard MIT Media Laboratory Cambridge, MA 02139" 909f91c1957ce2bf9d76ee2109a865e87bf17057,GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs,"GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs Amir Roshan Zamir, Afshin Dehghan, and Mubarak Shah UCF Computer Vision Lab, Orlando, FL 32816, USA" 90eb9f6a1b7e3dae24e438b201e6b1f671a87eb5,Single-Camera Automatic Landmarking for People Recognition with an Ensemble of Regression Trees,"Single-Camera Automatic Landmarking for People Recognition with an Ensemble of Regression Trees Karla Trejo, Cecilio Angulo Universitat Polit`ecnica de Catalunya, Barcelona, Spain (AAM) Active Appearance Model" 907fbe706ec14101978a63c6252e0d75e657e8dd,The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution,"The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution Muhammad Waleed Gondal Max Planck Institute for Intelligent Systems. Bernhard Schölkopf Max Planck Institute for Intelligent Systems. Michael Hirsch Amazon Research." 9099de23a4842b37b1612e90db18ec43d2e6250f,A comprehensive comparison of features and embedding methods for face recognition,"Turk J Elec Eng & Comp Sci (2016) 24: 313 { 340 ⃝ T (cid:127)UB_ITAK doi:10.3906/elk-1301-65 A comprehensive comparison of features and embedding methods for face recognition (cid:3) , Hakan C(cid:24) EV_IKALP, Rifat ED_IZKAN Hasan Serhan YAVUZ Department of Electrical and Electronics Engineering, Eski(cid:24)sehir Osmangazi University, Eski(cid:24)sehir, Turkey Received: 11.01.2013 (cid:15) Accepted/Published Online: 09.11.2013 (cid:15) Final Version: 01.01.2016" 90443ec362dc553f29fbf824b4d13fd7f26f2a32,A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval,"A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval Johannes L. Sch¨onberger1(cid:63), True Price2(cid:63), Torsten Sattler1(cid:63), Jan-Michael Frahm2, Marc Pollefeys1,3 ETH Z¨urich, 2 UNC Chapel Hill, 3 Microsoft" 903bc3588be010a5a166b48d3f52d0ee521dd4f9,"Discrete Energy Minimization, beyond Submodularity: Applications and Approximations","Thesis for the degree Doctor of Philosophy By Shai Bagon Advisor: Prof. Michal Irani September, 2012 Submitted to the Scientific Council of the Weizmann Institute of Science Rehovot, Israel ,תויטרקסיד תויגרנא רועזימ תתל רֶבֵעֵמ-:תויראלודומ םיבוריקו תויצקילפא Discrete Energy Minimization, beyond Submodularity: Applications and Approximations ראותל (הזת) רמג תדובע היפוסוליפל רוטקוד תאמ שןוגב י ירשתג""עשת , שגומת לש תיעדמה הצעומל עדמל ןמציו ןוכמ לארשי ,תובוחר חנמ:ה ינריא לכימ 'פורפ" 9095f633a153c0e3a5503c0373c9c1dfeeefb0cc,Fast 3D face reconstruction based on uncalibrated photometric stereo,"Multimed Tools Appl DOI 10.1007/s11042-013-1791-3 Fast 3D face reconstruction based on uncalibrated photometric stereo Yujuan Sun & Junyu Dong & Muwei Jian & Lin Qi # Springer Science+Business Media New York 2013" 907475a4febf3f1d4089a3e775ea018fbec895fe,Statistical modeling for facial expression analysis and synthesis,"STATISTICAL MODELING FOR FACIAL EXPRESSION ANALYSIS AND SYNTHESIS Bouchra Abboud, Franck Davoine, Mˆo Dang Heudiasyc Laboratory, CNRS, University of Technology of Compi`egne. BP 20529, 60205 COMPIEGNE Cedex, FRANCE. E-mail:" 90d8dbaa799430d7384425061317e0fa55bf5cbb,Representation Models and Machine Learning Techniques for Scene Classificatio,"Representation Models and Machine Learning Techniques for Scene Classificatio Giovanni Maria Farinella and Sebastiano Battiato Image Processing Lab, Dipartimento di Matematica e Informatica, Universit`a degli Studi di Catania, Viale A. Doria 6, 95125 Catania, Italy; E-mail: {gfarinella," 90de946acdc1dd6886c51f48031e2d5f3b4b8b28,Nonlinear Dimensionality Reduction with Locally Linear Embedding and Isomap,"Nonlinear Dimensionality Reduction with Locally Linear Embedding nd Isomap Tobias Friedrich Department of Computer Science The University of Sheffield September 2002 THIS DISSERTATION IS A PART REQUIREMENT FOR THE MSC IN ADVANCED COMPUTER SCIENCE." 9015fd773526e21e352037663de3f586ccf4e907,Fused Deep Neural Networks for Efficient Pedestrian Detection,"Fused Deep Neural Networks for Efficient Pedestrian Detection Xianzhi Du, Mostafa El-Khamy, Vlad I. Morariu, Jungwon Lee, and Larry Davis" 90a226bcd72ac3bd7a0e12d416055b6299613169,Classifying content-based Images using Self Organizing Map Neural Networks Based on Nonlinear Features,"Int. J. Advanced Networking and Applications Volume: 6 Issue: 1 Pages: 2135-2140 (2014) ISSN : 0975-0290 Classifying content-based Images using Self Organizing Map Neural Networks Based on Nonlinear Features Ebrahim Parcham Electrical and Computer Engineering Department, Tehran Science & Research University Tehran, Iran Department of Electrical Computer and BiomedicalEngineering,Qazvin Branch Islamic Azad University Qazvin,Iran Department of Electrical Computer and BiomedicalEngineering,Qazvin Branch Islamic Azad University Qazvin,Iran Email: Monireh Pournazari Email: Mina Hojati Email: Mehrdad Jalili Monir Shatel Isp technical Employer Email: Bahareh Mirzaei Sohrevardi private high educational institute,school of computer engineering Qazvin,Iran Email:" 90a545980b3bb2f001298fe5091847c9738be8a0,Automated vehicle's behavior decision making using deep reinforcement learning and high-fidelity simulation environment,"Automated Vehicle’s behavior decision making using deep reinforcement learning and high-fidelity simulation environment Yingjun Yea, Xiaohui Zhanga, Jian Suna Department of Traffic Engineering & Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China." 90915cc93248174c4729be65159fb946d2ad5f72,"Relative Dense Tracklets for Human Action Recognition Piotr Bilinski Etienne Corvee Slawomir Bak Francois Bremond INRIA Sophia Antipolis , STARS team 2004 Route des Lucioles , BP 93 , 06902 Sophia Antipolis , France","Relative Dense Tracklets for Human Action Recognition Piotr Bilinski Etienne Corvee Slawomir Bak Francois Bremond INRIA Sophia Antipolis, STARS team 004 Route des Lucioles, BP93, 06902 Sophia Antipolis, France" 903210406f14a12b481524d543b14f16114797e2,Pretest of images for the beauty dimension,"Análise Psicológica (2015), 4 (XXXIII): 453-466 doi: 10.14417/ap.1052 Pretest of images for the beauty dimension Joana Mello* / Filipe Loureiro* * ISPA – Instituto Universitário In this work, we present norms concerning the perceived association of two sets of image stimuli with the concept of “beauty”: 40 objects (Study 1) and 40 photos of human faces (Study 2)1. Participants were presented with a set of words associated with the construct of “beauty” and were subsequently sked to judge each image on how much they considered them to be related with this construct on a 7-point scale (1 – Not at all related; 7 – Very related). The interpretation of means’ confidence intervals distinguish between 40 images, evaluated as “ugly” – with low scores on the beauty dimension – (20 objects and 20 faces), and 28 images evaluated as “beautiful” – with high scores on the beauty dimension – (12 objects and 16 faces). Results are summarized and photos made available to support future research requiring beauty and/or ugly stimulus. Key words: Norms, Beauty, Ugly, People, Objects. Introduction The objective of this work consists on the presentation of beauty norms of a set of images from two categories (people and objects) for further use in different contexts and experimental settings. Our main purpose was to present norms of a set of updated to present-days photos of faces and objects regarding its level of activation of the “beauty” construct, i.e., of the perceived association" 9064e178864208cb0e89fecdc8d26b846ccc8e55,Localizing Moments in Video with Temporal Language,"Localizing Moments in Video with Temporal Language Lisa Anne Hendricks1∗, Oliver Wang2, Eli Shechtman2, Josef Sivic2,3∗ , Trevor Darrell1, Bryan Russell2 UC Berkeley, 2 Adobe Research, 3 INRIA" 904a8241ef400bd85b1ad10267a1177bbde1c048,Image-Text Dataset Generation for Image Annotation and Retrieval ⋆,"II Congreso Español de Recuperación de la Información CERI 2012 Image-Text Dataset Generation for Image Annotation and Retrieval⋆ Mauricio Villegas and Roberto Paredes Institut Tecnol`ogic d’Inform`atica Universitat Polit`ecnica de Val`encia Cam´ı de Vera s/n, 46022 Val`encia (Spain)" 9070045c1a9564a5f25b42f3facc7edf4c302483,Everybody needs somebody: Modeling social and grouping behavior on a linear programming multiple people tracker,"Everybody needs somebody: Modeling social and grouping behavior on a linear programming multiple people tracker Laura Leal-Taix´e, Gerard Pons-Moll and Bodo Rosenhahn Institute for Information Processing (TNT) Leibniz University Hannover, Germany" 900175d24928921600d09985211b6b9bfea44ce0,Person re-identification by pose priors,"Person re-identification by pose priors Sławomir Bąk Filipe Martins Francois Brémond INRIA Sophia Antipolis, STARS team, 2004, route des Lucioles, BP93 06902 Sophia Antipolis Cedex - France" 90dd6e7051a2dd8639d6f2d9f7b02acb43eb94c7,BlitzNet: A Real-Time Deep Network for Scene Understanding, 90dd771829094dad1230e32b8bc4385bfe86c4e5,A Comparison of Word Embeddings for the Biomedical Natural Language Processing,[cs.IR] 18 Jul 2018 90818e0ab85b6a5f03cd28bc5c23c90a0971c36e,Maximum Entropy-based Thresholding algorithm for Face image segmentation,"Maximum Entropy-based Thresholding algorithm for Face image segmentation Kittikhun Meethongjan Department of Computer Graphic, Faculty of Computer Science & Information System, University Technology of Malaysia, 81310 Skudai, Johor, Malaysia. +60127204314" 902d1b14b076120cb21029b51ed8e63529fe686d,PERFORMANCE ANALYSIS FOR FACIAL EXPRESSION RECOGNITION UNDER SALT AND PEPPER NOISE WITH MEDIAN FILTER APPROACH,"PERFORMANCE ANALYSIS FOR FACIAL EXPRESSION RECOGNITION UNDER SALT AND PEPPER NOISE WITH MEDIAN FILTER APPROACH AZRINI BINTI IDRIS A project report submitted in partial fulfillment of the requirement for the award of the Degree of Master of Electrical Engineering Facultyof Electrical and Electronic Engineering UniversitiTun Hussein Onn Malaysia JULY 2013" 90f0646c0801f1dad43d2374d1145be8e005bdbf,Raised Middle-Finger: Electrocortical Correlates of Social Conditioning with Nonverbal Affective Gestures,"Raised Middle-Finger: Electrocortical Correlates of Social Conditioning with Nonverbal Affective Gestures Matthias J. Wieser1*, Tobias Flaisch2, Paul Pauli1 Department of Psychology, University of Wu¨ rzburg, Wu¨ rzburg, Germany, 2 Department of Psychology, University of Konstanz, Konstanz, Germany" 90a70b38c5a1b40ac16e18628a7772923cdc5cb5,Exact Subspace Segmentation and Outlier Detection by Low-Rank Representation,"Exact Subspace Segmentation and Outlier Detection by Low-Rank Representation Anonymous Author 1 Anonymous Author 2 Anonymous Author 3" 90d8bf2199e7fd972dab3bd3dc6fb67536fa509b,Performance and Energy Modeling of Heterogeneous Many-core Architectures,"PERFORMANCE AND ENERGY MODELING OF HETEROGENEOUS MANY-CORE ARCHITECTURES Performance and Energy Modeling of Heterogeneous Many-core Architectures Rui Pedro Gaspar Pinheiro" 90e36f66c25a4c73a252102c6c6c329c36d82676,Probably Unknown: Deep Inverse Sensor Modelling In Radar,"Probably Unknown: Deep Inverse Sensor Modelling Radar Rob Weston, Sarah Cen, Paul Newman and Ingmar Posner" 9040fa6a62f6c185473f4043846de3aa7920624b,THERMAL IMAGING AS A BIOMETRICS APPROACH TO FACIAL SIGNATURE AUTHENTICATION 1,"October 2015, Volume 2, Issue 10 THERMAL IMAGING AS A BIOMETRICS APPROACH TO FACIAL SIGNATURE JETIR (ISSN-2349-5162) AUTHENTICATION .MundeBibhishanUttamrao 2.HONRAO S.B. [M.Tech.] Aditya college Associate Prof. , Aditya College difficulty in detecting facial disguises. The light variability leads to problems in matching. 1) Proposed Method This paper realizes the potential of thermal MWIR imagery for human identification using the vein structure of hands in “Biometric verification using thermal images of palm-dorsa vein patterns,” and by using finger vein patterns in “Artificial immune system for personal identification with finger vein pattern”. Thermal images have been used to identify the affective state of humans in the previous work on “Classifying affective states using thermal infrared imaging of the human face"". thermal templates" 9028fbbd1727215010a5e09bc5758492211dec19,Solving the Uncalibrated Photometric Stereo Problem Using Total Variation,"Solving the Uncalibrated Photometric Stereo Problem using Total Variation Yvain Qu´eau1, Fran¸cois Lauze2, and Jean-Denis Durou1 IRIT, UMR CNRS 5505, Toulouse, France Dept. of Computer Science, Univ. of Copenhagen, Denmark" 90c80317fa68784a3fe4fc3136bb188895b09fa4,Sparsity Invariant CNNs,"Sparsity Invariant CNNs Jonas Uhrig(cid:63),1,2 Nick Schneider(cid:63),1,3 Lukas Schneider1,4 Uwe Franke1 Thomas Brox2 Andreas Geiger4,5 The first two authors contributed equally to this work Daimler R&D Sindelfingen University of Freiburg KIT Karlsruhe ETH Z¨urich 5MPI T¨ubingen September 1, 2017" 904c53ea063d7d1e13b99d55257801d69d073775,Combined Object Detection and Segmentation,"International Journal of Machine Learning and Computing, Vol. 3, No. 1, February 2013 Combined Object Detection and Segmentation Jarich Vansteenberge, Masayuki Mukunoki, and Michihiko Minoh" 365b72a225a18a930b96e7c0b215b9fede8a0968,Storyline Reconstruction for Unordered Images Final Paper,"Storyline Reconstruction for Unordered Images Final Paper Sameedha Bairagi, Arpit Khandelwal, Venkatesh Raizaday Introduction: Storyline reconstruction is a relatively new topic and has not been researched extensively. The main objective is to take a stream of images as input and re-shuffle them in chronological order. The recent growth of online multimedia data has generated lots and lots of unstructured data on the web. Image streams are generated daily on websites like Flicker, Instagram etc. and almost 00 hours of video is uploaded on YouTube on a daily basis. In this paper, we try and implement an algorithm which uses the property of videos of being temporally adept to sort a stream of unordered images. The basic process is as follows: - Generate key frames/video summary of a video from multiple instances of the same ategory. - Cluster these key frames on the basis of the action being performed in them. - Create a graph from these clusters using temporal data from the videos. - Take an input stream of images and assign each image to its most probable cluster. - Use the graph to assign ordering to the images. In the following sections, we will try and go deep into each of the step mentioned above and discuss multiple approaches we implemented to do the same. Background and Related work:" 361367838ee5d9d5c9a77c69c1c56b1c309ab236,Salient Object Detection: A Survey,"Salient Object Detection: A Survey Ali Borji, Ming–Ming Cheng, Huaizu Jiang and Jia Li" 363913a335053c837d5fc279032d28c418dda1dc,ECE 533 – Image Processing Project Face Recognition Techniques,"ECE533 – Image Processing Project Face Recognition Techniques Jorge Orts" 36f039e39efde3558531b99d85cd9e3ab7d396b3,9 Efficiency of Recognition Methods for Single Sample per Person Based Face Recognition,"Efficiency of Recognition Methods for Single Sample per Person Based Face Recognition Miloš Oravec, Jarmila Pavlovičová, Ján Mazanec, Ľuboš Omelina, Matej Féder and Jozef Ban Faculty of Electrical Engineering and Information Technology Slovak University of Technology in Bratislava Slovakia . Introduction Even for the present-day computer technology, the biometric recognition of human face is difficult task and continually evolving concept in the area of biometric recognition. The rea of face recognition is well-described today in many papers and books, e.g. (Delac et al., 008), (Li & Jain, 2005), (Oravec et al., 2010). The idea that two-dimensional still-image face recognition in controlled environment is already a solved task is generally accepted and several benchmarks evaluating recognition results were done in this area (e.g. Face Recognition Vendor Tests, FRVT 2000, 2002, 2006, http://www.frvt.org/). Nevertheless, many tasks have to be solved, such as recognition in unconstrained environment, recognition of non-frontal images, single sample per person problem, etc. This chapter deals with single sample per person face recognition (also called one sample per person problem). This topic is related to small sample size problem in pattern recognition. Although there are also advantages of single sample – fast and easy creation of" 36c8f798145902583592a03df88a6043baa11fe7,Score Fusion of SIFT & SURF Descriptors for Face Recognition Using Wavelet Transforms,"I.J. Image, Graphics and Signal Processing, 2017, 10, 22-28 Published Online October 2017 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijigsp.2017.10.03 Score Fusion of SIFT & SURF Descriptors for Face Recognition Using Wavelet Transforms Musa M.Ameen Ishik University/Computer Engineering Department, Erbil, 44001, Iraq Email: Alaa Eleyan Avrasya University/Electrical and Electronics Engineering Department, Trabzon, 61000, Turkey Received: 09 June 2017; Accepted: 12 September 2017; Published: 08 October 2017 Email: human intervention. the automated" 366c14f477bf2ed16b1498d1c56a7e1f2af08e69,Comparative Analysis of Statistical Shape Spaces,"Comparative Analysis of Statistical Shape Spaces Alan Brunton∗ Augusto Salazar† Timo Bolkart† Stefanie Wuhrer†" 365866dc937529c3079a962408bffaa9b87c1f06,Facial Feature Expression Based Approach for Human Face Recognition : A Review,"IJISET - International Journal of Innovative Science, Engineering & Technology, Vol. 1 Issue 3, May 2014. www.ijiset.com ISSN 2348 – 7968 Facial Feature Expression Based Approach for Human Face Recognition: A Review Jageshvar K. Keche1, Mahendra P. Dhore2 Department of Computer Science, SSESA, Science College, Congress Nagar, Nagpur, (MS)-India, Department of Electronics & Computer Science, RTM Nagpur University, Campus Nagpur, (MS)-India. required extraction of" 36ab143da8b6f6d49811afaaa7bcbf81c22a210e,Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification Yu-Gang Jiang, Zuxuan Wu, Jinhui Tang, Zechao Li, Xiangyang Xue, Shih-Fu Chang" 36939e6a365e9db904d81325212177c9e9e76c54,"Assessing the Accuracy of Four Popular Face Recognition Tools for Inferring Gender, Age, and Race","Assessing the Accuracy of Four Popular Face Recognition Tools for Inferring Gender, Age, and Race Soon-Gyo Jung, Jisun An, Haewoon Kwak, Joni Salminen, Bernard J. Jansen Qatar Computing Research Institute, HBKU HBKU Research Complex, Doha, P.O. Box 34110, Qatar" 367b5b814aa991329c2ae7f8793909ad8c0a56f1,Performance evaluation of random set based pedestrian tracking algorithms,"Performance Evaluation of Random Set Based Pedestrian Tracking Algorithms Branko Ristic ISR Division Australia Jamie Sherrah ISR Division Australia ´Angel F. Garc´ıa-Fern´andez Department of Signals and Systems Chalmers University of Technology Sweden" 362bfeb28adac5f45b6ef46c07c59744b4ed6a52,Incorporating Scalability in Unsupervised Spatio- Temporal Feature Learning,"INCORPORATING SCALABILITY IN UNSUPERVISED SPATIO-TEMPORAL FEATURE LEARNING Sujoy Paul, Sourya Roy and Amit K. Roy-Chowdhury Dept. of Electrical and Computer Engineering, University of California, Riverside, CA 92521" 364584f8313e7601b1f5134d371e98aeb61110e8,An invariant bipolar representation for 3 D surfaces,"An invariant bipolar representation for 3D surfaces M. JRIBI and F. GHORBEL CRSITAL Laboratory / GRIFT research group, Ecole Nationale des Sciences de l’Informatique (ENSI), La Manouba University, 2010 La Manouba, Tunisia" 36513f869e5ba2928369014244dff998ab93728c,Discriminative cluster analysis,"Chapter 1 Discriminative Cluster Analysis Fernando De la Torre and Takeo Kanade" 361b19d2c00d086fa8ef860374f5e1d862fd2f30,Learning to Refine Object Segments,"Learning to Refine Object Segments Pedro O. Pinheiro(cid:63), Tsung-Yi Lin(cid:63), Ronan Collobert, Piotr Doll´ar Facebook AI Research (FAIR)" 362250566948f17693b737122fc1434173982da8,Automatic Image Annotation using Weakly Labelled Web Data,"Automatic Image Annotation using Weakly Labelled Web Data Pravin Kakar, Xiangyu Wang and Alex Yong-Sang Chia Social Media and Internet Vision Analytics Lab, Institute for Infocomm Research, #21-01, 1 Fusionopolis Way, {kakarpv, wangx, Singapore 138632." 3687bad2caa2d323941e6ec343e9156fca9cf606,Super Resolution of Images and Video,"MOBK071-FM MOBKXXX-Sample.cls April 16, 2007 5:48 Super Resolution of Images and Video" 36ca4ad185e68db34b0bbfa1057ebdaa9177c131,Segmented AAMs Improve Person-Indepedent Face Fitting,"Segmented AAMs Improve Person-Independent Face Fitting Julien Peyras1 Adrien Bartoli2 Hugo Mercier3 Patrice Dalle3 Dipartimento di Scienze dell’Informazione, Milano, Italy LASMEA, Clermont-Ferrand, France IRIT, Toulouse, France" 369c4a308ec9e56746f7cc1b164208b917e31a22,Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings,"Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings Bao Xin Chen, Raghavender Sahdev, Dekun Wu, Xing Zhao, Manos Papagelis and John K. Tsotsos" 36d8cc038db71a473d0c94c21f2b68a840dff21c,Unsupervised Detector Adaptation by Joint Dataset Feature Learning,"                                  !∀∀ ##!∃%&∋()      ∗+,       #−./!0!∀  !!2!342 ," 3646b42511a6a0df5470408bc9a7a69bb3c5d742,Detection of Facial Parts based on ABLATA,"International Journal of Computer Applications (0975 – 8887) Applications of Computers and Electronics for the Welfare of Rural Masses (ACEWRM) 2015 Detection of Facial Parts based on ABLATA Siddhartha Choubey Shri Shankaracharya Technical Campus, Bhilai Vikas Singh Shri Shankaracharya Technical Campus, Bhilai Abha Choubey Shri Shankaracharya Technical Campus, Bhilai" 363ca0a3f908859b1b55c2ff77cc900957653748,Local Binary Patterns and Linear Programming using Facial Expression,"International Journal of Computer Trends and Technology (IJCTT) – volume 1 Issue 3 Number 4 – Aug 2011 Local Binary Patterns and Linear Programming using Facial Expression Ms.P.Jennifer #MCA Department, Bharath Institute of Science and Technology +B.Tech (C.S.E), Bharath University , Chennai – 73. Dr. A. Muthu kumaravel #MCA Department, Bharath Institute of Science and Technology +B.Tech (C.S.E), Bharath University , Chennai – 73." 3678dac7e9998567b92f526046a16e2910ced55d,Talking Robots : grounding a shared lexicon in an unconstrained environment,"Berthouze, L., Prince, C. G., Littman, M., Kozima, H., and Balkenius, C. (2007). Proceedings of the Seventh International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems. Lund University Cognitive Studies, 135. Talking Robots: grounding a shared lexicon in an unconstrained environment Matthieu Nottale Jean-Christophe Baillie ENSTA-UEI cognitive robotics lab." 36973330ae638571484e1f68aaf455e3e6f18ae9,Scale-Aware Fast R-CNN for Pedestrian Detection,"Scale-aware Fast R-CNN for Pedestrian Detection Jianan Li, Xiaodan Liang, ShengMei Shen, Tingfa Xu, and Shuicheng Yan" 36018404263b9bb44d1fddaddd9ee9af9d46e560,OCCLUDED FACE RECOGNITION BY USING GABOR FEATURES,"OCCLUDED FACE RECOGNITION BY USING GABOR FEATURES Burcu Kepenekci 1,2, F. Boray Tek 1,2, Gozde Bozdagi Akar 1 Department of Electrical And Electronics Engineering, METU, Ankara, Turkey 7h%ł7$.(cid:3)%ł/7(1(cid:15)(cid:3)$QNDUD(cid:15)(cid:3)7XUNH\" 36fe39ed69a5c7ff9650fd5f4fe950b5880760b0,Tracking von Gesichtsmimik mit Hilfe von Gitterstrukturen zur Klassifikation von schmerzrelevanten Action Units,"Tracking von Gesichtsmimik mit Hilfe von Gitterstrukturen zur Klassifikation von schmerzrelevanten Action Units Christine Barthold1, Anton Papst1, Thomas Wittenberg1 Christian K¨ublbeck1, Stefan Lautenbacher2, Ute Schmid2, Sven Friedl1,3 Fraunhofer-Institut f¨ur Integrierte Schaltungen IIS, Erlangen, Otto-Friedrich-Universit¨at Bamberg, 3Universit¨atsklinkum Erlangen Kurzfassung. In der Schmerzforschung werden schmerzrelevante Mi- mikbewegungen von Probanden mittels des Facial Action Coding System klassifiziert. Die manuelle Klassifikation hierbei ist aufw¨andig und eine utomatische (Vor-)klassifikation k¨onnte den diagnostischen Wert dieser Analysen erh¨ohen sowie den klinischen Workflow unterst¨utzen. Der hier vorgestellte regelbasierte Ansatz erm¨oglicht eine automatische Klassifika- tion ohne große Trainingsmengen vorklassifizierter Daten. Das Verfahren erkennt und verfolgt Mimikbewegungen, unterst¨utzt durch ein Gitter, und ordnet diese Bewegungen bestimmten Gesichtsarealen zu. Mit die- sem Wissen kann aus den Bewegungen auf die zugeh¨origen Action Units geschlossen werden. Einleitung" 367231b80e8201fc9c461fbb42047b20e89ea961,Impatient DNNs - Deep Neural Networks with Dynamic Time Budgets,"MANUEL AMTHOR, ERIK RODNER, AND JOACHIM DENZLER: IMPATIENT DNNS Impatient DNNs – Deep Neural Networks with Dynamic Time Budgets Manuel Amthor Erik Rodner Joachim Denzler Computer Vision Group Friedrich Schiller University Jena Germany www.inf-cv.uni-jena.de" 362cfe79a6822f9e317555c5e3469dd038b9053f,Damped Gauss-Newton algorithm for nonnegative Tucker decomposition,"978-1-4577-0568-7/11/$26.00 ©2011 IEEE DY, An , G (cid:2) (cid:12)Y  G  A (cid:12)2 DECOMPOSITION . INTRODUCTION" 3674f3597bbca3ce05e4423611d871d09882043b,Facial Expression Spacial Charts for Describing Dynamic Diversity of Facial Expressions,"ISSN 1796-2048 Volume 7, Number 4, August 2012 Contents Special Issue: Multimedia Contents Security in Social Networks Applications Guest Editors: Zhiyong Zhang and Muthucumaru Maheswaran Guest Editorial Zhiyong Zhang and Muthucumaru Maheswaran SPECIAL ISSUE PAPERS DRTEMBB: Dynamic Recommendation Trust Evaluation Model Based on Bidding Gang Wang and Xiao-lin Gui Block-Based Parallel Intra Prediction Scheme for HEVC Jie Jiang, Baolong, Wei Mo, and Kefeng Fan Optimized LSB Matching Steganography Based on Fisher Information Yi-feng Sun, Dan-mei Niu, Guang-ming Tang, and Zhan-zhan Gao A Novel Robust Zero-Watermarking Scheme Based on Discrete Wavelet Transform Yu Yang, Min Lei, Huaqun Liu, Yajian Zhou, and Qun Luo Stego Key Estimation in LSB Steganography Jing Liu and Guangming Tang REGULAR PAPERS Facial Expression Spacial Charts for Describing Dynamic Diversity of Facial Expressions" 368132f8dfcbd6e857dfc1b7dce2ab91bd9648ad,"Simultaneous Localization And Mapping: Present, Future, and the Robust-Perception Age","Simultaneous Localization And Mapping: Present, Future, and the Robust-Perception Age Cesar Cadena, Luca Carlone, Henry Carrillo, Yasir Latif, Davide Scaramuzza, Jos´e Neira, Ian D. Reid, John J. Leonard" 36cd55cdb1b032c8f29e011ed0637923afc46d3f,Strategies to Improve Activity Recognition Based on Skeletal Tracking: Applying Restrictions Regarding Body Parts and Similarity Boundaries †,"Article Strategies to Improve Activity Recognition Based on Skeletal Tracking: Applying Restrictions Regarding Body Parts and Similarity Boundaries † Carlos Gutiérrez-López-Franca *, Ramón Hervás and Esperanza Johnson MAmI Research Lab, University of Castilla-La Mancha, Paseo de la Universidad 4, 13071 Ciudad Real, Spain; (R.H.); (E.J.) * Correspondence: This paper is an extended version of our paper published in Gutiérrez López de la Franca, C.; Hervás, R.; Johnson, E.; Bravo, J. Findings about Selecting Body Parts to Analyze Human Activities through Skeletal Tracking Joint Oriented Devices. In Proceedings of the 10th International Conference on Ubiquitous Computing and Ambient Intelligence (UCAMI 2016), Gran Canaria, Spain, 29 November–2 December 2016. Received: 4 April 2018; Accepted: 17 May 2018; Published: 22 May 2018" 3607afdb204de9a5a9300ae98aa4635d9effcda2,Face Description with Local Binary Patterns: Application to Face Recognition,"Face Description with Local Binary Patterns: Application to Face Recognition Timo Ahonen, Student Member, IEEE, Abdenour Hadid, nd Matti Pietik¨ainen, Senior Member, IEEE" 367008b91eb57c5ea64ef7520dfcabc0c5c85532,"Person Re-identification: Past, Present and Future","JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Person Re-identification: Past, Present and Future Liang Zheng, Yi Yang, and Alexander G. Hauptmann" 36b9faf0d6c4c6296193b8d5d7833624a181624c,Real-Time Multiple Human Perception With Color-Depth Cameras on a Mobile Robot,"Real-Time Multiple Human Perception with Color-Depth Cameras on a Mobile Robot Hao Zhang, Student Member, IEEE, Christopher Reardon, Student Member, IEEE, and Lynne E. Parker, Fellow, IEEE" 362a70b6e7d55a777feb7b9fc8bc4d40a57cde8c,A partial least squares based ranker for fast and accurate age estimation,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 36ca720185b62e92a7f3cce75418356a5a125d24,Template aging in 3D and 2D face recognition,"Template Aging in 3D and 2D Face Recognition Ishan Manjani∗ Hakki Sumerkan† Patrick J. Flynn† Kevin W. Bowyer†" 36fa002f36e14ab7d24ebcdd99b6589ed726b383,Detecting conversational gaze aversion using unsupervised learning,"Detecting Conversational Gaze Aversion Using Unsupervised Learning Matthew Roddy, Naomi Harte ADAPT Centre, School of Engineering Trinity College Dublin, Ireland" 36ce0b68a01b4c96af6ad8c26e55e5a30446f360,Facial expression recognition based on a mlp neural network using constructive training algorithm,"Multimed Tools Appl DOI 10.1007/s11042-014-2322-6 Facial expression recognition based on a mlp neural network using constructive training algorithm Hayet Boughrara · Mohamed Chtourou · Chokri Ben Amar · Liming Chen Received: 5 February 2014 / Revised: 22 August 2014 / Accepted: 13 October 2014 © Springer Science+Business Media New York 2014" 36cbcd70af6f2fd3e700e0a710acd5f1f6abebcf,Matching People across Camera Views using Kernel Canonical Correlation Analysis,"Matching People across Camera Views using Kernel Canonical Correlation Analysis Giuseppe Lisanti , Iacopo Masi , Alberto Del Bimbo Media Integration and Communication Center (MICC), Università degli Studi di Firenze Viale Morgagni 65 - 50134 Firenze, Italy" 36c9731f24e5daa42c1e2c6c68258567dfa78a0a,Movement tracking in terrain conditions accelerated with CUDA,"Proceedings of the 2014 Federated Conference on Computer Science and Information Systems pp. 709–717 DOI: 10.15439/2014F282 ACSIS, Vol. 2 978-83-60810-58-3/$25.00 c(cid:13) 2014, IEEE" 363e5a0e4cd857e98de72a726ad6f80cea9c50ab,Fast Landmark Localization With 3D Component Reconstruction and CNN for Cross-Pose Recognition,"Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition Gee-Sern (Jison) Hsu, Hung-Cheng Shie, Cheng-Hua Hsieh" 369bd35ab8bad4c7bc5e376cc776a5366d97b12e,An Object Detector Trained on Line Drawings,"Bachelor’s Thesis An Object Detector Trained on Line Drawings Patric Tippmann August 2012 Albert-Ludwigs-Universität Freiburg Department of Computer Science Computer Vision Group Supervisor: Prof. Dr. Thomas Brox" 36688a79cc8926f489ccb6e6dadba15afbb4b6a4,Linear discriminant analysis for the small sample size problem: an overview,"Int. J. Mach. Learn. & Cyber. DOI 10.1007/s13042-013-0226-9 O R I G I N A L A R T I C L E Linear discriminant analysis for the small sample size problem: n overview Alok Sharma • Kuldip K. Paliwal Received: 19 March 2013 / Accepted: 26 December 2013 Ó Springer-Verlag Berlin Heidelberg 2014" 3600f9def4e619e154a59df50dffe3cb23300e42,A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition,"Hindawi Computational Intelligence and Neuroscience Volume 2017, Article ID 4180510, 26 pages https://doi.org/10.1155/2017/4180510 Research Article A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition Daniela Sánchez, Patricia Melin, and Oscar Castillo Tijuana Institute of Technology, Tijuana, BC, Mexico Correspondence should be addressed to Oscar Castillo; Received 25 February 2017; Revised 17 June 2017; Accepted 10 July 2017; Published 14 August 2017 Academic Editor: Jos´e Alfredo Hern´andez-P´erez Copyright © 2017 Daniela S´anchez et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. A grey wolf optimizer for modular neural network (MNN) with a granular approach is proposed. The proposed method performs optimal granulation of data and design of modular neural networks architectures to perform human recognition, and to prove its effectiveness benchmark databases of ear, iris, and face biometric measures are used to perform tests and comparisons against other works. The design of a modular granular neural network (MGNN) consists in finding optimal parameters of its architecture; these parameters are the number of subgranules, percentage of data for the training phase, learning algorithm, goal error, number of hidden layers, and their number of neurons. Nowadays, there is a great variety of approaches and new techniques within the" 367c571480ac46d48be050dee4e6103a0ebb5db5,Multimedia Content Based Image Retrieval Iii : Local Tetra,"Manas M N et al Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 4, Issue 6( Version 3), June 2014, pp.104-107 RESEARCH ARTICLE OPEN ACCESS Multimedia Content Based Image Retrieval Iii: Local Tetra Pattern Nagaraja G S1, Rajashekara Murthy S2, Manas M N3, Sridhar N H4 (Department of CSE, RVCE, Visvesvaraya Technological University, Bangalore-59, Karnataka, India) (Department of ISE, RVCE, Visvesvaraya Technological University, Bangalore-59, Karnataka, India) (M. Tech, Department of CSE, RVCE, Visvesvaraya Technological University, Bangalore-59, Karnataka, India) (Research Scholar, Department of CSE, RVCE, Visvesvaraya Technological University, Bangalore-59, Karnataka, India)" 36b322095bd0953d6076096111e4a020f427793b,Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation Thomas Brox, Jitendra Malik, Fellow, IEEE" 36b2aa7248152fdad7bc7f670d0b577c9728d466,Data-dependent Initializations of Convolutional Neural Networks,"Under review as a conference paper at ICLR 2016 DATA-DEPENDENT INITIALIZATIONS OF CONVOLUTIONAL NEURAL NETWORKS Philipp Kr¨ahenb¨uhl1, Carl Doersch1,2, Jeff Donahue1, Trevor Darrell1 Department of Electrical Engineering and Computer Science, UC Berkeley Machine Learning Department, Carnegie Mellon" 366595171c9f4696ec5eef7c3686114fd3f116ad,Algorithms and Representations for Visual Recognition,"Algorithms and Representations for Visual Recognition Subhransu Maji Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2012-53 http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-53.html May 1, 2012" 36918b2ef6b20ffb8cffe458c0067742500c6149,"""Look, some Green Circles!"": Learning to Quantify from Images","Proceedings of the 5th Workshop on Vision and Language, pages 75–79, Berlin, Germany, August 12 2016. c(cid:13)2016 Association for Computational Linguistics" 36119c10f75094e0568cae8256400c94546d973b,The CASIA NIR-VIS 2.0 Face Database,"The CASIA NIR-VIS 2.0 Face Database Stan Z. Li, Dong Yi, Zhen Lei and Shengcai Liao Center for Biometrics and Security Research & National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences (CASIA) szli, dyi, zlei," 36358eff7c34de64c0ce8aa42cf7c4da24bf8e93,Deep Metric Learning for Person Re-identification,"Deep Metric Learning for Person Re-Identification (Invited Paper) Dong Yi, Zhen Lei, Shengcai Liao and Stan Z. Li Center for Biometrics and Security Research & National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences (CASIA)" 73599349402bf8f0d97f51862d11d128cdba44ef,Affective analysis of videos: detecting emotional content in real-life scenarios,"Affective Analysis of Videos: Detecting Emotional Content in Real-Life Scenarios vorgelegt von Master of Science Esra Acar Celik geb. in Afyonkarahisar Von der Fakultät IV – Elektrotechnik und Informatik – der Technischen Universität Berlin zur Erlangung des akademischen Grades Doktor der Ingenieurwissenschaften – Dr.-Ing. – genehmigte Dissertation Promotionsausschuss: Vorsitzender: Berichter: Berichter: Berichter: Prof. Dr. Thomas Wiegand Prof. Dr. Dr. h.c. Sahin Albayrak Prof. Dr. Adnan Yazıcı" 73d23c0e81c39b25cc43521a8f2697912d6cff94,Detecting Adversarial Examples in Deep Networks with Adaptive Noise Reduction,"IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, MANUSCRIPT ID Detecting Adversarial Image Examples in Deep Neural Networks with Adaptive Noise Reduction Bin Liang, Hongcheng Li, Miaoqiang Su, Xirong Li, Wenchang Shi and Xiaofeng Wang" 73351b313df89572afe1332625044f7e5dd0ce06,High-level Feature Learning by Ensemble Projection for Image Classification with Limited Annotations I,"High-level Feature Learning by Ensemble Projection for Image Classification with Limited Annotations $ Dengxin Dai∗, Luc Van Gool Computer Vision Lab, ETH Z¨urich, CH-8092, Switzerland" 73704242a548e8725926762faf7333e5598d0228,Surveillance of Super-Extended Objects : Bimodal Approach,"World Academy of Science, Engineering and Technology International Journal of Mechanical and Mechatronics Engineering Vol:8, No:9, 2014 Surveillance of Super-Extended Objects: Bimodal Approach Andrey V. Timofeev, Dmitry Egorov" 732e8d8f5717f8802426e1b9debc18a8361c1782,Unimodal Probability Distributions for Deep Ordinal Classification,"Unimodal Probability Distributions for Deep Ordinal Classification Christopher Beckham 1 Christopher Pal 1" 73200504c7381c48c900894455995b9188676cd5,Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes,"Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes Zhiyuan Shi, Yongxin Yang, Timothy M. Hospedales, Tao Xiang" 734cdda4a4de2a635404e4c6b61f1b2edb3f501d,Automatic landmark point detection and tracking for human facial expressions,"Tie and Guan EURASIP Journal on Image and Video Processing 2013, 2013:8 http://jivp.eurasipjournals.com/content/2013/1/8 R ES EAR CH Open Access Automatic landmark point detection and tracking for human facial expressions Yun Tie* and Ling Guan" 73ec2d5a6b4bee0f268b793ff646330507497e38,Is an Image Worth More than a Thousand Words? On the Fine-Grain Semantic Differences between Visual and Linguistic Representations,"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2807–2817, Osaka, Japan, December 11-17 2016." 7373c4a23684e2613f441f2236ed02e3f9942dd4,Feature extraction through Binary Pattern of Phase Congruency for facial expression recognition,"This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore. Title Feature extraction through binary pattern of phase ongruency for facial expression recognition Author(s) Shojaeilangari, Seyedehsamaneh; Yau, Wei-Yun; Li, Jun; Teoh, Eam Khwang Citation Shojaeilangari, S., Yau, W. Y., Li, J., & Teoh, E. K. (2012). Feature extraction through binary pattern of phase congruency for facial expression recognition. 12th International Conference on Control Automation Robotics & Vision (ICARCV), 166-170. http://hdl.handle.net/10220/18012 Rights © 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or" 73a4fe5072a30c132e8a0a18384caae4c112f198,What is typical is good: the influence of face typicality on perceived trustworthiness.,"554955 PSSXXX10.1177/0956797614554955Sofer et al.What Is Typical Is Good research-article2014 Research Article What Is Typical Is Good: The Influence of Face Typicality on Perceived Trustworthiness 015, Vol. 26(1) 39 –47 © The Author(s) 2014 Reprints and permissions: sagepub.com/journalsPermissions.nav DOI: 10.1177/0956797614554955 pss.sagepub.com Carmel Sofer1,2, Ron Dotsch2,3, Daniel H. J. Wigboldus2, and Alexander Todorov1,2 Department of Psychology, Princeton University; 2Behavioural Science Institute, Radboud University Nijmegen; and 3Department of Psychology, Utrecht University" 73bbbfac7b144f835840fe7f7b5139283bf4f3f1,Do we spontaneously form stable trustworthiness impressions from facial appearance?,"ATTITUDES AND SOCIAL COGNITION Do We Spontaneously Form Stable Trustworthiness Impressions From Facial Appearance? André Klapper Radboud University Ron Dotsch Utrecht University and Radboud University Iris van Rooij and Daniël H. J. Wigboldus Radboud University It is widely assumed among psychologists that people spontaneously form trustworthiness impressions of newly encountered people from their facial appearance. However, most existing studies directly or indirectly induced an impression formation goal, which means that the existing empirical support for spontaneous facial trustworthiness impressions remains insufficient. In particular, it remains an open question whether trustworthiness from facial appearance is encoded in memory. Using the ‘who said what’ paradigm, we indirectly measured to what extent people encoded the trustworthiness of observed faces. The results of 4 studies demonstrated a reliable tendency toward trustworthiness encoding. This was shown under conditions of varying context-relevance, and salience of trustworthiness. Moreover, evidence for this tendency was obtained using both (experimentally controlled) artificial and (naturalistic varying) real faces. Taken together, these results suggest that there is a spontaneous tendency to form relatively stable trustworthiness impressions from facial appearance, which is relatively independent of" 7306d42ca158d40436cc5167e651d7ebfa6b89c1,Transductive Zero-Shot Action Recognition by Word-Vector Embedding,"Noname manuscript No. (will be inserted by the editor) Transductive Zero-Shot Action Recognition by Word-Vector Embedding Xun Xu · Timothy Hospedales · Shaogang Gong Received: date / Accepted: date" 73be334ecc48751269443b0db2629086125e69f5,Robust Face Recognition under Difficult Lighting Conditions,"International Journal of Technological Exploration and Learning (IJTEL) Volume 1 Issue 1 (August 2012) Robust Face Recognition under Difficult Lighting Conditions S.S. Ghatge1,V.V. Dixit2 Department of Electronics &Telecomunication1, 2 Sinhgad College of Engineering1, 2 University of Pune, India1, 2" 73390af668a6c9662d15cdf84b2ddefaa3f7826f,FACE TRACKING FOR A SYSTEM OF COLLECTING STATISTICS ON VISITORS AND QUALITY ASSESSMENT OF ITS FUNCTIONING,"Journal of Theoretical and Applied Information Technology 31st January 2015. Vol.71 No.3 © 2005 - 2015 JATIT & LLS. All rights reserved. ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 FACE TRACKING FOR A SYSTEM OF COLLECTING STATISTICS ON VISITORS AND QUALITY ASSESSMENT OF ITS FUNCTIONING A.S.SAMOYLOV, D.M.MIKHAYLOV, P.E.MININ, A.D.EGOROV Engineering Centre of the National Research Nuclear University MEPhI (Moscow Engineering Physics Institute), Kashirskoye Highway 31, 115409, Moscow, Russian Federation E-mail: , , ," 738d5a6491ae0fef5d2debc17f951534061cf6f8,Advances in Learning Visual Saliency: From Image Primitives to Semantic Contents,"Chapter 14 Advances in Learning Visual Saliency: From Image Primitives to Semantic Contents Qi Zhao and Christof Koch" 73713880d4d1ec4c8f4608a94f67ea9e9f9a97a5,Visual query attributes suggestion,"Visual Query Attributes Suggestion Jingwen Bian National University of Singapore, Singapore Zheng-Jun Zha National University of Singapore, Singapore Hanwang Zhang National University of Singapore, Singapore Qi Tian University of Texas at San Antonio, USA" 73ed64803d6f2c49f01cffef8e6be8fc9b5273b8,Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos,"Noname manuscript No. (will be inserted by the editor) Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos Hilde Kuehne · Juergen Gall · Thomas Serre Received: date / Accepted: date" 73c13ba142588f45aaa92805fe75ca2691ac981b,A Comparative Study of Social Scene Parsing Strategies between Children with and without Autism Spectrum Disorder,"96 Jul 2016 Vol 9 No.3 North American Journal of Medicine and Science Original Research A Comparative Study of Social Scene Parsing Strategies between Children with and without Autism Spectrum Disorder Chen Song;1 Aosen Wang;1 Kathy Ralabate Doody, PhD;2* Michelle Hartley- McAndrew, MD;3 Jana Mertz, MBA;4 Feng Lin, PhD;1 Wenyao Xu, PhD1 Computer Science and Engineering, SUNY, University at Buffalo, Buffalo NY Exceptional Education, SUNY, Buffalo State, Buffalo, NY Jacobs School of Medicine and Biomedical Sciences, SUNY, University at Buffalo Women and Children's Hospital of Buffalo, Buffalo, NY Children’s Guild Foundation Autism Spectrum Disorder Center, Women and Children’s Hospital of Buffalo, Buffalo, NY Autism spectrum disorder (ASD) is a complex developmental disability characterized by deficits in social interaction. Gaze behavior is of great interest because it reveals the parsing strategy the participant uses to chieve social content. The legacy features in gaze fixation, such as time and area-of-interest, however, cannot omprehensively reveal the way the participant may cognize the social scene. In this work, we investigate the dynamic components within the gaze behavior of children with ASD upon the carefully-selected social scene. A cohort of child participants (n = 51) were recruited between 2 and 10 years. The results suggest significant differences in the social scene parsing strategies of children with ASD, giving added insight into the way they may decode and interpret the social scenarios. [N A J Med Sci. 2016;9(3):96-103. DOI: 10.7156/najms.2016.0903096]" 73d57e2c855c39b4ff06f2d7394ab4ea35f597d4,First Order Generative Adversarial Networks,"First Order Generative Adversarial Networks Calvin Seward 1 2 Thomas Unterthiner 2 Urs Bergmann 1 Nikolay Jetchev 1 Sepp Hochreiter 2" 73fbdd57270b9f91f2e24989178e264f2d2eb7ae,Kernel linear regression for low resolution face recognition under variable illumination,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 73c72161969a070b3caa40d4f075ba501a1b994b,Expression-Invariant 3D Face Recognition Using Patched Geodesic Texture Transform,"Expression-Invariant 3D Face Recognition using Patched Geodesic Texture Transform Author Hajati, Farshid, Raie, Abolghasem, Gao, Yongsheng Published Conference Title Proceedings 2010 Digital Image Computing: Techniques and Applications DICTA 2010 https://doi.org/10.1109/DICTA.2010.52 Copyright Statement © 2010 IEEE. Personal use of this material is permitted. However, permission to reprint/ republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Downloaded from http://hdl.handle.net/10072/37733 Link to published version http://dicta2010.conference.nicta.com.au/ Griffith Research Online https://research-repository.griffith.edu.au" 73c9cbbf3f9cea1bc7dce98fce429bf0616a1a8c,Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings,"imagesViewpoint factorizationLearned landmarksFigure1.Wepresentanovelmethodthatcanlearnviewpointin-variantlandmarkswithoutanysupervision.Themethodusesaprocessofviewpointfactorizationwhichlearnsadeeplandmarkdetectorcompatiblewithimagedeformations.Itcanbeappliedtorigidanddeformableobjectsandobjectcategories.terns.Achievingadeeperunderstandingofobjectsrequiresmodelingtheirintrinsicviewpoint-independentstructure.Oftenthisstructureisdefinedmanuallybyspecifyingen-titiessuchaslandmarks,parts,andskeletons.Givensuffi-cientmanualannotations,itispossibletoteachdeepneuralnetworksandothermodelstorecognizesuchstructuresinimages.However,theproblemoflearningsuchstructureswithoutmanualsupervisionremainslargelyopen.Inthispaper,wecontributeanewapproachtolearnviewpoint-independentrepresentationsofobjectsfromim-ageswithoutmanualsupervision(fig.1).Weformulatethistaskasafactorizationproblem,wheretheeffectsofimagedeformations,forexamplearisingfromaviewpointchange,areexplainedbythemotionofareferenceframeattachedtotheobjectandindependentoftheviewpoint.Afterdescribingthegeneralprinciple(sec.3.1),wein-1" 73866bdb723841da93b6ad93afe3d72817e2b377,Dense and Low-Rank Gaussian CRFs Using Deep Embeddings,"Dense and Low-Rank Gaussian CRFs Using Deep Embeddings Siddhartha Chandra1 Nicolas Usunier2 Iasonas Kokkinos2 INRIA GALEN, CentraleSup´elec Facebook AI Research, Paris" 73052a2bf7b41b7be2447fadc13c29be1d994708,"Pedestrian tracking using probability fields and a movement feature space Publicación científica Negri ,","Pedestrian tracking using probability fields and a movement feature space 1 Pablo Negri a & Damián Garayalde b Universidad Argentina de la Empresa (UADE). CONICET. Buenos Aires, Argentina. Instituto Tecnológico de Buenos Aires (ITBA), Buenos Aires, Argentina. Received: April 18th, 2016. Received in revised form: November 1rd, 2016. Accepted: December 2nd, 2016." 73a7ccf0facccd8943f7e54d19478f2bef9b7dab,Number 16,"Number 16 {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 132 Number 16 Year of Publication: 2015 Authors: Pronaya Prosun Das, Taskeed Jabid, S.M. Shariar Mahamud 10.5120/ijca2015907690 {bibtex}2015907690.bib{/bibtex}" 73d8fafee6be9d4fa789ece2192f259199f00e60,Face Recognition Using Radon Transform and Factorial Discriminant Analysis ( FDA ),"Volume 3, Issue 7, July 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com D Face Recognition Using Radon Transform and Factorial Discriminant Analysis (FDA) P. S. Hiremath , Manjunatha Hiremath Department of Computer Science Gulbarga University, Gulbarga-585106 Karnataka, India." 731840289e35c61c6e21ae18f2da2751bd8e2f20,Event-related potential (ERP) correlates of face processing in verbal children with autism spectrum disorders (ASD) and their first-degree relatives: a family study,"Sysoeva et al. Molecular Autism (2018) 9:41 https://doi.org/10.1186/s13229-018-0220-x Open Access R ES EAR CH Event-related potential (ERP) correlates of face processing in verbal children with utism spectrum disorders (ASD) and their first-degree relatives: a family study Olga V. Sysoeva1,2, John N. Constantino1* nd Andrey P. Anokhin1" 3e08d000ba3dd382c16e4295435ef8264235ccbc,Multiple People Tracking in Smart Camera Networks by Greedy Joint-Likelihood Maximization, 3ed186b4337f48e263ef60acffb49f16d5a85511,Discriminatively learned filter bank for acoustic features,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 3e2588aaa719c63e48fe599a7f0dbea10a41b4eb,Using Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledge,"Using sparse semantic embeddings learned from multimodal text and image data to model human conceptual knowledge Steven Derby1 Paul Miller1 Brian Murphy1,2 Barry Devereux1 Queen’s University Belfast, Belfast, United Kingdom {sderby02, p.miller, brian.murphy, BrainWaveBank Ltd., Belfast, United Kingdom" 3ea8d289313b0fe14031ea0d29f517f92a3b0fd3,Probability-based Detection Quality (PDQ): A Probabilistic Approach to Detection Evaluation,"Probability-based Detection Quality (PDQ): A Probabilistic Approach to Detection Evaluation David Hall1,2, Feras Dayoub1,2, John Skinner1,2, Peter Corke1,2, Gustavo Carneiro1,3, Niko S¨underhauf1,2 Australian Centre for Robotic Vision Queensland University of Technology (QUT), 3University of Adelaide {d20.hall, feras.dayoub, j6.skinner, peter.corke," 3ec0d2c66ba2f00d90470c03969372e610986833,EEG Data of Face Recognition in Case of Biological Compatible Changes: A Pilot Study on Healthy People, 3ede3ed28329bf48fbd06438a69c4f855bef003f,Large-scale geo-facial image analysis,"Islam et al. EURASIP Journal on Image and Video Processing (2015) 2015:17 DOI 10.1186/s13640-015-0070-9 RESEARCH Open Access Large-scale geo-facial image analysis Mohammad T. Islam1, Connor Greenwell1, Richard Souvenir2 and Nathan Jacobs1*" 3e50e351687779c05390daf117f0394d1556cd3c,Die Detektion interessanter Objekte unter Verwendung eines objektbasierten Aufmerksamkeitsmodells,"Die Detektion interessanter Objekte unter Verwendung eines objektbasierten Aufmerksamkeitsmodells Dissertation zur Erlangung des Grades eines D o k t o r s d e r I n g e n i e u r w i s s e n s c h a f t e n der Technischen Universit¨at Dortmund n der Fakult¨at f¨ur Informatik Fabian Naße Dortmund" 3e67058c6ddd0afae692b7665f82124945ea2c5a,On the Learning of Deep Local Features for Robust Face Spoofing Detection,"On the Learning of Deep Local Features for Robust Face Spoofing Detection Gustavo Botelho de Souza1, Jo˜ao Paulo Papa2 and Aparecido Nilceu Marana2 - in Proc. of SIBGRAPI 2018 UFSCar - Federal University of S˜ao Carlos. Rod. Washington Lu´ıs, Km 235. S˜ao Carlos (SP), Brazil. 13565-905. UNESP - S˜ao Paulo State University. Av. Eng. Luiz Edmundo Carrijo Coube, 14-01. Bauru (SP), Brazil. 17033-360. E-mail: {papa," 3e687d5ace90c407186602de1a7727167461194a,Photo Tagging by Collection-Aware People Recognition,"Photo Tagging by Collection-Aware People Recognition Cristina Nader Vasconcelos Vinicius Jardim Asla S´a Paulo Cezar Carvalho" 3ea8a6dc79d79319f7ad90d663558c664cf298d4,Automatic Facial Expression Recognition from Video Sequences Using Temporal Information Table of Contents,"(cid:13) Copyright by Ira Cohen, 2000" 3ee4076041fe2412d50e84d6778a974d997d8660,FACE RECOGNITION BASED ON OPTIMAL KERNEL MINIMAX PROBABILITY MACHINE,"Journal of Theoretical and Applied Information Technology 28th February 2013. Vol. 48 No.3 © 2005 - 2013 JATIT & LLS. All rights reserved. ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 FACE RECOGNITION BASED ON OPTIMAL KERNEL MINIMAX PROBABILITY MACHINE School of Information Science and Engineering, Henan University of Technology, Zhengzhou China ZHIQIANG ZHOU, 2ZIQIANG WANG, 3XIA SUN E-mail:" 3e0a12352fe3e9fb9246ee0f81ff7fbf0600f818,Facial Surface Analysis using Iso-Geodesic Curves in Three Dimensional Face Recognition System,"Facial Surface Analysis using Iso-Geodesic Curves in Three Dimensional Face Recognition System Rachid AHDID, El Mahdi BARRAH, Said SAFI and Bouzid MANAUT" 3e4bd583795875c6550026fc02fb111daee763b4,Convolutional Sketch Inversion,"Convolutional Sketch Inversion Ya˘gmur G¨u¸cl¨ut¨urk∗, Umut G¨u¸cl¨u∗, Rob van Lier, and Marcel A. J. van Gerven Radboud University, Donders Institute for Brain, Cognition and Behaviour, Nijmegen, the Netherlands Figure 1: Example results of our convolutional sketch inversion models. Our models invert face sketches to synthesize photorealistic face images. Each row shows the sketch inversion / photo synthesis pipeline that transforms a different sketch of the same face to a different image of the same face via a different deep neural network. Each deep neural network layer is represented by the top three principal components of its feature maps." 3e4ec7bdd279573d328a26b720854894e68230ed,Efficient Relative Attribute Learning Using Graph Neural Networks,"Ef‌f‌icient Relative Attribute Learning using Graph Neural Networks Zihang Meng1, Nagesh Adluru1, Hyunwoo J. Kim1⋆, Glenn Fung2, and Vikas Singh1 University of Wisconsin – Madison American Family Insurance" 3e4f84ce00027723bdfdb21156c9003168bc1c80,A co-training approach to automatic face recognition,"© EURASIP, 2011 - ISSN 2076-1465 9th European Signal Processing Conference (EUSIPCO 2011) INTRODUCTION" 3e685704b140180d48142d1727080d2fb9e52163,Single Image Action Recognition by Predicting Space-Time Saliency,"Single Image Action Recognition by Predicting Space-Time Saliency Marjaneh Safaei and Hassan Foroosh" 3e0db33884ca8c756b26dc0df85c498c18d5f2ec,Exploiting pedestrian interaction via global optimization and social behaviors,"Exploiting pedestrian interaction via global optimization nd social behaviors Laura Leal-Taix´e, Gerard Pons-Moll, and Bodo Rosenhahn Leibniz Universit¨at Hannover, Appelstr. 9A, Hannover, Germany" 3e04feb0b6392f94554f6d18e24fadba1a28b65f,14 Subspace Image Representation for Facial Expression Analysis and Face Recognition and its Relation to the Human Visual System,"Subspace Image Representation for Facial Expression Analysis and Face Recognition nd its Relation to the Human Visual System Ioan Buciu1,2 and Ioannis Pitas1 Department of Informatics, Aristotle University of Thessaloniki GR-541 24, Thessaloniki, Box 451, Greece. Electronics Department, Faculty of Electrical Engineering and Information Technology, University of Oradea 410087, Universitatii 1, Romania. Summary. Two main theories exist with respect to face encoding and representa- tion in the human visual system (HVS). The first one refers to the dense (holistic) representation of the face, where faces have “holon”-like appearance. The second one laims that a more appropriate face representation is given by a sparse code, where only a small fraction of the neural cells corresponding to face encoding is activated. Theoretical and experimental evidence suggest that the HVS performs face analysis (encoding, storing, face recognition, facial expression recognition) in a structured nd hierarchical way, where both representations have their own contribution and goal. According to neuropsychological experiments, it seems that encoding for face recognition, relies on holistic image representation, while a sparse image represen- tation is used for facial expression analysis and classification. From the computer vision perspective, the techniques developed for automatic face and facial expres-" 3e0415f0e8c36f20042d6a1f8b7c216fb5543c3a,RGB-D Segmentation of Poultry Entrails,"Aalborg Universitet RGB-D Segmentation of Poultry Entrails Philipsen, Mark Philip; Jørgensen, Anders; Guerrero, Sergio Escalera; Moeslund, Thomas B. Published in: IX International Conference on Articulated Motion and Deformable Objects DOI (link to publication from Publisher): 0.1007/978-3-319-41778-3_17 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Philipsen, M. P., Jørgensen, A., Guerrero, S. E., & Moeslund, T. B. (2016). RGB-D Segmentation of Poultry Entrails. In IX International Conference on Articulated Motion and Deformable Objects (pp. 168-174). Springer. Lecture Notes in Computer Science, Vol.. 9756, DOI: 10.1007/978-3-319-41778-3_17 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain" 3e3f305dac4fbb813e60ac778d6929012b4b745a,Feature sampling and partitioning for visual vocabulary generation on large action classification datasets.,"Feature sampling and partitioning for visual vocabulary generation on large action classification datasets. Michael Sapienza1, Fabio Cuzzolin1, and Philip H.S. Torr2 Department of Computing and Communications Technology, Oxford Brookes University. Department of Engineering Science, University of Oxford." 3eec9e8d5051e84624ea7e009a8947403dee99d1,"Material Recognition Meets 3D Reconstruction: Novel Tools for Efficient, Automatic Acquisition Systems","Material Recognition Meets 3D Reconstruction: Novel Tools for Efficient, Automatic Acquisition Systems Dissertation Erlangung des Doktorgrades (Dr. rer. nat.) Mathematisch-Naturwissenschaftlichen Fakultät der Rheinischen Friedrich-Wilhelms-Universität Bonn vorgelegt von Dipl.-Ing. Michael Weinmann us Karlsruhe Bonn, Dezember 2015" 3e309126c78261f242d21826bfac37412f5437cd,Attribute CNNs for Word Spotting in Handwritten,"International Journal on Document Analysis and Recognition manuscript No. (will be inserted by the editor) Attribute CNNs for Word Spotting in Handwritten Documents Sebastian Sudholt · Gernot A. Fink Received: date / Accepted: date" 3e63e93b46a403f4bdbf3f7e497dc53c23b6824c,Elastic appearance models,"HANSEN ET AL.: ELASTIC APPEARANCE MODELS Elastic Appearance Models Mads Fogtmann Hansen http://www.imm.dtu.dk/~mfh Jens Fagertun http://www.imm.dtu.dk/~jenf Rasmus Larsen http://www.imm.dtu.dk/~rl DTU Informatic Technical University of Denmark Kgs. Lyngby, Denmark" 3e30c59cfdf9ce2c89481d81912e179a9bd6cbee,Boosting Shape Classifiers Accuracy by Considering the Inverse Shape,"Journal of Pattern Recognition Research ??? (2016) 1-14 Boosting Shape Classifiers Accuracy by Considering the Inverse Shape Sébastien Piérard and Antoine Lejeune and Marc Van Droogenbroeck {Sebastien.Pierard, Antoine.Lejeune, INTELSIG Laboratory, Montefiore Institute, University of Liège, Belgium Received ???. Received in revised form ???. Accepted ???." 3e3ba138edbcf594cd0479ac2cddd5a8e3ee6a18,Edge detection for facial expression recognition,"Edge Detection for Facial Expression Recognition Jesús García-Ramírez, Ivan Olmos-Pineda, J. Arturo Olvera-López, Manuel Martín Ortíz Faculty of Computer Science, Benemérita Universidad Autónoma de Puebla, Av. San Claudio olvera, y 14 sur. Puebla, Pue. C.P. 72570, México" 3edf3a996790fef8957e21c68ddf48b52238e662,Product of tracking experts for visual tracking of surgical tools,"Product of Tracking Experts for Visual Tracking of Surgical Tools Suren Kumar, Madusudanan Sathia Narayanan, Pankaj Singhal, Jason J. Corso and Venkat Krovi State University of New York (SUNY) at Buffalo" 3e4a54adb53d69984bb1e113eb1a8184be4abe99,Person Authentication from Video of Faces: A Behavioral and Physiological Approach Using Pseudo Hierarchical Hidden Markov Models,"Person Authentication from Video of Faces: A Behavioral and Physiological Approach Using Pseudo Hierarchical Hidden Markov Models Manuele Bicego1, Enrico Grosso1, and Massimo Tistarelli2 DEIR - University of Sassari, via Torre Tonda 34 - 07100 Sassari - Italy DAP - University of Sassari, piazza Duomo 6 - 07041 Alghero (SS) - Italy" 3edb0fa2d6b0f1984e8e2c523c558cb026b2a983,Automatic Age Estimation Based on Facial Aging Patterns,"Automatic Age Estimation Based on Facial Aging Patterns Xin Geng, Zhi-Hua Zhou, Senior Member, IEEE, Kate Smith-Miles, Senior Member, IEEE" 3e5ba104e9fce5d57751d4314cf32118398d1f22,MODNet: Moving Object Detection Network with Motion and Appearance for Autonomous Driving,"MODNet: Motion and Appearance based Moving Object Detection Network for Autonomous Driving Mennatullah Siam, Heba Mahgoub, Mohamed Zahran, Senthil Yogamani, Martin Jagersand" 3e6b70e5be3dbe688866d8dd4382ce05b201fd28,Evaluation of Face Recognition Techniques,"PIAGENG 2009: Image Processing and Photonics for Agricultural Engineering, edited by Honghua Tan, Qi Luo, Proc. of SPIE Vol. 7489, 74890M · © 2009 SPIE · CCC code: 0277-786X/09/$18 · doi: 10.1117/12.836686 Proc. of SPIE Vol. 7489 74890M-1 Downloaded from SPIE Digital Library on 24 Jan 2010 to 130.194.78.137. Terms of Use: http://spiedl.org/terms" 3e9d04b62d3469fb155e02c1f30b8900381e1419,"Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV","FAST AND ACCURATE, CONVOLUTIONAL NEURAL NETWORK BASED APPROACH FOR OBJECT DETECTION FROM UAV Xiaoliang Wang Department of Technology College of Engineering and Technology Virginia State University Petersburg, VA, USA Peng Cheng Department of Technology College of Engineering and Technology Virginia State University Petersburg, VA, USA Xinchuan Liu Department of Technology College of Engineering and Technology Virginia State University" 3e4acf3f2d112fc6516abcdddbe9e17d839f5d9b,Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs,"Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs Michael Gygli 1 * Mohammad Norouzi 2 Anelia Angelova 2" 3eff18934f5870b27f80c8b1d7104967460e3035,Driver hand localization and grasp analysis: A vision-based real-time approach, 3e18b439a6fff09a0e4c245eb1298531cc766a72,"Semi-automatic Face Image Finding Method , Which Uses the 3 D Model of the Head for Recognising an Unknown Face","Technologies of Computer Control doi: 10.7250/tcc.2015.001 ______________________________________________________________________________________________ 2015 / 16 Semi-automatic Face Image Finding Method, Which Uses the 3D Model of the Head for Recognising an Olga Krutikova1, Aleksandrs Glazs2 , 2 Riga Technical University" 3efb04937f6d87ab9540700e04d8133102c67bc0,Ask Your Neurons: A Deep Learning Approach to Visual Question Answering,"myjournal Ask Your Neurons: A Deep Learning Approach to Visual Question Answering Mateusz Malinowski · Marcus Rohrbach · Mario Fritz Received: date / Accepted: date" 3e93e41ccd22596ca478f336727f6340b12e7572,LEARNING PHYSICAL DYNAMICS,"Published as a conference paper at ICLR 2017 A COMPOSITIONAL OBJECT-BASED APPROACH TO LEARNING PHYSICAL DYNAMICS Michael B. Chang*, Tomer Ullman**, Antonio Torralba*, and Joshua B. Tenenbaum** *Department of Electrical Engineering and Computer Science, MIT **Department of Brain and Cognitive Sciences, MIT" 3ee522805e16bf7816ec4abfaf0c7648b5cb5c95,From Numerical Sensor Data to Semantic Representations :,"From Numerical Sensor Data to Semantic Representations: A Data-driven Approach for Generating Linguistic Descriptions Hadi Banaee Akademisk avhandling Avhandling för filosofie doktorsexamen i datavetenskap, som kommer att försvaras offentligt fredag den 20 april 2018 kl. 13.15, Hörsal T, Örebro universitet, Örebro Opponent: Prof. Antonio Chella University of Palermo Italy Örebro universitet Institutionen för Naturvetenskap och Teknik 701 82 Örebro" 3e3ce21b1ef9e4c7199522d2c923e3771dbae930,EXT . ZIP : C OMPRESSING TEXT CLASSIFICATION MODELS,"Under review as a conference paper at ICLR 2017 FASTTEXT.ZIP: COMPRESSING TEXT CLASSIFICATION MODELS Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Herv´e J´egou & Tomas Mikolov Facebook AI Research" 3e8de2f904dea8368477daebab0c0dc97e0229f4,Detection and Classification of Vehicles from Omnidirectional Videos using Temporal Average of Silhouettes,"Detection and Classification of Vehicles from Omnidirectional Videos using Temporal Average of Silhouettes Computer Vision Research Group, Department of Computer Engineering, Izmir Institute of Technology, 35430, Hakki Can Karaimer and Yalin Bastanlar Izmir, Turkey {cankaraimer, Keywords: Omnidirectional Camera, Omnidirectional Video, Object Detection, Vehicle Detection, Vehicle Classification." 3efea06ad6398f9db07acf34479c81a99479e80b,Localizing Moments in Video with Natural Language,"Localizing Moments in Video with Natural Language Lisa Anne Hendricks1 , Oliver Wang2, Eli Shechtman2, Josef Sivic2 , Trevor Darrell1, Bryan Russell2 UC Berkeley, 2Adobe Research, 3INRIA https://people.eecs.berkeley.edu/˜lisa_anne/didemo.html Figure 1: We consider localizing moments in video with natural language and demonstrate that incorporating local and global video features is important for this task. To train and evaluate our model, we collect the Distinct Describable Moments (DiDeMo) dataset which consists of over 40,000 pairs of localized video moments and corresponding natural language." 3e7b5b07da3465103929b4347852d456c0f0ed58,Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey,"Video Processing from Electro-optical Sensors for Object Detection and Tracking in Maritime Environment: A Survey Dilip K. Prasad1,∗, Deepu Rajan2, Lily Rachmawati3, Eshan Rajabally4, and Chai Quek2" 3e56a9b6c6aced2cb14f9cd7f89d145851c44113,Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning,"Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning Zhiwu Lu, Jiechao Guan, Aoxue Li, Tao Xiang, An Zhao, and Ji-Rong Wen" 08ff3e9f5ad47e59592ad993348b817003b9c0e4,A Sequential Classifier for Hand Detection in the Framework of Egocentric Vision,"A Sequential Classifier for Hand Detection in the Framework of Egocentric Vision Alejandro Betancourt1,2 Miriam M. L´opez1 Carlo S. Regazzoni1 Matthias Rauterberg2 Department of Naval, Electric, Electronic and Telecommunications Engineering - University of Genoa, Italy Designed Intelligence Group, Department of Industrial Design - Eindhoven University of Technology, The Netherlands" 08f6745bc6c1b0fb68953ea61054bdcdde6d2fc7,Understanding Kin Relationships in a Photo,"Understanding Kin Relationships in a Photo Siyu Xia, Ming Shao, Student Member, IEEE, Jiebo Luo, Fellow, IEEE, and Yun Fu, Senior Member, IEEE" 0857281a3b6a5faba1405e2c11f4e17191d3824d,Face recognition via edge-based Gabor feature representation for plastic surgery-altered images,"Chude-Olisah et al. EURASIP Journal on Advances in Signal Processing 2014, 2014:102 http://asp.eurasipjournals.com/content/2014/1/102 R ES EAR CH Face recognition via edge-based Gabor feature representation for plastic surgery-altered images Chollette C Chude-Olisah1*, Ghazali Sulong1, Uche A K Chude-Okonkwo2 and Siti Z M Hashim1 Open Access" 08903bf161a1e8dec29250a752ce9e2a508a711c,Joint Dimensionality Reduction and Metric Learning: A Geometric Take,"Joint Dimensionality Reduction and Metric Learning: A Geometric Take Mehrtash Harandi 1 2 Mathieu Salzmann 3 Richard Hartley 2 1" 084f1a6c62a3464b1a9b745fee40af2895920301,Capitalize on dimensionality increasing techniques for improving face recognition grand challenge performance,"Capitalize on Dimensionality Increasing Techniques for Improving Face Recognition Grand Challenge Performance Chengjun Liu" 085ba9f82e15603f1fe2a29dfa0182d46465a591,Face Recognition In Presence Of Occlusion Using Machine Learning Classifier Vandana,"International Journal of Science, Engineering and Technology Research (IJSETR), Volume 3, Issue 4, April 2014 Face Recognition In Presence Of Occlusion Using Machine Learning Classifier Vandana P, Manjunath C N chieve" 083a2bc86e0984968b06593ba06654277b252f00,Neural evidence for the contribution of holistic processing but not attention allocation to the other-race effect on face memory.,"Cognitive, Affective, & Behavioral Neuroscience (2018) 18:1015–1033 https://doi.org/10.3758/s13415-018-0619-z Neural evidence for the contribution of holistic processing but not ttention allocation to the other-race effect on face memory Grit Herzmann 1 & Greta Minor 1 & Tim Curran 2 Published online: 25 June 2018 # Psychonomic Society, Inc. 2018" 08ff81f3f00f8f68b8abd910248b25a126a4dfa4,Symmetric Subspace Learning for Image Analysis,"Papachristou, K., Tefas, A., & Pitas, I. (2014). Symmetric Subspace Learning 5697. DOI: 10.1109/TIP.2014.2367321 Peer reviewed version Link to published version (if available): 0.1109/TIP.2014.2367321 Link to publication record in Explore Bristol Research PDF-document This is the author accepted manuscript (AAM). The final published version (version of record) is available online via Institute of Electrical and Electronic Engineers at http://dx.doi.org/10.1109/TIP.2014.2367321. Please refer to ny applicable terms of use of the publisher. University of Bristol - Explore Bristol Research General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: http://www.bristol.ac.uk/pure/about/ebr-terms" 088aabe3da627432fdccf5077969e3f6402f0a80,CLASSIFIER-TO-GENERATOR ATTACK: ESTIMATION,"Under review as a conference paper at ICLR 2018 CLASSIFIER-TO-GENERATOR ATTACK: ESTIMATION OF TRAINING DATA DISTRIBUTION FROM CLASSIFIER Anonymous authors Paper under double-blind review" 08f46d6a91e513edd57a0ef15d5367b5d0545c1b,"How do targets, nontargets, and scene context influence real-world object detection?","Atten Percept Psychophys DOI 10.3758/s13414-017-1359-9 How do targets, nontargets, and scene context influence real-world object detection? Harish Katti 1 & Marius V. Peelen 2 & S. P. Arun 1 # The Psychonomic Society, Inc. 2017" 08b76e6923eea74ab0ed149811b3144fa21c7c73,Scalable Laplacian K-modes,"Scalable Laplacian K-modes Imtiaz Masud Ziko ∗ ÉTS Montreal Eric Granger ÉTS Montreal Ismail Ben Ayed ÉTS Montreal" 08030f9d34cc96384f672d9f9f296914d594335b,Multiple Object Tracking: A Review,"Multiple Object Tracking: A Literature Review Wenhan Luo, Junliang Xing, Anton Milan, Xiaoqin Zhang, Wei Liu, Xiaowei Zhao and Tae-Kyun Kim" 0861f86fb65aa915fbfbe918b28aabf31ffba364,An Efficient Facial Annotation with Machine Learning Approach,"International Journal of Computer Trends and Technology (IJCTT) – volume 22 Number 3–April 2015 An Efficient Facial Annotation with Machine Learning Approach A.Anusha,2R.Srinivas Final M.Tech Student, 2Associate Professor ,2Dept of CSE ,Aditya Institute of Technology And Management, Tekkali, Srikakulam , Andhra Pradesh" 0816cbac9ea8f4425d9b57fd46174cb35cd5d7cc,People tracking in RGB-D data with on-line boosted target models,"People Tracking in RGB-D Data With On-line Boosted Target Models Matthias Luber Luciano Spinello Kai O. Arras" 0856622ce2fcc4e39fd396427abae90cddf78fd0,Abnormal activation of the social brain during face perception in autism.,"Abnormal Activation of the Social Brain During Face Perception in Autism Nouchine Hadjikhani,1,2* Robert M. Joseph,3 Josh Snyder,1 nd Helen Tager-Flusberg3 Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Division of Health Sciences and Technology, Harvard-Massachusetts Institute of Technology, Harvard Medical School, Charlestown, Massachusetts Department of Anatomy and Neurobiology, Boston University School of Medicine, Boston, Cambridge, Massachusetts Massachusetts" 08f48d8dd64328ec6c91cf0de8d19e80e65ad52c,Face recognition based on polar frequency features,"Face Recognition Based on Polar Frequency Features YOSSI ZANA1 Dept. of Computer Science – IME, University of São Paulo, São Paulo - SP, Brazil ROBERTO M. CESAR-JR Dept. of Computer Science – IME, University of São Paulo, São Paulo - SP, Brazil ________________________________________________________________________ A novel biologically motivated face recognition algorithm based on polar frequency is presented. Polar frequency descriptors are extracted from face images by Fourier-Bessel transform (FBT). Next, the Euclidean distance between all images is computed and each image is now represented by its dissimilarity to the other images. A Pseudo-Fisher Linear Discriminant was built on this dissimilarity space. The performance of Discrete Fourier transform (DFT) descriptors, and a combination of both feature types was also evaluated. The lgorithms were tested on a 40- and 1196-subjects face database (ORL and FERET, respectively). With 5 images per subject in the training and test datasets, error rate on the ORL database was 3.8, 1.25 and 0.2% for the FBT, DFT, and the combined classifier, respectively, as compared to 2.6% achieved by the best previous lgorithm. The most informative polar frequency features were concentrated at low-to-medium angular frequencies coupled to low radial frequencies. On the FERET database, where an affine normalization pre- processing was applied, the FBT algorithm outperformed only the PCA in a rank recognition test. However, it chieved performance comparable to state-of-the-art methods when evaluated by verification tests. These results indicate the high informative value of the polar frequency content of face images in relation to recognition and verification tasks, and that the Cartesian frequency content can complement information about" 08b70ab782141a2d7003226a0f438a6aea0a0d46,Parametrizing Fully Convolutional Nets,"Under review as a conference paper at ICLR 2019 PARAMETRIZING FULLY CONVOLUTIONAL NETS WITH A SINGLE HIGH-ORDER TENSOR Anonymous authors Paper under double-blind review" 0888b6904ef12bc7a3c59fa59c4051d5002de80f,Learning with Shared Information for Image and Video Analysis,"DEPARTMENT OF INFORMATION ENGINEERING AND COMPUTER SCIENCE ICT International Doctoral School LEARNING WITH SHARED INFORMATION FOR IMAGE AND VIDEO ANALYSIS Gaowen Liu Advisor Prof. Nicu Sebe Universit`a degli Studi di Trento" 08aedeb74dda306a14c699ffcef4f434a60f34e8,3d spatial layout and geometric constraints for scene understanding,(cid:13) 2011 Varsha Chandrashekhar Hedau 08d2f655361335bdd6c1c901642981e650dff5ec,Automatic Cast Listing in Feature-Length Films with Anisotropic Manifold Space,"This is the published version: Arandjelovic, Ognjen and Cipolla, R. 2006, Automatic cast listing in feature‐length films with Anisotropic Manifold Space, in CVPR 2006 : Proceedings of the Computer Vision and Pattern Recognition Conference 2006, IEEE, Piscataway, New Jersey, pp. 1513‐1520. http://hdl.handle.net/10536/DRO/DU:30058435 Reproduced with the kind permission of the copyright owner. Copyright : 2006, IEEE Available from Deakin Research Online:" 08ff22f76a567fcbc1afec6bfbf957a560cfadc7,Exploring Person Context and Local Scene Context for Object Detection.,"Exploring Person Context and Local Scene Context for Object Detection Saurabh Gupta∗ UC Berkeley Bharath Hariharan∗ Facebook AI Research Jitendra Malik UC Berkeley" 08ae1f8dea9b5ce7923db6469443f43f2c290510,Progressive sparse representation-based classification using local discrete cosine transform evaluation for image recognition,"Progressive sparse representation- ased classification using local discrete cosine transform evaluation for image recognition Xiaoning Song Zhen-Hua Feng Guosheng Hu Xibei Yang Jingyu Yang Yunsong Qi Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 02/27/2017 Terms of Use: http://spiedigitallibrary.org/ss/termsofuse.aspx" 081b6b99aabe36f8b5530163f991bae3f8015ff8,Deep Leaf Segmentation Using Synthetic Data,"Deep Leaf Segmentation Using Synthetic Daniel Ward Peyman Moghadam Nicolas Hudson Robotics and Autonomous Systems The Commonwealth Scientific and Industrial Research Organisation (CSIRO), Data61 Brisbane, Australia" 08ae100805d7406bf56226e9c3c218d3f9774d19,Predicting the Sixteen Personality Factors (16PF) of an individual by analyzing facial features,"Gavrilescu and Vizireanu EURASIP Journal on Image and Video Processing (2017) 2017:59 DOI 10.1186/s13640-017-0211-4 EURASIP Journal on Image nd Video Processing R ES EAR CH Predicting the Sixteen Personality Factors (16PF) of an individual by analyzing facial features Mihai Gavrilescu* and Nicolae Vizireanu Open Access" 08f00e5adaba03628144dbc97daefa8ceb6e5322,Machine Vision based Fruit Classification and Grading-A Review,"International Journal of Computer Applications (0975 – 8887) Volume 170 – No.9, July 2017 Machine Vision based Fruit Classification and Grading - A Review Sapan Naik Babu Madhav Institute of Information Technology Uka Tarsadia University, Bardoli, Surat, Gujarat, India." 082d339e29b1b1a9a800a1d72b401f69b6a157c5,Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval,"Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval Niluthpol Chowdhury Mithun University of California, Riverside, CA Evangelos E. Papalexakis University of California, Riverside, CA Rameswar Panda University of California, Riverside, CA Amit K. Roy-Chowdhury University of California, Riverside, CA" 0854b445973f5df79978cf4d4b031af696244ffb,Optimal Weighting of Landmarks for Face Recognition,"Optimal Weighting of Landmarks for Face Recognition Mechatronics Research Group, Department of Mechanical and Manufacturing Engineering, Rajinda S. Senaratne, and Saman K. Halgamuge The University of Melbourne, Melbourne, Australia Email:" 08847df8ea5b22c6a2d6d75352ef6270f53611de,Using k-Poselets for Detecting People and Localizing Their Keypoints,"Using k-poselets for detecting people and localizing their keypoints Georgia Gkioxari∗, Bharath Hariharan∗, Ross Girshick and Jitendra Malik University of California, Berkeley - Berkeley, CA 94720" 0834dff6e1d37ecb36137e019f8e2c933d5e74f6,Building Part-Based Object Detectors via 3D Geometry,"BUILDING PART-BASED OBJECT DETECTORS VIA 3D GEOMETRY Experimental Results Qualitative Results Input Image DPM Detection Test Set: NYU v2 RGB Images gDPM Detection Predicted Geometry Bed gDPM Model 3 Sofa gDPM Model 3 Table gDPM Model 3 Discriminative Part-based Models Supervised Parts Unsupervised Parts Key-point/part annotation, e.g., Heuristic initialization, e.g., gradient natomical. magnitudes. . Overview . Overview As input to the system, at training, we use RGB images" 08c6943a17f267ef27316cff9248b3036a7059f3,We are not contortionists: Coupled adaptive learning for head and body orientation estimation in surveillance video,"We are not Contortionists: Coupled Adaptive Learning for Head and Body Orientation Estimation in Surveillance Video Cheng Chen Jean-Marc Odobez Idiap Research Institute – CH-1920, Martigny, Switzerland (cid:3)" 089ad31ad5eef41bd179bb0a142d3386a8de5564,Continuous memories for representing sets of vectors and image collections. (Mémoires continues représentant des ensembles de vecteurs et des collections d'images),"Continuous memories for representing sets of vectors nd image collections Ahmet Iscen To cite this version: Ahmet Iscen. Continuous memories for representing sets of vectors and image collections. Com- puter Vision and Pattern Recognition [cs.CV]. Université Rennes 1, 2017. English. . HAL Id: tel-01661319 https://tel.archives-ouvertes.fr/tel-01661319 Submitted on 11 Dec 2017 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 08e24f9df3d55364290d626b23f3d42b4772efb6,Enhancing facial expression classification by information fusion,"ENHANCING FACIAL EXPRESSION CLASSIFICATION BY INFORMATION FUSION I. Buciu1, Z. Hammal 2, A. Caplier2, N. Nikolaidis 1, and I. Pitas 1 AUTH/Department of Informatics/ Aristotle University of Thessaloniki phone: + 30(2310)99.6361, fax: + 30(2310)99.8453, email: GR-54124, Thessaloniki, Box 451, Greece Laboratoire des Images et des Signaux / Institut National Polytechnique de Grenoble phone: + 33(0476)574363, fax: + 33(0476)57 47 90, email: web: http://www.aiia.csd.auth.gr 8031 Grenoble, France web: http://www.lis.inpg.fr" 08ab862450b42595be34510f8da8defcfaec3d2e,Object class recognition using multiple layer boosting with heterogeneous features,"Object Class Recognition Using Multiple Layer Boosting with Heterogeneous Features Wei Zhang1 Bing Yu1 Gregory J. Zelinsky2 Dimitris Samaras1 Dept. of Computer Science SUNY at Stony Brook Stony Brook, NY 11794 {wzhang, ybing, Dept. of Psychology SUNY at Stony Brook Stony Brook, NY 11794" 081d6ac51bbb7df142e3db6649fb5d663e90d569,Generalized zero-shot learning for action recognition with web-scale video data,"Noname manuscript No. (will be inserted by the editor) Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data Kun Liu · Wu Liu · Huadong Ma · Wenbing Huang · Xiongxiong Dong Received: date / Accepted: date" 0874a262c2ec7082658cbfc55892ec6e5ca6a374,CaTDet: Cascaded Tracked Detector for Efficient Object Detection from Video,"CATDET: CASCADED TRACKED DETECTOR FOR EFFICIENT OBJECT DETECTION FROM VIDEO Huizi Mao 1 Taeyoung Kong 1 William J. Dally 1 2" 08bdb84d5c66265b3b6d33e8f95c4cc27caf33ad,Detecting Visual Relationships Using Box Attention,"Detecting Visual Relationships Using Box Attention Alexander Kolesnikov∗ Google AI Christoph H. Lampert IST Austria Vittorio Ferrari Google AI" 081093b0b3195e3f6bfa283b49fee26b606d4f67,Object Co-detection,"Object Co-detection Sid Yingze Bao, Yu Xiang, Silvio Savarese University of Michigan at Ann Arbor, USA {yingze, yuxiang," 08b0664fd37cd434201a1b37c20c0919833a6ff1,Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering,"Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering Young-chul Yoon Abhijeet Boragule Young-min Song Kwangjin Yoon Moongu Jeon Gwangju Institute of Science and Technology 23 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, South Korea {zerometal9268, abhijeet, sym, yoon28, (cid:11)(cid:36)(cid:57)(cid:54)(cid:54)(cid:3)(cid:21)(cid:19)(cid:20)(cid:27)(cid:12) (cid:20)(cid:17)(cid:3)(cid:44)(cid:81)(cid:87)(cid:85)(cid:82)(cid:71)(cid:88)(cid:70)(cid:87)(cid:76)(cid:82)(cid:81)(cid:3)(cid:11)(cid:87)(cid:72)(cid:80)(cid:83)(cid:82)(cid:85)(cid:68)(cid:79)(cid:3)(cid:72)(cid:85)(cid:85)(cid:82)(cid:85)(cid:86)(cid:3)(cid:71)(cid:88)(cid:85)(cid:76)(cid:81)(cid:74)(cid:3)(cid:87)(cid:85)(cid:68)(cid:70)(cid:78)(cid:76)(cid:81)(cid:74)(cid:12)" 082a8642455b9a5cfb27c07cf9969106f8a7bf3c,Face recognition is similarly affected by viewpoint in school-aged children and adults,"Face recognition is similarly affected by viewpoint in school-aged children and dults Marisa Nordt and Sarah Weigelt Department of Developmental Neuropsychology, Institute of Psychology, Ruhr-Universität Bochum, Bochum, Germany" 08d40ee6e1c0060d3b706b6b627e03d4b123377a,Towards Weakly-Supervised Action Localization,"Human Action Localization with Sparse Spatial Supervision Philippe Weinzaepfel, Xavier Martin, and Cordelia Schmid, Fellow, IEEE" 080c204edff49bf85b335d3d416c5e734a861151,CLAD: A Complex and Long Activities Dataset with Rich Crowdsourced Annotations,"CLAD: A Complex and Long Activities Dataset with Rich Crowdsourced Annotations Jawad Tayyub1, Majd Hawasly2∗, David C. Hogg1 and Anthony G. Cohn1 Journal Title XX(X):1–6 (cid:13)The Author(s) 2016 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/ToBeAssigned www.sagepub.com/" 08809165154c9c557d368cddfa3ae66ccaceaed9,Taming VAEs,"Taming VAEs Danilo J. Rezende ∗ Fabio Viola ∗ {danilor, DeepMind, London, UK" 0871982db35e924506d41de97ba4d909bb727f50,Recognizing Rotated Faces from Two Orthogonal Views in Mugshot Databases,"Recognizing Rotated Faces from Two Orthogonal Views in Mugshot Databases Author Zhang, Paul, Gao, Yongsheng, Zhang, Bai-ling Published Conference Title Proceedings: The 18th International Conference of Pattern Recognition https://doi.org/10.1109/ICPR.2006.978 Copyright Statement © 2006 IEEE. Personal use of this material is permitted. However, permission to reprint/ republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Downloaded from http://hdl.handle.net/10072/13122 Griffith Research Online https://research-repository.griffith.edu.au" 08fbe3187f31b828a38811cc8dc7ca17933b91e9,Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based Recognition,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based Recognition Turaga, P.; Veeraraghavan, A.; Srivastava, A.; Chellappa, R. TR2011-084 April 2011" 085ca7f8935808986ae1c6afbbb62f6804049f26,Universität Augsburg Monocular 3d Human Pose Estimation by Classification Institut F ¨ Ur Informatik D-86135 Augsburg Monocular 3d Human Pose Estimation by Classification,"Universit¨at Augsburg Monocular 3D Human Pose Estimation y Classification T. Greif, D. Sengupta, R. Lienhart Report 2011-09 M¨arz 2011 Institut f¨ur Informatik D-86135 Augsburg" 081456e22734a2cdef442345f80182e84d1c6124,Approaches for Multi-Class Discriminant Analysis for Ranking Principal Components,"Approaches for Multi-Class Discriminant Analysis for Ranking Principal Components Tiene Andre Filisbino Laborat´orio Nacional Gilson Antonio Giraldi Laborat´orio Nacional Carlos Eduardo Thomaz Departamento de Engenharia El´etrica de Computac¸˜ao Cient´ıfica - LNCC de Computac¸˜ao Cient´ıfica - LNCC Centro Universit´ario da FEI Petr´opolis, RJ 25651-075 Email: Petr´opolis, RJ 25651-075 Email: S˜ao Bernardo do Campo, SP 09850-901 Email:" 08bbb59036c4b85a2418f9702ccd37929c5dd154,Understanding and Predicting the Memorability of Natural Scene Images,"Understanding and Predicting the Memorability of Natural Scene Images Jiaxin Lu, Mai Xu, Senior Member, IEEE, Ren Yang and Zulin Wang" 08f4832507259ded9700de81f5fd462caf0d5be8,Geometric Approach for Human Emotion Recognition using Facial Expression,"International Journal of Computer Applications (0975 – 8887) Volume 118 – No.14, May 2015 Geometric Approach for Human Emotion Recognition using Facial Expression S. S. Bavkar Assistant Professor VPCOE Baramati J. S. Rangole Assistant Professor VPCOE Baramati V. U. Deshmukh Assistant Professor VPCOE Baramati" 087337fdad69caaab8ebd8ae68a731c5bf2e8b14,Fully Convolutional Networks for Semantic Segmentation,"Fully Convolutional Networks for Semantic Segmentation Jonathan Long∗ Evan Shelhamer∗ UC Berkeley Trevor Darrell" 0875af310ab8c850b3232b3f6b84535ffff84e5d,A Novel Technique to Detect Faces in a Group Photo,"International Journal of Computer Applications (0975 – 8887) Volume 54– No.1, September 2012 A Novel Technique to Detect Faces in a Group Photo Saravanan Chandran Assistant Professor, National Institute of Technology, Durgapur, West Bengal, India." 085fce160b0fa279597bf23b518c56c735d9e7ff,Joint detection and recognition of human actions in wireless surveillance camera networks,"Joint Detection and Recognition of Human Actions in Wireless Surveillance Camera Networks Nikhil Naikal1, Pedram Lajevardi2 and Shankar. S. Sastry1" 084bd219dd239dc4c9a02621a5333d3bc1446566,DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking,"DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking Hanxi Li, Yi Li, Fatih Porikli" 82a610a59c210ff77cfdde7fd10c98067bd142da,Human attention and intent analysis using robust visual cues in a Bayesian framework,"UC San Diego UC San Diego Electronic Theses and Dissertations Title Human attention and intent analysis using robust visual cues in a Bayesian framework Permalink https://escholarship.org/uc/item/1cb8d7vw Author McCall, Joel Curtis Publication Date 006-01-01 Peer reviewed|Thesis/dissertation eScholarship.org Powered by the California Digital Library University of California" 82a2a523c4488c34b486c920046f4ebbf8ea828e,Vision-Based System for Human Detection and Tracking in Indoor Environment,"Author manuscript, published in ""International Journal of Social Robotics 2, 1 (2010) 41-52"" DOI : 10.1007/s12369-009-0040-4" 821ba3eba1e36a29cc482f5378f4a0d0f6893159,Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach,"Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach Avisek Lahiri∗ Abhinav Agarwalla Prabir Kumar Biswas Dept. of E&ECE, IIT Kharagpur Dept. of E&ECE, IIT Kharagpur Dept. of Mathematics, IIT Kharagpur" 82417d8ec8ac6406f2d55774a35af2a1b3f4b66e,Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval,"Some faces are more equal than others: Hierarchical organization for accurate and ef‌f‌icient large-scale identity-based face retrieval Binod Bhattarai1, Gaurav Sharma2, Fr´ed´eric Jurie1, Patrick P´erez2 GREYC, CNRS UMR 6072, Universit´e de Caen Basse-Normandie, France1 Technicolor, Rennes, France2" 82ec2ff0bef7db7e5ea48c42336200fb0e44dbf9,Reconstruction of 3D Human Facial Images Using Partial Differential Equations,"Reconstruction of 3D Human Facial Images Using Partial Differential Equations University of Bradford/EIMC Department, Richmond Road, BD7 1DP, Bradford, UK Email: {E.Elyan, Eyad Elyan, Hassan Ugail (PDE). Here" 828b73e8a4d539eeae82601b5f5a4392818c6430,Long-Term Tracking by Decision Making,"UNIVERSITY OF CALIFORNIA, IRVINE Long-Term Tracking by Decision Making DISSERTATION submitted in partial satisfaction of the requirements for the degree of DOCTOR OF PHILOSOPHY in Computer Science James Supanˇciˇc, III Dissertation Committee: Deva Ramanan, Chair Charless Fowlkes Alexander Ihler" 82319857563e7b578bcb66ec4df1c85decd6a624,Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure,"Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure G¨unther Reitberger, Maarten Bieshaar, Stefan Zernetsch, Konrad Doll, Bernhard Sick, and Erich Fuchs" 82a4562d9ef19aec3aeaf9bd9f0ac4e09bdf5c86,Putting Out a HIT: Crowdsourcing Malware Installs,"Putting Out a HIT: Crowdsourcing Malware Installs Chris Kanich UC San Diego Stephen Checkoway UC San Diego Keaton Mowery UC San Diego" 8285e1b5536ce11d55462ae757f61c75ec6773c6,The Frontiers of Fairness in Machine Learning,"The Frontiers of Fairness in Machine Learning Alexandra Chouldechova∗ Aaron Roth† October 23, 2018" 82fae97673a353271b1d4c001afda1af6ef6dc23,Semantic contours from inverse detectors,"Semantic Contours from Inverse Detectors∗ Bharath Hariharan1, Pablo Arbel´aez1, Lubomir Bourdev1 , Subhransu Maji1 and Jitendra Malik1 EECS, U.C. Berkeley, Berkeley, CA 94720 Adobe Systems, Inc., 345 Park Ave, San Jose, CA 95110 {bharath2, arbelaez, lbourdev, smaji," 82d5656c74362d6c5c5fd889fc48f7816bbb033a,Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias,"Contemplating Visual Emotions: Understanding nd Overcoming Dataset Bias Rameswar Panda1, Jianming Zhang2, Haoxiang Li3, Joon-Young Lee2, Xin Lu2, and Amit K. Roy-Chowdhury1 Department of ECE, UC Riverside. Adobe Research. Aibee." 8209445ce555d166580159ee18059fa41c0433cd,Real-world Object Recognition with Off-the-shelf Deep Conv Nets: How Many Objects can iCub Learn?,"Real-world Object Recognition with Off-the-shelf Deep Conv Nets: How Many Objects can iCub Learn? Giulia Pasquale ∗ Carlo Ciliberto † Francesca Odone ‡ Lorenzo Rosasco † ‡ Lorenzo Natale ∗" 82c303cf4852ad18116a2eea31e2291325bc19c3,Fusion Based FastICA Method : Facial Expression Recognition,"Journal of Image and Graphics, Volume 2, No.1, June, 2014 Fusion Based FastICA Method: Facial Expression Recognition Humayra B. Ali and David M W Powers Computer Science, Engineering and Mathematics School, Flinders University, Australia Email: {ali0041," 825bfa844e4493f205f66782c6ca68aa69018d9c,In-Place Activated BatchNorm for Memory-Optimized Training of DNNs,"In-Place Activated BatchNorm for Memory-Optimized Training of DNNs Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder Mapillary Research" 823f4300ddf64a95324db89035946638ecb02aa0,MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses,"MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses Irtiza Hasan1,2, Francesco Setti1, Theodore Tsesmelis1,2,3, Alessio Del Bue3, Fabio Galasso2, and Marco Cristani1 University of Verona (UNIVR) OSRAM GmbH Istituto Italiano di Tecnologia (IIT)" 8239e4a37825979f66ff0419ccd50a08aebfbadf,Tracing the Colors of Clothing in Paintings with Image Analysis,"Tracing the Colors of Clothing in Paintings with Image Analysis Cihan Sarı1, Albert Ali Salah2, and Alkım Almıla Akda˘g Salah3 Bo˘gazi¸ci University, Systems and Control Engineering, Bo˘gazi¸ci University, Computer Engineering, {cihan.sari, Istanbul S¸ehir University, College of Communications Introduction The history of color is full of instances of how and why certain colors become to e associated with certain concepts, ideas, politics, status and power. Sometimes the connotations occur arbitrarily, like in the instance when pink was assigned to baby girls, and blue started to be associated with baby boys at the turn of 9th Century [Paoletti, 1987]. Sometimes though, color associations have very tangible reasons, such as in the case of Marian blue and why over the centuries it was reserved only for painting Virgin Mary. The reason is to be found in the scarcity of the rock lapis lazuli -even more valuable than gold-, from which the lue pigments were extracted. Individual colors have convoluted and contested histories, since they have been attached to many symbols at any given time. John Gage, an art historian who has devoted 30 years of research on the topic of color, explains the conundrum of what he terms as “politics of color” in a" 82f6cc54ddb4df9fae811467bdf25f25985c7e2f,CNN features are also great at unsupervised classification,"CNN features are also great at unsupervised lassification Joris Guérin∗ Arts et Métiers ParisTech 59000, Lille, France Eric Nyiri∗ Arts et Métiers ParisTech 59000, Lille, France Olivier Gibaru∗ Arts et Métiers ParisTech 59000, Lille, France Stéphane Thiery∗ Arts et Métiers ParisTech 59000, Lille, France" 82a922e775ec3a83d2d5637030860f587697ae42,Dense Multiperson Tracking with Robust Hierarchical Linear Assignment,"Dense Multiperson Tracking with Robust Hierarchical Linear Assignment McLaughlin, N., Martinez-del-Rincon, J., & Miller, P. (2015). Dense Multiperson Tracking with Robust https://doi.org/10.1109/TCYB.2014.2348314 Published in: Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights Copyright 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any opyrighted components of this work in other works. General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to" 829f390b3f8ad5856e7ba5ae8568f10cee0c7e6a,A Robust Rotation Invariant Multiview Face Detection in Erratic Illumination Condition,"International Journal of Computer Applications (0975 – 8887) Volume 57– No.20, November 2012 A Robust Rotation Invariant Multiview Face Detection in Erratic Illumination Condition G.Nirmala Priya Associate Professor, Department of ECE Sona College of Technology Salem" 82f6dad08432a5f1b737ba91dd002ff1f89170f7,c○2013 The Association for Computational Linguistics Order copies of this and other ACL proceedings from:,"ACL201351stAnnualMeetingoftheAssociationforComputationalLinguisticsProceedingsoftheConferenceSystemDemonstrationsAugust4-9,2013Sofia,Bulgaria" 82a4a35b2bae3e5c51f4d24ea5908c52973bd5be,Real-time emotion recognition for gaming using deep convolutional network features,"Real-time emotion recognition for gaming using deep convolutional network features S´ebastien Ouellet" 825198ad69b2203997341fa903ce56ea28451644,Developing crossmodal expression recognition based on a deep neural model,"Special issue on Grounding Emotions in Robots Developing crossmodal expression recognition based on a deep neural model Pablo Barros and Stefan Wermter Adaptive Behavior 016, Vol. 24(5) 373–396 Ó The Author(s) 2016 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/1059712316664017 db.sagepub.com" 8210fd10ef1de44265632589f8fc28bc439a57e6,Single Sample Face Recognition via Learning Deep Supervised Autoencoders,"Single Sample Face Recognition via Learning Deep Supervised Auto-Encoders Shenghua Gao, Yuting Zhang, Kui Jia, Jiwen Lu, Yingying Zhang" 8239a0b4cdb480c9fb913c7476f12825418b0909,People detection in RGB-D data,"People Detection in RGB-D Data Luciano Spinello Kai O. Arras" 82d2af2ffa106160a183371946e466021876870d,A Novel Space-Time Representation on the Positive Semidefinite Cone for Facial Expression Recognition,"A Novel Space-Time Representation on the Positive Semidefinite Cone for Facial Expression Recognition Anis Kacem1, Mohamed Daoudi1, Boulbaba Ben Amor1, and Juan Carlos Alvarez-Paiva2 IMT Lille Douai, Univ. Lille, CNRS, UMR 9189 – CRIStAL – Centre de Recherche en Informatique Signal et Automatique de Lille, F-59000 Lille, France Univ. Lille, CNRS, UMR 8524, Laboratoire Paul Painlev´e, F-59000 Lille, France." 82d3dc1dd35e7d2d13bc43614b575dce61b0aba3,Head Pose Estimation from Passive Stereo Images,"Head Pose Estimation from Passive Stereo Images M. D. Breitenstein1, J. Jensen2, C. Høilund2, T. B. Moeslund2, L. Van Gool1 ETH Zurich, Switzerland1 Aalborg University, Denmark2" 826c66bd182b54fea3617192a242de1e4f16d020,Action-vectors: Unsupervised movement modeling for action recognition,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" 820b1349751d7e932b74c3de94b96557fa2534cf,BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography,"BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography Michael J. Wilber1,2 Chen Fang1 John Collomosse1 Adobe Research Aaron Hertzmann1 Hailin Jin1 Serge Belongie2 Cornell Tech" 8263834bbe6e986a703370810f9b963e2d25a7f7,Towards Head Motion Compensation Using Multi-Scale Convolutional Neural Networks,"Towards Head Motion Compensation Using Multi-Scale Convolutional Neural Networks O. Rajput1∗, N. Gessert1∗, M. Gromniak1, L. Matth¨aus2, A. Schlaefer1 Institute of Medical Technology, Hamburg University of Technology, Hamburg, Germany eemagine Medical Imaging Solutions GmbH, Berlin, Germany Both authors contributed equally. Contact:" 82fc08f5658e0e37aeb36177717621605e11cda1,CNN-Based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss,"CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss Christian Bailer1 Kiran Varanasi1 Didier Stricker1,2 German Research Center for Artificial Intelligence (DFKI), 2University of Kaiserslautern" 82eff71af91df2ca18aebb7f1153a7aed16ae7cc,MSU-AVIS dataset : Fusing Face and Voice Modalities for Biometric Recognition in Indoor Surveillance Videos,"MSU-AVIS dataset: Fusing Face and Voice Modalities for Biometric Recognition in Indoor Surveillance Videos Anurag Chowdhury*, Yousef Atoum+, Luan Tran*, Xiaoming Liu*, Arun Ross* *Michigan State University, USA +Yarmouk University, Jordan" 82ab819815c86e85128a2a055a0c0fcd1146b696,Sampled Image Tagging and Retrieval Methods on User Generated Content,[cs.CV] 23 Nov 2016 82752700f496d4575163b2c59a547d24eb916baf,Similarity Search on Spatio-Textual Point Sets,"Series ISSN: 2367-2005 0.5441/002/edbt.2016.31 o1, {shop,jeans}u2, o2, {football,match,stadium}u3, o3, {shop,market}u2, o5, {hurry, tube, time}u1, o4, {tube,ride}u3, o6, {thames,bridge}u3, o7, {bus,ride}spatial thresholdu2, o8, {football,derby}Figure1:STPSJoinqueryscenario.Multipleobjectsarespatiallyortextuallysimilar,butonlyusersu1andu3haveobjectswhicharemutuallysimilar.dayfrom100millionactiveusers.Useractivitiesintheseplatformsgeneratecontentthathastextualcomponent,e.g.,statusupdates,shortmessages,ortags,and,followingthewidespreadadoptionofGPSinmobiledevices,ageospatialcomponent,e.g.,geotaggedtweets,photos,andusercheck-ins.Thus,theactionsofusersaredocumentedbytheirmessagesinsocialnetworksandassuchgenerate“traces”,whichconsistofspatio-textualobjects.Ef‌f‌icientindexingandqueryingofspatio-textualdatahasreceivedalotofattentionoverthepastyears,duetothehighimportanceofsuchcontentinlocation-basedservices,suchasnearbysearchandrecommendations.Inparticu-lar,multipletypesofspatio-textualquerieshavebeenex-tensivelystudied,includingbooleanrangequeries,top-kqueries,k-nearestneighborqueries,andmorerecently,spatio-textualsimilarityjoins[11,7].Nevertheless,inexistingworks,spatio-textualentitiesaretypicallytreatedasisolatedobservations.Atypicalexamplequeryistofindnearbyrestaurantsorhotelsmatchingcertaincriteria.Theworkin[7]dealswithfindingpairsofentitiesthatarebothspatiallycloseandtextuallysimilar.Exampleusecasesarede-duplicatingPoints-of-Interestacrossdatasets,orfindingmatchingphotostakenatroughlythesameloca-tionandhavingsimilartags.Nowconsiderlookingforsimilarusersinsocialnetworks.Here,auserischaracterizedbythemessagestheygenerateand,ifavailable,respectivelocationinformation.Assuch,eachmessagecanbeconsideredaspatio-textualobject,e.g.,ageotaggedphotoortweet.Witheachuserbeingcharacter-" 82ffd9024dd6890e5469b587e3516cd07786d6d4,Using Image Fairness Representations in Diversity-Based Re-ranking for Recommendations,"Using Image Fairness Representations in Diversity-Based Re-ranking for Recommendations Chen Karako Shopify Inc. 90 Rue de la Gauchetiere O. Montreal, QC H2Z 0B2 Putra Manggala Shopify Inc. 90 Rue de la Gauchetiere O. Montreal, QC H2Z 0B2" 82d781b7b6b7c8c992e0cb13f7ec3989c8eafb3d,Robust Facial Expression Recognition Using a State-based Model of Spatially-localized Facial,"REFERENCES Adler A., Youmaran R. and Loyka S., “Towards a Measure of Biometric Information”, Canadian Conference on Electrical and Computer Engineering, pp. 210-213, 2006. Ahmed A.A.E. and Traore I., “Anomaly Intrusion Detection Based on Biometrics”, IEEE Workshop on Information Assurance, United States Military Academy, West Point, New York, pp. 452-458, 2005. Ahmed A.A.E. and Traore I., “Detecting Computer Intrusions using Behavioural Biometrics”, Third Annual Conference on Privacy, Security and Trust, St. Andrews, New Brunswick, Canada, pp. 1-8, 005. Al-Zubi S., Bromme A. and Tonnies K., “Using an Active Shape Structural Model for Biometric Sketch Recognition”, Proceedings of DAGM, Magdeburg, Germany, Vol. 2781, pp. 187-195, 2003. Angle S., Bhagtani R. and Chheda H., “Biometrics: a Further Echelon of Security”, The First UAE International Conference on Biological nd Medical Physics, pp. 1-4, 2005. Avraam Kasapis., “MLPs and Pose, Expression Classification”, Proceedings of UNiS Report, pp. 1-87, 2003. Banikazemi M., Poff D. and Abali B., “Storage-based Intrusion" 825f56ff489cdd3bcc41e76426d0070754eab1a8,Making Convolutional Networks Recurrent for Visual Sequence Learning,"Making Convolutional Networks Recurrent for Visual Sequence Learning Xiaodong Yang Pavlo Molchanov Jan Kautz NVIDIA" 8291491723d24fd242a3a93248f6475cb084999c,MobileFace: 3D Face Reconstruction with Efficient CNN Regression,"MobileFace: 3D Face Reconstruction with Ef‌f‌icient CNN Regression Nikolai Chinaev1, Alexander Chigorin1, and Ivan Laptev1,2 VisionLabs, Amsterdam, The Netherlands {n.chinaev, Inria, WILLOW, Departement d’Informatique de l’Ecole Normale Superieure, PSL Research University, ENS/INRIA/CNRS UMR 8548, Paris, France" 61b17f719bab899dd50bcc3be9d55673255fe102,Detecting Sarcasm in Multimodal Social Platforms,"Detecting Sarcasm in Multimodal Social Platforms Rossano Schifanella University of Turin Corso Svizzera 185 0149, Turin, Italy Paloma de Juan Yahoo 29 West 43rd Street New York, NY 10036 Joel Tetreault Yahoo 29 West 43rd Street New York, NY 10036 Liangliang Cao Yahoo 29 West 43rd Street New York, NY 10036 inc.com" 617c4e23fc7ca51d98dacb28779214b3e79e9720,Open-Ended Visual Question-Answering,"Open-Ended Visual Question-Answering Escola T`ecnica Superior d’Enginyeria de Telecomunicaci´o de Barcelona Submitted to the Faculty of the A Degree Thesis In partial fulfilment of the requirements for the degree in SCIENCE AND TELECOMMUNICATION TECHNOLOGIES ENGINEERING Author: Advisors: Xavier Gir´o i Nieto, Santiago Pascual de la Puente Issey Masuda Mora Universitat Polit`ecnica de Catalunya (UPC) June 2016" 610a4451423ad7f82916c736cd8adb86a5a64c59,A Survey on Search Based Face Annotation Using Weakly Labelled Facial Images,"Volume 4, Issue 11, November 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A Survey on Search Based Face Annotation Using Weakly Labelled Facial Images Shital A. Shinde*, Prof. Archana Chaugule Department of Computer Engg, DYPIET Pimpri, Savitri Bai Phule Pune University, Maharashtra India" 61c07d7387dcbfb8fa697f15316e3b265d78a2fa,Multi-modal Approach for Affective Computing,"Multi-modal Approach for Affective Computing Siddharth1,2, Tzyy-Ping Jung2 and Terrence J. Sejnowski2" 61c4969c78cff37357ac794af5ac8e439751b39f,Midrange Geometric Interactions for Semantic Segmentation Constraints for Continuous Multi-label Optimization,"Int J Comput Vis DOI 10.1007/s11263-015-0828-7 Midrange Geometric Interactions for Semantic Segmentation Constraints for Continuous Multi-label Optimization Julia Diebold1 · Claudia Nieuwenhuis2 · Daniel Cremers1 Received: 1 June 2014 / Accepted: 15 May 2015 © Springer Science+Business Media New York 2015" 61366c2eed49519e3adef44e8b7146db1fcc2113,Convex NMF on Non-Convex Massiv Data,"Convex NMF on Non-Convex Massiv Data Kristian Kersting1 and Mirwaes Wahabzada1 and Christian Thurau2 and Christian Bauckhage2 Knowledge Discovery Department, 2Vision and Social Media Group Fraunhofer IAIS, Schloss Birlinghoven, 53754 Sankt Augustin, Germany" 614524b27188bb8869ec7a5b374c2a9874f96ec5,A new covariance estimate for Bayesian classifiers in biometric recognition,"A New Covariance Estimate for Bayesian Classifiers in Biometric Recognition Carlos E. Thomaz, Duncan F. Gillies, and Raul Q. Feitosa" 61f04606528ecf4a42b49e8ac2add2e9f92c0def,Deep Deformation Network for Object Landmark Localization,"Deep Deformation Network for Object Landmark Localization Xiang Yu, Feng Zhou and Manmohan Chandraker NEC Laboratories America, Department of Media Analytics" 610c341985633b2d31368f8642519953c39ff7e8,Computational Load Balancing on the Edge in Absence of Cloud and Fog,"Computational Load Balancing on the Edge in Absence of Cloud nd Fog Citation for published version: Sthapit, S, Thompson, J, Robertson, NM & Hopgood, J 2018, 'Computational Load Balancing on the Edge in Absence of Cloud and Fog' IEEE Transactions on Mobile Computing. DOI: 10.1109/TMC.2018.2863301 Digital Object Identifier (DOI): 0.1109/TMC.2018.2863301 Link: Link to publication record in Edinburgh Research Explorer Document Version: Peer reviewed version Published In: IEEE Transactions on Mobile Computing General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) nd / or other copyright owners and it is a condition of accessing these publications that users recognise and bide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer ontent complies with UK legislation. If you believe that the public display of this file breaches copyright please" 619eaaa60f0194d456591983a6f26b04cd9e9a52,"Munafo, M. (2017). Impaired Recognition of Basic Emotions from Facial Expressions in Young People with Autism Spectrum Disorder: Assessing the Importance of Expression","Griffiths, S. L., Jarrold, C., Penton-Voak, I., Woods, A., Skinner, A., & Munafo, M. (2017). Impaired Recognition of Basic Emotions from Facial Expressions in Young People with Autism Spectrum Disorder: Assessing the Importance of Expression Intensity. Journal of Autism and Developmental Disorders. DOI: 10.1007/s10803-017-3091-7 Publisher's PDF, also known as Version of record Link to published version (if available): 0.1007/s10803-017-3091-7 Link to publication record in Explore Bristol Research PDF-document This is the final published version of the article (version of record). It first appeared online via Springer at http://link.springer.com/article/10.1007%2Fs10803-017-3091-7. Please refer to any applicable terms of use of the publisher. University of Bristol - Explore Bristol Research General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: http://www.bristol.ac.uk/pure/about/ebr-terms" 61c256071d3344cce6602afcf4f6c27593a2d93e,Online pedestrian group walking event detection using spectral analysis of motion similarity graph,"Online Pedestrian Group Walking Event Detection Using Spectral Analysis of Motion Similarity Graph Vahid Bastani, Damian Campo, Lucio Marcenaro and Carlo Regazzoni University of Genoa, DITEN {vahid.bastani, {lucio.marcenaro, Via all’Opera Pia, 11A - 16145 Genova (GE)" 610c62bd933c82b609555692ca7f8e9b77934034,DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data,"Arango-Argoty et al. Microbiome (2018) 6:23 DOI 10.1186/s40168-018-0401-z SO F T WA R E DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data Gustavo Arango-Argoty1, Emily Garner2, Amy Pruden2, Lenwood S. Heath1, Peter Vikesland2 and Liqing Zhang1* Open Access" 61c76ac08113e3f732e65a3593471c3e94ddda7b,Active Shape Models with Invariant Optimal Features (IOF-ASMs),"Active Shape Models with Invariant Optimal Features (IOF-ASMs) Federico Sukno1,2, Sebasti´an Ord´as1, Costantine Butakoff1, Santiago Cruz2, and Alejandro Frangi1 Department of Technology, Pompeu Fabra University, Barcelona, Spain Aragon Institute of Engineering Research, University of Zaragoza, Spain" 61f4e08b938986ea80f711c73cadbc84e1811181,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 619f9c1552f8f4f7c5927a7369c79e34d6294083,A Volumetric/Iconic Frequency Domain Representation for Objects With Application for Pose Invariant Face Recognition,"AVolumetric/IconicFrequencyDomain RepresentationforObjects withapplicationfor PoseInvariantFaceRecognition AppearedinIEEETrans.onPatternAnalysisandMachineIntelligence Vol.,No.,May ,pp. -. JezekielBen-ArieandDibyenduNandy DepartmentofElectricalEngineeringandComputerScience TheUniversityofIllinoisatChicago ContactAddress: Dr.JezekielBen-Arie TheUniversityofIllinoisatChicago DepartmentofElectricalEngineeringandComputerScience(M/C) SouthMorganStreetChicago,IL- Phone:() - Fax:() - ThisworkwassupportedbytheNationalScienceFoundationunderGrantNo.IRI-   ndGrantNo.IRI-  ." 6198c7d579726fcc0d4c62ac156b503fc9e39251,SEARCHINGWITH EXPECTATIONS Harsimrat Sandhawalia,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010" 61dfebbb02dad16b56cd9e6c54b5da3ab41caf1c,Exploiting Local Class Information in Extreme Learning Machine,"Iosifidis, A., Tefas, A., & Pitas, I. (2014). Exploiting Local Class Information in Extreme Learning Machine. Paper presented at International Joint Conference on Computational Intelligence (IJCCI), Rome, Italy. Peer reviewed version Link to publication record in Explore Bristol Research PDF-document University of Bristol - Explore Bristol Research General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: http://www.bristol.ac.uk/pure/about/ebr-terms" 618c13f1e13cc5346ed5c069a77acaa720b6a1a8,Learning More Universal Representations for Transfer-Learning,"SUBMISSION TO PAMI, SEPTEMBER 2018 Learning More Universal Representations for Transfer-Learning Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot, Mohamed-El-Amine Seddik nd Mohamed Tamaazousti" 610e0bee525a6573932e077f091505f54a5c4ede,"The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA","Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA The Wisdom of MaSSeS: Shailza Jolly∗ SAP SE, Berlin TU Kaiserslautern Sandro Pezzelle∗ SAP SE, Berlin CIMeC - University of Trento Tassilo Klein SAP SE, Berlin Andreas Dengel DFKI, Kaiserslautern CS Department, TU Kaiserslautern Moin Nabi SAP SE, Berlin" 6155d504d59c52dc3a6b8ad6aeae8bf249afd5ac,Analysis of Feature Fusion Based on HIK SVM and Its Application for Pedestrian Detection,Hindawi Publishing Corporation 611f9faa6f3aeff3ccd674d779d52c4f9245376c,Multiresolution models for object detection,"Multiresolution models for object detection Dennis Park, Deva Ramanan, and Charless Fowlkes UC Irvine, Irvine CA 92697, USA," 61e97d8440627bdc9772b3b2083c65f44a51107d,Oxytocin and vasopressin in the human brain: social neuropeptides for translational medicine,"R E V I E W S Oxytocin and vasopressin in the human brain: social neuropeptides for translational medicine Andreas Meyer‑Lindenberg*, Gregor Domes‡, Peter Kirsch* and Markus Heinrichs‡" 61f0cb2e3fdc6a5d0719184e51d2dc483a945ac1,Bilinear Attention Networks,"Bilinear Attention Networks Jin-Hwa Kim1∗, Jaehyun Jun2, Byoung-Tak Zhang2,3 SK T-Brain, 2Seoul National University, 3Surromind Robotics" 6163381244823241373f6741a282f2c4a868b59c,Multimodal biometrics for identity documents (MBioID).,"Multimodal Biometrics for Identity Documents 1 State-of-the-Art Research Report PFS 341-08.05 (Version 2.0) Damien Dessimoz Prof. Christophe Champod Jonas Richiardi Dr. Andrzej Drygajlo {damien.dessimoz, {jonas.richiardi, June 2006 This project was sponsored by the Foundation Banque Cantonale Vaudoise." 61c425bdda0e053074e96c3e6761ff1d7e0dd469,A Framework for Understanding Unintended Consequences of Machine Learning,"A Framework for Understanding Unintended Consequences of Machine Learning Harini Suresh John V. Guttag" 61764c068ad7d2ec988e6ec315d6ed2ed7489c2e,PhD Forum: Dynamic Camera Positioning and Reconfiguration for Multi Camera Networks,"Dynamic Camera Positioning and Reconfiguration for Multi Camera Networks Krishna Reddy Konda Advisor: Dr Nicola Conci February 2015" 617b719e6c31cdfe7c5c485a755435b95f0c4991,Visual Classification of Images by Learning Geometric Appearances Through Boosting,"Visual Classification of Images by Learning Geometric Appearances through Boosting Martin Antenreiter, Christian Savu-Krohn, and Peter Auer Chair of Information Technology (CiT) University of Leoben, Austria" 61a5ba0935e31dbc4cd448504f9b15455922c1f4,"Pengenalan wajah adalah salah satu teknologi biometrik yang telah banyak diaplikasikan dalam system security selain pengenalan retina mata, pengenalan sidik jari dan iris mata. Dalam aplikasinya sendiri pengenalan wajah menggunakan sebuah kamera untuk menangkap wajah seseorang kemudian dibandingkan ","Jarot Dwiprasetyo1, Mochamad Hariadi2 ,2Fakultas Teknik Industri, Elektro, Institut Teknologi Sepuluh Nopember, Surabaya 60111 E-mail :1 ,2 ABSTRAK Seminar Nasional Teknologi Informasi & Komunikasi Terapan 2012 (Semantik 2012) Semarang, 23 Juni 2012 ISBN 979 - 26 - 0255 - 0 PENGENALAN WAJAH DAN KOMPUTER VISION Pengenalan wajah adalah salah satu teknologi biometrik yang telah banyak diaplikasikan dalam system security selain pengenalan retina mata, pengenalan sidik jari dan iris mata. Dalam aplikasinya sendiri pengenalan wajah menggunakan sebuah kamera untuk menangkap wajah seseorang kemudian dibandingkan dengan wajah yang sebelumnya telah disimpan di dalam database tertentu. Ada beberapa macam metoda pengenalan wajah yaitu neural network, jaringan syaraf tiruan, neuro fuzzy adaptif dan eigenface. Secara khusus dalam paper ini metoda yang akan dijelaskan adalah metoda eigenface. Pada paper akhir ini menawarkan metode Eigenface, dan menggunakan webcam untuk menangkap gambar secara real- time. Metode eigenface berfungsi untuk menghitung eigenvalue dan eigenvector yang akan digunakan sebagai fitur dalam melakukan pengenalan. Metode Euclidean distance digunakan untuk mencari jarak dengan data fitur yang telah didapat , dan jarak terkecil adalah hasilnya. Kata kunci : eigenface, gambar, pengenalan wajah, PCA . PENDAHULUAN Teknologi biometrik adalah metode otomatis untuk mengidentifikasi manusia berdasarkan beberapa karakteristik biologis" 61c4b35443b152679c923d5db6c26daaec304172,Fast and stable human detection using multiple classifiers based on subtraction stereo with HOG features,"Fast and Stable Human Detection Using Multiple Classifiers Based on Subtraction Stereo with HOG Features Makoto Arie, Alessandro Moro, Yuma Hoshikawa, Toru Ubukata, Kenji Terabayashi, Kazunori Umeda" 614a7c42aae8946c7ad4c36b53290860f6256441,Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks,"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, Senior Member, IEEE, and Yu Qiao, Senior Member, IEEE" 61b0cfd75f5bce59cf79abb7b602e404fa5584e7,Person Re-Identification by Semantic Region Representation and Topology Constraint,"IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY Person Re-Identification by Semantic Region Representation and Topology Constraint Jianjun Lei, Senior Member, IEEE, Lijie Niu, Huazhu Fu, Senior Member, IEEE, Bo Peng, Qingming Huang, Fellow, IEEE, and Chunping Hou" 617253f275f14490c61dc9d8cb23ceb9c9d4ba35,A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking,"A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking Przemyslaw Szeptycki, Mohsen Ardabilian and Liming Chen" 61ab6e3f999269731b26155605f38bea6d3557f2,Unsupervised object discovery and co-localization by deep descriptor transformation,"Noname manuscript No. (will be inserted by the editor) Unsupervised Object Discovery and Co-Localization y Deep Descriptor Transforming Xiu-Shen Wei · Chen-Lin Zhang · Jianxin Wu · Chunhua Shen · Zhi-Hua Zhou Received: date / Accepted: date" 6106028c73d22570a01212814e1e4f4edb4abed6,Counting moving people in crowds using motion statistics of feature-points,"Multimed Tools Appl DOI 10.1007/s11042-013-1367-2 Counting moving people in crowds using motion statistics of feature-points Mahdi Hashemzadeh· Gang Pan· Min Yao © Springer Science+Business Media New York 2013" 614f4f8fe47e7c0bcf64aa0ad39dc371e4b4ab7b,promoting access to White Rose research papers,"promoting access to White Rose research papers Universities of Leeds, Sheffield and York http://eprints.whiterose.ac.uk/ This is an author produced version of a paper published in Journal of Autism nd Developmental Disorders. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/10325 Published paper Freeth, M., Chapman, P., Ropar, D., Mitchell, P. (2010) Do gaze cues in complex scenes capture and direct the attention of high functioning adolescents with ASD? evidence from eye-tracking, Journal of Autism and Developmental Disorders (In Press) http://dx.doi.org/10.1007/s10803-009-0893-2 White Rose Research Online" 61183c50509f7ad284ae52ef4768aced2af3d260,Data Fusion For Biometric Verification System,"Data Fusion For Biometric Verification System RICHARD A. WASNIOWSKI Computer Science Department California State University – Dominguez Hills Carson, CA 90747, USA" 618d3ad69c677016547098e01b9c6e94c260de1d,What are customers looking at?,"What are customers looking at?∗ Xiaoming Liu Nils Krahnstoever Ting Yu Peter Tu Visualization and Computer Vision Lab General Electric Global Research Center Niskayuna, NY, 12309, USA" 617a6935643615f09ef2b479609baa0d5f87cd67,To Be Taken At Face Value ? Computerised Identification,"Information and Communications Technology Law To Be Taken At Face Value? Computerised Identification Michael Bromby Joseph Bell Centre for Forensic Statistics and Legal Reasoning Glasgow Caledonian University and University of Edinburgh Scientific evidence such as fingerprints, blood, hair and DNA samples are often presented during legal proceedings. Without such evidence, a description provided by the victim or any eyewitnesses is often the only means to identify a suspect. With the dvent of closed circuit television (CCTV), many crimes are now recorded by ameras in the public or private domain, leading to a new form of forensic identification – facial biometrics. Decisions on how to view and interpret biometric evidence are important for both prosecution and defence, not least for the judge and jury who must decide the case. A jury may accept eyewitnesses as reliable sources of evidence more readily False eyewitness accounts appear reliable when confidently presented to a mock jury. The decision-making process of the judge and jury may be seriously flawed if an eyewitness has made a genuine mistake. Using computerised recognition, the judicial decision of whether to accept an alibi or whether to accept the eyewitness account" 617159ad6dfbadd396751058a1bb79e663b44a52,A Photometric Stereo Approach to Face Recognition,"A Photometric Stereo Approach to Face Recognition Roger Woodman [ www.brl.ac.uk/~rwoodman ] A dissertation submitted in partial fulfilment of the requirements of the University of the West of England, Bristol for the Degree of Master of Science Faculty of Computing, Engineering and Mathematical Sciences November 2007" 61692cffff60568da43780df38876c11390ccdc8,Gabor Orientation Histogram for Face Representation and Recognition,"Gabor Orientation Histogram for Face Representation and Recognition Jun Yi and Fei Su" 61bab86023de164bca3e35fc22944a7262970e1d,Child Facial Expression Detection,"CHILD FACIAL EXPRESSION DETECTION Eden Benhamou Deborah Wolhandler Supervisors: Alon Zvirin Michal Zivan Spring 2018" e70ebb9971b1fece8760293e61ed42e2372b1d19,An Evaluation of Large-scale Methods for Image Instance and Class Discovery,"An evaluation of large-scale methods for image instance and class discovery Matthijs Douze, Herv´e J´egou, Jeff Johnson Facebook AI Research ontact:" e7cac91da51b78eb4a28e194d3f599f95742e2a2,"Positive Feeling, Negative Meaning: Visualizing the Mental Representations of In-Group and Out-Group Smiles","RESEARCH ARTICLE Positive Feeling, Negative Meaning: Visualizing the Mental Representations of In- Group and Out-Group Smiles Andrea Paulus1☯*, Michaela Rohr1☯, Ron Dotsch2,3, Dirk Wentura1 Saarland University, Saarbrücken, Germany, 2 Utrecht University, Utrecht, the Netherlands, Behavioural Science Institute, Radboud University, Nijmegen, the Netherlands ☯ These authors contributed equally to this work." e7265c560b3f10013bf70aacbbf0eb4631b7e2aa,Look at Boundary: A Boundary-Aware Face Alignment Algorithm,"(68 points) COFW (29 points) AFLW (19 points) Figure1:Thefirstcolumnshowsthefaceimagesfromdifferentdatasetswithdifferentnumberoflandmarks.Thesecondcolumnillustratestheuniversallydefinedfacialboundariesestimatedbyourmethods.Withthehelpofboundaryinformation,ourapproachachieveshighaccuracylocalisationresultsacrossmultipledatasetsandannotationprotocols,asshowninthethirdcolumn.Differenttofacedetection[45]andrecognition[75],facealignmentidentifiesgeometrystructureofhumanfacewhichcanbeviewedasmodelinghighlystructuredout-put.Eachfaciallandmarkisstronglyassociatedwithawell-definedfacialboundary,e.g.,eyelidandnosebridge.However,comparedtoboundaries,faciallandmarksarenotsowell-defined.Faciallandmarksotherthancornerscanhardlyremainthesamesemanticallocationswithlargeposevariationandocclusion.Besides,differentannotationschemesofexistingdatasetsleadtoadifferentnumberoflandmarks[28,5,66,30](19/29/68/194points)andanno-tationschemeoffuturefacealignmentdatasetscanhardlybedetermined.Webelievethereasoningofauniquefacial" e79847c3bf3ffefe9304e212d8dda7aaa29eaada,From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning Jingkuan Song, Yuyu Guo, Lianli Gao, Xuelong Li, IEEE Fellow Alan Hanjalic, IEEE Fellow Heng Tao Shen" e7928bd33d09fd00a588617736b102063ca9d070,A Non-Technical Survey on Deep Convolutional Neural Network Architectures,"A Non-Technical Survey on Deep Convolutional Neural Network Architectures Felix Altenberger Technical University of Munich 85748 Garching, Germany Email: Claus Lenz Cognition Factory GmbH 80797 Munich, Germany Email:" e74bddccc40e65b31081a1599cbe7385d5d3e1c0,Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering,"Bottom-Up and Top-Down Attention for Image Captioning nd Visual Question Answering Peter Anderson1∗ Xiaodong He2 Chris Buehler3 Damien Teney4 Mark Johnson5 Stephen Gould1 Lei Zhang3 Australian National University 2JD AI Research 3Microsoft Research 4University of Adelaide 5Macquarie University" e79a34f9942172ad97c5fadca3701db3e29d32e2,Fusiform Correlates of Facial Memory in Autism,"NIH Public Access Author Manuscript Behav Sci (Basel). Author manuscript; available in PMC 2014 April 21. Published in final edited form as: Behav Sci (Basel). ; 3(3): 348–371. doi:10.3390/bs3030348. Fusiform Correlates of Facial Memory in Autism Haley G. Trontel1, Tyler C. Duffield2, Erin D. Bigler2,3,4,*, Alyson Froehlich5, Molly B.D. Prigge5, Jared A. Nielsen5, Jason R. Cooperrider5, Annahir N. Cariello5, Brittany G. Travers6, Jeffrey S. Anderson7, Brandon A. Zielinski8, Andrew Alexander6,11, Nicholas Lange9,10, and Janet E. Lainhart11,12 Department of Psychology, University of Montana, Missoula, MT 59812, USA; Department of Psychology, Brigham Young University, Provo, UT 84604, USA; (T.C.D.); (E.D.B.) 3Neuroscience Center, Brigham Young University, Provo, UT 84604, USA 4The Brain Institute of Utah, University of Utah, Salt Lake City, UT 84112, USA 5Department of Psychiatry, University of Utah, Salt Lake City, UT 84112, USA; (A.F.); (M.B.D.P); (J.A.N.); (J.R.C.); (A.N.C.) 6Department of Medical Physics, University of Wisconsin, Madison, WI 53706, USA; (B.G.T.); (A.A.) 7Department of Radiology, University of Utah, Salt Lake City, UT 84112, USA;" e72e852dca333d66559dbcfb050140fac5affe4f,Anatomical Landmark Tracking by One-shot Learned Priors for Augmented Active Appearance Models,"DataωLDAFull AAMAUGMENTED AAMSubset AAMLocal TrackingextractionlearnmodelOne-shotDetectortraintrainLower LegContraintsEipolar ConstraintsDistance ConstraintsTorso ConstraintsFigure1:BasedonfewannotatedbiplanarrecordedtrainingimagesanAugmentedAAM(HaaseandDenzler,2013)istrained,consistingofanatomicalknowledge,afullmulti-viewAAMmodel,anAAMmodelofthetorsoland-marksubset,epipolarconstraintsandalocaltracking-by-detectionpriorintroducedinthispaper.In(HaaseandDenzler,2013)ActiveAppearanceModels(AAM)(Cootesetal.,2001)havebeenap-pliedtoseveralbipedalbirdlocomotiondatasets.OnecrucialconclusionofthisworkisthatAAMsneedsubstantialconstraintsfromvarioussources.Withthesupportofadditionalanatomicalknowledge,i.e.re-gionsegmentation,multi-viewacquisition,andlocallandmarktracking,fortheanimalslowerlimbsys-tem,theresultingAugmentedAAM(HaaseandDen-zler,2013)providesrobustresultsforthemajorityoftheprocesseddatasets.However,theappliedonlinetrackingapproach(Amthoretal.,2012)suffersfrom246MothesO.andDenzlerJ.AnatomicalLandmarkTrackingbyOne-shotLearnedPriorsforAugmentedActiveAppearanceModels.DOI:10.5220/0006133302460254InProceedingsofthe12thInternationalJointConferenceonComputerVision,ImagingandComputerGraphicsTheoryandApplications(VISIGRAPP2017),pages246-254ISBN:978-989-758-227-1Copyrightc(cid:13)2017bySCITEPRESS–ScienceandTechnologyPublications,Lda.Allrightsreserved" e7dc0d5545e6e028b03a82d2f5bb3bccc995a0d7,A New Fast and Efficient HMM-Based Face Recognition System Using a 7-State HMM Along With SVD Coefficients,"Archive of SID A New Fast and Efficient HMM-Based Face Recognition System Using a 7-State HMM Along With SVD Coefficients H. Miar-Naimi* and P. Davari*" e7b6887cd06d0c1aa4902335f7893d7640aef823,Modeling of facial aging and kinship: A survey,"Modelling of Facial Aging and Kinship: A Survey Markos Georgopoulos, Yannis Panagakis, and Maja Pantic," e76798bddd0f12ae03de26b7c7743c008d505215,Joint Max Margin and Semantic Features for Continuous Event Detection in Complex Scenes, e74c4cf90c5bbb88a8ae77aaa5709984f7e6a80f,Viewpoint Unconstrained Face Recognition Based on Affine Local Descriptors and Probabilistic Similarity,"J Inf Process Syst, Vol.11, No.4, pp.643~654, December 2015 ISSN 1976-913X (Print) ISSN 2092-805X (Electronic) Viewpoint Unconstrained Face Recognition Based on Affine Local Descriptors and Probabilistic Similarity Yongbin Gao* and Hyo Jong Lee*,**" e741bced5c1d6368530ce8cdfcdcaa0d9e07c31c,On-Board Detection of Pedestrian Intentions,"Article On-Board Detection of Pedestrian Intentions Zhijie Fang 1,2,*, David Vázquez 2 and Antonio M. López 1,2 Computer Science Department, Universitat Autònoma Barcelona (UAB), 08193 Barcelona, Spain Computer Vision Center (CVC), Universitat Autònoma Barcelona (UAB), 08193 Barcelona, Spain; (D.V.); (A.M.L.) * Correspondence: Tel.: +34-93-581-1828 Received: 4 August 2017; Accepted: 20 September 2017; Published: 23 September 2017" e778e618862ea1c9a97e89e942228c4de98c9a86,Automated Pruning for Deep Neural Network Compression,"Automated Pruning for Deep Neural Network Compression Franco Manessi1†, Alessandro Rozza1†, Simone Bianco2, Paolo Napoletano2, Raimondo Schettini2 lastminute.com group — Strategic Analytics {first name.last Universit`a degli Studi di Milano Bicocca — DISCo {first name.last" e74e2004d8b7357c35d727cb4c92ca97142759f0,Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos,"Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos Seymour, R., Stewart, D., & Ji, M. (2008). Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos. EURASIP Journal on Image and Video Processing, 2008, 1-9. [810362]. DOI: 10.1155/2008/810362 Published in: EURASIP Journal on Image and Video Processing Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to ensure that content in the Research Portal does not infringe any person's rights, or applicable UK laws. If you discover content in the Research Portal that you believe breaches copyright or violates any law, please contact Download date:06. Nov. 2018" e7f00f6e5994c5177ec114ee353cc7064d40a78f,Back to Basic: Do Children with Autism Spontaneously Look at Screen Displaying a Face or an Object?,"Hindawi Publishing Corporation Autism Research and Treatment Volume 2013, Article ID 835247, 7 pages http://dx.doi.org/10.1155/2013/835247 Research Article Back to Basic: Do Children with Autism Spontaneously Look at Screen Displaying a Face or an Object? Marie Guimard-Brunault,1,2,3,4 Nadia Hernandez,3 Laetitia Roché,3 Sylvie Roux,3 Catherine Barthélémy,1,2,3 Joëlle Martineau,2,3 and Frédérique Bonnet-Brilhault1,2,3 CHRU de Tours, Centre Universitaire de P´edopsychiatrie, 2 Boulevard Tonnell´e, 37044 Tours Cedex 9, France Universit´e Franc¸ois Rabelais de Tours, 60 rue du Plat D’Etain, 37020 Tours Cedex 1, France UMR Inserm U 930, ´Equipe 1: Imagerie et Cerveau, Universit´e Franc¸ois Rabelais de Tours, Tours, France UMR Inserm U 930, ´Equipe 1: Imagerie et Cerveau, CHRU de Tours-Hˆopital Bretonneau, 2 boulevard Tonnell´e, Bˆat B1A, 1er Etage, 37044 Tours Cedex 9, France Correspondence should be addressed to Marie Guimard-Brunault; Received 29 June 2013; Revised 29 September 2013; Accepted 21 October 2013 Academic Editor: Elizabeth Aylward Copyright © 2013 Marie Guimard-Brunault et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited." e78394213ae07b682ce40dc600352f674aa4cb05,Expression-invariant three-dimensional face recognition,"Expression-invariant three-dimensional face recognition Alexander M. Bronstein Email: Michael M. Bronstein Ron Kimmel Computer Science Department, Technion – Israel Institute of Technology, Haifa 32000, Israel One of the hardest problems in face recognition is dealing with facial expressions. Finding an expression-invariant representation of the face could be a remedy for this problem. We suggest treating faces as deformable surfaces in the context of Riemannian geometry, and propose to ap- proximate facial expressions as isometries of the facial surface. This way, we can define geometric invariants of a given face under different expressions. One such invariant is constructed by iso- metrically embedding the facial surface structure into a low-dimensional flat space. Based on this pproach, we built an accurate three-dimensional face recognition system that is able to distinguish etween identical twins under various facial expressions. In this chapter we show how under the near-isometric model assumption, the dif‌f‌icult problem of face recognition in the presence of facial expressions can be solved in a relatively simple way. 0.1 Introduction It is well-known that some characteristics or behavior patterns of the human body are strictly" e73f1b6143dabf90fb7a45923b7808a5c35bfbcf,DeepMoTIon: Learning to Navigate Like Humans, e72f626074252b7e17ebc48d9fd4a4cd9d231359,Deep Feature Learning for Medical Image 2 Analysis with Convolutional Autoencoder 3 Neural Network,"IEEE TRANSACTIONS ON BIG DATA, VOL. 3, NO. X, XXXXX 2017 Deep Feature Learning for Medical Image Analysis with Convolutional Autoencoder Neural Network Index Terms—Convolutional autoencoder neural network, lung nodule, feature learning, hand-craft feature, unsupervised learning 6 1 INTRODUCTION Min Chen, Senior Member, IEEE, Xiaobo Shi, Yin Zhang, Senior Member, IEEE, Di Wu, Senior Member, IEEE, and Mohsen Guizani, Fellow, IEEE" e75cd1379b07d77358e5a2f4a042f624066603b6,Weakly-Supervised Learning of Visual Relations,"Weakly-supervised learning of visual relations Julia Peyre1,2 Ivan Laptev1,2 Cordelia Schmid2,4 Josef Sivic1,2,3" e746c8eec81384bd37dede9700be9c8a3700f936,Context Encoding for Semantic Segmentation,"Context Encoding for Semantic Segmentation Hang Zhang 1,2 Kristin Dana 1 Jianping Shi 3 Zhongyue Zhang 2 Xiaogang Wang 4 Ambrish Tyagi 2 Amit Agrawal 2 Rutgers University 2Amazon Inc 3SenseTime 4The Chinese University of Hong Kong" e72d35ae7c1f477ce4341a5fb3a15bcfe0481a0e,Behavioral Consistency Extraction for Face Verification,"Behavioral Consistency Extraction for Face Verification Hui Fang and Nicholas Costen Manchester Metropolitan University Department of Computing and Mathematics, Manchester, U.K." e7906370eae8655fb69844ae1a3d986c9f37c902,Face recognition using Deep Learning,"POLYTECHNIC UNIVERSITY OF CATALONIA MASTER THESIS Face recognition using Deep Learning Author: Xavier SERRA Advisor: Javier CASTÁN Tutor: Sergio ESCALERA This master thesis has been developed at GoldenSpear LLC January 2017" e719e1ed86bf2214512d5631e31716effe2e23d2,Learning to Estimate 3D Human Pose and Shape from a Single Color Image,"Learning to Estimate 3D Human Pose and Shape from a Single Color Image Georgios Pavlakos1, Luyang Zhu2, Xiaowei Zhou3, Kostas Daniilidis1 University of Pennsylvania 2 Peking University 3 Zhejiang University" e746447afc4898713a0bcf2bb560286eb4d20019,Leveraging Virtual and Real Person for Unsupervised Person Re-identification,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, NOVEMBER 2018 Leveraging Virtual and Real Person for Unsupervised Person Re-identification Fengxiang Yang, Zhun Zhong, Zhiming Luo, Sheng Lian, and Shaozi Li" e7f4951c1106bff0460665ef67d11fb9c2d07c41,Machine Vision-Based Analysis of Gaze and Visual Context : an Application to Visual Behavior of Children with Autism Spectrum Disorders by,"Machine Vision-Based Analysis of Gaze and Visual Context: an Application to Visual Behavior of Children with Autism Spectrum Disorders Basilio Noris MSc/BSc in Computer Science, Université de Lausanne, 2005 Dissertation Submitted to the School of Engineering in partial fulfillment of the requirements for the degree of Doctor of Philosophy Ecole Polytechnique Fédérale de Lausanne (EPFL) t the (Swiss Federal Insitute of Technology Lausanne) Supervisor: Prof. Aude Billard Examiners: Prof. Thierry Pun Prof. Jacqueline Nadel Prof. Nouchine Hadjikhani President of the jury:" e7721f40fed05aae4d49d84e9ebc94ced7015aac,Design and Implementation of Resampling Techniques for Face Recognition using Classical LDA Algorithm in MATLAB,"International Journal of Computer Applications (0975 – 8887) Volume 152 – No.6, October 2016 Design and Implementation of Resampling Techniques for Face Recognition using Classical LDA Algorithm in MATLAB S. R Bichwe Dept. of Electronics & Communication Kavikulguru Institute of Technology & Science, Ramtek, Maharashtra Sugandha Satija Dept. of Information Technology Kavikulguru Institute of Technology & Science, Ramtek, Maharashtra Madhavi R. Bichwe Dept of Computer Science & Technology" e72c5fb54c3d14404ebd1bf993e51d0056f6c429,Tempered Adversarial Networks, 7b8aa3ebeae17e5266dac23e87f603a5d5f7b1e3,Open Set Logo Detection and Retrieval,"Open Set Logo Detection and Retrieval Andras T¨uzk¨o1, Christian Herrmann1,2, Daniel Manger1, J¨urgen Beyerer1,2 Fraunhofer IOSB, Karlsruhe, Germany Karlsruhe Institute of Technology KIT, Vision and Fusion Lab, Karlsruhe, Germany Keywords: Logo Detection, Logo Retrieval, Logo Dataset, Trademark Retrieval, Open Set Retrieval, Deep Learning." 7b965bf132e5971dfa95c67bc7685b73b32e07df,Pedestrian Detection via Mixture of CNN Experts and Thresholded Aggregated Channel Features,"Pedestrian Detection via Mixture of CNN Experts and thresholded Aggregated Channel Features Ankit Verma, Ramya Hebbalaguppe, Lovekesh Vig, Swagat Kumar, and Ehtesham Hassan TCS Innovation Labs, New Delhi" 7b522c5d6d2d0699c4183a543b8e65b1a66d9e74,Understanding critical factors in appearance-based gender categorization,"Understanding Critical Factors in Appearance-based Gender Categorization Enrico Grosso, Andrea Lagorio, Luca Pulina, and Massimo Tistarelli POLCOMING – University of Sassari Viale Mancini, 5 – 07100 Sassari, Italy" 7b07a87ff71b85f3493d1944034a960917b8482f,Alternating BackPropagation for Generator Network,"Alternating Back-Propagation for Generator Network Tian Han†, Yang Lu†, Song-Chun Zhu, and Ying Nian Wu Department of Statistics, University of California, Los Angeles, USA" 7b6b49adf60d56d1b33b428fdf66aff7426fca6e,Survey on Deep Learning Techniques for Person Re-Identification Task, 7b66dababebd800e95d23a1fde299d44a52e98ed,Dual Recurrent Attention Units for Visual Question Answering,"Under review for Computer Vision and Image Understanding DRAU: Dual Recurrent Attention Units for Visual Question Answering Ahmed Osmana,, Wojciech Sameka, Fraunhofer Heinrich Hertz Institute, Einsteinufer 37, Berlin 10587, Germany" 7b67c38a6f49e02c03e1cea98146a506f607b0d7,Using Facial Symmetry to Handle Pose Variations in Real-World 3D Face Recognition,"Using Facial Symmetry to Handle Pose Variations in Real-World 3D Face Recognition Georgios Passalis1,2, Panagiotis Perakis1,2, Theoharis Theoharis1,2 nd Ioannis A. Kakadiaris2, Senior Member, IEEE" 7b3a63d030d03e536ddcbc217bc8d6fd630e3b53,xView: Objects in Context in Overhead Imagery,"xView: Objects in Context in Overhead Imagery Darius Lam1 Richard Kuzma2 Matthew Klaric4 Kevin McGee3 Yaroslav Bulatov5 Samuel Dooley4 Michael Laielli4 Brendan McCord2" 7b9a5d9d7386d47c51cb473f6338988bd6e9f2b1,An Individual-Specific Strategy for Management of Reference Data in Adaptive Ensembles for Person Re-Identification,"An Individual-Specific Strategy for Management of Reference Data in Adaptive Ensembles for Person Re-Identification Miguel De-la-Torre*†, Eric Granger*, Robert Sabourin*, Dmitry O. Gorodnichy‡ * ´Ecole de technologie sup´erieure, Universit´e du Qu´ebec, Montr´eal, Canada, Centro Universitario de Los Valles, Universidad de Guadalajara, Ameca, M´exico Science and Engineering Directorate, Canada Border Services Agency, Ottawa, Canada, Keywords: Multi-Classifier Systems; Adaptive Biometrics; Face Recognition; Video Surveillance; Person Re-Identification" 7be6fe8c58ca12974c563689b7230b933dfca432,Design of radial basis function network as classifier in face recognition using eigenfaces,"SBRN’98 – Simpósio Brasileiro de Redes Neurais, Belo Horizonte, Minas Gerais, dezembro de 1998. Design of Radial Basis Function Network as Classifier in Face Recognition Using Eigenfaces Carlos Eduardo Thomaz Raul Queiroz Feitosa Álvaro Veiga PUC RJ- Pontifícia Universidade Católica do Rio de Janeiro Departamento de Engenharia Elétrica Rua Marquês de São Vicente, 225, 22453-900 Rio de Janeiro, RJ, Brasil" 7b358ed87f39a12d737070dc22b4c547ce378648,Color Features for Boosted Pedestrian Detection,"Institutionen för systemteknik Department of Electrical Engineering Examensarbete Color Features for Boosted Pedestrian Detection Examensarbete utfört i Datorseende vid Tekniska högskolan vid Linköpings universitet Niklas Hansson LiTH-ISY-EX--15/4899--SE Linköping 2015 Department of Electrical Engineering Linköpings universitet SE-581 83 Linköping, Sweden Linköpings tekniska högskola Linköpings universitet 581 83 Linköping" 7bcd98ee2df3d14eae7bbed713208cb7da7b5db0,Unsupervised data association for metric learning in the context of multi-shot person re-identification,"Unsupervised data association for Metric Learning in the context of Multi-shot Person Re-identification Furqan M. Khan, Francois Bremond INRIA Sophia Antipolis-Mediterrannee 004 Route des Lucioles, Sophia Antipolis Cedex, France {furqan.khan |" 7b0e81249159686337ca2cfe81662123906b6b26,An Automatic Eye Detection Method for Gray Intensity Facial Images,"IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 4, No 2, July 2011 ISSN (Online): 1694-0814 www.IJCSI.org An Automatic Eye Detection Method for Gray Intensity Facial Images M. Hassaballah1,2 , Kenji Murakami1, Shun Ido1 Department of Computer Science, Ehime University, 790-8577, Japan Department of Mathematics, Faculty of Science, South Valley University, Qena, 83523, Egypt" 7bd18f70586a735313fb38f2cb5bb0113265567d,Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization,"Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization Hakan Karao˘guz1 and Patric Jensfelt1" 7b3b7769c3ccbdf7c7e2c73db13a4d32bf93d21f,"On the design and evaluation of robust head pose for visual user interfaces: algorithms, databases, and comparisons","On the Design and Evaluation of Robust Head Pose for Visual User Interfaces: Algorithms, Databases, and Comparisons Sujitha Martin Laboratory of Intelligent and Safe Automobiles UCSD - La Jolla, CA, USA Ashish Tawari Laboratory of Intelligent and Safe Automobiles UCSD - La Jolla, CA, USA Erik Murphy-Chutorian Laboratory of Intelligent and Safe Automobiles UCSD - La Jolla, CA, USA Shinko Y. Cheng Laboratory of Intelligent and Safe Automobiles UCSD - La Jolla, CA, USA Mohan Trivedi" 7b83867b7f79cbfbfc71996bcf07fe7ee7a7600c,Object detection through search with a foveated visual system,"Object Detection Through Exploration With A Foveated Visual Field Emre Akbas, Miguel P. Eckstein" 7be351e731eb9c3b71ad0c2a47ee8d300f7049be,Recognition for Objects by Relationships Between Attributes,"Journal of Computer Science Technology Updates, 2016, 3, 15-21 Recognition for Objects by Relationships Between Attributes Hiroka Horiguchi*, Kazuo Ikeshiro and Hiroki Imamura Graduate School of Engineering, Soka University, Hachioji-Shi, Tokyo, Japan" 7b9b3794f79f87ca8a048d86954e0a72a5f97758,Passing an Enhanced Turing Test - Interacting with Lifelike Computer Representations of Specific Individuals,"DOI 10.1515/jisys-2013-0016      Journal of Intelligent Systems 2013; 22(4): 365–415 Avelino J. Gonzalez*, Jason Leigh, Ronald F. DeMara, Andrew Johnson, Steven Jones, Sangyoon Lee, Victor Hung, Luc Renambot, Carlos Leon-Barth, Maxine Brown, Miguel Elvir, James Hollister and Steven Kobosko Passing an Enhanced Turing Test – Interacting with Lifelike Computer Representations of Specific Individuals" 7b0f1fc93fb24630eb598330e13f7b839fb46cce,Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings,"Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings Seonwook Park ETH Zurich Xucong Zhang MPI for Informatics Andreas Bulling MPI for Informatics Otmar Hilliges ETH Zurich" 7bbaa09c9e318da4370a83b126bcdb214e7f8428,"FaaSter, Better, Cheaper: The Prospect of Serverless Scientific Computing and HPC","FaaSter, Better, Cheaper: The Prospect of Serverless Scientific Computing and HPC Josef Spillner1, Cristian Mateos2, and David A. Monge3 Zurich University of Applied Sciences, School of Engineering Service Prototyping Lab (blog.zhaw.ch/icclab/), 8401 Winterthur, Switzerland ISISTAN Research Institute - CONICET - UNICEN Campus Universitario, Paraje Arroyo Seco, Tandil (7000), Buenos Aires, Argentina ITIC Research Institute, National University of Cuyo Padre Jorge Contreras 1300, M5502JMA Mendoza, Argentina" 7bce4f4e85a3bfcd6bfb3b173b2769b064fce0ed,A Psychologically-Inspired Match-Score Fusion Model for Video-Based Facial Expression Recognition,"A Psychologically-Inspired Match-Score Fusion Model for Video-Based Facial Expression Recognition Albert Cruz, Bir Bhanu, Songfan Yang, VISLab, EBUII-216, University of California Riverside, Riverside, California, USA, 92521-0425 {acruz, bhanu," 7b95bd44db15f7cf20bfc051c353841f3fcea383,Low-Complexity Face Recognition using a Multilevel DWT and Two States of Continuous HMM to recognize Noisy Images,"Low-Complexity Face Recognition using a Multilevel DWT and Two States of Continuous HMM to recognize Noisy Images Hameed R. Farhan1, Mahmuod H. Al-Muifraje2, Thamir R. Saeed2 Department of Electrical and Electronic Engineering, University of Kerbala, Kerbala, Iraq Department of Electrical Engineering, University of Technology, Baghdad, Iraq" 7b47ca13af16bdc1f4b88e9b68dd3ea52d959199,Online nonparametric discriminant analysis for incremental subspace learning and recognition,"Pattern Anal Applic (2008) 11:259–268 DOI 10.1007/s10044-008-0131-0 T H E O R E T I C A L A D V A N C E S Online nonparametric discriminant analysis for incremental subspace learning and recognition B. Raducanu Æ J. Vitria` Received: 15 December 2006 / Accepted: 20 January 2008 / Published online: 24 July 2008 Ó Springer-Verlag London Limited 2008" 7ba6ac1b769ad7098037c07a5b7399fe9d97fcc8,Moving Object Detection in Heterogeneous Conditions in Embedded Systems,"Article Moving Object Detection in Heterogeneous Conditions in Embedded Systems Alessandro Garbo and Stefano Quer * Dipartimento di Automatica ed Informatica, Politecnico di Torino, 10129 Torino, Italy; * Correspondence: Tel.: +39-011-090-7076 Received: 25 May 2017; Accepted: 27 June 2017; Published: 1 July 2017" 7bd6d0bca27ff68621acd10d6d1709f084f97602,Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World,"Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World Matteo Fabbri(cid:63), Fabio Lanzi(cid:63), Simone Calderara(cid:63), Andrea Palazzi, Roberto Vezzani, and Rita Cucchiara Department of Engineering “Enzo Ferrari” University of Modena and Reggio Emilia, Italy" 7b8e9c50f74ce6ca66a8ab61fb18ca31d26cf13f,Nonlinear Channels Aggregation Networks for Deep Action Recognition,"Under review as a conference paper at ICLR 2019 Nonlinear Channels Aggregation Networks for Deep Action Recognition Anonymous authors Paper under double-blind review" 7b1af8cc9c2c43fa9d528bcfb05142d714df3700,"Modeling shape, appearance and motion for human movement analysis", 7b2e0c87aece7ff1404ef2034d4c5674770301b2,Discriminative Feature Learning with Foreground Attention for Person Re-Identification,"Discriminative Feature Learning with Foreground Attention for Person Re-Identification Sanping Zhou, Jinjun Wang, Deyu Meng, Yudong Liang, Yihong Gong, Nanning Zheng" 7b3e725ff30fb9e70482af0873f46c599ac0f675,Deep Learning with Long Short-Term Memory for Time Series Prediction,"Deep Learning with Long Short-Term Memory for Time Series Prediction Yuxiu Hua, Zhifeng Zhao, Rongpeng Li, Xianfu Chen, Zhiming Liu, nd Honggang Zhang" 7b9961094d3e664fc76b12211f06e12c47a7e77d,Bridging biometrics and forensics,"Bridging Biometrics and Forensics Yanjun Yan and Lisa Ann Osadciw EECS, Syracuse University, Syracuse, NY, USA {yayan," 6b78f2ece211c2d1eb6699e1e057b7beb3e0b4a7,GM-PHD-Based Multi-Target Visual Tracking Using Entropy Distribution and Game Theory,"GM-PHD-Based Multi-Target Visual Tracking Using Entropy Distribution and Game Theory Xiaolong Zhou, Youfu Li, Senior Member, IEEE, Bingwei He, and Tianxiang Bai" 6bfae88bea2301f2abeb6d1ed62c8b9a99b251c0,CNRS TELECOM ParisTech at ImageCLEF 2015 Scalable Concept Image Annotation Task: Concept Detection with Blind Localization Proposals,"CNRS TELECOM ParisTech at ImageCLEF 015 Scalable Concept Image Annotation Task: Concept Detection with Blind Localization Proposals Hichem SAHBI CNRS TELECOM ParisTech" 6b5438161cfe55d1bd44829db81f396819e9e6b9,Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning,"Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning Morgan A. Schmitz∗ , Matthieu Heitz† , Nicolas Bonneel† , Fred Ngol`e‡ , David Coeurjolly† , Marco Cuturi§ , Gabriel Peyr´e¶, and Jean-Luc Starck∗" 6b6943a138938c31b285c1bb11213b87404feddf,Multiple Instance Learning-Based Birdsong Classification Using Unsupervised Recording Segmentation,"Multiple Instance Learning-Based Birdsong Classification Using Unsupervised Recording Segmentation J. F. Ruiz-Mu˜noz, Mauricio Orozco-Alzate, G. Castellanos-Dominguez Universidad Nacional de Colombia - Sede Manizales {jfruizmu, morozcoa," 6b55153f8d87bfd0dfb2f24eb2aa61d40e314cae,"Track, Then Decide: Category-Agnostic Vision-Based Multi-Object Tracking","Track, then Decide: Category-Agnostic Vision-based Multi-Object Tracking Aljoˇsa Oˇsep, Wolfgang Mehner, Paul Voigtlaender, and Bastian Leibe" 6b7f27cff688d5305c65fbd90ae18f3c6190f762,Generative networks as inverse problems with Scattering transforms,"Published as a conference paper at ICLR 2018 GENERATIVE NETWORKS AS INVERSE PROBLEMS WITH SCATTERING TRANSFORMS Tom´as Angles & St´ephane Mallat ´Ecole normale sup´erieure, Coll`ege de France, PSL Research University 75005 Paris, France" 6b0b10836197d7934f53080a39787b7d8d2b81f2,Detecting Granger-causal relationships in global spatio-temporal climate data via multitask learning,"Detecting Granger-causal relationships in global spatio-temporal climate data via multi-task learning Matthias Demuzere Christina Papagiannopoulou Diego G. Miralles Ghent University Ghent University Ghent University Niko E. C. Verhoest Ghent University Willem Waegeman Ghent University" 6b59716a193d3f91f88277e4c8a0f4cd0b6873c4,Detection of Deception in the Mafia Party Game,"Detection of Deception in the Mafia Party Game Sergey Demyanov James Bailey Kotagiri Ramamohanarao Christopher Leckie Department of Computing and Information Systems The University of Melbourne, Melbourne, VIC, Australia" 6b6e2c2ff6fcc5837523940c69cf2e9e94bc0503,Unsupervised Deep Video Hashing with Balanced Rotation,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 6b2db002cbc5312e4796de4d4b14573df2c01648,Learning Hierarchical Features from Deep Generative Models,"Learning Hierarchical Features from Deep Generative Models Shengjia Zhao 1 Jiaming Song 1 Stefano Ermon 1" 6b6493551017819a3d1f12bbf922a8a8c8cc2a03,Pose Normalization for Local Appearance-Based Face Recognition,"Pose Normalization for Local Appearance-Based Face Recognition Hua Gao, Hazım Kemal Ekenel, and Rainer Stiefelhagen Computer Science Department, Universit¨at Karlsruhe (TH) Am Fasanengarten 5, Karlsruhe 76131, Germany http://isl.ira.uka.de/cvhci" 6b089627a4ea24bff193611e68390d1a4c3b3644,PAID I CROSS-POLLINATION OF NORMALISATION TECHNIQUES FROM SPEAKER TO FACE AUTHENTICATION USING GAUSSIAN MIXTURE MODELS,"CROSS-POLLINATION OF NORMALISATION TECHNIQUES FROM SPEAKER TO FACE AUTHENTICATION USING GAUSSIAN MIXTURE MODELS Roy Wallace Mitchell McLaren Chris McCool Sébastien Marcel Idiap-RR-03-2012 JANUARY 2012 Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" 6bf57ae6c63873253d1b95782f8c6b7bbc91b9ac,Semantic face segmentation from video streams in the wild,"UNIVERSITAT POLITÈCNICA DE CATALUNYA Universitat de Barcelona Universitat Rovira i Virgili MASTER THESIS Semantic face segmentation from video streams in the wild Author: Deividas SKIPARIS Academic Supervisor: Dr. Sergio ESCALERA Industry Supervisor: Dr. Pascal LANDRY A thesis submitted in fulfillment of the requirements for the degree of Master of Artificial Intelligence in the Facultat d’Informàtica de Barcelona (FIB) Facultat de Matemàtiques (UB) Escola Tècnica Superior d’Enginyeria (URV) June 16, 2017" 6b95a3dbec92071c8552576930e69455c70e529c,BEGAN: Boundary Equilibrium Generative Adversarial Networks,"BEGAN: Boundary Equilibrium Generative Adversarial Networks David Berthelot, Thomas Schumm, Luke Metz Google" 6bcfcc4a0af2bf2729b5bc38f500cfaab2e653f0,Facial Expression Recognition in the Wild Using Improved Dense Trajectories and Fisher Vector Encoding,"Facial expression recognition in the wild using improved dense trajectories and Fisher vector encoding Sadaf Afshar1 Albert Ali Salah2 Computational Science and Engineering Program, Bo˘gazic¸i University, Istanbul, Turkey Department of Computer Engineering, Bo˘gazic¸i University, Istanbul, Turkey {sadaf.afshar," 6bf4f5f6f1fc30e7886812cc352ce6c2c95ae6e9,MGS2 : Optimisation multicrit ères de contours actifs par algorithmes génétiques,"MGS2 : Optimisation multicrit`eres de contours actifs par algorithmes g´en´etiques Nicolas CLADEL, Renaud S ´EGUIER ´Equipe SCEE (Supelec - IETR) Supelec, avenue de la boulaie, BP 81127, 35511 Cesson-S´evign´e Cedex, France R´esum´e – Dans cet article nous proposons une ´evolution de notre pr´ec´edent travail sur l’optimisation multicrit`eres de contours actifs. Cette pproche permet une exploration globale de l’image et une gestion efficace de plusieurs ´energies par la repr´esentation de Pareto. Notre nouvel lgorithme, le MultiObjective Genetic Snakes 2 (MGS2), associe l’algorithme multicrit`eres NSGA2 [4] au codage des contours actifs des MGS [3]. Les MGS2 exploitent de nouvelles ´energies d’attache `a l’image afin d’assurer la convergence des contours vers un objet creux en environ- nement bruit´e `a partir d’une initialisation al´eatoire. Nous proc´edons ici `a l’´etude de ces ´energies et `a l’analyse de la convergence de l’algorithme `a travers une s´erie de tests sur une base d’objets synth´etiques. Nous pr´esenterons ´egalement des r´esultats de l’application de MGS2 `a la lecture labiale." 6badfb6f273dce55ed058abe19c292f2519d12f6,Parts-based face detection at multiple views,"Savakis A. and Higgs D. (2007). PARTS-BASED FACE DETECTION AT MULTIPLE VIEWS. In Proceedings of the Second International Conference on Computer Vision Theory and Applications - IU/MTSV, pages 298-301 Copyright c(cid:13) SciTePress" 6bb55ed3761eb1556acbd1a0d15c2c9099bab0b7,Temporally Coherent Bayesian Models for Entity Discovery in Videos by Tracklet Clustering,"Temporally Coherent Chinese Restaurant Process for Discovery of Persons and Corresponding Tracklets from User-generated Videos" 6b6ff9d55e1df06f8b3e6f257e23557a73b2df96,Survey of Threats to the Biometric Authentication Systems and Solutions,"International Journal of Computer Applications (0975 – 8887) Volume 61– No.17, January 2013 Survey of Threats to the Biometric Authentication Systems and Solutions Sarika Khandelwal Research Scholor,Mewar University,Chitorgarh. (INDIA) P.C.Gupta Kota University,Kota(INDIA) Khushboo Mantri M.tech.student, Arya College of engineering ,Jaipur(INDIA)" 6bcc2b50e32bdbb0c668f75000badf21e6cd0839,Knowledge Projection for Deep Neural Networks,"Knowledge Projection for Effective Design of Thinner and Faster Deep Neural Networks Zhi Zhang, Guanghan Ning, and Zhihai He" 6b8a5a2d018356b396301b27156fd69dd18b1d82,A Study on the Impact of Wavelet Decomposition on Face Recognition Methods,"International Journal of Computer Applications (0975 – 8887) Volume 87 – No.3, February 2014 A Study on the Impact of Wavelet Decomposition on Face Recognition Methods M. M. Mohie El-Din1, Neveen. I. Ghali2, Ahmed. A. A. G1 and H. A. El Shenbary 1 Department of Mathematics and Computer Science, Faculty of Science, Al-Azhar University, Cairo, Egypt Assoc. Prof Computer Science, Faculty of Science, Al-Azhar University, Cairo. Egypt" 6b3c9c0e4d47bd960c0adc4d13ae524a5d9b94d1,Visual Multiple-Object Tracking for Unknown Clutter Rate,"Visual Multiple-Object Tracking for Unknown Clutter Rate Du Yong Kim" 6b4da897dce4d6636670a83b64612f16b7487637,Learning from Simulated and Unsupervised Images through Adversarial Training,"This paper has been submitted for publication on November 15, 2016. Learning from Simulated and Unsupervised Images through Adversarial Training Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda Wang, Russ Webb Apple Inc" 6bca057c25b48fa7d1607e5701c46392ec906822,An ordered topological representation of 3D triangular mesh facial surface: Concept and applications,"Werghi et al. EURASIP Journal on Advances in Signal Processing 2012, 2012:144 http://asp.eurasipjournals.com/content/2012/1/144 RESEARCH Open Access An ordered topological representation of 3D triangular mesh facial surface: concept and pplications Naoufel Werghi1*, Mohamed Rahayem2 and Johan Kjellander2" 6bf58047438f54720e03252d50984d1a340a116a,Discriminative Autoencoders for Small Targets Detection,"Discriminative Autoencoders for Small Targets Detection. Sebastien Razakarivony SAGEM D.S. – SAFRAN Group CNRS UMR 6072 – University of Caen – ENSICAEN Email: Fr´ed´eric Jurie CNRS UMR 6072 – University of Caen – ENSICAEN Email:" 6bd6460ec06adc1bd69d9517d116fd1545c04ac7,Small sample scene categorization from perceptual relations,"In the Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2012 Small Sample Scene Categorization from Perceptual Relations Ilan Kadar and Ohad Ben-Shahar Dept. of Computer Science, Ben-Gurion University Beer-Sheva, Israel" 6b02d73f097d745e58bb99a880e559b78c4594a1,Cross-Domain Face Verification: Matching ID Document and Self-Portrait Photographs,"Cross-Domain Face Verification: Matching ID Document and Self-Portrait Photographs Guilherme Folego 1,2 ∗ Marcus A. Angeloni 1,2 Jos´e Augusto Stuchi 2,3 Alan Godoy 1,2 Anderson Rocha 2 CPqD Foundation, Brazil University of Campinas (Unicamp), Brazil Phelcom Technologies, Brazil" 6bbcec054017a6fd64af8bf325cb6e3e7244ba55,On the Benefits and the Limits of ` p-norm Multiple Kernel Learning In Image Classification,"On the Benefits and the Limits of (cid:96)p-norm Multiple Kernel Learning In Image Classification Alexander Binder Technical University of Berlin Franklinstr. 28/29, 10587 Berlin, Germany Shinichi Nakajima NIKON Corporation Optical Research Laboratory, Tokyo, Japan Marius Kloft Technical University of Berlin Christina M¨uller Technical University of Berlin Wojciech Samek Technical University of Berlin Ulf Brefeld Yahoo! Research Barcelona, Spain Klaus-Robert M¨uller Technical University of Berlin Motoaki Kawanabe" 6bee77418af305d632b21eb03872a0d268eeebac,Understanding the Intrinsic Memorability of Images,"Understanding the Intrinsic Memorability of Images Phillip Isola Devi Parikh TTI-Chicago Antonio Torralba Aude Oliva" 6b5850c5a288fd26480ebcbbfc43172597e0d442,PHARMACOLOGICAL EFFECTS ON SOCIAL INTERACTION 1 Effects of Pharmacological Manipulations on Natural Social Interaction in Rhesus Macaques : A Pilot Investigation,"PHARMACOLOGICAL EFFECTS ON SOCIAL INTERACTION Effects of Pharmacological Manipulations on Natural Social Interaction in Rhesus Macaques: A Pilot Investigation Angelica Fuentes Spring, 2017 Cognitive Science Advisor: Steve W. Chang" 6b18628cc8829c3bf851ea3ee3bcff8543391819,Face recognition based on subset selection via metric learning on manifold,"Hong Shao, Shuang Chen, Jie-yi Zhao, Wen-cheng Cui, Tian-shu Yu, 2015. Face recognition based on subset selection via metric learning on manifold. 058. [doi:10.1631/FITEE.1500085] Face recognition based on subset selection via metric learning on manifold Key words: Face recognition, Sparse representation, Manifold structure, Metric learning, Subset selection Contact: Shuang Chen E-mail: ORCID: http://orcid.org/0000-0001-7441-4749 Front Inform Technol & Electron Eng" 6b6791c0a3f06c356035747f7e5f87d54bc5a657,A Neuro Fuzzy approach for Facial Expression Recognition using LBP Histograms,"International Journal of Computer Theory and Engineering, Vol. 2, No. 2 April, 2010 793-8201 A Neuro Fuzzy approach for Facial Expression Recognition using LBP Histograms V. Gomathi, Dr. K. Ramar, and A. Santhiyaku Jeevakumar" 6b6946ce943da5ba4bf6471609d3355cadec172e,Improvement of Facial Emotion Recognition Using Skin Color and Face Components kowsar,"International journal of Computer Science & Network Solutions April.2014-Volume 2.No4 http://www.ijcsns.com ISSN 2345-3397 Improvement of Facial Emotion Recognition Using Skin Color and Face Components Department of Computer Engineering, khouzestan Science and Research Branch, Islamic Azad kowsar azadmanesh, Reza javidan, S. Enayatolah Alavi Computer Engineering and IT Department Shiraz University of Technology, Shiraz, Iran, Department of computer Engineering, shahid chamran university, Ahvaz, Iran, University, Ahvaz, Iran," 6b4d1c0ddf606c84148edd889db231f67703ef3e,A comparison of techniques for robust gender recognition,"Repositorio Institucional de la Universidad Autónoma de Madrid https://repositorio.uam.es Esta es la versión de autor del congreso publicado en: This is an author produced version of a paper published in: Image Processing (ICIP), 2011 18th IEEE International Conference on. DOI: http://dx.doi.org/10.1109/ICIP.2011.6116610 IEEE, 2011. 561 - 564 Copyright: © 2011 IEEE El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription" e4a5ff03ac258f1bcc9c214c30497610b3d5faa2,DropBlock: A regularization method for convolutional networks,"DropBlock: A regularization method for onvolutional networks Golnaz Ghiasi Google Brain Tsung-Yi Lin Google Brain Quoc V. Le Google Brain" e4d08ef1b4350c7e03bdfb716200370c2ea87a6a,A novel approach for face recognition using fused GMDH-based networks,"The International Arab Journal of Information Technology, Vol. 15, No. 3, May 2018 369 A Novel Approach for Face Recognition Using Fused GMDH-Based Networks El-Sayed El-Alfy1, Zubair Baig2, and Radwan Abdel-Aal1 College of Computer Sciences and Engineering, King Fahd University of Petroleum and Minerals, KSA School of Science and Security Research Institute, Edith Cowan University, Australia" e467f7e2434ca74bdd4b19808a6b3d78b8c5ba1a,Feature Construction Using Evolution-COnstructed Features for General Object Recognition,"Feature Construction Using Evolution-COnstructed Features for General Object Recognition Kirt Dwayne Lillywhite A dissertation submitted to the faculty of Brigham Young University in partial fulfillment of the requirements for the degree of Doctor of Philosophy Dah-Jye Lee, Chair James K Archibald Bryan S. Morse Dan A. Ventura Brent E. Nelson Department of Electrical and Computer Engineering Brigham Young University April 2012 Copyright c(cid:13) 2012 Kirt Dwayne Lillywhite All Rights Reserved" e4501da190012623d5048d57b7e650de27643b8d,Learning Actionlet Ensemble for 3D Human Action Recognition,"Chapter 2 Learning Actionlet Ensemble for 3D Human Action Recognition" e4d4346bd415c6fa9187c16a9b7f5c69f48f1ec4,Towards High Performance Video Object Detection for Mobiles,"Towards High Performance Video Object Detection for Mobiles Xizhou Zhu(cid:63) Jifeng Dai Xingchi Zhu(cid:63) Yichen Wei Lu Yuan Microsoft Research Asia" e4d33362b4f99ab77fd6ceaafa183c087c79faea,Design and implementation of a high performance pedestrian detection,"June 23-26, 2013, Gold Coast, Australia 978-1-4673-2754-1/13/$31.00 ©2013 Crown" e475e857b2f5574eb626e7e01be47b416deff268,Facial Emotion Recognition Using Nonparametric Weighted Feature Extraction and Fuzzy Classifier,"Facial Emotion Recognition Using Nonparametric Weighted Feature Extraction and Fuzzy Classifier Maryam Imani and Gholam Ali Montazer" e4afc03c818bc9e357ea2fb23ebf73496f1ffc81,Mafalda Libório Baio Morais Alves,"Universidade do Minho Escola de Psicologia Mafalda Libório Baio Morais Alves Physical attractiveness: sexual satisfaction, promiscuity and infidelity janeiro de 2018" e46732f0c818b059420f68162363c9d1a9dc5395,Geometric and Physical Constraints for Head Plane Crowd Density Estimation in Videos.,"Geometric and Physical Constraints for Head Plane Crowd Density Estimation in Videos Weizhe Liu(cid:63) Krzysztof Lis Mathieu Salzmann Pascal Fua Computer Vision Laboratory, ´Ecole Polytechnique F´ed´erale de Lausanne {weizhe.liu, krzysztof.lis, mathieu.salzmann, (EPFL)" e4cbe39daed8700a1d6f4a25a3a98645c4f231d0,A nonconvex formulation for low rank subspace clustering: algorithms and convergence analysis,"Comput Optim Appl (2018) 70:395–418 https://doi.org/10.1007/s10589-018-0002-6 A nonconvex formulation for low rank subspace lustering: algorithms and convergence analysis Hao Jiang1 · Daniel P. Robinson1 René Vidal1 · Chong You1 Received: 14 July 2017 / Published online: 27 March 2018 © Springer Science+Business Media, LLC, part of Springer Nature 2018" e44f59da5b123da999738d10954a54e2fb635eda,Combined Correlation Rules to Detect Skin based on Dynamic Color Clustering, e43cc682453cf3874785584fca813665878adaa7,Face Recognition using Local Derivative Pattern Face Descriptor,"www.ijecs.in International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 3 Issue 10 October, 2014 Page No.8830-8834 Face Recognition using Local Derivative Pattern Face Descriptor Pranita R. Chavan1, Dr. Dnyandeo J. Pete2 Department of Electronics and Telecommunication Datta Meghe College of Engineering Airoli, Navi Mumbai, India 1,2 Mob: 99206746061 Mob: 99870353142" e48fa574960b23ba65b7ff1a732cc521213b5120,Mining Automatically Estimated Poses from Video Recordings of Top Athletes,"Mining Automatically Estimated Poses from Video Recordings of Top Athletes Rainer Lienhart∗ University of Augsburg uni-augsburg.de Moritz Einfalt University of Augsburg uni-augsburg.de Dan Zecha University of Augsburg" e4d0e87d0bd6ead4ccd39fc5b6c62287560bac5b,Implicit video multi-emotion tagging by exploiting multi-expression relations,"Implicit Video Multi-Emotion Tagging by Exploiting Multi-Expression Relations Zhilei Liu, Shangfei Wang*, Zhaoyu Wang and Qiang Ji" e480f8c00dfe217653c2569d0eec6e2ffa836d59,The “Something Something” Video Database for Learning and Evaluating Visual Common Sense,"The “something something” video database for learning and evaluating visual common sense Raghav Goyal Samira Ebrahimi Kahou Vincent Michalski Joanna Materzy´nska Susanne Westphal Heuna Kim Valentin Haenel Ingo Fruend Peter Yianilos Moritz Mueller-Freitag Florian Hoppe Christian Thurau Ingo Bax Roland Memisevic" e4896772d51a66b743e0d072d53cf26f6b61fc75,Automated Identification of Trampoline Skills Using Computer Vision Extracted Pose Estimation,"Automated Identification of Trampoline Skills Using Computer Vision Extracted Pose Estimation Paul W. Connolly, Guenole C. Silvestre and Chris J. Bleakley School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland." e45bcda905b897513f4cff9e5c0a5bf475674a02,"Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation","Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation Aysegul Dundar, Ming-Yu Liu, Ting-Chun Wang, John Zedlewski, Jan Kautz NVIDIA" e40007540c4813c81bc8b54dda4dd6f6c21deaa8,D Face Recognition using Patch Geodesic Derivative Pattern,"International Journal of Smart Electrical Engineering, Vol.2, No.3, Summer 2013 ISSN: 2251-9246 pp.127:132 D Face Recognition using Patch Geodesic Derivative Pattern" e443cb55dcc54de848e9f0c11a6194568a875011,From passive to interactive object learning and recognition through self-identification on a humanoid robot,"From passive to interactive object learning and recognition through self-identification on a humanoid robot Natalia Lyubova, Serena Ivaldi, David Filliat To cite this version: Natalia Lyubova, Serena Ivaldi, David Filliat. From passive to interactive object learning and recognition through self-identification on a humanoid robot. Autonomous Robots, Springer Verlag, 2015, pp.23. . HAL Id: hal-01166110 https://hal.archives-ouvertes.fr/hal-01166110 Submitted on 22 Jun 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," e496d6be415038de1636bbe8202cac9c1cea9dbe,Facial Expression Recognition in Older Adults using Deep Machine Learning,"Facial Expression Recognition in Older Adults using Deep Machine Learning Andrea Caroppo, Alessandro Leone and Pietro Siciliano National Research Council of Italy, Institute for Microelectronics and Microsystems, Lecce, Italy" e4abc40f79f86dbc06f5af1df314c67681dedc51,Head Detection with Depth Images in the Wild,"Head Detection with Depth Images in the Wild Diego Ballotta, Guido Borghi, Roberto Vezzani and Rita Cucchiara Department of Engineering ”Enzo Ferrari” University of Modena and Reggio Emilia, Italy Keywords: Head Detection, Head Localization, Depth Maps, Convolutional Neural Network" e4dc24e4926df4de3e8d7ca7cd1f4115e91f03e1,Instance-level video segmentation from object tracks Anonymous CVPR submission,"CVPR 2016 Submission #185. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. Instance-level video segmentation from object tracks Anonymous CVPR submission Paper ID 185" e42e7735f94a8f498ef0bf790ab43a668f904848,Low-Latency Detec on and Tracking of Aircra in Very High-Resolu on Video Feeds,"Linköping University | Department of Computer and Information Science Master thesis, 30 ECTS | Datateknik 018 | LIU-IDA/LITH-EX-A--18/022--SE Low-Latency Detec(cid:415)on and Tracking of Aircra(cid:332) in Very High-Resolu(cid:415)on Video Feeds Låglatent detek(cid:415)on och spårning av flygplan i högupplösta videokällor Jarle Mathiesen Supervisor : Magnus Bång Examiner : Erik Berglund Linköpings universitet SE–581 83 Linköping +46 13 28 10 00 , www.liu.se" e4d90019c312ed87a236a11374caeea9cc4e6940,Comparison Comparison PCA Train GMM Feature Reduction Classify GMM Threshold,"COVER SHEET Cook, Jamie and Chandran, Vinod and Sridharan, Sridha and Fookes, Clinton (2004) Face Recognition from 3D Data using Iterative Closest Point Algorithm and Gaussian Mixture Models. In Proceedings 3D Data Processing, Visualisation and Transmission, Thessaloniki, Greece. Accessed from http://eprints.qut.edu.au Copyright 2004 the authors." e4391993f5270bdbc621b8d01702f626fba36fc2,Head Pose Estimation Using Multi-scale Gaussian Derivatives,"Author manuscript, published in ""18th Scandinavian Conference on Image Analysis (2013)"" DOI : 10.1007/978-3-642-38886-6_31" e4c2f8e4aace8cb851cb74478a63d9111ca550ae,Distributed One-Class Learning,"DISTRIBUTED ONE-CLASS LEARNING Ali Shahin Shamsabadi(cid:63), Hamed Haddadi†, Andrea Cavallaro(cid:63) (cid:63)Queen Mary University of London,†Imperial College London" e4f032ee301d4a4b3d598e6fa6cffbcdb9cdfdd1,Facial Landmark Point Localization using Coarse-to-Fine Deep Recurrent Neural Network,"MAHPOD et al.: CCNN Facial Landmark Point Localization using Coarse-to-Fine Deep Recurrent Neural Network Shahar Mahpod, Rig Das, Emanuele Maiorana, Yosi Keller, and Patrizio Campisi," e4485930357db8248543eb78ce3bc9f32050694e,Drawn to danger: trait anger predicts automatic approach behaviour to angry faces.,"Cognition and Emotion ISSN: 0269-9931 (Print) 1464-0600 (Online) Journal homepage: http://www.tandfonline.com/loi/pcem20 Drawn to danger: trait anger predicts automatic pproach behaviour to angry faces Lotte Veenstra, Iris K. Schneider, Brad J. Bushman & Sander L. Koole To cite this article: Lotte Veenstra, Iris K. Schneider, Brad J. Bushman & Sander L. Koole (2016): Drawn to danger: trait anger predicts automatic approach behaviour to angry faces, Cognition nd Emotion, DOI: 10.1080/02699931.2016.1150256 To link to this article: http://dx.doi.org/10.1080/02699931.2016.1150256 Published online: 19 Feb 2016. Submit your article to this journal Article views: 39 View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pcem20 Download by: [Vrije Universiteit Amsterdam] Date: 04 April 2016, At: 13:19" e4d8ba577cabcb67b4e9e1260573aea708574886,Um Sistema De Recomendaç˜ao Inteligente Baseado Em V ´ Idio Aulas Para Educaç˜ao a Distˆancia an Intelligent Recommendation System Based on Video Lectures for Distance Education (revelation),"UM SISTEMA DE RECOMENDAC¸ ˜AO INTELIGENTE BASEADO EM V´IDIO AULAS PARA EDUCAC¸ ˜AO A DIST ˆANCIA Gaspare Giuliano Elias Bruno Tese de Doutorado apresentada ao Programa de P´os-gradua¸c˜ao em Engenharia de Sistemas e Computa¸c˜ao, COPPE, da Universidade Federal do Rio de Janeiro, como parte dos requisitos necess´arios `a obten¸c˜ao do t´ıtulo de Doutor em Engenharia de Sistemas e Computa¸c˜ao. Orientadores: Edmundo Albuquerque de Souza e Silva Rosa Maria Meri Le˜ao Rio de Janeiro Janeiro de 2016" e48432872be1e0449f50c6807b274d57c87a641f,Human Body Extraction from Single Images Using Images Processing Techniques,"Human Body Extraction from Single Images Using Images Processing Techniques T.Ravichandra Babu Associate Professor & HOD, Department of ECE, Katravath Rajendhar PG Scholar-SSP, Department of ECE, Krishnamurthy Institute of Technology and Krishnamurthy Institute of Technology and Engineering. Engineering. that can images to cope with" e4d2cc8fe567e8e1f2e0c5eb751ff9e9361346c0,ALTERED BRAIN ACTIVITY IN AUTISTIC CHILDREN VERSUS HEALTHY CONTROLS WHILE PERFORMING SIMPLE TASKS USING fMRI by Donald,"Copyright Warning & Restrictions The copyright law of the United States (Title 17, United States Code) governs the making of photocopies or other reproductions of copyrighted material. Under certain conditions specified in the law, libraries and rchives are authorized to furnish a photocopy or other reproduction. One of these specified conditions is that the photocopy or reproduction is not to be “used for any purpose other than private study, scholarship, or research.” If a, user makes a request for, or later uses, a photocopy or reproduction for purposes in excess of “fair use” that user may be liable for copyright infringement, This institution reserves the right to refuse to accept a opying order if, in its judgment, fulfillment of the order would involve violation of copyright law. Please Note: The author retains the copyright while the New Jersey Institute of Technology reserves the right to distribute this thesis or dissertation Printing note: If you do not wish to print this page, then select “Pages from: first page # to: last page #” on the print dialog screen" e4660f26d3d752349ec72c1f7ad6d14b13ab95c9,LIMO: Lidar-Monocular Visual Odometry,"LIMO: Lidar-Monocular Visual Odometry Johannes Graeter1, Alexander Wilczynski1 and Martin Lauer1" e43ea078749d1f9b8254e0c3df4c51ba2f4eebd5,Facial Expression Recognition Based on Constrained Local Models and Support Vector Machines,"Facial Expression Recognition Based on Constrained Local Models and Support Vector Machines Nikolay Neshov1, Ivo Draganov2, Agata Manolova3" eefb8768f60c17d76fe156b55b8a00555eb40f4d,Subspace Scores for Feature Selection in Computer Vision,"Subspace Scores for Feature Selection in Computer Vision Cameron Musco Christopher Musco" eec95bb8825f0f761706f2a89c6d078d6438590e,LandmarkBoost: Efficient Visual Context Classifiers for Robust Localization,"LandmarkBoost: Efficient Visual Context Classifiers for Robust Localization Marcin Dymczyk∗, Igor Gilitschenski‡, Juan Nieto∗, Simon Lynen∗†, Bernhard Zeisl†, and Roland Siegwart∗ Autonomous Systems Lab, ETH Z¨urich, †Google Inc., Z¨urich, ‡CSAIL, MIT" ee92d36d72075048a7c8b2af5cc1720c7bace6dd,Face recognition using mixtures of principal components,"FACE RECOGNITION USING MIXTURES OF PRINCIPAL COMPONENTS Deepak S. Turaga and Tsuhan Chen Video and Display Processing Philips Research USA Briarcliff Manor, NY 10510" ee87aa52d9642607d86f011c0d7326c4bdc63121,Automatic Detection of Facial Midline as a Guide for Facial Feature Extraction,"Automatic Detection of Facial Midline s a Guide for Facial Feature Extraction Nozomi Nakao, Wataru Ohyama, Tetsushi Wakabayashi and Fumitaka Kimura Graduate School of Engineering, Mie University 577 Kurimamachiya-cho, Tsu-shi, Mie, 5148507, Japan" eee8a37a12506ff5df72c402ccc3d59216321346,Volume C,"Uredniki: dr. Tomaž Erjavec Odsek za tehnologije znanja Institut »Jožef Stefan«, Ljubljana dr. Jerneja Žganec Gros Alpineon d.o.o, Ljubljana Založnik: Institut »Jožef Stefan«, Ljubljana Tisk: Birografika BORI d.o.o. Priprava zbornika: Mitja Lasič Oblikovanje naslovnice: dr. Damjan Demšar Tiskano iz predloga avtorjev Naklada: 50 Ljubljana, oktober 2008 Konferenco IS 2008 sofinancirata Ministrstvo za visoko šolstvo, znanost in tehnologijo Institut »Jožef Stefan« Informacijska družba ISSN 1581-9973 CIP - Kataložni zapis o publikaciji Narodna in univerzitetna knjižnica, Ljubljana" ee9385efb66ee0b1bee31c1632141729bb7fb6f5,Numerical simplification for bloat control and analysis of building blocks in genetic programming,"Noname manuscript No. (will be inserted by the editor) Numerical Simplification for Bloat Control and Analysis of Building Blocks in Genetic Programming David Kinzett · Mark Johnston · Mengjie Zhang the date of receipt and acceptance should be inserted later" eeec69e910430bebe3808773f5a6a155d77059a0,Multi-shot Pedestrian Re-identification via Sequential Decision Making,"Multi-shot Pedestrian Re-identification via Sequential Decision Making Jianfu Zhang1, Naiyan Wang2 and Liqing Zhang1 Shanghai Jiao Tong University∗, 2TuSimple" eed1dd2a5959647896e73d129272cb7c3a2e145c,The Elements of Fashion Style,"INPUTSTYLE DOCUMENTTOP ITEMS“ ”I need an outfit for a beach wedding that I'm going to early this summer. I'm so excited -- it's going to be warm and exotic and tropical... I want my outfit to look effortless, breezy, flowy, like I’m floating over the sand! Oh, and obviously no white! For a tropical spot, I think my outfit should be bright and" eedfb384a5e42511013b33104f4cd3149432bd9e,Multimodal probabilistic person tracking and identification in smart spaces,"Multimodal Probabilistic Person Tracking and Identification in Smart Spaces zur Erlangung des akademischen Grades eines Doktors der Ingenieurwissenschaften der Fakultät für Informatik der Universität Fridericiana zu Karlsruhe (TH) genehmigte Dissertation Keni Bernardin us Karlsruhe Tag der mündlichen Prüfung: 20.11.2009 Erster Gutachter: Zweiter Gutachter: Prof. Dr. A. Waibel Prof. Dr. R. Stiefelhagen" ee4fd1a1df6a01e7dabe82090b1024e2eb6d78a1,Effective Emotional Classification Combining Facial Classifiers and User Assessment,"Effective Emotional Classification Combining Facial Classifiers and User Assessment Isabelle Hupont1, Sandra Baldassarri2, Rafael Del Hoyo1, and Eva Cerezo2 Instituto Tecnológico de Aragón, Zaragoza (Spain) Departamento de Informática e Ingeniería de Sistemas, Instituto de Investigación en Ingeniería de Aragón, Universidad de Zaragoza (Spain)" eebe66c4d1a41b3c7830846306044c8f3fe0d350,Domain adaptation networks for noisy image classification Master Thesis,"Faculty of Electrical Engineering, Mathematics and Computer Science Department of Intelligent Systems Domain adaptation networks for noisy image lassification Master Thesis Chengqiu Zhang Committee: Supervisors: Dr. Jan van Gemert Prof. Martha Larson Dr. Silvia-Laura Pintea Dr. Jan van Gemert Dr. Ildiko Suveg Dr. Marco Loog Dr. Silvia-Laura Pintea Dr. Adriana Gonzalez Eindhoven, Aug 2017" eed98eb53b34820df736203d62076eff81de926e,Scene Segmentation and Object Classification for Place Recognition,"Dr. Mongi A. Abidi, Major Professor To the Graduate Council: I am submitting herewith a dissertation written by Chang Cheng entitled “Scene Segmentation and Object Classification for Place Recognition.” I have examined the final electronic copy of this dissertation for form and content and recommend that it be accepted in partial fulfillment of the requirements for the degree of Doctor of Philosophy, with a major in Electrical Engineering. We have read this dissertation nd recommend its acceptance: Dr. Seddik M. Djouadi Dr. Andreas Koschan Dr. Hairong Qi Dr. Timothy M. Young Accepted for the Council: Carolyn R. Hodges Vice Provost and Dean of the Graduate School" eef297f46b0f6deedde6b74fcd0b44a7a8df0d8b,"Performance evaluation of face alignment algorithms on "" inthe-wild "" selfies","ISSN 2464-4617 (print) ISSN 2464-4625 (CD) Computer Science Research Notes CSRN 2802 Short Papers Proceedings http://www.WSCG.eu Performance evaluation of face alignment algorithms on ""in-the-wild"" selfies Ivan Babanin Aleksandr Mashrabov Moscow Institute of Physics and Technology, Adorable Inc. Department of Innovations and High Moscow Institute of Physics and Technology, Adorable Inc. Department of Innovations and High Technology Institutskiy Pereulok, 9 region, Dolgoprudny Technology" eef82228530a70a3158e59be2b0b07d6dccd8a88,Nonlinear supervised dimensionality reduction via smooth regular embeddings,"Nonlinear Supervised Dimensionality Reduction via Smooth Regular Embeddings Department of Electrical and Electronics Engineering, METU, Ankara Cem ¨Ornek and Elif Vural" eed25d9b5b5b28e8454a359d54c9de5a05cc4682,Context-aware home monitoring system for Parkinson ' s disease patients : ambient and wearable sensing for freezing of gait detection,"Context-aware Home Monitoring System for Parkinson’s Disease Patients Ambient and Wearable Sensing for Freezing of Gait Detection B(cid:2456)(cid:2459)(cid:2450)(cid:2460) T(cid:2442)(cid:2452)(cid:2442)(cid:20)(cid:2444)" eec466317c83e8093a32b978e753c3fc8f21d21b,Performance Characterization in Computer Vision A Tutorial,"Performance Characterization in Computer Vision A Tutorial Adrian F. Clark and Christine Clark VASE Laboratory, Electronic Systems Engineering University of Essex, Colchester, CO4 3SQ, UK This document provides a tutorial on performance characterization in computer vision. It explains why learning to characterize the performances of vision tech- niques is crucial to the discipline’s development. It describes the usual proce- dure for evaluating vision algorithms and its statistical basis. The use of a soft- ware tool, a so-called test harness, for performing such evaluations is described. The approach is illustrated on an example technique. Contents Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . The Performance Assessment and Characterization Processes . . . Assessing an Individual Algorithm . . . . . . . . . . . . . . . . . . . .1 The Receiver Operating Characteristic Curve . . . . . . . . . . . . .2 The Detection Error Trade-off Curve . . . . . . . . . . . . . . . . .3 Confusion Matrices . . . . . . . . . . . . . . . . . . . . . . . . . . Comparing Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ." ee3a905ec8cd2e62dc642fad33d6f5f8516968a8,It depends: Approach and avoidance reactions to emotional expressions are influenced by the contrast emotions presented in the task.,"tapraid5/zfn-xhp/zfn-xhp/zfn00515/zfn3313d15z xppws S⫽1 8/4/15 5:44 Art: 2014-0213 APA NLM Journal of Experimental Psychology: Human Perception and Performance 015, Vol. 41, No. 5, 000 0096-1523/15/$12.00 © 2015 American Psychological Association http://dx.doi.org/10.1037/xhp0000130 It Depends: Approach and Avoidance Reactions to Emotional Expressions re Influenced by the Contrast Emotions Presented in the Task AQ: au Andrea Paulus and Dirk Wentura Saarland University Studies examining approach and avoidance reactions to emotional expressions have yielded conflicting results. For example, expressions of anger have been reported to elicit approach reactions in some studies ut avoidance reactions in others. Nonetheless, the results were often explained by the same general underlying process, namely the influence that the social message signaled by the expression has on" ee463f1f72a7e007bae274d2d42cd2e5d817e751,Automatically Extracting Qualia Relations for the Rich Event Ontology,"Automatically Extracting Qualia Relations for the Rich Event Ontology Ghazaleh Kazeminejad1, Claire Bonial2, Susan Windisch Brown1 and Martha Palmer1 {ghazaleh.kazeminejad, susan.brown, University of Colorado Boulder, 2U.S. Army Research Lab" 7897f6a19d5211bf6387f5c9e141c90a0cc84566,One-shot Texture Segmentation,"One-shot Texture Segmentation Ivan Ustyuzhaninov University of Tübingen Claudio Michaelis University of Tübingen Wieland Brendel∗ University of Tübingen Matthias Bethge∗ University of Tübingen" 789c76749a15614d97ac8f4ec18b3ce7d80a2d28,Explorer Multiplicative LSTM for sequence modelling,"Multiplicative LSTM for sequence modelling Citation for published version: Krause, B, Murray, I, Renals, S & LU, L 2017, Multiplicative LSTM for sequence modelling. in International Conference on Learning Representations - ICLR 2017 - Workshop Track. pp. 2872-2880. Link: Link to publication record in Edinburgh Research Explorer Document Version: Publisher's PDF, also known as Version of record Published In: International Conference on Learning Representations - ICLR 2017 - Workshop Track General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) nd / or other copyright owners and it is a condition of accessing these publications that users recognise and bide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer ontent complies with UK legislation. If you believe that the public display of this file breaches copyright please ontact providing details, and we will remove access to the work immediately and investigate your claim. Download date: 02. Sep. 2017" 78045e2b93745b16a174137074e430ccd5ff53ff,Hedging Deep Features for Visual Tracking.,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI Hedging Deep Features for Visual Tracking Yuankai Qi, Shengping Zhang, Lei Qin, Qingming Huang, Hongxun Yao, Jongwoo Lim, and Ming-Hsuan Yang" 7854876ab5d87248ace94615731ed3e3e56af769,MixedPeds: Pedestrian Detection in Unannotated Videos Using Synthetically Generated Human-Agents for Training, 780772a69b1556d5f725630dff8e79ec3ccb46bb,FieldSAFE: Dataset for Obstacle Detection in Agriculture,"FieldSAFE: Dataset for Obstacle Detection in Agriculture Mikkel Kragh∗1, Peter Christiansen∗1, Morten S. Laursen1, Morten Larsen2, Kim A. Steen3, Ole Green3, Henrik Karstoft1 and Rasmus N. Jørgensen1 Department of Engineering, Aarhus University, Denmark Conpleks Innovation ApS, Struer, Denmark AgroIntelli, Aarhus, Denmark" 7858410077f9ba94ca60d0f6b4d29509e46a4ef9,Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning,"Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning Soravit Changpinyo U. of Southern California Los Angeles, CA Wei-Lun Chao Los Angeles, CA U. of Southern California U. of Southern California Fei Sha Los Angeles, CA" 78f438ed17f08bfe71dfb205ac447ce0561250c6,Bridging the Semantic Gap : Image and video Understanding by Exploiting Attributes, 788eceb4d1b7556d1c9033224da2348b4402d6ca,An Empirical Evaluation of Visual Question Answering for Novel Objects,"An Empirical Evaluation of Visual Question Answering for Novel Objects Santhosh K. Ramakrishnan1,2 Ambar Pal1 Gaurav Sharma1 Anurag Mittal2 IIT Kanpur∗ IIT Madras†" 786e57ed6877dc8491b1bb9253f8b82c02732977,Efficient approach to de-identifying faces in videos,"Page 1 of 8 An Efficient Approach to De-Identifying Faces in Videos Li Meng *, Zongji Sun, Odette Tejada Collado School of Engineering and Technology, University of Hertfordshire, College Lane, Hatfield, UK" 783f22f9ad77e437438f24f2d0a7c1397468ec88,A New Quadratic Classifier Applied to Biometric Recognition,"A New Quadratic Classifier applied to Biometric Recognition Carlos E. Thomaz1, Duncan F. Gillies1 and Raul Q. Feitosa2 Imperial College of Science Technology and Medicine, Department of Computing, 80 Queen’s Gate, London SW7 2BZ, United Kingdom State University of Rio de Janeiro, Department of Computer Engineering, r. São Francisco Xavier, Rio de Janeiro 20559-900, Brazil Catholic University of Rio de Janeiro, Department of Electrical Engineering, r. Marques de Sao Vicente 225, Rio de Janeiro 22453-900, Brazil" 78a2a964b61308f683fae6f3a62e3a8aece51bae,EXECUTIVE NEURAL CIRCUITRY IN INDIVIDUALS WITH HIGH-FUNCTIONING AUTISM,"FUNCTIONAL NEUROIMAGING OF THE INTERACTION BETWEEN SOCIAL AND EXECUTIVE NEURAL CIRCUITRY IN INDIVIDUALS WITH HIGH- FUNCTIONING AUTISM Kimberly Lynn Hills Carpenter A dissertation submitted to the faculty of the University of North Carolina at Chapel Hill in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Curriculum in Neurobiology Chapel Hill Approved By: Dr. Aysenil Belger Dr. Jim Bodfish Dr. Gabriel Dichter Dr. Kevin LaBar Dr. Joseph Piven Dr. Aldo Rustioni" 78df7d3fdd5c32f037fb5cc2a7c104ac1743d74e,Temporal Pyramid Pooling-Based Convolutional Neural Network for Action Recognition,"TEMPORAL PYRAMID POOLING CNN FOR ACTION RECOGNITION Temporal Pyramid Pooling Based Convolutional Neural Network for Action Recognition Peng Wang, Yuanzhouhan Cao, Chunhua Shen, Lingqiao Liu, and Heng Tao Shen" 78c91d969c55a4a61184f81001c376810cdbd541,A Spike and Slab Restricted Boltzmann Machine,"A Spike and Slab Restricted Boltzmann Machine Aaron Courville James Bergstra Yoshua Bengio DIRO, Universit´e de Montr´eal, Montr´eal, Qu´ebec, Canada" 787c1bb6d1f2341c5909a0d6d7314bced96f4681,"Face Detection and Verification in Unconstrained Videos : Challenges , Detection , and Benchmark Evaluation","Face Detection and Verification in Unconstrained Videos: Challenges, Detection, and Benchmark Evaluation Mahek Shah IIIT-D-MTech-CS-GEN-13-106 July 16, 2015 Indraprastha Institute of Information Technology, Delhi Thesis Advisors Dr. Mayank Vatsa Dr. Richa Singh Submitted in partial fulfillment of the requirements for the Degree of M.Tech. in Computer Science (cid:13) Shah, 2015 Keywords: face recognition, face detection, face verification" 7808937b46acad36e43c30ae4e9f3fd57462853d,Describing people: A poselet-based approach to attribute classification,"Describing People: A Poselet-Based Approach to Attribute Classification ∗ Lubomir Bourdev1,2, Subhransu Maji1 and Jitendra Malik1 EECS, U.C. Berkeley, Berkeley, CA 94720 Adobe Systems, Inc., 345 Park Ave, San Jose, CA 95110" 78598c69201cccfc060d47fc0415f2f9365035fc,A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision,"A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision Chi-Hao Wu, Qin Huang, Siyang Li, and C.-C. Jay Kuo, Fellow, IEEE" 78fdf2b98cf6380623b0e20b0005a452e736181e,Dense Wide-Baseline Stereo with Varying Illumination and its Application to Face Recognition, 78c9a63be8e07dc6acb90f4fe3f06821719eaa34,Hierarchical online domain adaptation of deformable part-based models,"Hierarchical online domain adaptation of deformable part-based models Jiaolong Xu1, David V´azquez2, Krystian Mikolajczyk3 and Antonio M. L´opez1" 788a3faa14ca191d7f187b812047190a70798428,Interpretable Set Functions,"Interpretable Set Functions Andrew Cotter, Maya Gupta, Heinrich Jiang, James Muller, Taman Narayan, Serena Wang, Tao Zhu 600 Amphitheatre Parkway, Mountain View, CA 94043 Google Research" 7882c67f555b761e10ecc70216db25382890d9d7,Automated Characterization of Stenosis in Invasive Coronary Angiography Images with Convolutional Neural Networks,"Automated Characterization of Stenosis in Invasive Coronary Angiography Images with Convolutional Neural Networks" 78749b58299ecebf100e2512872029f89878449b,One-class Selective Transfer Machine for Personalized Anomalous Facial Expression Detection, 782188821963304fb78791e01665590f0cd869e8,Automatic Spatially-Aware Fashion Concept Discovery,"sleevelengthincreasing dress length+ mini =(b) Structured product browsing(c) Attribute-feedback product retrieval(a) Concept discoveryminimidimaxisleevelessshort-sleevelong-sleeveblueblackredyellowFigure1.(a)Weproposeaconceptdiscoveryapproachtoauto-maticallyclusterspatially-awareattributesintomeaningfulcon-cepts.Thediscoveredspatially-awareconceptsarefurtherutilizedfor(b)structuredproductbrowsing(visualizingimagesaccordingtoselectedconcepts)and(c)attribute-feedbackproductretrieval(refiningsearchresultsbyprovidingadesiredattribute).variousfeedback,includingtherelevanceofdisplayedim-ages[20,4],ortuningparameterslikecolorandtexture,andthenresultsareupdatedcorrespondingly.However,rel-evancefeedbackislimitedduetoitsslowconvergencetomeetthecustomerrequirements.Inadditiontocolorandtexture,customersoftenwishtoexploithigher-levelfea-tures,suchasneckline,sleevelength,dresslength,etc.Semanticattributes[13],whichhavebeenappliedef-fectivelytoobjectcategorization[15,27]andfine-grainedrecognition[12]couldpotentiallyaddresssuchchallenges.Theyaremid-levelrepresentationsthatdescribesemanticproperties.Recently,researchershaveannotatedclotheswithsemanticattributes[9,2,8,16,11](e.g.,material,pat-tern)asintermediaterepresentationsorsupervisorysignalstobridgethesemanticgap.However,annotatingsemanticattributesiscostly.Further,attributesconditionedonob-jectpartshaveachievedgoodperformanceinfine-grainedrecognition[3,33],confirmingthatspatialinformationiscriticalforattributes.Thisalsoholdsforclothingimages.Forexample,thenecklineattributeusuallycorrespondstothetoppartinimageswhilethesleeveattributeordinarily1" 78f7304ba4c853c568dc4e38fef35aa2c003e3f3,Modeling correlations in spontaneous activity of visual cortex with centered Gaussian-binary deep Boltzmann machines.,"visual cortex with centered Gaussian-binary deep Boltzmann machines Nan Wang Institut f¨ur Neuroinformatik Ruhr-Universit¨at Bochum Bochum, 44780, Germany Dirk Jancke Institut f¨ur Neuroinformatik Ruhr-Universit¨at Bochum Bochum, 44780, Germany Laurenz Wiskott Institut f¨ur Neuroinformatik Ruhr-Universit¨at Bochum Bochum, 44780, Germany" 78a144d5dce1a61c92420e77c11116f541a7617f,Box Aggregation for Proposal Decimation: Last Mile of Object Detection,"Box Aggregation for Proposal Decimation: Last Mile of Object Detection The Chinese University of Hong Kong ♯Stanford University ‡Shanghai Jiao Tong University Shu Liu† Cewu Lu♯,‡ Jiaya Jia†" 789389dce27ad72adad251c81734bdb6c274c30f,3D facial feature localization for registration,"D Facial Feature Localization for Registration Albert Ali Salah and Lale Akarun Bo˘gazi¸ci University Computer Engineering Department, Turkey Perceptual Intelligence Laboratory {salah," 781d3550f54f3b4bfbd99ca9957aba6d6dec990e,Regularized Kernel Discriminant Analysis With a Robust Kernel for Face Recognition and Verification,"This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. Brief Papers Regularized Kernel Discriminant Analysis With a Robust Kernel for Face Recognition and Verification Stefanos Zafeiriou, Georgios Tzimiropoulos, Maria Petrou, nd Tania Stathaki" 7803206f024ba6887d93e8aec91dd0097ffc5165,Automatic detection of facial actions from 3D data,"Automatic Detection of Facial Actions from 3D Data Arman Savran Electrical and Electronics Engineering Department Bo˘gazic¸i University, Istanbul, Turkey B¨ulent Sankur" 78d00241fc9798eba895d41a0068715212a70489,Person identification from gait analysis with a depth camera at home,978-1-4244-9270-1/15/$31.00 ©2015 IEEE 781c2553c4ed2a3147bbf78ad57ef9d0aeb6c7ed,Tubelets: Unsupervised Action Proposals from Spatiotemporal Super-Voxels,"Int J Comput Vis DOI 10.1007/s11263-017-1023-9 Tubelets: Unsupervised Action Proposals from Spatiotemporal Super-Voxels Mihir Jain1 Cees G. M. Snoek1 · Jan van Gemert2 · Hervé Jégou3 · Patrick Bouthemy3 · Received: 25 June 2016 / Accepted: 18 May 2017 © The Author(s) 2017. This article is an open access publication" 783f3fccde99931bb900dce91357a6268afecc52,Adapted Active Appearance Models,"Hindawi Publishing Corporation EURASIP Journal on Image and Video Processing Volume 2009, Article ID 945717, 14 pages doi:10.1155/2009/945717 Research Article Adapted Active Appearance Models Renaud S´eguier,1 Sylvain Le Gallou,2 Gaspard Breton,2 and Christophe Garcia2 SUP ´ELEC/IETR, Avenue de la Boulaie, 35511 Cesson-S´evign´e, France Orange Labs—TECH/IRIS, 4 rue du clos courtel, 35 512 Cesson S´evign´e, France Correspondence should be addressed to Renaud S´eguier, Received 5 January 2009; Revised 2 September 2009; Accepted 20 October 2009 Recommended by Kenneth M. Lam Active Appearance Models (AAMs) are able to align ef‌f‌iciently known faces under duress, when face pose and illumination are ontrolled. We propose Adapted Active Appearance Models to align unknown faces in unknown poses and illuminations. Our proposal is based on the one hand on a specific transformation of the active model texture in an oriented map, which changes the AAM normalization process; on the other hand on the research made in a set of different precomputed models related to the most dapted AAM for an unknown face. Tests on public and private databases show the interest of our approach. It becomes possible to align unknown faces in real-time situations, in which light and pose are not controlled. Copyright © 2009 Renaud S´eguier et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly" 49957368eceaa751c0b9c49251512ca6a8800cff,Accurate Object Localization with Shape Masks,"Accurate Object Localization with Shape Masks Marcin Marsza(cid:7)ek Cordelia Schmid INRIA, LEAR - LJK 665 av de l’Europe, 38330 Montbonnot, France" 499ec985f911bfdd44ca67af223e08916f9ee8ea,AN ALGEBRAIC FRAMEWORK FOR CLASSIFIER DEVELOPMENT AND ITS APPLICATION IN FACE RECOGNITION,"AN ALGEBRAIC FRAMEWORK FOR CLASSIFIER DEVELOPMENT AND ITS APPLICATION IN FACE RECOGNITION A THESIS Submitted by K. R. SUJITH in ful(cid:2)llment for the award of the degree MASTER OF SCIENCE (BY RESEARCH) FACULTY OF INFORMATION AND COMMUNICATION ENGINEERING ANNA UNIVERSITY: CHENNAI 600 025 DECEMBER 2005" 49d4cb2e1788552a04c7f8fec33fbfabb3882995,Visually-Enabled Active Deep Learning for (Geo) Text and Image Classification: A Review,"Article Visually-Enabled Active Deep Learning for (Geo) Text and Image Classification: A Review Liping Yang 1,*, Alan M. MacEachren 1,* ID , Prasenjit Mitra 2 and Teresa Onorati 3 Department of Geography and Institute for CyberScience, The Pennsylvania State University, University Park, PA 16802, USA College of Information Sciences and Technology, The Pennsylvania State University, University Park, PA 16802, USA; Computer Science Department, Universidad Carlos III de Madrid, 28911-Leganés, Madrid, Spain; * Correspondence: (L.Y.); (A.M.M.) Received: 29 December 2017; Accepted: 17 February 2018; Published: 20 February 2018" 496074fcbeefd88664b7bd945012ca22615d812e,Driver Distraction Using Visual-Based Sensors and Algorithms,"Review Driver Distraction Using Visual-Based Sensors nd Algorithms Alberto Fernández 1,*, Rubén Usamentiaga 2, Juan Luis Carús 1 and Rubén Casado 2 Grupo TSK, Technological Scientific Park of Gijón, 33203 Gijón, Asturias, Spain; Department of Computer Science and Engineering, University of Oviedo, Campus de Viesques, 33204 Gijón, Asturias, Spain; (R.U.); (R.C.) * Corrospondence: Tel.: +34-984-29-12-12; Fax: +34-984-39-06-12 Academic Editor: Gonzalo Pajares Martinsanz Received: 14 July 2016; Accepted: 24 October 2016; Published: 28 October 2016" 49004f22a420e0897f7b811239c1e098b0c655bf,Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering,"Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering Medhini Narasimhan, Svetlana Lazebnik, Alexander G. Schwing University of Illinois Urbana-Champaign {medhini2, slazebni," 4919663c62174a9bc0cc7f60da8f96974b397ad2,Human age estimation using enhanced bio-inspired features (EBIF),"HUMAN AGE ESTIMATION USING ENHANCED BIO-INSPIRED FEATURES (EBIF) Mohamed Y.El Dib and Motaz El-Saban Faculty of Computers and Information, Cairo University, Cairo, Egypt" 499842b3df387b81dbb2436c764d22b1a3f42cae,Collaborative feature learning from social media,"Collaborative Feature Learning from Social Media Chen Fang1, Hailin Jin2, Jianchao Yang3, Zhe Lin2 Department of Computer Science, Dartmouth College. 2Adobe Research. 3Snapchat. Image feature representation plays an essential role in image recognition nd related tasks. The current state-of-the-art feature learning paradigm is supervised learning from labeled data [3], which surpasses other well- known hand-crafted feature based methods [4, 5]. However, this paradigm requires large datasets with category labels to train properly, which limits its pplicability to new problem domains where labels are hard to obtain. In this paper, we ask an interesting research question: Are category-level labels the only way for data driven feature learning? There is a surge of social media websites in the last ten years. Most social media websites such as Pinterest have been collecting content data that the users share as well as behavior data of the users. User behavior data are the activities of individual users, such as likes, comments, or view histories and they carry rich information about corresponding content data. For instance, two photos of a similar style on Pinterest tend to be pinned by the same user. If we aggregate the user behavior data across many users, we may recover interesting properties of the content. For instance, the photos liked by a group of users of similar interests tend to have very similar styles." 494e736c05ddf500830e9c51b5fb42be9b9bff1a,Learning Depth from Monocular Videos using Direct Methods, 494c1630c93e74aca3169ae33734f2f733c95e05,The Iris Challenge Evaluation 2005,"The Iris Challenge Evaluation 2005 P. Jonathon Phillips, Kevin W. Bowyer, Patrick J. Flynn, Xiaomei Liu, W. Todd Scruggs" 49df381ea2a1e7f4059346311f1f9f45dd997164,Client-Specific Anomaly Detection for Face Presentation Attack Detection,"On the Use of Client-Specific Information for Face Presentation Attack Detection Based on Anomaly Detection Shervin Rahimzadeh Arashloo and Josef Kittler," 49e1aa3ecda55465641b2c2acc6583b32f3f1fc6,Support Vector Machine for age classification,"International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (ISSN 2250-2459, Volume 2, Issue 5, May 2012) Support Vector Machine for age classification Sangeeta Agrawal1, Rohit Raja2, Sonu Agrawal3 Assistant Professor, CSE, RSR RCET, Kohka Bhilai ,3 Sr. Assistant Professor, CSE, SSCET, Junwani Bhilai" 49b2545b8b9ed81cc547ec974e0b61d01b7bc759,Examplers based image fusion features for face recognition,"Examplers based image fusion features for face recognition Alex Pappachen James*1 and Sima Dimitrijev2 *1 Asst. Professor and Group Lead, Machine Intelligence Group, Indian Institute of Information Technology and Management-Kerala, India. www.mirgroup.co.cc, Professor and Deputy Director,Queensland Micro- and Nanotechnology Center, Griffith University, Australia, www.gu.edu.au/qmnc" 499343a2fd9421dca608d206e25e53be84489f44,Face Recognition with Name Using Local Weber‟s Law Descriptor,"Anil Kumar.C, et.al, International Journal of Technology and Engineering Science [IJTES]TM Volume 1[9], pp: 1371-1375, December 2013 Face Recognition with Name Using Local Weber‟s Law Descriptor C.Anil kumar,2A.Rajani,3I.Suneetha M.Tech Student,2Assistant Professor,3Associate Professor Department of ECE, Annamacharya Institute of Technology and Sciences, Tirupati, India-517520 on FERET" 4928d4a458355bbf2a9e8a7567125dd06e459cf8,198 : 500 Light Seminar : Readings on Generic Object Recognition,"98:500 Light Seminar: Readings on Generic Object Recognition Organizer: Ahmed Elgammal Description The field of computer vision witnesses recently a great interest focused on solving the generic object recognition problem. Traditionally, object recognition has een at the center of the computer vision field. The explosion of digital imaging nd digital video that we are witnessing makes a huge urgent demand for systems nd applications that are able to understand images and videos at the semantic level. The goal of this reading seminar is to catch up with the state of the art in this field and understand the achievements and challenges towards solving the generic object recognition problem. Class Time: Thursday 2-3pm Class Location: Hill 254 Extended Reading List Sept 19: Holistic appearance-based approaches: Murase, Hiroshi, and Nayar [1995] Presented by: Chan Su Lee Sept 27: Part-based Models: Schmid and Mohr [1997], Agarwal, Awan, and Roth [2004] Presented by: Afzal Mazhar and Marwan A. Torki" 494a71a5d0df506ea5803d1f4e691d4b10eae506,Chapter 2 Face Recognition in Subspaces,"Chapter 2 Face Recognition in Subspaces Gregory Shakhnarovich and Baback Moghaddam .1 Introduction Images of faces, represented as high-dimensional pixel arrays, often belong to a manifold of intrinsically low dimension. Face recognition, and computer vision re- search in general, has witnessed a growing interest in techniques that capitalize on this observation and apply algebraic and statistical tools for extraction and analy- sis of the underlying manifold. In this chapter, we describe in roughly chronologic order techniques that identify, parameterize, and analyze linear and nonlinear sub- spaces, from the original Eigenfaces technique to the recently introduced Bayesian method for probabilistic similarity analysis. We also discuss comparative experi- mental evaluation of some of these techniques as well as practical issues related to the application of subspace methods for varying pose, illumination, and expression. .2 Face Space and Its Dimensionality Computer analysis of face images deals with a visual signal (light reflected off the surface of a face) that is registered by a digital sensor as an array of pixel values. The pixels may encode color or only intensity. In this chapter, we assume the latter ase (i.e., gray-level imagery). After proper normalization and resizing to a fixed m-by-n size, the pixel array can be represented as a point (i.e., vector) in an mn-" 49a7949fabcdf01bbae1c2eb38946ee99f491857,A concatenating framework of shortcut convolutional neural networks,"A CONCATENATING FRAMEWORK OF SHORTCUT CONVOLUTIONAL NEURAL NETWORKS Yujian Li Ting Zhang, Zhaoying Liu, Haihe Hu" 4926af10d590686f4f5706b450515caaa1ddea54,Adaptive Deep Supervised Autoencoder Based Image Reconstruction for Face Recognition,"Publishing CorporationMathematical Problems in EngineeringVolume 2016, Article ID 6795352, 14 pageshttp://dx.doi.org/10.1155/2016/6795352" 4913477a16c8354f032546b1444728c592823586,Web Image Retrieval Search Engine based on Semantically Shared Annotation,"Web Image Retrieval Search Engine based on Semantically Shared Annotation Alaa Riad1, Hamdy Elminir2 and Sameh Abd-Elghany3 Vice dean of Students Affair, Faculty of Computers and Information Sciences, Mansoura University Mansoura, Egypt Mansoura, Egypt Mansoura, Egypt Head of Electronic and Communication Dept, Misr Higher Institute of Engineering and Technology Faculty of Computers and Information Sciences, Mansoura University" 498fd231d7983433dac37f3c97fb1eafcf065268,Linear Disentangled Representation Learning for Facial Actions,"LINEAR DISENTANGLED REPRESENTATION LEARNING FOR FACIAL ACTIONS Xiang Xiang1 and Trac D. Tran2 Dept. of Computer Science Dept. of Electrical & Computer Engineering Johns Hopkins University, 3400 N. Charles Street, Baltimore, MD 21218, USA Fig. 1. The separability of the neutral face yn and expression omponent ye. We find yn is better for identity recognition than y and ye is better for expression recognition than y." 4941f92222d660f9b60791ba95796e51a7157077,Conditional CycleGAN for Attribute Guided Face Image Generation,"Conditional CycleGAN for Attribute Guided Face Image Generation Yongyi Lu HKUST Yu-Wing Tai Tencent Chi-Keung Tang HKUST" 490a0b6ff5b982e884622bb9c81250f05c069f32,Template Aging in 3 D and 2 D Face Recognition,"Template Aging in 3D and 2D Face Recognition Ishan Manjani∗ Hakki Sumerkan† Patrick J. Flynn† Kevin W. Bowyer†" 490a217a4e9a30563f3a4442a7d04f0ea34442c8,An SOM-based Automatic Facial Expression Recognition System,"International Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI), Vol.2, No.4, August 2013 An SOM-based Automatic Facial Expression Recognition System Mu-Chun Su1, Chun-Kai Yang1, Shih-Chieh Lin1,De-Yuan Huang1, Yi-Zeng Hsieh1, andPa-Chun Wang2 Department of Computer Science &InformationEngineering,National Central University,Taiwan, R.O.C. Cathay General Hospital, Taiwan, R.O.C. E-mail:" 49d76cef9a31d18eda22057cfc99f7eb9e25bc7c,Implicit Non-linear Similarity Scoring for Recognizing Unseen Classes,"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) Feature ExtractionElephantDolphinLionClass Feature ExtractionImage Feature SpaceClass Feature SpaceSimilarity MeasureJoint Embedding Space0.110.040.94(cid:2030)(cid:2038)Figure1:ThebasicframeworkofexistingZSLapproaches.labeledexemplar.Inaddition,manynewconceptsemergeeverydayanditisdifficulttocollectlabeleddataforthem.Inthesecases,therecognitionmodelhastorecognizeclass-eswhichareunseenbefore.Therefore,howtotrainimagerecognitionmodelsthatiscapableofgeneralizingwellforunseenclasses,i.e.,zero-shotlearning,hasrecentlybecomeahotresearchtopicandisanopenissue[Xianetal.,2017].ThebasicideaofZSListolearnafunctiontomeasurethecorrespondence/similaritybetweenanimageandaclassusingseenclasseswhichhavesufficientlabeledimages,andthentransferthesimilarityfunctiontounseenones.Ifanim-ageisverysimilartoaclass,itislikelytobelongtothisclass.WesummarizetheframeworkinFigure1.Eachimageisrepresentedbyafeaturevector(imagefeatureextraction),likedeepfeature[Donahueetal.,2014].Eachclassisal-sogivenafeaturevector(classfeatureextraction),liketheword2vecoutputusingtheclassnameasinputortheclassattributes[Lampertetal.,2014].Thenthekeystepistoconstructanimagefeatureprojectionfunction(cid:30)andatextfeatureprojectionfunction’tomapthemintoajointem-beddingspacesuchthatthesimilaritybetweenthemcanbedirectlymeasured.Thejointembeddingspacecanbetheimagefeaturespace[Guoetal.,2017],theclassfeatures-pace[Socheretal.,2013],oranewlatentspace[Akataetal.,2016].Afterthejointembeddingstep,thesimilaritybetweenanimageandaclasscanbemeasureddirectlyinthisspace,wheretheexplicitlinearscoringiswidelyadopted,forexam-ple,innerproductsimilarity[Romera-ParedesandTorr,2015;ZhangandSaligrama,2016;Xianetal.,2016].Becausetheseenclassesandunseenclassesarerelatedandsimilar,al-thoughdifferent,thefunctionlearningonseenclassescanworkwellonunseenclasses.Inthisway,themodelisabletorecognizeunseenclassesbasedonthetransferredknowledge." 4906d54807947dcdbf2da174fd0cd716ea195006,Augmented Reality in Road Navigation,"TECHNION INSTITUTE OF TECHNOLOGY PROJECT IN IMAGE PROCESSING AND ANALYSIS 34329 Augmented Reality in Road Navigation Author: Doron Halevy Supervisor: Gil Shamai May 8, 2016" 49d7fd8975413fb2912e111093749733712210dd,Vpliv kakovosti vhodnih slik na zanesljivost samodejnega razpoznavanja obrazov,"Elektrotehniški vestnik 74(3): 145-150, 2007 Electrotechnical Review: Ljubljana, Slovenija Vpliv kakovosti vhodnih slik na zanesljivost samodejnega razpoznavanja obrazov Vitomir Štruc, Nikola Paveši(cid:29) Univerza v Ljubljani, Fakulteta za elektrotehniko, Tržaška 25, 1001 Ljubljana, Slovenija E-pošta: Povzetek. Zanesljivost samodejnega razpoznavanja obrazov je odvisna od številnih dejavnikov, med katerimi so najpomembnejši natan(cid:24)nost dolo(cid:24)itve slikovnega obmo(cid:24)ja obraza in njegova odpornost na slabšo kakovost slik, izbira ustreznega postopka izpeljave obraznih zna(cid:24)ilk ter uporaba primernega algoritma za izra(cid:24)un podobnosti in sprejetje odlo(cid:24)itve o identiteti osebe. V (cid:24)lanku predstavljamo rezultate vrednotenja napak, ki jih v biometri(cid:24)ni sistem vnašajo razli(cid:24)ne degradacije vhodnih slik. Njihov vpliv smo prou(cid:24)ili za tri na podro(cid:24)ju razpoznavanja obrazov pogosteje uporabljene postopke izpeljave zna(cid:24)ilk (analizo glavnih komponent – PCA, analizo linearne diskriminante – LDA ter analizo neodvisnih komponent – ICA), pri (cid:24)emer smo za dolo(cid:24)itev zanesljivosti razpoznavanja (verifikacije) uporabili bazo XM2VTS; za ovrednotenje napak, ki jih v biometri(cid:24)ni sistem vnašajo spremembe v kakovosti slik, pa njene degradirane razli(cid:24)ice. Klju ne besede: razpoznavanje obrazov, analiza glavnih komponent, analiza linearne diskriminante, analiza neodvisnih komponent, zanesljivost razpoznavanja, kakovost vhodnih slik Impact of image degradations on the face recognition accuracy" 49e85869fa2cbb31e2fd761951d0cdfa741d95f3,Adaptive Manifold Learning,"Adaptive Manifold Learning Zhenyue Zhang, Jing Wang, and Hongyuan Zha" 493abaf881c3a6e9d3bf47a8d6e75abb4e75f557,Introspective Evaluation of Perception Performance for Parameter Tuning without Ground Truth,"Introspective Evaluation of Perception Performance for Parameter Tuning without Ground Truth Humphrey Hu† and George Kantor†" 4967b0acc50995aa4b28e576c404dc85fefb0601,An Automatic Face Detection and Gender Classification from Color Images using Support Vector Machine,"Vol. 4, No. 1 Jan 2013 ISSN 2079-8407 Journal of Emerging Trends in Computing and Information Sciences ©2009-2013 CIS Journal. All rights reserved. An Automatic Face Detection and Gender Classification from http://www.cisjournal.org Color Images using Support Vector Machine Md. Hafizur Rahman, 2 Suman Chowdhury, 3 Md. Abul Bashar , 2, 3 Department of Electrical & Electronic Engineering, International University of Business Agriculture and Technology, Dhaka-1230, Bangladesh" 492f3def325296164cd32b80d19a591b72b480cd,Metric Learning,"Computer Vision Group Metric Learning Technical University of Munich Department of Informatics Computer Vision Group June 9, 2017 M.Sc. John Chiotellis: Metric Learning / 46" 4987ac5638e1fdb116cc76626465f166998d7536,Polysemous codes.,"Polysemous codes Matthijs Douze, Herv´e J´egou and Florent Perronnin Facebook AI Research" 490fa9ee39614e1ef1d74162e698e4a1f0e5f916,In Good Shape: Robust People Detection based on Appearance and Shape,"PISHCHULIN et al.: PEOPLE DETECTION USING APPEARANCE AND SHAPE In Good Shape: Robust People Detection ased on Appearance and Shape Computer Vision and Multimodal Computing MPI Informatics Saarbrücken, Germany Leonid Pishchulin Arjun Jain Christian Wojek Thorsten Thormählen Bernt Schiele" 4914f51bc2f5a35c0d15924e39a51975c53f9753,Recovered from a Single 2 D Palmprint Image,"A 3D Feature Descriptor Recovered from a Single 2D Palmprint Image Qian Zheng1,2, Ajay Kumar1, and Gang Pan2" 491cf4d86ed895000a35ba96f46261984c0bdf7c,Facial Expression Recognition for Domestic Service Robots,"Facial Expression Recognition for Domestic Service Robots Geovanny Giorgana and Paul G. Ploeger Bonn-Rhein-Sieg University of Applied Sciences, Grantham-Allee 20 53757 Sankt Augustin, Germany" 23d55061f7baf2ffa1c847d356d8f76d78ebc8c1,Generic and attribute-specific deep representations for maritime vessels,"Solmaz et al. IPSJ Transactions on Computer Vision and Applications (2017) 9:22 DOI 10.1186/s41074-017-0033-4 IPSJ Transactions on Computer Vision and Applications RESEARCH PAPER Open Access Generic and attribute-specific deep representations for maritime vessels Berkan Solmaz*† , Erhan Gundogdu†, Veysel Yucesoy and Aykut Koc" 2322ec2f3571e0ddc593c4e2237a6a794c61251d,Four not six: Revealing culturally common facial expressions of emotion.,"Jack, R. E. , Sun, W., Delis, I., Garrod, O. G. B. and Schyns, P. G. (2016) Four not six: revealing culturally common facial expressions of emotion.Journal of Experimental Psychology: General, 145(6), pp. 708- 730. (doi:10.1037/xge0000162) This is the author’s final accepted version. There may be differences between this version and the published version. You are advised to consult the publisher’s version if you wish to cite from http://eprints.gla.ac.uk/116592/ Deposited on: 20 April 2016 Enlighten – Research publications by members of the University of Glasgow http://eprints.gla.ac.uk" 2306b2a8fba28539306052764a77a0d0f5d1236a,Surveillance Face Recognition Challenge,"Noname manuscript No. (will be inserted by the editor) Surveillance Face Recognition Challenge Zhiyi Cheng · Xiatian Zhu · Shaogang Gong Received: date / Accepted: date" 23e1746c449e675a4ffa3833b0ac5c5a7b743f7f,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 23a2b75c92123b3e7bbaf1d98e434845167fe259,Multimodal Biometrics for Identity Documents 1 State-ofthe-Art Research Report PFS 341-08 . 05 ( Version 1 . 0 ),"Forensic Science International 167 (2007) 154–159 www.elsevier.com/locate/forsciint Multimodal biometrics for identity documents ( Damien Dessimoz a,*, Jonas Richiardi b, Christophe Champod a, Andrzej Drygajlo b Institut de Police Scientifique, E´ cole des Sciences Criminelles, Universite´ de Lausanne, Switzerland Speech Processing and Biometrics Group, Signal Processing Institute, E´ cole Polytechnique Fe´de´rale de Lausanne, Switzerland Received 9 June 2006; accepted 14 June 2006 Available online 4 August 2006" 239df42479c69cf95e7194cc0ec3d8cf7d4a98e8,Face Detection and Extraction from Low Resolution Surveillance Video Using Motion Segmentation,"Face Detection and Extraction from Low Resolution Surveillance Video Using Motion Segmentation Vikram Mutneja1 I.K. Gujral Punjab Technical University, Kapurthala, Punjab (India) Ph.D. Research Scholar, I.K. Gujral Punjab Technical University Main Campus, Kapurthala, Punjab (India) Dr. Satvir Singh2, Associate Professor," 230c4a30f439700355b268e5f57d15851bcbf41f,EM Algorithms for Weighted-Data Clustering with Application to Audio-Visual Scene Analysis,"EM Algorithms for Weighted-Data Clustering with Application to Audio-Visual Scene Analysis Israel D. Gebru, Xavier Alameda-Pineda, Florence Forbes and Radu Horaud" 23b93f3b237481bd1d36941ca3312bb16f4beb58,Reconnaissance d'événements et d'actions à partir de la profondeur thermique 3D. (Event and action recognition from thermal and 3D depth Sensing),"Reconnaissance d’événements et d’actions à partir de la profondeur thermique 3D Adnan Al Alwani To cite this version: Adnan Al Alwani. Reconnaissance d’événements et d’actions à partir de la profondeur thermique D. Vision par ordinateur et reconnaissance de formes [cs.CV]. Université de Caen Normandie, 2016. Français. HAL Id: tel-01418369 https://hal.archives-ouvertes.fr/tel-01418369 Submitted on 16 Dec 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 236db916e2c73eccfe8821110274affcc9b54360,From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains,"BMVC 2014 BAOCHEN SUN, KATE SAENKO: FROM VIRTUAL TO REALITY From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains Baochen Sun http://www.cs.uml.edu/~bsun Kate Saenko http://www.cs.uml.edu/~saenko Computer Science Department University of Massachusetts Lowell Lowell, Massachusetts, US" 23fd82c04852b74d655015ff0876e6c5defc6e61,Deep-based Ingredient Recognition for Cooking Recipe Retrieval,"Deep-based Ingredient Recognition for Cooking Recipe Retrieval Jingjing Chen City University of HongKong Kowloon, HongKong Chong-Wah Ngo City University of HongKong Kowloon, HongKong" 2396ff03c41c498ff20e3a0e5419afa45e4a9d41,MIT Autonomous Vehicle Technology Study: Large-Scale Deep Learning Based Analysis of Driver Behavior and Interaction with Automation,"MIT Autonomous Vehicle Technology Study: Large-Scale Deep Learning Based Analysis of Driver Behavior and Interaction with Automation Lex Fridman∗, Daniel E. Brown, Michael Glazer, William Angell, Spencer Dodd, Benedikt Jenik, Andrew Sipperley, Anthony Pettinato, Bobbie Seppelt, Linda Angell, Bruce Mehler, Bryan Reimer∗ Jack Terwilliger, Julia Kindelsberger, Li Ding, Sean Seaman, Hillary Abraham, Alea Mehler," 2331df8ca9f29320dd3a33ce68a539953fa87ff5,Extended Isomap for Pattern Classification,"Extended Isomap for Pattern Classification Ming-Hsuan Yang Honda Fundamental Research Labs Mountain View, CA 94041" 2312bc2d48a0f68bd5ab1b024d5726786455da3a,Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification,"Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification Supplementary Materials Dangwei Li1,2, Xiaotang Chen1,2, Zhang Zhang1,2, Kaiqi Huang1,2,3 CRIPAC & NLPR, CASIA 2University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology {dangwei.li, xtchen, zzhang, . Market1501 dataset To further understand the results on Market1501 [8], we show mean Average Precision (mAP) and Rank-1 identification rate between camera pairs in Figure 1 and Figure 2. Compared to the BOW methods, the proposed method improves mean mAP and Rank-1 identification rate between camera pairs by 35.09% and 40.01% respectively. In addition, we show some searching results with different query images in Figure 3. The dataset is challenging and the returned images have very similar ppearances and some pedestrians have large backgrounds and occlusions. For the query image in first row of Figure 3, even though the query person has large occlusions and some groundtruth images have large backgrounds, our proposed method an still return the right results. This shows the effectiveness of our proposed method. . CUHK03 dataset CUHK03 [3] is one of the largest person re-identification datasets. It provides two types of pedestrian bounding boxes, including detected and manually annotated. In this paragraph, we show the overall Cumulated Matching Characteristics (CMC) on both detected and labeled datasets in Figure 4. For the GateSCNN [5] in Figure 4(a), we use the singe-query results to approximate the single-shot results. The DGD [6] is trained using multiple datasets. In this paper, we use the" 23172f9a397f13ae1ecb5793efd81b6aba9b4537,Defining Visually Descriptive Language,"Proceedings of the 2015 Workshop on Vision and Language (VL’15), pages 10–17, Lisbon, Portugal, 18 September 2015. c(cid:13)2015 Association for Computational Linguistics." 23e881c9b791fd17e248b1fb4fc980710dd005d7,An Unbiased Temporal Representation for Video-Based Person Re-Identification,"AN UNBIASED TEMPORAL REPRESENTATION FOR VIDEO-BASED PERSON RE-IDENTIFICATION Xiu Zhang and Bir Bhanu Center for Research in Intelligent Systems University of California, Riverside, Riverside, CA 92521, USA" 23ea8a34570342855611a78a4ff00ddd902e6123,Gradient-based global features and its application to image retargeting,"Gradient-based Global Features and Its Application to Image Retargeting Izumi Ito Tokyo Institute of Technology Tokyo, 152-8552 Japan +81-3-5734-2997" 23cb53fd272c105e98111e66502120216ae1788c,Incremental learning for robot perception through HRI,"Incremental Learning for Robot Perception through HRI Sepehr Valipour∗, Camilo Perez∗ and Martin Jagersand" 2333cf918f50ac2ae201a837166d310adf3a00b0,Optimally Training a Cascade Classifier,"Optimally Training a Cascade Classifier Chunhua Shen, Peng Wang, and Anton van den Hengel" 23e0571fd42347ca2bdf424b8562c6c6f72b88fc,Classification of Things in DBpedia using Deep Neural Networks,"International Journal of Web & Semantic Technology (IJWesT) Vol.9, No.1, January 2018 CLASSIFICATION OF THINGS IN DBPEDIA USING DEEP NEURAL NETWORKS Rahul Parundekar Elevate.do" 235f4fad10a5d9e043759354a7cb94122a8f10fc,"Multi-perspective vehicle detection and tracking: Challenges, dataset, and metrics","Windsor Oceanico Hotel, Rio de Janeiro, Brazil, November 1-4, 2016 978-1-5090-1889-5/16/$31.00 ©2016 IEEE" 23d7833d63ed3e416bbb237ea39f751bc9bfb703,"THE MULTI-BIOMETRIC , MULTI-DEVICE AND MULTILINGUAL ( M 3 ) CORPUS","THE MULTI-BIOMETRIC, MULTI-DEVICE AND MULTILINGUAL (M3) CORPUS Helen Meng1, P.C. Ching1, Tan Lee1, Man Wai Mak2, Brian Mak3, Y.S. Moon1, Man-Hung Siu3, Xiaoou Tang1, Henry P.S. Hui1, Andrew Lee1, Wai-Kit Lo1, Bin Ma1 and Eddie K.T. Sio1 The Chinese University of Hong Kong (CUHK), 2The Hong Kong Polytechnic University (HKPolyU), Hong Kong University of Science and Technology (HKUST) Email:" 239492717385758c0e64afe4d31b789d000c18f2,Technical Report for Real-Time Certified Probabilistic Pedestrian Forecasting,"Technical Report for Real-Time Certified Probabilistic Pedestrian Forecasting Henry O. Jacobs, Owen K. Hughes, Matthew Johnson-Roberson, and Ram Vasudevan" 23e707600c3e9a240e24eaa4ed4b0e4ec6a436c1,Automatic foreground extraction via joint CRF and online learning,"Automatic foreground extraction via joint CRF and online learning Wenbin Zou, Kidiyo Kpalma, Joseph Ronsin To cite this version: Wenbin Zou, Kidiyo Kpalma, Joseph Ronsin. Automatic foreground extraction via joint CRF nd online learning. Electronics Letters, IET, 2013, 49 (18), pp.1140 - 1142. . HAL Id: hal-00875339 https://hal.archives-ouvertes.fr/hal-00875339 Submitted on 21 Oct 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires" 23ba9e462151a4bf9dfc3be5d8b12dbcfb7fe4c3,"Determining Mood from Facial Expressions CS 229 Project , Fall 2014","CS 229 Project, Fall 2014 Matthew Wang Spencer Yee Determining Mood from Facial Expressions Introduction Facial expressions play an extremely important role in human communication. As society continues to make greater use of human-machine interactions, it is important for machines to be able to interpret facial expressions in order to improve their uthenticity. If machines can be trained to determine mood to a better extent than humans can, especially for more subtle moods, then this could be useful in fields such as ounseling. This could also be useful for gauging reactions of large audiences in various ontexts, such as political talks. The results of this project could also be applied to recognizing other features of facial expressions, such as determining when people are purposefully suppressing emotions or lying. The ability to recognize different facial expressions could also improve technology that recognizes to whom specific faces belong. This could in turn be used to search a large number of pictures for a specific photo, which is becoming increasingly difficult, as storing photos digitally has been extremely common in the past decade. The possibilities re endless. II Data and Features" 2311cdd241c118395a510776ec226aff7725ebc8,Hunting Nessie - Real-time abnormality detection from webcams,"Hunting Nessie – Real-Time Abnormality Detection from Webcams Michael D. Breitenstein1 Helmut Grabner1 Luc Van Gool1,2 Computer Vision Laboratory ETH Zurich ESAT-PSI / IBBT KU Leuven" 23943197f4124aa6c5a263bf2042169c9b816906,Crafting GBD-Net for Object Detection,"MANUSCRIPT Crafting GBD-Net for Object Detection Xingyu Zeng*,Wanli Ouyang*,Junjie Yan, Hongsheng Li,Tong Xiao, Kun Wang, Yu Liu, Yucong Zhou, Bin Yang, Zhe Wang,Hui Zhou, Xiaogang Wang," 231a12de5dedddf1184ae9caafbc4a954ce584c3,Closed and Open World Multi-shot Person Re-identification. (Ré-identification de personnes à partir de multiples images dans le cadre de bases d'identités fermées et ouvertes),"Closed and Open World Multi-shot Person Re-identification Solène Chan-Lang To cite this version: Solène Chan-Lang. Closed and Open World Multi-shot Person Re-identification. Systems and Control [cs.SY]. Université Pierre et Marie Curie - Paris VI, 2017. English. . HAL Id: tel-01810504 https://tel.archives-ouvertes.fr/tel-01810504 Submitted on 8 Jun 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 2349eab05cd0c6f94ba5314c037d198aa12c2f0f,Eigen-profiles of spatio-temporal fragments for adaptive region-based tracking,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 237316762470d72a02795a7f57de9279e9cda16a,Dimensionality-reduced subspace clustering,"Dimensionality-reduced subspace clustering Reinhard Heckel, Michael Tschannen, and Helmut B¨olcskei December 15, 2015" 23095c6fc92f41a86f93276d446cfc72c7ce7b23,Stereo-based Pedestrian Detection using Multiple Patterns,"HATTORI et al.: STEREO-BASED PEDESTRIAN DETECTION USING MULTI-PATTERNS Stereo-based Pedestrian Detection using Multiple Patterns Research & Development Center, TOSHIBA Corporation, JAPAN Hiroshi Hattori Akihito Seki Manabu Nishiyama Tomoki Watanabe" 230ad73e8bd1d3268d56c66a83442d24176b864d,ORB-SLAM: A Versatile and Accurate Monocular SLAM System,"IEEE Xplore: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7219438 DOI: 10.1109/TRO.2015.2463671 (cid:13)2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any urrent or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new ollective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works." 230527d37421c28b7387c54e203deda64564e1b7,Person Re-identification: System Design and Evaluation Overview,"Person Re-identification: System Design and Evaluation Overview Xiaogang Wang and Rui Zhao" 23a8d02389805854cf41c9e5fa56c66ee4160ce3,Influence of low resolution of images on reliability of face detection and recognition,"Multimed Tools Appl DOI 10.1007/s11042-013-1568-8 Influence of low resolution of images on reliability of face detection and recognition Tomasz Marciniak· Agata Chmielewska· Radoslaw Weychan· Marianna Parzych· Adam Dabrowski © The Author(s) 2013. This article is published with open access at SpringerLink.com" 2310202b10c535b7228c9029e11a24d33deafdb2,Wavelet-based fingerprint image retrieval,"Accepted Manuscript Wavelet-based fingerprint image retrieval Javier A. Montoya Zegarra, Neucimar J. Leite, Ricardo da Silva Torres Reference: S0377-0427(08)00112-X 0.1016/j.cam.2008.03.017 CAM 6702 To appear in: Journal of Computational and Applied Mathe- matics Received date: 4 April 2006 Revised date: 0 September 2007 Please cite this article as: J.A. Montoya Zegarra, N.J. Leite, R. da Silva Torres, Wavelet-based fingerprint image retrieval, Journal of Computational and Applied Mathematics (2008), doi:10.1016/j.cam.2008.03.017 This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which" 23a68a8b181a2d29172a5b2fe61c72cecdc15638,Local Feature Based on Moment Invariants for Blurred Image Matching,"International Journal of Electronics and Computer Science Engineering 376 Available Online at www.ijecse.org ISSN- 2277-1956 Local Feature Based on Moment Invariants for Blurred Image Matching Qiang Tong 1 , Terumasa Aoki 1, 2 Graduate School of Information Sciences, Tohoku University，Japan 2 New Industry Creation Hatchery Center, Tohoku University，Japan" 23120f9b39e59bbac4438bf4a8a7889431ae8adb,Aalborg Universitet Improved RGB-D-T based Face Recognition,"Aalborg Universitet Improved RGB-D-T based Face Recognition Oliu Simon, Marc; Corneanu, Ciprian; Nasrollahi, Kamal; Guerrero, Sergio Escalera; Nikisins, Olegs; Sun, Yunlian; Li, Haiqing; Sun, Zhenan; Moeslund, Thomas B.; Greitans, Modris Published in: IET Biometrics DOI (link to publication from Publisher): 0.1049/iet-bmt.2015.0057 Publication date: Document Version Accepted manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Oliu Simon, M., Corneanu, C., Nasrollahi, K., Guerrero, S. E., Nikisins, O., Sun, Y., ... Greitans, M. (2016). Improved RGB-D-T based Face Recognition. IET Biometrics, (2047-4946 ). DOI: 10.1049/iet-bmt.2015.0057 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research." 237ec7e6d20025c32069e41f8007bb97931a7fc6,Learning real-time object detectors: probabilistic generative approaches, 2315371408e02cdff6f54359f159f192009d1600,Effective Pedestrian Detection Using Center-symmetric Local Binary/Trinary Patterns,"SEPTEMBER 2010 Effective Pedestrian Detection Using Center-symmetric Local Binary/Trinary Patterns Yongbin Zheng, Chunhua Shen, Richard Hartley, Fellow, IEEE, and Xinsheng Huang" f1c2ba8c7797c4844fa61068b3ce9d319e6ced3f,Human Head Tracking Based on Inheritance and Evolution Concept,"MVA2009 IAPR Conference on Machine Vision Applications, May 20-22, 2009, Yokohama, JAPAN Human Head Tracking Based on Inheritance and Evolution Concept Yi Hu, Tetsuya Takamori Fujifilm Corporation, Japan 798, Miyanodai, Kaisei-machi, Ashigarakami-gun, Kanagawa, 258-8538 JAPAN {yi_hu," f1ba2fe3491c715ded9677862fea966b32ca81f0,Face Tracking and Recognition in Videos : HMM Vs KNN,"ISSN: 2321-7782 (Online) Volume 1, Issue 7, December 2013 International Journal of Advance Research in Computer Science and Management Studies Research Paper Available online at: www.ijarcsms.com Face Tracking and Recognition in Videos: HMM Vs KNN Madhumita R. Baviskar Assistant Professor Department of Computer Engineering MIT College of Engineering (Pune University) Pune - India" f196a79c5e4b570013e4aa031cdd0fc0c98fc07d,Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions,"Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions Jun Hatori∗, Yuta Kikuchi∗, Sosuke Kobayashi∗, Kuniyuki Takahashi∗, Yuta Tsuboi∗, Yuya Unno∗, Wilson Ko, Jethro Tan†" f1bb2c95dc270ffa9c2f88e29ae5d2178b4459cb,A Generative Model of People in Clothing,"A Generative Model of People in Clothing Christoph Lassner1, 2 Gerard Pons-Moll2 Peter V. Gehler3,* BCCN, Tübingen MPI for Intelligent Systems, Tübingen 3University of Würzburg Figure 1: Random examples of people generated with our model. For each row, sampling is conditioned on the silhouette displayed on the left. Our proposed framework also supports unconditioned sampling as well as conditioning on local ppearance cues, such as color." f13552e2e2843716e7a1c7c2492cfcc6e86aa03c,Reinforced Pipeline Optimization: Behaving Optimally,"Under review as a conference paper at ICLR 2019 REINFORCED PIPELINE OPTIMIZATION: BEHAVING OPTIMALLY WITH NON-DIFFERENTIABILITIES Anonymous authors Paper under double-blind review" f1aaf4f80c2bd42f14d8feeec34bcb0af48a61db,PiEye in the Wild: Exploring Eye Contact Detection for Small Inexpensive Hardware,"Teknik och samhälle Datavetenskap Examensarbete 5 högskolepoäng, grundnivå PiEye in the Wild: Exploring Eye Contact Detection for Small Inexpensive Hardware PiEye: En Undersökning av Ögonkontakts-igenkänning för Liten och Billig Hårdvara Karl Casserfelt Ragnar Einestam Examen: kandidatexamen 180 hp Huvudområde: Datavetenskap Program: Datavetenskap och Applikation- sutveckling Datum för slutseminarium: 2017-05-30 Handledare: Shahram Jalalinya Examinator: Erik Pineiro" f131a654bbf4c8de0679d3c6054c10bba4a919d4,Vision-based Driver Assistance Systems,"Vision-based Driver Assistance Systems .enpeda.. (Environment Perception and Driver Assistance) Project CITR, Auckland, New Zealand Reinhard Klette 5 February 2015" f1d090fcea63d9f9e835c49352a3cd576ec899c1,Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information,"Iosifidis, A., Tefas, A., & Pitas, I. (2015). Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information. In . J. J. Merelo, A. Rosa, J. M. Cadenas, A. Dourado, K. Madani, & J. Filipe (Eds.), Computational Intelligence: International Joint Conference, IJCCI 2014 Rome, Italy, October 22-24, 2014 Revised Selected Papers. (Vol. III, pp. 51-364). (Studies in Computational Intelligence; Vol. 620). Springer. DOI: 0.1007/978-3-319-26393-9_21 Peer reviewed version Link to published version (if available): 0.1007/978-3-319-26393-9_21 Link to publication record in Explore Bristol Research PDF-document University of Bristol - Explore Bristol Research General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: http://www.bristol.ac.uk/pure/about/ebr-terms.html" f157daaffa1754aae5963d9c49247142b07c8d4a,DCT-BASED REDUCED FACE FOR FACE RECOGNITION,"International Journal of Information Technology and Knowledge Management January-June 2012, Volume 5, No. 1, pp. 97-100 DCT-BASED REDUCED FACE FOR FACE RECOGNITION Vikas Maheshkar1, Sushila Kamble2, Suneeta Agarwal3, and Vinay Kumar Srivastava4" f16921c1c6e8bce89bce7679cbd824d65b494e4d,The face of love: spontaneous accommodation as social emotion regulation.,"Personality and Social Psychology Bulletin http://psp.sagepub.com/ The Face of Love : Spontaneous Accommodation as Social Emotion Regulation Pers Soc Psychol Bull Michael Häfner and Hans IJzerman 2011 37: 1551 originally published online 21 July 2011 DOI: 10.1177/0146167211415629 The online version of this article can be found at: http://psp.sagepub.com/content/37/12/1551 Published by: http://www.sagepublications.com On behalf of: Society for Personality and Social Psychology Additional services and information for Personality and Social Psychology Bulletin can be found at: Email Alerts: http://psp.sagepub.com/cgi/alerts Subscriptions:" f19ab817dd1ef64ee94e94689b0daae0f686e849,Blickrichtungsunabhängige Erkennung von Personen in Bild- und Tiefendaten,"TECHNISCHE UNIVERSIT¨AT M ¨UNCHEN Lehrstuhl f¨ur Mensch-Maschine-Kommunikation Blickrichtungsunabh¨angige Erkennung von Personen in Bild- und Tiefendaten Andre St¨ormer Vollst¨andiger Abdruck der von der Fakult¨at f¨ur Elektrotechnik und Informationstechnik der Technischen Universit¨at M¨unchen zur Erlangung des akademischen Grades eines Doktor-Ingenieurs (Dr.-Ing.) genehmigten Dissertation. Vorsitzender: Univ.-Prof. Dr.-Ing. Thomas Eibert Pr¨ufer der Dissertation: . Univ.-Prof. Dr.-Ing. habil. Gerhard Rigoll . Univ.-Prof. Dr.-Ing. Horst-Michael Groß, Technische Universit¨at Ilmenau Die Dissertation wurde am 16.06.2009 bei der Technischen Universit¨at M¨unchen einge- reicht und durch die Fakult¨at f¨ur Elektrotechnik und Informationstechnik am 30.10.2009 ngenommen." f1498ba94d64ee221e27b658bcd407c160cf0897,LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation,"LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation Gabriele Costante†,1 and Thomas A. Ciarfuglia†,1" f11d070cdc9ee12b201757ca4a50a3682967ba0c,Spatial Language Understanding with Multimodal Graphs using Declarative Learning based Programming,"Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing, pages 33–43 Copenhagen, Denmark, September 7–11, 2017. c(cid:13)2017 Association for Computational Linguistics" f18c34458460b9b62b51213b9165b37c057c5837,Unsupervised object discovery and co-localization by deep descriptor transformation,"Noname manuscript No. (will be inserted by the editor) Unsupervised Object Discovery and Co-Localization y Deep Descriptor Transforming Xiu-Shen Wei · Chen-Lin Zhang · Jianxin Wu · Chunhua Shen · Zhi-Hua Zhou Received: date / Accepted: date" f1aa120fb720f6cfaab13aea4b8379275e6d40a2,InverseFaceNet: Deep Single-Shot Inverse Face Rendering From A Single Image,"InverseFaceNet: Deep Single-Shot Inverse Face Rendering From A Single Image Hyeongwoo Kim1 Justus Thies2 Max-Planck-Institute for Informatics Michael Zollhöfer1 Christian Richardt3 University of Erlangen-Nuremberg 3 University of Bath Christian Theobalt1 Ayush Tewari1 Figure 1. Our single-shot deep inverse face renderer InverseFaceNet obtains a high-quality geometry, reflectance and illumination estimate from just a single input image. We jointly recover the face pose, shape, expression, reflectance and incident scene illumination. From left to right: input photo, our estimated face model, its geometry, and the pointwise Euclidean error compared to Garrido et al. [14]." f157ec3f4d330aac34331300b4c1fd1edcb46156,Improving landfill monitoring programs with the aid of geoelectrical-imaging techniques and geographical information systems,"Analysis and Classification of Object Poses: Using Visual / Infrared Images and Feature Fusion Master of Science Thesis YIXIAO YUN Department of Signals and Systems Signal Processing Group Chalmers University of Technology Gothenburg, Sweden 2011 Report No. Ex 040/2011 Improving landfill monitoring programswith the aid of geoelectrical - imaging techniquesand geographical information systems Master’s Thesis in the Master Degree Programme, Civil Engineering KEVIN HINEDepartment of Civil and Environmental Engineering Division of GeoEngineering Engineering Geology Research GroupCHALMERS UNIVERSITY OF TECHNOLOGYGöteborg, Sweden 2005Master’s Thesis 2005:22" f1a0010f588a41682c1efd770541c4c381949d88,VisGraB: A benchmark for vision-based grasping,"VisGraB: A Benchmark for Vision-Based Grasping Gert Kootstra ∗1, Mila Popovi´c2, Jimmy Alison Jørgensen3, Danica Kragic1, Henrik Gordon Petersen3, and Norbert Kr¨uger2 Computer Vision and Active Perception Lab, CSC, Royal Institute of Technology (KTH), Stockholm, Sweden Cognitive Vision Lab, The Mærsk Mc-Kinney Møller Institute, University of Southern Denmark, Campusvej 55, DK-5230 Odense, Denmark Robotics Lab, The Mærsk Mc-Kinney Møller Institute, University of Southern Denmark, Campusvej 55, DK-5230 Odense, Denmark August 3, 2012" f17d6db4844f26a023f92b8771a1c33cea91b9e4,1 Million Captioned Dutch Newspaper Images,"Million Captioned Dutch Newspaper Images Desmond Elliott∗† and Martijn Kleppe‡ ILLC, University of Amsterdam; †CWI; ‡Erasmus University Rotterdam" f174b24860b4cacbe047d3a5650cf8866d2244d9,Monocular Depth Estimation by Learning from Heterogeneous Datasets,"Monocular Depth Estimation by Learning from Heterogeneous Datasets Akhil Gurram1,2, Onay Urfalioglu2, Ibrahim Halfaoui2, Fahd Bouzaraa2 and Antonio M. L´opez1" f1a05136c8b8f9334a4b3d9de2a4b192d2c762c2,Scene Classification via Hypergraph-Based Semantic Attributes Subnetworks Identification,"Scene Classification via Hypergraph-Based Semantic Attributes Subnetworks Identification Sun-Wook Choi, Chong Ho Lee, and In Kyu Park Department of Information and Communication Engineering Inha University, Incheon 402-751, Korea" f1052df3e311b7caa563685e741e0a1bb6b288df,A Hierarchical Fusion Strategy based Multimodal Biometric System,"The International Arab Conference on Information Technology (ACIT’2013) A Hierarchical Fusion Strategy based Multimodal Biometric System Youssef Elmir, 2Zakaria Elberrichi and 2Réda Adjoudj Faculty of Sciences and Technology, University of Adrar, Algeria Faculty of Technology, Djillali Liabès University of Sidi Bel Abbès, Algeria" f1d3e9335b4fe5c514c7ecd9e0d9bf3c864454ff,Driving dataset in the wild : Various driving scenes by Byung Gon,"Driving dataset in the wild: Various driving scenes Kurt Keutzer Byung Gon Song John Chuang, Ed. Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2016-92 http://www.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-92.html May 13, 2016" f168cfb66dc40b49d2e2076907a4c6ab1bdb0085,A Compositional Object-Based Approach to Learning Physical Dynamics,"Published as a conference paper at ICLR 2017 A COMPOSITIONAL OBJECT-BASED APPROACH TO LEARNING PHYSICAL DYNAMICS Michael B. Chang*, Tomer Ullman**, Antonio Torralba*, and Joshua B. Tenenbaum** *Department of Electrical Engineering and Computer Science, MIT **Department of Brain and Cognitive Sciences, MIT" f1d8c377093ecf64afd7f17383738e81666fe5ae,Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks,"Noname manuscript No. (will be inserted by the editor) Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks Muhammet Bastan · Kim-Hui Yap · Lap-Pui Chau Date: April 2018" 568727a76dc1242e3d48392f9c19678a27c63482,High Entropy Ensembles for Holistic Figure-ground Segmentation,"GALLO et al.: HEE FOR HOLISTIC FIGURE-GROUND SEGMENTATION High Entropy Ensembles for Holistic Figure-ground Segmentation Ignazio Gallo Alessandro Zamberletti Simone Albertini Lucia Noce Applied Recognition Technology Laboratory Department of Theoretical and Applied Science University of Insubria Varese, Italy" 566038a3c2867894a08125efe41ef0a40824a090,Face recognition and gender classification in personal memories,"978-1-4244-2354-5/09/$25.00 ©2009 IEEE ICASSP 2009" 56b9c6efe0322f0087d2f82b52129cc6b41ab356,"Acquire, Augment, Segment & Enjoy: Weakly Supervised Instance Segmentation of Supermarket Products","Acquire, Augment, Segment & Enjoy: Weakly Supervised Instance Segmentation of Supermarket Products Patrick Follmann+*, Bertram Drost+, and Tobias B¨ottger+* +MVTec Software GmbH, Munich, Germany Technical University of Munich (TUM) July 9, 2018" 56e95fa26fb417776824e5adf6d6d511e5b30110,Object and Action Classification with Latent Window Parameters,"Int J Comput Vis DOI 10.1007/s11263-013-0646-8 Object and Action Classification with Latent Window Parameters Hakan Bilen · Vinay P. Namboodiri · Luc J. Van Gool Received: 1 October 2012 / Accepted: 18 July 2013 © Springer Science+Business Media New York 2013" 56bc524d7cc1ff2fad8f27c0414cac437fc2b4f0,Protest Activity Detection and Perceived Violence Estimation from Social Media Images,"To appear in Proceedings of the 25th ACM International Conference on Multimedia 2017 Protest Activity Detection and Perceived Violence Estimation from Social Media Images Donghyeon Won Zachary C. Steinert-Threlkeld Jungseock Joo" 5665d98136cc39322d47cb782b8e49d141c5a29e,AN AGILE FRAMEWORK FOR REAL-TIME VISUAL TRACKING IN VIDEOS,"REPORT DOCUMENTATION PAGE Form Approved OMB NO. 0704-0188 this collection of information is estimated instructions, The public reporting burden Send comments searching existing data sources, gathering and maintaining to Washington regarding this burden estimate or any other aspect of Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA, 22202-4302. Headquarters Services, Directorate Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any oenalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. PLEASE DO NOT RETURN YOUR FORM TO THE ABOVE ADDRESS. . REPORT DATE (DD-MM-YYYY) the data needed, and completing and reviewing this collection of" 56852a56dd830a6ee3882773c453025ddec652e2,Emotion recognition through static faces and moving bodies: a comparison between typically developed adults and individuals with high level of autistic traits,"ORIGINAL RESEARCH published: 23 October 2015 doi: 10.3389/fpsyg.2015.01570 Emotion recognition through static faces and moving bodies: a omparison between typically developed adults and individuals with high level of autistic traits† Rossana Actis-Grosso1,2*, Francesco Bossi1 and Paola Ricciardelli1,2 Department of Psychology, University of Milano-Bicocca, Milano, Italy, 2 Milan Centre for Neuroscience, Milano, Italy We investigated whether the type of stimulus (pictures of static faces vs. body motion) ontributes differently to the recognition of emotions. The performance (accuracy and response times) of 25 Low Autistic Traits (LAT group) young adults (21 males) and 20 young adults (16 males) with either High Autistic Traits or with High Functioning Autism Spectrum Disorder (HAT group) was compared in the recognition of four emotions (Happiness, Anger, Fear, and Sadness) either shown in static faces or conveyed by moving body patch-light displays (PLDs). Overall, HAT individuals were as accurate as LAT ones in perceiving emotions both with faces and with PLDs. Moreover, they correctly described non-emotional actions depicted by PLDs, indicating that they perceived the motion conveyed by the PLDs per se. For LAT participants, happiness proved to be" 5615d6045301ecbc5be35e46cab711f676aadf3a,Discriminatively Learned Hierarchical Rank Pooling Networks,"Discriminatively Learned Hierarchical Rank Pooling Networks Basura Fernando · Stephen Gould Received: date / Accepted: date" 564555b7fdc45938d813650de7a7b1cd40005aa8,Implementation of SIFT In Various Applications,"International Journal of Engineering Research and Development e-ISSN: 2278-067X, p-ISSN: 2278-800X, www.ijerd.com Volume 7, Issue 4 (May 2013), PP. 59-64 Implementation of SIFT In Various Applications ,2,3Deen Bandhu Chotu Ram University of Science and Technology Murthal, Haryana, India. Ritu Rani1, S. K. Grewal 2, Indiwar 3" 564babec16b895d385d06d38545febd66ef02f35,Robust Statistics for Feature-based Active Appearance Models, 5666ed763698295e41564efda627767ee55cc943,Relatively-Paired Space Analysis: Learning a Latent Common Space From Relatively-Paired Observations,"Manuscript Click here to download Manuscript: template.tex Click here to view linked References Noname manuscript No. (will be inserted by the editor) Relatively-Paired Space Analysis: Learning a Latent Common Space from Relatively-Paired Observations Zhanghui Kuang · Kwan-Yee K. Wong Received: date / Accepted: date" 56a0ead811a1bf15e42be8a9a007b0299636f213,Talk the Walk: Navigating New York City through Grounded Dialogue,"Talk the Walk: Navigating New York City through Grounded Dialogue Harm de Vries1, Kurt Shuster3, Dhruv Batra3,2, Devi Parikh3,2, Jason Weston3 & Douwe Kiela3 MILA, Université de Montréal; 2Georgia Institute of Technology; 3Facebook AI Research" 56dca23481de9119aa21f9044efd7db09f618704,Riemannian Dictionary Learning and Sparse Coding for Positive Definite Matrices,"Riemannian Dictionary Learning and Sparse Coding for Positive Definite Matrices Anoop Cherian Suvrit Sra" 56c5d08103c5bf4b263a81da73135455136bbe6d,Kernel MBPLS for a Scalable and Multi-Camera Person Re-Identification System,"Kernel MBPLS for a Scalable and Multi-Camera Person Re-Identification System Raphael Pratesa,*, William Robson Schwartza Smart Surveillance Interest Group, Computer Science Department, Universidade Federal de Minas Gerais, Minas Gerais, Brazil Person re-identification aims at establishing global identities for individuals as they move cross a camera network. It is a challenging task due to the drastic appearance changes that occur between cameras as consequence of different pose and illumination conditions. Pairwise matching models yield state-of-the-art results in most of the person re-identification datasets by apturing nuances that are robust and discriminative for a specific pair of cameras. Nonetheless, pairwise models are not scalable with the number of surveillance cameras. Therefore, elegant solu- tions combining scalability with high matching rates are crucial for the person re-identification in real-world scenarios. In this work, we tackle this problem proposing a multi-camera nonlinear re- gression model called Kernel Multiblock Partial Least Squares (Kernel MBPLS), a single subspace model for the entire camera network that uses all the labeled information. In this subspace, probe nd gallery individual can be successfully matched. Experimental results in three multi-camera person re-identification datasets (WARD, RAID and SAIVT-SoftBIO) demonstrate that the Ker- nel MBPLS presents favorable aspects such as the scalability and robustness with respect to the number of cameras combined with the high matching rates." 56cf859363f1b5231418b40b957a9132a78ea546,VLASE: Vehicle Localization by Aggregating Semantic Edges,"VLASE: Vehicle Localization by Aggregating Semantic Edges Xin Yu1∗, Sagar Chaturvedi1∗, Chen Feng2, Yuichi Taguchi2, Teng-Yok Lee2, Clinton Fernandes1, Srikumar Ramalingam1" 564d4ee76c0511bc395dfc8ef8e3b3867fc34a6d,Robust group sparse representation via half-quadratic optimization for face recognition,"Robust Group Sparse Representation via Half-Quadratic Optimization for Face Recognition Yong Peng and Bao-Liang Lu(cid:3), Senior Member, IEEE" 560447750f45ea18cb21f202e30344c4fe12c52e,Removal Of Blurred And Illuminated Face Image With Different Poses,"International Journal of Scientific & Engineering Research, Volume 5, Issue 3, March-2014 33 ISSN 2229-5518 Removal Of Blurred And Illuminated Face Image With Different Poses C.Indhumathi, C.Dhanamani" 562f35a662545d839876deeb605ca2c864507a82,Revealing Variations in Perception of Mental States from Dynamic Facial Expressions: A Cautionary Note,"Revealing Variations in Perception of Mental States from Dynamic Facial Expressions: A Cautionary Note Elisa Back1*, Timothy R. Jordan2 Department of Psychology, Kingston University London, Kingston upon Thames, United Kingdom, 2 Department of Psychology, Zayed University, Dubai, United Arab Emirates" 987c9a137d638f3d561c52b6dd0f987734ad5460,Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation,"Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation Shao-Yuan Lo1 Hsueh-Ming Hang1 Sheng-Wei Chan2 Jing-Jhih Lin2 National Chiao Tung University 2 Industrial Technology Research Institute {ShengWeiChan," 98c548a4be0d3b62971e75259d7514feab14f884,Deep generative-contrastive networks for facial expression recognition,"Deep generative-contrastive networks for facial expression recognition Youngsung Kim†, ByungIn Yoo‡,†, Youngjun Kwak†, Changkyu Choi†, and Junmo Kim‡ Samsung Advanced Institute of Technology (SAIT), ‡KAIST hangkyu" 9817e0d11701e9ce0e31a32338ff3ff0969621ed,Dppnet: Approximating Determinantal Point Processes with Deep Networks,"Under review as a conference paper at ICLR 2019 DPPNET: APPROXIMATING DETERMINANTAL POINT PROCESSES WITH DEEP NETWORKS Anonymous authors Paper under double-blind review" 983534325c649e391fefe87025337187021b9830,Towards Automatic Generation of Question Answer Pairs from Images,"Towards Automatic Generation of Question Answer Pairs from Images Issey Masuda Mora, Santiago Pascual de la Puente, Xavier Giro-i-Nieto Universitat Politecnica de Catalunya (UPC) Barcelona, Catalonia/Spain" 9820f8d1f4fd7c1e5b294a2c8fef542d2f1050b4,Modeling of image variability for recognition,"Modeling of Image Variability for Recognition Von der Fakult¨at f¨ur Mathematik, Informatik und Naturwissenschaften der Rheinisch-Westf¨alischen Technischen Hochschule Aachen zur Erlangung des akademischen Grades eines Doktors der Naturwissenschaften genehmigte Dissertation vorgelegt von Diplom-Informatiker Daniel Martin Keysers us D¨usseldorf Berichter: Universit¨atsprofessor Dr.-Ing. Hermann Ney Universit¨atsprofessor Dr.-Ing. Hans Burkhardt Tag der m¨undlichen Pr¨ufung: 14. M¨arz 2006 Diese Dissertation ist auf den Internetseiten der Hochschulbibliothek online verf¨ugbar." 98a660c15c821ea6d49a61c5061cd88e26c18c65,Face Databases for 2 D and 3 D Facial Recognition : A Survey,"IOSR Journal of Engineering (IOSRJEN) e-ISSN: 2250-3021, p-ISSN: 2278-8719 Vol. 3, Issue 4 (April. 2013), ||V1 || PP 43-48 Face Databases for 2D and 3D Facial Recognition: A Survey R.Senthilkumar1, Dr.R.K.Gnanamurthy2 Assistant Professor, Department of Electronics and Communication Engineering, Institute of Road and Professor and Dean , Department of Electronics and Communication Engineering, Odaiyappa College of Transport Technology,Erode-638 316. Engineering and Technology,Theni-625 531." 981c2619adb110dec12165ac9dde93f2a9d4e389,Semi-automatic Hand Annotation Making Human-human Interaction Analysis Fast and Accurate, 9853136dbd7d5f6a9c57dc66060cab44a86cd662,"Improving the Neural Network Training for Face Recognition using Adaptive Learning Rate , Resilient Back Propagation and Conjugate Gradient Algorithm","International Journal of Computer Applications (0975 – 8887) Volume 34– No.2, November 2011 Improving the Neural Network Training for Face Recognition using Adaptive Learning Rate, Resilient Back Propagation and Conjugate Gradient Algorithm Hamed Azami M.Sc. Student Department of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran Saeid Sanei Associate Professor Department of Computing, Faculty of Engineering and Physical Sciences, University of Surrey, UK Karim Mohammadi Professor Department of Electrical" 98f66e4597fb51a1f9990d30856f2e190dc44da1,Quantum-inspired evolutionary algorithms: a survey and empirical study,"J Heuristics (2011) 17: 303–351 DOI 10.1007/s10732-010-9136-0 Quantum-inspired evolutionary algorithms: a survey nd empirical study Gexiang Zhang Received: 2 December 2009 / Revised: 1 June 2010 / Accepted: 13 June 2010 / Published online: 29 June 2010 © Springer Science+Business Media, LLC 2010" 98b98a8413f21a48ee6effd52da8c31ece6a910d,Detecting handwritten signatures in scanned documents,"9th Computer Vision Winter Workshop Zuzana Kúkelová and Jan Heller (eds.) Křtiny, Czech Republic, February 3–5, 2014 Detecting handwritten signatures in scanned documents İlkhan Cüceloğlu1,2, Hasan Oğul1 Department of Computer Engineering, Başkent University, Ankara, Turkey DAS Document Archiving and Management Systems CO., Ankara, Turkey" 981449cdd5b820268c0876477419cba50d5d1316,Learning Deep Features for One-Class Classification,"Learning Deep Features for One-Class Classification Pramuditha Perera, Student Member, IEEE, and Vishal M. Patel, Senior Member , IEEE" 984ecfbda7249e67eca8d9b1697e81f80e2e483d,Visual object categorization with new keypoint-based adaBoost features,"Visual object categorization with new keypoint-based daBoost features Taoufik Bdiri, Fabien Moutarde, Bruno Steux To cite this version: Taoufik Bdiri, Fabien Moutarde, Bruno Steux. Visual object categorization with new keypoint-based daBoost features. IEEE Symposium on Intelligent Vehicles (IV’2009), Jun 2009, XiAn, China. 2009. HAL Id: hal-00422580 https://hal.archives-ouvertes.fr/hal-00422580 Submitted on 7 Oct 2009 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 98127346920bdce9773aba6a2ffc8590b9558a4a,Efficient human action recognition using histograms of motion gradients and VLAD with descriptor shape information,"Noname manuscript No. (will be inserted by the editor) Ef‌f‌icient Human Action Recognition using Histograms of Motion Gradients and VLAD with Descriptor Shape Information Ionut C. Duta · Jasper R.R. Uijlings · Bogdan Ionescu · Kiyoharu Aizawa · Alexander G. Hauptmann · Nicu Sebe Received: date / Accepted: date" 9889596a98824bdf7e7c59b62e732c0b2d356c69,Soft Correspondences in Multimodal Scene Parsing.,"Sarah Taghavi Namin, Mohammad Najafi, Mathieu Salzmann, and Lars Petersson" 988d1295ec32ce41d06e7cf928f14a3ee079a11e,Semantic Deep Learning,"Semantic Deep Learning Hao Wang September 29, 2015" 98142e84a3cee08661b31371a2c610183df82c8f,Tight Bounds for the Expected Risk of Linear Classifiers and PAC-Bayes Finite-Sample Guarantees,"Tight Bounds for the Expected Risk of Linear Classifiers and PAC-Bayes Finite-Sample Guarantees Jean Honorio CSAIL, MIT Cambridge, MA 02139, USA" 98bf42055160845e6f8f3c022298e3b8e4e55f80,Vision Meets Drones: A Challenge,"Vision Meets Drones: A Challenge Pengfei Zhu, Longyin Wen, Xiao Bian, Haibin Ling and Qinghua Hu" 986be05b286d99d840583578c102af31c56428fd,An Efficient Algorithm for Implementing Traffic Sign Detection on Low Cost Embedded System,"International Journal of Innovative Computing, Information and Control Volume 14, Number 1, February 2018 ICIC International c(cid:13)2018 ISSN 1349-4198 pp. 1–14 AN EFFICIENT ALGORITHM FOR IMPLEMENTING TRAFFIC SIGN DETECTION ON LOW COST EMBEDDED SYSTEM Aryuanto Soetedjo and I Komang Somawirata Department of Electrical Engineering National Institute of Technology Jalan Raya Karanglo KM 2 Malang 65153, Indonesia Received May 2017; revised September 2017" 98220d35ae6a3ba745f7dea1434f000ca60c62c0,Multi-object Tracking using Particle Swarm Optimization on Target Interactions,"Multi-object Tracking using Particle Swarm Optimization on Target Interactions Bogdan Kwolek" 98f1613889657963b102460e4e970fe421c6ed3c,Accurate and Robust Neural Networks for Security Related Applications Exampled by Face Morphing Attacks,"Accurate and Robust Neural Networks for Security Related Applications Exampled by Face Morphing Attacks Clemens Seibold1, Wojciech Samek1, Anna Hilsmann1 and Peter Eisert1,2 Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany Humboldt University Berlin, Unter den Linden 6, 10099 Berlin, Germany" 9818c401e36dcf43b261e62c053bcfddd0b903ea,Visual Simultaneous Localization And Mapping ( VSLAM ) methods applied to indoor 3 D topographical and radiological mapping in real-time,"EPJ Web of Conferences 53 ICRS-13 & RPSD-2016 , 01005 (2017) DOI: 10.1051/ epjconf/201 71530 Visual Simultaneous Localization And Mapping (VSLAM) methods applied to indoor 3D topographical and radiological mapping in real-time Felix Hautot1,3, Philippe Dubart2, Charles-Olivier Bacri3, Benjamin Chagneau2, Roger Abou-Khalil4 AREVA D&S, Technical Department, 1 route de la Noue 91196 Gif-sur-Yvette, France AREVA D&S Technical Department, Marcoule, France CSNSM (IN2P3/CNRS), Bat 104 et 108, 91405 Orsay, France AREVA Corporate, Innovation Department, 1 place Jean Millier, 92084 Paris La Défense, France" 980cf8e3b59dd0923f7e7cf66d2bec4102d7035f,Unsupervised Learning for Physical Interaction through Video Prediction,"Unsupervised Learning for Physical Interaction through Video Prediction Chelsea Finn∗ UC Berkeley Ian Goodfellow OpenAI Sergey Levine Google Brain UC Berkeley" 98c7a6210ca7bc81d2f7092ab28451f47039e920,UC Merced Proceedings of the Annual Meeting of the Cognitive Science Society Title What is the Ground ?,"UC Merced Proceedings of the Annual Meeting of the Cognitive Science Society Title What is the Ground? Continuous Maps for Symbol Grounding Permalink https://escholarship.org/uc/item/9p5236j4 Journal Proceedings of the Annual Meeting of the Cognitive Science Society, 36(36) Authors Perera, Ian Allen, James Publication Date 014-01-01 Peer reviewed eScholarship.org Powered by the California Digital Library University of California" 9833e347f8e19de59b931c94d50ef2685fd405fb,Statistical models for fruit detectability : spatial and temporal analyses of sweet peppers,"Statistical models for fruit detectability: spatial and temporal analyses of sweet peppers. Polina Kurtser, Yael Edan Ben-Gurion University of the Negev" 98960be5ae51d30118f091f7091299a49f2f34bb,1 GLOBAL AND FEATURE BASED GENDER CLASSIFICATION OF FACES : A COMPARISON OF HUMAN PERFORMANCE AND COMPUTATIONAL MODELS,"GLOBAL AND FEATURE BASED GENDER CLASSIFICATION OF FACES: A COMPARISON OF HUMAN PERFORMANCE AND COMPUTATIONAL MODELS SAMARASENA BUCHALAA TIM M.GALEA,B NEIL DAVEYA RAY J.FRANKA KERRY FOLEYB A Department of Computer Science, University of Hertfordshire, College Lane, Hatfield, {S.Buchala, N.Davey, T.Gale, AL10 9AB, UK B Department of Psychiatry, QEII Hospital, Welwyn Garden City, AL7 4HQ, UK Most computational models for gender classification use global information (the full face image) giving equal weight to the whole face area irrespective of the importance of the internal features. Here, we use a global and feature based representation of face images that includes both global and featural information. We use dimensionality reduction techniques and a support vector machine classifier and show that this method performs etter than either global or feature based representations alone. . Introduction Most computational models of gender classification use whole face images, giving equal weight to all areas of the face, irrespective of the importance of internal facial features. In this paper we evaluate the importance of global and local information in a series of gender recognition experiments. Global" 981847c0a3d667aae385276221834edbb8ebd11c,A generalizable approach for multi-view 3D human pose regression,"A generalizable approach for multi-view 3D human pose regression Abdolrahim Kadkhodamohammadia,∗, Nicolas Padoya ICube, University of Strasbourg, CNRS, IHU Strasbourg, France" 984d5ed1fa80124117fdd0aa9a5be69f269da268,[insert Cover Letter Here],[Insert cover letter here] 98582edd6029c94844f5a40d246eaa86f74d8512,Learning Visual Scene Attributes,"Learning Visual Scene Attributes Vazheh Moussavi A Glance at Attribute-Centric Scene Representations Take a look around you. How would you describe your surroundings to best give an idea of what everything looks like to someone not there? Maybe you will give a category to the scene, say, ‘bedroom’. You might try to list some of the objects around you, like ‘bed’, ‘lamp’, and ‘desk’. Or perhaps you’ll describe it with adjectives like ‘indoors’, ‘cozy’, and ‘cluttered’. In computer vision, (or more specifically, in scene understanding), the most effective way to describe a visual scene is lso a major question. Of the these three ways of describing a scene, (commonly referred to as categorization, scene pars- ing, and attribute-based representation respectively), categories have historically been the method of hoice. In categorization, an image (scene) is allowed to fall into exactly one of an arbitrary number of buckets. Attribute representations, however, are typically composed of several sets of buckets each of which will have a value associated with that scene. For instance, a simple category-based model would place an image in one of urban/rural/room, whereas a binary attribute-based model would have as attributes indoors and warm, each of which are marked as either present or not. In larger models, this leads to high dimensionality for attribute-based models, which has been a large disincentive for its use. In addition, classifying a scene’s entire attribute set non-trivially falls un- der multi-label learning, for which there exist very few learning algorithms in popular use. Lastly, there is scene parsing[5], which involves using object detectors, possibly in conjunction, to build" 986224bad9684c359db7fac2192b7134b855fbe3,Shopping for emotion Evaluating the usefulness of emotion recognition data from a retail perspective,"Shopping for emotion Evaluating the usefulness of emotion recognition data from a retail perspective Anton Forsberg Anton Forsberg VT 2017 Examensarbete f¨or civilingenj¨orer, 30hp Supervisor: Lars-Erik Janlert Examiner: Anders Broberg Civilingenj¨orsprogammet i Interaktion & Design" 98424c79970a80f30db837db84880a4c02e76f1a,Deepagent: An Algorithm Integration Approach for Person Re-Identification,"DEEPAGENT: AN ALGORITHM INTEGRATION APPROACH FOR PERSON RE-IDENTIFICATION Fulong Jiao, Bir Bhanu Center for Research in Intelligent Systems University of California, Riverside, Riverside, CA 92521, USA" 98126d18be648640fc3cfeb7ffc640a2ec1d5f6f,Supplemental Material : Discovering Groups of People in Images,"Supplemental Material: Discovering Groups of People in Images Wongun Choi1, Yu-Wei Chao2, Caroline Pantofaru3 and Silvio Savarese4 . NEC Laboratories 2. University of Michigan, Ann Arbor . Google, Inc . Stanford University Qualitative Examples In Fig. 1 and 2, we show additional qualitative examples obtained using our model with poselet [1] and ground truth (GT) detections, respectively. We show the image onfiguration of groups on the left and corresponding 3D configuration on the right. Different colors and different line types (solid or dashed) represent different groups, the type of each structured group is overlayed on the bottom-left of one participant. In D visualization, squares represent standing people, circles represent people sitting on n object, and triangles represent people sitting on the ground. The view point of each individual is shown with a line. The gray triangle is the camera position. The poses are obtained by using the individual pose classification output for visualization purposes. The figures show that our algorithm is capable of correctly associating individu- ls into multiple different groups while estimating the type of each group. Notice that our algorithm can successfully segment different instances of the same group type that ppear in proximity. A distance-based clustering method would not be able to differ-" 98eba4505ae23473bb377ee1040ae24331b26247,An Anomaly Detection Algorithm of Cloud Platform Based on Self-Organizing Maps,"Publishing CorporationMathematical Problems in EngineeringVolume 2016, Article ID 3570305, 9 pageshttp://dx.doi.org/10.1155/2016/3570305" 982db27f0a092d5c8db88e959a77fae5b4f9cdf6,"A cross-cultural, multimodal, affective corpus for gesture expressivity analysis","J Multimodal User Interfaces DOI 10.1007/s12193-012-0112-x ORIGINAL PAPER A cross-cultural, multimodal, affective corpus for gesture expressivity analysis G. Caridakis · J. Wagner · A. Raouzaiou · F. Lingenfelser · K. Karpouzis · E. Andre Received: 5 March 2012 / Accepted: 15 September 2012 © OpenInterface Association 2012" 982b86f58f33fe27edc03bbde5a419e242c99998,Analysis Of Face Recognition-A Case Study On Feature Selection And Feature Normalization,"B.Vijay, A.Nagabhushana Rao / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 3, Issue 3, May-Jun 2013, pp.971-979 Analysis Of Face Recognition- A Case Study On Feature Selection And Feature Normalization B.Vijay1, A.Nagabhushana Rao2 ,2Assistant Professor, Dept of CSE, AITAM ,Tekkali, Andhra Pradesh, INDIA." 980d4a2aeb7e55406e6784340e846883b2f77021,Noise Models in Feature-based Stereo Visual Odometry,"Noise Models in Feature-based Stereo Visual Odometry Pablo F. Alcantarilla† and Oliver J. Woodford‡ the location of each feature in each image," 988d5ad8d114f5f21a73b2ae464dca4277f5725f,Persian Viseme Classification Using Interlaced Derivative Patterns and Support Vector Machine,"Journal of Information Assurance and Security. ISSN 1554-1010 Volume 9 (2014) pp. 148-156 © MIR Labs, www.mirlabs.net/jias/index.html Persian Viseme Classification Using Interlaced Derivative Patterns and Support Vector Machine Mohammad Mahdi Dehshibi1, Jamshid Shanbehzadeh2 Digital Signal Processing Lab., Pattern Research Center, Karaj, Iran Department of Computer Engineering, Kharazmi University, Tehran, Iran is a" 98f13ab2845cfe8513a0c05427a8b90d9c0c1b69,Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations, 9854145f2f64d52aac23c0301f4bb6657e32e562,An Improved Face Verification Approach Based on Speedup Robust Features and Pairwise Matching,"An Improved Face Verification Approach based on Speedup Robust Features and Pairwise Matching Eduardo Santiago Moura, Herman Martins Gomes and Jo˜ao Marques de Carvalho Center for Electrical Engineering and Informatics (CEEI) Federal University of Campina Grande (UFCG) Campina Grande, Para´ıba, Brazil Email:" 98c5b88db35d7ab2d3cc0a63c7ff1414160d2aa6,Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors,"Article Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors Hyung Gil Hong, Min Beom Lee and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (H.G.H); (M.B.L.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Academic Editor: Vittorio M. N. Passaro Received: 11 May 2017; Accepted: 1 June 2017; Published: 6 June 2017" 98a6f2145a358cb2e54eddc99dd29911764bce0e,Learning Single-view 3D Reconstruction of Objects and Scenes,"Learning Single-view 3D Reconstruction of Objects and Scenes Shubham Tulsiani Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2018-93 http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-93.html July 26, 2018" 98519f3f615e7900578bc064a8fb4e5f429f3689,Dictionary-Based Domain Adaptation Methods for the Re-identification of Faces,"Dictionary-based Domain Adaptation Methods for the Re-identification of Faces Qiang Qiu, Jie Ni, and Rama Chellappa" 987dd3dd6079e5fa8a10a1c53b2580fd71e27ede,Concept-Based Video Retrieval By Cees,"Foundations and Trends R(cid:1) in Information Retrieval Vol. 2, No. 4 (2008) 215–322 (cid:1) 2009 C. G. M. Snoek and M. Worring DOI: 10.1561/1500000014 Concept-Based Video Retrieval By Cees G. M. Snoek and Marcel Worring Contents Introduction How to Retrieve Video Content? Human-Driven Labeling .3 Machine-Driven Labeling Aims, Scope, and Organization Detecting Semantic Concepts in Video Introduction Basic Concept Detection Feature Fusion Classifier Fusion .5 Modeling Relations Best of Selection" fe4986bbb10f3417372a02fed1218acb5162ddec,Classification model of arousal and valence mental states by EEG signals analysis and Brodmann correlations,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 6, No. 6, 2015 Classification model of arousal and valence mental states by EEG signals analysis and Brodmann orrelations Adrian Rodriguez Aguin˜aga and Miguel Angel Lo´pez Ram´ırez Instituto Tecnolo´gico de Tijuana Calzada del Tecnolo´gico S/N, Toma´s Aquino, 22414 Tijuana, B.C. Me´xico Mar´ıa del Rosario Baltazar Flores Instituto Tecnolo´gico de Leo´n Av. Tecnolo´gico S/N Industrial Julia´n de Obrego´n, 37290 Leo´n, Gto. Me´xico" fe01e1099dc2ce02158de607be993f9fc8aade57,Aerial LaneNet: Lane Marking Semantic Segmentation in Aerial Imagery using Wavelet-Enhanced Cost-sensitive Symmetric Fully Convolutional Neural Networks,"Aerial LaneNet: Lane Marking Semantic Segmentation in Aerial Imagery using Wavelet-Enhanced Cost-sensitive Symmetric Fully Convolutional Neural Networks Seyed Majid Azimi, Peter Fischer, Marco Körner, and Peter Reinartz" fec5c0100c72d7c1c823a91dc146ecd5e98e77ff,Coherence criterion for region labelling and description,"Coherence criterion for region labelling and description Hichem Houissa INRIA Rocquencourt Domaine de Voluceau Nozha Boujemaa INRIA Rocquencourt Domaine de Voluceau Email: Email:" fecce467b42856eadb8dd0c08674d9381f52efab,The Role of Shape in Visual Recognition,"The Role of Shape in Visual Recognition Bj¨orn Ommer" fe7f5c7da203c48aa1a9a2468aae55c6e0053df9,Interactive Text2Pickup Network for Natural Language based Human-Robot Collaboration,"Interactive Text2Pickup Network for Natural Language based Human-Robot Collaboration Hyemin Ahn, Sungjoon Choi, Nuri Kim, Geonho Cha, and Songhwai Oh" fec6648b4154fc7e0892c74f98898f0b51036dfe,"A Generic Face Processing Framework : Technologies , Analyses and Applications","A Generic Face Processing Framework: Technologies, Analyses and Applications JANG Kim-fung A Thesis Submitted in Partial Ful(cid:12)lment of the Requirements for the Degree of Master of Philosophy Computer Science and Engineering Supervised by Prof. Michael R. Lyu (cid:13)The Chinese University of Hong Kong July 2003 The Chinese University of Hong Kong holds the copyright of this thesis. Any person(s) intending to use a part or whole of the materials in the thesis in proposed publication must seek copyright release from the Dean of the Graduate School." fe9c460d5ca625402aa4d6dd308d15a40e1010fa,Neural Architecture for Temporal Emotion Classification,"Neural Architecture for Temporal Emotion Classification Roland Schweiger, Pierre Bayerl, and Heiko Neumann Universit¨at Ulm, Neuroinformatik, Germany" fe51fd153fa6dac3b7c50fe79e71123af5c5f43c,Satellite image-based localization via learned embeddings,"Satellite Image-based Localization via Learned Embeddings Dong-Ki Kim Matthew R. Walter" fe35639349a87808481e64f9cbea065339063154,Understanding deep learning via backtracking and deconvolution,"Fang J Big Data (2017) 4:40 DOI 10.1186/s40537-017-0101-8 METHODOLOGY Understanding deep learning via backtracking and deconvolution Open Access Xing Fang* *Correspondence: School of Information Technology, Illinois State University, Normal, IL, USA" fed9e971e042b40cc659aca6e338d79dc1d4b59c,GROUPING-BY-ID: GUARDING AGAINST ADVERSAR-,"Under review as a conference paper at ICLR 2018 GROUPING-BY-ID: GUARDING AGAINST ADVERSAR- IAL DOMAIN SHIFTS Anonymous authors Paper under double-blind review" febb6454a3bfbc76f4c7934854d377ac15666215,Improving the Accuracy of Face Annotation in Social Network,"International Journal of Computer Applications (0975 – 8887) Volume 182 – No. 14, September 2018 Improving the Accuracy of Face Annotation in Social Network C. Jayaramulu Research Scholar individual Dayananda Sagar University, Bangalore photographs." fe07ddb8dd1ba331affea713b75f68546bbaf106,"People detection, tracking and re-identification through a video camera network. (Détection, suivi et ré-identification de personnes à travers un réseau de caméra vidéo)","People detection, tracking and re-identification through video camera network Malik Souded To cite this version: Malik Souded. People detection, tracking and re-identification through a video camera network. Other [cs.OH]. Université Nice Sophia Antipolis, 2013. English. . HAL Id: tel-00913072 https://tel.archives-ouvertes.fr/tel-00913072v2 Submitted on 29 Jan 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" fe8b2b2a2ace6d6af28dc0f1d63400554c8c675d,Random walk distances in data clustering and applications,"Adv Data Anal Classif (2013) 7:83–108 DOI 10.1007/s11634-013-0125-7 REGULAR ARTICLE Random walk distances in data clustering nd applications Sijia Liu · Anastasios Matzavinos · Sunder Sethuraman Received: 28 September 2011 / Revised: 24 May 2012 / Accepted: 30 September 2012 / Published online: 6 March 2013 © Springer-Verlag Berlin Heidelberg 2013" fe466e84fa2e838adc3c37ee327cd68004ae08fe,MUTAN: Multimodal Tucker Fusion for Visual Question Answering,"MUTAN: Multimodal Tucker Fusion for Visual Question Answering Hedi Ben-younes 1,2 * R´emi Cadene 1* Matthieu Cord 1 Nicolas Thome 3 Sorbonne Universit´es, UPMC Univ Paris 06, CNRS, LIP6 UMR 7606, 4 place Jussieu, 75005 Paris Heuritech, 248 rue du Faubourg Saint-Antoine, 75012 Paris Conservatoire National des Arts et M´etiers" fe9b0accf0e7d3821bc5d7d62937499a441633c9,Learning Disentangled Representations with Reference-Based Variational Autoencoders,"Learning Disentangled Representations with Reference-Based Variational Autoencoders Adria Ruiz 1 Oriol Martinez 2 Xavier Binefa 2 Jakob Verbeek 1" fea0895326b663bf72be89151a751362db8ae881,Homocentric Hypersphere Feature Embedding for Person Re-identification,"Homocentric Hypersphere Feature Embedding for Person Re-identification Wangmeng Xiang, Jianqiang Huang, Xianbiao Qi, Xiansheng Hua, Fellow, IEEE and Lei Zhang, Fellow, IEEE" fe07ab1f417c96ae9851aaf0b59908925073fdd5,AN ADAPTIVE COLOUR BASED FACE DETECTOR SYSTEM FOR A SOCIAL MOBILE ROBOT,"AN ADAPTIVE COLOUR BASED FACE DETECTOR SYSTEM FOR A SOCIAL MOBILE ROBOT Jon Azpiazu , Tim Smithers I˜naki Ra˜n´o Parque Tecnol´ogico de San Sebasti´an Depto. Inform´atica e Ingenier´ıa de Sistemas Mikeletegi 53, 0009 San Sebasti´an (Spain) / Mar´ıa de Luna 1, 50018 Zaragoza (Spain)" fec9fb202906e6f136ae92c3a3540b2a84257c4e,Automatic Facial Feature Detection for Facial Expression Recognition,"AUTOMATIC FACIAL FEATURE DETECTION FOR FACIAL EXPRESSION RECOGNITION Taner Danisman, Marius Bilasco, Nacim Ihaddadene and Chabane Djeraba LIFL - UMR CNRS 8022, University of Science and Technology of Lille, Villeneuve d'Ascq, France Keywords: Facial Feature Detection, Emotion Recognition, Eye Detection, Mouth Corner Detection." fe59049553ee2a6eb78a7aa1f6b660b122f312d9,Advances of Robust Subspace Face Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,700 08,500 .7 M Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact" fe41550ed350df4cd731a5df3dca5b0ea13511db,Compact Generalized Non-local Network,"Compact Generalized Non-local Network Kaiyu Yue1,3 Ming Sun1 Yuchen Yuan1 Feng Zhou2 Errui Ding1 Fuxin Xu3 Baidu VIS 2Baidu Research Central South University {yuekaiyu, sunming05, yuanyuchen02, zhoufeng09," fea83550a21f4b41057b031ac338170bacda8805,Learning a Metric Embedding for Face Recognition using the Multibatch Method,"Learning a Metric Embedding for Face Recognition using the Multibatch Method Oren Tadmor Yonatan Wexler Tal Rosenwein Shai Shalev-Shwartz Amnon Shashua Orcam Ltd., Jerusalem, Israel" feb4bcd20de6ce4f9503ef01c87390e662538c15,Monocular Depth Estimation with Augmented Ordinal Depth Relationships,"Monocular Depth Estimation with Augmented Ordinal Depth Relationships Yuanzhouhan Cao, Tianqi Zhao, Ke Xian, Chunhua Shen, Zhiguo Cao" fe40be62a131deaf62a5a313e2842234845ee200,Dissimilarity-based people re-identification and search for intelligent video surveillance,"Ph.D. in Electronic and Computer Engineering Dept. of Electrical and Electronic Engineering University of Cagliari Dissimilarity-based people re-identification and search for intelligent video surveillance Riccardo Satta Advisor: Prof. Fabio Roli Co-advisor: Prof. Giorgio Fumera Curriculum: ING-INF/05 - Sistemi di Elaborazione delle Informazioni XXV Cycle April 2013" feb171df36e33cfc23cc27b782c40fa49af64a58,Disentangling Propagation and Generation for Video Prediction,"Disentangling Propagation and Generation for Video Prediction Hang Gao∗,1 Huazhe Xu∗,2 Qi-Zhi Cai3 Ruth Wang2 Columbia University1 UC Berkeley2 Nanjing University3 Fisher Yu2 Trevor Darrell2" fe0c51fd41cb2d5afa1bc1900bbbadb38a0de139,Bayesian face recognition using 2D Gaussian-Hermite moments,"Rahman et al. EURASIP Journal on Image and Video Processing (2015) 2015:35 DOI 10.1186/s13640-015-0090-5 RESEARCH Open Access Bayesian face recognition using 2D Gaussian-Hermite moments S. M. Mahbubur Rahman1*, Shahana Parvin Lata2 and Tamanna Howlader2" fec295c6b6a1795d8ccb4592603040794667dfa7,LDOP: Local Directional Order Pattern for Robust Face Retrieval,"LDOP: Local Directional Order Pattern for Robust Face Retrieval Shiv Ram Dubey and Snehasis Mukherjee" fe005c5036ad646051cc779aafb63534bda14f06,I The Hand Vein Pattern Used as a Biometric Feature – Annemarie Nadort The Hand Vein Pattern Used as a Biometric Feature,"The Hand Vein Pattern Used as a Biometric Feature Master Literature Thesis Annemarie Nadort Amsterdam - May 2007" fe030b87e3c985c9dedab130949e2868e3e5e7d5,Explaining Neural Networks Semantically,"Under review as a conference paper at ICLR 2019 EXPLAINING NEURAL NETWORKS SEMANTICALLY AND QUANTITATIVELY Anonymous authors Paper under double-blind review" feaedb6766f42e867aab7f1a33ba4d7ddacfc7aa,UvA-DARE ( Digital Academic Repository ) Tag-based Video Retrieval by Embedding Semantic Content in a Continuous Word,"UvA-DARE (Digital Academic Repository) Tag-based Video Retrieval by Embedding Semantic Content in a Continuous Word Space Agharwal, A.; Kovvuri, R.; Nevatia, R.; Snoek, C.G.M. Published in: 016 IEEE Winter Conference on Applications of Computer Vision: WACV 2016: Lake Placid, New York, USA, 7-10 March 2016 0.1109/WACV.2016.7477706 Link to publication Citation for published version (APA): Agharwal, A., Kovvuri, R., Nevatia, R., & Snoek, C. G. M. (2016). Tag-based Video Retrieval by Embedding Semantic Content in a Continuous Word Space. In 2016 IEEE Winter Conference on Applications of Computer Vision: WACV 2016: Lake Placid, New York, USA, 7-10 March 2016 (pp. 1354-1361). Piscataway, NJ: Institute of Electrical and Electronic Engineers. DOI: 10.1109/WACV.2016.7477706 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask" fef89593599b78db7d133fc6893519b3ee8ff8d2,3 D Face recognition by ICP-based shape matching,"D Face recognition by ICP-based shape matching Boulbaba Ben Amor1, Karima Ouji1, Mohsen Ardabilian1, Liming Chen1 LIRIS Lab, Lyon Research Center for Images and Intelligent Information Systems, UMR 5205 CNRS Centrale Lyon, France" 346dbc7484a1d930e7cc44276c29d134ad76dc3f,Artists portray human faces with the Fourier statistics of complex natural scenes.,"This article was downloaded by:[University of Toronto] On: 21 November 2007 Access Details: [subscription number 785020433] Publisher: Informa Healthcare Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK Systems Publication details, including instructions for authors and subscription information: http://www.informaworld.com/smpp/title~content=t713663148 Artists portray human faces with the Fourier statistics of omplex natural scenes Christoph Redies a; Jan Hänisch b; Marko Blickhan a; Joachim Denzler b Institute of Anatomy I, School of Medicine, Friedrich Schiller University, Germany Department of Computer Science, Friedrich Schiller University, D-07740 Jena, Germany First Published on: 28 August 2007 To cite this Article: Redies, Christoph, Hänisch, Jan, Blickhan, Marko and Denzler, Joachim (2007) 'Artists portray human faces with the Fourier statistics of complex To link to this article: DOI: 10.1080/09548980701574496 URL: http://dx.doi.org/10.1080/09548980701574496" 34c594abba9bb7e5813cfae830e2c4db78cf138c,Transport-based single frame super resolution of very low resolution face images,"Transport-Based Single Frame Super Resolution of Very Low Resolution Face Images Soheil Kolouri1, Gustavo K. Rohde1,2 Department of Biomedical Engineering, Carnegie Mellon University. 2Department of Electrical and Computer Engineering, Carnegie Mellon University. We describe a single-frame super-resolution method for reconstructing high- resolution (abbr. high-res) faces from very low-resolution (abbr. low-res) face images (e.g. smaller than 16× 16 pixels) by learning a nonlinear La- grangian model for the high-res face images. Our technique is based on the mathematics of optimal transport, and hence we denote it as transport-based SFSR (TB-SFSR). In the training phase, a nonlinear model of high-res fa- ial images is constructed based on transport maps that morph a reference image into the training face images. In the testing phase, the resolution of degraded image is enhanced by finding the model parameters that best fit the given low resolution data. Generally speaking, most SFSR methods [2, 3, 4, 5] are based on a linear model for the high-res images. Hence, ultimately, the majority of SFSR models in the literature can be written as, Ih(x) = ∑i wiψi(x), where Ih is a high-res image or a high-res image patch, w’s are weight coefficients, nd ψ’s are high-res images (or image patches), which are learned from the training images using a specific model. Here we propose a fundamentally different approach toward modeling high-res images. In our approach the" 34d53d2a418051c56cad9e0c90ea793af6cbb729,Structured Multi-class Feature Selection for Effective Face Recognition,"Structured multi-class feature selection for effective face recognition Giovanni Fusco, Luca Zini, Nicoletta Noceti, and Francesca Odone DIBRIS - Universit`a di Genova via Dodecaneso, 35 6146-IT, Italy" 34128e93f4af820cea65477526645cdc82e0e59b,Decomposed Learning for Joint Object Segmentation and Categorization,"TSAI et al.: DECOMPOSED LEARNING FOR OBJECT RECOGNITION Decomposed Learning for Joint Object Segmentation and Categorization Yi-Hsuan Tsai Jimei Yang Ming-Hsuan Yang Electrical Engineering and Computer Science University of California Merced, USA" 34f60ecedeb798397849b171e2e8bcf46c9b7ada,An Efficient Face Recognition System based on the Combination of Pose Invariant and Illumination Factors,"International Journal of Computer Applications (0975 – 8887) Volume 50 – No.2, July 2012 An Efficient Face Recognition System based on the Combination of Pose Invariant and Illumination Factors S. Muruganantham Assistant Professor, S.T.Hindu College, Nagercoil. the performance of" 348035720dba98ff54f2ff8c375ace09287c89f6,3D Human Pose Estimation in RGBD Images for Robotic Task Learning,"D Human Pose Estimation in RGBD Images for Robotic Task Learning Christian Zimmermann*, Tim Welschehold*, Christian Dornhege, Wolfram Burgard and Thomas Brox" 341ed69a6e5d7a89ff897c72c1456f50cfb23c96,"DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network","DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Networks Afshin Dehghan Enrique G. Ortiz Guang Shu Syed Zain Masood {afshindehghan, egortiz, guangshu, Computer Vision Lab, Sighthound Inc., Winter Park, FL" 34d784636e2a8078a6c517f6a9b132b31c2ab3d2,Recognition of a Person Wearing Sport Shoes or High Heels through Gait Using Two Types of Sensors,"Article Recognition of a Person Wearing Sport Shoes or High Heels through Gait Using Two Types of Sensors Marcin Derlatka 1,* and Mariusz Bogdan 2 Department of Biocybernetics and Biomedical Engineering of the Faculty of Mechanical Engineering at Bialystok University of Technology, 15-351 Bialystok, Poland Department of Automatic Control and Robotics of the Faculty of Mechanical Engineering at Bialystok University of Technology, 15-351 Bialystok, Poland; * Correspondence: Tel.: +48-571-443-044 Received: 9 April 2018; Accepted: 18 May 2018; Published: 21 May 2018" 340d1a9852747b03061e5358a8d12055136599b0,Audio-Visual Recognition System Insusceptible to Illumination Variation over Internet Protocol,"Audio-Visual Recognition System Insusceptible to Illumination Variation over Internet Protocol Yee Wan Wong, Kah Phooi Seng, and Li-Minn Ang" 340798e6b7a9863005863f38c1bbfda5cf85d201,"Image Retrieval, Object Recognition, and Discriminative Models","Image Retrieval, Object Recognition, nd Discriminative Models Von der Fakult¨at f¨ur Mathematik, Informatik und Naturwissenschaften der RWTH Aachen University zur Erlangung des akademischen Grades eines Doktors der Naturwissenschaften genehmigte Dissertation vorgelegt von Diplom-Informatiker Thomas Deselaers us Aachen Berichter: Universit¨atsprofessor Dr.-Ing. Hermann Ney Universit¨atsprofessor Dr. Bernt Schiele Tag der m¨undlichen Pr¨ufung: 2. Dezember 2008 Diese Dissertation ist auf den Internetseiten der Hochschulbibliothek online verf¨ugbar." 343d21ae54b45ef219ac4ba024265eeabf4d6edd,Where Will They Go? Predicting Fine-Grained Adversarial Multi-agent Motion Using Conditional Variational Autoencoders,"Where Will They Go? Predicting Fine-Grained Adversarial Multi-Agent Motion using Conditional Variational Autoencoders Panna Felsen1,2, Patrick Lucey2, and Sujoy Ganguly2 BAIR, UC Berkeley STATS {plucey," 3468740e4a9fc72a269f4f0ca8470ccd60925f92,Robustness Analysis of Visual QA Models by Basic Questions,"Robustness Analysis of Visual QA Models by Basic Questions Jia-Hong Huang Bernard Ghanem Cuong Duc Dao* Modar Alfadly* C. Huck Yang King Abdullah University of Science and Technology ; Georgia Institute of Technology {jiahong.huang, dao.cuong, modar.alfadly, ;" 3402b5e354eebcf443789f3c8d3c97eccd3ae55e,Multimodal Machine Learning: A Survey and Taxonomy,"Multimodal Machine Learning: A Survey and Taxonomy Tadas Baltruˇsaitis, Chaitanya Ahuja, and Louis-Philippe Morency" 344f647463ef160956143ebc8ce370cca144961a,Confidence-Aware Probability Hypothesis Density Filter for Visual Multi-Object Tracking, 3493b2232449635aff50fc17e03163cb4b66f1b5,Visual exploration of machine learning results using data cube analysis,"Visual Exploration of Machine Learning Results using Data Cube Analysis Minsuk Kahng Georgia Tech Atlanta, GA, USA Dezhi Fang Georgia Tech Atlanta, GA, USA Duen Horng (Polo) Chau Georgia Tech Atlanta, GA, USA" 34d15fea236612e9df10e4c7a25ca31c0d95edd1,Biases in spatial bisection induced by viewing male and female faces.,"Research Article Biases in Spatial Bisection Induced y Viewing Male and Female Faces Zaira Cattaneo,1,2 Susanna Schiavi,1 Carlotta Lega,1 Chiara Renzi,2 Matteo Tagliaferri,1 Jana Boehringer,4 Claus-Christian Carbon,4 and Tomaso Vecchi2,3 Department of Psychology, University of Milano-Bicocca, Milano, Italy, 2Brain Connectivity Center, National Neurological Institute C. Mondino, Pavia, Italy, 3Department of Brain and Behavioral Sciences, University of Pavia, Italy, 4Department of General Psychology nd Methodology, University of Bamberg, Germany" 34ec83c8ff214128e7a4a4763059eebac59268a6,Action Anticipation By Predicting Future Dynamic Images,"Action Anticipation By Predicting Future Dynamic Images Cristian Rodriguez, Basura Fernando and Hongdong Li Australian Centre for Robotic Vision, ANU, Canberra, Australia {cristian.rodriguez, basura.fernando," 341002fac5ae6c193b78018a164d3c7295a495e4,von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification,"von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification Md. Abul Hasnat, Julien Bohn´e, Jonathan Milgram, St´ephane Gentric and Liming Chen" 34cf90fcbf83025666c5c86ec30ac58b632b27b0,Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification,"Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification Dangwei Li1,2, Xiaotang Chen1,2, Zhang Zhang1,2, Kaiqi Huang1,2,3 CRIPAC & NLPR, CASIA 2University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology {dangwei.li, xtchen, zzhang," 3413af6c689eedb4fe3e7d6c5dc626647976307a,Horizontally scalable submodular maximization,"Horizontally Scalable Submodular Maximization Mario Lucic1 Olivier Bachem1 Morteza Zadimoghaddam2 Andreas Krause1 Department of Computer Science, ETH Zurich, Switzerland Google Research, New York" 3423f3dcb0edee1c5c6a5505b9e8c0bbdcffbd51,Nurses ' Reactions to Patient Weight : Effects on Clinical Decisions,"University of Wisconsin Milwaukee UWM Digital Commons Theses and Dissertations May 2017 Nurses' Reactions to Patient Weight: Effects on Clinical Decisions Heidi M. Pfeiffer University of Wisconsin-Milwaukee Follow this and additional works at: http://dc.uwm.edu/etd Part of the Psychology Commons Recommended Citation Pfeiffer, Heidi M., ""Nurses' Reactions to Patient Weight: Effects on Clinical Decisions"" (2017). Theses and Dissertations. 1524. http://dc.uwm.edu/etd/1524 This Dissertation is brought to you for free and open access by UWM Digital Commons. It has been accepted for inclusion in Theses and Dissertations y an authorized administrator of UWM Digital Commons. For more information, please contact" 3410136b86b813b075a258842450835906d58600,A facial expression image database and norm for Asian population: A preliminary report,"Image Quality and System Performance VI, edited by Susan P. Farnand, Frans Gaykema, Proc. of SPIE-IS&T Electronic Imaging, SPIE Vol. 7242, 72421D · © 2009 SPIE-IS&T CCC code: 0277-786X/09/$18 · doi: 10.1117/12.806130 SPIE-IS&T/ Vol. 7242 72421D-1 Downloaded from SPIE Digital Library on 07 Oct 2009 to 140.112.113.225. Terms of Use: http://spiedl.org/terms" 344682f69dd9bec68d89a79b0b7f28a3891ab857,Perception of Social Cues of Danger in Autism Spectrum Disorders,"Perception of Social Cues of Danger in Autism Spectrum Disorders Nicole R. Zu¨ rcher1,2, Ophe´ lie Rogier1, Jasmine Boshyan2, Loyse Hippolyte1, Britt Russo1, Nanna Gillberg3, Adam Helles3, Torsten Ruest1, Eric Lemonnier4, Christopher Gillberg3, Nouchine Hadjikhani1,2,3* Brain Mind Institute, EPFL, Lausanne, Switzerland, 2 Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School, Massachusetts General Hospital, Charlestown, Massachusetts, United States of America, 3 Gillberg Centrum, University of Gothenburg, Gothenburg, Sweden, 4 Laboratoire de Neurosciences, Universite´ de Brest, Brest, France" 341de07abfb89bf78f3a72513c8bce40d654e0a3,Sparse and Deep Generalizations of the FRAME Model,"Annals of Mathematical Sciences and Applications Volume 3, Number 1, 211–254, 2018 Sparse and deep generalizations of the FRAME model Ying Nian Wu, Jianwen Xie, Yang Lu, and Song-Chun Zhu In the pattern theoretical framework developed by Grenander and dvocated by Mumford for computer vision and pattern recog- nition, different patterns are represented by statistical generative models. The FRAME (Filters, Random fields, And Maximum En- tropy) model is such a generative model for texture patterns. It is a Markov random field model (or a Gibbs distribution, or an energy-based model) of stationary spatial processes. The log prob- bility density function of the model (or the energy function of the Gibbs distribution) is the sum of translation-invariant potential functions that are one-dimensional non-linear transformations of linear filter responses. In this paper, we review two generalizations of this model. One is a sparse FRAME model for non-stationary patterns such as objects, where the potential functions are loca- tion specific, and they are non-zero only at a selected collection of locations. The other generalization is a deep FRAME model where" 3412d9f3c620155bf3eb203f5817a310000f0c63,Biomarkers in autism spectrum disorder: the old and the new,"DOI 10.1007/s00213-013-3290-7 REVIEW Biomarkers in autism spectrum disorder: the old and the new Barbara Ruggeri & Ugis Sarkans & Gunter Schumann & Antonio M. Persico Received: 15 April 2013 /Accepted: 7 September 2013 # Springer-Verlag Berlin Heidelberg 2013" 34f8086eb67eb2cd332cd2d6bca0dd8f1e8f1062,Face Recognition and Growth Prediction using a 3 D Morphable Face Model,"Saarland University Faculty of Natural Sciences and Technology I Department of Computer Science Master’s Program in Computer Science Master’s Thesis Face Recognition and Growth Prediction using 3D Morphable Face Model submitted by Kristina Scherbaum on October 30, 2007 Supervisor Prof. Dr. Hans-Peter Seidel Saarland University – Computer Science Department Advisor Prof. Dr. Volker Blanz Universit¨at Siegen – Dekanat FB 12 Reviewers Prof. Dr. Hans-Peter Seidel Prof. Dr. Volker Blanz" 34c7254d2f420df6309260b2bb461a9c107dfd5a,Semi-supervised image classification based on a multi-feature image query language,"University of Huddersfield Repository Pein, Raoul Pascal Semi-Supervised Image Classification based on a Multi-Feature Image Query Language Original Citation Pein, Raoul Pascal (2010) Semi-Supervised Image Classification based on a Multi-Feature Image Query Language. Doctoral thesis, University of Huddersfield. This version is available at http://eprints.hud.ac.uk/9244/ The University Repository is a digital collection of the research output of the University, available on Open Access. Copyright and Moral Rights for the items on this site are retained by the individual author and/or other copyright owners. Users may access full items free of charge; copies of full text items generally an be reproduced, displayed or performed and given to third parties in any format or medium for personal research or study, educational or not-for-profit purposes without prior permission or charge, provided: • The authors, title and full bibliographic details is credited in any copy; • A hyperlink and/or URL is included for the original metadata page; and • The content is not changed in any way. For more information, including our policy and submission procedure, please ontact the Repository Team at: http://eprints.hud.ac.uk/" 34b3b14b4b7bfd149a0bd63749f416e1f2fc0c4c,The AXES submissions at TrecVid 2013,"The AXES submissions at TrecVid 2013 Robin Aly1, Relja Arandjelovi´c3, Ken Chatfield3, Matthijs Douze6, Basura Fernando4, Zaid Harchaoui6, Kevin McGuinness2, Noel E. O’Conner2, Dan Oneata6, Omkar M. Parkhi3, Danila Potapov6, Jérôme Revaud6, Cordelia Schmid6, Jochen Schwenninger5, David Scott2, Tinne Tuytelaars4, Jakob Verbeek6, Heng Wang6, Andrew Zisserman3 University of Twente 2Dublin City University 3Oxford University KU Leuven 5Fraunhofer Sankt Augustin 6INRIA Grenoble" 34ae449ae64cd2c6bfc2f102eac82bd606cd12f7,A Unified Model with Structured Output for Fashion Images Classification,"A Unified Model with Structured Output for Fashion Images Classification Beatriz Quintino Ferreira ISR, Instituto Superior Técnico, Universidade de Lisboa, Portugal João Faria Farfetch" 343acba1d609c1e6f274e3b6733c9173b5a46342,Online Learning for Crowd-sensitive Path Planning,"Online Learning for Crowd-sensitive Path Planning Anoop Aroor of New York Robotics Track Susan L. Epstein New York Raj Korpan of New York The Graduate Center, City University Hunter College, City University of The Graduate Center, City University" 34d484b47af705e303fc6987413dc0180f5f04a9,RI : Medium : Unsupervised and Weakly-Supervised Discovery of Facial Events 1,"RI:Medium: Unsupervised and Weakly-Supervised Discovery of Facial Events Introduction The face is one of the most powerful channels of nonverbal communication. Facial expression has been a focus of emotion research for over a hundred years [11]. It is central to several leading theories of emotion [16, 28, 44] and has been the focus of at times heated debate about issues in emotion science [17, 23, 40]. Facial expression figures prominently in research on almost every aspect of emotion, including psychophys- iology [30], neural correlates [18], development [31], perception [4], addiction [24], social processes [26], depression [39] and other emotion disorders [46], to name a few. In general, facial expression provides cues bout emotional response, regulates interpersonal behavior, and communicates aspects of psychopathology. While people have believed for centuries that facial expressions can reveal what people are thinking and feeling, it is relatively recently that the face has been studied scientifically for what it can tell us about internal states, social behavior, and psychopathology. Faces possess their own language. Beginning with Darwin and his contemporaries, extensive efforts have been made to manually describe this language. A leading approach, the Facial Action Coding System (FACS) [19] , segments the visible effects of facial muscle activation into ”action units.” Because of its descriptive power, FACS has become the state of the art in manual measurement of facial expression and is widely used in studies of spontaneous facial behavior. The FACS taxonomy was develop by manually ob- serving graylevel variation between expressions in images and to a lesser extent by recording the electrical ctivity of underlying facial muscles [9]. Because of its importance to human social dynamics, person per-" 34e23b934794a5abff251698df09cbac5ad2dd56,Towards Engineering a Web-Scale Multimedia Service: A Case Study Using Spark,"Towards Engineering a Web-Scale Multimedia Service: A Case Study Using Spark∗ Gylfi Þór Guðmundsson Reykjavik University Reykjavík, Iceland Björn Þór Jónsson Reykjavik University, Iceland IT University of Copenhagen, Denmark Laurent Amsaleg IRISA–CNRS Rennes, France Michael J. Franklin University of Chicago Chicago, IL, USA" 34530c3a1df47c888506b836a061092df05972cc,Unpaired High-Resolution and Scalable Style Transfer Using Generative Adversarial Networks,"Unpaired High-Resolution and Scalable Style Transfer Using Generative Adversarial Networks Andrej Junginger, Markus Hanselmann, Thilo Strauss, Sebastian Boblest, Jens Buchner, and Holger Ulmer Machine Learning Team at ETAS GmbH (Bosch Group), Stuttgart, Germany Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data. Other astonishing results have been achieved using neural nets as data generators, especially in settings of generative adversarial networks (GANs). One special pplication is the field of image domain translations. Here, the goal is to take an image with a certain style (e. g. a photography) and transform it into another one (e. g. a painting). If such a task is performed nd this leads to a high peak memory consumption during, both, training and evaluation phase. This sets a limit to the highest processable image size. We address this issue by the idea of not processing the whole image at once, but to train and evaluate the domain translation on the level of overlapping image subsamples. This new approach not only enables us to translate high-resolution images that otherwise annot be processed by the neural network at once, but also allows us to work with comparably small neural networks and with limited hardware resources. Additionally, the number of images required for the training process is significantly reduced. We present high-quality results on images with a total resolution of up to over 50 megapixels and demonstrate that our method helps to preserve local image details while it also keeps global consistency. Introduction Over the recent years, neural networks (NNs) have be-" 3490683560ca18d19884949dccca0ad7c98d4749,Content-Based Filtering for Video Sharing Social Networks,"Content-Based Filtering for Video Sharing Social Networks Eduardo Valle1, Sandra Avila2, Fillipe de Souza2, Marcelo Coelho2,3, Arnaldo de A. Araújo2 RECOD Lab — DCA / FEEC / UNICAMP, Campinas, SP, Brazil NPDI Lab — DCC / UFMG, Belo Horizonte, MG, Brazil Preparatory School of Air Cadets — EPCAR, Barbacena, MG, Brazil {sandra, fdms, mcoelho," 34cd99528d873e842083abec429457233fdb3226,Person Re-identification using group context,"Person Re-identification using group context Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt To cite this version: Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt. Person Re- identification using group context. Advanced Concepts for Intelligent Vision systems, Sep 2018, Poitiers, France. HAL Id: hal-01895373 https://hal.archives-ouvertes.fr/hal-01895373 Submitted on 15 Oct 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 34df09a9445089c8f23eff5b2a43a822c9713f6e,Boosting chamfer matching by learning chamfer distance normalization,"Boosting Chamfer Matching by Learning Chamfer Distance Normalization Tianyang Ma, Xingwei Yang, and Longin Jan Latecki Dept. of Computer and Information Sciences,Temple Unviersity, Philadelphia. {tianyang.ma,xingwei,latecki}.temple.edu" 88dc2b2f6d033b290ed56b844c98c3ee6efde80b,Experimental manipulation of face-evoked activity in the fusiform gyrus of individuals with autism.,"!""#$%&’(#)*+%,&$%-.,/*.&-+-%012%34&*+%5/#6+’$#(17 8/2%9:%;+<(+=0+’%9>?> FB0*#$""+’%F$1)"".*.G1%F’+$$ H/I.’=&%J(-%K+G#$(+’+-%#/%L/G*&/-%&/-%M&*+$%K+G#$(+’+-%NB=0+’2%?>D9COP%K+G#$(+’+-%.II#)+2%Q.’(#=+’%R.B$+S%EDT P?%Q.’(#=+’%;(’++(S%J./-./%M?!%EURS%5V ;.)#&*%N+B’.$)#+/)+ FB0*#)&(#./%-+(&#*$S%#/)*B-#/G%#/$(’B)(#./$%I.’%&B("".’$%&/-%$B0$)’#<(#./%#/I.’=&(#./2 ""((<2WW,,,X#/I.’=&,.’*-X).=W$=<P%Q&1%9>?> N+B’.$)#+/)+SS%‘#’$(%P%Q&1%9>?>%a#‘#’$(b 5KJ2%""((<2WW-[X-.#X.’GW?>X?>d>W?DPD>C??>>E:dE?dO PLEASE SCROLL DOWN FOR ARTICLE Full terms and conditions of use: http://www.informaworld.com/terms-and-conditions-of-access.pdf This article may be used for research, teaching and private study purposes. Any substantial or systematic reproduction, re-distribution, re-selling, loan or sub-licensing, systematic supply or distribution in any form to anyone is expressly forbidden. The publisher does not give any warranty express or implied or make any representation that the contents will be complete or accurate or up to date. The accuracy of any instructions, formulae and drug doses" 8818dafda0cf230731ac2f962d8591c89a9fac09,xGEMs: Generating Examplars to Explain Black-Box Models,"xGEMs: Generating Examplars to Explain Black-Box Models Shalmali Joshi UT Austin Oluwasanmi Koyejo Been Kim Google Brain Joydeep Ghosh UT Austin" 88bbedf7f6f0dcc830640c521acece28e67be356,Robust sparse coding for face recognition,"Robust Sparse Coding for Face Recognition Meng Yang, Lei Zhang, Jian Yang, David Zhang Hong Kong Polytechnic Univ. Presenter : 江振國" 88cc7220be4ca882c129722a9a4e3ec420ece99c,Fusion of PCA and LDA Based Face Recognition System,"2012 International Conference on Software and Computer Applications (ICSCA 2012) IPCSIT vol. 41 (2012) © (2012) IACSIT Press, Singapore Fusion of PCA and LDA Based Face Recognition System Jamal Ahmad Dargham1, Ali Chekima1, Ervin Gubin Moung1 School of Engineering and Information Technology, University Malaysia Sabah, Locked Bag 2073, TelukLikas, 88999 Kota Kinabalu, Sabah, Malaysia email: {jamalad," 8855755a72c148dfde84bb08ae65d58c260e70d4,Robust image classification: analysis and applications,"POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCESacceptée sur proposition du jury:Prof. P. Vandergheynst, président du juryProf. P. Frossard, directeur de thèseProf. J. Bruna, rapporteurProf. N. Paragios, rapporteurDr F. Fleuret, rapporteurRobust image classification: analysis and applicationsTHÈSE NO 7258 (2016)ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNEPRÉSENTÉE LE 16 DÉCEMBRE 2016 À LA FACULTÉ DES SCIENCES ET TECHNIQUES DE L'INGÉNIEURLABORATOIRE DE TRAITEMENT DES SIGNAUX 4PROGRAMME DOCTORAL EN GÉNIE ÉLECTRIQUE Suisse2016PARAlhussein FAWZI" 8809860da2786eef69c078073df62f322ab882d1,Generating Textual Adversarial Examples for Deep Learning Models: A Survey,"JOURNAL OF XX, VOL. XX, NO. XX, JANUARY 2019 Generating Textual Adversarial Examples for Deep Learning Models: A Survey Wei Emma Zhang, Quan Z. Sheng, Ahoud Abdulrahmn F Alhazmi, and Chenliang Li" 8855d6161d7e5b35f6c59e15b94db9fa5bbf2912,COGNITION IN PREGNANCY AND THE POSTPARTUM PERIOD,COGNITION IN PREGNANCY AND THE POSTPARTUM PERIOD 88850b73449973a34fefe491f8836293fc208580,XBeats-An Emotion Based Music Player,"www.ijaret.org Vol. 2, Issue I, Jan. 2014 ISSN 2320-6802 INTERNATIONAL JOURNAL FOR ADVANCE RESEARCH IN ENGINEERING AND TECHNOLOGY WINGS TO YOUR THOUGHTS….. XBeats-An Emotion Based Music Player Sayali Chavan1, Ekta Malkan2, Dipali Bhatt3, Prakash H. Paranjape4 U.G. Student, Dept. of Computer Engineering, D.J. Sanghvi College of Engineering, Vile Parle (W), Mumbai-400056. U.G. Student, Dept. of Computer Engineering, D.J. Sanghvi College of Engineering, Vile Parle (W), Mumbai-400056. U.G. Student, Dept. of Computer Engineering, D.J. Sanghvi College of Engineering, Vile Parle (W), Mumbai-400056. Assistant Professor, Dept. of Computer Engineering, D.J. Sanghvi College of Engineering, Vile Parle (W), Mumbai-400056." 88c5baffa5522ea62ff5d5c41036b92e30d7e3c9,Who is who at different cameras. People re-identification using Depth Cameras,"Document downloaded from: This paper must be cited as: The final publication is available at Copyright Additional Information http://dx.doi.org/10.1049/iet-cvi.2011.0140http://hdl.handle.net/10251/56627Institution of Engineering and Technology (IET)Albiol Colomer, AJ.; Albiol Colomer, A.; Oliver Moll, J.; Mossi García, JM. (2012). Who iswho at different cameras: people re-identification using depth cameras. IET ComputerVision. 6(5):378-387. doi:10.1049/iet-cvi.2011.0140." 88fd4d1d0f4014f2b2e343c83d8c7e46d198cc79,Joint action recognition and summarization by sub-modular inference,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 88590857138505ee524f3adf6da9c57352d917f2,Random Subspace Two-Dimensional PCA for Face Recognition,"Random Subspace Two-Dimensional PCA for Face Recognition Nam Nguyen, Wanquan Liu and Svetha Venkatesh Department of Computing, Curtin University of Technology, WA 6845, Australia" 8813368c6c14552539137aba2b6f8c55f561b75f,Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition,"Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition Changxing Ding, Student Member, IEEE, Dacheng Tao, Fellow, IEEE" 8897dd825230695a8a669b29a4d1b284373adb31,Face Recognition using Co-occurrence Matrix of Local Average Binary Pattern ( CMLABP ),"Cyber Journals: Multidisciplinary Journals in Science and Technology, Journal of Selected Areas in Telecommunications (JSAT), April Edition, 2012 Face Recognition using Co-occurrence Matrix of Local Average Binary Pattern (CMLABP) A. Hazrati Bishak, Z. Ghandriz, T. Taheri" 8878871ec2763f912102eeaff4b5a2febfc22fbe,Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling,"Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling Yu-Gang Jiang, Qi Dai, Wei Liu, Xiangyang Xue, and Chong-Wah Ngo" 88c6d4b73bd36e7b5a72f3c61536c8c93f8d2320,Image patch modeling in a light field,"Image patch modeling in a light field Zeyu Li Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2014-81 http://www.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-81.html May 15, 2014" 88132a786442ab8a5038d81164384c1c1f7231c8,Limited attentional bias for faces in toddlers with autism spectrum disorders.,"ORIGINAL ARTICLE Limited Attentional Bias for Faces in Toddlers With Autism Spectrum Disorders Katarzyna Chawarska, PhD; Fred Volkmar, MD; Ami Klin, PhD Context: Toddlers with autism spectrum disorders (ASD) exhibit poor face recognition and atypical scanning pat- terns in response to faces. It is not clear if face-processing deficits are also expressed on an attentional level. Typical individuals require more effort to shift their attention from faces compared with other objects. This increased disen- gagement cost is thought to reflect deeper processing of these socially relevant stimuli. Objective: To examine if attention disengagement from faces is atypical in the early stages of ASD. Design: Attention disengagement was tested in a varia- tion of the cued attention task in which participants were required to move their visual attention from face or non- face central fixation stimuli and make a reactive saccade to a peripheral target. The design involved diagnosis as between-group factor and central fixation stimuli type" 886dfe069bd0f6bbb0a885e0bf2788007bfb737c,3-D Facial Expression Representation using B-spline Statistical Shape Model,"-D Facial Expression Representation using B-spline Statistical Shape Model Wei Quan, Bogdan J. Matuszewski, Lik-Kwan Shark, Djamel Ait-Boudaoud Applied Digital Signal and Image Processing Research Centre University of Central Lancashire Preston PR1 2HE, UK" 8850a9748da6579b939ab9f1aa705b7886c4417b,Serving Self Loading Video Composition,"International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 4, Issue 1, January 2014) Serving Self Loading Video Composition Rajesh1, Hariharan2 PG Student, 2Assistant Professor, PSN Engineering College" 887cd2271ca5a58501786d49afa53139f48c66f3,"Visual orienting in children with autism: Hyper‐responsiveness to human eyes presented after a brief alerting audio‐signal, but hyporesponsiveness to eyes presented without sound","SHORT REPORT Visual Orienting in Children With Autism: Hyper-Responsiveness to Human Eyes Presented After a Brief Alerting Audio-Signal, ut Hyporesponsiveness to Eyes Presented Without Sound Johan Lundin Kleberg, Emilia Thorup, and Terje Falck-Ytter Autism Spectrum Disorder (ASD) has been associated with reduced orienting to social stimuli such as eyes, but the results are inconsistent. It is not known whether atypicalities in phasic alerting could play a role in putative altered social orienting in ASD. Here, we show that in unisensory (visual) trials, children with ASD are slower to orient to eyes (among distractors) than controls matched for age, sex, and nonverbal IQ. However, in another condition where brief spatially nonpredictive sound was presented just before the visual targets, this group effect was reversed. Our results indicate that orienting to social versus nonsocial stimuli is differently modulated by phasic alerting mecha- nisms in young children with ASD. Autism Res 2017, 10: 246–250. VC 2016 The Authors Autism Research published y Wiley Periodicals, Inc. on behalf of International Society for Autism Research. Keywords: Autism; social orienting; eye tracking; phasic alerting; arousal; face perception According to social orienting theories of Autism Spec- trum Disorder (ASD), people with this condition orient less or slower to socially salient stimuli than people with typical development (TD; Dawson et al., 2004). Further, it is assumed that reduced orienting early in life may have cascading effects on both brain develop-" 885d589101ab3c09bda20ee9578f2c6d2f6cddfa,Learning to Guide Decoding for Image Captioning,"Learning to Guide Decoding for Image Captioning Wenhao Jiang1 Lin Ma1 Xinpeng Chen2 Hanwang Zhang3 Wei Liu1 Tencent AI Lab, 2Wuhan University, 3Nanyang Technological University {cswhjiang, xinpeng" 88a898592b4c1dfd707f04f09ca58ec769a257de,MobileFace: 3D Face Reconstruction with Efficient CNN Regression,"MobileFace: 3D Face Reconstruction with Ef‌f‌icient CNN Regression Nikolai Chinaev1, Alexander Chigorin1, and Ivan Laptev1,2 VisionLabs, Amsterdam, The Netherlands {n.chinaev, Inria, WILLOW, Departement d’Informatique de l’Ecole Normale Superieure, PSL Research University, ENS/INRIA/CNRS UMR 8548, Paris, France" 887b7d34ebac80bbe3fb3792ed579dd82ff7e373,Query-driven iterated neighborhood graph search for scalable visual indexing ∗,"Query-driven iterated neighborhood graph search for scalable visual indexing∗ Jingdong Wang† Xian-Sheng Hua‡ Shipeng Li† Microsoft Corporation Microsoft Research Asia August 10, 2012" 88e3aefe454e72388bbbe7dfa0b74fcfc52032f0,Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images,"Article Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images Yingchun Guo *, Ruoyu Wei and Yi Liu * School of Computer Science and Engineering, Hebei University of Technology, Tianjin 300400, China; * Correspondence: (Y.G.); (Y.L.) Received: 6 January 2018; Accepted: 19 February 2018; Published: 28 February 2018" 88f2952535df5859c8f60026f08b71976f8e19ec,A neural network framework for face recognition by elastic bunch graph matching,"A neural network framework for face recognition by elastic bunch graph matching Francisco A. Pujol López, Higinio Mora Mora*, José A. Girona Selva" 887b7676a4efde616d13f38fcbfe322a791d1413,Deep Temporal Appearance-Geometry Network for Facial Expression Recognition,"Deep Temporal Appearance-Geometry Network for Facial Expression Recognition Injae Lee‡ Chunghyun Ahn‡ Junmo Kim† Heechul Jung† Sihaeng Lee† Sunjeong Park† Korea Advanced Institute of Science and Technology† Electronics and Telecommunications Research Institute‡ {heechul, haeng, sunny0414, {ninja," 883006c0f76cf348a5f8339bfcb649a3e46e2690,Weakly supervised pain localization using multiple instance learning,"Weakly Supervised Pain Localization using Multiple Instance Learning Karan Sikka, Abhinav Dhall and Marian Bartlett" 8816ee1e23983f5a4340743c7744a336fae02d60,Face Recognition Using Boosted Local Features,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Face Recognition Using Boosted Local Features Michael J. Jones and Paul Viola TR2003-25 April 2003" 88babcb7cfa8e46f814c241e441c890285f6f9d4,"Is it Safe to Drive? An Overview of Factors, Challenges, and Datasets for Driveability Assessment in Autonomous Driving.","Is it Safe to Drive? An Overview of Factors, Challenges, and Datasets for Driveability Assessment in Autonomous Driving Junyao Guo, Unmesh Kurup, Mohak Shah" 88bee9733e96958444dc9e6bef191baba4fa6efa,Extending Face Identification to Open-Set Face Recognition,"Extending Face Identification to Open-Set Face Recognition Cassio E. dos Santos Jr., William Robson Schwartz Department of Computer Science Universidade Federal de Minas Gerais Belo Horizonte, Brazil" 50e47857b11bfd3d420f6eafb155199f4b41f6d7,Human Face Reconstruction Using a Hybrid of Photometric Stereo and Independent Component Analysis,"International Journal of Computer, Consumer and Control (IJ3C), Vol. 2, No.1 (2013) D Human Face Reconstruction Using a Hybrid of Photometric Stereo and Independent Component Analysis *Cheng-Jian Lin, 2Shyi-Shiun Kuo, 1Hsueh-Yi Lin, 2Shye-Chorng Kuo and 1Cheng-Yi Yu" 50bf792c721293222248f906e95726ac2ac2fe9e,Characterising Pedestrian Detection on a Heterogeneous Platform,"Characterising Pedestrian Detection on a Heterogeneous Platform Calum Blair1, Neil Robertson2 and Danny Hume3" 50a48fcd6176b72aea7a61233d3c7fb12a279ba4,A Computational Model of Eye Movements during Object Class Detection,"A Computational Model of Eye Movements during Object Class Detection Wei Zhang† Hyejin Yang‡∗ Dimitris Samaras† Gregory J. Zelinsky†‡ Dept. of Computer Science† Dept. of Psychology‡ State University of New York at Stony Brook Stony Brook, NY 11794" 50c1ab22f442470efbe3198f0b338fb699416bc5,A Commute in Data: The comma2k19 Dataset,"A Commute in Data: The comma2k19 Dataset Harald Sch¨afer, Eder Santana, Andrew Haden, and Riccardo Biasini omma.ai" 501eda2d04b1db717b7834800d74dacb7df58f91,Pedro Miguel Neves Marques Discriminative Sparse Representation for Expression Recognition,"Pedro Miguel Neves Marques Discriminative Sparse Representation for Expression Recognition Master Thesis in Electrical and Computer Engineering September, 2014" 5090e374a0d505040ca6fe957936a12026f5347a,Human Emotion Classification From Videos,"Human Emotion Classification From Videos Maria Soledad Elli (mselli) - Dhvani Kotak (dkotak)" 50a2ba70d42f6543b26444695459d0bac38a4ab3,Development and testing of new combined visual speech parameterization,"ISCA Archive http://www.isca-speech.org/archive Auditory-Visual Speech Processing 007 (AVSP2007) Hilvarenbeek, The Netherlands August 31 -- September 3, 2007 Development and Testing of New Combined Visual Speech Parameterization Petr Císař, Miloš Železný, Jan Zelinka, Jana Trojanová University of West Bohemia, Faculty of Applied Sciences, Department of Cybernetics Univerzitní 8, 306 14 Plzeň, Czech Republic" 5028c0decfc8dd623c50b102424b93a8e9f2e390,REVISITING CLASSIFIER TWO-SAMPLE TESTS,"Published as a conference paper at ICLR 2017 REVISITING CLASSIFIER TWO-SAMPLE TESTS David Lopez-Paz1, Maxime Oquab1,2 Facebook AI Research, 2WILLOW project team, Inria / ENS / CNRS" 50984f8345a3120d0e6c0a75adc2ac1a13e37961,Impaired face processing in autism: fact or artifact?,"DOI 10.1007/s10803-005-0050-5 Published Online: February 14, 2006 Impaired Face Processing in Autism: Fact or Artifact? Boutheina Jemel,1,3–5 Laurent Mottron,2–4 and Michelle Dawson2 Within the last 10 years, there has been an upsurge of interest in face processing abilities in utism which has generated a proliferation of new empirical demonstrations employing a variety of measuring techniques. Observably atypical social behaviors early in the develop- ment of children with autism have led to the contention that autism is a condition where the processing of social is impaired. While several empirical sources of evidence lend support to this hypothesis, others suggest that there are conditions under which autistic individuals do not differ from typically developing persons. The present paper reviews this bulk of empirical evidence, and concludes that the versatility and abilities of face processing in persons with autism have been underestimated. information, particularly faces, KEY WORDS: Autism; face processing; FFA; configural; local bias. Impaired face processing is one of the most the social cognition ommonly cited aspects of deficits observed among persons with autism spec-" 5083c6be0f8c85815ead5368882b584e4dfab4d1,Automated Face Analysis for Affective Computing,"Please do not quote. In press, Handbook of affective computing. New York, NY: Oxford Automated Face Analysis for Affective Computing Jeffrey F. Cohn & Fernando De la Torre" 506e2850a564b6085d8f0af4834a97ddd301d423,Visual object class recognition using local descriptions,"Alexandra Teynor Visual Object Class Recognition using Local Descriptions Dissertation zur Erlangung des Doktorgrades der Fakultät für Angewandte Wissenschaften der Albert-Ludwigs-Universität Freiburg im Breisgau August 2008" 5087d9bdde0ba5440eb8658be7183bf5074a2a94,Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model,"Object detection via a multi-region semantic segmentation-aware CNN model Spyros Gidaris, Nikos Komodakis To cite this version: Spyros Gidaris, Nikos Komodakis. Object detection via a multi-region semantic segmentation-aware CNN model. ICCV 2015, Dec 2015, Santiago, Chile. ICCV 2015, 2016, <10.1109/ICCV.2015.135>. HAL Id: hal-01245664 https://hal.archives-ouvertes.fr/hal-01245664 Submitted on 17 Dec 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 505942c5f9b5779bda2859e22e9ed0b1c0c7b54a,Towards 3D Face Recognition in the Real: A Registration-Free Approach Using Fine-Grained Matching of 3D Keypoint Descriptors,"Int J Comput Vis DOI 10.1007/s11263-014-0785-6 Towards 3D Face Recognition in the Real: A Registration-Free Approach Using Fine-Grained Matching of 3D Keypoint Descriptors Huibin Li · Di Huang · Jean-Marie Morvan · Yunhong Wang · Liming Chen Received: 26 April 2013 / Accepted: 27 October 2014 © Springer Science+Business Media New York 2014" 50457c55b318dde8c9024851fdf7e5ce3a936f65,Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network,"Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network Filip Piekniewski∗ Patryk Laurent Csaba Petre Micah Richert Dimitry Fisher Todd L. Hylton October 3, 2016" 50a0930cb8cc353e15a5cb4d2f41b365675b5ebf,Robust Facial Landmark Detection and Face Tracking in Thermal Infrared Images using Active Appearance Models, 50b6d2db19fb71ff5cfde8e2bfa484b10fbb39fe,Perception of Suicide Risk in Mental Health Professionals.,"RESEARCH ARTICLE Perception of Suicide Risk in Mental Health Professionals Tim M. Gale1,2*, Christopher J. Hawley3, John Butler4, Adrian Morton5, Ankush Singhal6 Department of Research, Hertfordshire Partnership University NHS Foundation Trust, Hatfield, United Kingdom, 2 Department of Psychology, University of Hertfordshire, Hatfield, United Kingdom, 3 Department of Post-graduate Medicine, University of Hertfordshire, Hatfield, United Kingdom, 4 School of Health, University of Central Lancaster, Preston, United Kingdom, 5 Reigate Psychology Service, Reigate, Surrey, United Kingdom, 6 Psychological Medicine Service, The Royal Oldham Hospital, Oldham, United Kingdom 11111" 50f0c495a214b8d57892d43110728e54e413d47d,Pairwise support vector machines and their application to large scale problems,"Submitted 8/11; Revised 3/12; Published 8/12 Pairwise Support Vector Machines and their Application to Large Scale Problems Carl Brunner Andreas Fischer Institute for Numerical Mathematics Technische Universit¨at Dresden 01062 Dresden, Germany Klaus Luig Thorsten Thies Cognitec Systems GmbH Grossenhainer Str. 101 01127 Dresden, Germany Editor: Corinna Cortes" 501096cca4d0b3d1ef407844642e39cd2ff86b37,Illumination Invariant Face Image Representation Using Quaternions,"Illumination Invariant Face Image Representation using Quaternions Dayron Rizo-Rodr´ıguez, Heydi M´endez-V´azquez, and Edel Garc´ıa-Reyes Advanced Technologies Application Center. 7a # 21812 b/ 218 and 222, Rpto. Siboney, Playa, P.C. 12200, La Habana, Cuba." 506f744801c97f005fa04a09e4a4ae5fdabe94d7,MARCOnI—ConvNet-Based MARker-Less Motion Capture in Outdoor and Indoor Scenes,"Local Submodularization for Binary Pairwise Energies Lena Gorelick, Yuri Boykov, Olga Veksler, Ismail Ben Ayed, and Andrew Delong" 50d15cb17144344bb1879c0a5de7207471b9ff74,"Divide , Share , and Conquer : Multitask Attribute Learning with Selective Sharing","Divide, Share, and Conquer: Multi-task Attribute Learning with Selective Sharing Chao-Yeh Chen*, Dinesh Jayaraman*, Fei Sha, and Kristen Grauman" 503c16d9cb1560f13a7d6baedf8c9f889b22459d,Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation,"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam {lcchen, yukun, gpapan, fschroff, Google Inc." 50ccc98d9ce06160cdf92aaf470b8f4edbd8b899,Towards robust cascaded regression for face alignment in the wild,"Towards Robust Cascaded Regression for Face Alignment in the Wild Chengchao Qu1,2 Hua Gao3 Eduardo Monari2 J¨urgen Beyerer2,1 Jean-Philippe Thiran3 Vision and Fusion Laboratory (IES), Karlsruhe Institute of Technology (KIT) Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (Fraunhofer IOSB) Signal Processing Laboratory (LTS5), ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL)" 50814328c14b107c62c3e49bc7347059a9f590ac,Evaluating aerial vessel detector in multiple maritime surveillance scenarios,"Evaluating Aerial Vessel Detector In Multiple Maritime Surveillance Scenarios Gonc¸alo Cruz Alexandre Bernardino Portuguese Air Force, 715-021 Sintra, Portugal Institute for Systems and Robotics, Department of Electrical and Computer Engineering, Instituto Superior Tcnico, 049-001 Lisboa, Portugal" 50dff7d619de13076f04382690f2ef83cbb43155,Improving Face Recognition with Multispectral Fusion and Support Vector Machines,"Improving Face Recognition with Multispectral Fusion and Support Vector Machines Giovani Chiachia, Aparecido Nilceu Marana High Performance Computing Laboratory UNESP - S˜ao Paulo State University Bauru, Brazil Christian K¨ublbeck Department of Electronic Imaging Fraunhofer Institute for Integrated Circuits Erlangen, Germany" 50fb5e2f0c2fe8679c218ff88d4906e5a0812d34,"Sketch-editing games: human-machine communication, game theory and applications","Sketch-Editing Games: Human-Machine Communication, Game Theory and Applications Andre Ribeiro Takeo Igarashi JST, Erato, Igarashi Design Interface Project, -28-1-7F, Koishikawa JST, Erato, Igarashi Design Interface Project, -28-1-7F, Koishikawa sketches). We argue" 50d9891114d281e498c4793962977d1ad3d2606f,Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks,"Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks Long Chen1 Hanwang Zhang2 Jun Xiao1∗ Wei Liu3 Shih-Fu Chang4 Zhejiang University 2Nanyang Technological University 3Tencent AI Lab 4Columbia University {longc, {wliu, Figure 1: (a) Attribute variance heat maps of the 312 attributes in CUB birds [60] and the 102 attributes in SUN scenes [47] (lighter color indicates lower variance, i.e., lower discriminability) and the t-SNE [35] visualizations of the test images represented by all attributes (left) and only the high-variance ones (right). Some of the low-variance attributes (the lighter part to the left of the cut-off line) discarded at training are still needed in discriminating unseen test classes. (b) Comparison of reconstructed images using SAE [25] and our proposed SP-AEN method, which is shown to retain sufficient semantics for photo-realistic reconstruction." 50eb2ee977f0f53ab4b39edc4be6b760a2b05f96,Emotion recognition based on texture analysis of facial expression,"Australian Journal of Basic and Applied Sciences, 11(5) April 2017, Pages: 1-11 AUSTRALIAN JOURNAL OF BASIC AND APPLIED SCIENCES ISSN:1991-8178 EISSN: 2309-8414 Journal home page: www.ajbasweb.com Emotion Recognition Based on Texture Analysis of Facial Expressions Using Wavelets Transform Suhaila N. Mohammed and 2Loay E. George Assistant Lecturer, Computer Science Department, College of Science, Baghdad University, Baghdad, Iraq, Assistant Professor, Computer Science Department, College of Science, Baghdad University, Baghdad, Iraq, Address For Correspondence: Suhaila N. Mohammed, Baghdad University, Computer Science Department, College of Science, Baghdad, Iraq. A R T I C L E I N F O Article history: Received 18 January 2017 Accepted 28 March 2017 Available online 15 April 2017 Keywords: Facial Emotion, Face Detection, Template Based Methods, Texture" 50ad84bdc3c7cd262ed22f360a37fef457550e25,NoScope: Optimizing Neural Network Queries over Video at Scale,"NoScope: Optimizing Neural Network Queries over Video at Scale Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, Matei Zaharia Stanford InfoLab" 509abc3031dbf347c29e2a42d88650e0b8545f3d,OBJECT DETECTION WITH LARGE INTRA-CLASS VARIATION,"OBJECT DETECTION WITH LARGE INTRA-CLASS VARIATION A Thesis presented to the Faculty of the Graduate School t the University of Missouri In Partial Fulfillmen of the Requirements for the Degree Master of Science GUANG CHEN Dr. Tony X Han DECEMBER 2011" 5020a75c45416073d0b07b1deb7382bc80de1779,Human Detection Using Learned Part Alphabet and Pose Dictionary,"Human Detection using Learned Part Alphabet nd Pose Dictionary Anonymous ECCV submission Paper ID 895" 508eb5a6156b8fa1b4547b611e85969438116fa2,Perceptual Generative Adversarial Networks for Small Object Detection,"Perceptual Generative Adversarial Networks for Small Object Detection Jianan Li Xiaodan Liang Yunchao Wei Tingfa Xu Jiashi Feng Shuicheng Yan" 507c9672e3673ed419075848b4b85899623ea4b0,Multi-View Facial Expression Classification,"Faculty of Informatics Institute for Anthropomatics Chair Prof. Dr.-Ing. R. Stiefelhagen Facial Image Processing and Analysis Group Multi-View Facial Expression Classification DIPLOMA THESIS OF Nikolas Hesse ADVISORS Dr.-Ing. Hazım Kemal Ekenel Dipl.-Inform. Hua Gao Dipl.-Inform. Tobias Gehrig MARCH 2011 KIT – University of the State of Baden-Württemberg and National Laboratory of the Helmholtz Association www.kit.edu" 5056186a5001921d0a24587e26167a7ee9d88cf9,Optimizing the Capacity of a Convolutional Neural Network for Image Segmentation and Pattern Recognition,"World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:12, No:10, 2018 Optimizing the Capacity of a Convolutional Neural Network for Image Segmentation and Pattern Recognition Yalong Jiang, Zheru Chi" 50bc8a4e7e6ab9837c6244b29ff800f523494d65,Learning to Answer Questions From Image using Convolutional Neural Network,"Learning to Answer Questions From Image Using Convolutional Neural Network Noah’s Ark Lab, Huawei Technologies Lin Ma Zhengdong Lu Hang Li" 5080655990fe0e0446bcb038b3e0adad0218bd29,Quantum Cuts A Quantum Mechanical Spectral Graph Partitioning Method for Salient Object Detection Julkaisu,"Çağlar Aytekin Quantum Cuts A Quantum Mechanical Spectral Graph Partitioning Method for Salient Object Detection Julkaisu 1440 • Publication 1440 Tampere 2016" 5058a7ec68c32984c33f357ebaee96c59e269425,A Comparative Evaluation of Regression Learning Algorithms for Facial Age Estimation,"A Comparative Evaluation of Regression Learning Algorithms for Facial Age Estimation Carles Fern´andez1, Ivan Huerta2, and Andrea Prati2 Herta Security Pau Claris 165 4-B, 08037 Barcelona, Spain DPDCE, University IUAV Santa Croce 1957, 30135 Venice, Italy" 50014f4f5b0bd604d65db278b22d1478beade5dc,Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection, 50da9965104d944a8ae648c9aaec43be8ea1c501,Improving the Correspondence Establishment Based on Interactive Homography Estimation,"Improving the Correspondence Establishment Based on Interactive Homography Estimation* Xavier Cortés, Carlos Moreno, and Francesc Serratosa Universitat Rovira i Virgili, Departament d’Enginyeria Informàtica i Matemàtiques, Spain" 50c5a552c191bff34ca74e0f8dbac159e3814533,"Overview of the ImageCLEF 2015 Scalable Image Annotation, Localization and Sentence Generation task","Overview of the ImageCLEF 2015 Scalable Image Annotation, Localization and Sentence Generation task Andrew Gilbert, Luca Piras, Josiah Wang, Fei Yan, Emmanuel Dellandrea, Robert Gaizauskas, Mauricio Villegas and Krystian Mikolajczyk" 1ca9ab2c1b5e8521cba20f78dcf1895b3e1c36ac,"""Here's looking at you, kid"". Detecting people looking at each other in videos","""Here's looking at you, kid"" Citation for published version: Marin-Jimenez, M, Zisserman, A & Ferrari, V 2011, ""Here's looking at you, kid"": Detecting people looking at each other in videos. in Proceedings of the British Machine Vision Conference (BMVC): Dundee, September 011. BMVA Press, pp. 22.1-22.12. DOI: 10.5244/C.25.22 Digital Object Identifier (DOI): 0.5244/C.25.22 Link: Link to publication record in Edinburgh Research Explorer Document Version: Peer reviewed version Published In: Proceedings of the British Machine Vision Conference (BMVC) General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) nd / or other copyright owners and it is a condition of accessing these publications that users recognise and bide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer ontent complies with UK legislation. If you believe that the public display of this file breaches copyright please" 1cbc189a4484cd2b1371798bae2ff50c0442ce60,A Hybrid Loss for Multiclass and Structured Prediction,"IEEE TRANSACTIONS ON PATTERN ANALYSIS & MACHINE INTELLIGENCE, FINAL DRAFT, FEB. 2014 A Hybrid Loss for Multiclass nd Structured Prediction Qinfeng Shi, Mark Reid, Tiberio Caetano, Anton van den Hengel and Zhenhua Wang" 1cd66a9d9158f65f9e099141189d9a00fb82b525,Quick and energy-efficient Bayesian computing of binocular disparity using stochastic digital signals,"Quick and energy-ef‌f‌icient Bayesian computing of inocular disparity using stochastic digital signals Alexandre Coninxa,∗, Pierre Bessi`erea, Jacques Drouleza ISIR CNRS/UPMC, 4 place Jussieu 75005 Paris, France" 1c1a24169be56e01b0e36e260f49025260a5c7e7,A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment,"A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment Haonan Yu, Haichao Zhang, and Wei Xu Baidu Research - Institue of Deep Learning Sunnyvale, CA 94089" 1cb95f013ec3e78acdda6ac6cfdb362ae6a5ceac,Nonnegative matrix factorization for segmentation analysis,"Nonnegative matrix factorization for segmentation analysis Roman Sandler Technion - Computer Science Department - Ph.D. Thesis PHD-2010-09 - 2010" 1c93b48abdd3ef1021599095a1a5ab5e0e020dd5,A Compositional and Dynamic Model for Face Aging,"JOURNAL OF LATEX CLASS FILES, VOL. *, NO. *, JANUARY 2009 A Compositional and Dynamic Model for Face Aging Jinli Suo , Song-Chun Zhu , Shiguang Shan and Xilin Chen" 1cf6bc0866226c1f8e282463adc8b75d92fba9bb,"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering Huijuan Xu UMass Lowell Kate Saenko UMass Lowell" 1ce3a91214c94ed05f15343490981ec7cc810016,Exploring photobios,"Exploring Photobios Ira Kemelmacher-Shlizerman1 Eli Shechtman2 Rahul Garg1,3 Steven M. Seitz1,3 University of Washington∗ Adobe Systems† Google Inc." 1c400dcd6c3e54498d9a7bd5aa4c456079a9d236,Sketch and Validate for Big Data Clustering,"Sketch and Validate for Big Data Clustering Panagiotis A. Traganitis, Konstantinos Slavakis, Senior Member, IEEE, and Georgios B. Giannakis, Fellow, IEEE" 1cd0bc067e66bc1f66a73b401a4a470e43e4bb9e,Houdini : Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples,"Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples Moustapha Cisse Facebook AI Research Natalia Neverova* Facebook AI Research" 1cd584f519d9cd730aeef1b1d87f7e2e82b4de59,A fully automatic face recognition system using a combined audio-visual approach ∗,"A fully automatic face recognition system using a combined udio-visual approach ∗ Alberto Albiol†, Luis Torres†, and Edward J. Delp? † Communications Department Technical University of Valencia, Valencia, Spain Department of Signal Theory & Communications Technical University of Catalonia, Barcelona, Spain ?School of Electrical and Computer Engineering Purdue University West Lafayette, IN 47907-1285 Corresponding Author: Dr. Alberto Albiol Communications Department Technical University of Valencia, Valencia, Spain 6022 Valencia (Spain) Telephone: +34 96 387 97 38 Fax: +34 96 387 73 09 Email:" 1c0eaf4c568664007b092225095c9c5e008c20fe,FEATURE EXTRACTION METHODS 3 . 1 Discrete Wavelet Transform ( DWT ),"International Journal of Scientific & Engineering Research Volume 3, Issue 8, August-2012 1 ISSN 2229-5518 Particle Swarm Optimization- Best Feature Selection method for Face Images Ms. P.V. Shinde M.E. 2nd Year Dept. Of Computer Engg. AVCOE Sangamner Prof. B.L. Gunjal Assistant Professor Dept. Of Computer Engg. AVCOE Sangamner" 1c80bc91c74d4984e6422e7b0856cf3cf28df1fb,Hierarchical Adaptive Structural SVM for Domain Adaptation,"Noname manuscript No. (will be inserted by the editor) Hierarchical Adaptive Structural SVM for Domain Adaptation Jiaolong Xu · Sebastian Ramos · David V´azquez · Antonio M. L´opez Received: date / Accepted: date" 1c3073b57000f9b6dbf1c5681c52d17c55d60fd7,Direction de thèse:,"THÈSEprésentéepourl’obtentiondutitredeDOCTEURDEL’ÉCOLENATIONALEDESPONTSETCHAUSSÉESSpécialité:InformatiqueparCharlotteGHYSAnalyse,Reconstruction3D,&AnimationduVisageAnalysis,3DReconstruction,&AnimationofFacesSoutenancele19mai2010devantlejurycomposéde:Rapporteurs:MajaPANTICDimitrisSAMARASExaminateurs:MichelBARLAUDRenaudKERIVENDirectiondethèse:NikosPARAGIOSBénédicteBASCLE" 1ca155a4b65ae19ccb73df48516e4775770a382c,Action Representations in Robotics: A Taxonomy and Systematic Classification,"Action representations in robotics: A taxonomy and systematic classification Journal Title XX(X):1–32 (cid:13)The Author(s) 2016 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/ToBeAssigned www.sagepub.com/ Philipp Zech, Erwan Renaudo, Simon Haller, Xiang Zhang and Justus Piater" 1c9333bcf523388d75f852e0689b0e7f5a04faa4,Person Part Segmentation based on Weak Supervision,"JIANG, CHI: PERSON PART SEGMENTATION BASED ON WEAK SUPERVISION 1 Person Part Segmentation based on Weak Supervision Yalong Jiang1 1Department of Electronic and Information Engineering Zheru Chi1 The Hong Kong Polytechnic University, HK" 1c40cb899fccbe98a2bb63088e02d6c59e87c187,An Interaction Framework for a Cooperation between Fully Automated Vehicles and External Users in Semi-stationary Urban Scenarios, 1c521ac6e68436f6c6aad3c0eb7ffa557fe25b0d,Modeling Image Patches with a Generic Dictionary of Mini-epitomes,"Modeling Image Patches with a Generic Dictionary of Mini-Epitomes George Papandreou TTI Chicago Liang-Chieh Chen UC Los Angeles Alan L. Yuille UC Los Angeles" 1cf29a0131211079fc73908ecf211ee78f090ad9,Regionlets for Generic Object Detection,"Regionlets for Generic Object Detection Xiaoyu Wang Ming Yang Shenghuo Zhu Yuanqing Lin NEC Laboratories America, Inc." 1cee733ee31e245dac4655a870fd9226163a52b5,Bidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning,"Bidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning Qing Sun Virginia Tech Stefan Lee Virginia Tech Dhruv Batra Georgia Tech" 1c012e5b3ddb8a60420e8f92162d32ad135f9ba1,Self-ensembling for visual domain adaptation,"Self-ensembling for visual domain adaptation French, G. Mackiewicz, M. Fisher, M. September 25, 2018" 1c90ad1e264c29a8d180de47373257a5f1b5aa57,Generalizing Image Captions for Image-Text Parallel Corpus,"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 790–796, Sofia, Bulgaria, August 4-9 2013. c(cid:13)2013 Association for Computational Linguistics house being pulled by a boat.” “I saw her in the light of her reading lamp and sneaked back to her door with the camera.” “Sections of the bridge sitting in the Dyer Construction yard south of Cabelas Driver.” Circumstantial information that is not visually present Visually relevant, but with overly extraneous details Visually truthful, but for an uncommon situation Figure1:Examplesofcaptionsthatarenotreadilyapplicabletoothervisuallysimilarimages.textfromtheretrievedsamplestothequeryim-age(e.g.Farhadietal.(2010),Ordonezetal.(2011),Kuznetsovaetal.(2012)).Otherwork(e.g.FengandLapata(2010a),FengandLapata(2010b))usescomputervisiontobiassummariza-tionoftextassociatedwithimagestoproducede-scriptions.Alloftheseapproachesrelyonex-istingtextthatdescribesvisualcontent,butmanytimesexistingimagedescriptionscontainsignifi-cantamountsofextraneous,non-visual,orother-wisenon-desirablecontent.Thegoalofthispaperistodeveloptechniquestoautomaticallycleanupvisuallydescriptivetexttomakeitmoredirectlyusableforapplicationsexploitingtheconnectionbetweenimagesandlanguage.Asaconcreteexample,considerthefirstimageinFigure1.Thiscaptionwaswrittenbythephotoownerandthereforecontainsinformationrelatedtothecontextofwhenandwherethephotowastaken.Objectssuchas“lamp”,“door”,“camera”arenotvisuallypresentinthephoto.Thesecondimageshowsasimilarbutsomewhatdifferentis-sue.Itscaptiondescribesvisibleobjectssuchas“bridge”and“yard”,but“CabelasDriver”areoverlyspecificandnotvisuallydetectable.The" 1cfe3533759bf95be1fce8ce1d1aa2aeb5bfb4cc,Recognition of Facial Gestures Based on Support Vector Machines,"Recognition of Facial Gestures based on Support Vector Machines Attila Fazekas and Istv(cid:19)an S(cid:19)anta Faculty of Informatics, University of Debrecen, Hungary H-4010 Debrecen P.O.Box 12." 1c0e8c3fb143eb5eb5af3026eae7257255fcf814,Weakly Supervised Deep Detection Networks,"GOALS Goal: Learn object detectors using only image-level labels Why weakly supervised learning? • annotations are costly • CNN training is data-hungry Hypothesis: Pre-trained CNNs should contain meaningful representations of data such as objects and object parts. Thus we can exploit this implicit knowledge to learn localizing objects. Classification stream 𝑹𝟏 𝑹𝟐 𝑹𝟑 𝑹𝟒 0.52 0.47 0.04 0.93 horse person 0.48 0.53 0.96 0.07 Normalize over classes Detection stream 𝑹𝟏 𝑹𝟐 𝑹𝟑 𝑹𝟒 horse 0.04 0.01 0.07 0.88 person 0.02 0.03 0.91 0.04" 1cc0183d8fbef098d29b6b5f621745ff099f6c6c,Joint Discovery of Object States and Manipulation Actions,"Joint Discovery of Object States and Manipulation Actions Jean-Baptiste Alayrac∗ † Josef Sivic∗ † ‡ Ivan Laptev∗ † Simon Lacoste-Julien§" 1c60a13e3d48c5425b08a775d40e0d92c9c581f8,Robust moving objects detection in lidar data exploiting visual cues,"Robust Moving Objects Detection in Lidar Data Exploiting Visual Cues Gheorghii Postica1 Andrea Romanoni1 Matteo Matteucci1" 1c6e22516ceb5c97c3caf07a9bd5df357988ceda,Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data,"NetworkCNNimageslabelsFakeDatasetimages24132labelsTarget NetworkCNNimageslabelsOriginalDatasetFakeDatasetFig.1:Ontheleft,thetargetnetworkistrainedwithanoriginal(confidential)datasetandisservedpubliclyasanAPI,receivingimagesasinputandprovidingclasslabelsasoutput.Ontheright,itispresentedtheprocesstogetstolenlabelsandtocreateafakedataset:randomnaturalimagesaresenttotheAPIandthelabelsareobtained.Afterthat,thecopycatnetworkistrainedusingthisfakedataset.cloud-basedservicestocustomersallowingthemtooffertheirownmodelsasanAPI.Becauseoftheresourcesandmoneyinvestedincreatingthesemodels,itisinthebestinterestofthesecompaniestoprotectthem,i.e.,toavoidthatsomeoneelsecopythem.Someworkshavealreadyinvestigatedthepossibilityofcopyingmodelsbyqueryingthemasablack-box.In[1],forexample,theauthorsshowedhowtoperformmodelextractionattackstocopyanequivalentornear-equivalentmachinelearningmodel(decisiontree,logisticregression,SVM,andmultilayerperceptron),i.e.,onethatachievescloseto100%agreementonaninputspaceofinterest.In[2],theauthorsevaluatedtheprocessofcopyingaNaiveBayesandSVMclassifierinthecontextoftextclassification.Bothworksfocusedongeneralclassifiersandnotondeepneuralnetworksthatrequirelargeamountsofdatatobetrainedleavingthequestionofwhetherdeepmodelscanbeeasilycopied.Althoughthesecondusesdeeplearningtostealtheclassifiers,itdoesnottrytouseDNNstostealfromdeepmodels.Additionally,theseworksfocusoncopyingbyqueryingwithproblemdomaindata.Inrecentyears,researchershavebeenexploringsomeintriguingpropertiesofdeepneuralnetworks[3],[4].More©2018IEEE.Personaluseofthismaterialispermitted.PermissionfromIEEEmustbeobtainedforallotheruses,inanycurrentorfuturemedia,includingreprinting/republishingthismaterialforadvertisingorpromotionalpurposes,creatingnewcollectiveworks,forresaleorredistributiontoserversorlists,orreuseofanycopyrightedcomponentofthisworkinotherworks." 1c0319d67707dd7dde76e47668e852e74692df30,Human Re-identification Through a Video Camera Network. (Ré-identification de personne dans un réseau de cameras vidéo),"Human Re-identification Through a Video Camera Network Slawomir Bak To cite this version: Slawomir Bak. Human Re-identification Through a Video Camera Network. Computer Vision and Pattern Recognition [cs.CV]. Université Nice Sophia Antipolis, 2012. English. HAL Id: tel-00763443 https://tel.archives-ouvertes.fr/tel-00763443 Submitted on 10 Dec 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 1c26e415c7eae2f3b0f49e0519f0d985ec661c63,Intersection of Longest Paths in Graph Theory and Predicting Performance in Facial Recognition,"Georgia State University ScholarWorks Georgia State University Mathematics Dissertations Department of Mathematics and Statistics -6-2017 Intersection of Longest Paths in Graph Theory and Predicting Performance in Facial Recognition Amy Yates Follow this and additional works at: http://scholarworks.gsu.edu/math_diss Recommended Citation Yates, Amy, ""Intersection of Longest Paths in Graph Theory and Predicting Performance in Facial Recognition."" Dissertation, Georgia State University, 2017. http://scholarworks.gsu.edu/math_diss/34 This Dissertation is brought to you for free and open access by the Department of Mathematics and Statistics at ScholarWorks Georgia State University. It has been accepted for inclusion in Mathematics Dissertations by an authorized administrator of ScholarWorks Georgia State University. For more information, please contact" 1c1e4415f0acf5d536c9579117d326471f0b678b,Temporal Model Adaptation for Person Re-Identification,"Temporal Model Adaptation for Person Re-Identification Niki Martinel1,3, Abir Das2, Christian Micheloni1, and Amit K. Roy-Chowdhury3 University of Udine, 33100 Udine, Italy University of Massatchussets Lowell, 01852 Lowell, MA, USA University of California Riverside, 92507 Riverside, CA, USA" 1cd9dba357e05c9be0407dc5d477fd528cfeb79b,Model-driven Simulations for Deep Convolutional Neural Networks,"Model-driven Simulations for Deep Convolutional Neural Networks V S R Veeravasarapu1, Constantin Rothkopf2, Visvanathan Ramesh1 Center for Cognition and Computing, Goethe University, Frankfurt. Cognitive Science Center, Technical University, Darmstadt." 1cbf3b90065e8a410668ed914e9d03a94a4d94aa,Visual-Inertial Semantic Scene Representation,"Visual-Inertial Semantic Scene Representation UCLA TR CSD160005 Stefano Soatto May 20, 2016" 1c51aeece7a3c30302ebd83bdcaa65df0bfc48fe,Unsupervised Video Indexing based on Audiovisual Characterization of Persons. (Indexation vidéo non-supervisée basée sur la caractérisation des personnes),"Unsupervised Video Indexing based on Audiovisual Characterization of Persons Elie El Khoury To cite this version: Elie El Khoury. Unsupervised Video Indexing based on Audiovisual Characterization of Per- sons. Human-Computer Interaction [cs.HC]. Universit´e Paul Sabatier - Toulouse III, 2010. English. HAL Id: tel-00515424 https://tel.archives-ouvertes.fr/tel-00515424v3 Submitted on 7 Sep 2010 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 45954ed44b99edc5f0d1100a1ea33d856602d78a,Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach,"Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach Avisek Lahiri*, Vineet Jain*, Arnab Mondal*, and Prabir Kumar Biswas, Senior Member, IEEE" 4583d7d1d76dfe18e86e91f7438ce1a03cdcf68f,3D Face: biometric template protection for 3d face recognition,"\3D Face"": Biometric Template Protection for D Face Recognition E.J.C. Kelkboom, B. G(cid:127)okberk, T.A.M. Kevenaar, A.H.M. Akkermans, and M. van der Veen Philips Research, High-Tech Campus 34, 5656AE, Eindhoven femile.kelkboom, berk.gokberk, tom.kevenaar, ton.h.akkermans," 45379046c6c1311dfa6d8e1941b3e2c7971ca2bc,An alternating direction and projection algorithm for structure-enforced matrix factorization,"Noname manuscript No. (will be inserted by the editor) An Alternating Direction and Projection Algorithm for Structure-enforced Matrix Factorization Lijun Xu · Bo Yu · Yin Zhang Received: date / Accepted: date" 4599b9d9a379385a3d31681696d2523beeb0e9c1,LG ] 8 F eb 2 01 6 A Latent-Variable Grid Model,"A Latent-Variable Grid Model Rajasekaran Masatran Computer Science and Engineering, Indian Institute of Technology Madras FREESHELL · ORG" 451bf4124ec8a55b9112cf9cc167d304fa004924,Modelling State of Interaction from Head Poses for Social Human-Robot Interaction,"Modelling State of Interaction from Head Poses for Social Human-Robot Interaction Andre Gaschler fortiss GmbH Guerickstr. 25 80805 München, Germany Ingmar Kessler fortiss GmbH Guerickstr. 25 80805 München, Germany Kerstin Huth Universität Bielefeld Universitätsstr. 25 3615 Bielefeld, Germany Jan de Ruiter Universität Bielefeld Universitätsstr. 25 3615 Bielefeld, Germany ielefeld.de Manuel Giuliani" 458e44d20f7a85a0ce378b48a41febb16383c075,Tracking Interacting Objects in Image Sequences,"Tracking Interacting Objects in Image Sequences THÈSE NO 6632 (2015) PRÉSENTÉE LE 3 JUILLET 2015 À LA FACULTÉ INFORMATIQUE ET COMMUNICATIONS LABORATOIRE DE VISION PAR ORDINATEUR PROGRAMME DOCTORAL EN INFORMATIQUE ET COMMUNICATIONS ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES Xinchao WANG cceptée sur proposition du jury: Prof. W. Gerstner, président du jury Prof. P. Fua, directeur de thèse Prof. J. Sullivan, rapporteuse Prof. P. Dillenbourg, rapporteur Prof. S. Roth, rapporteur Suisse" 450e9f80a273df2cdaafd9ae3a9ff149950cc834,Human Pose Estimation using Histograms of Edge Directions,"Human Pose Estimation using Histograms of Edge Directions Andrès Koetsier University of Twente HMI Department" 4541f3ee510b593243ff9a66d3586ef9125c2931,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 4560491820e0ee49736aea9b81d57c3939a69e12,Investigating the Impact of Data Volume and Domain Similarity on Transfer Learning Applications,"Investigating the Impact of Data Volume and Domain Similarity on Transfer Learning Applications Michael Bernico, Yuntao Li, and Dingchao Zhang State Farm Insurance, Bloomington IL 61710, USA," 4526992d4de4da2c5fae7a5ceaad6b65441adf9d,System for Medical Mask Detection in the Operating Room Through Facial Attributes,"System for Medical Mask Detection in the Operating Room Through Facial Attributes A. Nieto-Rodr´ıguez, M. Mucientes(B), and V.M. Brea Center for Research in Information Technologies (CiTIUS), University of Santiago de Compostela, Santiago de Compostela, Spain" 451ed51346fe2e6c5de2dbf29733711b31f5fd68,Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos,"Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos Armine Vardazaryan1, Didier Mutter2, Jacques Marescaux2, and Nicolas Padoy1 ICube, University of Strasbourg, CNRS, IHU Strasbourg, France University Hospital of Strasbourg, IRCAD, IHU Strasbourg, France" 453e311c6de1285cd5ea6d93fd78a636eac0ba82,Multi patches 3D facial representation for person authentication using AdaBoost,"Multi patches 3D facial representation for Person Authentication using AdaBoost Lahoucine Ballihi, Boulbaba Ben Amor, Mohamed Daoudi, Anuj Srivastava To cite this version: Lahoucine Ballihi, Boulbaba Ben Amor, Mohamed Daoudi, Anuj Srivastava. Multi patches 3D facial representation for Person Authentication using AdaBoost. I/V Communications and Mobile Network (ISVC), 2010 5th International Symposium on, Sep 2010, Rabat, Morocco. pp.1-4, 2010. HAL Id: hal-00665904 https://hal.archives-ouvertes.fr/hal-00665904 Submitted on 3 Feb 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 4534d78f8beb8aad409f7bfcd857ec7f19247715,Transformation-Based Models of Video Sequences,"Under review as a conference paper at ICLR 2017 TRANSFORMATION-BASED MODELS OF VIDEO SEQUENCES Joost van Amersfoort ∗, Anitha Kannan, Marc’Aurelio Ranzato, Arthur Szlam, Du Tran & Soumith Chintala Facebook AI Research {akannan, ranzato, aszlam, trandu," 45aefa11101129862e323958b62505700bc281ae,Unsupervised Learning in Generative Models of Occlusion,"Unsupervised Learning in Generative Models of Occlusion Dissertation zur Erlangung des Doktorgrades der Naturwissenschaften vorgelegt beim Fachbereich Physik der Johann Wolfgang Goethe-Universität in Frankfurt am Main Marc Henniges us Frankfurt am Main Frankfurt (2012) (D 30)" 456983805a8781d6429bed1ed66dc9f3902767af,Seeing with Humans : Gaze-Assisted Neural Image,"Seeing with Humans: Gaze-Assisted Neural Image Captioning Yusuke Sugano and Andreas Bulling" 451d777ee33833a3b5eb6ba5292fae162c6d265f,Exploiting Feature Correlations by Brownian Statistics for People Detection and Recognition,"TRANSACTIONS ON CYBERNETICS Exploiting Feature Correlations by Brownian Statistics for People Detection and Recognition Sławomir B ˛ak1, Marco San Biagio2, Ratnesh Kumar1, Vittorio Murino2 and François Brémond1 STARS Lab, INRIA Sophia Antipolis Méditerranée, Sophia Antipolis, 06902 Valbonne, France Pattern Analysis and Computer Vision (PAVIS), IIT IStituto Italiano di Tecnologia, 16163 Genova, Italy Characterizing an image region by its feature inter-correlations is a modern trend in computer vision. In this paper, we introduce new image descriptor that can be seen as a natural extension of a covariance descriptor with the advantage of capturing nonlinear nd non-monotone dependencies. Inspired from the recent advances in mathematical statistics of Brownian motion, we can express highly complex structural information in a compact and computationally efficient manner. We show that our Brownian covariance descriptor can capture richer image characteristics than the covariance descriptor. Additionally, a detailed analysis of the Brownian manifold reveals that in opposite to the classical covariance descriptor, the proposed descriptor lies in a relatively flat manifold, which can be treated as a Euclidean. This brings significant boost in the efficiency of the descriptor. The effectiveness and the generality of our approach is validated on two challenging vision tasks, pedestrian classification and person re-identification. The experiments are carried out on multiple datasets achieving promising results. Index Terms—brownian descriptor, covariance descriptor, pedestrian detection, re-identification. I. INTRODUCTION D ESIGNING proper image descriptors is a crucial step in computer vision applications, including scene detec- tion, target tracking and object recognition. A good descrip-" 45013959589013b946d98b787cfaef404f52a5b3,Linear measurements of facial morphology using automatic aproach,"ORIGINAL ARTICLE ORIGINALNI RAD Serbian Dental Journal, vol. 63, No 2, 2016 DOI: 10.1515/sdj-2016-0007 UDC: 572.544.087:004 Linear measurements of facial morphology using utomatic aproach Marijana Arapović-Savić1, Mirjana Umićević-Davidović1, Adriana Arbutina1, Mihajlo Savić2 Department of Orthodontics, Study Program Dentistry, Faculty of Medicine, University of Banja Luka, Banja Luka, Bosnia and Herzegovina; Faculty of Electrical Engineering, University of Banja Luka, Banja Luka, Bosnia and Herzegovina SUMMARY Introduction Clinical extraoral examination prior to orthodontic treatment includes face analysis (front and profile). Development of computer technology has increased efficacy and simplified this process through automating several steps of the analysis. The aim of this paper was to examine the possibility of automatic determining of linear measure- ments based on the facial image of a patient. Material and Methods Based on the set of 20 patients in NHP (Natural Head Position) position, three sets of measure- ments were conducted. Trained orthodontist performed positioning of predefined points on the image of the patient two times with one week apart, after which the points were automatically determined using customized computer software. Based on the position of the points, measurements for bizygomatic distance, upper and lower facial height" 457d3ca924afc21719d19175caf285aa575d1c90,Analyzing Structured Scenarios by Tracking People and Their Limbs, 45e7ddd5248977ba8ec61be111db912a4387d62f,Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization,"CHEN ET AL.: ADVERSARIAL POSENET Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization Yu Chen1, Chunhua Shen2, Hao Chen2, Xiu-Shen Wei3, Lingqiao Liu2 and Jian Yang1" 456f00e213e03058a056069fa75c34929cf7d4e9,Detecting ground control points via convolutional neural network for stereo matching,"Noname manuscript No. (will be inserted by the editor) Detecting Ground Control Points via Convolutional Neural Network for Stereo Matching Zhun Zhong · Songzhi Su · Donglin Cao · Shaozi Li Received: date / Accepted: date" 45c824c25e66b7bc1dd474f80cf2b0056b4fa6f8,"Selection of Location, Frequency, and Orientation Parameters of 2D Gabor Wavelets for Face Recognition","Selection of Location, Frequency and Orientation Parameters of 2D Gabor Wavelets for Face Recognition Berk G¨okberk, M.O. ˙Irfano˘glu, Lale Akarun, and Ethem Alpaydın Bo˘gazi¸ci University, Department of Computer Engineering, {gokberk, irfanoglu, akarun, TR-34342, Istanbul, Turkey" 45ca696076e9c073e6cf699766f808899589bc88,Aalborg Universitet Thermal Tracking of Sports Players,"Aalborg Universitet Thermal Tracking of Sports Players Gade, Rikke; Moeslund, Thomas B. Published in: Sensors DOI (link to publication from Publisher): 0.3390/s140813679 Publication date: Document Version Publisher's PDF, also known as Version of record Link to publication from Aalborg University Citation for published version (APA): Gade, R., & Moeslund, T. B. (2014). Thermal Tracking of Sports Players. Sensors, 14(8), 13679-13691. DOI: 0.3390/s140813679 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain ? You may freely distribute the URL identifying the publication in the public portal ?" 45dffa3cd37371c5eed78b6f170c7ab3b5cc491f,Face Recognition Using a Unified 3D Morphable Model,"Face Recognition Using a Unified 3D Morphable Model Hu, G., Yan, F., Chan, C-H., Deng, W., Christmas, W., Kittler, J., & Robertson, N. M. (2016). Face Recognition Using a Unified 3D Morphable Model. In Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII (pp. 73-89). (Lecture Notes in Computer Science; Vol. 9912). Springer Verlag. DOI: 10.1007/978-3-319-46484-8_5 Published in: Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 016, Proceedings, Part VIII Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-46484-8_5 General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to" 45a6333fc701d14aab19f9e2efd59fe7b0e89fec,Dataset Creation for Gesture Recognition,"HAND POSTURE DATASET CREATION FOR GESTURE RECOGNITION Luis Anton-Canalis Instituto de Sistemas Inteligentes y Aplicaciones Numericas en Ingenieria Campus Universitario de Tafira, 35017 Gran Canaria, Spain Elena Sanchez-Nielsen Departamento de E.I.O. y Computacion 8271 Universidad de La Laguna, Spain Keywords: Image understanding, Gesture recognition, Hand dataset." 4568063b7efb66801e67856b3f572069e774ad33,Correspondence driven adaptation for human profile recognition,"Correspondence Driven Adaptation for Human Profile Recognition Ming Yang1, Shenghuo Zhu1, Fengjun Lv2, Kai Yu1 NEC Laboratories America, Inc. Huawei Technologies (USA) Cupertino, CA 95014 Santa Clara, CA 95050" 458677de7910a5455283a2be99f776a834449f61,Face Image Retrieval Using Facial Attributes By K-Means,"Face Image Retrieval Using Facial Attributes By K-Means [1]I.Sudha, [2]V.Saradha, [3]M.Tamilselvi, [4]D.Vennila [1]AP, Department of CSE ,[2][3][4] B.Tech(CSE) Achariya college of Engineering Technology- Puducherry" 45e81d04d01ef1db78a04ef7a9472fd4cd6de84c,Variational learning of finite Beta-Liouville mixture models using component splitting,"Variational Learning of Finite Beta-Liouville Mixture Models Using Component Splitting Wentao Fan and Nizar Bouguila" 45ede580b1e402aae6832256586211a47c53afe3,BIOMETRIC APPLICATION : TEXTURE AND SHAPE BASED 3 D FACE RECOGNITION,"BIOMETRIC APPLICATION: TEXTURE AND SHAPE BASED 3D FACE RECOGNITION P.Manju Bala1 Senior Assistant professor, A.Kalaiselvi2 Assistant Professor, Department of Computer Science and Engineering, Department of Computer Science and Engineering, IFET College of Engineering, Villupuram." 45c340c8e79077a5340387cfff8ed7615efa20fd,Assessment of the Emotional States of Students during e-Learning, 4572725e98f3e1b6f258c03643d74b69982aa39a,Semantic Cluster Unary Loss for Efficient Deep Hashing,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Semantic Cluster Unary Loss for Efficient Deep Hashing Shifeng Zhang, Jianmin Li, and Bo Zhang hashing [15], [22], [27], [32], [38], [54] and semi-supervised hashing [43]. Experiments convey that hashcodes learned by (semi-)supervised hashing methods contain more semantic information than those learned by the unsupervised ones." 4508afd43a616e62627a5f5c6089bb3b3629518f,Dismantling Complicated Query Attributes with Crowd,0.5441/002/edbt.2015.36 4563cbfbdba1779fc598081071ae40be021cb81d,Adversarial Attacks on Variational Autoencoders,"Adversarial Attacks on Variational Autoencoders George Gondim-Ribeiro, Pedro Tabacof, and Eduardo Valle RECOD Lab. — DCA / School of Electrical and Computer Engineering (FEEC) University of Campinas (Unicamp) Campinas, SP, Brazil {gribeiro, tabacof," 45e459462a80af03e1bb51a178648c10c4250925,LCrowdV: Generating Labeled Videos for Simulation-based Crowd Behavior Learning,"LCrowdV: Generating Labeled Videos for Simulation-based Crowd Behavior Learning Ernest Cheung1, Tsan Kwong Wong1, Aniket Bera1, Xiaogang Wang2, and Dinesh Manocha1 The University of North Carolina at Chapel Hill" 456ccc8bbb538037ff00fabf25afb2aceb39149e,Computational Aspects of the Hausdorff Distance in Unbounded Dimension,"Journal of Computational Geometry COMPUTATIONAL ASPECTS OF THE HAUSDORFF DISTANCE IN UNBOUNDED DIMENSION Stefan K¨onig∗" 45f884c4c3bcdabdca46ee0e3794ce1631b9c558,Vision-based assessment of parkinsonism and levodopa-induced dyskinesia with pose estimation,"Vision-Based Assessment of Parkinsonism and Levodopa-Induced Dyskinesia with Deep Learning Pose Estimation Michael H. Li, Tiago A. Mestre, Susan H. Fox, Babak Taati*" 458713d5c1dd8ff95865302e51f0f8df22204d91,ON FACE RECOGNITION USING DIFFERENT PRE-PROCESSING METHODS IN IMAGES CAPTURED UNDER VARIOUS ILLUMINATION AND POSING CONDITIONS, 45ae4c0cdc2df02c278995623b2e25ae5cc4c91f,Visual Search for Musical Performances and Endoscopic Videos,"Visual Search for Musical Performances nd Endoscopic Videos Degree’s Final Project Dissertation Telecommunications Engineering Author: Advisors: Mathias Lux and Xavier Gir´o-i-Nieto Jennifer Rold´an Carlos Alpen-Adria University of Klagenfurt (AAU Klagenfurt) Universitat Polit`ecnica de Catalunya (UPC)) 014 - 2015" 2b0ff4b82bac85c4f980c40b3dc4fde05d3cc23f,An Effective Approach for Facial Expression Recognition with Local Binary Pattern and Support Vector Machine,"An Effective Approach for Facial Expression Recognition with Local Binary Pattern and Support Vector Machine Cao Thi Nhan, 2Ton That Hoa An, 3Hyung Il Choi *1School of Media, Soongsil University, School of Media, Soongsil University, School of Media, Soongsil University," 2badc21fc72730f3ae540ba2d20051d31c4a62bc,The audio-video australian English speech data corpus AVOZES,"The Audio-Video Australian English Speech Data Corpus AVOZES Roland Goecke1,3 and J Bruce Millar2,3 Fraunhofer IGD-R, Rostock, Germany, 2Australian National University, Canberra, Australia, National ICT Australia , Canberra Laboratory Corresponding author:" 2b0a6aea501a8a29b5a6b757e89a8ea502e654cd,Depth-Adaptive Deep Neural Network for Semantic Segmentation,"Depth Adaptive Deep Neural Network for Semantic Segmentation Byeongkeun Kang, Yeejin Lee, and Truong Q. Nguyen, Fellow, IEEE" 2b8dfbd7cae8f412c6c943ab48c795514d53c4a7,Polynomial based texture representation for facial expression recognition,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE e-mail: e-mail: RECOGNITION . INTRODUCTION (d1,d2)∈[0;d]2 d1+d2≤d" 2bae810500388dd595f4ebe992c36e1443b048d2,Analysis of Facial Expression Recognition by Event-related Potentials,"International Journal of Bioelectromagnetism Vol. 18, No. 1, pp. 13 - 18, 2016 www.ijbem.org Analysis of Facial Expression Recognition y Event-related Potentials Taichi Hayasaka and Ayumi Miyachi Department of Information and Computer Engineering, National Institute of Technology, Toyota College, Japan Correspondence: Taichi Hayasaka, Department of Information and Computer Engineering, National Institute of Technology, Toyota College, 2-1 Eisei, Toyota-shi, Aichi, 471-8525 Japan, E-mail: phone +81 565 36 5861, fax +81 565 36 5926" 2bdc0c79b26fed51bc2af1af16117879ee3f571e,Augmented Multitouch Interaction upon a 2-DOF Rotating Disk,"Augmented Multitouch Interaction upon a 2-DOF Rotating Disk Xenophon Zabulis, Panagiotis Koutlemanis, and Dimitris Grammenos Institute of Computer Science, Foundation for Research and Technology - Hellas, Herakleion, Crete, Greece" 2bac4161a928eb33e6be700ed8ea4d823494b22c,MergeNet: A Deep Net Architecture for Small Obstacle Discovery,"MergeNet: A Deep Net Architecture for Small Obstacle Discovery Krishnam Gupta1, Syed Ashar Javed2, Vineet Gandhi2 and K. Madhava Krishna2 evidences is more likely to perform the task better. Recent efforts [3] on multi modal fusion also suggests likewise." 2bfb43cb0e72aaa7aff71007bb420df2c9ae4375,Deep Attentional Structured Representation Learning for Visual Recognition,": DEEP ATTENTIONAL STRUCTURED REPRESENTATION LEARNING Deep Attentional Structured Representation Learning for Visual Recognition Krishna Kanth Nakka Mathieu Salzmann Computer Vision Lab, EPFL Lausanne, Switzerland Computer Vision Lab, EPFL Lausanne, Switzerland" 2b1327a51412646fcf96aa16329f6f74b42aba89,Improving performance of recurrent neural network with relu nonlinearity,"Under review as a conference paper at ICLR 2016 IMPROVING PERFORMANCE OF RECURRENT NEURAL NETWORK WITH RELU NONLINEARITY Sachin S. Talathi & Aniket Vartak Qualcomm Research San Diego, CA 92121, USA" 2baea24cc71793ba40cf738b7ad1914f0e549863,Attribute Augmented Convolutional Neural Network for Face Hallucination,"Attribute Augmented Convolutional Neural Network for Face Hallucination Cheng-Han Lee1 Kaipeng Zhang1 Hu-Cheng Lee1 Chia-Wen Cheng2 Winston Hsu1 National Taiwan University 2The University of Texas at Austin {r05922077, r05944047, r05922174," 2b35c76d511e9b9168152ebecd92284a4762b65f,A method of limiting performance loss of CNNs in noisy environments,"A method of limiting performance loss of CNNs in noisy environments James R. Geraci Samsung Electronics Co,Ltd. Seoul, South Korea Parichay Kapoor Samsung Electronics Co,Ltd. Seoul, South Korea" 2b4b0795358d0264f846e8b3c19ec3180da301cc,Active MAP Inference in CRFs for Efficient Semantic Segmentation,"Active MAP Inference in CRFs for Efficient Semantic Segmentation Roderick de Nijs2 Gemma Roig1 ∗ Sebastian Ramos3 Xavier Boix1 ∗ Kolja K¨uhnlenz2 Luc Van Gool1,4 ETH Z¨urich, Switzerland 2TU Munchen, Germany 3CVC Barcelona, Spain 4KU Leuven, Belgium Both first authors contributed equally." 2bf571fd8020a68f513ba4ce690083aa7dcdad6e,Visual Speech and Speaker Recognition,"VisualSpeechAndSpeaker Recognition JuergenLuettin DepartmentofComputerScience UniversityofShe(cid:14)eld DissertationsubmittedtotheUniversityofShe(cid:14)eld forthedegreeofDoctorofPhilosophy (cid:13)JuergenLuettin . May  Allrightsreserved.Thisworkmaynotbereproducedinwholeorinpartwithoutpriorwritten permissionbytheauthor." 2b50f8e4568ecd84e2f9d6357254272d8db4bbd4,Hierarchical Gaussian Descriptor for Person Re-identification,"Hierarchical Gaussian Descriptor for Person Re-Identification Tetsu Matsukawa1, Takahiro Okabe2, Einoshin Suzuki1, Yoichi Sato3 Kyushu University 2 Kyushu Institute of Technology 3 The University of Tokyo {matsukawa," 2b1358efbceda12de2f36398cdbdb3c7bccc70d4,Unified Detection and Tracking of Instruments during Retinal Microsurgery,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. JOURNAL OF LATEX CLASS FILES, VOL. 6, NO. 1, JANUARY 2007 Unified detection and tracking of instruments during retinal microsurgery Raphael Sznitman, Rogerio Richa, Russell H. Taylor Fellow, IEEE, Bruno Jedynak nd Gregory D. Hager, Fellow, IEEE" 2ba64deeb3e170e4776e2d2704771019cf9c8639,Differences between Old and Young Adults’ Ability to Recognize Human Faces Underlie Processing of Horizontal Information,"AGING NEUROSCIENCE ORIGINAL RESEARCH ARTICLE published: 23 April 2012 doi: 10.3389/fnagi.2012.00003 Differences between old and young adults’ ability to recognize human faces underlie processing of horizontal information Sven Obermeyer *,Thorsten Kolling, Andreas Schaich and Monika Knopf Department of Psychology, Institute for Psychology, Goethe-University Frankfurt am Main, Frankfurt am Main, Germany Edited by: Hari S. Sharma, Uppsala University, Sweden Reviewed by: Luis Francisco Gonzalez-Cuyar, University of Washington School of Medicine, USA Gregory F. Oxenkrug, Tufts University, *Correspondence: Sven Obermeyer , Department of Psychology, Goethe-University" 2b285e5eaeb7a2aa7e37c5ae6762b838d3742b4e,Video event recognition using concept attributes,"Video Event Recognition Using Concept Attributes Jingen Liu, Qian Yu, Omar Javed, Saad Ali, Amir Tamrakar, Ajay Divakaran, Hui Cheng, Harpreet Sawhney SRI International Sarnoff Princeton, NJ, USA 08540" 2beb9777bf452d02f9bec5275c100f4a736def10,Near Duplicate Image Discovery on One Billion Images,"Near Duplicate Image Discovery on One Billion Images Saehoon Kim ∗ Department of Computer Science, POSTECH, Korea Xin-Jing Wang Web Search and Mining Group Microsoft Research Asia, Beijing Lei Zhang Web Search and Mining Group Microsoft Research Asia, Beijing Seungjin Choi Department of Computer Science, POSTECH, Korea" 2baf54199b4b0047f3610ba691fb0a718dbce97e,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"International Journal of Computer Applications (0975 – 8887) Volume 134 – No.7, January 2016 Development of an Efficient Face Recognition System ased on Linear and Nonlinear Algorithms Filani Araoluwa S. Department of Computer Science, The Federal University of Technology, P.M.B.704, Akure, Ondo State, Nigeria." 2bd49bdfc61788c8ac5621fe7f08a06dd2152fb9,Pose Invariant Face Recognition Using Neuro-Biologically Inspired Features,"International Journal of Future Computer and Communication, Vol. 1, No. 3, October 2012 Pose Invariant Face Recognition Using Neuro-Biologically Inspired Features Pramod Kumar Pisharady and Martin Saerbeck" 2ba5e4c421b1413139e4bc5d935d6d48cc753757,Vantage Feature Frames for Fine-Grained Categorization,"Vantage Feature Frames For Fine-Grained Categorization Asma Rejeb Sfar INRIA Saclay Palaiseau, France Nozha Boujemaa INRIA Saclay Palaiseau, France Donald Geman Johns Hopkins University Baltimore, MD, USA sma.rejeb" 2b212a9416027dc63273f9e29d93230d837abacf,Fast Optical Flow using Dense Inverse Search,"Fast Optical Flow using Dense Inverse Search Till Kroeger1 Radu Timofte1 Dengxin Dai1 Luc Van Gool1,2 Computer Vision Laboratory, D-ITET, ETH Zurich VISICS / iMinds, ESAT, K.U. Leuven {kroegert, timofter, dai," 2befea9b289f22547f8911aa56672d6373c1ac64,Recognizing activities with cluster-trees of tracklets,"GAIDON et al.: RECOGNIZING ACTIVITIES WITH CLUSTER-TREES OF TRACKLETS Recognizing activities with cluster-trees of tracklets Adrien Gaidon http://lear.inrialpes.fr/people/gaidon Zaid Harchaoui http://lear.inrialpes.fr/people/harchaoui Cordelia Schmid http://lear.inrialpes.fr/people/schmid LEAR - INRIA Grenoble, LJK 655, avenue de l’Europe 8330 Montbonnot, France" 2b3fe9a0356eaf50f1340dda3f3d14f6904905ec,Taking advantage of sensor modality specific properties in Automated Driving Extended Abstract,"Taking advantage of sensor modality specific properties in Automated Driving" 2badc4c87a7751dd5ae1797bc4091d10d1acf442,Multimodal Retrieval with Asymmetrically Weighted Regularized Canonical Correla- Tion Analysis,"Under review as a conference paper at ICLR 2016 MULTIMODAL RETRIEVAL WITH ASYMMETRICALLY WEIGHTED REGULARIZED CANONICAL CORRELA- TION ANALYSIS Youssef Mroueh, Etienne Marcheret, Vaibhava Goel Multimodal Algorithms and Engines Group IBM T.J Watson Research Center, USA" 2b8667df1a0332386d8d799fbac0327496ce02c9,Stranger danger : Parenthood increases the envisioned bodily formidability of menacing men ☆,"Evolution and Human Behavior 35 (2014) 109–117 Contents lists available at ScienceDirect Evolution and Human Behavior j o u r n a l h o m e p a g e : w w w . e h b o n l i n e . o r g Original Article Stranger danger: Parenthood increases the envisioned bodily formidability of menacing men☆ Daniel M.T. Fessler a,b,⁎, Colin Holbrook a,b, Jeremy S. Pollack b, Jennifer Hahn-Holbrook b,c Department of Anthropology, University of California, Los Angeles, Los Angeles, CA 90095, USA Center for Behavior, Evolution, and Culture, University of California, Los Angeles, Los Angeles, CA 90095, USA Department of Psychology, University of California, Los Angeles, Los Angeles, CA 90095, USA r t i c l e i n f o b s t r a c t Article history: Initial receipt 6 April 2013 Final revision received 1 November 2013 Keywords: Parenthood Relative formidability" 2bf41bf420c8d86dd1bffbacd28c70fa8b12b6dd,Counting the uncountable: deep semantic density estimation from Space,"Counting the uncountable: Deep semantic density estimation from space Andres C. Rodriguez and Jan D. Wegner ETH Zurich, Stefano-franscini-platz 5 8093 Zurich, Switzerland Accepted at GCPR 2018" 2b507f659b341ed0f23106446de8e4322f4a3f7e,Deep Identity-aware Transfer of Facial Attributes,"Deep Identity-aware Transfer of Facial Attributes Mu Li1, Wangmeng Zuo2, David Zhang1 The Hong Kong Polytechnic University 2Harbin Institute of Technology" 2b537d826718b7578ea7c5d0164873d376824e6d,Gradient-based Camera Exposure Control for Outdoor Mobile Platforms,"Auto Manual Manual Ours Ours Auto Manual Ours Fig.1:Imagescapturedunderdifferentilluminationcondi-tions.Fromlefttorighttheimagesarefromcameraswithabuilt-inauto-exposuremethod,amanuallytunedfixedexpo-suresetting,andourmethod.Boththebuilt-inauto-exposuremethodandthemanualsettingfailtocapturewell-exposedimages,whileourmethodcapturesimagesthataresuitableforprocessingwithcomputervisionalgorithms.ascenehasasignificantilluminationgapbetweendynamicrangesoftheregionofinterestandthebackground.Thiscommonconditiondegradestheperformanceofthesubse-quentcomputervisionalgorithms.Therefore,overcomingtheproblemofdiverseandchallengingilluminationconditionsattheimagecapturestageisanessentialprerequisitefordevelopingrobustvisionsystems.Morespecifically,Figure1showssomecomparisonsofimagesresultingfromthestandardbuilt-inauto-exposureandthefixed-exposureapproachesinanoutdoorenvironment.Whenthedynamicrangeofthesceneisrelativelynarrow,bothmethodscapturewell-exposedimages.Consequently,underanarrowdynamicrange,asinglerepresentativepa-rametercaneasilybedetermined.Incontrast,bothmethodsresultinundesirablyexposedimagesunderabruptlyvaryingilluminationconditions.Therationalesbehindtheseresultscanbecharacterizedasfollows:1)theauto-exposurecontrolalgorithmshavelimitedadaptability(i.e.,prediction),2)donotconsiderthelimiteddynamicrangeofthecamera,and3)useweakcriteriatoassesstheexposurestatus.Weaddressthefirstandthesecondissuesusingasimulation-basedapproachandthethirdissueusingagradient-basedmetric.Inthispaper,wepresentanewmethodtoautomaticallyadjustcameraexposureusingthegradientinformation.Tohandlesevereilluminationchangesandawidedynamicrangeofsceneradiance,wesimulatetheproperexposureofthesceneinthegradientdomain;thisprocessisfollowedbyafeedbackmechanismtoperformauto-exposure.Becausethegradientdomainisrobustagainstilluminationchangesandhasbeenleveragedbymanycomputervisionalgorithms,theproposedmethodissuitableforcapturingwell-exposedimageswithenrichedimagefeaturesthatarebeneficialforcomputer" 2b8a61184b6423e3d5285803eb1908ff955db1a8,Processing and analysis of 2 . 5 D face models for non-rigid mapping based face recognition using differential geometry tools,"Processing and analysis of 2.5D face models for non-rigid mapping based face recognition using differential geometry tools Przemyslaw Szeptycki To cite this version: Przemyslaw Szeptycki. Processing and analysis of 2.5D face models for non-rigid mapping ased face recognition using differential geometry tools. Other. Ecole Centrale de Lyon, 2011. English. . HAL Id: tel-00675988 https://tel.archives-ouvertes.fr/tel-00675988 Submitted on 2 Mar 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," 2b632f090c09435d089ff76220fd31fd314838ae,Early Adaptation of Deep Priors in Age Prediction from Face Images,"Early Adaptation of Deep Priors in Age Prediction from Face Images Mahdi Hajibabaei Computer Vision Lab D-ITET, ETH Zurich Anna Volokitin Computer Vision Lab D-ITET, ETH Zurich Radu Timofte CVL, D-ITET, ETH Zurich Merantix GmbH" 4684c487758df6b6bf4b69f3fe22e1aad874378a,A Discriminative Voting Scheme for Object Detection using Hough Forests,"VIJAY KUMAR B G, IOANNIS PATRAS: A Discriminative Voting Scheme for Object Detection using Hough Forests Vijay Kumar.B.G Dr Ioannis Patras Multimedia Vision Research Group Queen Mary, UoL London, UK" 46a01565e6afe7c074affb752e7069ee3bf2e4ef,Local Descriptors Encoded by Fisher Vectors for Person Re-identification,"Local Descriptors Encoded by Fisher Vectors for Person Re-identification Bingpeng Ma, Yu Su, Fr´ed´eric Jurie To cite this version: Bingpeng Ma, Yu Su, Fr´ed´eric Jurie. Local Descriptors Encoded by Fisher Vectors for Person Re-identification. 12th European Conference on Computer Vision (ECCV) Workshops, 2012, Italy. pp.413-422, 2012, <10.1007/978-3-642-33863-2 41>. HAL Id: hal-00806066 https://hal.archives-ouvertes.fr/hal-00806066 Submitted on 29 Mar 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 46c82ea7aa2812e5adee6c4804d15cd5ecb96041,An affine view and illumination invariant iterative image matching approach for face recognition,"International Journal of Engineering & Technology, 7 (2.8) (2018) 42-46 International Journal of Engineering & Technology Website: www.sciencepubco.com/index.php/IJET Research Paper An affine view and illumination invariant iterative image matching approach for face recognition D. Rajasekhar 1 *, T. Jayachandra Prasad 2, K. Soundararajan 3 Research Scholar, Department of ECE, JNTUA, Ananthapuramu, Andhra Pradesh-515002 Professor and Principal, RGMCET, Nandyal, Andhra Pradesh, India-518501 Professor and Dean of R&D, TKREC, Hyderabad, Telangana-500097 *Corresponding author E-mail:" 46994b489f7c673d031f6ef644e84ebe5d843d93,A learning-based visual saliency prediction model for stereoscopic 3D video (LBVS-3D),"A Learning-Based Visual Saliency Prediction Model for Stereoscopic 3D Video (LBVS-3D) Amin Banitalebi-Dehkordi, Mahsa T. Pourazad, and Panos Nasiopoulos" 4686bdcee01520ed6a769943f112b2471e436208,Fast search based on generalized similarity measure,"Utsumi et al. IPSJ Transactions on Computer Vision and Applications (2017) 9:11 DOI 10.1186/s41074-017-0024-5 IPSJ Transactions on Computer Vision and Applications EXPRESS PAPER Open Access Fast search based on generalized similarity measure Yuzuko Utsumi*†, Tomoya Mizuno†, Masakazu Iwamura and Koichi Kise" 466212a84d5b60f4517e8ab3e4473c3c9e081897,Thermal-Visible Registration of Human Silhouettes : a Similarity Measure Performance Evaluation,"Thermal-Visible Registration of Human Silhouettes: a Similarity Measure Performance Evaluation Guillaume-Alexandre Bilodeaua,∗, Atousa Torabib, Pierre-Luc St-Charlesa, Dorra Riahia LITIV Lab., Department of Computer and Software Engineering, ´EcolePolytechnique de Montr´eal, P.O. Box 6079, Station Centre-ville, Montr´eal Qu´ebec, Canada, H3C 3A7 LISA, Dept. IRO, Universit´e de Montr´eal, Montr´eal, Qu´ebec, Canada, H2C 3J7" 4634bf44a0c994e2bed89686225f8cef601a0224,NLM at ImageCLEF 2018 Visual Question Answering in the Medical Domain,"NLM at ImageCLEF 2018 Visual Question Answering in the Medical Domain Asma Ben Abacha, Soumya Gayen, Jason J Lau, Sivaramakrishnan Rajaraman, and Dina Demner-Fushman Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD, USA." 46df854f57b6553b4b3238779e46bf2a3a3fffcf,3 D Face Recognition using ICP and Geodesic Computation Coupled Approach,"D Face Recognition using ICP and Geodesic Computation Coupled Approach Karima Ouji‡, Boulbaba Ben Amor§, Mohsen Ardabilian§, Faouzi Ghorbel‡, and Liming Chen§ §LIRIS, Laboratoire d’InfoRmatique en Image et Systmes d’information, 6, av. Guy de Collongue, 69134 Ecully, France. GRIFT, Groupe de Recherche en Images et Formes de Tunisie, Ecole Nationale des Sciences de l’Informatique, Tunisie. Key words: 3D face recognition, Iterative Closest Point, Geodesics computa- tion, biometric evaluation" 469fa274bbef1e8c7b5b4b1948963abdffaf4e1c,Socially Aware Kalman Neural Networks for Trajectory Prediction,"Socially Aware Kalman Neural Networks for Trajectory Prediction Ce Ju ∗ ‡ Zheng Wang† ‡ Xiaoyu Zhang∗ In spite of the challenges above, we exploit the following" 4669b079c3ca15aba08130c36ead597014f7341a,GrabCut-Based Human Segmentation in Video Sequences,"Sensors 2012, 12, 15376-15393; doi:10.3390/s121115376 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article GrabCut-Based Human Segmentation in Video Sequences Antonio Hern´andez-Vela 1,2,⋆, Miguel Reyes 1,2, V´ıctor Ponce 1,2 and Sergio Escalera 1,2 Departamento MAIA, Universitat de Barcelona, Gran Via 585, 08007 Barcelona, Spain; E-Mails: (M.R.); (V.P.); (S.E.) Centre de Visi´o per Computador, Campus UAB, Edifici O, 08193 Bellaterra, Barcelona, Spain * Author to whom correspondence should be addressed; E-Mail: Tel.: +34-93-402-1897; Fax: +34-93-402-1601. Received: 4 September 2012; in revised form: 1 November 2012 / Accepted: 6 November 2012 / Published: 9 November 2012" 46c3e8c2b2042b193659c0a613adc72100a2f301,Vision for Robotics By Danica Kragic and,"Foundations and Trends R(cid:1) in Robotics Vol. 1, No. 1 (2010) 1–78 (cid:1) 2009 D. Kragic and M. Vincze DOI: 10.1561/2300000001 Vision for Robotics By Danica Kragic and Markus Vincze Contents Introduction .1 Scope and Outline Historical Perspective .1 Early Start and Industrial Applications .2 Biological Influences and Affordances .3 Vision Systems What Works .1 Object Tracking and Pose Estimation .2 Visual Servoing–Arms and Platforms .3 Reconstruction, Localization, Navigation, and Visual SLAM .4 Object Recognition" 46f3b113838e4680caa5fc8bda6e9ae0d35a038c,Automated Dermoscopy Image Analysis of Pigmented Skin Lesions,"Cancers 2010, 2, 262-273; doi:10.3390/cancers2020262 OPEN ACCESS ancers ISSN 2072-6694 www.mdpi.com/journal/cancers Review Automated Dermoscopy Image Analysis of Pigmented Skin Lesions Alfonso Baldi 1,2,*, Marco Quartulli 3, Raffaele Murace 2, Emanuele Dragonetti 2, Mario Manganaro 3, Oscar Guerra 3 and Stefano Bizzi 3 Department of Biochemistry, Section of Pathology, Second University of Naples, Via L. Armanni 5, 80138 Naples, Italy Futura-onlus, Via Pordenone 2, 00182 Rome, Italy; E-Mail: ACS, Advanced Computer Systems, Via della Bufalotta 378, 00139 Rome, Italy * Author to whom correspondence should be addressed; E-Mail: Fax: +390815569693. Received: 23 February 2010; in revised form: 15 March 2010 / Accepted: 25 March 2010 / Published: 26 March 2010" 4640dfc0bfe7923c08d0c762a9c33b52b9029409,Head Movement and Facial Expression Transfer from 2 D Video to a 3 D Model,"Head Movement and Facial Expression Transfer from 2D Video to a 3D Model Mairead Grogan A dissertation submitted to the University of Dublin, Trinity College, in partial fulfilment of the requirements for the degree of Master of Science in Computer Science (Interactive Entertainment Technology) University of Dublin, Trinity College" 46971fb6caa61c606b046da855be4e196a830ccf,Identification of Scene Text by Character Descriptor in Smart Mobile Devices,"International Journal of Engineering Research and General Science Volume 3, Issue 3, Part-2 , May-June, 2015 ISSN 2091-2730 Identification of Scene Text by Character Descriptor in Smart Mobile Devices Devdas¹, Bhavana.S², Dr. Shubhangi D.C.³ Student, Department of computer science and engineering, VTU RO Kalaburagi, India¹ Assistant professor, Department of computer science and engineering, VTU RO Kalaburagi, India² Head of Department, Department of computer science and engineering, VTU RO Kalaburagi, India³ Contact no: 8951781387" 46386d4aa6a2b96106ab1d18658103622b24f9d8,Google Street View images support the development of vision-based driver assistance systems,"Google Street View Images Support the Development of Vision-Based Driver Assistance Systems Jan Salmen∗, Sebastian Houben∗, and Marc Schlipsing∗" 46c52f92e10fd2f2dddda162ad7995a1658e1245,Finding Socio-Textual Associations Among Locations,"Series ISSN: 2367-2005 0.5441/002/edbt.2017.12" 46471a285b1d13530f1885622d4551b48c19fc67,Generating Artificial Data for Private Deep Learning,"Generating Artificial Data for Private Deep Learning Ecole Polytechnique Fédérale de Lausanne Ecole Polytechnique Fédérale de Lausanne Aleksei Triastcyn Artificial Intelligence Laboratory Lausanne, Switzerland Boi Faltings Artificial Intelligence Laboratory Lausanne, Switzerland" 46a4551a6d53a3cd10474ef3945f546f45ef76ee,Robust and continuous estimation of driver gaze zone by dynamic analysis of multiple face videos,"014 IEEE Intelligent Vehicles Symposium (IV) June 8-11, 2014. Dearborn, Michigan, USA 978-1-4799-3637-3/14/$31.00 ©2014 IEEE" 460845e06ca99f292fa2265beb4e535d20ba16f8,Object Detection for Comics using Manga109 Annotations,"Object Detection for Comics using Manga109 Annotations Toru Ogawa · Atsushi Otsubo · Rei Narita · Yusuke Matsui · Toshihiko Yamasaki · Kiyoharu Aizawa" 4679f4a7da1cf45323c1c458b30d95dbed9c8896,Recognizing Facial Expressions Using Model-Based Image Interpretation,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 465b75fa4b84948e19d8bf2ebf4fe4459c3c87ae,A deformation model to reduce the effect of expressions in 3D face recognition,"Vis Comput (2011) 27: 333–345 DOI 10.1007/s00371-010-0530-2 O R I G I NA L A RT I C L E A deformation model to reduce the effect of expressions in 3D face recognition Yueming Wang · Gang Pan · Jianzhuang Liu Published online: 5 November 2010 © Springer-Verlag 2010" 463bfb0b55c085cda77c2c6e1583abb64baa5d0a,Learning Arbitrary Pairwise Potentials in CRFs for Semantic Segmentation,"Learning Arbitrary Potentials in CRFs with Gradient Descent M˚ans Larsson1 Fredrik Kahl1,2 Chalmers Univ. of Technology 2Lund Univ. Shuai Zheng3 Anurag Arnab3 Oxford Univ. Philip Torr3 Richard Hartley4 Australian National Univ." 46b031a3e368f25dd1e42f70f21165fef7b16de2,"Faces in the mirror, from the neuroscience of mimicry to the emergence of mentalizing.","doi 10.4436/jass.94037 Vol. 94 (2016), pp. 113-126 Faces in the mirror, from the neuroscience of mimicry to the emergence of mentalizing Antonella Tramacere & Pier Francesco Ferrari University of Parma, Dep. of Neuroscience, via Volturno 39, 43100, Parma, Italy e-mail: Summary - In the current opinion paper, we provide a comparative perspective on specific aspects of primate empathic abilities, with particular emphasis on the mirror neuron system associated with mouth/face actions and expression. Mouth and faces can be very salient communicative classes of stimuli that allow an observer access to the emotional and physiological content of other individuals. We thus describe patterns of activations of neural populations related to observation and execution of specific mouth actions and emotional facial expressions in some species of monkeys and in humans. Particular ttention is given to dynamics of face-to-face interactions in the early phases of development and to the differences in the anatomy of facial muscles among different species of primates. We hypothesize that increased complexity in social environments and patterns of social development have promoted specializations of facial musculature, behavioral repertoires related to production and recognition of facial emotional expression, and their neural correlates. In several primates, mirror circuits involving parietal-frontal regions, insular regions, cingulate cortices, and amygdala seem to support automatic forms of embodied empathy, which probably contribute to facial mimicry and behavioural synchrony." 4602bbec65b0c718d5887fdf2381fb7cee77a64d,Explicit Occlusion Modeling for 3D Object Class Representations,"Explicit Occlusion Modeling for 3D Object Class Representations M. Zeeshan Zia1, Michael Stark2, and Konrad Schindler1 Photogrammetry and Remote Sensing, ETH Z¨urich, Switzerland Stanford University and Max Planck Institute for Informatics" 46fbf807f1c0c863aa35d3d8acb40870182d3b28,Multi-Instance Dynamic Ordinal Random Fields for Weakly Supervised Facial Behavior Analysis,"Multi-Instance Dynamic Ordinal Random Fields for Weakly-supervised Facial Behavior Analysis Adria Ruiz∗, Ognjen (Oggi) Rudovic†, Xavier Binefa∗ and Maja Pantic(cid:5)" 46299c9db8a4570d060ee8fc1616c4a148056365,IJCSI Publicity Board 2011,"IJCSI IJCSI International Journal of Computer Science Issues © IJCSI PUBLICATION www.IJCSI.org Volume 7, Issue 5, September 2010 ISSN (Online): 1694-0814" 46106d9f9d9b90401b7984794536e2f45fff1dbe,Learning Distance Functions for Automatic Annotation of Images,"Learning Distance Functions for Automatic Annotation of Images Josip Krapac and Fr´ed´eric Jurie INRIA Rhˆone-Alpes, 655, Avenue de l’Europe, 38334 Saint Ismier Cedex, France" 468aaa87ccdba65f3115bd0864f7772b6706c00e,A Survey on Heterogeneous Face Matching : NIR Images to VIS Images,"International Journal of Computer Applications (0975 – 8887) Emerging Trends In Computing 2016 Heterogeneous Face Matching: NIR images to VIS Images Sandhya R.Waddhavane M.E Student Department of Computer Engineering KKWIEER, Nashik, India. Savitribai Phule Pune University,Pune S.M.Kamalapur, PhD Associate Professor Department of Computer Engineering KKWIEER, Nashik, India. Savitribai Phule Pune University,Pune" 4682fee7dc045aea7177d7f3bfe344aabf153bd5,Tabula rasa: Model transfer for object category detection,"Tabula Rasa: Model Transfer for Object Category Detection Yusuf Aytar & Andrew Zisserman, Department of Engineering Science Oxford (Presented by Elad Liebman)" 46312c80e0583e956ac351615d73e11c21749c4b,Chapter 5 Multimodal Affect Recognition : Current Approaches and Challenges,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 46888c67aa5351730ce5022cc800239f6557f254,Online Multi-target Visual Tracking using a HISP Filter, 463a1ca5f819af35e71ae47ea0e57293691507d3,Soft Biometrics Classification Using Denoising Convolutional Autoencoders and Support Vector Machines,"Soft Biometrics Classification Using Denoising Convolutional Autoencoders and Support Vector Machines Nelson Marcelo Romero Aquino1, Matheus Gutoski2 Leandro Takeshi Hattori3 and Heitor Silv´erio Lopes4 Federal University of Technology - Paran´a Av. Sete de Setembro, 3165 - Rebou¸cas CEP 80230-901" 462e4d0b35bf571bfc35dcd8e9bd589dca07a464,"Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation","Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov Liang-Chieh Chen {sandler, howarda, menglong, azhmogin, Google Inc." 46282f10271875647219b641dac2cc01c7dc8ab2,Psychopathic traits are associated with reduced fixations to the eye region of fearful faces.,"018, Vol. 127, No. 1, 43–50 0021-843X/18/$12.00 © 2018 American Psychological Association http://dx.doi.org/10.1037/abn0000322 Psychopathic Traits Are Associated With Reduced Fixations to the Eye Region of Fearful Faces Monika Dargis, Richard C. Wolf, and Michael Koenigs University of Wisconsin–Madison Impairments in processing fearful faces have been documented in both children and adults with psychopathic traits, suggesting a potential mechanism by which psychopathic individuals develop callous nd manipulative interpersonal and affective traits. Recently, research has demonstrated that psycho- pathic traits are associated with reduced fixations to the eye regions of faces in samples of children and ommunity-dwelling adults, however this relationship has not yet been established in an offender sample with high levels of psychopathy. In the current study, we employed eye-tracking with paradigms involving the identification and passive viewing of facial expressions of emotion, respectively, in a sample of adult male criminal offenders (n ⫽ 108) to elucidate the relationship between visual processing of fearful facial expressions and interpersonal and affective psychopathic traits. We found that the interpersonal-affective traits of psychopathy were significantly related to fewer fixations to the eyes of fear faces during the emotion recognition task. This association was driven particularly by the interper- sonal psychopathic traits (e.g., egocentricity, deceitfulness), whereas fear recognition accuracy was" 46d728356b5090bc28461b30cb21a08c3a690195,"Deep Multi-patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation","Deep Multi-Patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation Xin Lu(cid:63) James Z. Wang(cid:63) (cid:63)The Pennsylvania State University, University Park, Pennsylvania Zhe Lin† Xiaohui Shen† Radom´ır Mˇech† Adobe Research, San Jose, California {xinlu, {zlin, xshen," 46f2611dc4a9302e0ac00a79456fa162461a8c80,Spatio-Temporal Channel Correlation Networks for Action Classification,"for Action Classification Ali Diba1,4,(cid:63), Mohsen Fayyaz3,(cid:63), Vivek Sharma2, M.Mahdi Arzani4, Rahman Yousefzadeh4, Juergen Gall3, Luc Van Gool1,4 ESAT-PSI, KU Leuven, 2CV:HCI, KIT, Karlsruhe, 3University of Bonn, 4Sensifai" 3a4f522fa9d2c37aeaed232b39fcbe1b64495134,Face Recognition and Retrieval Using Cross-Age Reference Coding With Cross-Age Celebrity Dataset,"ISSN (Online) 2321 – 2004 ISSN (Print) 2321 – 5526 INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN ELECTRICAL, ELECTRONICS, INSTRUMENTATION AND CONTROL ENGINEERING Vol. 4, Issue 5, May 2016 IJIREEICE Face Recognition and Retrieval Using Cross Age Reference Coding Sricharan H S1, Srinidhi K S1, Rajath D N1, Tejas J N1, Chandrakala B M2 BE, DSCE, Bangalore1 Assistant Professor, DSCE, Bangalore2" 3a4ecdf7d73b0fb392763048aa834a537a495537,Contour-based object detection,"SCHLECHT, OMMER: CONTOUR-BASED OBJECT DETECTION Contour-based Object Detection Joseph Schlecht Björn Ommer Interdisciplinary Center for Scientific Computing University of Heidelberg Germany" 3a8f16d8f7adae8bd0cdc5cc5114dac0b388a9f6,Interpreting Deep Neural Network: Fast Object Localization via Sensitivity Analysis,"Under review as a conference paper at ICLR 2019 INTERPRETING DEEP NEURAL NETWORK: FAST OBJECT LOCALIZATION VIA SENSITIVITY ANALYSIS Anonymous authors Paper under double-blind review" 3a165f7e22f0667b401cba1b2615048193781b4c,Patch-Based Object Recognition,"Diplomarbeit im Fach Informatik Rheinisch-Westf¨alische Technische Hochschule Aachen Lehrstuhl f¨ur Informatik 6 Prof. Dr.-Ing. H. Ney Patch-Based Object Recognition vorgelegt von: Andre Hegerath Matrikelnummer 228760 Gutachter: Prof. Dr.-Ing. H. Ney Prof. Dr. T. Seidl Betreuer: Dipl.-Inform. T. Deselaers" 3a2fc58222870d8bed62442c00341e8c0a39ec87,Probabilistic Local Variation Segmentation,"Probabilistic Local Variation Segmentation Michael Baltaxe Technion - Computer Science Department - M.Sc. Thesis MSC-2014-02 - 2014" 3a8846ca16df5dfb2daadc189ed40c13d2ddc0c5,Validation loss for landmark detection,"Validation loss for landmark detection Wolfgang Fuhl Eberhard Karls Universit¨at T¨ubingen Institution1 address Rene Alexander Lotz Daimler AG Inselstrae 140, 70546 Stuttgart, Germany Wolfgang Rosenstiel Eberhard Karls Universit¨at T¨ubingen Auf der Morgenstelle 8, 72076 Tbingen, Germany Thomas K¨ubler Eberhard Karls Universit¨at T¨ubingen Sand 14, 72076 Tbingen, Germany Gjergji Kasneci Eberhard Karls Universit¨at T¨ubingen Sand 14, 72076 Tbingen, Germany Enkelejda Kasneci Eberhard Karls Universit¨at T¨ubingen Sand 14, 72076 Tbingen, Germany" 3a89236bb9fb3198a45089fb4a99ddba070d0cba,Image Area Reduction for Efficient Medical Image Retrieval,"Image Area Reduction for Ef‌f‌icient Medical Image Retrieval Zehra Camlica A thesis presented to the University of Waterloo in fulfillment of the thesis requirement for the degree of Master of Applied Science Systems Design Engineering Waterloo, Ontario, Canada, 2015 (cid:13) Zehra Camlica 2015" 3af0400c011700f3958062edfdfed001e592391c,The Intense World Theory – A Unifying Theory of the Neurobiology of Autism,"HUMAN NEUROSCIENCE The Intense World Theory – a unifying theory of the neurobiology of autism Review ARticle published: 21 December 2010 doi: 10.3389/fnhum.2010.00224 Kamila Markram * and Henry Markram Laboratory of Neural Microcircuits, Brain Mind Institute, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland Edited by: Silvia A. Bunge, University of California Berkeley, USA Reviewed by: Matthew K. Belmonte, Cornell University, USA; University of Cambridge, UK Egidio D’Angelo, University of Pavia, Italy *Correspondence:" 3aa9c8c65ce63eb41580ba27d47babb1100df8a3,Differentiating Duchenne from non-Duchenne smiles using active appearance models,"Annals of the University of North Carolina Wilmington Master of Science in Computer Science and Information Systems" 3acfbc2aee9b2ed246a640930ebc2e350621f990,Progressive Boosting for Class Imbalance,"Progressive Boosting for Class Imbalance Roghayeh Soleymania,∗, Eric Grangera, Giorgio Fumerab Laboratoire d’imagerie, de vision et d’intelligence artificielle, ´Ecole de technologie sup´erieure Pattern Recognition and Applications Group, Dept. of Electrical and Electronic Engineering Universit´e du Qu´ebec, Montreal, Canada University of Cagliari, Cagliari, Italy" 3ab13f3ee6d66186c33766ac115d57f8b381468f,Stream Clustering with Dynamic Estimation of Emerging Local Densities,"Stream Clustering with Dynamic Estimation of Emerging Local Densities Ziyin Wang Gavriil Tsechpenakis Department of Computer and Information Science Indiana University-Purdue University Indianapolis Department of Computer and Information Science Indiana University-Purdue University Indianapolis Indianapolis, IN 46202, USA Email: Indianapolis, IN 46202, USA Email:" 3aa66f2829ef440842c71a52cdaff30398a90ccb,Pointly-Supervised Action Localization,"International Journal of Computer Vision manuscript No. (will be inserted by the editor) Pointly-Supervised Action Localization Pascal Mettes · Cees G. M. Snoek Received: date / Accepted: date" 3abb51739b90c8bfd665e045b0eeadc87e065b63,Intrinsic 3D Dynamic Surface Tracking based on Dynamic Ricci Flow and Teichmüller Map,"Intrinsic 3D Dynamic Surface Tracking based on Dynamic Ricci Flow and Teichm ¨uller Map Xiaokang Yu Dept of Comp Sci Qingdao Univ Na Lei Dept of Soft and Tech Dalian Univ of Tech Qingdao, PR China Dalian,PR China Yalin Wang Comp.Sci.& Engin Arizona State Univ Arizona, USA Xianfeng Gu Dept of Comp Sci Stony Brook Univ Stony Brook, USA" 3a591a9b5c6d4c62963d7374d58c1ae79e3a4039,Driver Cell Phone Usage Detection from HOV/HOT NIR Images,"Driver Cell Phone Usage Detection From HOV/HOT NIR Images Yusuf Artan, Orhan Bulan, Robert P. Loce, and Peter Paul Xerox Research Center Webster 800 Phillips Rd. Webster NY 14580" 3aef744dad3982a7ae1ad97b4f126b6772fc3d07,Scene-Centric Joint Parsing of Cross-View Videos,"Scene-centric Joint Parsing of Cross-view Videos Hang Qi1∗, Yuanlu Xu1∗, Tao Yuan1∗, Tianfu Wu2, Song-Chun Zhu1 Dept. Computer Science and Statistics, University of California, Los Angeles (UCLA) {hangqi, tianfu Dept. Electrical and Computer Engineering, NC State University" 3abfab8740ffc66c0c191ce32ce1240062620bea,Continuous Facial Affect Recognition from Videos,"N. Garay, J. Abascal (Eds.): Actas del XII Congreso Internacional Interacción 2011, Lisboa Continuous Facial Affect Recognition from Videos Sergio Ballano1, Isabelle Hupont1, Eva Cerezo2 and Sandra Baldassarri2 Aragon Institute of Technology, Department of R&D and Technology Services, Zaragoza. 5018, María de Luna 7-8, Spain University of Zaragoza, Computer Science and Systems Engineering Department, Zaragoza. 50018, María de Luna 3, Spain {sballano, {ecerezo," 3a9681e2e07be7b40b59c32a49a6ff4c40c962a2,"Comparing treatment means : overlapping standard errors , overlapping confidence intervals , and tests of hypothesis","Biometrics & Biostatistics International Journal Comparing treatment means: overlapping standard errors, overlapping confidence intervals, and tests of hypothesis" 3af0a26ef9a4084703b310eb997ca630d0bae237,Automatic conversion of monoscopic image / video to stereo for 3 D visualization,"________________________________________________________________________________________________ International Journal of Recent Advances in Engineering & Technology (IJRAET) Automatic conversion of monoscopic image/ video to stereo for 3D visualization R.C.Gokul Nanda Kumar, 2Vijaykumar T 4th sem, M.Tech (Digital Electronics), SJBIT, Bangalore Assoc Prof, Dept. of ECE, SJBIT, Bangalore Email: into a" 3a7f9b4badc7407273325650763e887ad7b5cc9e,Anthropometric Comparison of Cross-Sectional External Ear between Monozygotic Twin,"Annals of Forensic Research and Analysis *Corresponding author Rumiza Abd Rashid, Institute of Forensic Sciences, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia; Tel: +60196943080; Fax: +603-55444562 ; Email: Submitted: 19 November 2014 Accepted: 20 November 2014 Published: 22 November 2014 Copyright © 2014 Rashid et al. OPEN ACCESS Keywords • External ear • Monozygotic twin • Anthropometric measurement • Forensic anthropology • Identification Research Article Anthropometric Comparison" 3a772ed83fdc90e10def9d38f59153aee49cd47b,A Camera Network Tracking (CamNeT) Dataset and Performance Baseline,"A Camera Network Tracking (CamNeT) Dataset and Performance Baseline Shu Zhang1, Elliot Staudt1, Tim Faltemier2, and Amit K. Roy-Chowdhury1 Department of Electrical and Computer Engineering, University of California, Riverside Progeny Systems Corporation" 3a192e0391c357124cd2ec2287b1706f523ecdfd,An Introduction to the 3rd Workshop on Egocentric (First-Person) Vision,"An Introduction to the 3rd Workshop on Egocentric (First-person) Vision Steve Mann, Kris M. Kitani, Yong Jae Lee, M. S. Ryoo, Alireza Fathi" 3affe6f9c2244f4b32c1c0f7d7f1d24770d40efe,Evaluating the Resilience of Face Recognition Systems against Malicious Attacks,"OMAR L., IVRISSIMTZIS I.: RESILIENCE OF FACE RECOGNITION SYSTEMS Evaluating the Resilience of Face Recognition Systems against Malicious Attacks Luma Omar1 Ioannis Ivrissimtzis1 School of Engineering and Computing Sciences Durham University Durham, UK" 3a28fe49e7a856ddd60d134696a891ed7bca5962,Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation,"Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation Tao Song, Leiyu Sun, Di Xie, Haiming Sun, Shiliang Pu Hikvision Research Institute" 3a846704ef4792dd329a5c7a2cb8b330ab6b8b4e,FACE-GRAB: Face recognition with General Region Assigned to Binary operator,"in any current or future media, for all other uses, © 2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any opyrighted component of this work in other works. Pre-print of article that appeared at the IEEE Computer Society Workshop on Biometrics 010. The published article can be accessed from: http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5544597" 3a13c964cc7adc5f010164ccb91d150457685a78,LIMO: Lidar-Monocular Visual Odometry,"LIMO: Lidar-Monocular Visual Odometry Johannes Graeter1, Alexander Wilczynski1 and Martin Lauer1" 3ab7f06cf8e7e7ca34427f81b766b823647ac117,To care or not to care: Analyzing the caregiver in a computational gaze following framework,"Proceedings of the 2004 International Conference on Development and Learning Editors: Jochen Triesch and Tony Jebara Publisher: UCSD Institute for Neural Computation Location: The Salk Institute for Biological Studies La Jolla California, USA ISBN: 0-615-12704-5" 3a37f57a9b94fff82ffea4e77803ebe5ebf6401b,ER7ST-algorithm for extracting facial expressions,"068 The International Arab Journal of Information Technology Vol. 13, No. 6B, 2016 ER7ST-Algorithm for Extracting Facial Expressions Ahmad Tayyar1, Shadi Al-Shehabi2, and Majida AlBakoor3 Department of Computer Science, Jerash University, Jordan Department of C omputer Engineeringm, Türk Hava Kurumu Üniversitesi, Turkey Department of Mathematics, Aleppo University, Syria" 3a280773e130abd44f44eb3181ea050e4e5b64f0,PRNU Variance Analysis for Morphed Face Image Detection,"⃝ IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked y each author’s copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder." 3a8023d206613c930cee8e9166fcbbfd743e6634,Enhancing Person Re-identification in a Self-Trained Subspace,"Enhancing Person Re-identification in a Self-trained Subspace Xun Yang, Meng Wang, Richang Hong, Qi Tian, Yong Rui" 3abd07b770c8cc0e3dc781611cab5e4e4aeb162c,"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","A Framework for Generating Controllable and Grounded Captions Show, Control and Tell: Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara University of Modena and Reggio Emilia" 3abbb484e93e87ae661a1a5c26990c61908398f7,Urban scene segmentation with laser-constrained CRFs,"Urban Scene Segmentation with Laser-Constrained CRFs Charika De Alvis Lionel Ott Fabio Ramos typically possess" 3a7f3d38157bf90cfb429c57bdf51933a6d5aabc,Shape Constraint Strategies: Novel Approaches and Comparative Robustness,"CERROLAZA,VILLANUEVA,CABEZA:SHAPECONSTRAINTSTRATEGIES Shape Constraint Strategies: Novel Approaches and Comparative Robustness Juan J. Cerrolaza Arantxa Villanueva Rafael Cabeza Biomedical Engineering Group. Department of Electrical and Electronics Engineering. Public University of Navarra. Navarra, SPAIN" 3abc833f4d689f37cc8a28f47fb42e32deaa4b17,Large Scale Retrieval and Generation of Image Descriptions,"Noname manuscript No. (will be inserted by the editor) Large Scale Retrieval and Generation of Image Descriptions Vicente Ordonez · Xufeng Han · Polina Kuznetsova · Girish Kulkarni · Margaret Mitchell · Kota Yamaguchi · Karl Stratos · Amit Goyal · Jesse Dodge · Alyssa Mensch · Hal Daum´e III · Alexander C. Berg · Yejin Choi · Tamara L. Berg Received: date / Accepted: date" 3a962138ede25d81a6d5aa42aa1abba649481f10,Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation,"Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation Christian Bailer1 Bertram Taetz1,2 Didier Stricker1,2 German Research Center for Artificial Intelligence (DFKI), 2University of Kaiserslautern" 3a032433fc93acd5a482e4194a49ee7f0fd86afd,Deposited in DRO : 28 April 2016 Version of attached le : Published Version Peer-review status of attached le : Peer-reviewed Citation for published item,"Durham Research Online Deposited in DRO: 8 April 2016 Version of attached le: Published Version Peer-review status of attached le: Peer-reviewed Citation for published item: Omar, Luma and Ivrissimtzis, Ioannis (2015) 'Evaluating the resilience of face recognition systems against malicious attacks.', in Proceedings of the 7th UK Computer Vision Student Workshop (BMVW). , 5.1-5.9. Further information on publisher's website: http://dx.doi.org/10.5244/C.29.BMVW.5 Publisher's copyright statement: Additional information: Use policy The full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that: • a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way" 3a24c276368fa63473078723ce4bc99c9ea36019,Stability comparison of dimensionality reduction techniques attending to data and parameter variations,"Eurographics Conference on Visualization (EuroVis) (2013) M. Hlawitschka and T. Weinkauf (Editors) Short Papers Stability comparison of dimensionality reduction techniques ttending to data and parameter variations Francisco J. García-Fernández1,2, Michel Verleysen2, John A. Lee2 and Ignacio Díaz1 University of Oviedo, Spain Université Catholique de Louvain, Belgium" 3aad63c3c049eedb1c6da4871faa90e797b933e8,Highway Networks for Visual Question Answering,"Highway Networks for Visual Question Answering Aaditya Prakash and James Storer Brandeis University" 3a0cceb1a10697e3e17738579d27708c9c3303a8,Data-Intensive Multimedia Semantic Concept Modeling using Robust Subspace Bagging and MapReduce,"Data-Intensive Multimedia Semantic Concept Modeling using Robust Subspace Bagging and MapReduce" 3abf8e5f1f5778b99890b193de59a3a9031e3691,Revisiting Linear Discriminant Techniques in Gender Recognition,"Revisiting Linear Discriminant Techniques in Gender Recognition Juan Bekios-Calfa, Jose´ M. Buenaposada, and Luis Baumela" 3a35154f765dcba4e3789a38346bf54bce69e336,Object Hallucination in Image Captioning,"Object Hallucination in Image Captioning Anna Rohrbach∗1, Lisa Anne Hendricks∗1, Kaylee Burns1 , Trevor Darrell1, Kate Saenko2 UC Berkeley, 2 Boston University" 3acb6b3e3f09f528c88d5dd765fee6131de931ea,Novel representation for driver emotion recognition in motor vehicle videos,"(cid:49)(cid:50)(cid:57)(cid:40)(cid:47)(cid:3)(cid:53)(cid:40)(cid:51)(cid:53)(cid:40)(cid:54)(cid:40)(cid:49)(cid:55)(cid:36)(cid:55)(cid:44)(cid:50)(cid:49)(cid:3)(cid:41)(cid:50)(cid:53)(cid:3)(cid:39)(cid:53)(cid:44)(cid:57)(cid:40)(cid:53)(cid:3)(cid:40)(cid:48)(cid:50)(cid:55)(cid:44)(cid:50)(cid:49)(cid:3)(cid:53)(cid:40)(cid:38)(cid:50)(cid:42)(cid:49)(cid:44)(cid:55)(cid:44)(cid:50)(cid:49)(cid:3)(cid:3) (cid:44)(cid:49)(cid:3)(cid:48)(cid:50)(cid:55)(cid:50)(cid:53)(cid:3)(cid:57)(cid:40)(cid:43)(cid:44)(cid:38)(cid:47)(cid:40)(cid:3)(cid:57)(cid:44)(cid:39)(cid:40)(cid:50)(cid:54)(cid:3) (cid:53)(cid:68)(cid:77)(cid:78)(cid:88)(cid:80)(cid:68)(cid:85)(cid:3)(cid:55)(cid:75)(cid:72)(cid:68)(cid:74)(cid:68)(cid:85)(cid:68)(cid:77)(cid:68)(cid:81)(cid:13)(cid:15)(cid:3)(cid:37)(cid:76)(cid:85)(cid:3)(cid:37)(cid:75)(cid:68)(cid:81)(cid:88)(cid:13)(cid:15)(cid:3)(cid:36)(cid:79)(cid:69)(cid:72)(cid:85)(cid:87)(cid:3)(cid:38)(cid:85)(cid:88)(cid:93)(cid:130)(cid:15)(cid:3)(cid:37)(cid:72)(cid:79)(cid:76)(cid:81)(cid:71)(cid:68)(cid:3)(cid:47)(cid:72)(cid:13)(cid:15)(cid:3)(cid:36)(cid:86)(cid:82)(cid:81)(cid:74)(cid:88)(cid:3)(cid:55)(cid:68)(cid:80)(cid:69)(cid:82)(cid:13)(cid:3) (cid:3) *Center for Research in Intelligent Systems, University of California, Riverside, CA 92521, USA (cid:130) Computer Perception Lab, California State University, Bakersfield, CA 93311, USA (cid:36)(cid:37)(cid:54)(cid:55)(cid:53)(cid:36)(cid:38)(cid:55)(cid:3) the background (cid:3) A novel feature representation of human facial expressions for emotion recognition is developed. The representation leveraged texture removal ability of Anisotropic Inhibited Gabor Filtering (AIGF) with the ompact representation of spatiotemporal local binary patterns. The emotion recognition system incorporated face detection and registration followed by the proposed feature representation: Local Anisotropic Inhibited Binary Patterns in Three Orthogonal" 3a0673199699cd51abe0f104ebe080f63d1b6d37,Sparse shape registration for occluded facial feature localization,"Sparse Shape Registration for Occluded Facial Feature Localization Fei Yang, Junzhou Huang and Dimitris Metaxas" 3ab036b680e8408ec74f78a918f3ffbf6c906d70,Saying What You're Looking For: Linguistics Meets Video Search,"Saying What You’re Looking For: Linguistics Meets Video Search Andrei Barbu∗ N. Siddharth∗ Jeffrey Mark Siskind∗" 3acdccd33e518f22dcfe36ee29c332a644afdb25,Automatic Detection of Facial Midline And Its Contributions To Facial Feature Extraction,"Electronic Letters on Computer Vision and Image Analysis 6(3):55-66, 2008 Automatic Detection of Facial Midline And Its Contributions To Facial Feature Extraction Nozomi NAKAO, Wataru OHYAMA, Tetsushi WAKABAYASHI and Fumitaka KIMURA Graduate School of Engineering, Mie University, 1577 Kurimamachiya–cho, Tsu–shi, Mie 514–8507, Japan Received 17 April 2007; revised 17 June 2007; accepted 17 September 2007" 3af28e9e9e883c235b6418a68bda519b08f9ae26,Implications of Adult Facial Aging on Biometrics,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." b516e9f933a573b957f21a8b9a617c8ebeaf1fea,Jawad Fusing Local Binary Patterns with Wavelet Features for Ethnicity Identification,"World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:7, No:7, 2013 Fusing Local Binary Patterns with Wavelet Features for Ethnicity Identification S. Hma Salah, H. Du, and N. Al-Jawad" b5c5a57f5ecd8e11cd47814d584daba53aa14d3c,SOSVR Team Description Paper Robocup 2017 Rescue Virtual Robot League,"SOSVR Team Description Paper Robocup 2017 Rescue Virtual Robot League Mahdi Taherahmadi, Sajjad Azami, MohammadHossein GohariNejad, Mostafa Ahmadi, and Saeed Shiry Ghidary Cognitive Robotics Lab, Amirkabir University of Technology (Tehran Polytechnic), No. 424, Hafez Ave., Tehran, Iran. P. O. Box" b503f481120e69b62e076dcccf334ee50559451e,Recognition of Facial Action Units with Action Unit Classifiers and an Association Network,"Recognition of Facial Action Units with Action Unit Classifiers and An Association Network Junkai Chen1, Zenghai Chen1, Zheru Chi1 and Hong Fu1,2 Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong Department of Computer Science, Chu Hai College of Higher Education, Hong Kong" b5160e95192340c848370f5092602cad8a4050cd,Video Classification With CNNs: Using the Codec as a Spatio-Temporal Activity Sensor,"Video Classification With CNNs: Using The Codec As A Spatio-Temporal Activity Sensor Aaron Chadha, Alhabib Abbas and Yiannis Andreopoulos, Senior Member, IEEE" b5f9d5be7561bb6eacee9012275b17c75696c388,A Teacher Student Network for Faster Video Classification,"Under review as a conference paper at ICLR 2019 A TEACHER STUDENT NETWORK FOR FASTER VIDEO CLASSIFICATION Anonymous authors Paper under double-blind review" b58417561ea400b60bd976104e43b1361e1314ba,Target Tracking In Real Time Surveillance Cameras and Videos,"Target Tracking In Real Time Surveillance Cameras and Videos Nayyab Naseem Mehreen Sirshar Department of Software Engineering Department of Software Engineering Fatima Jinnah Women University Fatima Jinnah Women University" b506aa23949b6d1f0c868ad03aaaeb5e5f7f6b57,Modeling Social and Temporal Context for Video Analysis,"UNIVERSITY OF CALIFORNIA RIVERSIDE Modeling Social and Temporal Context for Video Analysis A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Computer Science Zhen Qin June 2015 Dissertation Committee: Dr. Christian R. Shelton, Chairperson Dr. Tao Jiang Dr. Stefano Lonardi Dr. Amit Roy-Chowdhury" b573a57b3da678631bd78f25ecdeac7cd36fa617,A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms,"A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms Abdolrahim Kadkhodamohammadi1, Afshin Gangi1,2, Michel de Mathelin1, Nicolas Padoy1 ICube, University of Strasbourg, CNRS, IHU Strasbourg, France Radiology Department, University Hospital of Strasbourg, France {kadkhodamohammad, gangi, demathelin," b5f7b17b0feb3a1f3af60dce61fd9a9c6b067368,The Benefits of Dense Stereo for Pedestrian Detection,"The Benefits of Dense Stereo for Pedestrian Detection Christoph G. Keller, Markus Enzweiler, Marcus Rohrbach, David Fernández Llorca, Christoph Schnörr, and Dariu M. Gavrila" b510d66bc70772f89924863a8555d815aacf3bee,Modeling Marginal Distributions of Gabor Coefficients: Application to Biometric Template Reduction,"Modeling Marginal Distributions of Gabor Coef‌f‌icients: Application to Biometric Template Reduction Daniel Gonz´alez-Jim´enez and Jos´e Luis Alba-Castro(cid:2) Signal Theory and Communications Department University of Vigo, Spain" b5f5781cba3c3da807359a6f600aa19c666a3f81,Comparing Attention to Socially-Relevant Stimuli in Autism Spectrum Disorder and Developmental Coordination Disorder,"Journal of Abnormal Child Psychology https://doi.org/10.1007/s10802-017-0393-3 Comparing Attention to Socially-Relevant Stimuli in Autism Spectrum Disorder and Developmental Coordination Disorder Emma Sumner 1 & Hayley C. Leonard 2 & Elisabeth L. Hill 3 # The Author(s) 2018. This article is an open access publication" b5d1a7bc9f89ba9e8d99f6b151f83a4ff9220bb9,"A Framework for the Segmentation and Classification of 3D Point Clouds using Temporal, Spatial and Semantic Information", b5857b5bd6cb72508a166304f909ddc94afe53e3,SSIG and IRISA at Multimodal Person Discovery,"SSIG and IRISA at Multimodal Person Discovery Cassio E. dos Santos Jr1, Guillaume Gravier2, William Robson Schwartz1 Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil IRISA & Inria Rennes , CNRS, Rennes, France" b51e3d59d1bcbc023f39cec233f38510819a2cf9,"Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?","CBMM Memo No. 003 March 27, 2014 Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines? Qianli Liao1, Joel Z Leibo1, Youssef Mroueh1, Tomaso Poggio1" b5fffbc0e590ce67d485f1602c8158befcef9fa8,The use of hidden Markov models to verify the identity based on facial asymmetry,"Kubanek and Bobulski EURASIP Journal on Image and Video Processing (2017) 2017:45 DOI 10.1186/s13640-017-0193-2 EURASIP Journal on Image nd Video Processing RESEARCH Open Access The use of hidden Markov models to verify the identity based on facial asymmetry Mariusz Kubanek and Janusz Bobulski*" b58672881dd8112cd3e6dedebcf8367ce2c9d78b,Mechanistic Analytical Modeling of Superscalar In-Order Processor Performance,"Mechanistic Analytical Modeling of Superscalar In-Order Processor Performance MAXIMILIEN B. BREUGHE, STIJN EYERMAN, and LIEVEN EECKHOUT, Ghent University, Belgium Superscalar in-order processors form an interesting alternative to out-of-order processors because of their energy efficiency and lower design complexity. However, despite the reduced design complexity, it is nontrivial to get performance estimates or insight in the application–microarchitecture interaction without running slow, detailed cycle-level simulations, because performance highly depends on the order of instructions within the application’s dynamic instruction stream, as in-order processors stall on interinstruction dependences nd functional unit contention. To limit the number of detailed cycle-level simulations needed during design space exploration, we propose a mechanistic analytical performance model that is built from understanding the internal mechanisms of the processor. The mechanistic performance model for superscalar in-order processors is shown to be accurate with an verage performance prediction error of 3.2% compared to detailed cycle-accurate simulation using gem5. We lso validate the model against hardware, using the ARM Cortex-A8 processor and show that it is accurate within 10% on average. We further demonstrate the usefulness of the model through three case studies: (1) design space exploration, identifying the optimum number of functional units for achieving a given performance target; (2) program–machine interactions, providing insight into microarchitecture bottlenecks; nd (3) compiler–architecture interactions, visualizing the impact of compiler optimizations on performance. Categories and Subject Descriptors: C.0 [Computer Systems Organization]: General—Modeling of com-" b5cf931cf0bd606575bc793c0c8ec6d913d08bc6,"Geometric primitive feature extraction - concepts, algorithms, and applications","GEOMETRIC PRIMITIVE FEATURE EXTRACTION – CONCEPTS, ALGORITHMS, AND APPLICATIONS DILIP KUMAR PRASAD School of Computer Engineering A Thesis submitted to the Nanyang Technological University in fulfillment of the requirement for the degree of Doctor of Philosophy" b55d0c9a022874fb78653a0004998a66f8242cad,Hybrid Facial Representations for Emotion Recognition,"Hybrid Facial Representations for Emotion Recognition Woo-han Yun, DoHyung Kim, Chankyu Park, and Jaehong Kim Automatic facial expression recognition is a widely studied problem in computer vision and human-robot interaction. There has been a range of studies for representing facial descriptors for facial expression recognition. Some prominent descriptors were presented in the first facial expression recognition and analysis hallenge (FERA2011). In that competition, the Local Gabor Binary Pattern Histogram Sequence descriptor showed the most powerful description capability. In this paper, we introduce hybrid facial representations for facial expression recognition, which have more powerful description capability with lower dimensionality. Our descriptors consist of a block-based descriptor and a pixel- ased descriptor. The block-based descriptor represents the micro-orientation and micro-geometric structure information. The pixel-based descriptor represents texture information. We validate our descriptors on two public" b569f22ce779d221ec008c0baa354796d71e3d80,Image Classification for Arabic: Assessing the Accuracy of Direct English to Arabic Translations,"Image Classification for Arabic: Assessing the Accuracy of Direct English to Arabic Translations Information Systems Department, Prince Sattam Bin Abdulaziz university, Al Kharj, Saudi Arabia Abdulkareem Alsudais" b558be7e182809f5404ea0fcf8a1d1d9498dc01a,Bottom-up and top-down reasoning with convolutional latent-variable models,"Bottom-up and top-down reasoning with convolutional latent-variable models Peiyun Hu UC Irvine Deva Ramanan UC Irvine" b5fc4f9ad751c3784eaf740880a1db14843a85ba,Significance of image representation for face verification,"SIViP (2007) 1:225–237 DOI 10.1007/s11760-007-0016-5 ORIGINAL PAPER Significance of image representation for face verification Anil Kumar Sao · B. Yegnanarayana · B. V. K. Vijaya Kumar Received: 29 August 2006 / Revised: 28 March 2007 / Accepted: 28 March 2007 / Published online: 1 May 2007 © Springer-Verlag London Limited 2007" b599f323ee17f12bf251aba928b19a09bfbb13bb,Autonomous Quadcopter Videographer,"AUTONOMOUS QUADCOPTER VIDEOGRAPHER REY R. COAGUILA B.S. Universidad Peruana de Ciencias Aplicadas, 2009 A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science in the Department of Electrical Engineering and Computer Science in the College of Engineering and Computer Science t the University of Central Florida Orlando, Florida Spring Term Major Professor: Gita R. Sukthankar" b55853483873d3947e8c962f1152128059369d93,DoShiCo challenge: Domain shift in control prediction,"DoShiCo challenge: Domain Shift in Control prediction Klaas Kelchtermans∗ and Tinne Tuytelaars∗" b525a863eab597055e02351acfeab64754d22690,Pictorial Structures Revisited : Multiple Human Pose Estimation,"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE D Pictorial Structures Revisited: Multiple Human Pose Estimation Vasileios Belagiannis, Sikandar Amin, Mykhaylo Andriluka, Bernt Schiele, Nassir Navab, and Slobodan Ilic" b5ba0c50cfe2559f4197bb35cf50441118b768c8,audEERING's approach to the One-Minute-Gradual Emotion Challenge,"udEERING’s approach to the One-Minute-Gradual Emotion Challenge Andreas Triantafyllopoulos, Hesam Sagha, Florian Eyben, Bj¨orn Schuller udEERING GmbH, Gilching, Germany" b5476afccf97fc498f51170e65ac9cd9665fd2ce,Wide Range Face Pose Estimation by Modelling the 3D Arrangement of Robustly Detectable Sub-parts,"Wide Range Face Pose Estimation y Modelling the 3D Arrangement of Robustly Detectable Sub-Parts Thiemo Wiedemeyer1, Martin Stommel2 and Otthein Herzog3 TZI Center for Computing and Communication Technologies, University Bremen, Am Fallturm 1, 28359 Bremen, Germany" b5790f1bc586a77ff2cbea002b7ad2646e32af6b,Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis,"Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis Jorge Garc´ıa1, Niki Martinel2, Christian Micheloni2 and Alfredo Gardel1 Department of Electronics, University of Alcala, Alcal´a de Henares, Spain Department of Mathematics and Computer Science, University of Udine, Udine, Italy" b5f9c5af707f55d96b1d3d65d970270d35a60987,Comparison of face Recognition Algorithms on Dummy Faces,"The International Journal of Multimedia & Its Applications (IJMA) Vol.4, No.4, August 2012 Comparison of face Recognition Algorithms on Dummy Faces Aruni Singh, Sanjay Kumar Singh, Shrikant Tiwari Department of Computer Engineering, IT-BHU, Varanasi-India" b5d14fee9658877abbbfa760dd9765db0af86ba6,Swarm intelligence and evolutionary computation approaches for 2 D face recognition : a systematic review,"Revista Brasileira de Computação Aplicada, July, 2018 DOI: 10.5335/rbca.v10i2.8046 Vol. 10, No 2, pp. 2–17 Homepage: seer.upf.br/index.php/rbca/index TUTORIAL Swarm intelligence and evolutionary computation pproaches for 2D face recognition: a systematic review Guilherme Felippe Plichoski1, Chidambaram Chidambaram2 and Rafael Stubs Parpinelli1 Graduate Program in Applied Computing - State University of Santa Catarina, Joinville - SC - Brazil and Department of Production Engineering - State University of Santa Catarina, Joinville - SC - Brazil Received: 13/03/2018. Revised: 21/06/2018. Accepted: 23/06/2018." b5af4b9d68f1b9b2c2999a726f6d2fbb2a49a3bf,Modulating early visual processing by language,"Modulating early visual processing by language Harm de Vries∗ University of Montreal Florian Strub∗ Univ. Lille, CNRS, Centrale Lille, Jérémie Mary† Univ. Lille, CNRS, Centrale Lille, Inria, UMR 9189 CRIStAL Inria, UMR 9189 CRIStAL Hugo Larochelle Google Brain Olivier Pietquin DeepMind Aaron Courville University of Montreal, CIFAR Fellow" b58e71a3336193bed5785b2818a4fec85dd5f5ff,Object Detection and Tracking for Autonomous Navigation in Dynamic Environments,"Object detection and tracking for autonomous navigation in dynamic environments Andreas Ess · Konrad Schindler · Bastian Leibe · Luc Van Gool" b52886610eda6265a2c1aaf04ce209c047432b6d,Microexpression Identification and Categorization Using a Facial Dynamics Map,"Microexpression Identification and Categorization using a Facial Dynamics Map Feng Xu, Junping Zhang, James Z. Wang" b5dd744df6de73bd072b18d9108b79431a28c539,Gait Recognition With Shifted Energy Image and Structural Feature Extraction,"Gait Recognition with Shifted Energy Image nd Structural Feature Extraction Xiaxi Huang and Nikolaos V. Boulgouris, Senior Member, IEEE" d7eae9f76dcfa978b99eef430feb9420eac702eb,A Multi-Layer K-means Approach for Multi-Sensor Data Pattern Recognition in Multi-Target Localization,"A Multi-Layer K-means Approach for Multi-Sensor Data Pattern Recognition in Multi-Target Localization Samuel Silva, Rengan Suresh, Feng Tao, Johnathan Votion, Yongcan Cao" d7d09323bf8226f9cc06402dc3026fd4f1e75859,BDPCA plus LDA: a novel fast feature extraction technique for face recognition,"IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, VOL. 36, NO. 4, AUGUST 2006 BDPCA Plus LDA: A Novel Fast Feature Extraction Technique for Face Recognition Wangmeng Zuo, David Zhang, Senior Member, IEEE, Jian Yang, and Kuanquan Wang" d7e8672caecc7e4b17e8d9d3cbd673d402c7e7af,Robust Stereo-Based Person Detection and Tracking for a Person Following Robot,"Robust Stereo-Based Person Detection and Tracking for a Person Following Robot Junji Satake and Jun Miura Department of Information and Computer Sciences Toyohashi University of Technology" d7f19812ee77e508b314d0ac6ab49d05ac81e0d1,Active Visual-Based Detection and Tracking of Moving Objects from Clustering and Classification Methods,"Active Visual-based Detection and Tracking of Moving Objects from Clustering and Classification methods David Márquez-Gámez Michel Devy CNRS; LAAS; Université de Toulouse 7 avenue du Colonel Roche, F-31077 Toulouse Cedex, France" d7f3836f2d28adf15fc809bd4f90afb1f61ba8e0,Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images,"Article Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images Nicolas Audebert 1,2,*, Bertrand Le Saux 1 and Sébastien Lefèvre 2 ONERA, The French Aerospace Lab, F-91761 Palaiseau, France; Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), University Bretagne Sud, UMR 6074, F-56000 Vannes, France; * Correspondence: Academic Editors: Norman Kerle, Markus Gerke and Prasad S. Thenkabail Received: 28 December 2016; Accepted: 7 April 2017; Published: 13 April 2017" d745eaeb096fbf61ac0694e447acd2081a08b084,Ðáñáêïëïýèçóç øõ÷ïóùìáôéêÞò êáôÜóôáóçò ïäçãïý ìå,"Ðáñáêïëïýèçóç øõ÷ïóùìáôéêÞò êáôÜóôáóçò ïäçãïý ìå ÷ñÞóç âéïóçìÜôùí Ç ÄÉÄÁÊÔÏÑÉÊÇ ÄÉÁÔÑÉÂÇ õðïâÜëëåôáé óôçí ïñéóèåßóá áðü ôçí ÃåíéêÞ ÓõíÝëåõóç ÅéäéêÞò Óýíèåóçò ôïõ ÔìÞìáôïò ÐëçñïöïñéêÞò ÅîåôáóôéêÞ ÅðéôñïðÞ áðü ôïí Ãåþñãéï ÑÞãá ùò ìÝñïò ôùí Õðï÷ñåþóåùí ãéá ôç ëÞøç ôïõ ÄÉÄÁÊÔÏÑÉÊÏÕ ÄÉÐËÙÌÁÔÏÓ ÓÔÇÍ ÐËÇÑÏÖÏÑÉÊÇ ÄåêÝìâñéïò 2009" d7da0f595d135474cc2193d382b22458b313cdbf,Multi-View Constraint Propagation with Consensus Prior Knowledge.,Multi-View Constraint Propagation with Consensus Prior Knowledge d7c659ce0442bf1047e7d2e942837b18105f6f47,Depth-Adaptive Deep Neural Network for Semantic Segmentation,"Depth Adaptive Deep Neural Network for Semantic Segmentation Byeongkeun Kang, Yeejin Lee, and Truong Q. Nguyen, Fellow, IEEE" d7ed878c08c90186e3bf607c20ff943834ad0d68,Semantic Data Integration,"Semantic Data Integration Michelle Cheatham and Catia Pesquita" d7144bc7d91841963b037f210f9356d28f76e70e,A comparison of features for regression-based driver head pose estimation under varying illumination conditions,"A COMPARISON OF FEATURES FOR REGRESSION-BASED DRIVER HEAD POSE ESTIMATION UNDER VARYING ILLUMINATION CONDITIONS Dimitri J. Walger1, Toby P. Breckon2, Anna Gaszczak3, Thomas Popham3 Cranfield University, Bedfordshire, UK 2Durham University, Durham, UK Jaguar Land Rover, Warwickshire, UK" d767c97af96461eac76fb897a0eec35804f0398d,Learn to See by Events: RGB Frame Synthesis from Event Cameras,"Learn to See by Events: RGB Frame Synthesis from Event Cameras Stefano Pini, Guido Borghi, Roberto Vezzani, Rita Cucchiara University of Modena and Reggio Emilia Figure 1: Sample frames synthesized by the proposed framework. Given an initial RGB frame at time t0 and a set of following event frames at time t1, ..., tn as input, the proposed framework accordingly synthesizes a RGB frame for each time step." d7f7eb0fbe3339d13f5a6a23df0fd27fdb357d48,Intention-Aware Multi-Human Tracking for Human-Robot Interaction via Particle Filtering over Sets,"Intention-Aware Multi-Human Tracking for Human-Robot Interaction via Particle Filtering over Sets Aijun Bai Univ. of Sci. & Tech. of China Reid Simmons Carnegie Mellon Univ. Manuela Veloso Carnegie Mellon Univ. The Approach The ability for an autonomous robot to track and identify multiple humans and understand their intentions is crucial for socialized human-robot interactions in dynamic envi- ronments (Michalowski and Simmons 2006). Take CoBot (Rosenthal, Biswas, and Veloso 2010) trying to enter an ele- vator as an example. When the elevator door opens, suppose there are multiple humans occupied, CoBot needs to track each human’s state and intention in terms of whether he/she is going to exit the elevator or not. For the purposes of safely nd friendly interacting with humans, CoBot can only make the decision to enter the elevator when any human who in-" d79f9ada35e4410cd255db39d7cc557017f8111a,Evaluation of accurate eye corner detection methods for gaze estimation,"Journal of Eye Movement Research 7(3):3, 1-8 Evaluation of accurate eye corner detection methods for gaze estimation Jose Javier Bengoechea Public University of Navarra, Spain Juan J. Cerrolaza Childrens National Medical Center, USA Arantxa Villanueva Public University of Navarra, Spain Rafael Cabeza Public University of Navarra, Spain Accurate detection of iris center and eye corners appears to be a promising pproach for low cost gaze estimation. In this paper we propose novel eye inner corner detection methods. Appearance and feature based segmentation pproaches are suggested. All these methods are exhaustively tested on a realistic dataset containing images of subjects gazing at different points on a screen. We have demonstrated that a method based on a neural network presents the est performance even in light changing scenarios." d7d9fa9a5a57f9f3da7ab2c87ca58127665774cc,Improving Shadow Suppression for Illumination Robust Face Recognition,"Improving Shadow Suppression for Illumination Robust Face Recognition Wuming Zhang, Xi Zhao, Jean-Marie Morvan and Liming Chen, Senior Member, IEEE" d74c6e6fbd8952cbad96013e227374c903797162,With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning,"With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning Bolun Wang Yuanshun Yao Bimal Viswanath Haitao Zheng UC Santa Barbara University of Chicago Virginia Tech University of Chicago Ben Y. Zhao University of Chicago" d75d074c11a62780b836376249391da39660cad6,Task Scheduling Frameworks for Heterogeneous Computing Toward Exascale,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 9, No. 10, 2018 Task Scheduling Frameworks for Heterogeneous Computing Toward Exascale Suhelah Sandokji1, Fathy Eassa2 Faculty of Computing and Information Technology, KAU Jeddah ,Saudi Arabia studies consider partitioning" d745cf8c51032996b5fee6b19e1b5321c14797eb,Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features,"Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features Douglas Gray and Hai Tao University of California, Santa Cruz {dgray, http://vision.soe.ucsc.edu/" d7d2a1d42f0e3182d538cf8fb4d55f3e9d7ce779,"Setting an attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels","Setting an attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels Sagi Eppel1" d7d6200e41d574e2f3ddd9ded299613683519c7c,Accurate Iris Recognition at a Distance Using Stabilized Iris Encoding and Zernike Moments Phase Features,"IEEE Trans. Image Processing, 2014 Accurate Iris Recognition at a Distance Using Stabilized Iris Encoding and Zernike Moments Phase Features Chun-Wei Tan, Ajay Kumar" d7612e01c10f351a3e2ff1a57465c3d17ddbb193,Rain Streaks Removal in an Image by using Image Decomposition,"International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013): 6.14 | Impact Factor (2015): 6.391 Rain Streaks Removal in an Image by using Image Decomposition Priyanka A. Chougule1, J. A. Shaikh2 Research Student, Electronics Dept., PVPIT, Budhgaon Associate Professor, Electronics Dept. PVPIT, Budhgaon" d76f68c2d0a45ab224065d57836bf3da360c82f2,Learning to Segment Human by Watching YouTube,"Learning to Segment Human by Watching YouTube Xiaodan Liang, Yunchao Wei, Liang Lin, Yunpeng Chen, Xiaohui Shen, Jianchao Yang, Shuicheng Yan" d78dde04ac4215ed0ed6f2bd5d85094b389d7f5e,A Warping Window Approach to Real-time Vision-based Pedestrian Detection in a Truck's Blind Spot Zone,"A warping window approach to real-time vision-based pedestrian detection in a truck’s blind spot zone Kristof Van Beeck1, Toon Goedem´e1;2 and Tinne Tuytelaars2 IIW/EAVISE, Lessius Mechelen - Campus De Nayer, J. De Nayerlaan 5, 2860, Sint-Katelijne-Waver, Belgium ESAT/PSI-VISICS, KU Leuven, IBBT, Kasteelpark Arenberg 10, 3100, Heverlee, Belgium fkristof.vanbeeck, Keywords: Computer vision: Pedestrian tracking: Real-time: Active safety systems" d7b6bbb94ac20f5e75893f140ef7e207db7cd483,griffith . edu . au Face Recognition across Pose : A Review,"Griffith Research Online https://research-repository.griffith.edu.au Face Recognition across Pose: A Review Author Zhang, Paul, Gao, Yongsheng Published Journal Title Pattern Recognition https://doi.org/10.1016/j.patcog.2009.04.017 Copyright Statement Copyright 2009 Elsevier. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher. Please refer to the journal's website for access to the definitive, published version. Downloaded from http://hdl.handle.net/10072/30193" d7a0f9ab321e728b981e12775b4906f55d3aab15,3 D Object Reconstruction using Computer Vision : Reconstruction and Characterization Applications for External Human Anatomical Structures,"D Object Reconstruction using Computer Vision: Reconstruction nd Characterization Applications for External Human Anatomical Structures Teresa Cristina de Sousa Azevedo BSc in Electrical and Computer Engineering by Faculdade de Engenharia da Universidade do Porto (2002) MSc in Biomedical Engineering by Faculdade de Engenharia da Universidade do Porto (2007) Thesis submitted for the fulfilment of the requirements for the PhD degree in Informatics Engineering by Faculdade de Engenharia da Universidade do Porto Supervisor: João Manuel R. S. Tavares Associate Professor of the Department of Mechanical Engineering Faculdade de Engenharia da Universidade do Porto Co-supervisor: Mário A. P. Vaz Associate Professor of the Department of Mechanical Engineering Faculdade de Engenharia da Universidade do Porto" d78b190f98f9630cab261eabc399733af052f05c,Unsupervised Deep Domain Adaptation for Pedestrian Detection, d7d166aee5369b79ea2d71a6edd73b7599597aaa,Fast Subspace Clustering Based on the Kronecker Product,"Fast Subspace Clustering Based on the Kronecker Product Lei Zhou1, Xiao Bai1, Xianglong Liu1, Jun Zhou2, and Hancock Edwin3 Beihang University 2Grif‌f‌ith University 3University of York, UK" d708ce7103a992634b1b4e87612815f03ba3ab24,FCVID : Fudan-Columbia Video Dataset,"FCVID: Fudan-Columbia Video Dataset Yu-Gang Jiang, Zuxuan Wu, Jun Wang, Xiangyang Xue, Shih-Fu Chang Available at: http://bigvid.fudan.edu.cn/FCVID/ OVERVIEW Recognizing visual contents in unconstrained videos has become a very important problem for many ap- plications, such as Web video search and recommen- dation, smart content-aware advertising, robotics, etc. Existing datasets for video content recognition are either small or do not have reliable manual labels. In this work, we construct and release a new Inter- net video dataset called Fudan-Columbia Video Dataset (FCVID), containing 91,223 Web videos (total duration ,232 hours) annotated manually according to 239 ategories. We believe that the release of FCVID can stimulate innovative research on this challenging and important problem. COLLECTION AND ANNOTATION The categories in FCVID cover a wide range of topics like social events (e.g., “tailgate party”), procedural" d7c6e4348542fd2b5e64a73d9c1fd0172e2b1774,Grounding language acquisition by training semantic parsers using captioned videos,"Grounding language acquisition by training semantic parsers using captioned videos Candace Ross CSAIL, MIT Andrei Barbu CSAIL, MIT Yevgeni Berzak BCS, MIT Battushig Myanganbayar CSAIL, MIT" d73b16b1a4f96eda9abcecaf6425b17fd02c631f,A Survey Paper on Retrieval of Deterministic Data with Ranking Strategy,"International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013): 6.14 | Impact Factor (2015): 6.391 A Survey Paper on Retrieval of Deterministic Data with Ranking Strategy Ashish S Mutrak1, Kishor Shedge2 Student, Master of Engineering, Department of Computer Engineering, Sir Visvesvaraya Institute of Technology, Chincholi, Sinner Assistant Professor, Department of Computer Engineering, Sir Visvesvaraya Institute of Technology, Chincholi, Sinner" d7f153112c51923c8e78036fc694220c9d4bf4bc,The 2018 DAVIS Challenge on Video Object Segmentation,"The 2018 DAVIS Challenge on Video Object Segmentation Sergi Caelles, Alberto Montes, Kevis-Kokitsi Maninis, Yuhua Chen, Luc Van Gool, Federico Perazzi, and Jordi Pont-Tuset" d7b850537ccf33cabc2f0b231553aad79ad43aa8,Grid Map based Free Space Estimation using Stereo Vision,"Grid Map based Free Space Estimation using Stereo Vision Hannes Harms1, Eike Rehder1 and Martin Lauer1" d7e8c6da1a95f41d8097b7b713890ccde13ef1d8,Development of an Efficient Face Recognition System Based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 2284ab73ac9c913328349de54f9892082f16dd3b,"Biometrics at the Frontiers : Assessing the Impact on Society For the European Parliament Committee on Citizens ' Freedoms and Rights , Justice and Home Affairs ( LIBE ) February","Biometrics at the Frontiers: Assessing the impact on Society Institute for Prospective Technological Studies Directorate General Joint Research Centre European Commission Biometrics at the Frontiers: Assessing the Impact on Society For the European Parliament Committee on Citizens' Freedoms and Rights, Justice and Home Affairs (LIBE) February 2005 IPTS, Edificio Expo-WTC, C/ Inca Garcilaso, s/n, E-41092, Seville, Spain Tel: +34 954488281, Fax: +34 954488208 EC-DG JRC-IPTS Page 1 of 166" 229bce6384ae16a388881e766bfa5a672b61dc9b,Application of Video Scene Semantic Recognition Technology in Smart Video,"ISSN 1330-3651 (Print), ISSN 1848-6339 (Online) https://doi.org/10.17559/TV-20180620082101 Original scientific paper Application of Video Scene Semantic Recognition Technology in Smart Video Lele QIN, Lihua KANG" 224d4cf75e8baf32a795f38ee8ccfdf82e4c5a70,Identifying Exceptional Descriptions of People Using Topic Modeling and Subgroup Discovery,"Identifying Exceptional Descriptions of People using Topic Modeling and Subgroup Discovery Andrew T. Hendrickson, Jason Wang, and Martin Atzmueller Tilburg University, 5037AB, the Netherlands {a.hendrickson, y.w.wang," 22043cbd2b70cb8195d8d0500460ddc00ddb1a62,Separability-Oriented Subclass Discriminant Analysis,"Separability-Oriented Subclass Discriminant Analysis Huan Wan, Hui Wang, Gongde Guo, Xin Wei" 227b18fab568472bf14f9665cedfb95ed33e5fce,Compositional Dictionaries for Domain Adaptive Face Recognition,"Compositional Dictionaries for Domain Adaptive Face Recognition Qiang Qiu, and Rama Chellappa, Fellow, IEEE." 22264e60f1dfbc7d0b52549d1de560993dd96e46,UnitBox: An Advanced Object Detection Network,"UnitBox: An Advanced Object Detection Network Jiahui Yu1,2 Yuning Jiang2 Zhangyang Wang1 Zhimin Cao2 Thomas Huang1 University of Illinois at Urbana−Champaign Megvii Inc {jyu79, zwang119, {jyn," 220b815229ac5557b3360f96b3afd9453635088d,Artificial Intelligence with Stereo Vision Algorithms and its Methods,"International Conference on Recent Trends in Information Technology and Computer Science (IRCTITCS) 2011 Proceedings published in International Journal of Computer Applications® (IJCA) Artificial Intelligence with Stereo Vision Algorithms and its Methods Sahil S.Thakare#1, Rupesh P. Arbal#2, Makarand R. Shahade*3 #1,2Student, Department of IT, Jawaharlal Darda Institute of Engineering & Technology, Yavatmal *Asst. Professor, Department of IT, Jawaharlal Darda Institute of Engineering & Technology, Yavatmal (MS) INDIA *Third Author (MS) INDIA" 2251a88fbccb0228d6d846b60ac3eeabe468e0f1,Matrix-Based Kernel Subspace Methods,"Matrix-Based Kernel Subspace Methods S. Kevin Zhou Integrated Data Systems Department Siemens Corporate Research 755 College Road East, Princeton, NJ 08540 Email:" 22fb836a593267d9ff09a4d12aa5b4a6fd52c81e,Brief report: Visual processing of faces in individuals with fragile X syndrome: an eye tracking study.,"J Autism Dev Disord (2009) 39:946–952 DOI 10.1007/s10803-009-0744-1 B R I E F R E P O R T Brief Report: Visual Processing of Faces in Individuals with Fragile X Syndrome: An Eye Tracking Study Faraz Farzin Æ Susan M. Rivera Æ David Hessl Published online: 28 April 2009 Ó The Author(s) 2009. This article is published with open access at Springerlink.com" 229e105fd4d34815e476702dd5ca4362943c475d,WildDash - Creating Hazard-Aware Benchmarks,"WildDash - Creating Hazard-Aware Benchmarks Oliver Zendel, Katrin Honauer, Markus Murschitz, Daniel Steininger, and Gustavo Fern´andez Dom´ınguez AIT, Austrian Institute of Technology, Giefinggasse 4, 1210, Vienna, Austria {oliver.zendel, katrin.honauer.fl, markus.murschitz, daniel.steininger," 22c01d758a4941c01239fa8facdb3407559132ed,Segmentation and Restoration of Images on Surfaces by Parametric Active Contours with Topology Changes,"Segmentation and Restoration of Images on Surfaces by Parametric Active Contours with Topology Changes Heike Benninghoff∗ and Harald Garcke†" 22ee43dbd2bdefbc8945d453c6cd453f49ab5eb7,Urban Traffic Surveillance in Smart Cities Using Radar Images,"Urban Traffic Surveillance in Smart Cities Using Radar Images J. S´anchez-Oro, David Fern´andez-L´opez, R. Cabido, Antonio S. Montemayor, and Juan Jos´e Pantrigo Dept. Ciencias de la Computaci´on Universidad Rey Juan Carlos Spain" 22532c6e38ded690dc1420f05c18e23f6f24804d,Chapter 5 Genetic & Evolutionary Biometrics,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,700 08,500 .7 M Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact" 2279cae83716e2a00181593a7b10966020dd11d1,Real-time head pose estimation and facial feature localization using a depth sensor and triangular surface patch features,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Real-time head pose estimation and facial feature localization using a depth sensor and triangular surface patch features Papazov, C.; Marks, T.K.; Jones, M.J. TR2015-069 June 2015" 227a312324edd41892eb2c1dbc4bf8d94984a326,Deep Learning Based Vehicle Make-Model Classification,"Deep Learning Based Vehicle Make-Model Classification Burak Satar1 and Ahmet Emir Dirik2(cid:63) Uludag University, Bursa, Turkey Department of Electrical-Electronics Engineering Uludag University, Bursa, Turkey Department of Computer Engineering" 22dabd4f092e7f3bdaf352edd925ecc59821e168,Exploiting side information in locality preserving projection,"Deakin Research Online This is the published version: An, Senjian, Liu, Wanquan and Venkatesh, Svetha 2008, Exploiting side information in locality preserving projection, in CVPR 2008 : Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Washington, D. C., pp. 1-8. Available from Deakin Research Online: http://hdl.handle.net/10536/DRO/DU:30044576 Reproduced with the kind permissions of the copyright owner. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Copyright : 2008, IEEE" 22f8148e43c50341bad686d7fccb425b0682e667,Facial ethnicity classification based on boosted local texture and shape descriptions,"Facial Ethnicity Classification based on Boosted Local Texture and Shape Descriptions Huaxiong Ding, Di Huang, IEEE Member, Yunhong Wang, IEEE Member, Liming Chen, IEEE Member," 22029beb936c9871757813758c5ae3e5820260c9,Proximity Distribution Kernels for Geometric Context in Category Recognition,"Proximity Distribution Kernels for Geometric Context in Category Recognition Haibin Ling∗ Stefano Soatto Integrated Data Systems Department Computer Science Department Siemens Corporate Research, Princeton, NJ University of California, Los Angeles, CA haibin.ling siemens.com soatto cs.ucla.edu" 227094e85ae30794d03f3cee426f40877ac2b11b,Performance Improvements in Face Classification using Random Forest,"Vatsal Vishwakarma, Abhishek Kumar Srivastava / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 2, Issue 3, May-Jun 2012, pp.2384-2388 Performance Improvements in Face Classification using Random Forest Vatsal Vishwakarma*, Abhishek Kumar Srivastava ** *(Department of Electronics and Communication, Lovely Professional University, Jalandhar , India.) ** (Department of Electronics and Communication, Lovely Professional University, Jalandhar , India.)" 2270c94d3f9d9451b3d337aa5ba2d5681cb98497,Evaluation of GIST descriptors for web-scale image search,"Evaluation of GIST descriptors for web-scale image search Matthijs Douze, Hervé Jégou, Sandhawalia Harsimrat, Laurent Amsaleg, Cordelia Schmid To cite this version: Matthijs Douze, Hervé Jégou, Sandhawalia Harsimrat, Laurent Amsaleg, Cordelia Schmid. Evaluation of GIST descriptors for web-scale image search. CIVR 2009 - International Conference on Image and Video Retrieval, Jul 2009, Santorini, Greece. ACM, pp.19:1-8, 2009, <10.1145/1646396.1646421>. HAL Id: inria-00394212 https://hal.inria.fr/inria-00394212 Submitted on 23 Mar 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents" 2230848e506553159e0edfc20472b8cd6084be17,Vision Based Hand Puppet,"ENTERFACE’10, JULY 12TH - AUGUST 6TH, AMSTERDAM, THE NETHERLANDS. Vision Based Hand Puppet Cem Keskin, ˙Ismail Arı, Tolga Eren, Furkan Kırac¸, Lukas Rybok, Hazım Ekenel, Rainer Stiefelhagen, Lale Akarun" 22e4e64c1172c90ba23f634d850931ee5f9a972f,Robust Bayesian fitting of 3D morphable model,"Robust Bayesian Fitting of 3D Morphable Model Claudia Arellano and Rozenn Dahyot School of Computer Science and Statistics Trinity College Dublin, Ireland 7th November 2013" 22c951d542f4d03c718bd58f8ec1b40239af6974,Neural Learning Methods for Visual Object Detection I Foundations 13,"Neural learning methods for visual object detection (Neuronale Lernverfahren zur visuellen Objekterkennung) Dissertation zur Erlangung des Grades ”Doktor der Naturwissenschaften” n der Fakult¨at f¨ur Physik und Astronomie der Ruhr-Universit¨at Bochum vorgelegt von Alexander Rainer Tassilo Gepperth m 19.April 2006" 22086b3c772ba638e7d50b10bcf544abd93c9305,Face Localization based on Skin Color,"International Journal of Computer Applications (0975 – 8887) Volume 109 – No. 12, January 2015 Face Localization based on Skin Color M. Mahadevi Research Scholar, M.S. University S.D.N.B. Vaishnav College for Women Chrompet,Chennai-44" 22aa426aeffb77339646cc03da8e94de22396efc,S HAKES HAKE REGULARIZATION OF 3-BRANCH RESIDUAL NETWORKS,"Workshop track - ICLR 2017 SHAKE-SHAKE RESIDUAL NETWORKS REGULARIZATION OF -BRANCH Xavier Gastaldi" 22137ce9c01a8fdebf92ef35407a5a5d18730dde,Recognition of Faces from single and Multi-View Videos, 227b1a09b942eaf130d1d84cdcabf98921780a22,Multi-feature shape regression for face alignment,"Yang et al. EURASIP Journal on Advances in Signal Processing (2018) 2018:51 https://doi.org/10.1186/s13634-018-0572-6 EURASIP Journal on Advances in Signal Processing R ES EAR CH Multi-feature shape regression for face lignment Wei-Jong Yang, Yi-Chen Chen, Pau-Choo Chung and Jar-Ferr Yang* Open Access" 22fdd8d65463f520f054bf4f6d2d216b54fc5677,Efficient Small and Capital Handwritten Character Recognition with Noise Reduction,"International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 3, Issue 8, August 2013) Efficient Small and Capital Handwritten Character Recognition with Noise Reduction Beerendra Kumar Pal, Prof. Shailendra Tiwari, Prof. Sandeep Kumar Department of Computer Science Engg., IES College of Technology, Bhopal" 22e189a813529a8f43ad76b318207d9a4b6de71a,What will Happen Next? Forecasting Player Moves in Sports Videos,"What will Happen Next? Forecasting Player Moves in Sports Videos Panna Felsen UC Berkeley, STATS Pulkit Agrawal UC Berkeley Jitendra Malik UC Berkeley" 22d656a6395e22473b8764eddff759ea03f48032,Nonrigid Image Registration Using Higher-Order MRF Model with Dense Local Descriptor,"Nonrigid Image Registration Using Higher-Order MRF Model with Dense Local Descriptor Dongjin Kwon1, Kyong Joon Lee1, Il Dong Yun2, and Sang Uk Lee1 School of EECS, ASRI, Seoul Nat’l Univ., Seoul, 151-742, Korea School of EIE, Hankuk Univ. of F. S., Yongin, 449-791, Korea fdjk," 22634b09c3c83f4a959f4f732b03ec3c92808094,DeepMatching: Hierarchical Deformable Dense Matching,"Noname manuscript No. (will be inserted by the editor) DeepMatching: Hierarchical Deformable Dense Matching Philippe Weinzaepfel Jerome Revaud Cordelia Schmid INRIA Zaid Harchaoui the date of receipt and acceptance should be inserted later" 2258e01865367018ed6f4262c880df85b94959f8,Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics,"Hindawi Publishing Corporation EURASIP Journal on Image and Video Processing Volume 2008, Article ID 246309, 10 pages doi:10.1155/2008/246309 Research Article Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics Keni Bernardin and Rainer Stiefelhagen Interactive Systems Lab, Institut f¨ur Theoretische Informatik, Universit¨at Karlsruhe, 76131 Karlsruhe, Germany Correspondence should be addressed to Keni Bernardin, Received 2 November 2007; Accepted 23 April 2008 Recommended by Carlo Regazzoni Simultaneous tracking of multiple persons in real-world environments is an active research field and several approaches have een proposed, based on a variety of features and algorithms. Recently, there has been a growing interest in organizing systematic evaluations to compare the various techniques. Unfortunately, the lack of common metrics for measuring the performance of multiple object trackers still makes it hard to compare their results. In this work, we introduce two intuitive and general metrics to llow for objective comparison of tracker characteristics, focusing on their precision in estimating object locations, their accuracy in recognizing object configurations and their ability to consistently label objects over time. These metrics have been extensively used in two large-scale international evaluations, the 2006 and 2007 CLEAR evaluations, to measure and compare the performance of multiple object trackers for a wide variety of tracking tasks. Selected performance results are presented and the advantages and" 22cf367d14e646914cc959bbcd402df0c20cd0dc,Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results,"Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results Michel Fornaciali, Micael Carvalho, Fl´avia Vasques Bittencourt, Sandra Avila, Eduardo Valle" 220f8088f2fc1ddd9df1a0b583d3d01cb929ee8d,ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images,"Noname manuscript No. (will be inserted by the editor) ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images Kui Jia · Tsung-Han Chan · Zinan Zeng · Shenghua Gao Gang Wang · Tianzhu Zhang · Yi Ma" 223ec77652c268b98c298327d42aacea8f3ce23f,TR-CS-1102 Acted Facial Expressions In The Wild Database,"TR-CS-11-02 Acted Facial Expressions In The Wild Database Abhinav Dhall, Roland Goecke, Simon Lucey, Tom Gedeon September 2011 ANU Computer Science Technical Report Series" 22c89775cb5309eae5ac1f9ce9d1c2d569439492,Face recognition based on extended separable lattice 2-D HMMS,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 224ffad672f7e6c7995780eb9bd3c8a141cb25cd,Understanding pedestrian behaviors from stationary crowd groups,"Understanding Pedestrian Behaviors from Stationary Crowd Groups Shuai Yi1, Hongsheng Li1,2, Xiaogang Wang1 Department of Electronic Engineering, The Chinese University of Hong Kong. School of Electronic Engineering, University of Electronic Science and Technology of China. Pedestrian behavior modeling and analysis is important for crowd scene un- derstanding and has various applications in video surveillance. Stationary rowd groups are a key factor influencing pedestrian walking patterns but was largely ignored in literature. As shown in Figure 1 (d), the walking path of a pedestrian (black curve) is affected by a stationary crowd group. Without modeling the stationary crowd group, it is difficult to explain why the pedestrian detours when approaching the destination (Figure 1 (f)). Sta- tionary crowd groups can serve as multiple roles (Figure 1 (e)) for different pedestrians, such as source, destination, or obstacle. Moreover, the spatial distribution of stationary crowd groups might change over time (Figure 1 (a)-(d)), which leads to the dynamic variations of traffic patterns. In our work, the factor of stationary crowd groups is introduced for the first time to model pedestrian behaviors. The Proposed Pedestrian Behavior Model A general energy map M is proposed to model the traveling difficulty of every location of the scene. It can be modeled with three channels calculated" 22355c1b0a8af6b9e1cc2ef3fd5dce08edc48dd5,Learning to Detect Vehicles by Clustering Appearance Patterns,"(cid:13)2015IEEE.Personaluseofthismaterialispermitted.PermissionfromIEEEmustbeobtainedforallotheruses,inanycurrentorfuturemedia,includingreprinting/republishingthismaterialforadvertisingorpromotionalpurposes,creatingnewcollectiveworks,forresaleorredistributiontoserversorlists,orreuseofanycopyrightedcomponentofthisworkinotherworks." 225f09fd8103626c486ea9bfcd3770858dcf1906,Strangeness Based Feature Selection for Part Based Recognition,"Strangeness Based Feature Selection for Part Based Recognition Fayin Li and Jana Koˇseck´a and Harry Wechsler George Mason Univerity 400 University Dr. Fairfax, VA 22030 USA" 222d86787abed673600f1054796367f439c2eec1,Etworks via a Ttention T Ransfer,"Published as a conference paper at ICLR 2017 PAYING MORE ATTENTION TO ATTENTION: IMPROVING THE PERFORMANCE OF CONVOLUTIONAL NEURAL NETWORKS VIA ATTENTION TRANSFER Sergey Zagoruyko, Nikos Komodakis Universit´e Paris-Est, ´Ecole des Ponts ParisTech Paris, France" 2251a1efad0cef802fd64fc79cc1b7007b64f425,Estimating 3D Pose via Stochastic Search and Expectation Maximization,"-IJE=JEC !, 2IA LE= 5J?D=IJE? 5A=H?D -NFA?J=JE =NEE=JE *A ,=K>AO :E=CDK= :EA ,AF=HJAJ B +FKJAH 5?EA?A 5M=IA= 7ELAHIEJO 5) &22 *,=K>AO::EA(IM=IA==?K )>IJH=?J 1 JDEI F=FAH = =FFH=?D EI J AIJE=JA !, FIA KIEC = F=HJ IJ?D=IJE? ) HAFHAIAJ=JE B JDA DK= EI LAH EJI JD=J AFOI BK A=HJ >AJMAA EJI 6DEI HAFHAIAJ=JE EI =C=EIJ = FFK=H =JAH=JELA LAH F=HJI KIEC E> J EI IDM JD=J KIEC BK E> HAIKJI E = JD=J EI B=H HA HAFHAIAJ=JELA B JDA HECE= JH=EEC .KH JDAHHA EJ EI JD=J -NFA?J=JE =NEE=JE EI IKEJ=>A BH AIJE=JEC !, FIA >AJJAH ?LAHCA?A EI MDA KIEC BK E> 6 JDA A?=?O B JDA EJ EI J JDA B !, FIA AIJE=JE KIEC = IECA ?K=H E=CA 3K=JEJ=JELA HAIKJI =HA KIEC JDA 0K=-L= MDE?D ?H JD=J JDA KJFAHBHI JD=J B JDA ? FAJEC F=HJ 1 JDEI MH KIJ = IECA EI A=HJ J" 225fbfd99465033e993460a1bc838a87fbf42346,Gaussian-Bernoulli deep Boltzmann machine,"Gaussian-Bernoulli Deep Boltzmann Machine KyungHyun Cho, Tapani Raiko and Alexander Ilin Department of Information and Computer Science, Aalto University School of Science Email:" 221debbd7878ed303eaa4666f8df04a48e4c5070,Making Computer Vision Computationally Efficient,"Making computer vision computationally efficient Narayanan Sundaram Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2012-106 http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-106.html May 11, 2012" 228558a2a38a6937e3c7b1775144fea290d65d6c,Nonparametric Context Modeling of Local Appearance for Pose- and Expression-Robust Facial Landmark Localization,"Nonparametric Context Modeling of Local Appearance for Pose- and Expression-Robust Facial Landmark Localization Brandon M. Smith1 Jonathan Brandt2 University of Wisconsin–Madison Zhe Lin2 Adobe Research Li Zhang1 http://www.cs.wisc.edu/~lizhang/projects/face-landmark-localization/" 7c8d57ca9cbefd1c2b3f4d45ab6791adba2d6bb4,Two-Stage Hashing for Fast Document Retrieval,"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 495–500, Baltimore, Maryland, USA, June 23-25 2014. c(cid:13)2014 Association for Computational Linguistics" 7c2f2080473d25db73c53869337afb79d2135731,"Remondino , Gerke 75 Oblique Aerial Imagery – A Review","Remondino, Gerke Oblique Aerial Imagery – A Review Fabio Remondino, Trento Markus Gerke, Twente" 7c349932a3d083466da58ab1674129600b12b81c,Leveraging Multiple Features for Image Retrieval and Matching, 7c0ffae3acb0fd0a14ff66b6d474229aa16c53ab,Covariance Descriptor Multiple Object Tracking and Re-identification with Colorspace Evaluation,"Covariance Descriptor Multiple Object Tracking nd Re-Identification with Colorspace Evaluation Andr´es Romero, Mich`ele Gouiff´es and Lionel Lacassagne Institut d’´El´ectronique Fondamentale, UMR 8622, Universit´e Paris-Sud XI, Bˆatiment 660, rue Noetzlin, Plateau du Moulon, 91400 Orsay" 7c7b0550ec41e97fcfc635feffe2e53624471c59,"Head, Eye, and Hand Patterns for Driver Activity Recognition","051-4651/14 $31.00 © 2014 IEEE DOI 10.1109/ICPR.2014.124" 7c8adb2fa156b119a1f576652c39fb06e4e19675,Ordinal Regression using Noisy Pairwise Comparisons for Body Mass Index Range Estimation,"Ordinal Regression using Noisy Pairwise Comparisons for Body Mass Index Range Estimation Luisa F. Polan´ıa Dongning Wang Glenn M. Fung American Family Insurance, Strategic Data & Analytics, Madison, WI {lpolania, dwang1," 7c26559e7269679ef52a85d02c6ff7000c2387d2,Towards a Development of a Learners’ Ratified Acceptance of Multi-biometrics Intentions Model (RAMIM): Initial Empirical Results,"Yair Levy, Michelle M. Ramim Towards a Development of a Learners’ Ratified Acceptance of Multi-biometrics Intentions Model (RAMIM): Initial Empirical Results Graduate School of Computer and Information H. Wayne Huizenga School of Business and Nova Southeastern University, USA Nova Southeastern University, USA Yair Levy Sciences Michelle M. Ramim Entrepreneurship implemented as" 7c03a0ad5202a6a31ad3b78b11f6b45ecd840616,Scale-Invariant Feature Learning using Deconvolutional Neural Networks for Weakly-Supervised Semantic Segmentation,"Scale-Invariant Feature Learning using Deconvolutional Neural Networks for Weakly-Supervised Semantic Segmentation Hyo-Eun Kim and Sangheum Hwang Lunit Inc., Seoul, South Korea {hekim," 7c739dddc905c967e0b432dc7515cb1f4b82e580,Social Attention: Modeling Attention in Human Crowds,"Social Attention: Modeling Attention in Human Crowds Anirudh Vemula, Katharina Muelling and Jean Oh" 7c4864065f4e107cb5be49a8dba8cf7d94b8340f,Multi-target Tracking by Lagrangian Relaxation to Min-cost Network Flow,"Multi-target Tracking by Lagrangian Relaxation to Min-Cost Network Flow Asad A. Butt and Robert T. Collins The Pennsylvania State University, University Park, PA. 16802, USA" 7c7af300c4780ad01e7db4d60fbf89771672585b,Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning,"Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning Max Ferguson1 Ronay Ak2 Yung-Tsun Tina Lee2 and Kincho. H. Law1" 7cda4fc187f446a52cc5c9ac0e6a0752c1f0d5e9,Domain-Specific Approximation for Object Detection,"© 2018 IEEE. DOI: 10.1109/MM.2018.112130335 © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in ny current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any opyrighted component of this work in other works. DOI: 0.1109/MM.2018.112130335" 7c98c27f4be40a7675ba9c85179ce72d12593a7a,Training Bit Fully Convolutional Network for Fast Semantic Segmentation,"Training Bit Fully Convolutional Network for Fast Semantic Segmentation He Wen and Shuchang Zhou and Zhe Liang and Yuxiang Zhang and Dieqiao Feng and Xinyu Zhou and Cong Yao {wenhe, zsc, liangzhe, zyx, fdq, zxy, Megvii Inc." 7cf579088e0456d04b531da385002825ca6314e2,Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks,"Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks Sayyed M. Zahiri Jinho D. Choi Mathematics and Computer Science Mathematics and Computer Science Emory University Atlanta, GA 30322, USA Emory University Atlanta, GA 30322, USA" 7c3e09e0bd992d3f4670ffacb4ec3a911141c51f,Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images,"Noname manuscript No. (will be inserted by the editor) Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images Limin Wang · Zhe Wang · Yu Qiao · Luc Van Gool Received: date / Accepted: date" 7c18965f5573020f32b151a08178ee4906b5bf4c,Recursive Coarse-to-Fine Localization for Fast Object Detection,"Recursive Coarse-to-Fine Localization for fast Object Detection Marco Pedersoli, Jordi Gonz`alez, Andrew D. Bagdanov, and Juan J. Villanueva Dept. Ci`encies de la Computaci´o & Centre de Visi´o per Computador, Edifici O, Campus UAB 08193 Bellaterra (Cerdanyola) Barcelona, Spain" 7c7158273f0f833329ad86f7f642aedeb161a73c,A video database of human faces under near Infra-Red illumination for human computer interaction applications,"A Video Database of Human Faces under Near Infra-Red Illumination for Human Computer Interaction Aplications S L Happy, Anirban Dasgupta, Anjith George, and Aurobinda Routray Department of Electrical Engineering Indian Institute of Technology Kharagpur" 7c25a4b2eaa7bf0bc4e0bd239f05d6c0d4cb3431,Fast Appearance-based Person Re-identification and Retrieval Using Dissimilarity Representations,"Fast Appearance-based Person Re-identification nd Retrieval Using Dissimilarity Representations Riccardo Satta, Giorgio Fumera, and Fabio Roli Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d’Armi, 09123 Cagliari, Italy e-mail: {satta, fumera, WWW: http://prag.diee.unica.it" 7c95449a5712aac7e8c9a66d131f83a038bb7caa,Facial first impressions from another angle: How social judgements are influenced by changeable and invariant facial properties.,"This is an author produced version of Facial first impressions from another angle: How social judgements are influenced by changeable and invariant facial properties. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/102935/ Article: Sutherland, Clare, Young, Andrew William orcid.org/0000-0002-1202-6297 and Gillian, Rhodes (2017) Facial first impressions from another angle: How social judgements are 97-415. ISSN 0007-1269 https://doi.org/10.1111/bjop.12206 promoting access to White Rose research papers http://eprints.whiterose.ac.uk/" 7ca37d66cbedf61d30e18e0608078c7b1d7cbf58,Photometric Normalization Techniques for Illumination Invariance,"Photometric Normalization Techniques for Illumination Invariance AVTOR: Vitomir Štruc INTERNAL REPORT: LUKS" 7ca600523495b3d6c9addf26cd89d3bd23ce4cf3,ReDMark : Framework for Residual Diffusion Watermarking based on Deep Networks,"Copyright may be transferred without notice, after which this version may no longer be accessible. This work has been submitted to the IEEE for possible publication. ReDMark: Framework for Residual Diffusion Watermarking based on Deep Networks Mahdi Ahmadi, Alireza Norouzi, S.M.Reza Soroushmehr, Nader Karimi, Kayvan Najarian, Shadrokh Samavi and Ali Emami" 7c25ed788da1f5f61d8d1da23dd319dfb4e5ac2d,Human-In-The-Loop Person Re-Identification,"Human-In-The-Loop Person Re-Identification Hanxiao Wang, Shaogang Gong, Xiatian Zhu, and Tao Xiang" 7c45b5824645ba6d96beec17ca8ecfb22dfcdd7f,News Image Annotation on a Large Parallel Text-image Corpus.,"News image annotation on a large parallel text-image corpus Pierre Tirilly, Vincent Claveau, Patrick Gros Universit´e de Rennes 1/IRISA, CNRS/IRISA, INRIA Rennes-Bretagne Atlantique Campus de Beaulieu 5042 Rennes Cedex, France" 7c1802d8d43dfe783650a03f03d41609fa5ae91e,Discriminability Objective for Training Descriptive Captions,"Discriminability objective for training descriptive captions Ruotian Luo TTI-Chicago Brian Price Adobe Research Scott Cohen Adobe Research Gregory Shakhnarovich TTI-Chicago" 7c9a65f18f7feb473e993077d087d4806578214e,SpringerLink - Zeitschriftenbeitrag,"SpringerLink - Zeitschriftenbeitrag http://www.springerlink.com/content/93hr862660nl1164/?p=abe5352... Deutsch Deutsch Vorherige Beitrag Nächste Beitrag Beitrag markieren In den Warenkorb legen Zu gespeicherten Artikeln hinzufügen Permissions & Reprints Diesen Artikel empfehlen Ergebnisse finden Erweiterte Suche im gesamten Inhalt in dieser Zeitschrift in diesem Heft Diesen Beitrag exportieren Diesen Beitrag exportieren als RIS | Text" 7cbf3ff040ce3d68d530fcddccf56788fa9b7a53,An algorithm to minimize within-class scatter and to reduce common matrix dimension for image recognition,"Turk J Elec Eng & Comp Sci, Vol.19, No.6, 2011, c(cid:2) T ¨UB˙ITAK doi:10.3906/elk-1003-403 An algorithm to minimize within-class scatter and to reduce common matrix dimension for image recognition ¨Umit C¸ i˘gdem TURHAL1,∗, Alpaslan DUYSAK2 Department of Electrical and Electronics Engineering, Bilecik University, Bilecik-TURKEY Department of Computer Engineering, Dumlupınar University, K¨utahya-TURKEY e-mail: Received: 12.03.2010" 7caca02d3c61271d22c43580677acb6d52b23503,What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?,"IJCV VISI manuscript No. (will be inserted by the editor) What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation? Nikolaus Mayer · Eddy Ilg · Philipp Fischer · Caner Hazirbas · Daniel Cremers · Alexey Dosovitskiy · Thomas Brox Received: date / Accepted: date" 7cb4d30b3bfb0d4b02499c15c7c7a9dfddda8049,Object Tracking using L 1 / L 2 Sparse Coding and Multi Scale Max Pooling,"________________________________________________________________________________________________ International Journal of Electrical, Electronics and Computer Systems (IJEECS) Online Object Tracking using L1/L2 Sparse Coding and Multi Scale Max Pooling V.S.R Kumari, 2K.Srinivasarao Professor & HOD, Dept. of ECE, Sri Mittapalli College of Engineering, Guntur, A.P, India. PG Student (M. Tech), Dept. of ECE, Sri Mittapalli College of Engineering, Guntur, A.P, India. Email : In order" 7c4022dd2525882a0f7ba0d60db1c6290d5a9aa8,CSRNCVA: A MODEL OF CROSS-MEDIA SEMANTIC RETRIEVAL BASED ON NEURAL COMPUTING OF VISUAL AND AUDITORY SENSATIONS,"CSRNCVA: A MODEL OF CROSS-MEDIA SEMANTIC RETRIEVAL BASED ON NEURAL COMPUTING OF VISUAL AND AUDITORY SENSATIONS Y. Liu∗, K. Cai†, C. Liu‡, F. Zheng§" 513b11920f15a55ff4e3dd1a063c386b863d6679,Real-time CPU-based large-scale 3D mesh reconstruction,"Real-time CPU-based large-scale 3D mesh reconstruction Enrico Piazza1 Andrea Romanoni1 Matteo Matteucci1" 5122a5d4bdf58b4f413d4de1fb250d4ab5e0608a,Gender Classification from Pose-Based GEIs,"Gender Classification from Pose-Based GEIs(cid:2) Ra´ul Mart´ın-F´elez, Ram´on A. Mollineda, and J. Salvador S´anchez Institute of New Imaging Technologies (INIT) Universitat Jaume I. Av. Sos Baynat s/n, 12071, Castell´o de la Plana, Spain" 51bfc693d170b4171f5bd9f9aed51f1fe8b5304d,Zero-shot Recognition via Direct Classifier Learning with Transferred Samples and Pseudo Labels AAAI Anonymous Submission 182,"Zero-shot Recognition via Direct Classifier Learning with Transferred Samples and Pseudo Labels AAAI Anonymous Submission 182" 5121f42de7cb9e41f93646e087df82b573b23311,Classifying Online Dating Profiles on Tinder using FaceNet Facial Embeddings,"CLASSIFYING ONLINE DATING PROFILES ON TINDER USING FACENET FACIAL EMBEDDINGS Charles F. Jekel and Raphael T. Haftka Department of Mechanical & Aerospace Engineering - University of Florida - Gainesville, FL 32611" 51319bb12c67fb5b11cbf2012a7e2059718b52eb,Local Fisher Discriminant Analysis for Pedestrian Re-identification,"Local Fisher Discriminant Analysis for Pedestrian Re-identification Sateesh Pedagadi, James Orwell Kingston University London Sergio Velastin Universidad de Santiago de Chile Boghos Boghossian Ipsotek Ltd, UK" 5120fb7db8eadb26118847d0553fca1c22ed6f07,DEEP EXTREME TRACKER BASED ON BOOTSTRAP PARTICLE FILTER,"Journal of Theoretical and Applied Information Technology 31st August 2014. Vol. 66 No.3 © 2005 - 2014 JATIT & LLS. All rights reserved. ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 DEEP EXTREME TRACKER BASED ON BOOTSTRAP PARTICLE FILTER ALEXANDER A S GUNAWAN, 2 MOHAMAD IVAN FANANY, WISNU JATMIKO Bina Nusantara University, Mathematics Department, School of Computer Science, Jakarta, Indonesia , 3 Universitas Indonesia, Faculty of Computer Science, Depok, Indonesia E-mail: 1 2 3" 511dda02d39dc8107ac385ea8a572970e2eb9b7b,"Face recognition using distributed, mobile computing","014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE Klipsch School of Electrical and Computer Engineering Gregorio Hinojos and Phillip L. De Leon Las Cruces, New Mexico, U.S.A. New Mexico State University . INTRODUCTION" 51b7a57a2dbc2df0b0353cfcb4331c8f9c621e56,Bayesian learning for weakly supervised object classification,"Bayesian learning for weakly supervised object classification Peter Carbonetto, Gyuri Dork´o and Cordelia Schmid INRIA Rhˆone-Alpes, Grenoble, France August 5, 2004" 518439ba2895c84ba686db5b83674c440e637c0b,The Price of Fair PCA: One Extra Dimension,"The Price of Fair PCA: One Extra Dimension Samira Samadi Georgia Tech Uthaipon Tantipongpipat Georgia Tech Jamie Morgenstern Georgia Tech Mohit Singh Georgia Tech Santosh Vempala Georgia Tech" 516a014f4654c90a22ae3d363b6e80bda68a084d,Adaptive human-centered representation for activity recognition of multiple individuals from 3D point cloud sequences,"Adaptive Human-Centered Representation for Activity Recognition of Multiple Individuals from 3D Point Cloud Sequences Hao Zhang1, Christopher Reardon2, Chi Zhang2, and Lynne E. Parker2" 51c3050fb509ca685de3d9ac2e965f0de1fb21cc,Fantope Regularization in Metric Learning,"Fantope Regularization in Metric Learning Marc T. Law Nicolas Thome Matthieu Cord Sorbonne Universit´es, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005, Paris, France" 5193328862366e114781cb6b196ae958c1553357,Incremental Learning in Person Re-Identification,"Incremental Learning in Person Re-Identification Prajjwal Bhargava SRM University Chennai" 51d97f4e4385a3da78bf9277a5426216198698c3,Improving the Accuracy of Face Detection for Damaged Video and Distant Targets,"Improving the Accuracy of Face Detection for Damaged Video and Distant Targets Department of Communication Engineering, Oriental Institute of Technology, New Taiepi City, Taiwan Jun-Horng Chen Keywords: Error Concealment, Face Detection, Super-resolution." 5194a8acc87dd05a92a21f94fea966a2815f9b38,Noise aware analysis operator learning for approximately cosparse signals,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 51d1a6e15936727e8dd487ac7b7fd39bd2baf5ee,"A Fast and Accurate System for Face Detection, Identification, and Verification","JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 A Fast and Accurate System for Face Detection, Identification, and Verification Rajeev Ranjan, Ankan Bansal, Jingxiao Zheng, Hongyu Xu, Joshua Gleason, Boyu Lu, Anirudh Nanduri, Jun-Cheng Chen, Carlos D. Castillo, Rama Chellappa" 51a81a17328ad36f1bbc15e240076b68d3271c0c,Laplacian object: One-shot object detection by locality preserving projection,"LAPLACIAN OBJECT: ONE-SHOT OBJECT DETECTION BY LOCALITY PRESERVING PROJECTION Sujoy Kumar Biswas and Peyman Milanfar Electrical Engineering Department University of California, Santa Cruz 156 High Street, Santa Cruz, CA, 95064" 51a162f6d21e48c3731aec8f676ba7c18c65bd26,From trajectories to behaviors : an algorithm to track and describe dancing birds,"2nd Computer Vision Winter Workshop Nicole M. Artner, Ines Janusch, Walter G. Kropatsch (eds.) Retz, Austria, February 6–8, 2017 From trajectories to behaviors: n algorithm to track and describe dancing birds Leonardo Oliva1,2, Alessia Saggese2, Nicole M. Artner1, Walter G. Kropatsch1, and Mario Vento2 Pattern Recognition and Image Processing Group (PRIP), TU Wien, Austria Dept. of Information Eng., Electrical Eng. and Applied Mathematics (DIEM) Faculty of Engineering, University of Salerno, Italy" 5171157c2c09a85ad6558c5c03da6b75b0cf5fe6,Dynamic Coattention Networks For Question Answering,"Published as a conference paper at ICLR 2017 DYNAMIC COATTENTION NETWORKS FOR QUESTION ANSWERING Caiming Xiong∗, Victor Zhong∗, Richard Socher Salesforce Research Palo Alto, CA 94301, USA {cxiong, vzhong," 511662e02373433c8c9e27d1425707069e3695b7,Effects of image compression on ear biometrics,"Engineering and Technology Copyright. The copy of record is available at IET Digital Library. Research Article Effects of image compression on ear iometrics ISSN 2047-4938 Received on 23rd October 2015 Revised on 27th January 2016 Accepted on 15th February 2016 doi: 10.1049/iet-bmt.2015.0098 www.ietdl.org Christian Rathgeb1 ✉, Anika Pflug2, Johannes Wagner1, Christoph Busch1 da/sec – Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany Media Security and IT Forensics – Fraunhofer Institute for Secure Information Technology, Germany ✉ E-mail:" 51cf3fa26b7c31c10427317fb5d72a6712023279,What Shape Is Your Conjugate? A Survey of Computational Convex Analysis and Its Applications,"A SURVEY OF COMPUTATIONAL CONVEX ANALYSIS AND ITS APPLICATIONS WHAT SHAPE IS YOUR CONJUGATE? YVES LUCET" 51a9f9dcffad494cb88b949b7e98e7e11240a015,A Hybrid Face Recognition Approach Using GPUMLib,"A Hybrid Face Recognition Approach Using GPUMLib Noel Lopes1,2 and Bernardete Ribeiro1 CISUC - Center for Informatics and Systems of University of Coimbra, Portugal UDI/IPG - Research Unit, Polytechnic Institute of Guarda, Portugal" 51b70582fb0d536d4a235f91bf6ad382f29e2601,Detection of emotions from video in non-controlled environment. (Détection des émotions à partir de vidéos dans un environnement non contrôlé),"Detection of emotions from video in non-controlled environment Rizwan Ahmed Khan To cite this version: Rizwan Ahmed Khan. Detection of emotions from video in non-controlled environment. Image Processing. Universit´e Claude Bernard - Lyon I, 2013. English. . HAL Id: tel-01166539 https://tel.archives-ouvertes.fr/tel-01166539v2 Submitted on 23 Jun 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 51e43578ad761c7c4d58cb159eee0f8e6cf0f7a4,Incremental indexing and distributed image search using shared randomized vocabularies,"Introduction Method Results Incremental Indexing and Distributed Image Search using Shared Randomized Vocabularies Rapha¨el Mar´ee, Philippe Denis, Louis Wehenkel, Pierre Geurts GIGA Bioinformatics GIGA Research ; Dept. EE & CS (Montefiore Institute) University of Li`ege, Belgium MIR 2010 March 29–31, 2010 Philadelphia, Pennsylvania, USA Mar´ee et al. Shared Randomized Vocabularies (1 / 44)" 5146832515ba8b4ad48372967d9fb7dcdea61869,CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks,"Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers, pages 646–654, Berlin, Germany, August 11-12, 2016. c(cid:13)2016 Association for Computational Linguistics" 51ab92566306c2f26e8415b451f3dd1f83f59008,The USC CreativeIT database of multimodal dyadic interactions: from speech and full body motion capture to continuous emotional annotations,"The USC CreativeIT Database of Multimodal Dyadic Interactions: From Speech and Full Body Motion Capture to Continuous Emotional Annotations Angeliki Metallinou · Zhaojun Yang · Chi-chun Lee · Carlos Busso · Sharon Carnicke · Shrikanth Narayanan March 23, 2015" 51cc78bc719d7ff2956b645e2fb61bab59843d2b,Face and Facial Expression Recognition with an Embedded System for Human-Robot Interaction,"Face and Facial Expression Recognition with an Embedded System for Human-Robot Interaction Yang-Bok Lee1, Seung-Bin Moon1, and Yong-Guk Kim 1* School of Computer Engineering, Sejong University, Seoul, Korea" 51c7c5dfda47647aef2797ac3103cf0e108fdfb4,Cs 395t: Celebrity Look-alikes *,"CS 395T: Celebrity Look-Alikes ∗ Adrian Quark" 51c7236feaa2ae23cef78c7bca75c69d7081e24a,Deep multi-frame face super-resolution,"Deep multi-frame face super-resolution Evgeniya Ustinova, Victor Lempitsky October 17, 2017" ddbfea5302fcb5cbc2ca4c498a592ddb063b9eff,L Ow Supervision Visual Learning through Cooperative Agents,"Low-supervision visual learning through cooperative agents Ashish Bora Abhishek Sinha" ddfdc4bf9fe440926e5e80909d444316fb7bc694,UvA-DARE ( Digital Academic Repository ) Selective Search for Object Recognition,"UvA-DARE (Digital Academic Repository) Selective Search for Object Recognition Uijlings, J.R.; van de Sande, K.E.A.; Gevers, T.; Smeulders, A.W.M. Published in: International Journal of Computer Vision 0.1007/s11263-013-0620-5 Link to publication Citation for published version (APA): Uijlings, J. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013). Selective Search for Object Recognition. International Journal of Computer Vision, 104(2), 154-171. DOI: 10.1007/s11263-013-0620-5 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Download date: 03 Dec 2018 UvA-DARE is a service provided by the library of the University of Amsterdam (http://dare.uva.nl)" ddbd24a73ba3d74028596f393bb07a6b87a469c0,Multi-region Two-Stream R-CNN for Action Detection,"Multi-region two-stream R-CNN for action detection Xiaojiang Peng, Cordelia Schmid Inria(cid:63)" dde24967490f58c8d10b2a00f12bf9103bd9b4a6,EVALUATION OF SHAPE FEATURES FOR EFFICIENT CLASSIFICATION BASED ON ROTATIONAL INVARIANT USING TEXTON MODEL,"Dr. P Chandra Sekhar Reddy, International Journal of Computer Science and Mobile Computing, Vol.5 Issue.8, August- 2016, pg. 282-295 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320–088X IMPACT FACTOR: 5.258 IJCSMC, Vol. 5, Issue. 8, August 2016, pg.282 – 295 EVALUATION OF SHAPE FEATURES FOR EFFICIENT CLASSIFICATION BASED ON ROTATIONAL INVARIANT USING TEXTON MODEL Dr. P Chandra Sekhar Reddy Professor, CSE Dept. Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad" dd54255065cf93895661c40073cdd031af7dd7e8,"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose Zhichao Yin and Jianping Shi SenseTime Research {yinzhichao," ddfde5d6f4e720aeb770a20e4197db3a0c279958,Learning Convolutional Text Representations for Visual Question Answering,"Learning Convolutional Text Representations for Visual Question Answering Zhengyang Wang∗ Shuiwang Ji†" dda7bb490171a1d3364928fb8143bbe021146c5f,Local Shape Spectrum Analysis for 3D Facial Expression Recognition,"Local Shape Spectrum Analysis for 3D Facial Expression Recognition Department of Information and Communication Technologies, Pompeu Fabra University, Barcelona, Spain Dmytro Derkach and Federico M. Sukno" dd80f3d19a4e3de9e9ef6dc3d23d52852a2ec23c,Audio-Visual Arabic Speech ( AVAS ) Database for Human-Computer Interaction Applications,"Volume 3, Issue 10, October 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Audio-Visual Arabic Speech (AVAS) Database for Human- Computer Interaction Applications Samar Antar Alaa Sagheer Center for Artificial Intelligence and Robotics (CAIRO), Department of Mathematics, Aswan University, Aswan, Egypt" dd7ed20a65d811dcf863f796d6dcbe873f57e7c4,Object Detection Via Structural Feature Selection and Shape Model,"Object Detection via Structural Feature Selection and Shape Model Huigang Zhang, Xiao Bai, Jun Zhou, Senior Member, IEEE, Jian Cheng and Huijie Zhao" ddcb77d09e4e9e2a948f9ffe7eaa5554dceb8ce3,Revisiting Cross Modal Retrieval, ddeb017c0452f14690ce240c90128d979289ab5f,A Comprehensive Survey on Human Skin Detection,"I.J. Image, Graphics and Signal Processing, 2016, 5, 1-35 Published Online May 2016 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijigsp.2016.05.01 A Comprehensive Survey on Human Skin Detection Mohammad Reza Mahmoodi Department of Electrical and Computer Engineering, Isfahan University of Technology, 8415683111 Isfahan, Iran E-mail addresses: Sayed Masoud Sayedi Department of Electrical and Computer Engineering, Isfahan University of Technology, 8415683111 Isfahan, Iran E-mail addresses:" dd0a334b767e0065c730873a95312a89ef7d1c03,Eigenexpressions: Emotion Recognition Using Multiple Eigenspaces,"Eigenexpressions: Emotion Recognition using Multiple Eigenspaces Luis Marco-Gim´enez1, Miguel Arevalillo-Herr´aez1, and Cristina Cuhna-P´erez2 University of Valencia. Computing Department, Burjassot. Valencia 46100, Spain, Universidad Cat´olica San Vicente M´artir de Valencia (UCV), Burjassot. Valencia. Spain" ddc8f480898a846c2a6ba0dddd7d733ce35f0e19,Dense Pose Transfer,"Dense Pose Transfer Natalia Neverova1, Rıza Alp G¨uler2, and Iasonas Kokkinos1 Facebook AI Research, Paris, France, {nneverova, INRIA-CentraleSup´elec, Paris, France," ddf55fc9cf57dabf4eccbf9daab52108df5b69aa,Methodology and Performance Analysis of 3-D Facial Expression Recognition Using Statistical Shape Representation,"International Journal of Grid and Distributed Computing Vol. 4, No. 3, September, 2011 Methodology and Performance Analysis of 3-D Facial Expression Recognition Using Statistical Shape Representation Wei Quan, Bogdan J. Matuszewski, Lik-Kwan Shark ADSIP Research Centre, University of Central Lancashire {WQuan, BMatuszewski1, Charlie Frowd School of Psychology, University of Central Lancashire" ddea3c352f5041fb34433b635399711a90fde0e8,FACIAL EXPRESSION CLASSIFICATION USING VISUAL CUES AND LANGUAGE,"Facial Expression Classification using Visual Cues and Language Abhishek Kar Advisor: Dr. Amitabha Mukerjee Department of Computer Science and Engineering, IIT Kanpur" ddefb92908e6174cf48136ae139efbb4bd198896,Feature-wise Bias Amplification,"Under review as a conference paper at ICLR 2019 FEATURE-WISE BIAS AMPLIFICATION Anonymous authors Paper under double-blind review" dde5125baefa1141f1ed50479a3fd67c528a965f,Synthesizing Normalized Faces from Facial Identity Features,"Synthesizing Normalized Faces from Facial Identity Features Forrester Cole1 David Belanger1,2 Dilip Krishnan1 Aaron Sarna1 Inbar Mosseri1 William T. Freeman1,3 Google, Inc. 2University of Massachusetts Amherst 3MIT CSAIL {fcole, dbelanger, dilipkay, sarna, inbarm," 596b2ad91ba21884960c67fad21bc2ac62800200,RelCom: Relational combinatorics features for rapid object detection,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com RelCom: Relational Combinatorics Features for Rapid Object Detection Vijay Venkataraman, Fatih Porikli TR2010-036 July 2010" 5911dcef05ffec02cc1dd88ec6feb1f1e0e8bdcb,Happy Companion: A System of Multimodal Human-Computer Affective Interaction,"Happy Companion: A System of Multimodal Human-Computer Affective Interaction Jia Jia1,2,3, Lianhong Cai1,2,3, Sirui Wang4, Xiaolan Fu4 State Key Laboratory on Intelligent Technology and Systems" 59f65b2a3a50b64193ee09dac29137cdd8dc6688,Learning Similarity Metrics by Factorising Adjacency Matrices,"Learning Similarity Metrics by Factorising Adjacency Matrices Henry Gouk† Bernhard Pfahringer† Michael Cree‡ Department of Computer Science, University of Waikato, Hamilton, New Zealand School of Engineering, University of Waikato, Hamilton, New Zealand" 59d0d7ccec2db66cad20cac5721ce54a8a058294,Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference,"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference Benoit Jacob Skirmantas Kligys Matthew Tang Andrew Howard Bo Chen Hartwig Adam Menglong Zhu Dmitry Kalenichenko {benoitjacob,skligys,bochen,menglong, Google Inc." 59b71e19819c1c6aee98020b34bf92e605f33819,Max-min convolutional neural networks for image classification,"MAX-MIN CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE CLASSIFICATION Michael Blot, Matthieu Cord, Nicolas Thome Sorbonne Universit´es, UPMC Univ Paris 06, CNRS, LIP6 UMR 7606, 4 place Jussieu 75005 Paris" 59ee0f67bcf2d8ea0bbbfcbc71159725fc3a7059,Object Detection with Appearance-based Mixture Models Anonymous CVPR submission,"CVPR 2011 Submission #885. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. Object Detection with Appearance-based Mixture Models Anonymous CVPR submission Paper ID 885" 59ee327192c270fc727c5f6d2ef90058ed072b14,Motion Models for People Tracking,"Motion Models for People Tracking David J. Fleet" 59f325e63f21b95d2b4e2700c461f0136aecc171,Kernel sparse representation with local patterns for face recognition,"978-1-4577-1302-6/11/$26.00 ©2011 IEEE FOR FACE RECOGNITION . INTRODUCTION" 59b11427853b7892a9f0d8ab6683d96ce59c2ff2,A Multi-Face Challenging Dataset for Robust Face Recognition,"A Multi-Face Challenging Dataset for Robust Face Recognition Shiv Ram Dubey and Snehasis Mukherjee" 593d8c2230cda76c83385ab90677a024c3b04a90,A Canonical Image Set for Examining and Comparing Image Processing Algorithms,"A Canonical Image Set for Examining and Comparing Image Processing Algorithms Jeffrey Uhlmann Dept. of Electrical Engineering & Computer Science University of Missouri-Columbia" 59031a35b0727925f8c47c3b2194224323489d68,Sparse Variation Dictionary Learning for Face Recognition with a Single Training Sample per Person,"Sparse Variation Dictionary Learning for Face Recognition with A Single Training Sample Per Person Meng Yang, Luc Van Gool ETH Zurich Switzerland" 59945763707557baace208253c029265b4b6e0a9,FACE RECOGNITION UNDER PARTIAL OCCLUSION AND SMALL DENSE NOISE,"FACE RECOGNITION UNDER PARTIAL OCCLUSION AND SMALL DENSE NOISE A THESIS SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTER OF TECHNOLOGY ELECTRONIC SYSTEMS AND COMMUNICATIONS ROHIT KUMAR ROLL NO. -212EE1210 Department of Electrical Engineering National Institute of Technology, Rourkela-769008 | P a g e" 59efb1ac77c59abc8613830787d767100387c680,DIF : Dataset of Intoxicated Faces for Drunk Person Identification,"DIF : Dataset of Intoxicated Faces for Drunk Person Identification Devendra Pratap Yadav Indian Institute of Technology Ropar Abhinav Dhall Indian Institute of Technology Ropar" 59bdd317abe8d87fb525eb4e3197a9311e2766e7,AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"DEMYSTIFYING UNSUPERVISED FEATURE LEARNING A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Adam Coates September 2012" 590a52702bdf7f9522cff02f477de1fa98fc2ff3,"Visual tracking of hands, faces and facial features of multiple persons","DOI 10.1007/s00138-012-0409-5 ORIGINAL PAPER Visual tracking of hands, faces and facial features of multiple persons Haris Baltzakis · Maria Pateraki · Panos Trahanias Received: 17 November 2010 / Revised: 9 December 2011 / Accepted: 18 January 2012 © Springer-Verlag 2012" 59fc69b3bc4759eef1347161e1248e886702f8f7,Final Report of Final Year Project HKU-Face : A Large Scale Dataset for Deep Face Recognition,"Final Report of Final Year Project HKU-Face: A Large Scale Dataset for Deep Face Recognition Haoyu Li 035141841 COMP4801 Final Year Project Project Code: 17007" 5984c4a65c8fbd02be6054c30d929e76b9b9110a,Discovery of Sets of Mutually Orthogonal Vanishing Points in Videos,"Discovery of Sets of Mutually Orthogonal Vanishing Points in Videos Till Kroeger1 Dengxin Dai1 Radu Timofte1 Luc Van Gool1,2 Computer Vision Laboratory, D-ITET, ETH Zurich VISICS / iMinds, ESAT, K.U. Leuven {kroegert, dai, timofter," 5950512e21114236208b9eaeebc9a09735e367a6,Master research Internship Internship report Segmentation and recognition of symbols for printed and handwritten music scores,"Master research Internship Internship report Segmentation and recognition of symbols for printed and handwritten music scores Domain: Document and Text Processing, Computer Vision and Pattern Recognition Author: Kwon-Young Choi Supervisors: Bertrand Coüasnon Yann Ricquebourg Intuidoc, Irisa, France Richard Zanibbi RIT, USA" 59ec9bef0d331444db7d763960095213eecb3b20,INVARIANT FACE RECOGNITION IN A NETWORK OF CORTICAL COLUMNS,"INVARIANT FACE RECOGNITION IN A NETWORK OF CORTICAL COLUMNS Frankfurt Institute for Advanced Studies, JWG University, Ruth-Moufang-Str. 1, Frankfurt am Main, Germany Philipp Wolfrum J¤org L¤ucke Gatsby Unit, UCL, London, United Kingdom Christoph von der Malsburg Frankfurt Institute for Advanced Studies, JWG University, Ruth-Moufang-Str. 1, Frankfurt am Main, Germany Keywords:" 59c9d416f7b3d33141cc94567925a447d0662d80,Matrix factorization over max-times algebra for data mining,"Universität des Saarlandes Max-Planck-Institut für Informatik Matrix factorization over max-times lgebra for data mining Masterarbeit im Fach Informatik Master’s Thesis in Computer Science von / by Sanjar Karaev ngefertigt unter der Leitung von / supervised by Dr. Pauli Miettinen egutachtet von / reviewers Dr. Pauli Miettinen Prof. Gerhard Weikum November 2013 UNIVERSITASSARAVIENSIS" 59b21f61ac46e1f982cbd9f49cb855ba5fcd3c45,CCNY at TRECVID 2014 : Surveillance Event Detection,"CCNY at TRECVID 2014: Surveillance Event Detection Yang Xian, Xuejian Rong, Xiaodong Yang, and Yingli Tian Graduate Center and City College City University of New York {xrong, xyang02," 59bfeac0635d3f1f4891106ae0262b81841b06e4,Face Verification Using the LARK Face Representation,"Face Verification Using the LARK Face Representation Hae Jong Seo, Student Member, IEEE, Peyman Milanfar, Fellow, IEEE," 59d225486161b43b7bf6919b4a4b4113eb50f039,Complex Event Recognition from Images with Few Training Examples,"Complex Event Recognition from Images with Few Training Examples Unaiza Ahsan∗ Chen Sun∗∗ James Hays∗ Irfan Essa∗ *Georgia Institute of Technology **University of Southern California1" 598ccf73ba504a31d65b50c7ede8982c3b1d9192,Learning a Family of Detectors,"LEARNING A FAMILY OF DETECTORS QUAN YUAN Dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy BOSTON UNIVERSITY" 595d0fe1c259c02069075d8c687210211908c3ed,A Survey on Learning to Hash,"A Survey on Learning to Hash Jingdong Wang, Ting Zhang, Jingkuan Song, Nicu Sebe, and Heng Tao Shen" 591bd78a06814e75cae7cdef50ad91cf22e66c23,3D face recognition based on evolution of iso-geodesic distance curves,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010" 5925a25dfe107c49c636eccb8f9fd1aeef7b438c,Temporal Shift Module for Efficient Video Understanding,"Temporal Shift Module for Efficient Video Understanding Ji Lin Chuang Gan MIT-IBM Watson AI Lab Song Han" 59da714d643757871bf3a48757a5919b9b577e89,A Statistical Quadtree Decomposition to Improve Face Analysis, 599b7e1b4460c8ad77def2330ec76a2e0dfedb84,Robust Subspace Clustering via Smoothed Rank Approximation,"Robust Subspace Clustering via Smoothed Rank Approximation Zhao Kang, Chong Peng, and Qiang Cheng∗" 590c277e8ca10f2c2d7e32eb4a9dc61078a67b96,Statistical Approaches to Face Recognition a Qualifying Examination Report,"StatisticalApproachesTo FaceRecognition AQualifyingExaminationReport AraV.Ne(cid:12)an PresentedtotheQualifyingExaminationCommittee InPartialFul(cid:12)llmentoftheRequirementsforthe DegreeofDoctorofPhilosophyinElectricalEngineering Dr.AlbinJ.Gasiewski Dr.Je(cid:11)Geronimo Dr.MonsonH.HayesIII Dr.RussellM.Mersereau Dr.RonaldW.Schafer GeorgiaInstituteofTechnology SchoolofElectricalEngineering December, " 59f8d0e79eb02c30a5f872038129c4b5dd9bc73a,Design of a Face Recognition System for Security Control,"International Conference on African Development Issues (CU-ICADI) 2015: Information and Communication Teclmology Track Design of a Face Recognition System for Security Control Ambrose A. Azeta, Nicholas A. Omoregbe, Adewole Adewumi, Dolapo Oguntade Department of Computer and Information Sciences, Covenant University, Ota, Ogun-State, Nigeria" 59d25dfa200e099662ec34eec620726ebcf02ea8,Information fusion and evidential grammars for object class segmentation,"Information fusion and evidential grammars for object class segmentation Jean-Baptiste Bordes1 Philippe Xu1,2 Franck Davoine2 Huijing Zhao2 Thierry Denœux1" 59ef1efb9239a101c2782fab8adc09b7af07d336,Cross-Domain Image Matching with Deep Feature Maps,"Cross-Domain Image Matching with Deep Feature Maps Bailey Kong · James Supan˘ci˘c, III · Deva Ramanan · Charless C. Fowlkes Received: date / Accepted: date" 590630990cf014f8c30296bc7a622d9dccc43163,Recognition of expression variant faces using masked log-Gabor features and Principal Component Analysis,"Recognition of expression variant faces using masked log-Gabor features and Principal Component Analysis Vytautas Perlibakas Image Processing and Analysis Laboratory, Computational Technologies Centre, Kaunas University of Technology, Studentu st. 56-305, LT-51424 Kaunas, Lithuania" 598f330fc061852162f2aaaf59ea9a3a55d3f6f7,A new strategy based on spatiogram similarity association for multi-pedestrian tracking,"A NEW STRATEGY BASED ON SPATIOGRAM SIMILARITY ASSOCIATION FOR MULTI-PEDESTRIAN TRACKING Nabila MANSOURI1 5, Yousra BEN JEMAA2, Cina MOTAMED 3, Antonio PINTI 4 and Eric WATELAIN1 6 University of Lille North of France, UVHC, LAMIH laboratory e-mail: University of Sfax-Tunisie, U2S laboratory e-mail: University of Lille North of France, ULCO, LISIC laboratory e-mail: University of Orleans -France, I3MTO laboratory e-mail: 5 University of Sfax-Tunisie, ReDCAD laboratory 6 University of south Toulon-Var, HandiBio laboratory" 5945464d47549e8dcaec37ad41471aa70001907f,Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos,"Noname manuscript No. (will be inserted by the editor) Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos Serena Yeung · Olga Russakovsky · Ning Jin · Mykhaylo Andriluka · Greg Mori · Li Fei-Fei Received: date / Accepted: date" 59c194bc84d604baf09241238dc47806a998df70,Building a post-compression region-of-interest encryption framework for existing video surveillance systems,"(will be inserted by the editor) Building a Post-Compression Region-of-Interest Encryption Framework for Existing Video Surveillance Systems Challenges, obstacles and practical concerns Andreas Unterweger · Kevin Van Ryckegem · Dominik Engel · Andreas Uhl Received: November 13, 2014 / Accepted: (will be entered by the editor)" 59e266adc3525b4325156f0cc0052c1d76b1c9ae,Contextual Spatial Analysis and Processing for Visual Surveillance Applications,"Contextual Spatial Analysis and Processing for Visual Surveillance Applications Vikas Reddy A thesis submitted for the degree of Doctor of Philosophy at The University of Queensland in September 2011 (revised in March 2012) School of Information Technology and Electrical Engineering" 590065c40574dc797e5aeb380d6e6dab79fad6e5,Face detection using boosted Jaccard distance-based regression,"FACE DETECTION USING BOOSTED JACCARD DISTANCE-BASED REGRESSION Cosmin Atanasoaei Chris McCool Sébastien Marcel Idiap-RR-02-2012 JANUARY 2012 Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" 595ff304aac871abcccaffec7c1d33c3800ddf36,Robust Matching of Occupancy Maps for Odometry in Autonomous Vehicles, 5921d9a8e143b6d82a2722d9ee27bafa363475f0,Driving Policy Transfer via Modularity and Abstraction, 259bd09bc382763f864986498e46ab0178714f58,Lifelong Machine Learning,"Lifelong Machine Learning November, 2016 Zhiyuan Chen and Bing Liu Draft : This is mainly an early draft of the book. We also updated a few places after the publication, highlighted in yellow. Zhiyuan Chen and Bing Liu. Lifelong Machine Learning. Morgan & Claypool Publishers, Nov 2016. LifelongMachineLearningZhiyuan ChenBing Liu" 2504b7bddd1892bc905fc5df6b5afc0b109ef40e,Function Norms and Regularization in Deep Networks,"Function Norms and Regularization in Deep Networks Amal Rannen Triki∗ KU Leuven, ESAT-PSI, imec, Belgium Maxim Berman KU Leuven, ESAT-PSI, imec, Belgium Matthew B. Blaschko KU Leuven, ESAT-PSI, imec, Belgium" 2551721b91069d8eff0816da87a29bb133de8351,A Hybrid Method Using Temporal and Spatial Information for 3D Lidar Data Segmentation, 25a5f7179b794ab2bb7283c8337480fccee51944,Two novel motion-based algorithms for surveillance video analysis on embedded platforms,"Julien A. Vijverberg, Marijn J.H. Loomans, Cornelis J. Koeleman and Peter H.N. de With, ”Two novel motion-based algorithms for surveillance video analysis on embedded platforms,” Real-Time Image and Video Processing, Nasser Kehtarnavaz and Matthias F. Carlsohn, Editors, Proc. SPIE 7724, 77240I(2010). Copyright 2010 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic electronic or print reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. http://dx.doi.org/10.1117/12.851371" 2581bfa070095f60786452dec3df006e240283b0,Older Adults' Trait Impressions of Faces Are Sensitive to Subtle Resemblance to Emotions.,"J Nonverbal Behav (2013) 37:139–151 DOI 10.1007/s10919-013-0150-4 O R I G I N A L P A P E R Older Adults’ Trait Impressions of Faces Are Sensitive to Subtle Resemblance to Emotions Robert G. Franklin Jr. • Leslie A. Zebrowitz Published online: 9 April 2013 Ó Springer Science+Business Media New York 2013" 2528022c14428ad5912c323f6a356009457c985b,Automatic 3D facial expression recognition using geometric and textured feature fusion,"Automatic 3D Facial Expression Recognition using Geometric and Textured Feature Fusion Department of Electronic and Computer Engineering, Brunel University London, UK Asim Jan and Hongying Meng" 25337690fed69033ef1ce6944e5b78c4f06ffb81,STRATEGIC ENGAGEMENT REGULATION: AN INTEGRATION OF SELF-ENHANCEMENT AND ENGAGEMENT,"STRATEGIC ENGAGEMENT REGULATION: AN INTEGRATION OF SELF-ENHANCEMENT AND ENGAGEMENT Jordan B. Leitner A dissertation submitted to the Faculty of the University of Delaware in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Psychology Spring 2014 © 2014 Jordan B. Leitner All Rights Reserved" 251da2569036cebc2ea109972f412c5b1a9db20f,Appearance modeling for person re-identification using Weighted Brightness Transfer Functions,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-1-6 ©2012 IAPR" 25e62096a44e3fe2f641b492379e7c4babce7ee6,Investigating Gaze of Children with ASD in Naturalistic Settings,"Investigating Gaze of Children with ASD in Naturalistic Settings Basilio Noris1*, Jacqueline Nadel2, Mandy Barker3, Nouchine Hadjikhani4, Aude Billard1 Learning Algorithms and Systems Laboratory, Ecole Polyte´chnique Fe´de´rale de Lausanne, Lausanne, Switzerland, 2 Emotion Centre, Hoˆ pital de La Salpe´trie`re, Paris, France, 3 Lausanne University Department of Child and Adolescent Psychiatry, University Hospital of Canton de Vaud, Lausanne, Switzerland, 4 Brain and Mind Institute, Ecole Polyte´chnique Fe´de´rale de Lausanne, Lausanne, Switzerland & Martinos Center for Biomedical Imaging Massachusetts General Hospital/Healthcare Management Systems/HST, Boston, Massachusetts, United States of America" 25291c10213b6bec098e1611d145facfa5d2b398,Personalized Recommendation of Travel Itineraries based on Tourist Interests and Preferences,"Personalized Recommendation of Travel Itineraries based on Tourist Interests and Preferences *Department of Computing and Information Systems, The University of Melbourne, Australia Victoria Research Laboratory, National ICT Australia, Australia Kwan Hui Lim*†" 25ae83767c926898047bbc50971b5b11de34e12a,Detection and Tracking of Occluded People,"Noname manuscript No. (will be inserted by the editor) Detection and Tracking of Occluded People Siyu Tang · Mykhaylo Andriluka · Bernt Schiele Received: date / Accepted: date" 252ea831fbc092b95ae464bce2476619aaf02d01,Acoustic-labial Speaker Verification Pattern Recognition Letters Acoustic-labial Speaker Verification,"IDIAP Martigny - Valais - Suisse Acoustic(cid:0)Labial Speaker Verification Pierre Jourlin   Dominique Genoud  Juergen Luettin  Hubert Wassner  IDIAP(cid:0)RR (cid:3) to appear in Pattern Recognition Letters D a l l e M o l l e I n s t i t u t e f o r P e r c e p t i v e A r t i f i c i a l Intelligence (cid:0) P(cid:0)O(cid:0)Box   (cid:0) Martigny (cid:0) Valais (cid:0) Switzerland phone (cid:0) (cid:1)  (cid:1)    (cid:0) (cid:1)  (cid:1)    e(cid:4)mail secretariat(cid:0)idiap(cid:1)ch internet http(cid:2)(cid:3)(cid:3)www(cid:1)idiap(cid:1)ch" 254f7ef73629c18ff9ba13af59b2d78df3fda59d,Deep Object-Centric Representations for Generalizable Robot Learning,"Deep Object-Centric Representations for Generalizable Robot Learning Coline Devin1, Pieter Abbeel1,2, Trevor Darrell1, Sergey Levine1" 253cedd3022e25a79bcaffe74e3405db65c6d2ce,Deep Hashing for Scalable Image Search,"Deep Hashing for Scalable Image Search Jiwen Lu, Senior Member, IEEE, Venice Erin Liong, and Jie Zhou, Senior Member, IEEE" 258a2dad71cb47c71f408fa0611a4864532f5eba,Discriminative Optimization of Local Features for Face Recognition,"Discriminative Optimization of Local Features for Face Recognition H O S S E I N A Z I Z P O U R Master of Science Thesis Stockholm, Sweden 2011" 25b9ef5c78dbf17c71e6fd94054dd55d66c39264,Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text,"Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text Ayush Jaiswal∗ USC Information Sciences Institute Marina del Rey, CA, USA Ekraam Sabir∗ USC Information Sciences Institute Marina del Rey, CA, USA Wael AbdAlmageed USC Information Sciences Institute Marina del Rey, CA, USA Premkumar Natarajan USC Information Sciences Institute Marina del Rey, CA, USA" 259f0699d7e4066966a38860ad3227fe123d1660,Convolutional Neural Networks for joint object detection and pose estimation: A comparative study.,"Under review as a conference paper at ICLR 2015 CONVOLUTIONAL NEURAL NETWORKS FOR JOINT OBJECT DETECTION AND POSE ESTIMATION: A COMPARATIVE STUDY Francisco Massa, Mathieu Aubry, Renaud Marlet Universit´e Paris-Est, LIGM (UMR CNRS 8049), ENPC F-77455 Marne-la-Vall´ee, France" 2547607a98eff30654994902f518e30caf2f8271,Synthesizing manipulation sequences for under-specified tasks using unrolled Markov Random Fields,"Synthesizing Manipulation Sequences for Under-Specified Tasks using Unrolled Markov Random Fields Jaeyong Sung, Bart Selman and Ashutosh Saxena" 25c19d8c85462b3b0926820ee5a92fc55b81c35a,Pose-Invariant Facial Expression Recognition Using Variable-Intensity Templates,"Noname manuscript No. (will be inserted by the editor) Pose-Invariant Facial Expression Recognition Using Variable-Intensity Templates Shiro Kumano · Kazuhiro Otsuka · Junji Yamato · Eisaku Maeda · Yoichi Sato Received: date / Accepted: date" 25b83cffddff334d78c55db4d67c65b1d8999b2f,Optimization of Person Re-Identification through Visual Descriptors, 25e3fd1074968896fca45be20ca1d678438081fc,Group Invariant Deep Representations for Image Instance Retrieval, 25bb4212af72d64ec20cac533f58f7af1472e057,Person Re-Identification by Camera Correlation Aware Feature Augmentation,"Person Re-Identification by Camera Correlation Aware Feature Augmentation Ying-Cong Chen, Xiatian Zhu, Wei-Shi Zheng, Jian-Huang Lai Code is available at the project page: http://isee.sysu.edu.cn/%7ezhwshi/project/CRAFT.html For reference of this work, please cite: Ying-Cong Chen, Xiatian Zhu,Wei-Shi Zheng, and Jian-Huang Lai. Per- son Re-Identification by Camera Correlation Aware Feature Augmenta- 0.1109/TPAMI.2017.2666805) title={Person Re-Identification by Camera Correlation Aware Feature Aug- mentation}, uthor={Chen, Ying-Cong and Zhu, Xiatian and Zheng, Wei-Shi and Lai, Jian-Huang}, (DOI: 10.1109/TPAMI.2017.2666805)}" 25982e2bef817ebde7be5bb80b22a9864b979fb0,Facial Feature Tracking Under Varying Facial Expressions and Face Poses Based on Restricted Boltzmann Machines,"(a)26facialfeaturepointsthatwetrack(b)oneexamplesequenceFigure1.Facialfeaturepointtrackingunderexpressionvariationandocclusion.Inrecentyears,thesemodelshavebeenusedexplicitlytohandletheshapevariations[17][5].Thenonlinearityem-beddedinRBManditsvariantsmakesthemmoreeffectiveandefficienttorepresentthenonrigiddeformationsofob-jectscomparedtothelinearmethods.Theirlargenumberofhiddennodesanddeeparchitecturesalsocanimposesuffi-cientconstraintsaswellasenoughdegreesoffreedomsintotherepresentationsofthetargetobjects.Inthispaper,wepresentaworkthatcaneffectivelytrackfacialfeaturepointsusingfaceshapepriormodelsthatareconstructedbasedonRBM.Thefacialfeaturetrackercantrack26facialfeaturepoints(Fig.1(a))eveniffaceshavedifferentfacialexpressions,varyingposes,orocclu-sion(Fig.1(b)).Unlikethepreviousworksthattrackfacialfeaturepointsindependentlyorbuildashapemodeltocap-turethevariationsoffaceshapeorappearanceregardlessofthefacialexpressionsandfaceposes,theproposedmodelcouldcapturethedistinctionsaswellasthevariationsoffaceshapesduetofacialexpressionandposechangeinaunifiedframework.Specifically,wefirstconstructamodel1" 25894be540936562953f37fbbcff69e5ac17a494,Semantic Image Retrieval via Active Grounding of Visual Situations,"Semantic Image Retrieval via Active Grounding of Visual Situations Max H. Quinn1, Erik Conser1, Jordan M. Witte1, and Melanie Mitchell1,2 Portland State University 2Santa Fe Institute Email:" 2598c02e537b02ce181eea1aa49a698080a391a8,Improving Recognition Performance for Duplicate Facial Images,"ImprovingRecognitionPerformancefor DuplicateFacialImages KazunoriOkada UniversityofSouthernCalifornia,Dept.ofComputerscienceandSectionforNeu- robiology,LosAngeles,CA  -,USA Summary.Previousworkinourgrouphasdescribedafacerecognitiontechnology asedonGaborwaveletsbasedrepresentationandElasticGraphMatching.[]We heredescribeasummaryofoure(cid:11)ortstowardstheFaceRecognitionTechnology (FERET)PhaseIIItestheldinFebruary .Oneofourgoalsinthistestwas toimproverecognitionperformanceforduplicatefacialimages.Weproposeda modelofcuestoexplainbehavioroffailuresandanalyzedvariousfailurecases ndcauses.Utilizingtheselearnedknowledgeofthefailuresasageneralstrategy, threeadditionalfunctions,histogramequalization,facesizenormalizationbykernel rescalingandjettransformationforrotationindepth[][]wereevaluatedinour systemaspostprocessesafterafacemodelgraphcreation.Theperformanceofthe systemisimprovedforrecognitionofduplicatefacialimages. .Introduction Thispapersummarizesoure(cid:11)ortstopreparefortheFaceRecognitionTechnology (FERET)PhaseIIItestwhichwassuccessfullyoperatedinFebruary .Thistest isthethirdofaseriesoftestsconductedbyUSArmyResearchLaboratory(ARL)." 257eb6d5ca49eb4ea90658a8668d1853d9c38af7,"Wide-Area Video Understanding: Tracking, Video Summarization and Algorithm-Platform Co-Design","UNIVERSITY OF CALIFORNIA RIVERSIDE Wide-Area Video Understanding: Tracking, Video Summarization and Algorithm-Platform Co-Design A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Electrical Engineering Shu Zhang December 2015 Dissertation Committee: Dr. Amit K. Roy-Chowdhury, Chairperson Dr. Qi Zhu Dr. Ertem Tuncel" 25f1f195c0efd84c221b62d1256a8625cb4b450c,Experiments with Facial Expression Recognition using Spatiotemporal Local Binary Patterns,"-4244-1017-7/07/$25.00 ©2007 IEEE ICME 2007" 25695abfe51209798f3b68fb42cfad7a96356f1f,AN INVESTIGATION INTO COMBINING BOTH FACIAL DETECTION AND LANDMARK LOCALISATION INTO A UNIFIED PROCEDURE USING GPU COMPUTING,"AN INVESTIGATION INTO COMBINING BOTH FACIAL DETECTION AND LANDMARK LOCALISATION INTO A UNIFIED PROCEDURE USING GPU COMPUTING J M McDonagh MSc by Research" 25aa935217a52d83bc1637687a78017984fcb731,The Continuous N-tuple Classiier and Its Application to Face Recognition,"Thecontinuousn-tupleclassi(cid:12)eranditsapplicationto facerecognition S.M.Lucas DepartmentofElectronicSystemsEngineering UniversityofEssex ColchesterCOSQ,UK" 25127c2d9f14d36f03d200a65de8446f6a0e3bd6,EVALUATING THE PERFORMANCE OF DEEP SUPERVISED AUTO ENCODER IN SINGLE SAMPLE FACE RECOGNITION PROBLEM USING KULLBACK-LEIBLER DIVERGENCE SPARSITY REGULARIZER,"Journal of Theoretical and Applied Information Technology 20th May 2016. Vol.87. No.2 © 2005 - 2016 JATIT & LLS. All rights reserved. ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 EVALUATING THE PERFORMANCE OF DEEP SUPERVISED AUTO ENCODER IN SINGLE SAMPLE FACE RECOGNITION PROBLEM USING KULLBACK-LEIBLER DIVERGENCE SPARSITY REGULARIZER OTNIEL Y. VIKTORISA, 2ITO WASITO, 2ARIDA F. SYAFIANDINI Faculty of Computer of Computer Science, Universitas Indonesia, Kampus UI Depok, Indonesia E-mail: ," 25474c21613607f6bb7687a281d5f9d4ffa1f9f3,Recognizing disguised faces,"This article was downloaded by: [Carnegie Mellon University] On: 03 May 2012, At: 06:22 Publisher: Psychology Press Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, Visual Cognition Publication details, including instructions for authors nd subscription information: http://www.tandfonline.com/loi/pvis20 Recognizing disguised faces Giulia Righi a , Jessie J. Peissig b & Michael J. Tarr c Children's Hospital Boston, Harvard Medical School, Boston, MA, USA Department of Psychology, California State University Fullerton, Fullerton, CA, USA Department of Psychology, Carnegie Mellon University, Pittsburgh, PA, USA Available online: 13 Feb 2012 To cite this article: Giulia Righi, Jessie J. Peissig & Michael J. Tarr (2012): Recognizing disguised faces, Visual Cognition, 20:2, 143-169" 2562d6ec0044eee9d604fe3a351f80d4d10d4a3d,Conditional Image-Text Embedding Networks,"Conditional Image-Text Embedding Networks Bryan A. Plummer†, Paige Kordas†, M. Hadi Kiapour‡, Shuai Zheng‡, Robinson Piramuthu‡, and Svetlana Lazebnik† University of Illinois at Urbana-Champaign† Ebay Inc.‡" 258a8c6710a9b0c2dc3818333ec035730062b1a5,Benelearn 2005 Annual Machine Learning Conference of Belgium and the Netherlands,"Benelearn 2005 Annual Machine Learning Conference of Belgium and the Netherlands CTIT PROCEEDINGS OF THE FOURTEENTH ANNUAL MACHINE LEARNING CONFERENCE OF BELGIUM AND THE NETHERLANDS Martijn van Otterlo, Mannes Poel and Anton Nijholt (eds.)" 25d48ab3b05bf299fe61ed6580674e893f08380b,"Pedestrian Detection : A Survey of Methodologies , Techniques and Current Advancements","International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 – 0882 Volume 4, Issue 1, January 2015 Pedestrian Detection: A Survey of Methodologies, Techniques and Current Advancements Tanmay Bhadra1, Joydeep Sonar2 , Arup Sarmah3 ,Chandan Jyoti Kumar4 Dept. of CSE & IT, School of Technology Assam Don Bosco University" 25d3e122fec578a14226dc7c007fb1f05ddf97f7,The first facial expression recognition and analysis challenge,"The First Facial Expression Recognition and Analysis Challenge Michel F. Valstar, Bihan Jiang, Marc Mehu, Maja Pantic, and Klaus Scherer" 25811285a1c1fd514b315d6a05adc2cb4abe9618,"DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes","DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes Berta Bescos, Jos´e M. F´acil, Javier Civera and Jos´e Neira" 250ebcd1a8da31f0071d07954eea4426bb80644c,DenseBox: Unifying Landmark Localization with End to End Object Detection,"DenseBox: Unifying Landmark Localization with End to End Object Detection Lichao Huang1 Yi Yang2 Yafeng Deng2 Institute of Deep Learning Baidu Research Yinan Yu3" 250449a9827e125d6354f019fc7bc6205c5fd549,Adversarial Reconstruction Loss,"PAIRWISE AUGMENTED GANS WITH ADVERSARIAL RECONSTRUCTION LOSS Aibek Alanov1,2,3∗, Max Kochurov1,2∗, Daniil Yashkov5, Dmitry Vetrov1,3,4 Samsung AI Center in Moscow Skolkovo Institute of Science and Technology National Research University Higher School of Economics Joint Samsung-HSE lab 5Federal Research Center ""Informatics and Management"" of the Russian Academy of Sciences" 25afa24d85e693351bad795ee1c3e801d10c4a15,"Anisotropic Gaussian Filters for Face Class Modeling August 31 , 2006","Anisotropic Gaussian Filters for Face Class Modeling August 31, 2006" 258972e9df3cdf0b8babbf607eaef7cce689226a,Multimodal Affect Recognition: Current Approaches and Challenges,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,900 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 25c57d1916c926bea3d92548f1c9836cffc23fe5,Automatic Ground Truths: Projected Image Annotations for Omnidirectional Vision,"Automatic Ground Truths: Projected Image Annotations for Omnidirectional Vision Victor Stamatescu∗, Peter Barsznica∗, Manjung Kim ∗, Kin K. Liu∗, Mark McKenzie†, Will Meakin∗, Gwilyn Saunders∗, Sebastien C. Wong† and Russell S. A. Brinkworth∗ University of South Australia, Mawson Lakes, SA, Australia Defence Science and Technology Group, Edinburgh, SA, Australia Email:" 259706f1fd85e2e900e757d2656ca289363e74aa,Improving People Search Using Query Expansion : How Friends Help To Find People,"Improving People Search Using Query Expansions How Friends Help To Find People Thomas Mensink and Jakob Verbeek LEAR - INRIA Rhˆone Alpes - Grenoble, France" 253325f09f07c2f7a05191f76e4977f473f4bac5,Filtering and Optimization Strategies for Markerless Human Motion Capture with Skeleton-based Shape Models,"FILTERING AND OPTIMIZATION STRATEGIES FOR MARKERLESS HUMAN MOTION CAPTURE WITH SKELETON-BASED SHAPE MODELS. DISSERTATION ZUR ERLANGUNG DES GRADES DES DOKTORS DER INGENIEURWISSENSCHAFTEN (DR.-ING.) DER NATURWISSENSCHAFTLICH-TECHNISCHEN FAKULT ¨ATEN DER UNIVERSIT ¨AT DES SAARLANDES VORGELEGT VON JUERGEN GALL SAARBR ¨UCKEN" 257e61e6b38ae23b7ddce9907c05b0e78be4d79d,The LORACs prior for VAEs: Letting the Trees Speak for the Data,"The LORACs prior for VAEs: Letting the Trees Speak for the Data Sharad Vikram U.C. San Diego1 Matthew D. Hoffman Matthew J. Johnson Google AI Google Brain" 25885e9292957feb89dcb4a30e77218ffe7b9868,Analyzing the Affect of a Group of People Using Multi-modal Framework,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2016 Analyzing the Affect of a Group of People Using Multi-modal Framework Xiaohua Huang, Abhinav Dhall, Xin Liu, Guoying Zhao, Jingang Shi, Roland Goecke and Matti Pietik¨ainen" 551fa37e8d6d03b89d195a5c00c74cc52ff1c67a,GeThR-Net: A Generalized Temporally Hybrid Recurrent Neural Network for Multimodal Information Fusion,"GeThR-Net: A Generalized Temporally Hybrid Recurrent Neural Network for Multimodal Information Fusion Ankit Gandhi1 ∗, Arjun Sharma1 ∗ , Arijit Biswas2, and Om Deshmukh1 Xerox Research Centre India; 2 Amazon Development Center India (*-equal contribution)" 558613d96d7c125c00eae0c58c56ee6983208fd5,Identification of Unmodeled Objects from Symbolic Descriptions,"Identification of Unmodeled Objects from Symbolic Descriptions* Andrea Baisero, Stefan Otte, Peter Englert and Marc Toussaint" 5523c9ed32d2e5acd09cccf4f0370f9dd3d9a6c4,Improving the Egomotion Estimation by Correcting the Calibration Bias,"Improving the Egomotion Estimation by Correcting the Calibration Bias University of Zagreb Faculty of Electrical Engineering and Computing, Unska 3, 10000 Zagreb, Croatia Ivan Kreˇso and Siniˇsa ˇSegvi´c fivan.kreso, Keywords: stereo vision, camera motion estimation, visual odometry, feature tracking, camera calibration, camera model ias, deformation field" 55eaece6db38d90704081ddcef06339cc5af1016,Representing 3 D models for alignment and recognition,"Representing 3D models for alignment and recognition Mathieu Aubry To cite this version: Mathieu Aubry. Representing 3D models for alignment and recognition. Computer Vision and Pattern Recognition [cs.CV]. ENS, 2015. English. HAL Id: tel-01160300 https://tel.archives-ouvertes.fr/tel-01160300 Submitted on 9 Jun 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires publics ou priv´es." 5582bebed97947a41e3ddd9bd1f284b73f1648c2,Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,"Visual Explanations from Deep Networks via Gradient-based Localization Grad-CAM: Why did you say that? Ramprasaath R. Selvaraju Abhishek Das Devi Parikh Ramakrishna Vedantam Dhruv Batra Virginia Tech Michael Cogswell {ram21, abhshkdz, vrama91, cogswell, parikh, (a) Original Image (b) Guided Backprop ‘Cat’ (c) Grad-CAM for ‘Cat’ (d) Guided Grad-CAM ‘Cat’ (e) Occlusion Map ‘Cat’ (f) ResNet Grad-CAM ‘Cat’ (g) Original Image (h) Guided Backprop ‘Dog’ (i) Grad-CAM for ‘Dog’ (l) ResNet Grad-CAM ‘Dog’" 5522073ebd53a6502cec9d716a77bb2c18aca593,Multi-view Body Part Recognition with Random Forests,"KAZEMI, BURENIUS, AZIZPOUR, SULLIVAN: MULTI-VIEW BODY PART RECOGNITION 1 Multi-view Body Part Recognition with Random Forests CVAP / KTH The Royal Institute of Technology Stockholm, Sweden Vahid Kazemi Magnus Burenius Hossein Azizpour Josephine Sullivan" 55956278efa78ccb59660a48c4ce9ad3e7d88e70,Video Based Group Tracking and Management,"Video Based Group Tracking and Management Am(cid:19)erico Pereira1;2, Alexandra Familiar1;2, Bruno Moreira1;2, Teresa Terroso1;4, Pedro Carvalho1;3, and Lu(cid:19)(cid:16)s C^orte-Real1;2 INESC TEC, Portugal Faculty of Engineering of the University of Porto, Porto, Portugal School of Engineering, Polytechnic Institute of Porto, Porto, Portugal The School of Management and Industrial Studies, Polytechnic Institute of Porto, Vila do Conde, Portugal" 551fedfeaf55e3f7a7cf19d2b21f1a56f8cbe9f6,Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems,"Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems Yu Yao1∗, Mingze Xu2∗, Chiho Choi3, David J. Crandall2, Ella M. Atkins1, and Behzad Dariush3" 5582aafd943f2b67805cdb4aba9e2f288dfe0ca8,"Human Object Sketches: Datasets, Descriptors, Computational Recognition and 3d Shape Retrieval","Human Object Sketches: Datasets, Descriptors, Computational Recognition and 3d Shape Retrieval vorgelegt von Mathias Eitz, Dipl.-Inf., M.Eng. us Friedrichshafen von der Fakultät IV - Elektrotechnik und Informatik der Technischen Universität Berlin zur Erlangung des akademischen Grades Doktor der Ingenieurwissenschaften – Dr.-Ing. – genehmigte Dissertation Promotionsausschuss: Vorsitzender: Prof. Dr. Oliver Brock Gutachter: Prof. Dr. Marc Alexa Gutachter: Prof. Tamy Boubekeur, PhD Tag der wissenschaftlichen Aussprache: 07.12.2012 Berlin 2012" 55dcaee65936583846e8c4fa36589df066ebadfa,Learning to Relate Literal and Sentimental Descriptions of Visual Properties,"Atlanta, Georgia, 9–14 June 2013. c(cid:13)2013 Association for Computational Linguistics Proceedings of NAACL-HLT 2013, pages 416–425," 55c40cbcf49a0225e72d911d762c27bb1c2d14aa,Indian Face Age Database : A Database for Face Recognition with Age Variation,"Indian Face Age Database: A Database for Face Recognition with Age Variation {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 126 Number 5 Year of Publication: 2015 Authors: Reecha Sharma, M.S. Patterh 10.5120/ijca2015906055 {bibtex}2015906055.bib{/bibtex}" 554b53f6e5e37d0f8c8eade1a962b39ce591f6ae,"COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval","COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval Xirong Li, Xiaoxu Wang, Chaoxi Xu, Weiyu Lan, Qijie Wei, Gang Yang, Jieping Xu Key Lab of Data Engineering and Knowledge Engineering, Renmin University of China Multimedia Computing Lab, Renmin University of China" 5502dfe47ac26e60e0fb25fc0f810cae6f5173c0,Affordance Prediction via Learned Object Attributes,"Affordance Prediction via Learned Object Attributes Tucker Hermans James M. Rehg Aaron Bobick" 558719ec858120908ef40b27a5d32904a68f6dd9,Mini Cooper Mini Driggs Idaho Black cat Cat Felix Bombay Posing Windows Bay Beach Boxing,"Towards an Automatic Evaluation of Retrieval Performance with Large Scale Image Collections Adrian Popescu1, Eleftherios Spyromitros-Xioufis2, Symeon Papadopoulos2, Hervé Le Borgne1, Ioannis Kompatsiaris2 CEA, LIST, 91190 Gif-sur-Yvette, France, CERTH-ITI, Thermi-Thessaloniki, Greece," 55cad1f4943018459b761f89afd9292d347610f2,Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz, 55079a93b7d1eb789193d7fcdcf614e6829fad0f,Efficient and Robust Inverse Lighting of a Single Face Image Using Compressive Sensing,"Efficient and Robust Inverse Lighting of a Single Face Image using Compressive Sensing Miguel Heredia Conde†, Davoud Shahlaei#, Volker Blanz# and Otmar Loffeld† Center for Sensor Systems† (ZESS) and Institute for Vision and Graphics#, University of Siegen 57076 Siegen, Germany" 554b9478fd285f2317214396e0ccd81309963efd,Spatio-Temporal Action Localization For Human Action Recognition in Large Dataset,"Spatio-Temporal Action Localization For Human Action Recognition in Large Dataset Sameh MEGRHI1, Marwa JMAL 2, Azeddine BEGHDADI1 and Wided Mseddi1,2 L2TI, Institut Galil´ee, Universit´e Paris 13, France; SERCOM, Ecole Polytechnique de Tunisie" 5556234869c36195ffdcd29349e5dcdf695023e9,Minimum Distance between Pattern Transformation Manifolds: Algorithm and Applications,"JULY 2009 Minimum Distance between Pattern Transformation Manifolds: Algorithm and Applications Effrosyni Kokiopoulou, Student Member, IEEE, and Pascal Frossard, Senior Member, IEEE" 55c22f9c8f76b40793a8473248873f726abd8ce9,Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks,"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks Jun-Yan Zhu∗ Taesung Park∗ Berkeley AI Research (BAIR) laboratory, UC Berkeley Phillip Isola Alexei A. Efros Figure 1: Given any two unordered image collections X and Y , our algorithm learns to automatically “translate” an image from one into the other and vice versa: (left) Monet paintings and landscape photos from Flickr; (center) zebras and horses from ImageNet; (right) summer and winter Yosemite photos from Flickr. Example application (bottom): using a collection of paintings of famous artists, our method learns to render natural photographs into the respective styles." 555488f1da920bb1a06b4d19ff687805993eb7fb,Finding Speaker Face Region by Audiovisual Correlation,"Author manuscript, published in ""Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications - M2SFA2 008, Marseille : France (2008)""" 55ba5e4c07f6ecf827bfee04e96de35a170f7485,MODELING THE HUMAN FACE THROUGH MULTIPLE VIEW THREE-DIMENSIONAL STEREOPSIS : A SURVEY AND COMPARATIVE ANALYSIS OF FACIAL RECOGNITION OVER MULTIPLE MODALITIES,"This Dissertation entitled MODELING THE HUMAN FACE THROUGH MULTIPLE VIEW THREE-DIMENSIONAL STEREOPSIS: A SURVEY AND COMPARATIVE ANALYSIS OF FACIAL RECOGNITION OVER MULTIPLE MODALITIES typeset with nddiss2"" v1.0 (2004/06/15) on July 26, 2006 for Xin Chen This LATEX 2"" class(cid:12)le conforms to the University of Notre Dame style guide- lines established in Spring 2004. However it is still possible to generate a non- onformant document if the published instructions are not followed! Be sure to re- fer to the published Graduate School guidelines at http://graduateschool.nd.edu s well. It is YOUR resposnsibility to ensure that the Chapter titles and Table caption titles are put in CAPS LETTERS. This class(cid:12)le does NOT do that! This way, you have total control over how you want the symbols and sub-/superscripts in titles and captions look like. This summary page can be disabled by specifying the nosummary option to the class invocation. (i.e., ndocumentclass[...,nosummary,...]fnddiss2eg) THIS PAGE IS NOT PART OF THE THESIS, BUT" 558fd79d8f0d7b05c3db32b8efa0cce4bd5d9970,"Biometrics at the frontiers , assessing the impact on Society Technical impact of Biometrics","Biometrics at the frontiers, assessing the impact on Society Technical impact of Biometrics Bernadette Dorizzi Background paper for the Institute of Prospective Technological Studies, DG JRC – Sevilla, European Commission January 2005 Legal notice Neither the European Commission nor any person acting on behalf of the Commission is responsible for the use which might be made of the following information. Disclaimer The author of this report is solely responsible for the content, style, language and editing. The views expressed do not necessarily reflect those of the European Commission. Reproduction is authorised provided the source is acknowledged © European Communities, 2005" 555b332252522fce0f31b0c0b7630cf4f36ba0a5,Face processing in Williams syndrome and Autism,"Face processing in Williams syndrome and Autism Deborah Michelle Riby Department of Psychology, University of Stirling" 55a158f4e7c38fe281d06ae45eb456e05516af50,Simile Classifiers for Face Classification,"The 22nd International Conference on Computer Graphics and Vision GraphiCon’2012" 5543224d6f8e22e7eaabfcbc4bed9e8a9451e3f8,Automatische Bildfolgenanalyse mit statistischen Mustererkennungsverfahren,"Automatische Bildfolgenanalyse mit statistischen Mustererkennungsverfahren Vom Fachbereich Elektrotechnik der Gerhard-Mercator-Universit¨at Duisburg zur Erlangung des akademischen Grades eines Doktors der Ingenieurwissenschaften genehmigte Dissertation Dipl.-Ing. Stefan Eickeler us Duisburg Referent: Prof. Dr. Gerhard Rigoll Korreferent: Prof. Dr. Martin Reiser Tag der m¨undlichen Pr¨ufung: 5. November 2001" 550c369cc3080c03b89d738d82f1ed50145c5aa7,"Information, Technology, and Information Worker Productivity","Information, Technology and Information Worker Productivity NYU Stern School of Business & MIT, 44 West 4th Street Room: 8-81, New York, NY 10012 MIT Sloan School of Management, Room: E53-313, 50 Memorial Drive, Cambridge, MA 02142 Sinan Aral Erik Brynjolfsson Marshall Van Alstyne Boston University & MIT, 595 Commonwealth Avenue, Boston, MA 02215 We study the fine-grained relationships among information flows, IT use, and individual information-worker produc- tivity, by analyzing work at a midsize executive recruiting firm. We analyze both project-level and individual-level performance using: (1) direct observation of over 125,000 e-mail messages over a period of 10 months by individual workers (2) detailed accounting data on revenues, compensation, project completion rates, and team membership for over 1300 projects spanning 5 years, and (3) survey data on a matched set of the same workers’ IT skills, IT use and in- formation sharing. These detailed data permit us to econometrically evaluate a multistage model of production and in- teraction activities at the firm, and to analyze the relationships among communications flows, key technologies, work practices, and output. We find that (a) the structure and size of workers’ communication networks are highly correlated with their performance; (b) IT use is strongly correlated with productivity but mainly by allowing multitasking rather than by speeding up work; (c) productivity is greatest for small amounts of multitasking but beyond an optimum, mul- titasking is associated with declining project completion rates and revenue generation; and (d) asynchronous informa- tion seeking such as email and database use promotes multitasking while synchronous information seeking over the phone shows a negative correlation. Overall, these data show statistically significant relationships among social net-" 55ea0c775b25d9d04b5886e322db852e86a556cd,DOCK: Detecting Objects by transferring Common-sense Knowledge,"DOCK: Detecting Objects y transferring Common-sense Knowledge Santosh Divvala2,3[0000−0003−4042−5874], Ali Farhadi2,3[0000−0001−7249−2380], and Krishna Kumar Singh1,3[0000−0002−8066−6835], Yong Jae Lee1[0000−0001−9863−1270] University of California, Davis 2University of Washington 3Allen Institute for AI https://dock-project.github.io" 5592574c82eec9367e9173b7820ff329a27b6c21,Image Enhancement and Automated Target Recognition Techniques for Underwater Electro-Optic Imagery,"Image Enhancement and Automated Target Recognition Techniques for Underwater Electro-Optic Imagery Thomas Giddings (PI), Cetin Savkli and Joseph Shirron Metron, Inc. 1911 Freedom Dr., Suite 800 Reston, VA 20190 phone: (703) 437-2428 fax: (703) 787-3518 email: Contract Number N00014-07-C-0351 http:www.metsci.com LONG TERM GOALS The long-term goal of this project is to provide a flexible, accurate and extensible automated target recognition (ATR) system for use with a variety of imaging and non-imaging sensors. Such an ATR system, once it achieves a high level of performance, can relieve human operators from the tedious usiness of pouring over vast quantities of mostly mundane data, calling the operator in only when the omputer assessment involves an unacceptable level of ambiguity. The ATR system will provide most leading edge algorithms for detection, segmentation, and classification while incorporating many novel lgorithms that we are developing at Metron. To address one of the most critical challenges in ATR technology, the system will also provide powerful feature extraction routines designed for specific pplications of current interest. OBJECTIVES" 55c68c1237166679d2cb65f266f496d1ecd4bec6,Learning to score the figure skating sports videos,"Learning to Score Figure Skating Sport Videos Chengming Xu, Yanwei Fu, Zitian Chen,Bing Zhang, Yu-Gang Jiang, Xiangyang Xue" 550edcdc27aff4e7ea8807356a265a0031434a49,Fine-Grained Recognition with Automatic and Efficient Part Attention,"Fine-Grained Recognition with Automatic and Efficient Part Attention Xiao Liu, Tian Xia, Jiang Wang, Yi Yang, Feng Zhou and Yuanqing Lin Baidu Research {liuxiao12,xiatian,wangjiang03, yangyi05, zhoufeng09," 5520fdb531a27bebe7df8062dd5450344dea107c,DepthComp: Real-time Depth Image Completion Based on Prior Semantic Scene Segmentation,"ATAPOUR-ABARGHOUEI, BRECKON: REAL-TIME DEPTH IMAGE COMPLETION DepthComp: Real-time Depth Image Completion Based on Prior Semantic Scene Segmentation Amir Atapour-Abarghouei Toby P. Breckon Engineering and Computer Science Durham University Durham, UK" 55202f10bb1d7640b0b279a4cdc8e9925cd9ef81,ICM: An Intuitive Model Independent and Accurate Certainty Measure for Machine Learning, 559295770dc2e2e3a1348df31ac5c3f3e66f1764,Generating Multiple Hypotheses for Human 3D Pose Consistent with 2D Joint Detections,"Generating Multiple Hypotheses for Human 3D Pose Consistent with 2D Joint Detections Johns Hopkins University Johns Hopkins University Alan L. Yuille Baltimore, USA Ehsan Jahangiri Baltimore, USA" 558c587373e2ea44898f70de7858da71aa217b8d,Cross-Lingual Image Caption Generation,"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1780–1790, Berlin, Germany, August 7-12, 2016. c(cid:13)2016 Association for Computational Linguistics" 55e8cfd4a96bdc77d10459c0aa73991ff098c60e,Nonnegative Discriminant Matrix Factorization,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TCSVT.2016.2539779, IEEE Transactions on Circuits and Systems for Video Technology Copyright (c) 2016 IEEE. Personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending an email to Nonnegative Discriminant Matrix Factorization Yuwu Lu, Zhihui Lai, Yong Xu, Senior Member, IEEE, Xuelong Li, Fellow, IEEE, David Zhang, Fellow, IEEE and Chun Yuan" 55ef8c3c28e2afda486d8471205204927127c605,Multiview Alignment Hashing for Efficient Image Search,"Multiview Alignment Hashing for Efficient Image Search Li Liu, Mengyang Yu, Student Member, IEEE, and Ling Shao, Senior Member, IEEE" 555222f2ad6dae447eef04f96fa40c1b8a397150,CaloriNet: From silhouettes to calorie estimation in private environments,"CaloriNet: From silhouettes to calorie estimation in private environments Alessandro Masullo∗ Tilo Burghardt Victor Ponce-López Dima Damen Majid Mirmehdi Sion Hannuna June 22, 2018" 4e25cd4e40494aa5073fcfbef7506336b84152f4,"Independent Component Analysis, Principal Component Analysis and Rough Sets in Face Recognition","Independent Component Analysis, Principal Component Analysis and Rough Sets in Face Recognition Roman W. ´Swiniarski1 and Andrzej Skowron2 Department of Mathematical and Computer Sciences San Diego State University 5500 Campanile Drive San Diego, CA 92182, USA Institute of Computer Science, Polish Academy of Sciences Ordona 21, 01-237 Warsaw, Poland Institute of Mathematics, Warsaw University Banacha 2, 02-097 Warsaw, Poland" 4e4b41b8d9f27e262e4a853082e690c32c490954,Towards MultiView Object Class Detection,"Author manuscript, published in ""IEEE Conference on Computer Vision & Pattern Recognition (CPRV '06) 2 (2006) 1589"" DOI : 10.1109/CVPR.2006.311" 4ecaa651722a98c2847377f3ae1c70294b4791ce,Few-Example Object Detection with Model Communication.,"Few-Example Object Detection with Model Communication Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng" 4e8206dd2e163c6a139bfd0ec3adf410e7b78c4a,A Multi-scale Boosted Detector for Efficient and Robust Gesture Recognition,"A Multi-scale Boosted Detector for Ef‌f‌icient and Robust Gesture Recognition Camille Monnier, Stan German, Andrey Ost Charles River Analytics Cambridge, MA, USA" 4e23628370d3ca9695c8eb1eee488a9eea4d5eec,Contributions to Statistical Signal Processing with Applications in Biomedical Engineering. (Contributions au traitement statistique du signal avec des applications biomédicales),"N° d’ordre : 2012telb0244 Sous le sceau de lSous le sceau de l’’UUniversitniversitéé européenne de Beuropéenne de Bretagneretagne Télécom Bretagne En habilitation conjointe avec l’Université de Bretagne Occidentale Ecole Doctorale – SICMA CONTRIBUTIONS TO STATISTICAL SIGNAL PROCESSING WITH APPLICATIONS IN BIOMEDICAL ENGINEERING Thèse de Doctorat Mention : STIC – Science et Technologies Information Communication Présentée par Quang-Thang NGUYEN Département : Signal et Communications Laboratoire : Lab-STICC Pôle: CID Directeur de thèse : Dominique PASTOR Soutenue le 23 Novembre 2012 Jury : M. Lionel Fillatre – Professeur, I3S (Rapporteur) M. Alfredo Hernandez – Chargé de recherche (HDR), LTSI INSERM U642 (Rapporteur) M. Dominique Pastor – Professeur, TELECOM Bretagne (Directeur de thèse) M. Erwan L’Her – Professeur, LaTIM INSERM U1101 (Examinateur) M. Lotfi Senhadji – Professeur, LTSI INSERM U642 (Examinateur) M. Emanuel Radoi – Professeur, UBO/Lab-STICC CNRS UMR 6285 (Examinateur) M. Ronan Fablet – Maître de conférence (HDR), TELECOM Bretagne (Examinateur) M. François Lellouche – Professeur, Université Laval (Québec –Canada) (Invité)" 4e608c77043f56b0abfb2760fb2fd2516b5412b0,Spectral Face Recognition Using Orthogonal Subspace Bases, 4ecd459aa4b4590bdc552e07b6d0bbe132fb1fcf,Learning of Graph Compressed Dictionaries for Sparse Representation Classification,"Learning of Graph Compressed Dictionaries for Sparse Representation Classification Farshad Nourbakhsh and Eric Granger Laboratoire d’imagerie de vision et d’intelligence artificielle ´Ecole de technologie sup´erieure, Universit´e du Qu´ebec, Montr´eal, Canada Keywords: Matrix Factorization, Graph Compression, Dictionary Learning, Sparse Representation Classification, Clustering, Face Recognition, Video Surveillance" 4e27fec1703408d524d6b7ed805cdb6cba6ca132,SSD-Sface: Single shot multibox detector for small faces,"SSD-Sface: Single shot multibox detector for small faces C. Thuis" 4e1029a43324eccae1f25a342cd615f57c47a740,Circle-based eye center localization (CECL),"This is the non-final version of the paper. The final version is published in the 14th IAPR International Conference on Machine Vision Applications (18-22 May 2015, http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7153202). Content may change prior to final publication. Circle-based Eye Center Localization (CECL) Yustinus Eko Soelistio1,2, Eric Postma2, Alfons Maes2 Information System Department1, Tilburg center for Cognition and Communication2 Universitas Multimedia Nusantara1, Tilburg University2 Tangerang, Indonesia1, Tilburg, The Netherlands2" 4e5698894946680e4d6e766346355b2dc1959819,Cross-pose Facial Expression Recognition,Cross-pose Facial Expression Recognition 4ed0be0b5d67cff63461ba79f2a7928d652cf310,Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey,"JOURNAL OF LATEX CLASS FILES, VOL. PP, AUGUST 2017 Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey ACKNOWLEDGEMENTS: The authors thank Nicholas Carlini (UC Berkeley) and Dimitris Tsipras (MIT) for feedback to improve the survey quality. We also acknowledge X. Huang (Uni. Liverpool), K. R. Reddy (IISC), E. Valle (UNICAMP), Y. Yoo (CLAIR) and others for providing pointers to make the survey more comprehensive. This research was supported by ARC grant DP160101458. Naveed Akhtar and Ajmal Mian" 4ec3c7fa51d823a43b3808c7c6baa2e153104bdf,Neuron Pruning for Compressing Deep Networks using Maxout Architectures,"Neuron Pruning for Compressing Deep Networks using Maxout Architectures Fernando Moya Rueda, Rene Grzeszick, Gernot A. Fink TU Dortmund University Department of Computer Science" 4ee380e444063f9b948a2fd82e5c11b97a570ad1,Operating system support to an online hardware-software co-design scheduler for heterogeneous multicore architectures,"Universidade de São Paulo Biblioteca Digital da Produção Intelectual - BDPI Departamento de Sistemas de Computação - ICMC/SSC Comunicações em Eventos - ICMC/SSC 014-08-20 Operating system support to an online hardware-software co-design scheduler for heterogeneous multicore architectures IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, 0th, 2014, Chongqing. http://www.producao.usp.br/handle/BDPI/48567 Downloaded from: Biblioteca Digital da Produção Intelectual - BDPI, Universidade de São Paulo" 4e12080616da4b540c8f79db2dd1b654cd8345ce,Pose-Driven Deep Models for Person Re-Identification.,"Pose-Driven Deep Models for Person Re-Identification Masters thesis of Andreas Eberle At the faculty of Computer Science Institute for Anthropomatics and Robotics Reviewer: Second reviewer: Advisors: Prof. Dr.-Ing. Rainer Stiefelhagen Prof. Dr.-Ing. Jürgen Beyerer Dr.-Ing. Saquib Sarfraz Dipl.-Inform. Arne Schumann Duration: 31. August 2017 – 8. February 2018 KIT – University of the State of Baden-Wuerttemberg and National Laboratory of the Helmholtz Association www.kit.edu" 4e613c9342d6e90f7af5fd3f246c6d82a33fe98d,Estimating Human Pose in Images,"Estimating Human Pose in Images Navraj Singh December 11, 2009 Introduction This project attempts to improve the performance of an existing method of estimating the pose of humans in still images. Tasks such as object detection and classification have received much attention already in the literature. However, sometimes we are interested in more detailed aspects of objects like pose. This is a challenging task due to the large variety of poses an object can take in a variety of settings. For human pose estimation, aspects such as clothing, occlusion of body parts, etc. make the task even harder. The approaches taken up in the literature to solve this problem focus on either a top-down approach, bottom-up approach, or a hybrid of the two. The top-down approach involves comparing test images with stored examples of humans in various poses using some similarity measure. This approach might require a very large set of examples of human poses. The bottom-up approach, on the other hand, uses low level human body part detectors and in some manner assembles the information to predict the entire ody pose. This project attempts to build upon a mostly bottom-up approach, called LOOPS (Localizing Object Outlines using Probabilistic Shape), that was developed in [1] by G. Heitz, et al. in Prof. Daphne Koller's group. Specifically, we investigate the onstruction and incorporation of a skin detector into the LOOPS pipeline, and a couple of pairwise features in the appearance model. The overall improvement in the localization is negligible, with some improvement in head localization. Since the improvements considered are within the framework of LOOPS, a brief overview of the LOOPS method is discussed next. Brief Overview of the LOOPS method as applied to humans The main random variables defined in the LOOPS method, described in detail in [1], are the locations of a set of key" 4ee87ed965e78adb1035a5322350afac9ca901f5,Multi-target tracking of time-varying spatial patterns,"Multi-Target Tracking of Time-varying Spatial Patterns Jingchen Liu1 Yanxi Liu1,2 Department of Computer Science and Engineering Department of Electrical Engineering The Pennsylvania State University University Park, PA 16802, USA {jingchen," 4eda4c1c63d96c2764577fed9a2bb3e10937e551,Robust Facial Feature Extraction Using Embedded Hidden Markov Model for Face Recognition under Large Pose Variation,"MVA2007 IAPR Conference on Machine Vision Applications, May 16-18, 2007, Tokyo, JAPAN Robust Facial Feature Extraction Using Embedded Hidden Markov Model for Face Recognition under Large Pose Variation , Ming-Hsuan Yang3 and Yi-Ping Hung1 Ping-Han Lee1 Dept. of Computer Science and Information Engineering, Nation Taiwan University , Yun-Wen Wang1 , Jison Hsu2 PENPOWER Technology Ltd., Taiwan Honda Research Institute ontact email:" 4e97b53926d997f451139f74ec1601bbef125599,Discriminative Regularization for Generative Models,"Discriminative Regularization for Generative Models Alex Lamb, Vincent Dumoulin and Aaron Courville Montreal Institute for Learning Algorithms, Universit´e de Montr´eal" 4ebf84c6389e842e90c39850f0152671ba7fa0dc,Adversarial Attribute-Image Person Re-identification,"Adversarial Attribute-Image Person Re-identification Zhou Yin, Wei-Shi Zheng, Ancong Wu, Hong-Xing Yu, Hai Wan, Xiaowei Guo, Feiyue Huang, Jianhuang Lai For reference of this work, please cite: Adversarial Attribute-Image Person Re-identification Zhou Yin, Wei-Shi Zheng, Ancong Wu, Hong-Xing Yu, Hai Wan, Xiaowei Guo, Feiyue Huang, Jianhuang Lai, IJCAI, 2018 title={Adversarial Attribute-Image Person Re-identification}, uthor={Zhou Yin, Wei-Shi Zheng, Ancong Wu, Hong-Xing Yu, Hai Wan, Xiaowei Guo, Feiyue Huang, Jianhuang Lai}, journal={ International Joint Conference on Artificial Intelligence}, year={2018}" 4e6ff8ff80a1610bb841b669bb7667413ed2982f,Dependence Characteristics of Face Recognition Algorithms,"Dependence Characteristics of Face Recognition Algorithms Patrick Grother, P. Jonathon Phillips, Stefan Leighy, Alan Heckerty, NIST, Gaithersburg, MD Elaine Newton Rand Corporation Pittsburgh, PA Andrew Rukhin University of Maryland Baltimore County Baltimore, MD" 4ec4392246a7760d189cd6ea48a81664cd2fe4bf,GPU Accelerated ACF Detector, 4edd41dcd724df28302cc5a7bc0bee348fc81456,Large Scale Correlation Clustering Optimization,"Shai Bagon Meirav Galun Dept. of Computer Science and Applied Mathmatics The Weizmann Institute of Scince http://www.wisdom.weizmann.ac.il/∼{bagon, meirav} Rehovot 76100, Israel" 4ec4e9a682cab979e90c5029d8455e852abedf26,A New Approach for Face Recognition Using Power Method Algorithm,"Proc. Int. Conf. on Advances in Computing, Control, and Telecommunication Technologies, ACT A New Approach for Face Recognition Using Power Method Algorithm Shivam Gupta1,1, Vilas H. Gaidhane1 and Vijander Singh1 ICE Division Netaji Subhas Institute of Technology, University of Delhi, Sector-3, Dwarka, New Delhi, 110078 India" 4e32fbb58154e878dd2fd4b06398f85636fd0cf4,A Hierarchical Matcher using Local Classifier Chains,"A Hierarchical Matcher using Local Classifier Chains L. Zhang and I.A. Kakadiaris Computational Biomedicine Lab, 4849 Calhoun Rd, Rm 373, Houston, TX 77204" 4efb08fcd652c60764b6fd278cee132b71c612a1,Pixel Deconvolutional Networks,"PIXEL DECONVOLUTIONAL NETWORKS Hongyang Gao Washington State University Hao Yuan Washington State University Zhengyang Wang Washington State University Shuiwang Ji Washington State University" 4ea53e76246afae94758c1528002808374b75cfa,A Review of Scholastic Examination and Models for Face Recognition and Retrieval in Video,"Lasbela, U. J.Sci. Techl., vol.IV , pp. 57-70, 2015 Review ARTICLE A Review of Scholastic Examination and Models for Face Recognition ISSN 2306-8256 nd Retrieval in Video Varsha Sachdeva1, Junaid Baber2, Maheen Bakhtyar2, Muzamil Bokhari3, Imran Ali4 Department of Computer Science, SBK Women’s University, Quetta, Balochistan Department of CS and IT, University of Balochistan, Quetta Department of Physics, University of Balochistan, Quetta Institute of Biochemistry, University of Balochistan, Quetta" 4e7f0dfc390f88623c825fe702da45b994342011,Photorealistic Face De-Identification by Aggregating Donors' Face Components,"Photorealistic Face de-Identification by Aggregating Donors’ Face Components Saleh Mosaddegh, Lo¨ıc Simon, Fr´ed´eric Jurie To cite this version: Saleh Mosaddegh, Lo¨ıc Simon, Fr´ed´eric Jurie. Photorealistic Face de-Identification by Aggre- gating Donors’ Face Components. Asian Conference on Computer Vision, Nov 2014, Singapore. pp.1-16, 2014. HAL Id: hal-01070658 https://hal.archives-ouvertes.fr/hal-01070658 Submitted on 2 Oct 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 4eb600aa4071b9a73da49e5374d6e22ca46eaba6,Understanding bag-of-words model: a statistical framework,"Noname manuscript No. (will be inserted by the editor) Understanding Bag-of-Words Model: A Statistical Framework Yin Zhang ⋅ Rong Jin ⋅ Zhi-Hua Zhou Received: date / Accepted: date" 4eca3e3c4876fc7ec81224d4ec2f159c9e7c72c3,Facial recognition using new LBP representations, 4e33798e364826af1241d28d57977bec9a579709,Active learning with version spaces for object detection,"Active learning with version spaces for object detection 1 Soumya Roy 2 Vinay P. Namboodiri 2 Arijit Biswas 3" 4e6c9be0b646d60390fe3f72ce5aeb0136222a10,Long-Term Temporal Convolutions for Action Recognition,"Long-term Temporal Convolutions for Action Recognition G¨ul Varol, Ivan Laptev, and Cordelia Schmid, Fellow, IEEE" 4e0e49c280acbff8ae394b2443fcff1afb9bdce6,Automatic Learning of Gait Signatures for People Identification,"Automatic learning of gait signatures for people identification F.M. Castro Univ. of Malaga fcastrouma.es M.J. Mar´ın-Jim´enez Univ. of Cordoba mjmarinuco.es N. Guil Univ. of Malaga nguiluma.es N. P´erez de la Blanca Univ. of Granada nicolasugr.es" 4eb22856671b9340e5ae532a021be62b9d31c9bc,THE MINORITY GLASS CEILING HYPOTHESIS : EXPLORING REASONS AND REMEDIES FOR THE UNDERREPRESENTATION OF RACIAL-ETHNIC MINORITIES IN LEADERSHIP POSITIONS,"THE MINORITY GLASS CEILING HYPOTHESIS: EXPLORING REASONS AND REMEDIES FOR THE UNDERREPRESENTATION OF RACIAL-ETHNIC MINORITIES IN LEADERSHIP POSITIONS Seval Gündemir" 4e3c07283334a9b90dac011033fa2403bcf3c473,A novel feature selection method and its application,"J Intell Inf Syst (2013) 41:235–268 DOI 10.1007/s10844-013-0243-x A novel feature selection method and its application Bing Li· Tommy W. S. Chow· Di Huang Received: 11 April 2012 / Revised: 8 March 2013 / Accepted: 11 March 2013 / Published online: 4 April 2013 © Springer Science+Business Media New York 2013" 4e61f3dc6aa7994613a3708e823aadd478c73f5f,Generating Discriminative Object Proposals via Submodular Ranking,"Generating Discriminative Object Proposals via Submodular Ranking Yangmuzi Zhang∗, Zhuolin Jiang†, Xi Chen∗, and Larry S. Davis∗ University of Maryland at College Park, MD Raytheon BBN Technologies, USA Email:" 4e165914c800d5569fd22cd69ca2ca7d92ffe705,Graph based over-segmentation methods for 3D point clouds,"Graph Based Over-Segmentation Methods for 3D Point Clouds Yizhak Ben-Shabat · Tamar Avraham · Michael Lindenbaum · Anath Fischer Received: date / Accepted: date" 4e19917a786c611ffdecd171fae37183ad55ad49,A survey of practical adversarial example attacks,"Sun et al. Cybersecurity (2018) 1:9 https://doi.org/10.1186/s42400-018-0012-9 SURVEY Cybersecurity Open Access A survey of practical adversarial example ttacks Lu Sun, Mingtian Tan and Zhe Zhou*" 4edc7f27d4512b69be54abfc6b9876e5b00725ab,Facial Expression Recognition using Convolutional Neural Networks: State of the Art,"Facial Expression Recognition using Convolutional Neural Networks: State of the Art Christopher Pramerdorfer, Martin Kampel Computer Vision Lab, TU Wien Vienna, Austria Email:" 4e82908e6482d973c280deb79c254631a60f1631,Improving Efficiency and Scalability in Visual Surveillance Applications, 4eaaefc53fd61d27b9ce310c188fe76003a341bd,Assessing Generative Models via Precision and Recall,"Assessing Generative Models via Precision and Recall Mehdi S. M. Sajjadi∗ MPI for Intelligent Systems, Max Planck ETH Center for Learning Systems Olivier Bachem Google Brain Mario Lucic Google Brain Olivier Bousquet Google Brain Sylvain Gelly Google Brain" 4e71e03d4122aad182ad51ab187d4b55b41fc957,Clustering-Based Discriminant Analysis for Eye Detection,"Clustering-Based Discriminant Analysis for Eye Detection Shuo Chen and Chengjun Liu paper three proposes" 4e83b9cfd19b7963e2044916821d7a09bbd1574d,LINGYU ZHU TEACHING DEVELOPMENT PROJECT: GENE EXPRESSION PREDICTION WITH DEEP LEARNING,"LINGYU ZHU TEACHING DEVELOPMENT PROJECT: GENE EXPRESSION PREDICTION WITH DEEP LEARNING Master of Science thesis Examiner: University lecturer Heikki Huttunen Examiner and topic approved by the Faculty Council of the Faculty of Computing and Electrical Engineering on 1 February 2017" eacb95e81156c48f4ff7470567ba205225170fa7,Learning Aerial Image Segmentation From Online Maps,"Learning Aerial Image Segmentation from Online Maps Pascal Kaiser, Jan Dirk Wegner, Aur´elien Lucchi, Martin Jaggi, Thomas Hofmann, and Konrad Schindler" ea94d834f912f092618d030f080de8395fe39b3f,Joint autoencoders : a flexible meta-learning framework,"Under review as a conference paper at ICLR 2018 JOINT AUTOENCODERS: A FLEXIBLE META-LEARNING FRAMEWORK Anonymous authors Paper under double-blind review" ea3e3f62be20b9b11994a6308c79a286725db116,DCAR: A Discriminative and Compact Audio Representation to Improve Event Detection,"DCAR: A Discriminative and Compact Audio Representation to Improve Event Detection Liping Jing ∗ Bo Liu∗ Michael W. Mahoney § Jaeyoung Choi † Adam Janin ‡ Gerald Friedland § Julia Bernd‡" ea099ee1183145131e29009f2af0e4b13ac583f0,Effects of exposure to facial expression variation in face learning and recognition,"Psychological Research (2015) 79:1042–1053 DOI 10.1007/s00426-014-0627-8 O R I G I N A L A R T I C L E Effects of exposure to facial expression variation in face learning nd recognition Chang Hong Liu • Wenfeng Chen • James Ward Received: 25 July 2014 / Accepted: 6 November 2014 / Published online: 15 November 2014 Ó The Author(s) 2014. This article is published with open access at Springerlink.com" eaaf411826d129c2a31d997dc3f5f708a8186656,SDALF: Modeling Human Appearance with Symmetry-Driven Accumulation of Local Features,"SDALF: Modeling Human Appearance with Symmetry-Driven Accumulation of Local Features Loris Bazzani and Marco Cristani and Vittorio Murino" eabbf37742b79147c3bcf42d376dbceaae869a01,Recurrent Multimodal Interaction for Referring Image Segmentation,"Recurrent Multimodal Interaction for Referring Image Segmentation Chenxi Liu1 Zhe Lin2 Xiaohui Shen2 Jimei Yang2 Xin Lu2 Alan Yuille1 Johns Hopkins University1 Adobe Research2 {cxliu, {zlin, xshen, jimyang," ea638559b6dd6b5520f9abe2674b92c07873a157,Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks,"Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks Nicolas Audebert1,2, Bertrand Le Saux1, S´ebastien Lef`evre2 ONERA, The French Aerospace Lab, F-91761 Palaiseau, France - {nicolas.audebert,bertrand.le Univ. Bretagne-Sud, UMR 6074, IRISA, F-56000 Vannes, France -" ea2d43aa2490331cd1406e1432ce706c53139323,Tracked Instance Search,"TRACKED INSTANCE SEARCH Andreu Girbau† Ryota Hinami(cid:63) Shin’ichi Satoh(cid:63) Universitat Polit`ecnica de Catalunya, Barcelona (cid:63) National Institute of Informatics, Tokyo" eabdefeb685dd71a39417bf40247d206af4f9b9e,"Of Kith and Kin: Perceptual Enrichment, Expectancy, and Reciprocity in Face Perception.","657250 PSRXXX10.1177/1088868316657250Personality and Social Psychology ReviewCorrell et al. research-article2016 Article Of Kith and Kin: Perceptual Enrichment, Expectancy, and Reciprocity in Face Perception Personality and Social Psychology Review 1 –25 © 2016 by the Society for Personality nd Social Psychology, Inc. Reprints and permissions: sagepub.com/journalsPermissions.nav DOI: 10.1177/1088868316657250 pspr.sagepub.com Joshua Correll1, Sean M. Hudson1, Steffanie Guillermo1, nd Holly A. Earls1" eac1b644492c10546a50f3e125a1f790ec46365f,"Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection","Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection Mohammadreza Zolfaghari , Gabriel L. Oliveira, Nima Sedaghat, and Thomas Brox University of Freiburg Freiburg im Breisgau, Germany" ea572991a75acfc8a8791955f670d2c48db49023,Arbitrary-Shape object localization using adaptive image grids,"Arbitrary-Shape Object Localization using Adaptive Image Grids Chunluan Zhou and Junsong Yuan School of EEE, Nanyang Technology University, Singapore" ead2701e883174028a1b1b25472bc83bedc330aa,"Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis and Self-Organizing Map","RADIOENGINEERING, VOL. 16, NO. 1, APRIL 2007 Face Recognition Methods Based on Feedforward Neural Networks, Principal Component Analysis nd Self-Organizing Map Miloš ORAVEC, Jarmila PAVLOVIČOVÁ Dept. of Telecommunications, Faculty of Electrical Engineering and Information Technology, Slovak University of Technology, Ilkovičova 3, 812 19 Bratislava, Slovak Republic" ea8cb4a79b211fb288f747bdd64b3fc36e11c0fc,Chapter 10 Automatic Facial Action Unit Recognition by Modeling Their Semantic And Dynamic Relationships,"Chapter 10 Automatic Facial Action Unit Recognition y Modeling Their Semantic And Dynamic Relationships Yan Tong, Wenhui Liao, and Qiang Ji" ea8b306eb10ea4de4c0253d63750b29467b581e1,A Survey of the Recent Architectures of Deep Convolutional Neural Networks,"A Survey of the Recent Architectures of Deep Convolutional Neural Networks Asifullah Khan1, 2*, Anabia Sohail1 , Umme Zahoora1, and Aqsa Saeed Qureshi1 Pattern Recognition Lab, DCIS, PIEAS, Nilore, Islamabad 45650, Pakistan Deep Learning Lab, Center for Mathematical Sciences, PIEAS, Nilore, Islamabad 45650, Pakistan" ea0785c2d4ac8f8d6415cffdb83547bfc4e7adba,Spontaneous Facial Expression Recognition using Sparse Representation,"Spontaneous Facial Expression Recognition using Sparse Representation Univ. Grenoble Alpes, GIPSA-Lab, F-38000 Grenoble, France CNRS, GIPSA-Lab, F-38000 Grenoble, France Dawood Al Chanti1 and Alice Caplier1 Keywords: Dictionary learning, Random projection, Spontaneous facial expression, Sparse representation." eafda8a94e410f1ad53b3e193ec124e80d57d095,Observer-Based Measurement of Facial Expression With the Facial Action Coding System,"Jeffrey F. Cohn Zara Ambadar Paul Ekman Observer-Based Measurement of Facial Expression With the Facial Action Coding System Facial expression has been a focus of emotion research for over hundred years (Darwin, 1872/1998). It is central to several leading theories of emotion (Ekman, 1992; Izard, 1977; Tomkins, 1962) and has been the focus of at times heated debate about issues in emotion science (Ekman, 1973, 1993; Fridlund, 1992; Russell, 1994). Facial expression figures prominently in research on almost every aspect of emotion, including psychophysiology (Levenson, Ekman, & Friesen, 990), neural bases (Calder et al., 1996; Davidson, Ekman, Saron, Senulis, & Friesen, 1990), development (Malatesta, Culver, Tesman, & Shephard, 1989; Matias & Cohn, 1993), perception (Ambadar, Schooler, & Cohn, 2005), social pro- esses (Hatfield, Cacioppo, & Rapson, 1992; Hess & Kirouac, 000), and emotion disorder (Kaiser, 2002; Sloan, Straussa, Quirka, & Sajatovic, 1997), to name a few." ea8abe31f3cac058cf757f16e1eefa11295322bc,Ensemble of Deep Learned Features for Melanoma Classification,"Ensemble of Deep Learned Features for Melanoma Classification Loris Nanni1*, Alessandra Lumini2, Stefano Ghidoni1 Department of Information Engineering, University of Padua, via Gradenigo 6/B, 35131 Padova, Italy. Department of Computer Science and Engineering, University of Bologna, via Sacchi 3, 7521, Cesena (FC), Italy." ea2c44e4792c0d35af737f46a2dc2b78e6dedc8d,Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction,"Deep Stacked Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction Zhiyong Cui, Student Member, IEEE, Ruimin Ke, Student Member, IEEE, and Yinhai Wang*" ea9857a5e5c72d435054a5a73e50dafb755a2597,Comparative study of histogram distance measures for re-identification,"Comparative study of histogram distance measures for re-identification Pedro A. Mar´ın-Reyes, Javier Lorenzo-Navarro, Modesto Castrill´on-Santana Instituto Universitario SIANI Universidad de Las Palmas de Gran Canaria" eaaec63bb86ee87d56f5844951143485ce84a4ea,GANtruth – an unpaired image-to-image translation method for driving scenarios,"GANtruth – an unpaired image-to-image translation method for driving scenarios Anonymous Author(s) Affiliation Address email" ea5eaaadb8bc928fb7543d6fa24f9f4a229ff979,Mirror Neuron Forum.,"Perspectives on Psychological Science http://pps.sagepub.com/ Vittorio Gallese, Morton Ann Gernsbacher, Cecilia Heyes, Gregory Hickok and Marco Iacoboni Mirror Neuron Forum Perspectives on Psychological Science DOI: 10.1177/1745691611413392 2011 6: 369 The online version of this article can be found at: http://pps.sagepub.com/content/6/4/369 Perspectives on Psychological Science can be found at: Additional services and information for Email Alerts: Subscriptions: Reprints: Permissions: http://pps.sagepub.com/cgi/alerts http://pps.sagepub.com/subscriptions http://www.sagepub.com/journalsReprints.nav" ea3503e9dc74b30b4c98a89843fe2ea0dc9221ab,Human Action Recognition Using LBP-TOP as Sparse Spatio-Temporal Feature Descriptor,"Human Action Recognition Using LBP-TOP as Sparse Spatio-Temporal Feature Descriptor Riccardo Mattivi and Ling Shao Philips Research, Eindhoven, The Netherlands" eadf6cb8f16c507e4a73db33da201cde3d9b2f5a,PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing,"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing Dan Xu1, Wanli Ouyang2, Xiaogang Wang3, Nicu Sebe1 The University of Trento, 2The University of Sydney, 3The Chinese University of Hong Kong {dan.xu," eaa334c28bd53d2cc37c1973cd9f5f4a5be1012b,SPADE: Scalar Product Accelerator by Integer Decomposition for Object Detection,"SPADE: Scalar Product Accelerator by Integer Decomposition for Object Detection Mitsuru Ambai and Ikuro Sato Denso IT Laboratory, Inc." ea482bf1e2b5b44c520fc77eab288caf8b3f367a,Flexible Orthogonal Neighborhood Preserving Embedding,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) ea2ee5c53747878f30f6d9c576fd09d388ab0e2b,Viola-Jones based detectors: how much affects the training set?,"Viola-Jones based Detectors: How much affects the Training Set? Modesto Castrill´on-Santana, Daniel Hern´andez-Sosa, Javier Lorenzo-Navarro SIANI Edif. Central del Parque Cient´ıfico Tecnol´ogico Universidad de Las Palmas de Gran Canaria 5017 - Spain" eace134548f9be17c243b06f133bfac76a797676,ADNet: A Deep Network for Detecting Adverts,"ADNet: A Deep Network for Detecting Adverts Murhaf Hossari(cid:63)1, Soumyabrata Dev(cid:63)1, Matthew Nicholson1, Killian McCabe1, Atul Nautiyal1, Clare Conran1, Jian Tang3, Wei Xu3, and Fran¸cois Piti´e1,2 The ADAPT SFI Research Centre, Trinity College Dublin Department of Electronic & Electrical Engineering, Trinity College Dublin Huawei Ireland Research Center, Dublin" ea251fc90da36fdbaf7be76f449a9e0dac1d42ef,Brain mechanisms for processing direct and averted gaze in individuals with autism.,"J Autism Dev Disord DOI 10.1007/s10803-011-1197-x O R I G I N A L P A P E R Brain Mechanisms for Processing Direct and Averted Gaze in Individuals with Autism Naomi B. Pitskel • Danielle Z. Bolling • Caitlin M. Hudac • Stephen D. Lantz • Nancy J. Minshew • Brent C. Vander Wyk • Kevin A. Pelphrey Ó Springer Science+Business Media, LLC 2011" ea5dd7125c73756d7d81e49fa9826198f533cff7,Appearance tracking by transduction in surveillance scenarios,"8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, 2011 978-1-4577-0845-9/11/$26.00 c(cid:13)2011 IEEE" ea9cecb5b619cfa4afef6c70e193c2303696a4f9,Integration of Probabilistic Pose Estimates from Multiple Views,"Integration of Probabilistic Pose Estimates From Multiple Views ¨Ozg¨ur Erkent, Dadhichi Shukla and Justus Piater Institute of Computer Science, University of Innsbruck" eaa0433abe4601aefe865a82119b4491e3618a61,Global fitting of a facial model to facial features for model – based video coding,"Global fitting of a facial model to facial features for model–based video coding P M Hillman J M Hannah P M Grant University of Edinburgh School of Engineering and Electronics Sanderson Building, King’s Buildings, Mayfield Road, Edinburgh EH9 3JL, UK" ea4a61299b3b19adb02d4246aa33cf8e8469ce98,A Novel Technique for Face Recognition through Gabor Ordinal,"A Novel Technique for Face Recognition through Gabor Ordinal H.Swarnalatha1, A.Valli Bhasha2 PG Student. Dept. of Electronics and Communication Engineering, KSRM College of Engineering, Kadapa Email: Assistant Professor, Dept. of Electronics and Communication Engineering, KSRM College of Engineering, Kadapa" ead587db6b2b76726e98b17cb1fbf973a34ddf31,Development of an Efficient Face Recognition System Based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" ea6f5c8e12513dbaca6bbdff495ef2975b8001bd,Applying a Set of Gabor Filter to 2 D-Retinal Fundus Image to Detect the Optic Nerve Head ( ONH ),"Applying a Set of Gabor Filter to 2D-Retinal Fundus Image to Detect the Optic Nerve Head (ONH) Rached Belgacem1,2*, Hédi Trabelsi2, Ines Malek3, Imed Jabri1 Higher National School of engineering of Tunis, ENSIT, Laboratory LATICE (Information Technology and Communication and Electrical Engineering LR11ESO4), University of Tunis EL Manar. Adress: ENSIT 5, Avenue Taha Hussein, B. P. : 56, Bab Menara, 1008 Tunis; 2University of Tunis El-Manar, Tunis with expertise in Mechanic, Optics, Biophysics, Conference Master ISTMT, Laboratory of Research in Biophysics and Medical Technologies LRBTM Higher Institute of Medical Technologies of Tunis ISTMT, University of Tunis El Manar Address: 9, Rue Docteur Zouheïr Safi – 1006; 3Faculty of Medicine of Tunis; Address: 15 Rue Djebel Lakhdhar. La Rabta. 1007, Tunis - Tunisia Corresponding author: Rached Belgacem, High Institute of Medical Technologies of Tunis, ISTMT, and High National School Engineering of Tunis, Information Technology and Communication Technology and Electrical Engineering, University of Tunis El-Manar, ENSIT 5, Avenue Taha Hussein, B. P.: 56, Bab Menara, 1008 Tunis, Tunisia," ea939d72d55c095e57fedaaf2aa49f596002c196,A Part based Modeling Approach for Invoice Parsing, eaf8c104ab14600ecc5e9cce739b55280eef7ad4,Abstractive Compression of Captions with Attentive Recurrent Neural Networks,"Proceedings of The 9th International Natural Language Generation conference, pages 41–50, Edinburgh, UK, September 5-8 2016. c(cid:13)2016 Association for Computational Linguistics" ea079334121a0ba89452036e5d7f8e18f6851519,Unsupervised incremental learning of deep descriptors from video streams,"UNSUPERVISED INCREMENTAL LEARNING OF DEEP DESCRIPTORS FROM VIDEO STREAMS Federico Pernici and Alberto Del Bimbo MICC – University of Florence" ea533fac61db537fe1e1f351c98ae28db7272705,Theoretical Informatics and Applications Eye Localization for Face Recognition *,"Theoretical Informatics and Applications Informatique Th´eorique et Applications Will be set by the publisher EYE LOCALIZATION FOR FACE RECOGNITION ∗ PAOLA CAMPADELLI, RAFFAELLA LANZAROTTI, GIUSEPPE LIPORI 1" eae625274767cb695fa2121ccdcb30828ffc9b66,Social Context Modulates Facial Imitation of Children’s Emotional Expressions,"RESEARCH ARTICLE Social Context Modulates Facial Imitation of Children’s Emotional Expressions Peter A. Bos*, Nadine Jap-Tjong, Hannah Spencer, Dennis Hofman Department of Experimental Psychology, Utrecht University, Utrecht, The Netherlands" 27e97b67a8401def58eb41b4b00d3dfb0e4ad1a8,Knowledge Based Face Detection Using Fusion Features,"International Journal of Computer Engineering and Applications, ICCSTAR-2016, Special Issue, May.16 Knowledge Based Face Detection Using Fusion Features. Savitri Kulkarni Assistant Professor,Department of CSE City Engineering College, 2Annapurna N S UG Student (B.E) Department of CSE City Engineering College," 2725a68be6bc677bd435c19664569ecd45c52d7a,DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers,"DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers Amir Ghodrati1∗, Ali Diba1∗, Marco Pedersoli2†‡, Tinne Tuytelaars1, Luc Van Gool1,3 KU Leuven, ESAT-PSI, iMinds Inria CVL, ETH Zurich" 2792e5d569b94406ca28f86c9999f569a3d60c6d,Illumination Multiplexing within Fundamental Limits,"Illumination Multiplexing within Fundamental Limits Netanel Ratner Yoav Y. Schechner Department of Electrical Engineering Technion - Israel Institute of Technology Haifa 32000, ISRAEL" 27ee8482c376ef282d5eb2e673ab042f5ded99d7,Scale Normalization for the Distance Maps AAM,"Scale Normalization for the Distance Maps AAM. Denis GIRI, Maxime ROSENWALD, Benjamin VILLENEUVE, Sylvain LE GALLOU and Renaud S ´EGUIER Email: {denis.giri, maxime.rosenwald, benjamin.villeneuve, sylvain.legallou, Avenue de la boulaie, BP 81127, 5 511 Cesson-S´evign´e, France Sup´elec, IETR-SCEE Team" 2757ff9bba677e7bceaa4802d85cc6f872618583,From basis components to complex structural patterns,"FROM BASIS COMPONENTS TO COMPLEX STRUCTURAL PATTERNS Anh Huy Phan‡, Andrzej Cichocki‡∗, Petr Tichavsk´y•†, Rafal Zdunek§ and Sidney Lehky‡⋆ Brain Science Institute, RIKEN, Wakoshi, Japan •Institute of Information Theory and Automation, Prague, Czech Republic §Wroclaw University of Technology, Poland ⋆Computational Neurobiology Lab, The Salk Institute, USA" 277cadfadc4550fc781be7df8cb4ec89e54b793e,Autonomous Real-time Vehicle Detection from a Medium-Level UAV,"Autonomous Real-time Vehicle Detection from a Medium-Level UAV Toby P. Breckon, Stuart E. Barnes, Marcin L. Eichner and Ken Wahren" 2704959c75a2e6741867ae18f11fa822fa544c74,Hierarchical Convex NMF for Clustering Massive Data,"JMLR: Workshop and Conference Proceedings 13: 253-268 nd Asian Conference on Machine Learning (ACML2010), Tokyo, Japan, Nov. 8–10, 2010. Hierarchical Convex NMF for Clustering Massive Data Kristian Kersting Mirwaes Wahabzada Knowledge Discovery Department Fraunhofer IAIS, Schloss Birlinghoven 53754 Sankt Augustin, Germany Christian Thurau Christian Bauckhage Vision and Social Media Group Fraunhofer IAIS, Schloss Birlinghoven 53754 Sankt Augustin, Germany Editor: Masashi Sugiyama and Qiang Yang" 27f8b01e628f20ebfcb58d14ea40573d351bbaad,Events based Multimedia Indexing and Retrieval,"DEPARTMENT OF INFORMATION ENGINEERING AND COMPUTER SCIENCE ICT International Doctoral School Events based Multimedia Indexing nd Retrieval Kashif Ahmad SUBMITTED TO THE DEPARTMENT OF INFORMATION ENGINEERING AND COMPUTER SCIENCE (DISI) IN THE PARTIAL FULFILMENT OF THE REQUIREMENTS FOR THE DEGREE DOCTOR OF PHILOSOPHY Advisor: Examiners: Prof. Marco Carli, Universit`a degli Studi di Roma Tre, Italy Prof. Nicola Conci, Universit`a degli Studi di Trento, Italy Prof. Pietro Zanuttigh, Universit`a degli Studi di Padova, Italy Prof. Giulia Boato, Universit`a degli Studi di Trento, Italy December 2017" 273d6c307cae64e3f3813a1a70299205f519e8a7,Regularised Energy Model for Robust Monocular Ego-motion Estimation, 2799d53ca80d67f104bef207a667fa12b4c59d62,Multiple-Person Tracking for a Mobile Robot Using Stereo,"MVA2009 IAPR Conference on Machine Vision Applications, May 20-22, 2009, Yokohama, JAPAN Multiple-Person Tracking for a Mobile Robot using Stereo Junji Satake Jun Miura Toyohashi University of Technology -1 Hibarigaoka, Tempaku-cho, Toyohashi, Aichi 441-8580, Japan {satake," 27fda2c61f3fe1f74e18bd11555df7751d178bca,Real-time 3D head pose and facial landmark estimation from depth images using triangular surface patch features,"Real-time 3D Head Pose and Facial Landmark Estimation from Depth Images Using Triangular Surface Patch Features Chavdar Papazov Tim K. Marks Michael Jones Mitsubishi Electric Research Laboratories (MERL) 01 Broadway, Cambridge, MA 02139" 2713423d87d011c0a5aae99bef57523769121a1d,A Codebook Design Method for Robust VQ-Based Face Recognition Algorithm,"J. Software Engineering & Applications, 2010, 3: 119-124 A Codebook Design Method for Robust VQ-Based Face Recognition Algorithm Qiu Chen1, Koji Kotani2, Feifei Lee1, Tadahiro Ohmi1 New Industry Creation Hatchery Center, Tohoku University; 2Department of Electronics, Graduate School of Engineering, Tohoku Univer- sity, Japan.. Email: Received September 5th, 2009; revised November 2nd, 2009; accepted November 6th, 2009." 27c978bdb9de3a5135349976fdbc514ff547dcab,Multi-Objective Stochastic Optimization by Co-Direct Sequential Simulation for History Matching of Oil Reservoirs,"Multi-Objective Stochastic Optimization by Co-Direct Sequential Simulation for History Matching of Oil Reservoirs Jo˜ao Daniel Trigo Pereira Carneiro∗ under the supervision of Am´ılcar de Oliveira Soares† Dep. Mines, IST, Lisbon, Portugal December 2010" 27448716366bed56515c1b32579daf224165861e,Deep Multi-camera People Detection,"Deep Multi-Camera People Detection Tatjana Chavdarova and Franc¸ois Fleuret Idiap Research Institute and ´Ecole Polytechnique F´ed´erale de Lausanne Email:" 27ae95d9ad6492511296360ba0618f5d0565cf9e,Person re-Identification over distributed spaces and time,"Person re-Identification over distributed spaces and time Prosser, Bryan James For additional information about this publication click this link. http://qmro.qmul.ac.uk/jspui/handle/123456789/2513 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 2785c5769489825671a6138fdf0537fcd444038a,A Deep Cascade Network for Unaligned Face Attribute Classification,"A Deep Cascade Network for Unaligned Face Attribute Classification Hui Ding,1 Hao Zhou,2 Shaohua Kevin Zhou,3 Rama Chellappa4 ,2,4University of Maryland, College Park Siemens Healthineers, New Jersey" 2734b3a6345396499b2b7c6cc1b43fc7e9b375ee,Full-System Simulation of big.LITTLE Multicore Architecture for Performance and Energy Exploration,"Full-System Simulation of big.LITTLE Multicore Architecture for Performance and Energy Exploration Anastasiia Butko, Florent Bruguier, Abdoulaye Gamati´e, Gilles Sassatelli, David Novo, Lionel Torres and Michel Robert LIRMM (CNRS and University of Montpellier) Montpellier, France Email:" 27f1fd71538ba420c63aa4c74704718a0633b22a,Multimodal News Article Analysis,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 275416b209906988a73125e8ee0615774895c869,Use of Sparse Representation for Pedestrian Detection in Thermal Images,"Use of Sparse Representation for Pedestrian Detection in Thermal Images Bin Qi1,2, Vijay John1,2, Zheng Liu1,2, and Seiichi Mita2 Intelligent Information Processing Laboratory, Toyota Technological Institute, Nagoya, Japan, Research Centre for Smart Vehicles, Toyota Technological Institute, Nagoya, Japan," 27b87bdee46964757b83b5afb4184e438cad6b1b,Sequence searching with deep-learnt depth for condition- and viewpoint-invariant route-based place recognition,"Sequence Searching with Deep-learnt Depth for Condition- and Viewpoint- invariant Route-based Place Recognition Michael Milford, Stephanie Lowry, Niko Sunderhauf, Sareh Shirazi, Edward Pepperell, Ben Upcroft Queensland University of Technology Australia Australian Centre for Robotic Vision" 276d35fef150f61adf53270eb6e50625022d4e7f,The ACRV picking benchmark: A robotic shelf picking benchmark to foster reproducible research,"A Robotic Shelf Picking Benchmark to Foster Reproducible Research The ACRV Picking Benchmark: J¨urgen Leitner1,2, Adam W. Tow1,2, Niko S¨underhauf1,2, Jake E. Dean2, Joseph W. Durham3, Matthew Cooper2, Markus Eich1,2, Christopher Lehnert2, Ruben Mangels2, Christopher McCool2, Peter T. Kujala1,2, Lachlan Nicholson2, Trung Pham1,4, James Sergeant1,2, Fangyi Zhang1,2, Ben Upcroft1,2, and Peter Corke1,2." 270567401251cad629f6d569febe95fe446a895c,A Pose Invariant Face Recognition system using Subspace Techniques,"A Pose Invariant Face Recognition system using Subspace Techniques Mohammed Aleemuddin A Thesis Presented to the DEANSHIP OF GRADUATE STUDIES In Partial Fulfillment of the Requirements for the Degree MASTER OF SCIENCE Telecommunication Engineering KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS Dhahran, Saudi Arabia November 2004" 27962faaafbf01092da03130550a70e097e1dd9f,Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields,"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields Fayao Liu, Chunhua Shen, Guosheng Lin, Ian Reid" 27f9b43737e234cefb3c5cd72324a36cbe61ee3c,Sparse Manifold Clustering and Embedding,"Sparse Manifold Clustering and Embedding Ehsan Elhamifar Center for Imaging Science Johns Hopkins University Ren´e Vidal Center for Imaging Science Johns Hopkins University" 2770b095613d4395045942dc60e6c560e882f887,GridFace: Face Rectification via Learning Local Homography Transformations,"GridFace: Face Rectification via Learning Local Homography Transformations Erjin Zhou, Zhimin Cao, and Jian Sun Face++, Megvii Inc." 2783efc96a0d59473e4236ccf1db6ed7e958839e,An Overview of Multi-Task Learning in Deep Neural Networks,"An Overview of Multi-Task Learning in Deep Neural Networks∗ Sebastian Ruder Insight Centre for Data Analytics, NUI Galway Aylien Ltd., Dublin" 273b973092a4491974d173cc5258c74aede692cc,Monocular Long-Term Target Following on UAVs,"Monocular Long-term Target Following on UAVs Rui Li ∗ Minjian Pang† Cong Zhao ‡ Guyue Zhou ‡ Lu Fang †§" 27421586a04584d38dd961b37d0ca85408acfe59,Large brains in autism: the challenge of pervasive abnormality.,"Large Brains in Autism: The Challenge of Pervasive Abnormality MARTHA R. HERBERT Pediatric Neurology, Center for Morphometric Analysis Massachusetts General Hospital REVIEW I The most replicated finding in autism neuroanatomy—a tendency to unusually large brains—has seemed paradoxical in relation to the specificity of the abnormalities in three behavioral domains that define autism. We now know a range of things about this phenomenon, including that brains in autism have a growth spurt shortly after birth and then slow in growth a few short years afterward, that only younger but not older rains are larger in autism than in controls, that white matter contributes disproportionately to this volume increase and in a nonuniform pattern suggesting postnatal pathology, that functional connectivity among regions of autistic brains is diminished, and that neuroinflammation (including microgliosis and astrogliosis) ppears to be present in autistic brain tissue from childhood through adulthood. Alongside these pervasive rain tissue and functional abnormalities, there have arisen theories of pervasive or widespread neural information processing or signal coordination abnormalities (such as weak central coherence, impaired omplex processing, and underconnectivity), which are argued to underlie the specific observable behav- ioral features of autism. This convergence of findings and models suggests that a systems- and chronic disease–based reformulation of function and pathophysiology in autism needs to be considered, and it opens the possibility for new treatment targets. NEUROSCIENTIST 11(5):417–440; 2005. DOI:" 276dbb667a66c23545534caa80be483222db7769,An Introduction to Image-based 3 D Surface Reconstruction and a Survey of Photometric Stereo Methods,"D Res. 2, 03(2011)4 0.1007/3DRes.03(2011)4 DR REVIEW w An Introduction to Image-based 3D Surface Reconstruction and a Survey of Photometric Stereo Methods Steffen Herbort • Christian Wöhler introduction image-based 3D techniques. Then we describe Received: 21Feburary 2011 / Revised: 20 March 2011 / Accepted: 11 May 2011 © 3D Research Center, Kwangwoon University and Springer 2011" 27d2e977356915c63c4562fe41df9e9ed0290f15,A Hierarchical Compositional Model for Face Representation and Sketching,"A Hierarchical Compositional Model for Face Representation and Sketching Zijian Xu1, Hong Chen1, Song-Chun Zhu1, Jiebo Luo2 Department of Statistics, University of California at Los Angeles, Los Angeles, CA 90095 Kodak Research Laboratories, Eastman Kodak Company, Rochester, NY 14650-1816" 27326ae43ec7a6a31ecd257171b8a338053946cd,Boundary-enhanced supervoxel segmentation for sparse outdoor LiDAR data,"Boundary-enhanced supervoxel segmentation for sparse outdoor LiDAR data Soohwan Song, Honggu Lee and Sungho Jo supervoxel Voxelisation methods are extensively employed for efficiently proces- sing large point clouds. However, it is possible to lose geometric in- formation and extract inaccurate features through these voxelisation methods. A novel, flexibly shaped ‘supervoxel’ algorithm, called oundary-enhanced omplex outdoor light detection and ranging (LiDAR) data is pro- posed. The algorithm consists of two key components: (i) detecting oundaries by analysing consecutive points and (ii) clustering the points by first excluding the boundary points. The generated super- voxels include spatial and geometric properties and maintain the shape of the object’s boundary. The proposed algorithm is tested using sparse LiDAR data obtained from outdoor urban environments. segmentation, sparse Introduction: Correctly perceiving a three-dimensional (3D) outdoor environment is still a challenging task for autonomous vehicles. For" 272ac22c670fd0c7c3f1b4ca02e925ff22dd4b27,Articulated part-based model for joint object detection and pose estimation,"Articulated Part-based Model for Joint Object Detection and Pose Estimation Dept. of Electrical and Computer Engineering, University of Michigan at Ann Arbor, USA Min Sun Silvio Savarese COARSE LEVEL" 27187d4c36f71d08898a53dfda0e81df11b25f21,Worst Case Linear Discriminant Analysis as Scalable Semidefinite Feasibility Problems,"MANUSCRIPT Worst-Case Linear Discriminant Analysis as Scalable Semidefinite Feasibility Problems Hui Li, Chunhua Shen, Anton van den Hengel, Qinfeng Shi" 277096c5e536784da9856ac083a972715ce9f9c3,Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction,"Article Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction Dat Tien Nguyen, Ki Wan Kim, Hyung Gil Hong, Ja Hyung Koo, Min Cheol Kim and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (D.T.N.); (K.W.K.); (H.G.H.); (J.H.K.); (M.C.K.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Academic Editor: Joonki Paik Received: 31 January 2017; Accepted: 18 March 2017; Published: 20 March 2017" 275ad26b7e4d7847f7ad4eedda65f327007a9452,Query-by-Example Image Retrieval using Visual Dependency Representations,"Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 109–120, Dublin, Ireland, August 23-29 2014." 27173d0b9bb5ce3a75d05e4dbd8f063375f24bb5,Effect of Different Occlusion on Facial Expressions Recognition,"Ankita Vyas Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 4, Issue 10( Part - 3), October 2014, pp.40-44 RESEARCH ARTICLE OPEN ACCESS Effect of Different Occlusion on Facial Expressions Recognition Ankita Vyas*, Ramchand Hablani** *(Department of Computer Science, RGPV University, Indore) ** (Department of Computer Science, RGPV University, Indore)" 27a4bbd7bc90ad118f15c61bb30079d6e6bff78e,3D Deformable Super-Resolution for Multi-Camera 3D Face Scanning,"J Math Imaging Vis DOI 10.1007/s10851-012-0399-y D Deformable Super-Resolution for Multi-Camera 3D Face Scanning Karima Ouji · Mohsen Ardabilian · Liming Chen · Faouzi Ghorbel © Springer Science+Business Media New York 2012" 27a0a7837f9114143717fc63294a6500565294c2,Face Recognition in Unconstrained Environments : A Comparative Study,"Face Recognition in Unconstrained Environments: A Comparative Study Rodrigo Verschae, Javier Ruiz-Del-Solar, Mauricio Correa To cite this version: Rodrigo Verschae, Javier Ruiz-Del-Solar, Mauricio Correa. Face Recognition in Unconstrained Environments: A Comparative Study: . Workshop on Faces in ’Real-Life’ Images: Detection, Alignment, and Recognition, Oct 2008, Marseille, France. 2008. HAL Id: inria-00326730 https://hal.inria.fr/inria-00326730 Submitted on 5 Oct 2008 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 27183d23f50884a0e06b978acf9ad77dbcbfb112,Autonomous indoor helicopter flight using a single onboard camera,"The 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems October 11-15, 2009 St. Louis, USA 978-1-4244-3804-4/09/$25.00 ©2009 IEEE" 27dafaa0478bc70e3af9c5a45f278bcee44a920c,Learnability and semantic universals,"Learnability and semantic universals* Shane Steinert-Threlkeld Institute for Logic, Language and Jakub Szymanik Institute for Logic, Language and Computation Computation Universiteit van Amsterdam Universiteit van Amsterdam Forthcoming in Semantics & Pragmatics." 274046ccc3f6641f29e404f4c731e5d6b771de26,A New Approach to Object-Related Image Retrieval,"(cid:74)(cid:111)(cid:117)(cid:114)(cid:110)(cid:97)(cid:108) (cid:111)(cid:102) (cid:86)(cid:105)(cid:115)(cid:117)(cid:97)(cid:108) (cid:76)(cid:97)(cid:110)(cid:103)(cid:117)(cid:97)(cid:103)(cid:101)(cid:115) (cid:97)(cid:110)(cid:100) (cid:67)(cid:111)(cid:109)(cid:112)(cid:117)(cid:116)(cid:105)(cid:110)(cid:103) (cid:40)(cid:50)(cid:48)(cid:48)(cid:48)(cid:41) 11, (cid:51)(cid:52)(cid:53)(cid:177)(cid:51)(cid:54)(cid:51) (cid:100)(cid:111)(cid:105)(cid:58)(cid:49)(cid:48)(cid:46)(cid:49)(cid:48)(cid:48)(cid:54)/(cid:106)(cid:118)(cid:108)(cid:99)(cid:46)(cid:50)(cid:48)(cid:48)(cid:48)(cid:46)(cid:48)(cid:49)(cid:54)(cid:50)(cid:44) (cid:97)(cid:118)(cid:97)(cid:105)(cid:108)(cid:97)(cid:98)(cid:108)(cid:101) (cid:111)(cid:110)(cid:108)(cid:105)(cid:110)(cid:101) (cid:97)(cid:116) (cid:104)(cid:116)(cid:116)(cid:112)(cid:58)//(cid:119)(cid:119)(cid:119)(cid:46)(cid:105)(cid:100)(cid:101)(cid:97)(cid:108)(cid:105)(cid:98)(cid:114)(cid:97)(cid:114)(cid:121)(cid:46)(cid:99)(cid:111)(cid:109) (cid:111)(cid:110) A New Approach to Object-Related Image Retrieval (cid:65)(cid:76)(cid:69)(cid:73)(cid:88) (cid:77)(cid:46) (cid:77)(cid:65)(cid:82)(cid:84)(cid:73)D (cid:78)(cid:69)(cid:90)* (cid:65)(cid:78)(cid:68) (cid:74)(cid:85)(cid:65)(cid:78) (cid:82)(cid:46) (cid:83)(cid:69)(cid:82)(cid:82)(cid:65)s *(cid:82)(cid:111)(cid:98)(cid:111)(cid:116) (cid:86)(cid:105)(cid:115)(cid:105)(cid:111)(cid:110) (cid:76)(cid:97)(cid:98)(cid:44) (cid:83)(cid:99)(cid:104)(cid:111)(cid:111)(cid:108) (cid:111)(cid:102) (cid:69)(cid:108)(cid:101)(cid:99)(cid:116)(cid:114)(cid:105)(cid:99)(cid:97)(cid:108) (cid:97)(cid:110)(cid:100) (cid:67)(cid:111)(cid:109)(cid:112)(cid:117)(cid:116)(cid:101)(cid:114) (cid:69)(cid:110)(cid:103)(cid:105)(cid:110)(cid:101)(cid:101)(cid:114)(cid:105)(cid:110)(cid:103)(cid:44) (cid:87)(cid:101)(cid:115)(cid:116) (cid:76)(cid:97)(cid:102)(cid:97)(cid:121)(cid:101)(cid:116)(cid:116)(cid:101)(cid:44) (cid:73)(cid:78) (cid:52)(cid:55)(cid:57)(cid:48)(cid:54)(cid:44) (cid:85)(cid:83)(cid:65)(cid:59) (cid:83)(cid:111)(cid:110)(cid:121) (cid:67)(cid:111)(cid:109)(cid:112)(cid:117)(cid:116)(cid:101)(cid:114) (cid:83)(cid:99)(cid:105)(cid:101)(cid:110)(cid:99)(cid:101) (cid:76)(cid:97)(cid:98)(cid:44) (cid:54) (cid:114)(cid:117)(cid:101) (cid:65)(cid:109)(cid:121)(cid:111)(cid:116)(cid:44) (cid:55)(cid:53)(cid:48)(cid:48)(cid:53) (cid:80)(cid:97)(cid:114)(cid:105)(cid:115)(cid:44) (cid:70)(cid:114)(cid:97)(cid:110)(cid:99)(cid:101)(cid:44) (cid:69)(cid:45)(cid:109)(cid:97)(cid:105)(cid:108)(cid:58) s(cid:83)(cid:79)(cid:67) (cid:67)(cid:111)(cid:109)(cid:112)(cid:117)(cid:116)(cid:105)(cid:110)(cid:103)(cid:44) (cid:65)(cid:118)(cid:100)(cid:97)(cid:44) (cid:65)(cid:108)(cid:101)(cid:120)(cid:97)(cid:110)(cid:100)(cid:114)(cid:101) (cid:82)(cid:111)(cid:115)(cid:115)(cid:101)(cid:108)(cid:108)(cid:111)H (cid:50)(cid:57)(cid:44) (cid:57)(cid:45)(cid:50)(cid:46) (cid:48)(cid:55)(cid:48)(cid:48)(cid:50) (cid:80)(cid:97)(cid:108)(cid:109)(cid:97) (cid:100)(cid:101) (cid:77)(cid:99)(cid:97)(cid:46) (cid:66)(cid:97)(cid:108)(cid:101)(cid:97)(cid:114)(cid:115)(cid:44) (cid:83)(cid:112)(cid:97)(cid:105)(cid:110)(cid:44) (cid:69)(cid:45)(cid:109)(cid:97)(cid:105)(cid:108)(cid:58) (cid:65)(cid:99)(cid:99)(cid:101)(cid:112)(cid:116)(cid:101)(cid:100) (cid:49)(cid:56) (cid:74)(cid:97)(cid:110)(cid:117)(cid:97)(cid:114)(cid:121) (cid:50)(cid:48)(cid:48)(cid:48) (cid:73)(cid:109)(cid:97)(cid:103)(cid:101) (cid:114)(cid:101)(cid:116)(cid:114)(cid:105)(cid:101)(cid:118)(cid:97)(cid:108) (cid:104)(cid:97)(cid:115) (cid:98)(cid:101)(cid:101)(cid:110) (cid:99)(cid:111)(cid:109)(cid:109)(cid:111)(cid:110)(cid:108)(cid:121) (cid:97)(cid:116)(cid:116)(cid:101)(cid:109)(cid:112)(cid:116)(cid:101)(cid:100) (cid:117)(cid:115)(cid:105)(cid:110)(cid:103) (cid:110)(cid:111)(cid:110)(cid:45)(cid:115)(cid:101)(cid:109)(cid:97)(cid:110)(cid:116)(cid:105)(cid:99) (cid:97)(cid:112)(cid:112)(cid:114)(cid:111)(cid:97)(cid:99)(cid:104)(cid:101)(cid:115)(cid:46) (cid:73)(cid:116) (cid:105)(cid:115) (cid:99)(cid:108)(cid:101)(cid:97)(cid:114) (cid:116)(cid:104)(cid:111)(cid:117)(cid:103)(cid:104)(cid:44) (cid:116)(cid:104)(cid:97)(cid:116) (cid:115)(cid:101)(cid:109)(cid:97)(cid:110)(cid:116)(cid:105)(cid:99) (cid:114)(cid:101)(cid:116)(cid:114)(cid:105)(cid:101)(cid:118)(cid:97)(cid:108) (cid:105)(cid:115) (cid:109)(cid:111)(cid:114)(cid:101) (cid:100)(cid:101)(cid:115)(cid:105)(cid:114)(cid:97)(cid:98)(cid:108)(cid:101) (cid:98)(cid:101)(cid:99)(cid:97)(cid:117)(cid:115)(cid:101) (cid:105)(cid:116) (cid:102)(cid:97)(cid:99)(cid:105)(cid:108)(cid:105)(cid:116)(cid:97)(cid:116)(cid:101)(cid:115) (cid:116)(cid:104)(cid:101) (cid:117)(cid:115)(cid:101)(cid:114)(cid:39)(cid:115) (cid:116)(cid:97)(cid:115)(cid:107)(cid:46) (cid:73)(cid:110) (cid:116)(cid:104)(cid:105)(cid:115) (cid:112)(cid:97)(cid:112)(cid:101)(cid:114)(cid:44) (cid:119)(cid:101) (cid:112)(cid:114)(cid:101)(cid:115)(cid:101)(cid:110)(cid:116) (cid:97) (cid:110)(cid:101)(cid:119) (cid:97)(cid:112)(cid:112)(cid:114)(cid:111)(cid:97)(cid:99)(cid:104) (cid:116)(cid:111) (cid:115)(cid:101)(cid:109)(cid:97)(cid:110)(cid:116)(cid:105)(cid:99) (cid:97)(cid:99)(cid:99)(cid:101)(cid:115)(cid:115) (cid:111)(cid:102) (cid:97) (cid:100)(cid:97)(cid:116)(cid:97)(cid:98)(cid:97)(cid:115)(cid:101) (cid:111)(cid:102) (cid:105)(cid:109)(cid:97)(cid:103)(cid:101)(cid:115) (cid:98)(cid:121) (cid:97)(cid:115)(cid:107)(cid:105)(cid:110)(cid:103) (cid:102)(cid:111)(cid:114) (cid:116)(cid:104)(cid:101) (cid:112)(cid:114)(cid:101)(cid:115)(cid:101)(cid:110)(cid:99)(cid:101) (cid:111)(cid:102) (cid:99)(cid:101)(cid:114)(cid:116)(cid:97)(cid:105)(cid:110) (cid:111)(cid:98)(cid:106)(cid:101)(cid:99)(cid:116)(cid:115)(cid:59) (cid:116)(cid:104)(cid:105)(cid:115) (cid:105)(cid:115) (cid:107)(cid:110)(cid:111)(cid:119)(cid:110) (cid:97)(cid:115) (cid:111)(cid:98)(cid:106)(cid:101)(cid:99)(cid:116)(cid:45)(cid:114)(cid:101)(cid:108)(cid:97)(cid:116)(cid:101)(cid:100) (cid:105)(cid:109)(cid:97)(cid:103)(cid:101) (cid:114)(cid:101)(cid:116)(cid:114)(cid:105)(cid:101)(cid:118)(cid:97)(cid:108)(cid:46) (cid:84)(cid:104)(cid:105)(cid:115) (cid:97)(cid:112)(cid:112)(cid:114)(cid:111)(cid:97)(cid:99)(cid:104) (cid:105)(cid:115) (cid:98)(cid:117)(cid:105)(cid:108)(cid:116) (cid:119)(cid:105)(cid:116)(cid:104)(cid:105)(cid:110) (cid:97) (cid:99)(cid:108)(cid:97)(cid:115)(cid:115)(cid:105)(cid:99)(cid:97)(cid:108) (cid:99)(cid:111)(cid:109)(cid:112)(cid:117)(cid:116)(cid:101)(cid:114) (cid:118)(cid:105)(cid:115)(cid:105)(cid:111)(cid:110) (cid:102)(cid:114)(cid:97)(cid:109)(cid:101)(cid:119)(cid:111)(cid:114)(cid:107) (cid:40)(cid:105)(cid:46)(cid:101)(cid:46) (cid:108)(cid:111)(cid:99)(cid:97)(cid:108)(cid:105)(cid:122)(cid:97)(cid:116)(cid:105)(cid:111)(cid:110)(cid:44) (cid:115)(cid:101)(cid:103)(cid:109)(cid:101)(cid:110)(cid:116)(cid:97)(cid:116)(cid:105)(cid:111)(cid:110) (cid:97)(cid:110)(cid:100) (cid:105)(cid:100)(cid:101)(cid:110)(cid:116)(cid:105)(cid:174)(cid:99)(cid:97)(cid:116)(cid:105)(cid:111)(cid:110)(cid:41)(cid:46) (cid:79)(cid:117)(cid:114) (cid:97)(cid:112)(cid:112)(cid:114)(cid:111)(cid:97)(cid:99)(cid:104) (cid:174)(cid:114)(cid:115)(cid:116) (cid:115)(cid:101)(cid:97)(cid:114)(cid:99)(cid:104)(cid:101)(cid:115) (cid:102)(cid:111)(cid:114) (cid:116)(cid:104)(cid:101) (cid:109)(cid:97)(cid:105)(cid:110) (cid:97)(cid:114)(cid:101)(cid:97)(cid:115) (cid:111)(cid:102) (cid:97)(cid:116)(cid:116)(cid:101)(cid:110)(cid:116)(cid:105)(cid:111)(cid:110) (cid:40)(cid:109)(cid:111)(cid:115)(cid:116) (cid:115)(cid:97)(cid:108)(cid:105)(cid:101)(cid:110)(cid:116) (cid:97)(cid:114)(cid:101)(cid:97)(cid:115) (cid:111)(cid:102) (cid:97)(cid:110) (cid:105)(cid:109)(cid:97)(cid:103)(cid:101)(cid:41) (cid:97)(cid:110)(cid:100) (cid:116)(cid:104)(cid:101)(cid:110) (cid:97)(cid:112)(cid:112)(cid:108)(cid:105)(cid:101)(cid:115) (cid:97)(cid:112)(cid:112)(cid:101)(cid:97)(cid:114)(cid:97)(cid:110)(cid:99)(cid:101)(cid:45)(cid:98)(cid:97)(cid:115)(cid:101)(cid:100) (cid:109)(cid:101)(cid:116)(cid:104)(cid:111)(cid:100)(cid:115) (cid:116)(cid:111) (cid:99)(cid:108)(cid:97)(cid:115)(cid:115)(cid:105)(cid:102)(cid:121) (cid:40)(cid:105)(cid:110)(cid:100)(cid:101)(cid:120)(cid:41) (cid:97)(cid:108)(cid:108) (cid:105)(cid:109)(cid:97)(cid:103)(cid:101)(cid:115) (cid:98)(cid:121) (cid:96)(cid:115)(cid:121)(cid:109)(cid:98)(cid:111)(cid:108)(cid:105)(cid:99)(cid:39) (cid:110)(cid:97)(cid:109)(cid:101)(cid:115)(cid:46) (cid:84)(cid:104)(cid:101)(cid:115)(cid:101) (cid:110)(cid:97)(cid:109)(cid:101)(cid:115) (cid:97)(cid:114)(cid:101) (cid:114)(cid:101)(cid:102)(cid:101)(cid:114)(cid:114)(cid:101)(cid:100) (cid:116)(cid:111) (cid:111)(cid:98)(cid:106)(cid:101)(cid:99)(cid:116)(cid:115)(cid:44) (cid:119)(cid:104)(cid:105)(cid:99)(cid:104) (cid:174)(cid:110)(cid:97)(cid:108)(cid:108)(cid:121) (cid:97)(cid:108)(cid:108)(cid:111)(cid:119)(cid:115) (cid:116)(cid:104)(cid:101) (cid:117)(cid:115)(cid:101) (cid:111)(cid:102) (cid:115)(cid:101)(cid:109)(cid:97)(cid:110)(cid:116)(cid:105)(cid:99)(cid:115) (cid:100)(cid:114)(cid:105)(cid:118)(cid:101)(cid:110) (cid:98)(cid:121) (cid:116)(cid:104)(cid:101)(cid:115)(cid:101) (cid:111)(cid:98)(cid:106)(cid:101)(cid:99)(cid:116) (cid:110)(cid:97)(cid:109)(cid:101)(cid:115)(cid:44) (cid:101)(cid:46)(cid:103)(cid:46) (cid:114)(cid:101)(cid:116)(cid:114)(cid:105)(cid:101)(cid:118)(cid:101) (cid:96)(cid:97)(cid:108)(cid:108) (cid:116)(cid:104)(cid:111)(cid:115)(cid:101) (cid:105)(cid:109)(cid:97)(cid:103)(cid:101)(cid:115) (cid:116)(cid:104)(cid:97)(cid:116) (cid:104)(cid:97)(cid:118)(cid:101) (cid:97) (cid:98)(cid:117)(cid:108)(cid:108) (cid:97)(cid:110)(cid:100) (cid:77)(cid:101)(cid:108)(cid:105)(cid:115)(cid:115)(cid:97)(cid:39)(cid:115) (cid:102)(cid:97)(cid:99)(cid:101)(cid:39)(cid:46)" d69e644016042d1032995bc9f51e2d72a1c1cd93,Beyond trees: adopting MITI to learn rules and ensemble classifiers for multi-instance data,"Beyond Trees: Adopting MITI to Learn Rules nd Ensemble Classifiers for Multi-instance Data Luke Bjerring and Eibe Frank Department of Computer Science, University of Waikato" d6f49b63e4e285ff2bb3ba92e1e10287d407d6c0,Tasks determine what is learned in visual statistical learning.,"Psychon Bull Rev https://doi.org/10.3758/s13423-017-1405-6 BRIEF REPORT Tasks determine what is learned in visual statistical learning Timothy J. Vickery 1 & Su Hyoun Park 1 & Jayesh Gupta 1 & Marian E. Berryhill 2 # Psychonomic Society, Inc. 2017" d6255a0db6f8f157c5c901d758c7a5f36416ab51,Face Recognition Using Gabor Wavelet Transform,"FACE RECOGNITION USING GABOR WAVELET TRANSFORM A THESIS SUBMITTED TO THE GRADUATE SCHOOL OF NATURAL SCIENCES THE MIDDLE EAST TECHNICAL UNIVERSITY BURCU KEPENEKCI IN PARTIAL FULLFILMENT OF THE REQUIREMENTS FOR THE DEGREE MASTER OF SCIENCE THE DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING SEPTEMBER 2001" d6adb54f5d25dda71d157b5d574c70c732fdd722,Feature Map Filtering: Improving Visual Place Recognition with Convolutional Calibration,"Pre-print of article that will appear in Proceedings of the Australasian Conference on Robotics and Automation 018. Please cite this paper as: Stephen Hausler, Adam Jacobson, and Michael Milford. Feature Map Filtering: Improving Visual Place Recognition with Convolutional Calibration. Proceedings of Australasian Conference on Robotics and Automation, 2018. ibtex: uthor = {Hausler, Stephen and Jacobson, Adam and Milford, Michael}, title = {Feature Map Filtering: Improving Visual Place Recognition with Convolutional Calibration}, ooktitle = {Proceedings of Australasian Conference on Robotics and Automation (ACRA)}, year = {2018}," d68f24e2c8e753d4d1e62f2231f6f33370de24de,NATIONAL BIOMETRIC TEST CENTER COLLECTED WORKS 1997-2000,"NATIONAL BIOMETRIC TEST CENTER COLLECTED WORKS 997-2000 Edited by: James L. Wayman, Director Version 1.2 August, 2000 Prepared under DoD Contract MDA904-97-C-03 nd FAA Award DTFA0300P10092" d6dfe23018172d29c36746d24f73bf86e1aaa0a6,Searching Scenes by Abstracting Things., d6c7092111a8619ed7a6b01b00c5f75949f137bf,A Novel Feature Extraction Technique for Facial Expression Recognition *,"A Novel Feature Extraction Technique for Facial Expression Recognition *Mohammad Shahidul Islam1, Surapong Auwatanamongkol2 1 Department of Computer Science, School of Applied Statistics, National Institute of Development Administration, Bangkok, 10240, Thailand Department of Computer Science, School of Applied Statistics, National Institute of Development Administration, Bangkok, 10240, Thailand" d65b82b862cf1dbba3dee6541358f69849004f30,Elastic graph matching,"Computer Vision and Image Understanding 115 (2011) 1062–1072 Contents lists available at ScienceDirect Computer Vision and Image Understanding j o u r n a l h o m e p a g e : w w w . e l s e v i e r . c o m / l o c a t e / c v i u .5D Elastic graph matching Stefanos Zafeiriou , Maria Petrou Imperial College, Department of Electrical and Electronic Engineering, London, UK r t i c l e i n f o b s t r a c t Article history: Received 29 November 2009 Accepted 1 December 2010 Available online 17 March 2011 Keywords: Elastic graph matching D face recognition Multiscale mathematical morphology Geodesic distances" d6b514a68abff3ab14af9fc0152cd5b28bd0192c,Instance Segmentation by Deep Coloring,"JULY 2018 Instance Segmentation by Deep Coloring Victor Kulikov, Victor Yurchenko, and Victor Lempitsky" d671a210990f67eba9b2d3dda8c2cb91575b4a7a,Social Environment Description from Data Collected with a Wearable Device,"Journal of Machine Learning Research () Submitted ; Published Social Environment Description from Data Collected with a Wearable Device Pierluigi Casale Computer Vision Center Autonomous University of Barcelona Barcelona, Spain Editor: Radeva Petia, Pujol Oriol" d687fa99586a9ad229284229f20a157ba2d41aea,Face Recognition Based on Wavelet Packet Coefficients and Radial Basis Function Neural Networks,"Journal of Intelligent Learning Systems and Applications, 2013, 5, 115-122 http://dx.doi.org/10.4236/jilsa.2013.52013 Published Online May 2013 (http://www.scirp.org/journal/jilsa) Face Recognition Based on Wavelet Packet Coefficients nd Radial Basis Function Neural Networks Thangairulappan Kathirvalavakumar1*, Jeyasingh Jebakumari Beulah Vasanthi2 Department of Computer Science, Virudhunagar Hindu Nadars’ Senthikumara Nadar College, Virudhunagar, India; 2Department of Computer Applications, Ayya Nadar Janaki Ammal College, Sivakasi, India. Email: Received December 12th, 2012; revised April 19th, 2013; accepted April 26th, 2013 Copyright © 2013 Thangairulappan Kathirvalavakumar, Jeyasingh Jebakumari Beulah Vasanthi. This is an open access article dis- tributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any me- dium, provided the original work is properly cited." d6a9ea9b40a7377c91c705f4c7f206a669a9eea2,Visual Representations for Fine-grained Categorization,"Visual Representations for Fine-grained Categorization Ning Zhang Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2015-244 http://www.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-244.html December 17, 2015" d6683c74c17d4fcc48ce3d9df9df6aea38fd4923,Learning Instance Weights in Multi-Instance Learning,"Learning Instance Weights in Multi-Instance Learning James Foulds This thesis is submitted in partial fulfillment of the requirements for the degree of Master of Science t the University of Waikato. Department of Computer Science Hamilton, New Zealand February 2007 - February 2008 (cid:13) 2008 James Foulds" d6dab84451254d7fbb5b9e1d40a7d2a92dec13b3,Enhanced Local Binary Patterns for Automatic Face Recognition,"ENHANCED LOCAL BINARY PATTERNS FOR AUTOMATIC FACE RECOGNITION Pavel Kr´al1 , Anton´ın Vrba1 Dept. of Computer Science & Engineering 2New Technologies for the Information Society Faculty of Applied Sciences University of West Bohemia Plzeˇn, Czech Republic Faculty of Applied Sciences University of West Bohemia Plzeˇn, Czech Republic" d65f11b44180d9997ad5ba6e6970fe4874891f4f,Unobtrusive emotion sensing and interpretation in smart environment,"Journal of Ambient Intelligence and Smart Environments 7 (2015) 59–83 DOI 10.3233/AIS-140298 IOS Press Unobtrusive emotion sensing and interpretation in smart environment Oleg Starostenko *, Ximena Cortés, J. Afredo Sánchez and Vicente Alarcon-Aquino Department of Computing, Electronics and Mechatronics, Universidad de las Americas Puebla, Cholula, Pue. 72810, Mexico" d69df51cff3d6b9b0625acdcbea27cd2bbf4b9c0,Robust Remote Heart Rate Determination for E-Rehabilitation - A Method that Overcomes Motion and Intensity Artefacts, d689cdb4e535be040316722229e6362de6617f9e,GEOMETRIC DEEP PARTICLE FILTER FOR MOTORCYCLE TRACKING : DEVELOPMENT OF INTELLIGENT TRAFFIC SYSTEM IN JAKARTA,"INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS VOL. 8, NO. 1, MARCH 2015 GEOMETRIC DEEP PARTICLE FILTER FOR MOTORCYCLE TRACKING: DEVELOPMENT OF INTELLIGENT TRAFFIC SYSTEM IN JAKARTA Alexander A S Gunawan1, Wisnu Jatmiko2 Bina Nusantara University, Mathematics Department, School of Computer Science, Jakarta, Indonesia Faculty of Computer Science,Universitas Indonesia, Depok, Indonesia Submitted: Oct. 4, 2014 Accepted: Jan. 20, 2015 Published: Mar. 1, 2015" d6bfa9026a563ca109d088bdb0252ccf33b76bc6,Unsupervised Temporal Segmentation of Facial Behaviour,"Unsupervised Temporal Segmentation of Facial Behaviour Abhishek Kar Advisors: Dr. Amitabha Mukerjee & Dr. Prithwijit Guha Department of Computer Science and Engineering, IIT Kanpur" d69ef8b5658fabd0ac092fb2bfd0c9c109574dcc,Neural Class-Specific Regression for face verification,"Neural Class-Specific Regression for face verification Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj" d65bcbcddec932480c434f0ffa778e429cdd4ee7,Periocular biometrics: When iris recognition fails,"Periocular Biometrics: When Iris Recognition Fails Samarth Bharadwaj, Himanshu S. Bhatt, Mayank Vatsa and Richa Singh" d660abfbe5f84c1c49f1e7174eb166b8b23e53c4,"AMIGOS: A dataset for Mood, personality and affect research on Individuals and GrOupS","AMIGOS: A dataset for Mood, personality and ffect research on Individuals and GrOupS Nicu Sebe, Senior Member, IEEE, and Ioannis Patras, Senior Member, IEEE" d6102a7ddb19a185019fd2112d2f29d9258f6dec,Fashion Style Generator,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) GeneratorPatch……Global+…lstyle(2)lstyle(1)lcontent(1)lcontent(2)φθϕsϕcDiscriminatorDGXX(1)X(2)(a) Framework of the training stage(b) Examples of fashion style generationFigure1:Fashionstylegeneratorframeworkoverview.TheinputXconsistsofasetofclothingpatchesX(1)andfullclothingimagesX(2).Thesystemconsistsoftwocomponents:animagetransfor-mationnetworkGservedasfashionstylegenerator,andadiscrimi-natornetworkDcalculatesbothglobalandpatchbasedcontentandstylelosses.Gisaconvolutionalencoderdecodernetworkparam-eterizedbyweights(cid:18).Sixgeneratedshirtswithdifferentstylesbyourmethodareshownasexamples.(Wehighlyrecommendtozoominallthefigureswithcolorversionformoredetails.)recentneuralstyletransferworks[Gatysetal.,2015].Tak-ingVanGogh’s“StarryNight”astheexamplestyleimage,styleisbetweenthelow-levelcolor/texture(e.g.,blueandyellowcolor,roughorsmoothertexture)andthehigh-levelobjects(e.g.,houseandmountain).“Style”isarelativelyab-stractconcept.Fashionstylegenerationhasatleasttwoprac-ticalusages.Designerscouldquicklyseehowtheclothinglookslikeinagivenstyletofacilitatethedesignprocessing.Shopperscouldsynthesizetheclothingimagewiththeidealstyleandapplyclothingretrievaltools[Jiangetal.,2016b]tosearchthesimilaritems.Fashionstylegenerationisrelatedtoexistingneuralstyletransferworks[Gatysetal.,2015;LiandWand,2016a;EfrosandFreeman,2001],buthasitsownchallenges.Infashionstylegeneration,thesyntheticclothingimageshould" d623428f02e80a689eb58d022237daeae2ae7b9c,Guided depth upsampling for precise mapping of urban environments,"Guided Depth Upsampling for Precise Mapping of Urban Environments Sascha Wirges1, Bj¨orn Roxin2 , Eike Rehder2, Tilman K¨uhner1 and Martin Lauer2" d65ad3e9293bd1dca1b137f8b81f18e201e76c3a,Supplementary Material for Hierarchical Gaussian Descriptor for Person Re-Identification,"Supplementary Material for Hierarchical Gaussian Descriptor for Person Re-Identification Tetsu Matsukawa1, Takahiro Okabe2, Einoshin Suzuki1, Yoichi Sato3 Kyushu University 2 Kyushu Institute of Technology 3 The University of Tokyo fmatsukawa, . Details of the baseline descriptors In section 4.2 of the paper, we compared the distribu- tion modeling of GOG to other distributions. Below, we describe the details of the compared methods. The Mean, Cov and Gauss are global distribution de- scriptors of pixel features within each region. The Cov-of- Cov, Cov-of-Gauss and GOG are hierarchical distribution descriptors. The Cov-of-Cov uses covariance matrix in both patch and region modeling. The Cov-of-Gauss uses Gaus- sian for patch modeling and covariance matrix for region modeling. For a fair comparison to GOG which is incorporated with patch weights, we adopted the weighted pooling for all de- scriptors. Formally, Mean: (cid:22)" d69b542b3714b5e90c384d39b5ab0c4bf9dd5375,Activity Report 2012 Project-Team EMOTION Geometry and Probability for Motion and Action,"IN PARTNERSHIP WITH: Institut polytechnique de Grenoble Université Pierre Mendes-France (Grenoble) Université Joseph Fourier (Grenoble) Activity Report 2012 Project-Team E-MOTION Geometry and Probability for Motion and Action IN COLLABORATION WITH: Laboratoire d’Informatique de Grenoble (LIG) RESEARCH CENTER Grenoble - Rhône-Alpes THEME Robotics" d6eda0c16d226976506396653d14044c185eaf3e,Toward Multimodal Image-to-Image Translation,"Toward Multimodal Image-to-Image Translation Jun-Yan Zhu UC Berkeley Richard Zhang UC Berkeley Deepak Pathak UC Berkeley Trevor Darrell UC Berkeley Alexei A. Efros UC Berkeley Oliver Wang Adobe Research Eli Shechtman Adobe Research" d6efd1b7b39d91b067488e0c4bf800ce3e3704d8,Visual Analysis of Pedestrian Motion,"Visual Analysis of Pedestrian Motion PRS Transfer Report Supervised by Dr Ian Reid David Ellis St John’s College Robotics Research Group Department of Engineering Science Michaelmas 2009" d6ceebb0cde7fb0fbe916472d7b613a2d7d2e1e6,Do faces capture the attention of individuals with Williams syndrome or autism? Evidence from tracking eye movements.,"Do faces capture the attention of individuals with Williams syndrome or Autism? Evidence from tracking eye movements Deborah M Riby & Peter J B Hancock http://dx.doi.org/10.1007/s10803-008-0641-z" d665213b59f2460faf171d3b03ecd9c96d606883,A MULTIMODAL NONVERBAL HUMAN-ROBOT COMMUNICATION SYSTEM,"VI International Conference on Computational Bioengineering ICCB 2015 M. Cerrolaza and S.Oller (Eds) A MULTIMODAL NONVERBAL HUMAN-ROBOT COMMUNICATION SYSTEM S. SALEH†*, M. SAHU†, Z. ZAFAR† AND K. BERNS† Robotics Research Lab. - Dept. of Computer Science University of Kaiserslautern Kaiserslautern, Germany web page: http://agrosy.cs.uni-kl.de e-mail: {saleh, sahu, zafar, * Dept. of Computer Science, University of Basrah Basrah, Iraq Key words: HRI, Facial Expression Recognition, Nonverbal Communication" d64b24e9b01f4681d92fc29f36e46d94db7b8bb0,Avoiding Extraverts : Pathogen Concern Downregulates Preferences for Extraverted Faces,"See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/305793723 Avoiding Extraverts: Pathogen Concern Downregulates Preferences for Extraverted Faces Article · August 2016 DOI: 10.1007/s40806-016-0064-6 CITATIONS authors, including: Mitch Brown University of Southern Mississippi 6 PUBLICATIONS 5 CITATIONS SEE PROFILE READS Some of the authors of this publication are also working on these related projects: Limbal Rings View project Morality and Mate Preferences View project All content following this page was uploaded by Mitch Brown on 06 December 2016. The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the original document nd are linked to publications on ResearchGate, letting you access and read them immediately." 807913b776bc5039cd3f195841419e55979ec7c7,Recreation of spontaneous non-verbal behavior on a synthetic agent,"Roboti c.s. d.o.o, 2Faculty of Electrical Engineering and Computer Science, University of Maribor IZIDOR MLAKAR, 2MATEJ ROJC Recreation of spontaneous non-verbal behavior on a synthetic agent Tržaška cesta 23, 2Smetanova ulica 17 SLOVENIA systematic sequencing" 80135ed7e34ac1dcc7f858f880edc699a920bf53,EFFICIENT ACTION AND EVENT RECOGNITION IN VIDEOS USING EXTREME LEARNING MACHINES,"EFFICIENT ACTION AND EVENT RECOGNITION IN VIDEOS USING EXTREME LEARNING MACHINES G¨ul Varol B.S., Computer Engineering, Bo˘gazi¸ci University, 2013 Submitted to the Institute for Graduate Studies in Science and Engineering in partial fulfillment of the requirements for the degree of Master of Science Graduate Program in Computer Engineering Bo˘gazi¸ci University" 80d9d4b5d7af67721212c0e9a89efb7f69671a5c,People detection and tracking using a network of low-cost depth cameras,"Tommi Tikkanen People detection and tracking using a network of low-cost depth cameras School of Electrical Engineering Thesis submitted for examination for the degree of Master of Science in Technology. Espoo 20.1.2014 Thesis supervisor: Thesis advisor: Prof. Arto Visala M.Sc. (Tech.) Otto Korkalo" 801a80f7a18fccb2e8068996a73aee2cf04ae460,Optimal transport maps for distribution preserving operations on latent spaces of Generative Models,"OPTIMAL TRANSPORT MAPS FOR DISTRIBUTION PRE- SERVING OPERATIONS ON LATENT SPACES OF GENER- ATIVE MODELS Eirikur Agustsson D-ITET, ETH Zurich Switzerland Alexander Sage D-ITET, ETH Zurich Switzerland Radu Timofte D-ITET, ETH Zurich Merantix GmbH Luc Van Gool D-ITET, ETH Zurich ESAT, KU Leuven" 808b03e28bb45bd446ee7e82f767e48db354fefd,Fast Optical Flow using Dense Inverse Search Supplementary Material,"Fast Optical Flow using Dense Inverse Search Supplementary Material Till Kroeger1 Radu Timofte1 Dengxin Dai1 Luc Van Gool1,2 Computer Vision Laboratory, D-ITET, ETH Zurich VISICS / iMinds, ESAT, KU Leuven {kroegert, timofter, dai, A Derivation of the fast inverse search in § 2.1 of the paper We adopt the terminology of [1,2] and closely follow their derivation. We consider W(x; u) a warp, parametrized by u = (u, v)T , on pixel x such that W(x; u) = (x + u, y + v). The following derivation holds for other warps as well: See [2] for a discussion on the limits of its applicability. The objective function for the inverse search, eq. (1) in the paper, then becomes (cid:88) [It+1(W(x; u)) − T (x)]2 . The warp parameter u is found by iteratively minimizing [It+1(W(x; u + ∆u)) − T (x)]2" 809e25da311366bfd684228e16184737d948eef6,Supplementary material for : Learning Finer-class Networks for Universal Representations,"GIRARD ET AL.: SUPPLEMENTARY FOR FINER-CLASS NETWORKS Supplementary material for: Learning Finer-class Networks for Universal Representations Julien Girard12 Youssef Tamaazousti123 Hervé Le Borgne2 Céline Hudelot3 Both authors contributed equally. CEA LIST Vision Laboratory, Gif-sur-Yvette, France. CentraleSupélec, MICS Laboratory, Châtenay-Malabry, France." 802ecaabffbece0dc2c31d44b693967c683fc5ff,Faster RER-CNN: application to the detection of vehicles in aerial images,"Faster RER-CNN: application to the detection of vehicles in aerial images Jean Ogier du Terrail(1,2), Fr´ed´eric Jurie(1) (1)Normandie Univ, UNICAEN, ENSICAEN, CNRS (2)Safran Electronics and Defense September 21, 2018" 8093b784be493efc1d833af7e99c5de72eb5afe9,Understanding object descriptions in robotics by open-vocabulary object retrieval and detection,"Understanding Object Descriptions in Robotics by Open-vocabulary Object Retrieval and Detection The International Journal of Robotics Research 000(00):1–20 (cid:13)The Author(s) 2010 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI:doi number http://mms.sagepub.com Sergio Guadarrama∗1, Erik Rodner2, Kate Saenko3 and Trevor Darrell1 EECS Department, University of California at Berkeley, USA Computer Vision Group, Friedrich Schiller University of Jena, Germany CS Department, University of Massachussetts Lowell, USA" 8064d7a28c763ec37a840450d729f23428ad8f8b,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 80c8d143e7f61761f39baec5b6dfb8faeb814be9,Local Directional Pattern based Fuzzy Co-occurrence Matrix Features for Face recognition,"Local Directional Pattern based Fuzzy Co- occurrence Matrix Features for Face recognition Dr. P Chandra Sekhar Reddy Professor, CSE Dept. Gokaraju Rangaraju Institute of Engineering and Technology, Hyd." 80510c47d7fad872b18d865f3957568dc512780c,Occlusion Invariant 3 D Face Recognition with UMB – DB and BOSPHORUS Databases,"International Journal of Computer Applications (0975 – 8887) National Conference on Advances in Computing (NCAC 2015) Occlusion Invariant 3D Face Recognition with UMB – DB nd BOSPHORUS Databases G.E.S. R.H. Sapat College of Engineering, Nashik G.E.S. R.H. Sapat College of Engineering, Nashik H. Y. Patil, PhD Assistant Professor (Dept. of E&TC), Maharashtra Charushila R. Singh M.E. student (Dept. of E&TC), Maharashtra" 804b4c1b553d9d7bae70d55bf8767c603c1a09e3,CLUSTERING WITH A LEARNED DIMENSIONALITY REDUCTION PROJECTION,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 80fdf9757c0e4b62dcfff03941f1951304ba002c,Geometry of face space,"Geometry of face space Lawrence Sirovich and Marsha Meytlis Laboratory of Applied Mathematics Mount Sinai School of Medicine Gustave L. Levy Place New York, NY 10029" 80345fbb6bb6bcc5ab1a7adcc7979a0262b8a923,Soft Biometrics for a Socially Assistive Robotic Platform,"Research Article Pierluigi Carcagnì*, Dario Cazzato, Marco Del Coco, Pier Luigi Mazzeo, Marco Leo, and Cosimo Distante Soft Biometrics for a Socially Assistive Robotic Platform Open Access" 800cbbe16be0f7cb921842d54967c9a94eaa2a65,MULTIMODAL RECOGNITION OF EMOTIONS,"MULTIMODAL RECOGNITION OF EMOTIONS" 8010636454316faf1a09202542af040ffd04fefa,"Performance Parameter Analysis of Face Recognition Based On Fuzzy C-Means Clustering , Shape and Corner Detection","Minj Salen Kujur et al Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.515-520 RESEARCH ARTICLE OPEN ACCESS Performance Parameter Analysis of Face Recognition Based On Fuzzy C-Means Clustering, Shape and Corner Detection Minj Salen Kujur1, Prof. Prashant Jain2 Department of Electronics & Communication Engineering college Jabalpur" 80265d7c9fe6a948dd8c975bd4d696fb7ba099c9,Face Recognition Based on Human Visual Perception Theories and Unsupervised ANN,"Face Recognition Based on Human Visual Perception Theories and Unsupervised ANN Mario I. Chacon M. and Pablo Rivas P. Chihuahua Institute of Technology Mexico . Introduction The face recognition problem has been faced for more than 30 years. Although a lot of research has been done, much more research is and will be required in order to end up with robust face recognition system with a potential close to human performance. Currently face recognition systems, FRS, report high performance levels, however achievement of 00% of correct recognition is still a challenge. Even more, if the FRS must work on non- ooperative environment its performance may decrease dramatically. Non-cooperative environments are characterized by changes on; pose, illumination, facial expression. Therefore FRS for non-cooperative environment represents an attractive challenge to researchers working on the face recognition area. Most of the work presented in the literature dealing with the face recognition problem follows an engineering approach that in some cases do not incorporate information from a psychological or neuroscience perspective. It is our interest in this material, to show how information from the psychological and neuroscience areas may contribute in the solution of" 80242615f2370f494432633adcd620e04dbecbc1,Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation,"Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation Yoshikatsu Nakajima1, Keisuke Tateno2, Federico Tombari2 and Hideo Saito1" 80c4f5bc43f21041343c6d7a61cdc281cb36be07,"Information routing, correspondence finding, and object recognition in the brain","Information Routing, Correspondence Finding, and Object Recognition in the Brain DISSERTATION Erlangung des Grades „Doktor der Naturwissenschaften“ vorgelegt beim Fachbereich Informatik und Mathematik der Goethe-Universität Frankfurt am Main Philipp Wolfrum Heilbronn Frankfurt (2008)" 803c92a3f0815dbf97e30c4ee9450fd005586e1a,Max-Mahalanobis Linear Discriminant Analysis Networks,"Max-Mahalanobis Linear Discriminant Analysis Networks Tianyu Pang 1 Chao Du 1 Jun Zhu 1" 805c77bd351fc98d6acbee68b73af915c5cb6776,Overview of the ImageCLEF 2012 Scalable Web Image Annotation Task,"Overview of the ImageCLEF 2012 Scalable Web Image Annotation Task Mauricio Villegas and Roberto Paredes Institut Tecnol`ogic d’Inform`atica Universitat Polit`ecnica de Val`encia Cam´ı de Vera s/n, 46022 Val`encia, Spain" 80a6bb337b8fdc17bffb8038f3b1467d01204375,Subspace LDA Methods for Solving the Small Sample Size Problem in Face Recognition,"Proceedings of the International Conference on Computer and Information Science and Technology Ottawa, Ontario, Canada, May 11 – 12, 2015 Paper No. 126 Subspace LDA Methods for Solving the Small Sample Size Problem in Face Recognition Ching-Ting Huang, Chaur-Chin Chen Department of Computer Science/National Tsing Hua University 01 KwanFu Rd., Sec. 2, Hsinchu, Taiwan" 801b0ae343a11a15fd7abc5720831afea6f0a61d,Similarity Learning with Listwise Ranking for Person Re-Identification,"SIMILARITY LEARNING WITH LISTWISE RANKING FOR PERSON RE-IDENTIFICATION Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt To cite this version: Yiqiang Chen, Stefan Duffner, Andrei Stoian, Jean-Yves Dufour, Atilla Baskurt. SIMILARITY LEARNING WITH LISTWISE RANKING FOR PERSON RE-IDENTIFICATION. International onference on image processing, Oct 2018, Athenes, Greece. HAL Id: hal-01895355 https://hal.archives-ouvertes.fr/hal-01895355 Submitted on 15 Oct 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 8031dd2c6583d8681fdd85bdae4371c7c745713f,Generative adversarial models for people attribute recognition in surveillance,"Generative Adversarial Models for People Attribute Recognition in Surveillance Matteo Fabbri Simone Calderara Rita Cucchiara University of Modena and Reggio Emilia via Vivarelli 10 Modena 41125 Italy" 80097a879fceff2a9a955bf7613b0d3bfa68dc23,Active Self-Paced Learning for Cost-Effective and Progressive Face Identification,"Active Self-Paced Learning for Cost-Effective and Progressive Face Identification Liang Lin, Keze Wang, Deyu Meng, Wangmeng Zuo, and Lei Zhang" 80c8f02c945c1dbbec31983164c1e4e0b742c44a,Cohort of LSTM and lexicon verification for handwriting recognition with gigantic lexicon,"Cohort of LSTM and lexicon verification for handwriting recognition with gigantic lexicon Bruno STUNERa,∗, Cl´ement CHATELAINa, Thierry PAQUETa Normandie Univ, UNIROUEN, UNIHAVRE, INSA Rouen, LITIS, 76000 Rouen, France" 8097841cc4f3559e32c32db97624255808bacf22,Biometrie symmetry: Implications on template protection,"Biometric Symmetry: Implications on Template Protection M. Gomez-Barrero∗, C. Rathgeb∗, K. B. Raja†, R. Raghavendra†, C. Busch∗ da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany Email: Norwegian Biometrics Laboratory, NTNU, Gjøvik, Norway Email:" 8047586d2223f3076a1fc028197f54d0997bccfc,Pelee: A Real-Time Object Detection System on Mobile Devices,"2nd Conference on Neural Information Processing Systems (NeurIPS 2018) Pelee: A Real-Time Object Detection System on Mobile Devices Robert J. Wang, Xiang Li & Charles X. Ling Department of Computer Science University of Western Ontario London, Ontario, Canada, N6A 3K7" 8096279890779bdcce4bfa8e1f753389e8eb8fda,A Real-Time Pedestrian Detector using Deep Learning for Human-Aware Navigation,"A Real-Time Pedestrian Detector using Deep Learning for Human-Aware Navigation David Ribeiro, Andr´e Mateus, Jacinto C. Nascimento, and Pedro Miraldo" 57165586f65f25edd9d14f0173c4c35dab8c2e66,Aligning plot synopses to videos for story-based retrieval,"Noname manuscript No. (will be inserted by the editor) Aligning Plot Synopses to Videos for Story-based Retrieval Makarand Tapaswi · Martin B¨auml · Rainer Stiefelhagen Received: date / Accepted: date" 573b687ad970e1931debbf366004c0983de28718,A Corpus for Investigating the Multimodal Nature of Multi-Speaker Spontaneous Conversations – EVA Corpus,"A Corpus for Investigating the Multimodal Nature of Multi-Speaker Spontaneous Conversations – EVA Corpus IZIDOR MLAKAR, ZDRAVKO KAČIČ, MATEJ ROJC Faculty of Electrical Engineering and Computer Science, University of Maribor SLOVENIA" 578d4ad74818086bb64f182f72e2c8bd31e3d426,"The MR2: A multi-racial, mega-resolution database of facial stimuli.","Behav Res DOI 10.3758/s13428-015-0641-9 The MR2: A multi-racial, mega-resolution database of facial stimuli Nina Strohminger1,6 · Kurt Gray2 · Vladimir Chituc3 · Joseph Heffner4 · Chelsea Schein2 · Titus Brooks Heagins5 © Psychonomic Society, Inc. 2015" 57235f22abcd6bb928007287b17e235dbef83347,Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency,"EXEMPLAR GUIDED UNSUPERVISED IMAGE-TO- IMAGE TRANSLATION WITH SEMANTIC CONSISTENCY Liqian Ma1 Xu Jia2 KU-Leuven/PSI, TRACE (Toyota Res in Europe) {liqian.ma, xu.jia, tinne.tuytelaars, {georgous, Stamatios Georgoulis1,3 Tinne Tuytelaars2 Luc Van Gool1,3 KU-Leuven/PSI, IMEC 3ETH Zurich" 5725c06b406b5291915a6bef8b5c3d20b2873aa0,Face Recognition Using Principal Component Analysis Based Feature Space By Incorporating With Probabilistic Neural Network,"International Journal of Computer Science Trends and Technology (IJCST) – Volume 4 Issue 2, Mar - Apr 2016 RESEARCH ARTICLE OPEN ACCESS Face Recognition Using Principal Component Analysis Based Feature Space By Incorporating With Probabilistic Muhammad Tahir, Shahid Akbar, Shahzad, Maqsood Hayat, Nazia Azim Neural Network Department of Computer Science Abdul Wali Khan University Mardan - Pakistan" 57e8e226e605fe6491111c5dc9461527c5fce56c,Articulated Object Detection,"Articulated Object Detection Maciej Halber MEng Computer Science Submission Date: 26th April 2013 Supervisors Niloy J. Mitra Simon Julier This report is submitted as part requirement for the MEng Degree in Computer Science at UCL. It is substantially the result of my own work except where ex- plicitly indicated in the text. The report may be freely copied and distributed provided the source is explicitly acknowledged." 579bf3ac200b6262458b054e3866f76a80d4b6d8,Recognition and Detection of Occluded Faces by a Neural Network Classifier with Recursive Data Reconstruction,"RECOGNITION AND DETECTION OF OCCLUDED FACES BY A NEURAL NETWORK CLASSIFIER WITH RECURSIVE DATA RECONSTRUCTION T. Kurita, M. Pic T. Takahashi Neuroscience Research Institute, AIST takio-kurita,mickael.pic" 576372383bfd6ce6944d885e60b19151efdffc99,Can we unify monocular detectors for autonomous driving by using the pixel-wise semantic segmentation of CNNs?,"Can we unify monocular detectors for autonomous driving y using the pixel-wise semantic segmentation of CNNs? Eduardo Romera, Luis M. Bergasa, Roberto Arroyo" 57d37ad025b5796457eee7392d2038910988655a,Aeaeêêìáîî Áåèääååaeììáçae Çç Àááêêêàáááä Aeçîîäìì Ììììçê,"GEERATVEEETATF ERARCCAVETYDETECTR DagaEha UdeheS eviif f.DahaWeiha ATheiS biediaiaF (cid:28)efhe Re ieefheDegeef aefSciece TheSchfC eScieceadEgieeig ebewUiveiyfe aeae91904 Decebe2009" 57a14a65e8ae15176c9afae874854e8b0f23dca7,Seeing Mixed Emotions: The Specificity of Emotion Perception From Static and Dynamic Facial Expressions Across Cultures,"UvA-DARE (Digital Academic Repository) Seeing mixed emotions: The specificity of emotion perception from static and dynamic facial expressions across cultures Fang, X.; Sauter, D.A.; van Kleef, G.A. Published in: Journal of Cross-Cultural Psychology 0.1177/0022022117736270 Link to publication Citation for published version (APA): Fang, X., Sauter, D. A., & van Kleef, G. A. (2018). Seeing mixed emotions: The specificity of emotion perception from static and dynamic facial expressions across cultures. Journal of Cross-Cultural Psychology, 49(1), 130- 48. DOI: 10.1177/0022022117736270 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible." 5712cfc11c561c453da6a31d515f4340dacc91a4,3D Facial Expression Reconstruction using Cascaded Regression,"SUBMITTED TO PATTERN RECOGNITION LETTERS Cascaded Regression using Landmark Displacement for 3D Face Reconstruction Fanzi Wu, Songnan Li, Tianhao Zhao, and King Ngi Ngan,Lv Sheng" 57f8e1f461ab25614f5fe51a83601710142f8e88,Region Selection for Robust Face Verification using UMACE Filters,"Region Selection for Robust Face Verification using UMACE Filters Salina Abdul Samad*, Dzati Athiar Ramli, Aini Hussain Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia. In this paper, we investigate the verification performances of four subdivided face images with varying expressions. The objective of this study is to evaluate which part of the face image is more tolerant to facial expression and still retains its personal haracteristics due to the variations of the image. The Unconstrained Minimum Average Correlation Energy (UMACE) filter is implemented to perform the verification process because of its advantages such as shift–invariance, ability to trade-off between discrimination and distortion tolerance, e.g. variations in pose, illumination and facial expression. The database obtained from the facial expression database of Advanced Multimedia Processing (AMP) Lab at CMU is used in this study. Four equal sizes of face regions i.e. bottom, top, left and right halves are used for the purpose of this study. The results show that the bottom half of the face region gives the best performance in terms of the PSR values with zero false accepted rate (FAR) and zero false rejection rate (FRR) compared to the other three regions. . Introduction Face recognition is a well established field of research, nd a large number of algorithms have been proposed in the literature. Various classifiers have been explored to improve the accuracy of face classification. The basic approach is to use distance-base methods which measure Euclidean distance etween any two vectors and then compare it with the preset" 57a1466c5985fe7594a91d46588d969007210581,A taxonomy of face-models for system evaluation,"A Taxonomy of Face-models for System Evaluation Vijay N. Iyer, Shane. R. Kirkbride, Brian C. Parks, Walter J. Scheirer and Terrance. E. Boult Motivation and Data Types Synthetic Data Types Unverified – Have no underlying physical or statistical basis Physics -Based – Based on structure and materials combined with the properties formally modeled in physics. Statistical – Use statistics from real data/experiments to estimate/learn model parameters. Generally have measurements of accuracy Guided Synthetic – Individual models based on individual people. No attempt to capture properties of large groups, a unique model per person. For faces, guided models are omposed of 3D structure models and skin textures, capturing many artifacts not easily parameterized. Can be combined with" 57680f0d53392178bb3c431e03bcd8626c12f620,SEMANTIC IMAGE SEGMENTATION,"Workshop track - ICLR 2017 ADVERSARIAL EXAMPLES FOR SEMANTIC IMAGE SEGMENTATION Volker Fischer1, Mummadi Chaithanya Kumar2, Jan Hendrik Metzen1 & Thomas Brox2 Bosch Center for Artificial Intelligence, Robert Bosch GmbH University of Freiburg {volker.fischer," 57e9b0d3ab6295e914d5a30cfaa3b2c81189abc1,Self-Learning Scene-Specific Pedestrian Detectors Using a Progressive Latent Model,"Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model Qixiang Ye1,4, Tianliang Zhang 1, Qiang Qiu4, Baochang Zhang2, Jie Chen3, and Guillermo Sapiro4 EECE, University of Chinese Academy of Sciences. ASEE, Beihang University. 3CMV, Oulu University. 4ECE, Duke University." 5720784b7e45693109b867992e3f93e4c747e536,Sparse Methods for Robust and Efficient Visual Recognition, 57b55a7a1adc8ec06285ebaf93995d67cf80c719,External Data Overcomplete Dictionary Similarity Graph ≈ + Probeimage Gallery Compressed Dictionary With Coefficient Design Phase : Operational Phase : CD Compressed Dictionary, 57e562cf99b3dfbb6baa5bbf665aa6fd97ffe8ca,Expression-Compensated 3D Face Recognition with Geodesically Aligned Bilinear Models,"Expression-Compensated 3D Face Recognition with Geodesically Aligned Bilinear Models Iordanis Mpiperis1,2,Sotiris Malassiotis1 and Michael G. Strintzis1,2" 57126589b3fe62c35a36a2646dac3045d095ecf5,Adversarial Defense based on Structure-to-Signal Autoencoders,"Adversarial Defense based on Structure-to-Signal Autoencoders Joachim Folz(cid:63), Sebastian Palacio(cid:63), Joern Hees, Damian Borth, and Andreas Dengel German Research Center for Artificial Intelligence (DFKI) TU Kaiserslautern" 5700291077b509b11fb227f84ee9fc2de8f2df99,Line search and trust region strategies for canonical decomposition of semi-nonnegative semi-symmetric 3 rd order tensors,"Line search and trust region strategies for canonical decomposition of semi-nonnegative semi-symmetric 3rd Julie Coloigner, Ahmad Karfoul, Laurent Albera, Pierre Comon order tensors To cite this version: Julie Coloigner, Ahmad Karfoul, Laurent Albera, Pierre Comon. Line search and trust region strategies for canonical decomposition of semi-nonnegative semi-symmetric 3rd order tensors. Linear Algebra and Applications, Elsevier - Academic Press, 2014, 450, pp.334-374. HAL Id: hal-00945606 https://hal.archives-ouvertes.fr/hal-00945606 Submitted on 12 Feb 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," 57ff1222a78a230c46fc81f22daa57981b0fa306,Face recognition in multi-camera surveillance videos using Dynamic Bayesian Network,"Face Recognition in Multi-Camera Surveillance Videos using Dynamic Bayesian Network Center for Research Le An, Mehran Kafai, Bir Bhanu in Intelligent Systems, University of California, Riverside .edu, mkafai bhanu" 57246142814d7010d3592e3a39a1ed819dd01f3b,Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-resolution Network,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Verification of Very Low-Resolution Faces Using An Identity-Preserving Deep Face Super-resolution Network Ataer-Cansizoglu, E.; Jones, M.J.; Zhang, Z.; Sullivan, A. TR2018-116 August 24, 2018" 57db5825a8eb2927735fb7c18c3ee4fb18d27d47,Max-Mahalanobis Linear Discriminant Analysis Networks,"Max-Mahalanobis Linear Discriminant Analysis Networks Tianyu Pang 1 Chao Du 1 Jun Zhu 1" 57c59011614c43f51a509e10717e47505c776389,Unsupervised Human Action Detection by Action Matching,"Unsupervised Human Action Detection by Action Matching Basura Fernando∗ Sareh Shirazi† Stephen Gould∗ The Australian National University †Queensland University of Technology" 5782d17ad87262739d69dcbe76cadfa881179a91,Data Analysis Project : What Makes Paris Look like Paris ?,"Data Analysis Project: What Makes Paris Look like Paris? Machine Learning Department Carnegie-Mellon University Pittsburgh, PA 15213 Carl Doersch⇤" 57fd8bafa4526b9a56fe43fac22dd62b2ab94563,BEYOND SHARED HIERARCHIES: DEEP MULTITASK LEARNING THROUGH SOFT LAYER ORDERING,"Under review as a conference paper at ICLR 2018 BEYOND SHARED HIERARCHIES: DEEP MULTITASK LEARNING THROUGH SOFT LAYER ORDERING Anonymous authors Paper under double-blind review" 5740a5f9cbfe790afc0ba9a425cfb71197927470,Supplementary Material for Superpixel Sampling Networks,"Supplementary Material for Superpixel Sampling Networks Varun Jampani1, Deqing Sun1, Ming-Yu Liu1, Ming-Hsuan Yang1,2, Jan Kautz1 NVIDIA UC Merced In Section 1, we formally define the Acheivable Segmentation Accuracy (ASA) used for evaluating superpixels. Then, in Section 2, we report F-measure and Compactness scores with more visual results on different datasets. We also in- lude a supplementary video1 that gives an overview of Superpixel Sampling Networks (SSN) with a glimpse of experimental results. Evaluation Metrics Here, we formally define the Achievable Segmentation Accuracy (ASA) met- ric that is used in the main paper. Given an image I with n pixels, let H ∈ {0, 1,··· , m}n×1 denotes the superpixel segmentation with m superpixels. H is j=1 H j, where jth segment is repre- sented as H j. Similarly, let G ∈ {0, 1,··· , w}n×1 denotes ground-truth (GT) l=1 Gl, where Gl denotes lth GT segment. ASA Score. The ASA score between a given superpixel segmentation H and the GT segmentation G is defined as" 57fd229097e4822292d19329a17ceb013b2cb648,Fast Structural Binary Coding,"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16) Fast Structural Binary Coding ⇤Department of Electrical and Computer Engineering,University of California, San Diego Dongjin Song⇤, Wei Liu], and David A. Meyer† La Jolla, USA, 92093-0409. Email: ] Didi Research, Didi Kuaidi, Beijing, China. Email: Department of Mathematics,University of California, San Diego La Jolla, USA, 92093-0112. Email:" 9c4365a56fb3cf41b15712657b15f7422ca0dab2,A Hybrid Supervised-Unsupervised Vocabulary Generation Algorithm for Visual Concept Recognition,"A Hybrid Supervised-Unsupervised Vocabulary Generation Algorithm for Visual Concept Recognition Alexander Binder1, Wojciech Wojcikiewicz1,2, Christina M¨uller1,2, and Motoaki Kawanabe1,2 Berlin Institute of Technology, Machine Learning Group, Franklinstr. 28/29, 10587 Berlin, Germany Fraunhofer Institute FIRST, Kekul´estr. 7, 12489 Berlin, Germany" 9c2739256937fbe66c5b5ce2a23d2d47b48aa4aa,On Optimising Local Feature Face Recognition for Mobile Devices !,"Huesca • 2 y 3 de Septiembre de 2010 V Jornadas de Reconocimiento Biom´etrico de Personas On Optimising Local Feature Face Recognition for Mobile Devices! Mauricio Villegas and Roberto Paredes Instituto Tecnol´ogico de Inform´atica Universidad Polit´ecnica de Valencia Camino de Vera s/n, Edif. 8G Acc. B 46022 Valencia (Spain)" 9cc4abd2ec10e5fa94ff846c5ee27377caf17cf0,Improved Techniques for GAN based Facial Inpainting,"Improved Techniques for GAN based Facial Inpainting Avisek Lahiri*, Arnav Jain*, Divyasri Nadendla and Prabir Kumar Biswas, Senior Member, IEEE" 9c8da385750db215dc0728dc310251b320d319af,- CL-TR-899 ISSN 1476-2986 Deep embodiment : grounding semantics in perceptual modalities,"Technical Report UCAM-CL-TR-899 ISSN 1476-2986 Number 899 Computer Laboratory Deep embodiment: grounding semantics in perceptual modalities Douwe Kiela February 2017 5 JJ Thomson Avenue Cambridge CB3 0FD United Kingdom phone +44 1223 763500 http://www.cl.cam.ac.uk/" 9c63c2210b5dde771ec8751cebc4281e74034fb0,CNN for IMU assisted odometry estimation using velodyne LiDAR,"CNN for IMU Assisted Odometry Estimation using Velodyne LiDAR Martin Velas, Michal Spanel, Michal Hradis, and Adam Herout" 9ca82f5936723a773fb44336cd66c315f2024d34,Latent-Class Hough Forests for 3D Object Detection and Pose Estimation,"Latent-Class Hough Forests for 3D Object Detection nd Pose Estimation Alykhan Tejani, Danhang Tang, Rigas Kouskouridas, and Tae-Kyun Kim Imperial Collge London" 9cdb83ed96f5aa74bc4e2e9edacfbb5263e8fc37,Learning Mutual Visibility Relationship for Pedestrian Detection with a Deep Model,"Manuscript Click here to download Manuscript: Mutual-DBN-J2.pdf Click here to view linked References Noname manuscript No. (will be inserted by the editor) Learning Mutual Visibility Relationship for Pedestrian Detection with a Deep Model Wanli Ouyang · Xingyu Zeng · Xiaogang Wang Received: date / Accepted: date" 9cb152758ee57f2abcc0b59348752e528a2ed2f7,Full Video Processing for Mobile Audio-Visual Identity Verification, 9c1860de6d6e991a45325c997bf9651c8a9d716f,3D reconstruction and face recognition using kernel-based ICA and neural networks,"D Reconstruction and Face Recognition Using Kernel-Based ICA and Neural Networks Cheng-Jian Lin Ya-Tzu Huang Chi-Yung Lee Dept. of Electrical Dept. of CSIE Dept. of CSIE Engineering Chaoyang University Nankai Institute of National University of Technology Technology of Kaohsiung" 9ce0d64125fbaf625c466d86221505ad2aced7b1,Recognizing expressions of children in real life scenarios View project PhD ( Doctor of Philosophy ) View project,"Saliency Based Framework for Facial Expression Recognition Rizwan Ahmed Khan, Alexandre Meyer, Hubert Konik, Saïda Bouakaz To cite this version: Rizwan Ahmed Khan, Alexandre Meyer, Hubert Konik, Saïda Bouakaz. Saliency Based Framework for Facial Expression Recognition. Frontiers of Computer Science, 2017, <10.1007/s11704-017-6114-9>. HAL Id: hal-01546192 https://hal.archives-ouvertes.fr/hal-01546192 Submitted on 23 Jun 2017 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 9caa7f125d3e861450bc3685699fceeaebea04d8,Designing Video Surveillance Systems as Services,"Designing Video Surveillance Systems as Services R. Cucchiara and A. Prati and R. Vezzani" 9c781f7fd5d8168ddae1ce5bb4a77e3ca12b40b6,Attribute Based Face Classification Using Support Vector Machine Brindha,"International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 03 Issue: 07 | July-2016 www.irjet.net p-ISSN: 2395-0072 Attribute Based Face Classification Using Support Vector Machine Brindha.M1, Amsaveni.R2 Research Scholar, Dept. of Computer Science, PSGR Krishnammal College for Women, Coimbatore Assistant Professor, Dept. of Information Technology, PSGR Krishnammal College for Women, Coimbatore." 9cd3ea5cbbe0716fe19ff750940222cdedb22fc8,Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Scientific Question Answering,"Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Scientific Question Answering Jianmo Ni1,2∗, Chenguang Zhu1, Weizhu Chen1, Julian McAuley2 Microsoft Business Applications Group AI Research Department of Computer Science, UC San Diego" 9cc3172efb42d2f9fa1b9ae7b7eef9cc349cdef9,Imbalanced Deep Learning by Minority Class Incremental Rectification,"Imbalanced Deep Learning by Minority Class Incremental Rectification Qi Dong, Shaogang Gong, and Xiatian Zhu" 9cf07922cf91c4aea66c8d72606ca444f4607cc6,Distinct neural activation patterns underlie economic decisions in high and low psychopathy scorers.,"doi:10.1093/scan/nst093 SCAN (2014) 9,1099^1107 Distinct neural activation patterns underlie economic decisions in high and low psychopathy scorers Joana B. Vieira,1,2,3 Pedro R. Almeida,1,4 Fernando Ferreira-Santos,1 Fernando Barbosa,1 Joa˜o Marques-Teixeira,1 nd Abigail A. Marsh3 Laboratory of Neuropsychophysiology, Faculty of Psychology and Educational Sciences, 2Faculty of Medicine, University of Porto, 4200-135 Porto, Portugal, 3Department of Psychology, Georgetown University, Washington, DC 20057, USA, and 4School of Criminology, Faculty of Law, University of Porto, 4200-135 Porto, Portugal Psychopathic traits affect social functioning and the ability to make adaptive decisions in social interactions. This study investigated how psychopathy ffects the neural mechanisms that are recruited to make decisions in the ultimatum game. Thirty-five adult participants recruited from the community underwent functional magnetic resonance imaging scanning while they performed the ultimatum game under high and low cognitive load. Across load onditions, high psychopathy scorers rejected unfair offers in the same proportion as low scorers, but perceived them as less unfair. Among low scorers, the perceived fairness of offers predicted acceptance rates, whereas in high scorers no association was found. Imaging results revealed that responses in each group were associated with distinct patterns of brain activation, indicating divergent decision mechanisms. Acceptance of unfair offers was associated with dorsolateral prefrontal cortex activity in low scorers and ventromedial prefrontal cortex activity in high scorers. Overall, our findings point to distinct motivations for rejecting unfair offers in individuals who vary in psychopathic traits, with rejections in high psychopathy scorers being probably induced by frustration. Implications of these results for models of ventromedial prefrontal cortex dysfunction in psychopathy re discussed. Keywords: psychopathy; functional magnetic resonance imaging; ultimatum game; ventromedial prefrontal cortex" 9c2039d036c01e421176d33c1436633d03be4678,Review of Person Re-identification Techniques,"Received on 21st February 2013 Revised on 14th November 2013 Accepted on 18th December 2013 doi: 10.1049/iet-cvi.2013.0180 www.ietdl.org ISSN 1751-9632 Review of person re-identification techniques Mohammad Ali Saghafi1, Aini Hussain1, Halimah Badioze Zaman2, Mohamad Hanif Md. Saad1 Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia (UKM), Bangi, Malaysia Institute of Visual Informatics, Universiti Kebangsaan Malaysia (UKM), Bangi, Malaysia E-mail:" 9cd8e1ccc5a410c7f31c7e404588597c0bb1952b,What ’ s your type ? Personalized Prediction of Facial Attractiveness 
,"Whats Your Type? Personalized Prediction of Facial Attractiveness Sam Crognale, Computer Science, Danish Shabbir Electrical Engineering INTRODUCTION Attempts to obtain a universal model of facial beauty by the way of symmetry, golden ratios, and measured placement of various facial features fall short in explaining the varied attraction that is actually witnessed in the world. In this investigation, we devise an application to give a user some insight about their ‘type’ as users swipe yes or no on a large dataset of images There is a wealth of interesting literature attempting to map the psychophysics of attraction. For example, Johnston nd Franklin (1993) use a genetic algorithm which evolves a “most beautiful” female face according to interactive user selections. They sought to mimic the way humans filter for features they find the most attractive. Our approach builds on Kagian et. al (2007), where it was shown that feature selection and training procedure with the original geometric features instead of the eigenfeatures fails" 9cb916aa3672a8071d2d77931ed221f4f98138f2,Composition-Aided Face Photo-Sketch Synthesis,"JOURNAL OF LATEX CLASS FILES, VOL. X, NO. X, XX 2018 Composition-Aided Face Photo-Sketch Synthesis Jun Yu, Senior Member, IEEE,, Shengjie Shi, Fei Gao, Dacheng Tao, Fellow, IEEE, nd Qingming Huang, Fellow, IEEE" 9c6d92f3d796242332ebf419a4f9b584864cfa15,Genetic Model Optimization for Hausdorff Distance-Based Face Localization,"(cid:176) In Proc. International ECCV 2002 Workshop on Biometric Authentication, Springer, Lecture Notes in Computer Science, LNCS-2359, pp. 103{111, Copenhagen, Denmark, June 2002. Genetic Model Optimization for Hausdorfi Distance-Based Face Localization Klaus J. Kirchberg, Oliver Jesorsky, and Robert W. Frischholz BioID AG, Germany WWW home page: http://www.bioid.com" 9c2f3e9c223153b70f37ee84224d67b5a577bd58,Towards unlocking web video: Automatic people tracking and clustering,"Towards Unlocking Web Video: Automatic People Tracking and Clustering Alex Holub*, Pierre Moreels*, Atiq Islam*, Andrei Makhanov*, Rui Yang* Ooyala Inc, 800 W. El Camino Real, Suite 350, Mountain View, CA 94040 *All authors contributed equally to this work" 9c93512df188d7dbab63ebe47586a930559e6279,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 9cf6d66a0b4e5a3347466a60caea411d67c4b5b7,Joint transfer component analysis and metric learning for person re-identification,"Joint transfer component analysis and metric learning for person re-identification Yixiu Liu, Yunzhou Zhang✉, Sonya Coleman and Jianning Chi nd efficient metric A novel learning strategy for person re-identification is proposed. Person re-identification is formulated as multi-domain learning problem. The assumption that the feature dis- tributions from different camera views are the same is overthrown in this Letter. ID-based transfer component analysis (IDB-TCA) is pro- posed to learn a shared subspace, in which the differences in the feature distribution between source domain and target domain are sig- nificantly reduced. Experimental evaluation on the CUHK01 dataset demonstrates that metric learning with IDB-TCA embedded outper- forms state-of-art metric methods for person re-identification. Introduction: Person re-identification, aiming to finding the images that match the target person in a large-scale image library, greatly reduces the time cost of human search. Due to its great significance to visual super- vision, it has rapidly become a research hotspot in the field of computer" 9ca2dfe8a6265c4f6ea12bae0e7ff6ffc9128226,Dialog-based Interactive Image Retrieval,"Dialog-based Interactive Image Retrieval Xiaoxiao Guo† IBM Research AI Hui Wu† IBM Research AI Steven Rennie Fusemachines Inc. Gerald Tesauro IBM Research AI" 9c3b9dee9da817134325357afbebbd1a0d67cab2,Deep Learning for Saliency Prediction in Natural Video,"Deep Learning for Saliency Prediction in Natural Video Souad CHAABOUNIa,b, Jenny BENOIS-PINEAUa, Ofer HADARc, Chokri BEN AMARb Universit´e de Bordeaux, Laboratoire Bordelais de Recherche en Informatique, Bˆatiment Sfax university, Research Groups in Intelligent Machines, National Engineering School of A30, F-33405 Talence cedex, France Communication Systems Engineering department, Ben Gurion University of the Nagev Sfax (ENIS), Tunisia" 9ca7899338129f4ba6744f801e722d53a44e4622,Deep neural networks regularization for structured output prediction,"Deep Neural Networks Regularization for Structured Output Prediction Soufiane Belharbi∗ INSA Rouen, LITIS 76000 Rouen, France Clément Chatelain INSA Rouen, LITIS 76000 Rouen, France Romain Hérault INSA Rouen, LITIS 76000 Rouen, France Sébastien Adam INSA Rouen, LITIS 76000 Rouen, France Normandie Univ, UNIROUEN, UNIHAVRE, Normandie Univ, UNIROUEN, UNIHAVRE, Normandie Univ, UNIROUEN, UNIHAVRE, Normandie Univ, UNIROUEN, UNIHAVRE," 9cabbb686883635d8755706ee4f1349d812d7ccb,Detection and Tracking of General Movable Objects in Large 3D Maps,"Detection and Tracking of General Movable Objects in Large 3D Maps Nils Bore, Johan Ekekrantz, Patric Jensfelt and John Folkesson Robotics, Perception and Learning Lab Royal Institute of Technology (KTH) Stockholm, SE-100 44, Sweden Email: {nbore, ekz, patric," 9cfb3a68fb10a59ec2a6de1b24799bf9154a8fd1,Semi-supervised learning in Spectral Dimensionality Reduction,"Semi-supervised learning in Spectral Dimensionality Reduction Maryam Mehdizadeh This thesis is presented for the degree of Masters by Research of The University of Western Australia Department of Computer Science & Software Engineering. June 20, 2016" 9cf69de9e06e39f7f7ce643b3327bf69be8b9678,SHREC ’ 18 track : Recognition of geometric patterns over 3 D models,"SHREC’18 track: Recognition of geometric patterns over 3D models S Biasotti, E. Moscoso Thompson, L Bathe, S Berretti, A. Giachetti, T Lejemble, N Mellado, K Moustakas, Iason Manolas, Dimitrios Dimou, et al. To cite this version: S Biasotti, E. Moscoso Thompson, L Bathe, S Berretti, A. Giachetti, et al.. SHREC’18 track: Recog- nition of geometric patterns over 3D models. Eurographics Workshop on 3D Object Retrieval, 2018. https://hal-mines-paristech.archives-ouvertes.fr/hal-01774423 HAL Id: hal-01774423 Submitted on 30 Apr 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 9cd7487e0eed11dabc94dd867178204c53eb2270,Self-Organizing Traffic Lights : A Pedestrian Oriented Approach,"Self-Organizing Traffic Lights: A Pedestrian Oriented Approach Jessica S. Souza1, Cesar A. M. Ferreira2, Cassio E. dos Santos Jr3, Victor H. C. Melo4, William Robson Schwartz4 Computer Science Department, Federal University of Minas Gerais, Belo Horizonte, Brazil the vehicular and pedestrian traffic. One of" 9c341221e19fac7a5e38b9fe5c62361f780a7f08,Productivity Effects of Information Diffusion in Networks Paper 234,"A research and education initiative at the MIT Sloan School of Management Productivity Effects of Information Diffusion in Networks Paper 234 July 2007 Sinan Aral Erik Brynjolfsson Marshall Van Alstyne For more information, please visit our website at http://digital.mit.edu or contact the Center directly at or 617-253-7054" 9c49e4ba8ad0ba4634fe9306fb612695ed2b8cae,Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition,"Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition Vladimir Iglovikov True Accord Sergey Mushinskiy Open Data Science Vladimir Osin AeroState" 9c065dfb26ce280610a492c887b7f6beccf27319,Learning from Video and Text via Large-Scale Discriminative Clustering,"Learning from Video and Text via Large-Scale Discriminative Clustering Antoine Miech1,2 Jean-Baptiste Alayrac1,2 Piotr Bojanowski2 Ivan Laptev 1,2 Josef Sivic1,2,3 ´Ecole Normale Sup´erieure Inria CIIRC" 9c59304a619b7d503be95bd560f90be976a5309a,DenseASPP for Semantic Segmentation in Street Scenes,"DenseASPP for Semantic Segmentation in Street Scenes Maoke Yang Kun Yu Chi Zhang DeepMotion Zhiwei Li Kuiyuan Yang {maokeyang, kunyu, chizhang, zhiweili," 9294bba3ea887a16ce6332cedf40eb389b8aeb73,DISOCCLUSION OF 3 D LIDAR POINT CLOUDS USING RANGE IMAGES,"DISOCCLUSION OF 3D LIDAR POINT CLOUDS USING RANGE IMAGES P. Biasuttia, b, J-F. Aujola, M. Br´edifc, A. Bugeaub Universit´e de Bordeaux, IMB, CNRS UMR 5251, INP, 33400 Talence, France. Universit´e de Bordeaux, LaBRI, CNRS UMR 5800, 33400 Talence, France. Universit´e Paris-Est, LASTIG MATIS, IGN, ENSG, F-94160 Saint-Mand´e, France. {pierre.biasutti, KEY WORDS: LiDAR, MMS, Range Image, Disocclusion, Inpainting, Variational, Segmentation, Point Cloud" 92c2dd6b3ac9227fce0a960093ca30678bceb364,On Color Texture Normalization for Active Appearance Models,"Provided by the author(s) and NUI Galway in accordance with publisher policies. Please cite the published version when available. Title On color texture normalization for active appearance models Author(s) Ionita, Mircea C.; Corcoran, Peter M.; Buzuloiu, Vasile Publication 009-05-12 Publication Information Ionita, M. C., Corcoran, P., & Buzuloiu, V. (2009). On Color Texture Normalization for Active Appearance Models. Image Processing, IEEE Transactions on, 18(6), 1372-1378. Publisher Link to publisher's version http://dx.doi.org/10.1109/TIP.2009.2017163 Item record http://hdl.handle.net/10379/1350" 921aaac9b33ec6a417bfc8bb0e21e11e743342c2,Image enhancement for improving face detection under non-uniform lighting conditions,"978-1-4244-1764-3/08/$25.00 ©2008 IEEE ICIP 2008" 923412acb90ed2acbb29290147a567f39d2dfc95,FACS-BASED EMOTIONAL FACIAL EXPRESSIONS FACSGen : A Tool to Synthesize Emotional Facial Expressions through Systematic Manipulation of Facial Action Units,"J Nonverbal Behav DOI 10.1007/s10919-010-0095-9 O R I G I N A L P A P E R FACSGen: A Tool to Synthesize Emotional Facial Expressions Through Systematic Manipulation of Facial Action Units Etienne B. Roesch • Lucas Tamarit • Lionel Reveret • Didier Grandjean • David Sander • Klaus R. Scherer Ó Springer Science+Business Media, LLC 2010" 92f57973d84404505fdaac530d0009b7bafdae68,Two-Dimensional-Oriented Linear Discriminant Analysis for Face Recognition,"Two-Dimensional-Oriented Linear Discriminant Analysis for Face Recognition Muriel Visani, Christophe Garcia, Jean-Michel Jolion To cite this version: Muriel Visani, Christophe Garcia, Jean-Michel Jolion. Two-Dimensional-Oriented Linear Discriminant Analysis for Face Recognition. Springer. International Conference on Computer Vision and Graphics (ICCVG 04), Sep 2004, Warsaw, Poland. pp.1008-1017, 2004, Computational Imaging and Vision. HAL Id: hal-00452438 https://hal.archives-ouvertes.fr/hal-00452438 Submitted on 9 Sep 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 927ad0dceacce2bb482b96f42f2fe2ad1873f37a,Interest-Point based Face Recognition System,"Interest-Point based Face Recognition System Interest-Point based Face Recognition System Cesar Fernandez and Maria Asuncion Vicente Miguel Hernandez University Spain . Introduction Among all applications of face recognition systems, surveillance is one of the most hallenging ones. In such an application, the goal is to detect known criminals in crowded environments, like airports or train stations. Some attempts have been made, like those of Tokio (Engadget, 2006) or Mainz (Deutsche Welle, 2006), with limited success. The first task to be carried out in an automatic surveillance system involves the detection of ll the faces in the images taken by the video cameras. Current face detection algorithms are highly reliable and thus, they will not be the focus of our work. Some of the best performing examples are the Viola-Jones algorithm (Viola & Jones, 2004) or the Schneiderman-Kanade lgorithm (Schneiderman & Kanade, 2000). The second task to be carried out involves the comparison of all detected faces among the database of known criminals. The ideal behaviour of an automatic system performing this task would be to get a 100% correct identification rate, but this behaviour is far from the apabilities of current face recognition algorithms. Assuming that there will be false identifications, supervised surveillance systems seem to be the most realistic option: the" 92b748f2629b3227a9c56bc9e580f45eb5bdfba5,Novel Adaptive Eye Detection and Tracking for Challenging Lighting Conditions,"Version This is the Accepted Manuscript version. This version is defined in the NISO recommended practice RP-8-2008 http://www.niso.org/publications/rp/ Suggested Reference Rezaei, M., & Klette, R. (2013). Novel Adaptive Eye Detection and Tracking for Challenging Lighting Conditions. In Lecture Notes in Computer Science Vol. 7729 (pp. 427-440). Daejeon, Korea: Springer Berlin Heidelberg. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3- 642-37484-5_35 Copyright Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. http://www.sherpa.ac.uk/romeo/issn/0302-9743/ https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm" 92a044df6c37571aac25756252dda27676492bb5,IMPLEMENTATION OF REAL-TIME SYSTEM ON FPGA BOARD FOR HUMAN ' S FACE DETECTION AND TRACKING AUTHOR,"IMPLEMENTATION OF REAL-TIME SYSTEM ON FPGA BOARD FOR HUMAN'S FACE DETECTION AND TRACKING AUTHOR MOHD NORHAFIZ HASHIM A project report submitted in partial Fulfillment of the requirement for the award of the Degree of Master Electrical Engineering Fakulti Kejuruteraan Elektrik dan Elektronik Universiti Tun Hussein Onn Malaysia JANUARY 2014" 92d614b732b89cbdfc0e726f9ac057de5a17d997,A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision,"A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision Chi-Hao Wu, Qin Huang, Siyang Li, and C.-C. Jay Kuo, Fellow, IEEE" 9282239846d79a29392aa71fc24880651826af72,Classification of extreme facial events in sign language videos,"Antonakos et al. EURASIP Journal on Image and Video Processing 2014, 2014:14 http://jivp.eurasipjournals.com/content/2014/1/14 RESEARCH Open Access Classification of extreme facial events in sign language videos Epameinondas Antonakos1,2*, Vassilis Pitsikalis1 and Petros Maragos1" 921c33d3036818d4e2d5f879c667eaa669729adb,Object Recognition using Geometric Properties and a variant of Boosting 1 ),"Object Recognition using Geometric Properties and a variant of Boosting1) Martin Antenreiter and Peter Auer Chair of Information Technology (CiT), University of Leoben, Austria {martin.antenreiter, http://www.unileoben.ac.at/˜infotech/" 9207671d9e2b668c065e06d9f58f597601039e5e,Face Detection Using a 3D Model on Face Keypoints,"Face Detection Using a 3D Model on Face Keypoints Adrian Barbu, Gary Gramajo" 923e9b437a55853120f1778f55fcd956d81260f8,Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection,"Noname manuscript No. (will be inserted by the editor) Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection Hongyang Li · Yu Liu · Wanli Ouyang · Xiaogang Wang Received: date / Accepted: date" 927ba64123bd4a8a31163956b3d1765eb61e4426,Customer satisfaction measuring based on the most significant facial emotion,"Customer satisfaction measuring based on the most significant facial emotion Mariem Slim, Rostom Kachouri, Ahmed Atitallah To cite this version: Mariem Slim, Rostom Kachouri, Ahmed Atitallah. Customer satisfaction measuring based on the most significant facial emotion. 15th IEEE International Multi-Conference on Systems, Signals Devices (SSD 2018), Mar 2018, Hammamet, Tunisia. HAL Id: hal-01790317 https://hal-upec-upem.archives-ouvertes.fr/hal-01790317 Submitted on 11 May 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 927ac98da38db528b780f14996bb02b05009c9cc,Hand pose estimation through semi-supervised and weakly-supervised learning,"Hand Pose Estimation through Semi-Supervised and Weakly-Supervised Learning Natalia Neverovaa,∗, Christian Wolfa, Florian Neboutb, Graham W. Taylorc Universit´e de Lyon, INSA-Lyon, CNRS, LIRIS, F-69621, France Awabot SAS, France School of Engineering, University of Guelph, Canada" 92a5af98c47bce7208d043c7c418633cd537701c,Improving Image Captioning by Leveraging Knowledge Graphs,"Improving Image Captioning by Leveraging Knowledge Graphs Yimin Zhou, Yiwei Sun, Vasant Honavar Artificial Intelligent Research Laboratory The Pennsylvania State University" 92f0e02c9f4e95098452d0fd78ba46cd6e7b1f6d,Dynamic machine learning for supervised and unsupervised classification. (Apprentissage automatique dynamique pour la classification supervisée et non supervisée),"Dynamic machine learning for supervised and unsupervised classification Adela-Maria Sîrbu To cite this version: Adela-Maria Sîrbu. Dynamic machine learning for supervised and unsupervised classification. Machine Learning [cs.LG]. INSA de Rouen, 2016. English. . HAL Id: tel-01402052 https://tel.archives-ouvertes.fr/tel-01402052 Submitted on 24 Nov 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 929bd1d11d4f9cbc638779fbaf958f0efb82e603,"Improving the Performance of Facial Expression Recognition Using Dynamic, Subtle and Regional Features","This is the author’s version of a work that was submitted/accepted for pub- lication in the following source: Zhang, Ligang & Tjondronegoro, Dian W. (2010) Improving the perfor- mance of facial expression recognition using dynamic, subtle and regional features. In Kok, WaiWong, B. Sumudu, U. Mendis, & Abdesselam , Bouzerdoum (Eds.) Neural Information Processing. Models and Applica- tions, Lecture Notes in Computer Science, Sydney, N.S.W, pp. 582-589. This file was downloaded from: http://eprints.qut.edu.au/43788/ (cid:13) Copyright 2010 Springer-Verlag Conference proceedings published, by Springer Verlag, will be available via Lecture Notes in Computer Science http://www.springer.de/comp/lncs/ Notice: Changes introduced as a result of publishing processes such as opy-editing and formatting may not be reflected in this document. For a definitive version of this work, please refer to the published source: http://dx.doi.org/10.1007/978-3-642-17534-3_72" 920a92900fbff22fdaaef4b128ca3ca8e8d54c3e,LEARNING PATTERN TRANSFORMATION MANIFOLDS WITH PARAMETRIC ATOM SELECTION,"LEARNING PATTERN TRANSFORMATION MANIFOLDS WITH PARAMETRIC ATOM SELECTION Elif Vural and Pascal Frossard Ecole Polytechnique F´ed´erale de Lausanne (EPFL) Signal Processing Laboratory (LTS4) Switzerland-1015 Lausanne" 923ede53b0842619831e94c7150e0fc4104e62f7,Masked correlation filters for partially occluded face recognition,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 92679c8cff92442f39de3405c21c8028162fe56a,Temporal 3 D ConvNets using Temporal Transition Layer,"Temporal 3D ConvNets using Temporal Transition Layer Ali Diba1 , Mohsen Fayyaz2, Vivek Sharma3, A.Hossein Karami4, M.Mahdi Arzani4, Rahman Yousefzadeh4, Luc Van Gool1 ESAT-PSI, KU Leuven, 2University of Bonn, 3CV:HCI, KIT, Karlsruhe, 4Sensifai" 92b61b09d2eed4937058d0f9494d9efeddc39002,BoxCars: Improving Vehicle Fine-Grained Recognition using 3D Bounding Boxes in Traffic Surveillance,"Under review in IJCV manuscript No. (will be inserted by the editor) BoxCars: Improving Vehicle Fine-Grained Recognition using D Bounding Boxes in Traf‌f‌ic Surveillance Jakub Sochor · Jakub ˇSpaˇnhel · Adam Herout Received: date / Accepted: date" 926ca7ce14332f9f848c28565d0f2f9a2d1e35a8,Impaired facial and vocal emotion decoding in schizophrenia is underpinned by basic perceptivo-motor deficits,"Cognitive Neuropsychiatry ISSN: 1354-6805 (Print) 1464-0619 (Online) Journal homepage: http://www.tandfonline.com/loi/pcnp20 Impaired facial and vocal emotion decoding in schizophrenia is underpinned by basic perceptivo- motor deficits C. Mangelinckx, J. B. Belge, P. Maurage & E. Constant To cite this article: C. Mangelinckx, J. B. Belge, P. Maurage & E. Constant (2017): Impaired facial nd vocal emotion decoding in schizophrenia is underpinned by basic perceptivo-motor deficits, Cognitive Neuropsychiatry, DOI: 10.1080/13546805.2017.1382342 To link to this article: http://dx.doi.org/10.1080/13546805.2017.1382342 Published online: 03 Oct 2017. Submit your article to this journal View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pcnp20 Download by: [University of Virginia, Charlottesville] Date: 06 October 2017, At: 09:26" 9263ca6211ec39469f0daa8790ccaecbd5898423,Exploring Models and Data for Remote Sensing Image Caption Generation,"Exploring Models and Data for Remote Sensing Image Caption Generation Xiaoqiang Lu, Senior Member, IEEE, Binqiang Wang, Xiangtao Zheng, and Xuelong Li, Fellow, IEEE" 92bbb5364f65b1b0fccc27032b688e1ff0dafa00,RED-Net: A Recurrent Encoder–Decoder Network for Video-Based Face Alignment,"IJCV special issue (Best papers of ECCV 2016) manuscript No. (will be inserted by the editor) RED-Net: A Recurrent Encoder-Decoder Network for Video-based Face Alignment Xi Peng · Rogerio S. Feris · Xiaoyu Wang · Dimitris N. Metaxas Submitted: April 19 2017 / Revised: December 12 2017" 92373095869f1b9e93823f0bd16bb8527c1665dc,How face blurring affects body language processing of static gestures in women and men,"Social Cognitive and Affective Neuroscience, 2018, 590–603 doi: 10.1093/scan/nsy033 Advance Access Publication Date: 14 May 2018 Original article How face blurring affects body language processing of static gestures in women and men Alice Mado Proverbio, Laura Ornaghi, and Veronica Gabaro Department of Psychology, Neuro-MI Center for Neuroscience, University of Milano-Bicocca, Milano, Italy Correspondence should be addressed to Alice Mado Proverbio, Department of Psychology, University of Milano-Bicocca, piazza dell’Ateneo Nuovo 1, U6 Building, Milano, Italy. E-mail:" a3f1db123ce1818971a57330d82901683d7c2b67,Poselets and their applications in high-level computer vision,"Poselets and Their Applications in High-Level Computer Vision Lubomir Bourdev Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2012-52 http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-52.html May 1, 2012" a32fc1edb2d23d117f47d86f79ac88c9dc3a45b1,Evaluation of LDA based face verification with respect to available computational resources,"Evaluation of LDA-based Face Veriflcation with respect to Available Computational Resources Jacek Czyz and Luc Vandendorpe Telecommunication Laboratory Universit¶e catholique de Louvain Place du Levant, 1348 Louvain-la-Neuve, Belgium" a3fdba7975494c34552b33cf839f21d62734e6f0,Excavate Condition-invariant Space by Intrinsic Encoder,"Excavate Condition-invariant Space by Intrinsic Encoder Jian Xu, Chunheng Wang, Cunzhao Shi, and Baihua Xiao Institute of Automation, Chinese Academy of Sciences (CASIA)" a35d85c2efd1fb090267980ebb3fd7b6381e3b74,Very Low Resolution Image Classification,"Very Low Resolution Image Classification Adam Vest1 Muhammadabdullah Jamal2 Boqing Gong2 University of Louisville 2 University of Central Florida" a3ccf7fa5c130c8bcd20cbcd356ad7a47cdd4296,SymNMF: nonnegative low-rank approximation of a similarity matrix for graph clustering,"Journal of Global Optimization manuscript No. (will be inserted by the editor) SymNMF: Nonnegative Low-Rank Approximation of Similarity Matrix for Graph Clustering Da Kuang · Sangwoon Yun · Haesun Park The final publication is available at Springer via http://dx.doi.org/10.1007/s10898-014-0247-2." a3f78cc944ac189632f25925ba807a0e0678c4d5,Action Recognition in Realistic Sports Videos,"Action Recognition in Realistic Sports Videos Khurram Soomro and Amir Roshan Zamir" a3a34c1b876002e0393038fcf2bcb00821737105,Face Identification across Different Poses and Illuminations with a 3D Morphable Model,"Face Identification across Different Poses and Illuminations with a 3D Morphable Model V. Blanz, S. Romdhani, and T. Vetter University of Freiburg Georges-K¨ohler-Allee 52, 79110 Freiburg, Germany fvolker, romdhani," a3a97bb5131e7e67316b649bbc2432aaa1a6556e,Role of the hippocampus and orbitofrontal cortex during the disambiguation of social cues in working memory.,"Cogn Affect Behav Neurosci DOI 10.3758/s13415-013-0170-x Role of the hippocampus and orbitofrontal cortex during the disambiguation of social cues in working memory Robert S. Ross & Matthew L. LoPresti & Karin Schon & Chantal E. Stern # Psychonomic Society, Inc. 2013" a38b4eaa536dd2b709eb725bf2a2192b162cbf06,Multi-modal Deep Learning Approach for Flood Detection,"Multi-modal Deep Learning Approach for Flood Detection Laura Lopez-Fuentes1,2,3, Joost van de Weijer2, Marc Bolaños 4, Harald Skinnemoen3 University of the Balearic Islands, Palma, Spain Autonomous University of Barcelona, Barcelona, Spain AnsuR Technologies, Oslo, Norway, 4Universitat de Barcelona, Barcelona, Spain" a3fe284b029269ad5f071dd37bb137593c67dfc2,Feature Learning for the Image Retrieval Task,"Feature Learning for the Image Retrieval Task Aakanksha Rana, Joaquin Zepeda, Patrick Perez Technicolor R&I, 975 avenue des Champs Blancs, CS 17616, 35576 Cesson Sevigne, France" a378fa57d6638fe89772a4a4ac12d07087e81a6d,Automatic Person Verification Using Speech and Face Information,"Automatic Person Verification Using Speech and Face Information A Dissertation Presented to The School of Microelectronic Engineering Faculty of Engineering and Information Technology Grif‌f‌ith University Submitted in Fulfillment of the Requirements of the Degree of Doctor of Philosophy Conrad Sanderson, BEng (Hons) August 2002 [revised February 2003]" a32ebfa79097fdf5c9d44d2f74e33b7c8343425c,A Deeper Look at Dataset Bias,"Chapter 2 A Deeper Look at Dataset Bias Tatiana Tommasi, Novi Patricia, Barbara Caputo and Tinne Tuytelaars" a3ad32249fcc85ef9dfb2ea575b0c636edcb2da9,Local Appearance-based 3D Face Recognition,"Universit¨at Karlsruhe Fakult¨at f¨ur Informatik Institut f¨ur Theoretische Informatik (ITI) Prof. Dr. A. Waibel WS 2006/07 Studienarbeit Local Appearance-based 3D Face Recognition Hua Gao November 2006 Betreuer: M.Sc. H. K. Ekenel Dr.-Ing. R. Stiefelhagen Prof. Dr. A. Waibel" a357bc79b1ac6f2474ff6b9f001419745a8bc21c,Toward More Realistic Face Recognition Evaluation Protocols for the YouTube Faces Database,"Toward More Realistic Face Recognition Evaluation Protocols for the YouTube Faces Database Yoanna Mart´ınez-D´ıaz, Heydi M´endez-V´azquez, Leyanis L´opez-Avila Advanced Technologies Application Center (CENATAV) 7A ♯21406 Siboney, Playa, P.C. 12200, Havana, Cuba Leonardo Chang L. Enrique Sucar Massimo Tistarelli Tecnol´ogico de Monterrey, Estado de Mexico, Mexico INAOE, University of Sassari, Puebla, Mexico Sassari, Italy" a3a6e3cadfed3c0a520e4417fc27da561324fbc6,Facing the challenge of teaching emotions to individuals with low- and high-functioning autism using a new Serious game: a pilot study,"Serret et al. Molecular Autism 2014, 5:37 http://www.molecularautism.com/content/5/1/37 R ES EAR CH Facing the challenge of teaching emotions to individuals with low- and high-functioning autism using a new Serious game: a pilot study Sylvie Serret1*, Stephanie Hun1, Galina Iakimova2, Jose Lozada3, Margarita Anastassova3, Andreia Santos1, Stephanie Vesperini1 and Florence Askenazy4 Open Access" a3431ac9b157f7f510b855988107b065ce1deef8,Launch These Manhunts! Shaping the Synergy Maps for Multi-camera Detection,"Launch These Manhunts! Shaping the Synergy Maps for Multi-camera Detection Muhammad Owais Mehmood1, Sebastien Ambellouis1 and Catherine Achard2 LEOST, French Institute of Science and Technology for Transport, Spatial Planning, Development and Networks, Sorbonne Universites, UPMC Univ. Paris 06 and CNRS UMR 7222, ISIR, F-75005, Paris, France Villeneuve D’Ascq, France Keywords: People Localization, Ghost Pruning, Multi-camera Surveillance, Shape Representations, Pattern Recognition." a3d8887625040d3c07f779ac5353452fd48058e4,A Study of Activity Recognition and Questionable Observer Detection,"International Journal of Computer Applications (0975 – 8887) Volume 182 – No. 15, September 2018 A Study of Activity Recognition and Questionable Observer Detection D. M. Anisuzzaman Department of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka, Bangladesh" a3eab933e1b3db1a7377a119573ff38e780ea6a3,Sparse Representation for accurate classification of corrupted and occluded facial expressions,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010" a32c5138c6a0b3d3aff69bcab1015d8b043c91fb,Video redaction: a survey and comparison of enabling technologies,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 9/19/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use Videoredaction:asurveyandcomparisonofenablingtechnologiesShaganSahAmeyaShringiRaymondPtuchaAaronBurryRobertLoceShaganSah,AmeyaShringi,RaymondPtucha,AaronBurry,RobertLoce,“Videoredaction:asurveyandcomparisonofenablingtechnologies,”J.Electron.Imaging26(5),051406(2017),doi:10.1117/1.JEI.26.5.051406." a3fcf3d32a5a4fcc83027e3d367ecc0df3ec4f64,Iris Recognition: On the Segmentation of Degraded Images Acquired in the Visible Wavelength,"Iris Recognition: On the Segmentation of Degraded Images Acquired in the Visible Wavelength Hugo Proenc¸ a" a348c7d55b97a3dc77eb8890b63f2c228bf94504,A Symmetry Based Face Detection Technique,"A Symmetry Based Face Detection Technique Sriparna Saha, Student Member, IEEE and Sanghamitra Bandyopadhyay, Senior Member, IEEE Machine Intelligence Unit, Indian Statistical Institute, Kolkata, India-700108 Email: fsriparna r," a3bf7248e38ed6f9456f0f309b36470c5c0dabd0,Predicting the Driver's Focus of Attention: the DR(eye)VE Project,"Predicting the Driver’s Focus of Attention: the DR(eye)VE Project Andrea Palazzi∗, Davide Abati∗, Simone Calderara, Francesco Solera, and Rita Cucchiara" a30e987e9909a4e307c35809275cf80431211f22,Automatic Sapstain Detection in Processed Timber Through Image Feature Analysis,"Automatic Sapstain Detection in Processed Timber Through Image Feature Analysis Jeremiah Deng The Information Science Discussion Paper Series Number 2009/04 April 2009 ISSN 1177-455X" a34d75da87525d1192bda240b7675349ee85c123,Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?,"Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not? Erjin Zhou Face++, Megvii Inc. Zhimin Cao Face++, Megvii Inc. Qi Yin Face++, Megvii Inc." a32dadf343f811e6837b8ac5bab873674fa626b3,Moving Object Detection and Tracking in Forward Looking Infra-Red Aerial Imagery,"Moving Object Detection and Tracking in Forward Looking Infra-Red Aerial Imagery Subhabrata Bhattacharya, Haroon Idrees, Imran Saleemi, Saad Ali nd Mubarak Shah" a3b87364aa68b371ca9831d333b934402fbc3713,Which neural mechanisms mediate the effects of a parenting intervention program on parenting behavior: design of a randomized controlled trial,"Kolijn et al. BMC Psychology (2017) 5:9 DOI 10.1186/s40359-017-0177-0 Open Access ST UD Y P R O T O C O L Which neural mechanisms mediate the effects of a parenting intervention program on parenting behavior: design of a randomized controlled trial Laura Kolijn1,2,3, Saskia Euser1,2,3, Bianca G. van den Bulk1,2,3, Renske Huffmeijer1,2,3, Marinus H. van IJzendoorn1,2,3 and Marian J. Bakermans-Kranenburg1,2,3*" a3ed080262f130051d2a02e846f5d227a440b294,ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time,"ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time Rudra P K Poudel, Ujwal Bonde, Stephan Liwicki, and Christopher Zach Toshiba Research, Cambridge, UK" a30869c5d4052ed1da8675128651e17f97b87918,Fine-Grained Comparisons with Attributes,"Fine-Grained Comparisons with Attributes Aron Yu and Kristen Grauman" a3017bb14a507abcf8446b56243cfddd6cdb542b,Face Localization and Recognition in Varied Expressions and Illumination,"Face Localization and Recognition in Varied Expressions and Illumination Hui-Yu Huang, Shih-Hang Hsu" a3ebacd8bcbc7ddbd5753935496e22a0f74dcf7b,"First International Workshop on Adaptive Shot Learning for Gesture Understanding and Production ASL4GUP 2017 Held in conjunction with IEEE FG 2017, in May 30, 2017, Washington DC, USA","First International Workshop on Adaptive Shot Learning for Gesture Understanding and Production ASL4GUP 2017 Held in conjunction with IEEE FG 2017, in May 30, 2017, Washington DC, USA" a3a6a6a2eb1d32b4dead9e702824375ee76e3ce7,Multiple Local Curvature Gabor Binary Patterns for Facial Action Recognition,"Multiple Local Curvature Gabor Binary Patterns for Facial Action Recognition Anıl Y¨uce, Nuri Murat Arar and Jean-Philippe Thiran Signal Processing Laboratory (LTS5), ´Ecole Polytechnique F´ed´erale de Lausanne, Switzerland" a3c8c7da177cd08978b2ad613c1d5cb89e0de741,A Spatio-temporal Approach for Multiple Object Detection in Videos Using Graphs and Probability Maps,"A Spatio-temporal Approach for Multiple Object Detection in Videos Using Graphs nd Probability Maps Henrique Morimitsu1(B), Roberto M. Cesar Jr.1, and Isabelle Bloch2 University of S˜ao Paulo, S˜ao Paulo, Brazil Institut Mines T´el´ecom, T´el´ecom ParisTech, CNRS LTCI, Paris, France" a3fd234763844663f72a8fa22a076eeadce7245c,DelugeNets: Deep Networks with Efficient and Flexible Cross-Layer Information Inflows,"DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows Jason Kuen1 Xiangfei Kong1 Gang Wang2 Yap-Peng Tan1 Nanyang Technological University1 Alibaba Group2" a3d071d2a5c11329aa324b2cae6b7b6ca7800213,C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset,"C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset Aishwarya Agrawal∗, Aniruddha Kembhavi†, Dhruv Batra‡, Devi Parikh‡ Virginia Tech, †Allen Institute for Artificial Intelligence, ‡Georgia Institute of Technology {dbatra," a32f693e98ae35da5508c8eee245a876b6e130a1,Small Sample Scene Categorization from Perceptual Relations Ilan Kadar and,"Small Sample Scene Categorization from Perceptual Relations Ilan Kadar and Ohad Ben-Shahar Dept. of Computer Science, Ben-Gurion University Beer-Sheva, Israel" a38045ed82d6800cbc7a4feb498e694740568258,African American and Caucasian males ' evaluation of racialized female facial averages,"UNLV Theses, Dissertations, Professional Papers, and Capstones 5-2010 African American and Caucasian males' evaluation of racialized female facial averages Rhea M. Watson University of Nevada Las Vegas Follow this and additional works at: http://digitalscholarship.unlv.edu/thesesdissertations Part of the Cognition and Perception Commons, Race and Ethnicity Commons, and the Social Psychology Commons Repository Citation Watson, Rhea M., ""African American and Caucasian males' evaluation of racialized female facial averages"" (2010). UNLV Theses, Dissertations, Professional Papers, and Capstones. 366. http://digitalscholarship.unlv.edu/thesesdissertations/366 This Thesis is brought to you for free and open access by Digital It has been accepted for inclusion in UNLV Theses, Dissertations, Professional Papers, and Capstones by an authorized administrator of Digital For more information, please contact" a3f69a073dcfb6da8038607a9f14eb28b5dab2db,3D-Aided Deep Pose-Invariant Face Recognition,Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) a3d836f601c9c462cddaf1c7175246617dd8f3af,MyIdea - Sensors Specifications and Acquisition Protocol,"MyIdea - Sensors Specifications and Acquisition Protocol DIUF-RR 05-12 By alphabetical order : Bruno Dumas1 Jean Hennebert2 Andreas Humm3 Rolf Ingold4 Dijana Petrovska5 Catherine Pugin6 Didier Von Rotz7 Initial: January 2005 - Revision 1.2.5 as of June 2005 Computer Science Department Research Report D´epartement d’Informatique - Departement f¨ur Informatik • Universit´e de Fribourg - Universit¨at Freiburg • Chemin du mus´ee 3 • 1700 Fribourg • Switzerland phone +41 (26) 300 84 65 fax +41 (26) 300 97 31 http://diuf.unifr.ch DIUF, University of Fribourg, Ch. du Mus´ee 3, 1700 Fribourg, Switzerland, DIUF, University of Fribourg, Ch. du Mus´ee 3, 1700 Fribourg, Switzerland," 793e896c2f66fb66bfc6c834f2678cf349af4e20,Incorporating Computation Time Measures During Heterogeneous Features Selection in a Boosted Cascade People Detector,"Incorporating Computation Time Measures during Heterogeneous Features Selection in a Boosted Cascade People Detector Alhayat Ali Mekonnen, Frédéric Lerasle, Ariane Herbulot, Cyril Briand To cite this version: Alhayat Ali Mekonnen, Frédéric Lerasle, Ariane Herbulot, Cyril Briand. Incorporating Computation Time Measures during Heterogeneous Features Selection in a Boosted Cascade People Detector. Inter- national Journal of Pattern Recognition and Artificial Intelligence, World Scientific Publishing, 2016, 0 (8), pp.1655022. <10.1142/S0218001416550223>. HAL Id: hal-01300472 https://hal.archives-ouvertes.fr/hal-01300472 Submitted on 11 Apr 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents" 79b669abf65c2ca323098cf3f19fa7bdd837ff31,Efficient tensor based face recognition,"Deakin Research Online This is the published version: Rana, Santu, Liu, Wanquan, Lazarescu, Mihai and Venkatesh, Svetha 2008, Efficient tensor ased face recognition, in ICPR 2008 : Proceedings of the 19th International Conference on Pattern Recognition, IEEE, Washington, D. C., pp. 1-4. Available from Deakin Research Online: http://hdl.handle.net/10536/DRO/DU:30044585 Reproduced with the kind permissions of the copyright owner. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Copyright : 2008, IEEE" 79335495e54446541a3655d145911beba7c29d7d,The face inversion effect in opponent-stimulus rivalry,"ORIGINAL RESEARCH ARTICLE published: 15 May 2014 doi: 10.3389/fnhum.2014.00295 The face inversion effect in opponent-stimulus rivalry Malte Persike*, Bozana Meinhardt-Injac and Günter Meinhardt Research Methods and Statistics, Department of Psychology, Institute of Psychology, Johannes Gutenberg University Mainz, Mainz, Germany Edited by: Davide Rivolta, University of East London, UK Reviewed by: Guillaume A. Rousselet, University of Glasgow, UK Timo Stein, Charité Universitätsmedizin Berlin, Germany *Correspondence: Malte Persike, Research Methods nd Statistics, Department of Psychology, Institute of Psychology, Johannes Gutenberg University Mainz, Mainz, Rheinland-Pfalz," 79e7f1e13e8aafee6558729804cf1284134815b3,Deep Representation Learning for Domain Adaptation of Semantic Image Segmentation,"BENBIHI, GEIST, PRADALIER: DEEP REPRESENTATION LEARNING Deep Representation Learning for Domain Adaptation of Semantic Image Segmentation Assia Benbihi1 Matthieu Geist2 Cedric Pradalier1 UMI 2958 GT-CNRS – GeorgiaTech Lorraine Metz, France Université de Lorraine CNRS LIEC UNR 7360, Metz, France" 790aa543151312aef3f7102d64ea699a1d15cb29,Confidence-Weighted Local Expression Predictions for Occlusion Handling in Expression Recognition and Action Unit Detection,"Confidence-Weighted Local Expression Predictions for Occlusion Handling in Expression Recognition and Action Unit detection Arnaud Dapogny1 Kevin Bailly1 Séverine Dubuisson1 Sorbonne Universités, UPMC Univ Paris 06, CNRS, ISIR UMR 7222 place Jussieu 75005 Paris" 7918698ffa86cdd6123bc2f1f613be1ab38c0d2f,Learning to Recognize Faces in Realistic Conditions,"Learning to Recognize Faces in Realistic Conditions Anonymous Author(s) Affiliation Address email" 794cf037dac115755cd15295d8c5fc1c00242548,The City Infant Faces Database: A validated set of infant facial expressions,"Behav Res (2018) 50:151–159 DOI 10.3758/s13428-017-0859-9 The City Infant Faces Database: A validated set of infant facial expressions Rebecca Webb 1 & Susan Ayers 1 & Ansgar Endress 2 Published online: 15 February 2017 # The Author(s) 2017. This article is published with open access at Springerlink.com" 79d13b74952449667c769be76dac9065db1acc22,STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"FINE-GRAINED RECOGNITION: DATA, RECOGNITION, AND APPLICATION A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Jonathan Krause October 2016" 791eb376d4db96376eba3ef804657c5f0ba7229a,SAFE: Secure authentication with Face and Eyes,"SAFE: Secure Authentication with Face and Eyes Arman Boehm(cid:91), Dongqu Chen§, Mario Frank(cid:91), Ling Huang†, Cynthia Kuo(cid:93), Tihomir Lolic(cid:91), Ivan Martinovic(cid:63), Dawn Song(cid:91) (cid:91) University of California, Berkeley; † Intel Labs; (cid:93) Nokia Research; (cid:63) Oxford University; § Yale University" 7960336aed2aa701c147ccfe36d153046f1500bc,Occlusion Reasoning for Multiple Object Visual Tracking Dissertation Occlusion Reasoning for Multiple Object Visual Tracking Occlusion Reasoning for Multiple Object Visual Tracking,"OCCLUSION REASONING FOR MULTIPLE OBJECT VISUAL TRACKING ZHENG WU Dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy BOSTON UNIVERSITY" 795cea6b95af22238600aa129b1975e83c531858,Sentence Directed Video Object Codetection.,"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Sentence Directed Video Object Codetection Haonan Yu, Student Member, IEEE and Jeffrey Mark Siskind, Senior Member, IEEE" 79fc892abaf44a84a758268efd4d1b9e6b64ecf5,Leveraging Random Label Memorization for Unsupervised Pre-Training,"Leveraging Random Label Memorization for Unsupervised Pre-Training Vinaychandran Pondenkandath * 1 Michele Alberti * 1 Sammer Puran 1 Rolf Ingold 1 Marcus Liwicki 1 2" 79d3e7321e50be745bef92ba1405b486bd1f133d,Emotion Recognition in Simulated Social Interactions,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TAFFC.2018.2799593, IEEE > TAFFC-2017-04-0117.R1 < Transactions on Affective Computing Emotion Recognition in Simulated Social Interactions C. Mumenthaler, D. Sander, and A. S. R. Manstead" 79dd787b2877cf9ce08762d702589543bda373be,Face detection using SURF cascade,"Face Detection Using SURF Cascade Jianguo Li, Tao Wang, Yimin Zhang Intel Labs China" 7954a1bd6e693da8f2ae69ad01233e937d600e9b,The Lov\'asz-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks,"Accepted as a conference paper at CVPR 2018 The Lov´asz-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks Maxim Berman Amal Rannen Triki Matthew B. Blaschko Dept. ESAT, Center for Processing Speech and Images KU Leuven, Belgium" 7902309d3c5ab2e1e3a1f08503dc39108e1639dc,Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark,"Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark Xiaodan Liang, Ke Gong, Xiaohui Shen, and Liang Lin" 796e333796024acf662fe76c4761607eaaa98a5d,Nested multi-instance image classification,"Nested multi-instance image classification Anonymous Authors" 79fc3c10ce0d0f48b25c8cf460048087c97e2e90,Variational Bi-domain Triplet Autoencoder,"Variational learning across domains with triplet information Rita Kuznetsova1,2, Oleg Bakhteev1,2 and Alexandr Ogaltsov2,3 Moscow Institute of Physics and Technology National Research University Higher School of Economics {rita.kuznetsova, Antiplagiat Company" 7985ac55e170273dd0ffa6bd756e588bab301d57,Mind's eye: A recurrent visual representation for image caption generation,"Mind’s Eye: A Recurrent Visual Representation for Image Caption Generation Xinlei Chen1, C. Lawrence Zitnick2 Carnegie Mellon University. 2Microsoft Research Redmond. A good image description is often said to “paint a picture in your mind’s eye.” The creation of a mental image may play a significant role in sentence omprehension in humans [3]. In fact, it is often this mental image that is remembered long after the exact sentence is forgotten [5, 7]. As an illus- trative example, Figure 1 shows how a mental image may vary and increase in richness as a description is read. Could computer vision algorithms that omprehend and generate image captions take advantage of similar evolving visual representations? Recently, several papers have explored learning joint feature spaces for images and their descriptions [2, 4, 9]. These approaches project image features and sentence features into a common space, which may be used for image search or for ranking image captions. Various approaches were used to learn the projection, including Kernel Canonical Correlation Anal- ysis (KCCA) [2], recursive neural networks [9], or deep neural networks [4]. While these approaches project both semantics and visual features to common embedding, they are not able to perform the inverse projection. That is, they cannot generate novel sentences or visual depictions from the" 79f6a8f777a11fd626185ab549079236629431ac,Pradeep RavikumarDiscriminative Object Categorization with External Semantic Knowledge,"Copyright Sung Ju Hwang" 794dbf68bae49bb571d1b2461289a6bb629de875,The Lovász Hinge: A Convex Surrogate for Submodular Losses,"The Lov´asz Hinge: A Convex Surrogate for Submodular Losses Jiaqian Yu∗1 and Matthew B. Blaschko†2 Center for Visual Computing, CentraleSup´elec, Inria, Universit´e Paris-Saclay, Grande Voie des Vignes, 92295 Chˆatenay-Malabry, France Center for Processing Speech and Images, Dept. Elektrotechniek, KU Leuven, Kasteelpark Arenberg 10, 3001 Leuven, Belgium" 7903bccf6f98436f4916419e5450d1bb890876ea,Analysis of Spatiotemporal Ensemble Data Using Machine Learning,"Institut für Visualisierung und Interaktive Systeme Universität Stuttgart Universitätsstraße 38 D - 70569 Stuttgart Masterarbeit Analysis of Spatiotemporal Ensemble Data Using Machine Learning Stefan Scheller Studiengang: Informatik Prüfer: Betreuer: Prof. Dr. Thomas Ertl Dr. Steffen Frey Gleb Tkachev, M. Sc. Dipl.-Phys. Oliver Fernandes Beginn am: Beendet am: . November 2017" 790bce6cbe30ef9bc4431c988d0d747da1c6bb1d,Salient Object Detection Using Window Mask Transferring with Multi-layer Background Contrast,"Salient Object Detection using Window Mask Transferring with Multi-layer Background Contrast Quan Zhou1, Shu Cai1, Shaojun Zhu2, and Baoyu Zheng1 College of Telecom & Inf Eng, Nanjing Univ of Posts & Telecom, P.R. China Dept. of Comput & Inf Sci, University of Pennsylvania Philadelphia, PA, USA" 79ab59b0fafda4c3f369dbb7fae61c620dabcd10,Identifying Human Face Profiles with Semi-Local Integral Invariants,"ROBUST GEOMETRICALLY INVARIANT FEATURES FOR 2D SHAPE MATCHING AND 3D FACE RECOGNITION Wei-Yang Lin A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy (Electrical Engineering) t the UNIVERSITY OF WISCONSIN–MADISON" 792e656d2297d3b00da73c7a606eb6f539311c25,Force from Motion: Decoding Control Force of Activity in a First Person Video.,"Force from Motion: Decoding Control Force of Activity in a First Person Video Hyun Soo Park and Jianbo Shi" 7910d3a86e03f4c41fbbe8029fab115547be151b,Taming Adversarial Domain Transfer with Structural Constraints for Image Enhancement,"Taming Adversarial Domain Transfer with Structural Constraints for Image Enhancement Elias Vansteenkiste and Patrick Kern Brighter.AI Torstrasse 177, Berlin {elias, Figure 1: Our domain transfer techniques applied to the night-to-day, removing rain and removing fog applications" 79e39f3d0577b9c5a47b93eb6d75bec04d14c07a,Person tracking and following with 2D laser scanners,"Person Tracking and Following with 2D Laser Scanners Angus Leigh1, Joelle Pineau1, Nicolas Olmedo2, and Hong Zhang2" 7950d67f7104e9bd82d957f0ed80f11982802397,Coupled Action Recognition and Pose Estimation from Multiple Views,"Noname manuscript No. (will be inserted by the editor) Coupled Action Recognition and Pose Estimation from Multiple Views Angela Yao (cid:1) Juergen Gall (cid:1) Luc Van Gool Received: date / Accepted: date" 79f12f28b060221f3b80ea1b7b16779ef9362ca8,Investigations of face expertise in the social developmental disorders.,"Jason J.S. Barton, MD, PhD, FRCPC Rebecca L. Hefter, BSc Mariya V. Cherkasova, BSc Dara S. Manoach, Address correspondence and reprint requests to Dr. Jason J.S. Barton, Neuro- ophthalmology Section D, VGH Eye Care Center, 2550 Willow Street, Vancouver, BC Canada V5Z 3N9 Investigations of face expertise in the social developmental disorders" 7917a7549f00306db8775d2d559460fc93dbde5a,DaP 2018 Proceedings of the Workshop on Dialogue and Perception,"DaP 2018 Proceedings of the Workshop on Dialogue and Perception Christine Howes, Simon Dobnik and Ellen Breitholtz (eds.) Gothenburg, 14–15 June 2018" 79b50cd468fcdba8f3c841c9d28d84ff66fd97fd,What do Deep Networks Like to See?,"What do Deep Networks Like to See? Sebastian Palacio∗ Federico Raue Damian Borth Andreas Dengel Joachim Folz∗ German Research Center for Artificial Intelligence (DFKI) J¨orn Hees TU Kaiserslautern" 79f02a006c77f2d7fece8302bf54d851269a515a,A Study of Deep CNN-Based Classification of Open and Closed Eyes Using a Visible Light Camera Sensor,"Article A Study of Deep CNN-Based Classification of Open nd Closed Eyes Using a Visible Light Camera Sensor Ki Wan Kim, Hyung Gil Hong, Gi Pyo Nam and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (K.W.K.); (H.G.H.); (G.P.N.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 2 June 2017; Accepted: 28 June 2017; Published: 30 June 2017" 79ade61f677dcadfc2b46444d2e0275d25ca1f06,Nonnegative Tucker decomposition with alpha-divergence,"NONNEGATIVE TUCKER DECOMPOSITION WITH ALPHA-DIVERGENCE Yong-Deok Kim §, Andrzej Cichocki †, Seungjin Choi § § Department of Computer Science, POSTECH, Korea Brain Science Institute, RIKEN, Japan" 79815f31f42708fd59da345f8fa79f635a070730,Autoregressive Quantile Networks for Generative Modeling,"Autoregressive Quantile Networks for Generative Modeling Georg Ostrovski * 1 Will Dabney * 1 R´emi Munos 1" 795bd86fc22ec544e7cd9b3d3c2ccabe72de54ec,Max Margin AND / OR Graph Learning for Efficient Articulated Object Parsing Long,"Noname manuscript No. (will be inserted by the editor) Max Margin AND/OR Graph Learning for Efficient Articulated Object Parsing Long (Leo) Zhu · Yuanhao Chen · Chenxi Lin · Alan Yuille the date of receipt and acceptance should be inserted later" 796d5d1f6052cd600e183471a2354751883d8d5d,Feature Extraction Techniques Implementation Review and Case Study,"ISSN: 2278 – 909X International Journal of Advanced Research in Electronics and Communication Engineering (IJARECE) Volume 4, Issue 12, December 2015 Feature Extraction Techniques Implementation Review and Case Study Uma Bhati Department of Computer Science & Engineering JSS Academy of Technical Education Noida-201301 Krishna Nand Chaturvedi Department of Computer Science & Engineering JSS Academy of Technical Education Noida-201301 utilizing recognition" 794fd0fb684f90704e108677edb40d3ff6a85f8c,"EyeLad: Remote Eye Tracking Image Labeling Tool - Supportive Eye, Eyelid and Pupil Labeling Tool for Remote Eye Tracking Videos","EyeLad:Remote Eye Tracking Image Labeling Tool Supportive eye, eyelid and pupil labeling tool for remote eye tracking videos. Wolfgang Fuhl1, Thiago Santini1, David Geisler1, Thomas K¨ubler1, and Enkelejda Kasneci1 {wolfgang.fuhl, thiago.santini, david.geisler, thomas.kuebler, Perception Engineering, University of Tbingen, Tbingen, Germany Keywords: data labeling, image processing, feature tracking, object detection, eye tracking data, remote eye tracking" 1debc9cd258a8c66045f01bbb50b6c9d15883256,Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization,"Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization Kuo-Hao Zeng∗† Shih-Han Chou∗ Fu-Hsiang Chan∗ Juan Carlos Niebles† Min Sun∗ Stanford University ∗National Tsing Hua University {khzeng, {happy810705," 1d3004953fd521adc8be457765ec978f0df1ac60,Exploiting Spatio-Temporal Scene Structure for Wide-Area Activity Analysis in Unconstrained Environments,"Exploiting Spatio-Temporal Scene Structure for Wide-Area Activity Analysis in Unconstrained Environments Nandita M. Nayak, Yingying Zhu, and Amit K. Roy-Chowdhury" 1df314a1e4dce42fd9fab094b79a0f2a10ad0b03,People Detection in Fish-eye Top-views, 1d9497450f60b874eb6ecbf82e3d0808a6fe236c,Nonconvex proximal splitting with computational errors ∗,"Nonconvex proximal splitting with computational errors∗ Suvrit Sra Max Planck Institute, T¨ubingen, Germany Introduction We study in this chapter large-scale nonconvex optimization problems with composite objective functions that are composed of a differentiable possibly nonconvex cost and a nonsmooth but convex regularizer. More precisely, we consider optimization problems of the form minimize Φ(x) := f (x) + r(x), where X ⊂ Rn is a compact convex set, f : Rn → R is a differentiable cost function and r : Rn → R is a losed convex function. Further, we assume that the gradient ∇ f is Lipschitz continuous on X (denoted f ∈ C1 L(X )), i.e., x ∈ X , ∃L > 0 s.t. (cid:107)∇ f (x) − ∇ f (y)(cid:107) ≤ L(cid:107)x − y(cid:107) for all x, y ∈ X . Throughout this chapter, (cid:107)·(cid:107) denotes the standard Euclidean norm. Problem (1) generalizes the more thoroughly studied class of composite convex optimization prob- lems [30], a class that has witnessed huge interest in machine learning, signal processing, statistics, nd other related areas. We refer the interested reader to [2, 3, 21, 37] for several convex examples" 1d58d83ee4f57351b6f3624ac7e727c944c0eb8d,Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions,"Enhanced Local Texture Feature Sets for Face Recognition under Difficult Lighting Conditions Xiaoyang Tan and Bill Triggs INRIA & Laboratoire Jean Kuntzmann, 655 avenue de l'Europe, Montbonnot 38330, France" 1dd3a58ab363cb396bf36223fadc8d2341bfdb83,Picture: A probabilistic programming language for scene perception,"Picture: a probabilistic programming language for scene perception Tejas D Kulkarni1, Pushmeet Kohli2, Joshua B Tenenbaum1, Vikash Mansinghka1 Brain and Cognitive Science, Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology. 2Microsoft Research Cambridge. Probabilistic scene understanding systems aim to produce high-probability descriptions of scenes conditioned on observed images or videos, typically ei- ther via discriminatively trained models or generative models in an “analysis y synthesis” framework. Discriminative approaches lend themselves to fast, ottom-up inference methods and relatively knowledge-free, data-intensive training regimes, and have been remarkably successful on many recognition problems. Generative approaches hold out the promise of analyzing complex scenes more richly and flexibly, but have been less widely embraced for two main reasons: Inference typically depends on slower forms of approximate inference, and both model-building and inference can involve considerable problem-specific engineering to obtain robust and reliable results. These factors make it difficult to develop simple variations on state-of-the-art mod- els, to thoroughly explore the many possible combinations of modeling, representation, and inference strategies, or to richly integrate complemen- tary discriminative and generative modeling approaches to the same problem. More generally, to handle increasingly realistic scenes, generative approaches will have to scale not just with respect to data size but also with respect to" 1d59ffad091a5bffa5fe935b79f5bfc08d2e802d,A ug 2 01 7 1 Intensity Video Guided 4 D Fusion for Improved Highly Dynamic 3 D Reconstruction,"Intensity Video Guided 4D Fusion for Improved Highly Dynamic 3D Reconstruction Jie Zhang, Christos Maniatis, Luis Horna and Robert B. Fisher" 1d585d2a5a57549e734f1b6f77ebcf4377730aab,DATABASES FOR SPEAKER RECOGNITION : ACTIVITIES IN COST 250 WORKING GROUP 2,"DATABASES FOR SPEAKER RECOGNITION: ACTIVITIES IN COST250 WORKING GROUP 2 Håkan Melin KTH, Centre for Speech Technology (CTT), Drottning Kristinas väg 31, SE-100 44 Stockholm, Sweden Email:" 1d5fe82303712a70c1d231ead2ee03f042d8ad70,ImageNet pre-trained models with batch normalization,"ImageNet pre-trained models with batch normalization Marcel Simon, Erik Rodner, Joachim Denzler Computer Vision Group Friedrich-Schiller-Universit¨at Jena, Germany {marcel.simon, erik.rodner," 1dd3faf5488751c9de10977528ab96be24616138,Detecting Anomalous Faces with 'No Peeking' Autoencoders,"Detecting Anomalous Faces with ‘No Peeking’ Autoencoders Anand Bhattad 1 Jason Rock 1 David Forsyth 1" 1d7df7000a3e8fafa21679db4efe2ffedcfe0335,And the Committee on Graduate Studies of Stanford University in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy,"SEMANTIC IMAGE UNDERSTANDING: FROM THE WEB, IN LARGE SCALE, WITH REAL-WORLD CHALLENGING DATA A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Jia Li November 2011" 1dce2617c751230b51d9264af99b8c651a2494c0,Multi-shot Pedestrian Re-identification via Sequential Decision Making,"Multi-shot Pedestrian Re-identification via Sequential Decision Making Jianfu Zhang1, Naiyan Wang2 and Liqing Zhang1 Shanghai Jiao Tong University∗, 2TuSimple" 1dc45403839d6aefe65c6e7f2179d5ea697dfeac,DCT-based features for categorisation of social media in compressed domain,"DCT-based Features for Categorisation of Social Media in Compressed Domain Sebastian Schmiedeke, Pascal Kelm, Thomas Sikora Communication Systems Group Technische Universit¨at Berlin Germany" 1d455f918062f66e86ed53cf258284abd6abd8fc,SMSnet: Semantic motion segmentation using deep convolutional neural networks,"SMSnet: Semantic Motion Segmentation using Deep Convolutional Neural Networks Johan Vertens∗ Abhinav Valada∗ Wolfram Burgard" 1dc07322715e093c560b30fdf1e168e58e9a9409,DRBF and IRBF Based Face Recognition and Extraction of Facial Expressions from the Blur Image,"Australian Journal of Basic and Applied Sciences, 8(3) March 2014, Pages: 61-68 AENSI Journals Australian Journal of Basic and Applied Sciences ISSN:1991-8178 Journal home page: www.ajbasweb.com DRBF and IRBF Based Face Recognition and Extraction of Facial Expressions from the Blur Image M. Jayashree, 2Dr. D. Deepa, 3M. Rubhashree PG Scholar, Department of Information Technology, Bannari Amman Institute of Technology, Sathyamangalam, TamilNadu, India. 2Associate Professor, Department of Information Technology, Bannari Amman Institute of Technology, Sathyamangalam, TamilNadu, India. Assistant Professor, Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Sathyamangalam, TamilNadu, India. A R T I C L E I N F O Article history: Received 12 January 2014 Received in revised form 22 March 2014 Accepted 27 March 2014 Available online 2 April 2014" 1daaeae28270b06962eb6fcf812a368892b5dff4,Modeling Visual Context Is Key to Augmenting Object Detection Datasets,"Modeling Visual Context is Key to Augmenting Object Detection Datasets Nikita Dvornik, Julien Mairal, Cordelia Schmid Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP(cid:63), LJK, 38000 Grenoble, France" 1d4f56a9bb093c52569917537a93c7671db28e6f,Real-time Tracking of Player Identities in Team Sports,"Real-time Tracking of Player Identities in Team Sports Dissertation Nicolai Baron von Hoyningen-Huene" 1d03698a46ff12fdfaf4811528b3e7961dfd2fe6,Fast Exact Max-Kernel Search,"Fast Exact Max-kernel Search Ryan R. Curtin Parikshit Ram Alexander G. Gray" 1d53aebe67d0e088e2da587fd6b08c8e8ed7f45c,A Selection Module for Large-Scale Face Recognition Systems,"A Selection module for large-scale face recognition systems Giuliano Grossi, Raffaella Lanzarotti, and Jianyi Lin Dipartimento di Informatica, Universit`a degli Studi di Milano Via Comelico 39/41, Milano, Italy" 1d729693a888a460ee855040f62bdde39ae273af,Photorealistic Face De-Identification by Aggregating Donors' Face Components,"Photorealistic Face de-Identification by Aggregating Donors’ Face Components Saleh Mosaddegh, Lo¨ıc Simon, Fr´ed´eric Jurie To cite this version: Saleh Mosaddegh, Lo¨ıc Simon, Fr´ed´eric Jurie. Photorealistic Face de-Identification by Aggre- gating Donors’ Face Components. Asian Conference on Computer Vision, Nov 2014, Singapore. pp.1-16, 2014. HAL Id: hal-01070658 https://hal.archives-ouvertes.fr/hal-01070658 Submitted on 2 Oct 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 1d6905e88f64ac826344d89c51ad8daea3b95e0e,Monocular Object Orientation Estimation using Riemannian Regression and Classification Networks,"Noname manuscript No. (will be inserted by the editor) Monocular Object Orientation Estimation using Riemannian Regression and Classification Networks Siddharth Mahendran · Ming Yang Lu · Haider Ali · Ren´e Vidal the date of receipt and acceptance should be inserted later" 1d679b371c9dfd833cee0925de483562d2bc7d88,Face Recognition using 3D Summation Invariant Features,"­4244­0367­7/06/$20.00 ©2006 IEEE ICME 2006" 1d93a1af770040cb8a64e96215884ee363a8f53a,Improved face recognition at a distance using light field camera & super resolution schemes,"Improved Face Recognition At A Distance Using Light Field Camera & Super Resolution Schemes R. Raghavendra* Kiran B. Raja*† Bian Yang* Christoph Busch*† {raghavendra.ramachandra, kiran.raja, bian.yang, *Norwegian Biometrics Laboratory Hochschule Darmstadt - CASED Gjøvik University College 802 Gjøvik, Norway Haardtring 100, 64295 Darmstadt, Germany" 1d9306ea0f0239c88aecbcf0a48a11c964a0fcd4,3D facial expression recognition using maximum relevance minimum redundancy geometrical features,"Rabiu et al. EURASIP Journal on Advances in Signal Processing 2012, 2012:213 http://asp.eurasipjournals.com/content/2012/1/213 RESEARCH Open Access D facial expression recognition using maximum relevance minimum redundancy geometrical features Habibu Rabiu*, M. Iqbal Saripan, Syamsiah Mashohor and Mohd Hamiruce Marhaban" 1de8f38c35f14a27831130060810cf9471a62b45,A Branch-and-Bound Framework for Unsupervised Common Event Discovery,"Int J Comput Vis DOI 10.1007/s11263-017-0989-7 A Branch-and-Bound Framework for Unsupervised Common Event Discovery Wen-Sheng Chu1 Jeffrey F. Cohn1,2 · Daniel S. Messinger3 · Fernando De la Torre1 · Received: 3 June 2016 / Accepted: 12 January 2017 © Springer Science+Business Media New York 2017" 1da57510321fb8b25dc4d21844fb9afa4e40571e,Activity representation with motion hierarchies,"Int J Comput Vis DOI 10.1007/s11263-013-0677-1 Activity representation with motion hierarchies Adrien Gaidon · Zaid Harchaoui · Cordelia Schmid Received: 17 May 2013 / Accepted: 20 November 2013 © Springer Science+Business Media New York 2013" 1d35a0955d2c406d7399d54117af58e2f434fa59,Efficient Learning of Relational Object Class Models,"Efficient Learning of Relational Object Class Models Aharon Bar Hillel Tomer Hertz Daphna Weinshall School of Computer Science and Engineering and the Center for Neural Computation Hebrew university of Jerusalem, Israel 91904 { aharonbh, tomboy," 1d0a6759de0d55d15439b0367f0aa49c1e248c5c,"Networking in Autism: Leveraging Genetic, Biomarker and Model System Findings in the Search for New Treatments","............................................................................................................................................................... REVIEW Networking in Autism: Leveraging Genetic, Biomarker nd Model System Findings in the Search for New Treatments Jeremy Veenstra-VanderWeele1,2,3,4 and Randy D Blakely*,1,3,4 Department of Psychiatry, Vanderbilt University School of Medicine, Nashville, TN, USA; 2Department of Pediatrics, Vanderbilt University School of Medicine, Nashville, TN, USA; 3Department of Pharmacology, Vanderbilt University School of Medicine, Nashville, TN, USA; 4Center for Molecular Neuroscience, Vanderbilt University School of Medicine, Nashville, TN, USA Autism Spectrum Disorder (ASD) is a common neurodevelopmental disorder affecting approximately 1% of children. ASD is defined by core symptoms in two domains: negative symptoms of impairment in social and communication function, and positive symptoms of restricted and repetitive behaviors. Available treatments are inadequate for treating both core symptoms and associated conditions. Twin studies indicate that ASD susceptibility has a large heritable component. Genetic studies have identified promising leads, with converging insights emerging from single-gene disorders that bear ASD features, with particular interest in mammalian target of rapamycin (mTOR)-linked synaptic plasticity mechanisms. Mouse models of these disorders are revealing not only opportunities to model behavioral perturbations across species, but also evidence of postnatal rescue of brain and behavioral phenotypes. An intense search for ASD biomarkers has consistently pointed to elevated platelet serotonin (5-HT) levels and a surge in brain growth in the first 2 years of life. Following a review of the diversity of ASD phenotypes and its genetic origins and biomarkers, we discuss opportunities for translation of these" 1d1cc4936d72fd78d8001a20d4c1981b8f6c1ce9,Continuous Audio-visual Speech Recognition Continuous Audio-visual Speech Recognition,"IDIAP Martigny - Valais - Suisse Continuous Audio(cid:0)Visual Speech Recognition Juergen Luettin  St(cid:0)ephane Dupont (cid:5) IDIAP(cid:0)RR (cid:3) th European Conference on Computer Vision(cid:1) Freiburg(cid:1)   published in D a l l e M o l l e I n s t i t u t e f o r P e r c e p t u a l A r t i f i c i a l Intelligence (cid:0) P(cid:0)O(cid:0)Box   (cid:0) Martigny (cid:0) Valais (cid:0) Switzerland phone (cid:0) (cid:1)  (cid:1)    (cid:0) (cid:1)  (cid:1)    e(cid:4)mail secretariat(cid:0)idiap(cid:1)ch internet http(cid:2)(cid:3)(cid:3)www(cid:1)idiap(cid:1)ch  IDIAP(cid:5) email(cid:6) luettin(cid:7)idiap(cid:8)ch  Facult(cid:9)e Polytechnique de Mons (cid:10) TCTS (cid:5) Bld(cid:8) Dolez(cid:5) B(cid:12) Mons(cid:5) Belgium(cid:5)" 1d0cbbe466647286bd73d41032a418b0e2265e7c,Fusion of face and gait for human recognition,"FUSION OF FACE AND GAIT FOR HUMAN RECOGNITION RABIA JAFRI (Under the Direction of Hamid R. Arabnia)" 1d5caa4128fc169bf961830048fe493ed0da0e98,Image Recognition with Deep Learning Techniques and TensorFlow,"Universitat Politècnica de Catalunya (UPC) - BarcelonaTech Facultat d’Informàtica de Barcelona (FIB) Image Recognition with Deep Learning Techniques and TensorFlow Maurici Yagües Gomà Master in Innovation and Research in Informatics Data Mining and Business Intelligence Advisor: Jordi Torres Viñals Universitat Politècnica de Catalunya (UPC) Department of Computer Architecture (DAC) Co-Advisor: Ruben Tous Liesa Universitat Politècnica de Catalunya (UPC) Department of Computer Architecture (DAC) October 20, 2016" 1d776bfe627f1a051099997114ba04678c45f0f5,Deployment of Customized Deep Learning based Video Analytics On Surveillance Cameras,"Deployment of Customized Deep Learning based Video Analytics On Surveillance Cameras Pratik Dubal(cid:63), Rohan Mahadev(cid:63), Suraj Kothawade(cid:63), Kunal Dargan, and Rishabh Iyer AitoeLabs (www.aitoelabs.com)" 1d1e78bb93590a86ecfd2516f4e5789cc05d76f5,Generative Models,"FACE AUTHENTICATION BASED ON LOCAL FEATURES AND GENERATIVE MODELS Fabien Cardinaux (a) IDIAP–RR 05-85 JANUARY 2006 ESEARCHREPRORTIDIAPRue du Simplon 4IDIAP Research Institute1920 Martigny − Switzerlandwww.idiap.chTel: +41 27 721 77 11Email: Box 592Fax: +41 27 721 77 12" 1d524c57214384ad6a003c54b1918130744b69d2,Identifying Human-Object Interactions in Motionless Images by Modeling the Mutual Context of Objects and Human Poses,"International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Impact Factor (2012): 3.358 Identifying Human-Object Interactions in Motionless Images by Modeling the Mutual Context of Objects and Human Poses A. N. Bhagat1, N. B. Pokale2 Department of Computer Engineering, TSSM,s Bhivrabai Sawant College Of Engineering and Research, Narhe, Pune, Maharashtra, India. Associate Professor, Department of Computer Engineering, TSSM,s Bhivrabai Sawant College Of Engineering and Research, Narhe, Pune, Maharashtra, India." 1d4c2dd3996cb3d87da6c35d72572637d3175ea5,Toward Storytelling From Visual Lifelogging: An Overview,"JOURNAL OF TRANSACTIONS ON HUMAN-MACHINE SYSTEMS JULY 2015 Towards Storytelling from Visual Lifelogging: An Overview Marc Bola˜nos∗, Mariella Dimiccoli∗, and Petia Radeva" 1da8178bfca7c76cae53ec34364d86c7d5713fdd,Pairwise Relational Networks using Local Appearance Features for Face Recognition,"Pairwise Relational Networks using Local Appearance Features for Face Recognition Bong-Nam Kang Yonghyun Kim, Daijin Kim Department of Creative IT Engineering Department of Computer Science and Engineering POSTECH, Korea POSTECH, Korea" 1d7ecdcb63b20efb68bcc6fd99b1c24aa6508de9,The Hidden Sides of Names—Face Modeling with First Name Attributes,"The Hidden Sides of Names—Face Modeling with First Name Attributes Huizhong Chen, Student Member, IEEE, Andrew C. Gallagher, Senior Member, IEEE, and Bernd Girod, Fellow, IEEE" 1d9bd24e65345258259ee24332141e371c6e4868,Learning Image Descriptors with Boosting,"Learning Image Descriptors with Boosting Tomasz Trzcinski, Mario Christoudias, and Vincent Lepetit" 1d5d68bee741d81771e9224fe53806e85ed469aa,RATM: Recurrent Attentive Tracking Model,"RATM: Recurrent Attentive Tracking Model Samira Ebrahimi Kahou, Vincent Michalski, and Roland Memisevic" 1dc94886ca1d4893208d38b18cb7ad1541a74b82,Weakly Supervised Training of Speaker Identification Models,"Weakly Supervised Training of Speaker Identification Models Martin Karu, Tanel Alum¨ae Department of Software Science Tallinn University of Technology, Estonia" 1d6e0399ccf832585dcb3541f1b3ca8358f0c462,Data-Efficient Decentralized Visual SLAM,"Data-Efficient Decentralized Visual SLAM Titus Cieslewski1, Siddharth Choudhary2 and Davide Scaramuzza1" 1dca96fdcab180133644442df4ad78eeec1aa00b,Learning from Synthetic Humans,"Learning from Synthetic Humans G¨ul Varol∗† Javier Romero‡ Xavier Martin† Naureen Mahmood‡ Michael Black‡ Ivan Laptev∗ Cordelia Schmid†" 1df554e992baf60f2d0b7c1b563250ba19b8f8ff,3D Face Recognition Based on 3D Ridge Lines in Range Data,"-4244-1437-7/07/$20.00 ©2007 IEEE I - 137 ICIP 2007" 1daf18f2b1bed861a9483de129223755260193fa,Near-Eye Display Gaze Tracking via Convolutional Neural Networks,"Near-Eye Display Gaze Tracking via Convolutional Neural Networks Robert Konrad Shikhar Shrestha Paroma Varma" 1d4e1b4f37caf40dc70d211c6b2745195dfa6c3f,Facial Expression Recognition Using Interpolation Features,"Facial Expression Recognition Using Interpolation Features Jesús García-Ramírez, Ivan Olmos-Pineda, J. Arturo Olvera-López, and Manuel Martín-Ortíz Benemérita Universidad Autónoma de Puebla, Faculty of Computer Science, Puebla, México" 1d1f83023686d43fd4e8805c8e517dffb02d118c,Compiler Enhanced Scheduling for OpenMP for Heterogeneous Multiprocessors,"Compiler Enhanced Scheduling for OpenMP for Heterogeneous Multiprocessors Jyothi Krishna V S IIT Madras" 1d692f37c2594ddb30518da27bfc0f5044690d09,Learning Depth From Single Images With Deep Neural Network Embedding Focal Length,"Learning Depth from Single Images with Deep Neural Network Embedding Focal Length Lei He, Guanghui Wang (Senior Member, IEEE) and Zhanyi Hu" 1d81293bc17a135cfd35912146c538cd81830381,Single camera multi-person tracking based on crowd simulation,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-1-6 ©2012 IAPR" 1dd481c6158c6f6acb99ccbd4b64018b873f7dce,Multi-Modal Target Detection for Autonomous Wide Area Search and Surveillance,"Multi-Modal Target Detection for Autonomous Wide Area Search and Surveillance Toby P. Breckon, Anna Gaszczak, Jiwan Han, Marcin L. Eichner, Stuart E. Barnes School of Engineering, Cranfield University, Bedfordshire, UK" 1db316f850ccd3600ce3526da4a611f8078ec33c,Estimating Vehicle Ego-Motion and Piecewise Planar Scene Structure from Optical Flow in a Continuous Framework,"Estimating Vehicle Ego-Motion and Piecewise Planar Scene Structure from Optical Flow in a Continuous Framework Andreas Neufeld, Johannes Berger, Florian Becker, Frank Lenzen, and Christoph Schn¨orr IPA & HCI, University of Heidelberg, Germany" 1d2af64416882b2ae8fe4de51b85fdd7d561cfee,Headgear Accessories Classification Using an Overhead Depth Sensor,"Article Headgear Accessories Classification Using an Overhead Depth Sensor Carlos A. Luna, Javier Macias-Guarasa ID , Cristina Losada-Gutierrez * ID , Marta Marron-Romera, Manuel Mazo, Sara Luengo-Sanchez and Roberto Macho-Pedroso Department of Electronics, University of Alcala, Ctra. Madrid-Barcelona, km.33,600, 28805 Alcalá de Henares, Spain; (C.A.L.); (J.M.-G.); (M.M.-R.); (M.M.); (S.L.-S.); (R.M.-P.) * Correspondence: Tel.: +34-918-856-906; Fax: +34-918-856-591 Received: 22 June 2017; Accepted: 8 August 2017; Published: 10 August 2017" 1db44d94f6a4eaa3780c251446fa0fba14dfae44,Rapid prefrontal cortex activation towards aversively paired faces and enhanced contingency detection are observed in highly trait-anxious women under challenging conditions,"ORIGINAL RESEARCH published: 10 June 2015 doi: 10.3389/fnbeh.2015.00155 Rapid prefrontal cortex activation towards aversively paired faces and enhanced contingency detection are observed in highly trait-anxious women under challenging conditions Maimu Alissa Rehbein 1,2*, Ida Wessing 3, Pienie Zwitserlood 2,4, Christian Steinberg 1,2, Annuschka Salima Eden 1,2, Christian Dobel 1,2 and Markus Junghöfer 1,2 Institute for Biomagnetism and Biosignalanalysis, University Hospital Münster, Münster, Germany, 2 Otto Creutzfeldt Center for Cognitive and Behavioral Neuroscience, University of Münster, Münster, Germany, 3 Department of Child and Adolescent Psychiatry, University Hospital Münster, Münster, Germany, 4 Institute of Psychology, University of Münster, Münster, Germany Relative to healthy controls, anxiety-disorder patients show anomalies in classical onditioning that may either result from, or provide a risk factor for, clinically relevant nxiety. Here, we investigated whether healthy participants with enhanced anxiety vulnerability show abnormalities in a challenging affective-conditioning paradigm, in which many stimulus-reinforcer associations had to be acquired with only few learning trials. Forty-seven high and low trait-anxious females underwent MultiCS conditioning," 1d99282d00f7cf3e4d912428313848add8de8220,Comparing Attribute Classifiers for Interactive Language Grounding,"Proceedings of the 2015 Workshop on Vision and Language (VL’15), pages 60–69, Lisbon, Portugal, 18 September 2015. c(cid:13)2015 Association for Computational Linguistics." d341ff4e93ff4407251d00417c9a756a68b6f5be,Recognition of identical twins using fusion of various facial feature extractors,"Afaneh et al. EURASIP Journal on Image and Video Processing (2017) 2017:81 DOI 10.1186/s13640-017-0231-0 EURASIP Journal on Image nd Video Processing RESEARCH Open Access Recognition of identical twins using fusion of various facial feature extractors Ayman Afaneh1, Fatemeh Noroozi2 and Önsen Toygar1*" d3b73e06d19da6b457924269bb208878160059da,IMPLEMENTATION OF AN AUTOMATED SMART HOME CONTROL FOR DETECTING HUMAN EMOTIONS VIA FACIAL DETECTION,"Proceedings of the 5th International Conference on Computing and Informatics, ICOCI 2015 1-13 August, 2015 Istanbul, Turkey. Universiti Utara Malaysia (http://www.uum.edu.my ) Paper No. IMPLEMENTATION OF AN AUTOMATED SMART HOME CONTROL FOR DETECTING HUMAN EMOTIONS VIA FACIAL DETECTION Lim Teck Boon1, Mohd Heikal Husin2, Zarul Fitri Zaaba3 and Mohd Azam Osman4 Universiti Sains Malaysia, Malaysia, Universiti Sains Malaysia, Malaysia, Universiti Sains Malaysia, Malaysia, Universiti Sains Malaysia, Malaysia," d3797366259182070c598e95cef8fff1ddb21f65,Distance-based Camera Network Topology Inference for Person Re-identification,"Distance-based Camera Network Topology Inference for Person Re-identification Yeong-Jun Cho and Kuk-Jin Yoon Computer Vision Laboratory, GIST, South Korea {yjcho," d3b898fbd3e6d788020f07c8514ecbbcebde8b9b,A Comparison of People Counting Techniques via Video Scene Analysis, d3565af8028c0ca486b452e55d0c577c34efb5a6,Face Recognition with VG-RAM Weightless Neural Networks,"Face Recognition with VG-RAM Weightless Neural Networks Alberto F. De Souza1, Claudine Badue1, Felipe Pedroni1, Elias Oliveira2, Stiven Schwanz Dias1, Hallysson Oliveira1, and Soterio Ferreira de Souza Departamento de Inform´atica Departamento de Ciˆencia da Informa¸c˜ao Universidade Federal do Esp´ırito Santo Av. Fernando Ferrari, 514, 29075-910 - Vit´oria-ES, Brazil" d331099a0e527bfe5f74c74d13c65b45fabcf88e,Dynamic 3D Scene Reconstruction and Enhancement,"Dynamic 3D Scene Reconstruction and Enhancement Cansen Jiang, Yohan Fougerolle, David Fofi, Cédric Demonceaux To cite this version: Cansen Jiang, Yohan Fougerolle, David Fofi, Cédric Demonceaux. Dynamic 3D Scene Reconstruction nd Enhancement. IAPR 19th International Conference in Image Analysis and Processing (ICIAP17), Sep 2017, Catania, Italy. 2017. HAL Id: hal-01569314 https://hal.archives-ouvertes.fr/hal-01569314 Submitted on 26 Jul 2017 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" d3b18ba0d9b247bfa2fb95543d172ef888dfff95,Learning and Using the Arrow of Time,"Learning and Using the Arrow of Time Donglai Wei1, Joseph Lim2, Andrew Zisserman3 and William T. Freeman4,5 Harvard University 2University of Southern California University of Oxford 4Massachusetts Institute of Technology 5Google Research Figure 1: Seeing these ordered frames from videos, can you tell whether each video is playing forward or backward? (answer elow1). Depending on the video, solving the task may require (a) low-level understanding (e.g. physics), (b) high-level reasoning (e.g. semantics), or (c) familiarity with very subtle effects or with (d) camera conventions. In this work, we learn nd exploit several types of knowledge to predict the arrow of time automatically with neural network models trained on large-scale video datasets." d360968cbcca774bf0b70bb0f3fc870aea121924,Deep Neural Ranking for Crowdsourced Geopolitical Event Forecasting,"Deep Neural Ranking for Crowdsourced Geopolitical Event Forecasting Giuseppe Nebbione1, Derek Doran2, Srikanth Nadella3, and Brandon Minnery3 Dept. of Electrical & Computer Engineering, University of Pavia, Italy Dept. of Computer Science & Engineering, Wright State University, Dayton, OH, USA Wright State Research Institute, Dayton, OH, USA {derek.doran, srikanth.nadella," d3c1612ae08241dadf6abd650663f4f9351abaf9,Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network,"Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network Stefan Zernetsch, Viktor Kress, Bernhard Sick and Konrad Doll" d33f75bc05bcce1779fce534da86cb039d11ed26,Occupancy Grid Mapping using Stereo Vision by Alwyn,"Occupancy Grid Mapping using Stereo Vision Alwyn Johannes Burger Thesis presented in partial fulfilment of the requirements for the degree of Master of Engineering t Stellenbosch University Supervisors: Dr C.E. van Daalen Electrical and Electronic Engineering Dr W.H. Brink Mathematical Sciences March 2015" d33beb4f1477374fbcffd8e9df74ca2547eb77ee,Feature Selection for Tracker-Less Human Activity Recognition,"Feature Selection for tracker-less human activity recognition(cid:63) Plinio Moreno, Pedro Ribeiro, and Jos´e Santos-Victor Instituto de Sistemas e Rob´otica & Instituto Superior T´ecnico Portugal" d318f3ca49f7f2159b9fc0face08eb284d5442dc,"Scene Text Detection via Holistic, Multi-Channel Prediction","Scene Text Detection via Holistic, Multi-Channel Prediction Cong Yao1,2, Xiang Bai1, Nong Sang1, Xinyu Zhou2, Shuchang Zhou2, Zhimin Cao2 Huazhong University of Science and Technology (HUST). Wuhan, China. Email: {xbai, {zxy, zsc, Megvii Inc. Beijing, China. its great" d3d71a110f26872c69cf25df70043f7615edcf92,Learning Compact Feature Descriptor and Adaptive Matching Framework for Face Recognition,"Learning Compact Feature Descriptor and Adaptive Matching Framework for Face Recognition Zhifeng Li, Senior Member, IEEE, Dihong Gong, Xuelong Li, Fellow, IEEE, and Dacheng Tao, Fellow, IEEE improvements" d3c99ec84197320443127d2f2f2a8f42c878b310,Final Report : GBS : Guidance By Semantics-Using High-Level Visual Inference to Improve Vision-based Mobile Robot Localization Report,"REPORT DOCUMENTATION PAGE Form Approved OMB NO. 0704-0188 The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggesstions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA, 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any oenalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. PLEASE DO NOT RETURN YOUR FORM TO THE ABOVE ADDRESS. . REPORT DATE (DD-MM-YYYY) 8-08-2015 . TITLE AND SUBTITLE Final Report: GBS: Guidance By Semantics-Using High-Level Visual Inference to Improve Vision-based Mobile Robot Localization 5a. CONTRACT NUMBER W911NF-11-1-0090 5b. GRANT NUMBER . REPORT TYPE Final Report" d3f5a1848b0028d8ab51d0b0673732cad2e3c8c9,STAIR Actions: A Video Dataset of Everyday Home Actions, d31d4bb58f5dd67016e77352ac7600e2ba71e38f,Deep Learning Object Detection Methods for Ecological Camera Trap Data,"Deep Learning Object Detection Methods for Ecological Camera Trap Data Stefan Schneider∗, Graham W. Taylor†, Stefan C. Kremer∗ School of Computer Science, University of Guelph {sschne01, School of Engineering, University of Guelph Vector Institute for Artificial Intelligence Canadian Institute for Advanced Research" d31e47f45041736c93ec23ba1dbaef6c311e76d6,TÜB İ TAK UZAY at TRECVID 2009 : High-Level Feature Extraction and Content-Based Copy Detection,"TÜBİTAK UZAY at TRECVID 2009: High-Level Feature Extraction and Content-Based Copy Detection Ahmet Saracoğlu1,2, Ersin Esen1,2, Medeni Soysal1,2, Tuğrul K. Ateş1,2, Berker Loğoğlu1, Mashar Tekin1, Talha Karadeniz1, Müge Sevinç1, Hakan Sevimli1, Banu Oskay Acar1, Ünal Zubari1, Ezgi C. Ozan1,2, Egemen Özalp1, Duygu Oskay Onur1, Sezin Selçuk1, A. Aydın Alatan2, Tolga Çiloğlu2 TÜBİTAK Space Technologies Research Institute Department of Electrical and Electronics Engineering, M.E.T.U. {ahmet.saracoglu, ersin.esen, medeni.soysal, tugrul.ates, berker.logoglu, mashar.tekin, talha.karadeniz, muge.sevinc, hakan.sevimli, banu.oskay, unal.zubari, ezgican.ozan, duygu.oskay, sezin.selcuk," d3e9c5a63215a9c46bc61ec04df5285ac355e42c,Integration of visual and depth information for vehicle detection,pport (cid:13)(cid:13)de recherche(cid:13)ISSN0249-6399ISRNINRIA/RR--7703--FR+ENGRoboticsINSTITUTNATIONALDERECHERCHEENINFORMATIQUEETENAUTOMATIQUEIntegrationofvisualanddepthinformationforvehicledetectionAlexandrosMakris—MathiasPerrollaz—IgorParomtchik—ChristianLaugierN°7703July2011 d3d4700181179ed24b7afc5510ab1ea1cb8cfdc2,Development of an Efficient Face Recognition System Based on Linear and Nonlinear Algorithms,"IAES International Journal of Artificial Intelligence (IJ-AI) Vol. 5, No. 2, June 2016, pp. 80~88 ISSN: 2252-8938 Development of an Efficient Face Recognition System Based on Linear and Nonlinear Algorithms Araoluwa Simileolu Filani, Adebayo Olusola Adetunmbi Federal University of Technology, Akure, Ondo State, Nigeria" d3612bcc772761b611365fe21c42eafb181338ef,Face and Street Detection with Asymmetric Haar Features,"Face and Street Detection with Asymmetric Haar Features Geovany A. Ramirez University of Texas at El Paso 500 W University Ave - El Paso TX 79968 500 W University Ave - El Paso TX 79968 Olac Fuentes University of Texas at El Paso" d3e51c0cfd6ae3d3082c2aa27fa1c73fa9662fdf,Isometry-invariant Surface Matching : Numerical Algorithms and Applications,"ISOMETRY-INVARIANT SURFACE MATCHING: NUMERICAL ALGORITHMS AND APPLICATIONS MICHAEL M. BRONSTEIN Technion - Computer Science Department - Ph.D. Thesis PHD-2007-04 - 2007" d309e414f0d6e56e7ba45736d28ee58ae2bad478,Efficient Two-Stream Motion and Appearance 3 D CNNs for Video Classification,"Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification Ali Diba ESAT-KU Leuven Ali Pazandeh Sharif UTech Luc Van Gool ESAT-KU Leuven, ETH Zurich" d3761354b7df1228eabf46032fd01a4109229d43,Selection of optimal narrowband multispectral images for face recognition. (Sélection des bandes spectrales optimales pour la reconnaissance des visages),"UNIVERSITY OF BURGUANDY SPIM doctoral school PhD from the University of Burgundy in Computer Science Presented by: Hamdi Bouchech Defense Date: January 26, 2015 Selection of optimal narrowband multispectral images for face recognition Thesis supervisor: Dr. Sebti Foufou Jury: Frederic Morain-Nicolier, Professeur a I’IUT de Troyes, Rapporteur. Pierre BONTON, Professeur à l’ Université Blaise Pascal, retraité , Rapporteur. Saida Bouakaz, Professeur à l’ Université Claude Bernard Lyon 1, Examinatrice. Pierre Gouton, Professeur à l’ Université de Bourgogne, Examinateur. Yassine Ruichek, Professeur à l’ Université de Technologie de Belfort-Montbéliard, Examinateur. Sebti Foufou, Professeur à l’ Université de Bourgogne, directeur de thèse." d33c9fe66bad7a90e34e8bc1332b73147a30d202,Trace alignment algorithms for offline workload analysis of heterogeneous architectures,"Trace Alignment Algorithms for Offline Workload Analysis of Heterogeneous Architectures Muhammet Mustafa Ozdal Intel Corporation Hillsboro, OR 97124 Aamer Jaleel Intel Corporation Hudson, MA Paolo Narvaez Intel Corporation Hudson, MA Steven Burns Intel Corporation Hillsboro, OR Ganapati Srinivasa Intel Corporation Hillsboro, OR" d348197e47a8e081bd3f12a22bc52b055ecd8302,Unified Framework for Automated Person Re-identification and Camera Network Topology Inference in Camera Networks,"Unified Framework for Automated Person Re-identification and Camera Network Topology Inference in Camera Networks Yeong-Jun Cho, Jae-Han Park*, Su-A Kim*, Kyuewang Lee and Kuk-Jin Yoon Computer Vision Laboratory, GIST, South Korea {yjcho, qkrwogks, suakim, kyuewang," 8ff3c7b46ab36f1d01e96681baf512859cc80a4d,Dynamics of alpha oscillations elucidate facial affect recognition in schizophrenia.,"Dynamics of alpha oscillations elucidate facial affect recognition in schizophrenia Tzvetan G. Popov & Brigitte S. Rockstroh & Petia Popova & Almut M. Carolus & Gregory A. Miller" 8fc21217ee89c505930b540b716b11bab89d3bcd,Memory Efficient Nonuniform Quantization for Deep Convolutional Neural Network,"Memory Efficient Nonuniform Quantization for Deep Convolutional Neural Network Fangxuan Sun and Jun Lin" 8f6d05b8f9860c33c7b1a5d704694ed628db66c7,Non-linear dimensionality reduction and sparse representation models for facial analysis. (Réduction de la dimension non-linéaire et modèles de la représentations parcimonieuse pour l'analyse du visage),"Non-linear dimensionality reduction and sparse representation models for facial analysis Yuyao Zhang To cite this version: Yuyao Zhang. Non-linear dimensionality reduction and sparse representation models for facial analysis. Medical Imaging. INSA de Lyon, 2014. English. . HAL Id: tel-01127217 https://tel.archives-ouvertes.fr/tel-01127217 Submitted on 7 Mar 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 8f2e594f55ca1b1675d8bfef25922c97109cb599,An evil face? Verbal evaluative multi-CS conditioning enhances face-evoked mid-latency magnetoencephalographic responses,"Social Cognitive and Affective Neuroscience, 2017, 695–705 doi: 10.1093/scan/nsw179 Advance Access Publication Date: 22 December 2016 Original article An evil face? Verbal evaluative multi-CS conditioning enhances face-evoked mid-latency magnetoencephalo- graphic responses Markus Jungho¨ fer,1,2 Maimu Alissa Rehbein,1,2 Julius Maitzen,1 Sebastian Schindler,3,4 and Johanna Kissler3,4 Institute for Biomagnetism and Biosignalanalysis, University Hospital Mu¨ nster, Mu¨ nster D-48149, Germany, Otto Creutzfeldt Center for Cognitive and Behavioral Neuroscience, University of Mu¨ nster, Mu¨ nster D-48151, Germany, 3Department of Psychology, Affective Neuropsychology Unit and 4Center of Excellence Cognitive Interaction Technology (CITEC), University of Bielefeld, Bielefeld D-33501, Germany Correspondence should be addressed to Johanna Kissler, Department of Psychology, Affective Neuropsychology Unit, University of Bielefeld, Bielefeld D-33501, Germany. E-mail:" 8fe43144c0ff36ffefca869eec0a63e71ca02049,D correlation filter based class-dependence feature analysis for face recognition,"This article appeared in a journal published by Elsevier. The attached opy is furnished to the author for internal non-commercial research nd education use, including for instruction at the authors institution nd sharing with colleagues. Other uses, including reproduction and distribution, or selling or licensing copies, or posting to personal, institutional or third party websites are prohibited. In most cases authors are permitted to post their version of the rticle (e.g. in Word or Tex form) to their personal website or institutional repository. Authors requiring further information regarding Elsevier’s archiving and manuscript policies are encouraged to visit: http://www.elsevier.com/copyright" 8f0c11a3332c434af11c01ee11ff7c492c7968da,Domain Adaptive Faster R-CNN for Object Detection in the Wild,"Domain Adaptive Faster R-CNN for Object Detection in the Wild Yuhua Chen1 Wen Li1 Christos Sakaridis1 Dengxin Dai1 Luc Van Gool1,2 Computer Vision Lab, ETH Zurich VISICS, ESAT/PSI, KU Leuven" 8fc730d22f33d08be927e5449f359dc15b5c3503,Measuring and modeling the perception of natural and unconstrained gaze in humans and machines,"CBMM Memo No. 059 November 28, 2016 Measuring and modeling the perception of natural nd unconstrained gaze in humans and machines Daniel Harari*, Tao Gao*, Nancy Kanwisher, Joshua Tenenbaum, Shimon Ullman" 8f7babdf96ac2ceab69ee5101a0a2eda5a73f775,Using KL-divergence to focus Deep Visual Explanation,"Using KL-divergence to focus Deep Visual Explanation Housam Khalifa Bashier Babiker and Randy Goebel Alberta Machine Intelligence Institute Department of Computing Science University of Alberta Edmonton, Alberta Canada T6G 2E8" 8f8c0243816f16a21dea1c20b5c81bc223088594,LOCAL DIRECTIONAL NUMBER BASED CLASSIFICATION AND RECOGNITION OF EXPRESSIONS USING SUBSPACE METHODS, 8f98e1e041e7d3e27397c268e85e815065329d2d,Hierarchical feed forward models for robust object recognition,"Hierarchical Feed-Forward Models for Robust Object Recognition Ingo Bax Der Technischen Fakult¨at der Universit¨at Bielefeld vorgelegt zur Erlangung des akademischen Grades Doktor der Ingenieurwissenschaften" 8f2e83f6d70b9e161ad714fee79ed6d23ae2a93f,Image Intelligent Detection Based on the Gabor Wavelet and the Neural Network,"Article Image Intelligent Detection Based on the Gabor Wavelet and the Neural Network Yajun Xu 1, Fengmei Liang 1,*, Gang Zhang 1 and Huifang Xu 2 College of Information Engineering, Taiyuan University of Technology, Taiyuan 030024, China; (Y.X.); (G.Z.) Daqin Railway Co. Ltd., Taiyuan Railway Administration, Taiyuan 030013, China; * Correspondence: Tel.: +86-186-0341-0966 Academic Editor: Angel Garrido Received: 21 September 2016; Accepted: 11 November 2016; Published: 15 November 2016" 8fdfd4c5039cf7d70470a2a3ac52bfd229bcd4e2,Pushing the Limits of Radiology with Joint Modeling of Visual and Textual Information,"Pushing the Limits of Radiology with Joint Modeling of Visual and Textual Information Department of Computing, Macquarie University1 Sonit Singh1,2 DATA61, CSIRO2 Sydney, Australia" 8f2b348673e1b59a821a3d0ff6276acdc16a1a7f,Differential training in physical prevention and rehabilitation programmes for health and exercise,"This is the author’s version of a work that was submitted/accepted for pub- lication in the following source: Schollhorn, Wolfgang, Beckmann, Hendrik, & Davids, Keith W. (2010) Ex- ploiting system fluctuations. Differential training in physical prevention and rehabilitation programs for health and exercise. Medicina (Kaunas), 46(6), pp. 365-373. This file was downloaded from: http://eprints.qut.edu.au/41038/ (cid:13) Copyright 2010 Kauno Medicinos Universitetas Notice: Changes introduced as a result of publishing processes such as opy-editing and formatting may not be reflected in this document. For a definitive version of this work, please refer to the published source:" 8fe7354a92b4c74c22dc0a253dfe7320487d22ab,LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETECTION AND RECOGNITION,"Circuits and Systems: An International Journal (CSIJ), Vol. 1, No.2, April 2014 LITERATURE SURVEY ON SPARSE REPRESENTATION FOR NEURAL NETWORK BASED FACE DETECTION AND RECOGNITION Raviraj Mane,Poorva Agrawal, Nisha Auti CS Department SIT, Pune" 8fe9cd45280696574a6afc10e5a06eb1888d82ee,Illumination Invariant Face Recognition Using Thermal Infrared Imagery,"Illumination Invariant Face Recognition Using Thermal Infrared Imagery Diego A. Socolinsky† Christopher K. Eveland‡ Lawrence B. Wolff‡ Equinox Corporation 9 West 57th Street Joshua D. Neuheisel† Equinox Corporation 07 East Redwood Street New York, NY 10019 Baltimore, MD 21202" 8f077eeeb9678a31e77a17a5c28c36699cf13f83,Gender classification of faces using adaboost,"Gender Classification of Faces Using Adaboost* Rodrigo Verschae1,2,3, Javier Ruiz-del-Solar1,2, and Mauricio Correa1,2 Department of Electrical Engineering, Universidad de Chile Center for Web Research, Department of Computer Science, Universidad de Chile CMLA, ENS Cachan, France" 8f9c37f351a91ed416baa8b6cdb4022b231b9085,Generative Adversarial Style Transfer Networks for Face Aging,"Generative Adversarial Style Transfer Networks for Face Aging Sveinn Palsson D-ITET, ETH Zurich Eirikur Agustsson D-ITET, ETH Zurich" 8f5566fa00f8c79f4720e14084489e784688ab0b,The role of the amygdala in atypical gaze on emotional faces in autism spectrum disorders.,"The Journal of Neuroscience, July 11, 2012 • 32(28):9469 –9476 • 9469 Behavioral/Systems/Cognitive The Role of the Amygdala in Atypical Gaze on Emotional Faces in Autism Spectrum Disorders Dorit Kliemann,1,2,3,4 Isabel Dziobek,2,3 Alexander Hatri,1,2,3 Ju¨rgen Baudewig,2,3 and Hauke R. Heekeren1,2,3,4 Department of Education and Psychology, 2Cluster of Excellence “Languages of Emotion,” and 3Dahlem Institute for Neuroimaging of Emotion (D.I.N.E), Freie Universita¨t Berlin, 14195 Berlin, Germany, and 4Max Planck Institute for Human Development, 14195 Berlin, Germany Reduced focus toward the eyes is a characteristic of atypical gaze on emotional faces in autism spectrum disorders (ASD). Along with the typical gaze, aberrant amygdala activity during face processing compared with neurotypically developed (NT) participants has been repeatedly reported in ASD. It remains unclear whether the previously reported dysfunctional amygdalar response patterns in ASD support an active avoidance of direct eye contact or rather a lack of social attention. Using a recently introduced emotion classification task, we investigated eye movements and changes in blood oxygen level-dependent (BOLD) signal in the amygdala with a 3T MRI scanner in 16 autistic and 17 control adult human participants. By modulating the initial fixation position on faces, we investigated changes triggered by the eyes compared with the mouth. Between-group interaction effects revealed different patterns of gaze and amygdalar BOLD changes in ASD and NT: Individuals with ASD gazed more often away from than toward the eyes, compared with the NT group, which showed the reversed tendency. An interaction contrast of group and initial fixation position further yielded a significant cluster of mygdala activity. Extracted parameter estimates showed greater response to eyes fixation in ASD, whereas the NT group showed an increase for mouth fixation. The differing patterns of amygdala activity in combination with differing patterns of gaze behavior between groups triggered by direct eye contact and mouth fixation, suggest a dysfunctional profile of the amygdala in ASD involving an interplay of both eye-avoidance" 8fbfdd249ebf5a83ed3c43f185d143375382cea4,Design and realisation of an audiovisual speech activity detector,"Technical Note PR-TN 2006/00169 Issued: 02/2006 Design and realisation of an audiovisual speech activity detector K.C. van Bree Philips Research Europe Unclassified © Koninklijke Philips Electronics N.V. 2006" 8f9fa03690428cde478f1a27d4773f78d857b88f,Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity,"Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity Angela Eigenstetter HCI & IWR, University of Heidelberg Bj¨orn Ommer HCI & IWR, University of Heidelberg" 8fd9c22b00bd8c0bcdbd182e17694046f245335f,Recognizing Facial Expressions in Videos,"Recognizing Facial Expressions in Videos Lin Su, Matthew Balazsi" 8fb849fe51fbf4b56393cfef26397caef2a22fb0,Public Document Agreed Plans for Open Source Reference Software Document Evolution Executive Summary,"Project N° IST-2002-507634 - BioSecure D2.2.1 – Revision: b3 2 March 2005 Contract Number : Project Acronym : Project Title : Instrument : Start Date of Project : Duration : Deliverable Number : Title of Deliverable : Contractual Due Date : Actual Date of Completion : IST-2002-507634 BioSecure Biometrics for Secure Authentication Network of Excellence 01 June, 2004 6 months D2.2.1" 8fa3478aaf8e1f94e849d7ffbd12146946badaba,Attributes for classifier feedback,"Attributes for Classifier Feedback Amar Parkash1 and Devi Parikh2 Indraprastha Institute of Information Technology (Delhi, India) Toyota Technological Institute (Chicago, US)" 8fc60a7489b76641ceee5da9180a3ca76b18560d,AI Fairness for People with Disabilities: Point of View,"isabilities: Point of View AI Fairness for People with D Shari Trewin, IBM Accessibility Research," 8f772d9ce324b2ef5857d6e0b2a420bc93961196,Facial Landmark Point Localization using Coarse-to-Fine Deep Recurrent Neural Network,"MAHPOD et al.: CFDRNN Facial Landmark Point Localization using Coarse-to-Fine Deep Recurrent Neural Network Shahar Mahpod, Rig Das, Emanuele Maiorana, Yosi Keller, and Patrizio Campisi," 8fda2f6b85c7e34d3e23927e501a4b4f7fc15b2a,Feature Selection with Annealing for Big Data Learning,"Feature Selection with Annealing for Big Data Learning Adrian Barbu, Yiyuan She, Liangjing Ding, Gary Gramajo" 8f05c4c1b3c1ad31ec95ccb87bca24a884b5ad4c,Overhead Detection: Beyond 8-bits and RGB,"Overhead Detection: Beyond 8-bits and RGB Eliza Mace1 Keith Manville1 Monica Barbu-McInnis1 Michael Laielli2 Matthew Klaric2 Samuel Dooley2 MITRE, NGA," 8f44e8e3a5b233642f53c50919422425146cc443,I Know How You Feel: Emotion Recognition with Facial Landmarks,"I Know How You Feel: Emotion Recognition with Facial Landmarks Tooploox 2Polish-Japanese Academy of Information Technology 3Warsaw University of Technology Ivona Tautkute1,2, Tomasz Trzcinski1,3 and Adam Bielski1" 8fcdeda0c2f4e265e2180eb5ed39f6548ae3ba99,A Generic Middle Layer for Image Understanding,"UNIVERSIT ¨AT HAMBURG A Generic Middle Layer for Image Understanding Kasim Terzi´c Doktorarbeit Fakult¨at f¨ur Mathematik, Informatik und Naturwissenschaften Fachbereich Informatik" 91edca64a666c46b0cbca18c3e4938e557eeb21a,Guiding InfoGAN with Semi-Supervision,"Guiding InfoGAN with Semi-Supervision Adrian Spurr, Emre Aksan, and Otmar Hilliges Advanced Interactive Technologies, ETH Zurich {adrian.spurr, emre.aksan," 9143742eac54dfc1025134b8bc10f12795916ba5,Getting Robots Unfrozen and Unlost in Dense Pedestrian Crowds,"Getting Robots Unfrozen and Unlost in Dense Pedestrian Crowds Tingxiang Fan∗, Xinjing Cheng∗, Jia Pan†, Pinxin Long, Wenxi Liu, Ruigang Yang and Dinesh Manocha" 91aff7996ea9a7257517819f8079880b6f35c92b,The non-contact biometric identified bio signal measurement sensor and algorithms,"Technology and Health Care 26 (2018) S215–S228 DOI 10.3233/THC-174569 IOS Press The non-contact biometric identified bio signal measurement sensor and algorithms Chan-Il Kim and Jong-Ha Lee∗ Department of Biomedical Engineering, School of Medicine, Keimyung University, Korea" 912f6a6ac8703e095d21e2049da4871cc6d4d23b,Partitioning Networks with Node Attributes by Compressing Information Flow,"Partitioning Networks with Node Attributes by Compressing Information Flow Laura M. Smith Department of Mathematics California State University Fullerton, CA Kristina Lerman Information Sciences Institute U. of Southern California Marina del Rey, CA 90292 Linhong Zhu Information Sciences Institute U. of Southern California Marina del Rey, CA 90292 Allon G. Percus Claremont Graduate U. Claremont, CA 91711" 91d83d20cc22bde6b4b06afc87f76a1b0140d4e2,Image Classification Based on Quantum KNN Algorithm,"Noname manuscript No. (will be inserted by the editor) Image Classification Based on Quantum KNN Algorithm Yijie Dang · Nan Jiang · Hao Hu · Zhuoxiao Ji · Wenyin Zhang Received: date / Accepted: date" 91eae81dbba3013261292296bb929a18d73b447f,Utilization of Interest Point Detectors in Content Based Image Retrieval,"Ročník 2011 Číslo II Utilization of Interest Point Detectors in Content Based Image Retrieval M. Zukal 1, P. Číka1 Department of Telecommunications, Faculty of Electrical Engineering, BUT, Brno, E-mail : Purkyňova 118, Brno" 91b3aeca88e910be86f23a5bb6c1a2351eb23fae,Fast Low-Rank Shared Dictionary Learning for Image Classification,"TRANSACTIONS ON IMAGE PROCESSING, VOL. , NO. , JULY 2017 Fast Low-rank Shared Dictionary Learning for Image Classification Tiep Huu Vu, Student Member, IEEE, Vishal Monga, Senior Member, IEEE" 919e827c449ca77bcff4ce5f2ccbccdab8399ac6,Purple Triangle Orange Circle FC Layers,"Under review as a conference paper at ICLR 2018 GENERATIVE ENTITY NETWORKS: DISENTANGLING ENTI- TIES AND ATTRIBUTES IN VISUAL SCENES USING PARTIAL NATURAL LANGUAGE DESCRIPTIONS Anonymous authors Paper under double-blind review" 919d3067bce76009ce07b070a13728f549ebba49,Time Based Re-ranking for Web Image Search Ms .,"International Journal of Scientific and Research Publications, Volume 4, Issue 6, June 2014 ISSN 2250-3153 Time Based Re-ranking for Web Image Search Ms. A.Udhayabharadhi *, Mr. R.Ramachandran ** * MCA Student, Sri Manakula Vinayagar Engineering College, Pondicherry-605106 ** Assistant Professor dept of MCA, Sri Manakula Vinayagar Engineering College, Pondicherry-605106" 91ddac7d1d63c52cbe30fe27674b9c1e54bc584c,Development of EyeBlink and Face Corpora for Research in Human Computer Interaction,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 6, No. 5, 2015 Development of Eye-Blink and Face Corpora for Research in Human Computer Interaction Emmanuel Jadesola Adejoke. Dept. of Computer science Bingham University Nassarawa, Nigeria Ibiyemi Tunji Samuel Dept. of Electrical Engineering University of Ilorin Ilorin, Nigeria oded voluntary eye-blink based language communication depends" 91e57667b6fad7a996b24367119f4b22b6892eca,Probabilistic Corner Detection for Facial Feature Extraction,"Probabilistic Corner Detection for Facial Feature Extraction Article Accepted version E. Ardizzone, M. La Cascia, M. Morana In Lecture Notes in Computer Science Volume 5716, 2009 It is advisable to refer to the publisher's version if you intend to cite from the work. Publisher: Springer http://link.springer.com/content/pdf/10.1007%2F978-3- 642-04146-4_50.pdf" 91f820e2cb6fb5a8adc83e6065cbdf071aca84bd,What makes Federer look so elegant ?,"What makes Federer look so elegant? Kuldeep Kulkarni and Vinay Venkataraman" 917611cfc0fee3e834d1a6cc13ad5bc18ae428f3,Geometric models with co-occurrence groups,"Geometric Models with Co-occurrence Groups Joan Bruna1 and St´ephane Mallat2 8/16 rue Paul Vaillant Couturier, 92240, Malakoff - France - Zoran France - Ecole Polytechnique - CMAP Route de Saclay, 91128 Palaiseau - France" 91a7816609f991c1ac45b791c1cd3c6117194bb0,I Know How You Feel: Emotion Recognition with Facial Landmarks,"I Know How You Feel: Emotion Recognition with Facial Landmarks Tooploox 2Polish-Japanese Academy of Information Technology 3Warsaw University of Technology Ivona Tautkute1,2, Tomasz Trzcinski1,3 and Adam Bielski1" 914902618e7cc864393ad508521eb582a5af5b87,The differential effects of emotional salience on direct associative and relational memory during a nap.,"Cogn Affect Behav Neurosci (2016) 16:1150–1163 DOI 10.3758/s13415-016-0460-1 The differential effects of emotional salience on direct associative nd relational memory during a nap Sara E. Alger 1,2 & Jessica D. Payne 1 Published online: 26 September 2016 # Psychonomic Society, Inc. 2016" 9175b123837ecf55a9aae6c40ba245ddacbc37d5,Various Fusion Schemes to Recognize Simulated and Spontaneous Emotions,"Various Fusion Schemes to Recognize Simulated and Spontaneous Emotions Sonia Gharsalli1, H´el`ene Laurent2, Bruno Emile1 and Xavier Desquesnes1 Univ. Orl´eans, INSA CVL, PRISME EA 4229, Bourges, France on secondment from INSA CVL, Univ. Orl´eans, PRISME EA 4229, Bourges, France to the Rector of the Academy of Strasbourg, Strasbourg, France Keywords: Facial Emotion Recognition, Posed Expression, Spontaneous Expression, Early Fusion, Late Fusion, SVM, FEEDTUM Database, CK+ Database." 91811203c2511e919b047ebc86edad87d985a4fa,Expression Subspace Projection for Face Recognition from Single Sample per Person,"Expression Subspace Projection for Face Recognition from Single Sample per Person Hoda Mohammadzade, Student Member, IEEE, and Dimitrios Hatzinakos, Senior Member, IEEE" 91d513af1f667f64c9afc55ea1f45b0be7ba08d4,Automatic Face Image Quality Prediction,"Automatic Face Image Quality Prediction Lacey Best-Rowden, Student Member, IEEE, and Anil K. Jain, Life Fellow, IEEE" 91e58c39608c6eb97b314b0c581ddaf7daac075e,Pixel-wise Ear Detection with Convolutional Encoder-Decoder Networks,"Pixel-wise Ear Detection with Convolutional Encoder-Decoder Networks ˇZiga Emerˇsiˇc 1, Luka Lan Gabriel 2, Vitomir ˇStruc 3 and Peter Peer 1" 9120d59f2ca86954b45d254cae1409cb0806d9c7,DenseFuse: A Fusion Approach to Infrared and Visible Images,"DenseFuse: A Fusion Approach to Infrared and Visible Images Hui Li and Xiao-Jun Wu" 916c816f16e4934e41f09a3ff81a10e5fc4bb459,Multicalibration: Calibration for the (Computationally-Identifiable) Masses,"Multicalibration: Calibration for the (Computationally-Identifiable) Masses ´Ursula H´ebert-Johnson 1 Michael P. Kim 1 Omer Reingold 1 Guy N. Rothblum 2" 91dda4183c6118de8195e07a623962dbd22cc34e,Representing local binary descriptors with BossaNova for visual recognition,"Representing Local Binary Descriptors with BossaNova for Visual Recognition Carlos Caetano†, Sandra Avila†, Silvio Guimarães‡, Arnaldo de A. Araújo† Federal University of Minas Gerais, NPDI Lab — DCC/UFMG, Minas Gerais, Brazil Pontifical Catholic University of Minas Gerais, VIPLAB — ICEI/PUC Minas, Minas Gerais, Brazil {carlos.caetano," 911505a4242da555c6828509d1b47ba7854abb7a,Improved Active Shape Model for Facial Feature Localization,"IMPROVED ACTIVE SHAPE MODEL FOR FACIAL FEATURE LOCALIZATION Hui-Yu Huang and Shih-Hang Hsu National Formosa University, Taiwan Email:" 9117fd5695582961a456bd72b157d4386ca6a174,Facial Expression,"Facial Expression n Recognition Using Dee ep Neural Networks Junnan Li and Edmund Y. Lam Departm ment of Electrical and Electronic Engineering he University of Hong Kong, Pokfulam, Hong Kong" 9168b36568b8abffab5b9de029be5941f673dca2,Improving 3 D Facial Action Unit Detection with Intrinsic Normalization,"YUDIN, ET AL.: IMPROVING 3D AU DETECTION WITH INTRINSIC NORMALIZATION Improving 3D Facial Action Unit Detection with Intrinsic Normalization Geometric Image Processing Lab Technion - Israel Institute of Technology Technion City, Haifa, Israel Eric Yudin Aaron Wetzler Matan Sela Ron Kimmel" 910da5e0afef96c8acca3c6a4314a9ab5121b1e4,Détection d'obstacles multi-capteurs supervisée par stéréovision. (Multi-sensor road obstacle deetection controled by stereovision),"Détection d’obstacles multi-capteurs supervisée par stéréovision Mathias Perrollaz To cite this version: Mathias Perrollaz. Détection d’obstacles multi-capteurs supervisée par stéréovision. Vision par ordi- nateur et reconnaissance de formes [cs.CV]. Université Pierre et Marie Curie - Paris VI, 2008. Français. HAL Id: tel-00656864 https://tel.archives-ouvertes.fr/tel-00656864 Submitted on 5 Jan 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 916ca7000c022fbd97ea15cc0094f0e53c408b56,Spontaneous and Non-Spontaneous 3D Facial Expression Recognition Using a Statistical Model with Global and Local Constraints,"SPONTANEOUS AND NON-SPONTANEOUS 3D FACIAL EXPRESSION RECOGNITION USING A STATISTICAL MODEL WITH GLOBAL AND LOCAL CONSTRAINTS" 91ead35d1d2ff2ea7cf35d15b14996471404f68d,Combining and Steganography of 3D Face Textures,"Combining and Steganography of 3D Face Textures Mohsen Moradi and Mohammad-Reza Rafsanjani-Sadeghi" 91f67f69597a52b905c748a15db427c61f352073,Scale-Aware Pixelwise Object Proposal Networks,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Scale-aware Pixel-wise Object Proposal Networks Zequn Jie, Xiaodan Liang, Jiashi Feng, Wen Feng Lu, Eng Hock Francis Tay, Shuicheng Yan essential proposal" 91b0081a348d182d616f74a0c9fb80d56acf4198,Exploiting photographic style for category-level image classification by generalizing the spatial pyramid,"Exploiting Photographic Style for Category-Level Image Classification by Generalizing the Spatial Pyramid Jan C. van Gemert Puzzual Oudeschans 18 011LA, Amsterdam, The Netherlands" 91b1a59b9e0e7f4db0828bf36654b84ba53b0557,Simultaneous Hallucination and Recognition of Low-Resolution Faces Based on Singular Value Decomposition,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI > REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < Simultaneous Hallucination and Recognition of Low-Resolution Faces Based on Singular Value Decomposition Muwei Jian, Kin-Man Lam*, Senior Member, IEEE (SVD) for performing both" 91a5897565818631a32ce4edae5548d2baf99d77,APPROACH TO RECOGNIZING FACES UNDER VARYING POSE GIVEN A SINGLE-VIEW,"The Pennsylvania State University The Graduate School College of Engineering A PATCH CORRESPONDENCE APPROACH TO RECOGNIZING FACES UNDER VARYING POSE GIVEN A SINGLE-VIEW GALLERY A Thesis in Electrical Engineering Michael Charles Ferster II © 2012 Michael Charles Ferster II Submitted in Partial Fulfillment of the Requirements for the Degree of Master of Science August 2012" 91bdc706ad1d7b246e457870a7eb8caff87ec05a,Face Recognition Using Holistic Based Approach,"International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 4, Issue 7, July 2014) Face Recognition Using Holistic Based Approach 1Research Scholar, 2Professor, Department of Information Science and Engineering, SDM CET, Dharwad Vandana S. Bhat1, Dr. Jagadeesh D. Pujari2" 2057837e059a1dde8c6c4c0587e652b79c04780a,Learning to Recognize Novel Objects in One Shot through Human-Robot Interactions in Natural Language Dialogues,"Learning to Recognize Novel Objects in One Shot through Human-Robot Interactions in Natural Language Dialogues Thomas Williams Matthias Scheutz Evan Krause HRI Laboratory Tufts University 00 Boston Ave Medford, MA 02155, USA Michael Zillich Inst. for Automation and Control Technical University Vienna Gusshausstr 27-29/E376 040 Vienna, Austria HRI Laboratory Tufts University 00 Boston Ave HRI Laboratory Tufts University 00 Boston Ave" 20717f1cb12ab208458c0f2505b237d8f061f97a,Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder,"Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder Xi Zhang, Yanwei Fu, Andi Zang, Leonid Sigal, Gady Agam" 204db062f4952ce446cbb28fbc40d4a7f4424b03,Systematic evaluation of super-resolution using classification,"SYSTEMATIC EVALUATION OF SUPER-RESOLUTION USING CLASSIFICATION Vinay P. Namboodiri1, Vincent De Smet1 and Luc Van Gool1,2 ESAT-PSI/IBBT, K.U.Leuven, Belgium Computer Vision Laboratory, BIWI/ETH Z¨urich, Switzerland" 20c71ee8275969a7df881de69b8d8baf88f1d120,A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM,"A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM H. W. Yu and B. H. Lee" 20a0b23741824a17c577376fdd0cf40101af5880,Learning to Track for Spatio-Temporal Action Localization,"Learning to track for spatio-temporal action localization Philippe Weinzaepfela Zaid Harchaouia,b NYU Inria∗ Cordelia Schmida" 20f9a09defe5b02b98c464ca6df36b3b6358f60b,The State-of-the-Art in Visual Object Tracking,Volume 36 Number 3 September 2012 2049ca79ce94ddfe0cc3d39bf770f580a740f3ac,Activity analysis : finding explanations for sets of events,ActivityAnalysis:FindingExplanationsforSetsofEventsbyDimaJamalAlDamenSubmittedinaccordancewiththerequirementsforthedegreeofDoctorofPhilosophy.TheUniversityofLeedsSchoolofComputingSeptember2009Thecandidateconfirmsthattheworksubmittedisherownandthattheappropriatecredithasbeengivenwherereferencehasbeenmadetotheworkofothers.Thiscopyhasbeensuppliedontheunderstandingthatitiscopyrightmaterialandthatnoquotationfromthethesismaybepublishedwithoutproperacknowledgement. 20928315086a49e0cdea0ec66f2e78e9c564f794,Person Detection for Indoor Videosurveillance Using Spatio-temporal Integral Features,"Person Detection for Indoor Videosurveillance using Spatio-Temporal Integral Features Adrien Descamps1, Cyril Carincotte2, and Bernard Gosselin1 TCTS Lab, University of Mons, Mons, Belgium Multitel ASBL, 2 Rue Pierre et Marie Curie, Mons, Belgium" 20111924fbf616a13d37823cd8712a9c6b458cd6,Linear Regression Line based Partial Face Recognition,"International Journal of Computer Applications (0975 – 8887) Volume 130 – No.11, November2015 Linear Regression Line based Partial Face Recognition Naveena M. Department of Studies in Computer Science, Manasagagothri, Mysore. G. Hemantha Kumar Department of Studies in Computer Science, Manasagagothri, Mysore. P. Nagabhushan Department of Studies in Computer Science, Manasagagothri, Mysore. images. In" 20500887735f3fb87ae3ec351e2115e89c0f663e,Multiview random forest of local experts combining RGB and LIDAR data for pedestrian detection,"Multiview Random Forest of Local Experts Combining RGB and LIDAR data for Pedestrian Detection Alejandro Gonz´alez1,2, Gabriel Villalonga1,2, Jiaolong Xu2, David V´azquez1,2, Jaume Amores2, Antonio M. L´opez1,2 {agalzate,gvillalonga,jiaolong,dvazquez,jaume,antonio} Autonomous University of Barcelona, 2Computer Vision Center" 20a6de85d7d5f445dfaba90ab2e33879142023fc,Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice,"THIS WORK HAS BEEN SUBMITTED TO THE IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS. Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice Amir Rasouli and John K. Tsotsos" 20b8a76e988e796f0f225876a69842f6839e4c98,Real-time Gender Recognition for Uncontrolled Environment of Real-life Images,"REAL-TIME GENDER RECOGNITION FOR UNCONTROLLED ENVIRONMENT OF REAL-LIFE IMAGES Duan-Yu Chen and Kuan-Yi Lin Department of Electrical Engineering, Yuan-Ze University, Taiwan Keywords: Gender recognition, Uncontrolled environment, Real-life images." 20e903faf8e2e656a89d983541b15f2e0d614eeb,Image to Image Translation for Domain Adaptation,"Image to Image Translation for Domain Adaptation Zak Murez1,2 Soheil Kolouri2 David Kriegman1 Ravi Ramamoorthi1 Kyungnam Kim2 University of California, San Diego; 2 HRL Laboratories, LLC;" 209324c152fa8fab9f3553ccb62b693b5b10fb4d,CROWDSOURCED VISUAL KNOWLEDGE REPRESENTATIONS A THESIS SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTERS OF SCIENCE,"CROWDSOURCED VISUAL KNOWLEDGE REPRESENTATIONS VISUAL GENOME A THESIS SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTERS OF SCIENCE Ranjay Krishna March 2016" 20e504782951e0c2979d9aec88c76334f7505393,Robust LSTM-Autoencoders for Face De-Occlusion in the Wild,"Robust LSTM-Autoencoders for Face De-Occlusion in the Wild Fang Zhao, Jiashi Feng, Jian Zhao, Wenhan Yang, Shuicheng Yan" 203abfcc3df8de6606cf34fa32cf225627f52d00,Learning Robot Vision for Assisted Living,"Robotic Vision: Technologies for Machine Learning and Vision Applications José García-Rodríguez University of Alicante, Spain Miguel Cazorla University of Alicante, Spain" 20823c6b9798094048bf4d59b26f5b92723c9b71,Color Face Recognition Using Quaternion PCA,"Color Face Recognition Using Quaternion PCA Emad S. Jaha1 and Lahouari Ghouti2 King Abdulaziz University. Jeddah. Saudi Arabia.1 King Fahd University of Petroleum and Minerals. Dhahran 31261. Saudi Arabia. Keywords: Biometric Systems, Face Recognition, Color Face Recognition, Principal Component Analysis (PCA), Hy- percomplex PCA." 205672cd9986044a03483058d9462f52c2cfc543,A Practical Guide to CNNs and Fisher Vectors for Image Instance Retrieval,"A practical guide to CNNs and Fisher Vectors for image instance retrieval Vijay Chandrasekhar∗,1, Jie Lin∗,1, Olivier Mor`ere∗,1,2 Hanlin Goh1, Antoine Veillard2 Institute for Infocomm Research (A*STAR), 1 Fusionolopis Way, #21-01, 138632, Singapore Universit´e Pierre et Marie Curie, 4 place Jussieu, 75252, Paris, France" 20a432a065a06f088d96965f43d0055675f0a6c1,The E ff ects of Regularization on Learning Facial Expressions with Convolutional Neural Networks,"In: Proc. of the 25th Int. Conference on Artificial Neural Networks (ICANN) Part II, LNCS 9887, pp. 80-87, Barcelona, Spain, September 2016 The final publication is available at Springer via http://dx.doi.org//10.1007/978-3-319-44781-0_10 The Effects of Regularization on Learning Facial Expressions with Convolutional Neural Networks Tobias Hinz, Pablo Barros, and Stefan Wermter University of Hamburg Department of Computer Science, Vogt-Koelln-Strasse 30, 22527 Hamburg, Germany http://www.informatik.uni-hamburg.de/WTM" 208e903211ddc62b997afb5a1bd3c2c43e0e69ee,Real-Time Action Detection in Video Surveillance using Sub-Action Descriptor with Multi-CNN,"Real-Time Action Detection in Video Surveillance using Sub-Action Descriptor with Multi-CNN Cheng-Bin Jin*, Shengzhe Li†, and Hakil Kim* *Inha University, Incheon, Korea Visionin Inc., Incheon, Korea" 202d8d93b7b747cdbd6e24e5a919640f8d16298a,Face Classification via Sparse Approximation,"Face Classification via Sparse Approximation Elena Battini S˝onmez1, Bulent Sankur2 and Songul Albayrak3 Computer Science Department, Bilgi University, Dolapdere, Istanbul, TR Electric and Electronic Engineering Department, Bo¯gazici University, Istanbul, TR Computer Engineering Department, Yıldız Teknik University, Istanbul, TR" 205b34b6035aa7b23d89f1aed2850b1d3780de35,Log-domain polynomial filters for illumination-robust face recognition,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE Shenzhen Key Lab. of Information Sci&Tech, ♯Nagaoka University of Technology, Japan RECOGNITION . INTRODUCTION" 20cdf98173bb99bb59c5a1d387f9a45d3f7755ae,CNN-based thermal infrared person detection by domain adaptation,"CNN-based thermal infrared person detection by domain adaptation Christian Herrmanna,b, Miriam Rufa, and J¨urgen Beyerera,b Vision and Fusion Lab, Karlsruhe Institute of Technology KIT, Karlsruhe, Germany Fraunhofer IOSB, Karlsruhe, Germany" 2069f85e9efcd429a3d68c918ebd8c13aefb46cb,Measuring External Face Appearance for Face Classification,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 20a3ce81e7ddc1a121f4b13e439c4cbfb01adfba,Sparse-MVRVMs Tree for Fast and Accurate Head Pose Estimation in the Wild,"Sparse-MVRVMs Tree for Fast and Accurate Head Pose Estimation in the Wild Mohamed Selim, Alain Pagani, and Didier Stricker Augmented Vision Research Group, German Research Center for Artificial Intelligence (DFKI), Tripstaddterstr. 122, 67663 Kaiserslautern, Germany Technical University of Kaiserslautern http://www.av.dfki.de" 200f1a55c5974c4cac243bed3131ac5a9338840d,Human Computation for Object Detection,"May 09, 2013 TR Number: UCSC-SOE-15-03 Human Computation for Object Detection Rajan Vaish1, Sascha T. Ishikawa1, Sheng Lundquist2, Reid Porter2, James Davis1 University of California at Santa Cruz1, Los Alamos National Laboratory2 {rvaish, stishika, {slundquist," 20e783a2df0486cd1c8b6b59fc76220f5718b304,Stereo-based Pedestrian Detection Using Two-stage Classifiers,"4-26 MVA2011 IAPR Conference on Machine Vision Applications, June 13-15, 2011, Nara, JAPAN Stereo-based Pedestrian Detection Using Two-stage Classifiers Manabu Nishiyama, Akihito Seki, Tomoki Watanabe Corporate Research and Development Center, Toshiba Corporation , Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan" 203fcd66c043e44fefd783b8f54105f0a577fc25,Analyzing Content and Customer Engagement in Social Media with Deep Learning,"Analyzing Content and Customer Engagement in Social Media with Deep Learning (The bulk of this work was done by a student.)" 2056ba48e687d619c0ce69d0be323d48c5b90701,Similarity Mapping with Enhanced Siamese Network for Multi-Object Tracking.,"Similarity Mapping with Enhanced Siamese Network for Multi-Object Tracking Minyoung Kim Cupertino, CA Stefano Alletto Modena, MO Panasonic Silicon Valley Laboratory University of Modena and Reggio Emilia Panasonic Silicon Valley Laboratory Luca Rigazio Cupertino, CA" 20260d36506911e04ad1efed1e60b06bfc178d52,Deep 3D face identification,"Deep 3D Face Identification Donghyun Kim Matthias Hernandez Jongmoo Choi G´erard Medioni USC Institute for Robotics and Intelligent Systems (IRIS) Unversity of Southern California {kim207, mthernan, jongmooc," 2067ab35379381f05acaa7406a30d0ee02c0b8cc,Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval,"Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval Xuefei Zhe, Shifeng Chen, and Hong Yan, Fellow, IEEE" 20100323ec5c32ae91add8e866d891a78f1a2bbe,Unsupervised Object Discovery and Tracking in Video Collections,"Unsupervised Object Discovery and Tracking in Video Collections Suha Kwak1,∗ Minsu Cho1,∗ Ivan Laptev1,∗ Jean Ponce2,∗ Cordelia Schmid1,† Inria ´Ecole Normale Sup´erieure / PSL Research University" 202cbc83c22a9c7b3d878cc1bed1c5cf152eb6fb,Learning Embeddings for Product Visual Search with Triplet Loss and Online Sampling,"Learning Embeddings for Product Visual Search with Triplet Loss and Online Sampling Eric Dodds, Huy Nguyen, Simao Herdade, Jack Culpepper, Andrew Kae, Pierre Garrigues {eric.mcvoy.dodds, huyng, sherdade, jackcul, andrewkae, Yahoo Research" 202a923504ea81e94c06a81581539b893b461ee5,YELP : Masking Sound-based Opportunistic A acks in Zero-E ort,"YELP: Masking Sound-based Opportunistic A(cid:130)acks in Zero-E(cid:128)ort Deauthentication University of Alabama at Birmingham University of Alabama at Birmingham University of Alabama at Birmingham Prakash Shrestha S Abhishek Anand Nitesh Saxena" 20f272f4bdf562aa8b4dae84b67cfafa34a00738,Periocular biometrics: An emerging technology for unconstrained scenarios,"Periocular Biometrics: An Emerging Technology for Unconstrained Scenarios Gil Santos and Hugo Proenc¸a IT - Instituto de Telecomunicac¸ ˜oes Universidade da Beira Interior Covilh˜a, Portugal Email:" 20e64f44ce2977a4dc5099fce6f73842613f0865,"Ridge Regression, Hubness, and Zero-Shot Learning","Ridge Regression, Hubness, and Zero-Shot Learning(cid:63) Yutaro Shigeto1, Ikumi Suzuki2, Kazuo Hara3, Masashi Shimbo1, and Yuji Matsumoto1 Nara Institute of Science and Technology, Ikoma, Nara, Japan The Institute of Statistical Mathematics, Tachikawa, Tokyo, Japan National Institute of Genetics, Mishima, Shizuoka, Japan" 20e210bb6b1d3e637e2b2674aeead3fad8c2c70e,Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer,"Published as a conference paper at ICLR 2017 PAYING MORE ATTENTION TO ATTENTION: IMPROVING THE PERFORMANCE OF CONVOLUTIONAL NEURAL NETWORKS VIA ATTENTION TRANSFER Sergey Zagoruyko, Nikos Komodakis Universit´e Paris-Est, ´Ecole des Ponts ParisTech Paris, France" 20eaa3ebe2b6e1aff7c4585733c9fb0cfc941919,Image similarity using Deep CNN and Curriculum Learning,"Image similarity using Deep CNN and Curriculum Learning Srikar Appalaraju Vineet Chaoji Amazon Development Centre (India) Pvt. Ltd. Image similarity involves fetching similar looking images given a reference image. Our solution called SimNet, is a deep Siamese network which is trained on pairs of positive and negative images using a novel online pair mining strategy inspired y Curriculum learning. We also created a multi-scale CNN, where the final image embedding is a joint representation of top as well as lower layer embedding’s. We go on to show that this multi-scale Siamese network is better at capturing fine grained image similarities than traditional CNN’s. Keywords — Multi-scale CNN, Siamese network, Curriculum learning, Transfer learning. I. INTRODUCTION The ability to find a similar set of images for a given image has multiple uses-cases from visual search to duplicate product detection to domain specific image lustering. Our approach called SimNet, tries to identify similar images for a new image using multi-scale Siamese network. Fig. 1 shows examples of image samples from CIFAR10 [39] on which SimNet is trained on. Fig. 1 examples of CIFAR 10 images. Task is - given a new image ut belonging to one of the 10 categories, find similar set of images." 20c59a55795eaa4f2629cc83fb556dc8c5bcfc1f,Modeling and visual recognition of human actions and interactions,"Modeling and visual recognition of human actions and interactions Ivan Laptev To cite this version: Ivan Laptev. Modeling and visual recognition of human actions and interactions. Computer Vision and Pattern Recognition [cs.CV]. Ecole Normale Supérieure de Paris - ENS Paris, 2013. HAL Id: tel-01064540 https://tel.archives-ouvertes.fr/tel-01064540 Submitted on 16 Sep 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 2084e54505cfe4fd81005167b1b11d10b5f837d1,Person Re-Identification by Discriminative Selection in Video,"Person Re-Identification by Discriminative Selection in Video Ranking Wang, T; Gong, S; Zhu, X; Wang, S •(cid:9)“The final publication is available at http://link.springer.com/chapter/10.1007%2F978-3-319- 0593-2_45” For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle/123456789/11432 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 200f68f899f0bf72dd2c49ba2b4a5027e0291531,Efficient Activity Detection in Untrimmed Video with Max-Subgraph Search,"Efficient Activity Detection in Untrimmed Video with Max-Subgraph Search Chao Yeh Chen and Kristen Grauman" 205af28b4fcd6b569d0241bb6b255edb325965a4,Facial expression recognition and tracking for intelligent human-robot interaction,"Intel Serv Robotics (2008) 1:143–157 DOI 10.1007/s11370-007-0014-z SPECIAL ISSUE Facial expression recognition and tracking for intelligent human-robot interaction Y. Yang · S. S. Ge · T. H. Lee · C. Wang Received: 27 June 2007 / Accepted: 6 December 2007 / Published online: 23 January 2008 © Springer-Verlag 2008" 2059d2fecfa61ddc648be61c0cbc9bc1ad8a9f5b,Co-Localization of Audio Sources in Images Using Binaural Features and Locally-Linear Regression,"TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 23, NO. 4, APRIL 2015 Co-Localization of Audio Sources in Images Using Binaural Features and Locally-Linear Regression Antoine Deleforge∗ Radu Horaud∗ Yoav Y. Schechner‡ Laurent Girin∗† INRIA Grenoble Rhˆone-Alpes, Montbonnot Saint-Martin, France Univ. Grenoble Alpes, GIPSA-Lab, France Dept. Electrical Eng., Technion-Israel Inst. of Technology, Haifa, Israel" c4dcf41506c23aa45c33a0a5e51b5b9f8990e8ad,Understanding Activity : Learning the Language of Action,"Understanding Activity: Learning the Language of Action Randal Nelson and Yiannis Aloimonos Univ. of Rochester and Maryland .1 Overview Understanding observed activity is an important problem, both from the standpoint of practical applications, nd as a central issue in attempting to describe the phenomenon of intelligence. On the practical side, there are a large number of applications that would benefit from improved machine ability to analyze activity. The most prominent are various surveillance scenarios. The current emphasis on homeland security has brought this issue to the forefront, and resulted in considerable work on mostly low- level detection schemes. There are also applications in medical diagnosis and household assistants that, in the long run, may be even more important. In addition, there are numerous scientific projects, ranging from monitoring of weather conditions to observation of animal behavior that would be facilitated by automatic understanding of activity. From a scientific standpoint, understanding activity" c46ae522b8cedb68339dbb8fd9c1fa3b2d676f8e,Kinship Verification,"Kinship Verification Kanchan Pardeshi , Vrushali Pawar, Snehal Sonawane , Kavita Wagh KKWIEER, Nashik images" c46d44143d1e0cbab34f120d65c3a869101c7622,DecomposeMe: Simplifying ConvNets for End-to-End Learning,"DecomposeMe: Simplifying ConvNets for End-to-End Learning Jose M. Alvarez and Lars Petersson NICTA / Data61, Canberra, Australia" c4a024d73902462275879fa6133bff22134fcc7e,When crowds hold privileges: Bayesian unsupervised representation learning with oracle constraints,"When crowds hold privileges: Bayesian unsupervised representation learning with oracle constraints Theofanis Karaletsos Computational Biology Program, Sloan Kettering Institute 275 York Avenue, New York, USA Serge Belongie Cornell Tech 11 Eighth Avenue #302, New York, USA Gunnar R¨atsch Computational Biology Program, Sloan Kettering Institute 275 York Avenue, New York, USA" c45183ec95f89aff793a2629a0520006b4153d6a,Entropy-based template analysis in face biometric identification systems,"SIViP (2013) 7:493–505 DOI 10.1007/s11760-013-0451-4 ORIGINAL PAPER Entropy-based template analysis in face biometric identification systems Maria De Marsico · Michele Nappi · Daniel Riccio · Genoveffa Tortora Received: 19 December 2011 / Revised: 7 June 2012 / Accepted: 10 October 2012 / Published online: 17 March 2013 © Springer-Verlag London 2013" c4f1fcd0a5cdaad8b920ee8188a8557b6086c1a4,The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization,"Int J Comput Vis (2014) 108:3–29 DOI 10.1007/s11263-014-0698-4 The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization Steve Branson · Grant Van Horn · Catherine Wah · Pietro Perona · Serge Belongie Received: 7 March 2013 / Accepted: 8 January 2014 / Published online: 20 February 2014 © Springer Science+Business Media New York 2014" c4baa3d2fe702d3e96c500274f7fd9e63f8b3d6d,Pedestrian Detection Optimization Based on Random Filtering,"Pedestrian Detection Optimization Based on Random Filtering Victor Hugo Cunha de Melo, Samir Le˜ao, William Robson Schwartz Universidade Federal de Minas Gerais Department of Computer Science Belo Horizonte, Minas Gerais, Brazil Email: {victorhcmelo, samirleao," c4b3a1cf8842da8c64f7abf4a352583d5fd9762c,Gait recognition using sub-vector quantisation technique,"Int. J. Machine Intelligence and Sensory Signal Processing, Vol. 1, No. 1, 2013 Gait recognition using sub-vector quantisation technique Neel K. Pandey* Department of Electrical Engineering and Trades, Faculty of Engineering and Trades, Manukau Institute of Technology, Private Bag 94006, Manukau 2241, Auckland, New Zealand E-mail: *Corresponding author Waleed H. Abdulla and Zoran Salcic Department of Electrical and Computer Engineering, The University of Auckland, Private Bag 92019, Auckland Mail Centre, Auckland 1142, New Zealand E-mail: E-mail:" c4d3033356066ef8133f03f4060bb8cad842918f,Inference of quantized neural networks on heterogeneous all-programmable devices,"Inference of Quantized Neural Networks on Heterogeneous All-Programmable Devices Thomas B. Preußer Marie Skłodowska-Curie Fellow Xilinx Research Labs Giulio Gambardella Xilinx Research Labs Dublin, Ireland Nicholas Fraser Xilinx Research Labs Dublin, Ireland Michaela Blott Xilinx Research Labs Dublin, Ireland Dublin, Ireland" c4827fe8002ea61a2748b78369afe3a0747d1a0c,Towards Optimal Naive Bayes Nearest Neighbor,"Towards Optimal Naive Bayes Nearest Neighbor R´egis Behmo1, Paul Marcombes1,2, Arnak Dalalyan2, and V´eronique Prinet1 NLPR / LIAMA, Institute of Automation, Chinese Academy of Sciences(cid:2) IMAGINE, LIGM, Universit´e Paris-Est" c43490eb0a3ce18fb2326ef1d0828664b60e73e2,Is This Car Looking at You? How Anthropomorphism Predicts Fusiform Face Area Activation when Seeing Cars,"RESEARCH ARTICLE Is This Car Looking at You? How Anthropomorphism Predicts Fusiform Face Area Activation when Seeing Cars Simone Ku¨ hn1*, Timothy R. Brick1, Barbara C. N. Mu¨ ller2,3, Ju¨ rgen Gallinat4,5 . Center for Lifespan Psychology, Max Planck Institute for Human Development, Lentzeallee 94, 14195, Berlin, Germany, 2. Behavioural Science Institute, Radboud University of Nijmegen, P. O. Box 9104, 6500 HE, Nijmegen, Netherlands, 3. Department of Psychology, Ludwig-Maximilian University, Leopoldstrasse 13, 80802, Mu¨ nchen, Germany, 4. Clinic for Psychiatry and Psychotherapy, Charite´ University Medicine, St. Hedwig-Krankenhaus, Große Hamburger Straße 5–11, 10115, Berlin, Germany, 5. Clinic and Policlinic for Psychiatry and Psychotherapy, University Clinic Hamburg-Eppendorf, Martinistraße 52, 20246, Hamburg, Germany" c48ec3d14a223346bb50002176e9a04bfb385cc7,Fuzzy Modelling for Human Dynamics Based on Online Social Networks,"Article Fuzzy Modelling for Human Dynamics Based on Online Social Networks Jesus Cuenca-Jara , Fernando Terroso-Saenz * ID , Mercedes Valdes-Vela and Antonio F. Skarmeta Department of Communications and Information Engineering, University of Murcia, Murcia 30100, Spain; (J.C.-J.); (M.V.-V.); (A.F.S.) * Correspondence: Tel.: +34-868-884-644 Received: 30 June 2017; Accepted: 21 August 2017; Published: 24 August 2017" c48c452f26e54f37faaf025ca3c76b33ce3e40f6,Incremental learning of latent structural SVM for weakly supervised image classification,"INCREMENTAL LEARNING OF LATENT STRUCTURAL SVM FOR WEAKLY SUPERVISED IMAGE CLASSIFICATION Thibaut Durand (1) Nicolas Thome (1) Matthieu Cord (1) David Picard (2) (1) Sorbonne Universit´es, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005, Paris, France (2) ETIS/ENSEA, University of Cergy-Pontoise, CNRS, UMR 8051, France" c4f3375dab1886f37f542d998e61d8c30a927682,BEYOND SHARED HIERARCHIES: DEEP MULTITASK LEARNING THROUGH SOFT LAYER ORDERING,"Under review as a conference paper at ICLR 2018 BEYOND SHARED HIERARCHIES: DEEP MULTITASK LEARNING THROUGH SOFT LAYER ORDERING Anonymous authors Paper under double-blind review" c44e2fa02f0b578a2cc92795fe6a4c578f65dc97,A Method for Copyright Protection of Line Drawings,"A Method for Copyright Protection of Line Drawings Weihan Sun*, Koichi Kise* * Graduate School of Engineering, Osaka Prefecture University, Osaka E-mail:" c4c4e5ff454584ae6a68d25b36bfc860e9a893a0,"Real-Time Facial Recognition System—Design, Implementation and Validation","Journal of Signal Processing Theory and Applications (2013) 1: 1-18 doi:10.7726/jspta.2013.1001 Research Article Real-Time Facial Recognition System—Design, Implementation and Validation M. Meenakshi* Received 29 August 2012; Published online November 10, 2012 © The author(s) 2012. Published with open access at uscip.org" c48bde5b9ff17b708ab3e4f7c62a31a46c77f2f1,Nested sparse quantization for efficient feature coding,"Nested Sparse Quantization for Ef‌f‌icient Feature Coding Xavier Boix1(cid:63), Gemma Roig1(cid:63), and Luc Van Gool1,2 (cid:63)(cid:63) Computer Vision Lab, ETH Zurich, Switzerland, KU Leuven, Belgium" c4fed8f23bc9ff1ffc27edb12970963ecf2dead9,Statistical Models and Optimization Algorithms for High-Dimensional Computer Vision Problems, c4f632a1b6faa43c217e63c58a4764511104c303,Extracting Pathlets FromWeak Tracking Data,"Extracting Pathlets From Weak Tracking Data∗ Kevin Streib James W. Davis Dept. of Computer Science and Engineering Ohio State University, Columbus, OH 43210" c42a8969cd76e9f54d43f7f4dd8f9b08da566c5f,0 Towards Unconstrained Face Recognition Using 3 D Face Model,"Towards Unconstrained Face Recognition Using 3D Face Model Zahid Riaz1, M. Saquib Sarfraz2 and Michael Beetz1 Intelligent Autonomous Systems (IAS), Technical University of Munich, Garching Computer Vision Research Group, COMSATS Institute of Information Technology, Lahore Germany Pakistan . Introduction Over the last couple of decades, many commercial systems are available to identify human faces. However, face recognition is still an outstanding challenge against different kinds of real world variations especially facial poses, non-uniform lightings and facial expressions. Meanwhile the face recognition technology has extended its role from biometrics and security pplications to human robot interaction (HRI). Person identity is one of the key tasks while interacting with intelligent machines/robots, exploiting the non intrusive system security nd authentication of the human interacting with the system. This capability further helps machines to learn person dependent traits and interaction behavior to utilize this knowledge for tasks manipulation. In such scenarios acquired face images contain large variations which demands an unconstrained face recognition system. Fig. 1. Biometric analysis of past few years has been shown in figure showing the" 8ec7194952ee9e7cf383b1a1b0aeccaed5b7daaa,Constrained multi-target tracking for team sports activities,"Gade and Moeslund IPSJ Transactions on Computer Vision and Applications (2018) 10:2 DOI 10.1186/s41074-017-0038-z IPSJ Transactions on Computer Vision and Applications SYSTEMS PAPER Open Access Constrained multi-target tracking for team sports activities Rikke Gade* nd Thomas B. Moeslund" 8edb2219370a86c4277549813d36a6c139503fb4,Facial feature units ’ localization using horizontal information of most significant bit planes,"Journal of Engineering and Technology Research Vol. 3(14), pp. 381-387, 22 December, 2011 Available online at http:// www.academicjournals.org/JETR DOI: 10.5897/JETR11.068 ISSN 2006-9790 ©2011 Academic Journals Full Length Research Paper Facial feature units’ localization using horizontal information of most significant bit planes Asif Khan1*, Khalilullah1, Ihtesham-Ul-Islam1 and Mohammad A. U. Khan2 FAST National University of Computer and Emerging Sciences, Peshawar, Pakistan. Effat University, Jeddah, Saudi Arabia. Accepted 8 November, 2011 We present here an approach to find the exact position of some feature units related to human face images. We use the horizontal information in most significant bit planes of images to accomplish the task. Finding location of facial feature units is of importance as most human face recognition pproaches take it as initial point. The prominent feature units in a face are eyes, nostrils and lips which re usually oriented in horizontal direction and visually significant in face image. The majority of the visually significant data in image can be extracted using higher order bits of that image. Our four step method consists of bit planes processing, separating horizontal information using wavelet transform (WT), binary thresholding and appropriate combination of Dilation and Erosion. The proposed method shows high accuracy in the presence of all real world situations like various gestures, illumination" 8eed02b44383abf697b39721f369d1ff38386901,Coin-Tracking - Double-Sided Tracking of Flat Objects,"Master Thesis Czech Technical University in Prague Faculty of Electrical Engineering Department of Cybernetics Coin-Tracking - Double-Sided Tracking of Flat Objects Jonáš Šerých Supervisor: Prof. Ing. Jiří Matas, Ph.D. Field of study: Computer Vision and Image Processing January 2018" 8e36100cb144685c26e46ad034c524b830b8b2f2,Modeling Facial Geometry using Compositional,"Modeling Facial Geometry using Compositional VAEs Timur Bagautdinov∗1, Chenglei Wu2, Jason Saragih2, Pascal Fua1, Yaser Sheikh2 ´Ecole Polytechnique F´ed´erale de Lausanne Facebook Reality Labs, Pittsburgh" 8ef484990214b80dd0e02de09d8d65906f4daf6a,Face Authentication Using One-Class Support Vector Machines,"Face Authentication Using One-Class Support Vector Machines Manuele Bicego1,(cid:1), Enrico Grosso1, and Massimo Tistarelli2 DEIR, University of Sassari, via Torre Tonda 34, 07100 Sassari, Italy Phone +39 079 2017321 DAP, University of Sassari, piazza Duomo 6, 07041 Alghero (SS), Italy" 8e112ad656ff90720ae609841bd0fcb2caa90d65,"""Show Me the Cup"": Reference with Continuous Representations",[cs.CL] 28 Jun 2016 8eabd39cf43596e56f377aa26f985ef20f0aeb4e,On the Recent Use of Local Binary Patterns for Face Authentication,"INTERNATIONAL JOURNAL OF IMAGE AND VIDEO PROCESSING, SPECIAL ISSUE ON FACIAL IMAGE PROCESSING On the Recent Use of Local Binary Patterns for Face Authentication S´ebastien Marcel, Yann Rodriguez and Guillaume Heusch" 8e33183a0ed7141aa4fa9d87ef3be334727c76c0,Robustness of Face Recognition to Image Manipulations,"– COS429 Written Report, Fall 2017 – Robustness of Face Recognition to Image Manipulations Cathy Chen (cc27), Zachary Liu (zsliu), and Lindy Zeng (lindy) . Motivation We can often recognize pictures of people we know even if the image has low resolution or obscures part of the face, if the camera angle resulted in a distorted image of the subject’s face, or if the subject has aged or put on makeup since we last saw them. Although this is a simple recognition task for a human, when we think about how we accomplish this task, it seems non-trivial for computer lgorithms to recognize faces despite visual changes. Computer facial recognition is relied upon for many application where accuracy is important. Facial recognition systems have applications ranging from airport security and suspect identification to personal device authentication and face tagging [7]. In these real-world applications, the system must continue to recognize images of a person who looks slightly different due to the passage of time, a change in environment, or a difference in clothing. Therefore, we are interested in investigating face recognition algorithms and their robustness to image changes resulting from realistically plausible manipulations. Furthermore, we are curious bout whether the impact of image manipulations on computer algorithms’ face recognition ability mirrors related insights from neuroscience about humans’ face recognition abilities. . Goal In this project, we implement both face recognition algorithms and image manipulations. We then" 8e579a8a43f6af1d66e927a48b89e8296eba63f7,Learning to hash faces using large feature vectors,"Learning to Hash Faces Using Large Feature Vectors Cassio E. dos Santos Jr.∗, Ewa Kijak†, Guillaume Gravier†, William Robson Schwartz∗ Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil IRISA & Inria Rennes (CNRS, Univ. Rennes 1), Campus de Beaulieu, Rennes, France" 8ec7fff88b2e5b49154e6654e5e27f6678ddb7f0,On identification from periocular region utilizing SIFT and SURF,"ON IDENTIFICATION FROM PERIOCULAR REGION UTILIZING SIFT AND SURF Şamil Karahan, 1Adil Karaöz, 1Ömer Faruk Özdemir, 1Ahmet Gökhan Gül, 2Umut Uludağ Department of Computer Engineering, Gebze Institute of Technology, 41400, Gebze, Kocaeli, Turkey TUBITAK BILGEM, 41470, Gebze, Kocaeli, Turkey { samilkarahan, adilkaraoz, farukozdemir24, ahmetgokhangul" 8e378ef01171b33c59c17ff5798f30293fe30686,A system for automatic face analysis based on statistical shape and texture models,"Lehrstuhl f¨ur Mensch-Maschine-Kommunikation der Technischen Universit¨at M¨unchen A System for Automatic Face Analysis Based on Statistical Shape and Texture Models Ronald M¨uller Vollst¨andiger Abdruck der von der Fakult¨at f¨ur Elektrotechnik und Informationstechnik der Technischen Universit¨at M¨unchen zur Erlangung des akademischen Grades eines Doktor-Ingenieurs genehmigten Dissertation Vorsitzender: Prof. Dr. rer. nat. Bernhard Wolf Pr¨ufer der Dissertation: . Prof. Dr.-Ing. habil. Gerhard Rigoll . Prof. Dr.-Ing. habil. Alexander W. Koch Die Dissertation wurde am 28.02.2008 bei der Technischen Universit¨at M¨unchen eingereicht und durch die Fakult¨at f¨ur Elektrotechnik und Informationstechnik m 18.09.2008 angenommen." 8e6957334ab60111fd7e2ae59b008a745223aabe,An incremental learning face recognition system for single sample per person,"An Incremental Learning Face Recognition System for Single Sample Per Person Tao Zhu, Furao Shen and Jinxi Zhao recognition system. In nowadays, most of the existed in- remental learning systems are designed to update the eigenspace of face data as new images arrive [8]. To our knowledge, few of them can automatically decide when to learn new information from an input image. In other words, they need an external observer to tell them how to prevent learning distorted information from a misclassified or non- ideal image. Moreover, few of these methods can be applied in the scenario of single sample per person. In this paper, we mainly focus on the issue of robust incre- mental face recognition under the condition of one training sample per person. Inspired by the Single Image subspace (SIS) approach [9], we propose an incremental learning face recognition system. The goals of the proposed system are: (1) self-adaptively updating and adjusting training samples during learning process; (2) keeping learning new knowledge" 8e7749f635b161558efa3e98a324e88c73e2b18f,Neuroimaging Findings in Au ti sm : A Brief Review,"Türk Psikiyatri Dergisi 2009; Turkish Journal of Psychiatry Neuroimaging Findings in Auti sm: A Brief Review Halime Tuna ULAY1, Aygün ERTUĞRUL2" 8e9ff8224753b22e3b1f8bbe271382d6fdb8ddfa,Scale optimization for full-image-CNN vehicle detection,"Scale Optimization for Full-Image-CNN Vehicle Detection Yang Gao, Shouyan Guo, Kaimin Huang, Jiaxin Chen, Qian Gong, Yang Zou, Tong Bai and Gary Overetta" 8e6526b46a52a18028336a8d026e9d466aa12edf,Moving Poselets: A Discriminative and Interpretable Skeletal Motion Representation for Action Recognition,"Moving Poselets: A Discriminative and Interpretable Skeletal Motion Representation for Action Recognition Lingling Tao and Ren´e Vidal Center for Imaging Science, Johns Hopkins University ltao4," 8e8c511ebc12a093d3f73a4717ec71c32e4dbd49,The use of visual information in the recognition of posed and spontaneous facial expressions.,"The use of visual information in the recognition of posed and spontaneous facial expressions Camille Saumure Marie-Pier Plouffe-Demers Amanda Est ´ephan Daniel Fiset Caroline Blais Department of Psychoeducation and Psychology, Universit ´e du Qu ´ebec en Outaouais, Gatineau, Qu ´ebec, Canada Department of Psychoeducation and Psychology, Universit ´e du Qu ´ebec en Outaouais, Gatineau, Qu ´ebec, Canada Department of Psychoeducation and Psychology, Universit ´e du Qu ´ebec en Outaouais, Gatineau, Qu ´ebec, Canada Department of Psychoeducation and Psychology, Universit ´e du Qu ´ebec en Outaouais, Gatineau, Qu ´ebec, Canada Department of Psychoeducation and Psychology," 8ee50fd3e19729a487f7196b682ccaa2d17aa0df,Improving head and body pose estimation through semi-supervised manifold alignment,"IMPROVING HEAD AND BODY POSE ESTIMATION THROUGH SEMI-SUPERVISED MANIFOLD ALIGNMENT Alexandre Heili(cid:63), Jagannadan Varadarajan†, Bernard Ghanem‡, Narendra Ahuja(cid:63)†, Jean-Marc Odobez(cid:63) (cid:63) Idiap Research Institute, ´Ecole Polytechnique F´ed´erale de Lausanne, Switzerland Advanced Digital Sciences Center, Singapore, (cid:63)† University of Illinois at Urbana-Champaign King Abdullah University of Science and Technology, Saudi Arabia" 8ee62f7d59aa949b4a943453824e03f4ce19e500,Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions,"Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regression Vincent Drouard∗, Radu Horaud∗, Antoine Deleforge†, Sil`eye Ba∗ and Georgios Evangelidis∗ INRIA Grenoble Rhˆone-Alpes, Montbonnot Saint-Martin, France INRIA Rennes Bretagne Atlantique, Rennes, France" 8e36cc33db5aa581cd826e6ba5f830d40d674712,Using Biologically Inspired Features for Face Processing,"Int J Comput Vis (2008) 76: 93–104 DOI 10.1007/s11263-007-0058-8 S H O RT PA P E R Using Biologically Inspired Features for Face Processing Ethan Meyers · Lior Wolf Received: 4 March 2006 / Accepted: 2 April 2007 / Published online: 12 July 2007 © Springer Science+Business Media, LLC 2007" 8ec76d7d4a9abd09f088fb3f7a3351a7fda1fde0,Generative Adversarial Networks to Synthetically Augment Data for Deep Learning based Image Segmentation *,"Proceedings of the OAGM Workshop 2018 DOI: 10.3217/978-3-85125-603-1-07" 8e0becfc5fe3ecdd2ac93fabe34634827b21ef2b,Learning from Longitudinal Face Demonstration - Where Tractable Deep Modeling Meets Inverse Reinforcement Learning,"International Journal of Computer Vision manuscript No. (will be inserted by the editor) Learning from Longitudinal Face Demonstration - Where Tractable Deep Modeling Meets Inverse Reinforcement Learning Chi Nhan Duong · Kha Gia Quach · Khoa Luu · T. Hoang Ngan Le · Marios Savvides · Tien D. Bui Received: date / Accepted: date" 8eeab0aeb3170b1ef6497745d2a9bf78c001331d,Machine Vision Techniques for the Evaluation of Animal Behaviour by Dr,"Machine Vision Techniques for the Evaluation of Animal Behaviour Dr Derek Robert Magee Submitted in accordance with the requirements for the degree of Doctor of Philosophy SI T Y O The University of Leeds School of Computing October 2000 The candidate confirms that the work submitted is his own and that appropriate credit has been given where reference has been made to the work of others." 8e7493bdabddc2ec99cfa2b9b862343f70c1701a,Pseudo-positive regularization for deep person re-identification,"Noname manuscript No. (will be inserted by the editor) Pseudo-positive regularization for deep person re-identification Fuqing Zhu · Xiangwei Kong · Haiyan Fu · Qi Tian Received: date / Accepted: date" 8ea30ade85880b94b74b56a9bac013585cb4c34b,From turbo hidden Markov models to turbo state-space models [face recognition applications],"FROM TURBO HIDDEN MARKOV MODELS TO TURBO STATE-SPACE MODELS Florent Perronnin and Jean-Luc Dugelay Institut Eur´ecom Multimedia Communications Department BP 193, 06904 Sophia Antipolis Cedex, France fflorent.perronnin," 8e963c09144cab961bc90a3c807dc9b92c6aa916,Support Vector Number Reduction: Survey and Experimental Evaluations,"Support Vector Number Reduction: Survey and Experimental Evaluations Ho Gi Jung, Senior Member, IEEE, and Gahyun Kim" 8e6a403943d00b31aa0241c36b00234353507124,Learn to Detect and Recognize Humans using Small Data Sets,"Learn to Detect and Recognize Humans using Small Data Sets Shichao Ou Laboratory for Perceptual Robotics Computer Science Department University of Masschusetts Amherst Amherst, Massachusetts Rachel Lee Computer Science Department Swarthmore College, PA Rod Grupen Laboratory for Perceptual Robotics Computer Science Department University of Masschusetts" 8e6f67ba883169d6103795d7366a3821843ac758,A Novel Face Recognition Algorithm with Support Vector Machine Classifier,"INTERNATIONAL JOURNAL OF MATHEMATICS AND SCIENTIFIC COMPUTING, VOL. 1, NO. 1, 2011 A Novel Face Recognition Algorithm with Support Vector Machine Classifier Latha Parthiban Phase-based Texture Representation" 8e9f973e9d01fdd275af6c1460e5307d2ff3d2bc,"OF KITH AND KIN 1 Of kith and kin : Perceptual enrichment , expectancy and reciprocal processing in face perception","OF KITH AND KIN Of kith and kin: Perceptual enrichment, expectancy and reciprocal processing in face perception Joshua Correll Sean M. Hudson Steffanie Guillermo Holly A. Earls University of Colorado Boulder Author Note Joshua Correll, Sean M. Hudson, Steffanie Guillermo, Holly A. Earls, Department of Psychology & Neuroscience, University of Colorado Boulder. We dedicate this paper to the memory of Sean Hudson, a wonderful scientist and a true friend. We thank Jasmin Cloutier, Tim Correll, Tim Curran, Tiffany Ito, Sarah Lamer, Debbie Ma, Max Weisbuch, and Bernd Wittenbrink for their thoughtful comments on previous drafts. Correspondence should be addressed to Joshua Correll, Department of Psychology & Neuroscience, UCB 345, Boulder, Colorado, 80309-0345;" 8e723e8a3a5a9ea258591d384232e0251f842a1c,Twin-GAN - Unpaired Cross-Domain Image Translation with Weight-Sharing GANs,"Twin-GAN – Unpaired Cross-Domain Image Translation with Weight-Sharing GANs Jerry Li Google 600 Amphitheatre Parkway, Mountain View, CA 94040" 8ed051be31309a71b75e584bc812b71a0344a019,Class-Based Feature Matching Across Unrestricted Transformations,"Class-based feature matching across unrestricted transformations Evgeniy Bart and Shimon Ullman" 8e8e3f2e66494b9b6782fb9e3f52aeb8e1b0d125,"Detecting and classifying scars, marks, and tattoos found in the wild","in any current or future media, for all other uses,  2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any opyrighted component of this work in other works. Pre-print of article that will appear at BTAS 2012.!!" 8e3d0b401dec8818cd0245c540c6bc032f169a1d,McGan: Mean and Covariance Feature Matching GAN,"McGan: Mean and Covariance Feature Matching GAN Youssef Mroueh * 1 2 Tom Sercu * 1 2 Vaibhava Goel 2" 8ed32c8fad924736ebc6d99c5c319312ba1fa80b,Centralized Gradient Pattern for Face Recognition,"IEICE TRANS. INF. & SYST., VOL.E96–D, NO.3 MARCH 2013 PAPER SpecialSectiononFacePerceptionandRecognition Centralized Gradient Pattern for Face Recognition Dong-Ju KIM†a), Sang-Heon LEE†, and Myoung-Kyu SHON†, Members SUMMARY This paper proposes a novel face recognition approach using a centralized gradient pattern image and image covariance-based fa- ial feature extraction algorithms, i.e. a two-dimensional principal compo- nent analysis and an alternative two-dimensional principal component anal- ysis. The centralized gradient pattern image is obtained by AND operation of a modified center-symmetric local binary pattern image and a modified local directional pattern image, and it is then utilized as input image for the facial feature extraction based on image covariance. To verify the proposed face recognition method, the performance evaluation was carried out using various recognition algorithms on the Yale B, the extended Yale B and the CMU-PIE illumination databases. From the experimental results, the pro- posed method showed the best recognition accuracy compared to different pproaches, and we confirmed that the proposed approach is robust to illu- mination variation. key words: centralized gradient pattern, local binary pattern, local direc-" 8e0cc47c194ef7daf15aaef14d61e493879ae137,Deep Network Flow for Multi-object Tracking,"Deep Network Flow for Multi-Object Tracking Samuel Schulter Paul Vernaza Wongun Choi Manmohan Chandraker NEC Laboratories America, Media Analytics Department Cupertino, CA, USA" 8e92168860d8c6591a0c088573629e4d167f5947,"Look at the Driver, Look at the Road: No Distraction! No Accident!","Look at the Driver, Look at the Road: No Distraction! No Accident! Mahdi Rezaei and Reinhard Klette The University of Auckland Private Bag 92019, Auckland, New Zealand" 8e1d84e08109b5c692f7eff5cbc1816e5bdb00a3,Adversarial Face Recognition and Phishing Detection Using Multi-Layer Data Fusion,"Mason Archival Repository Service http://mars.gmu.edu etd Mason (Electronic Theses and Dissertations) The Volgenau School of Engineering Adversarial Face Recognition and Phishing Detection Using Multi-Layer Data Fusion Ramanathan, Venkatesh http://hdl.handle.net/1920/8075 service of Mason Publishing" 8eb2e7c9017b4a110978a1bb504accbc7b9ba211,Marching into battle: synchronized walking diminishes the conceptualized formidability of an antagonist in men.,"Downloaded from http://rsbl.royalsocietypublishing.org/ on June 9, 2015 rsbl.royalsocietypublishing.org Research Cite this article: Fessler DMT, Holbrook C. 014 Marching into battle: synchronized walking diminishes the conceptualized formidability of an antagonist in men. Biol. Lett. 10: 20140592. http://dx.doi.org/10.1098/rsbl.2014.0592 Received: 25 July 2014 Accepted: 6 August 2014 Subject Areas: ehaviour Keywords: synchrony, alliance, fighting capacity Author for correspondence: Daniel M. T. Fessler e-mail:" 8e6adaf03ac84acc16e428869b66a5a1e94ed753,Privacy-preserving classifiers recognize shared mobility behaviours from WiFi network imperfect data,"Privacy-preserving classifiers recognize shared mobility behaviours from WiFi network imperfect Orestes Manzanilla-Salazar∗ and Brunilde Sansò† Email:" 8ee02b8d375b21fe37b837e1a9288624f47c38d3,The Lifecycle of Geotagged Data,"The Lifecycle of Geotagged Data Rossano Schifanella University of Turin Turin, Italy Bart Thomee Google San Bruno, CA, USA David A. Shamma Centrum Wiskunde & Informatica Amsterdam, Netherlands" 8ec368bcc138736efedec4ce4fb5eac2c7d7585f,Testosterone Modulates Altered Prefrontal Control of Emotional Actions in Psychopathic Offenders123,"New Research Cognition and Behavior Testosterone Modulates Altered Prefrontal Control of Emotional Actions in Psychopathic Offenders1,2,3 Inge Volman,1,2,3 Anna Katinka Louise von Borries2,3,4,5, Berend Hendrik Bulten,5 Robbert Jan Verkes,3,4,5 Ivan Toni,3 and Karin Roelofs2,3 DOI:http://dx.doi.org/10.1523/ENEURO.0107-15.2016 Sobell Department of Motor Neuroscience and Movement Disorders, UCL Institute of Neurology, University College London, London WC1N 3BG, United Kingdom, 2Behavioural Science Institute, Radboud University Nijmegen, 6525 HR, Nijmegen, The Netherlands, 3Donders Institute for Brain, Cognition and Behavior, Radboud University Nijmegen, 6525 EN, Nijmegen, The Netherlands, 4Department of Psychiatry, UMC Sint Radboud, 6525 GA, Nijmegen, The Netherlands, and 5Pompestichting, 6532 CN, Nijmegen, The Netherlands" 8ea9093542075bd8cc4928a4c671a95f363c61ef,Sliced-Wasserstein Autoencoder : An Embarrassingly Simple Generative Model,"Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model" 8e42568c2b3feaafd1e442e1e861ec50a4ac144f,An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-identification,"An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification Paul Marchwica, Michael Jamieson, Parthipan Siva Senstar Corporation Waterloo, Canada {Paul.Marchwica, Mike.Jamieson, the art" 8e94ed0d7606408a0833e69c3185d6dcbe22bbbe,For your eyes only,"© 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, reating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Pre-print of article that will appear at WACV 2012." a1132e2638a8abd08bdf7fc4884804dd6654fa63,Real-Time Video Face Recognition for Embedded Devices,"Real-Time Video Face Recognition for Embedded Devices Gabriel Costache, Sathish Mangapuram, Alexandru Drimbarean, Petronel Bigioi and Peter Corcoran Tessera, Galway, Ireland . Introduction This chapter will address the challenges of real-time video face recognition systems implemented in embedded devices. Topics to be covered include: the importance and hallenges of video face recognition in real life scenarios, describing a general architecture of generic video face recognition system and a working solution suitable for recognizing faces in real-time using low complexity devices. Each component of the system will be described together with the system’s performance on a database of video samples that resembles real life conditions. . Video face recognition Face recognition remains a very active topic in computer vision and receives attention from large community of researchers in that discipline. Many reasons feed this interest; the main being the wide range of commercial, law enforcement and security applications that require authentication. The progress made in recent years on the methods and algorithms for data processing as well as the availability of new technologies makes it easier to study" a11600deb182677f4fe586fcea59f10d032a6c6f,Active Appearance Models with Rotation Invariant Kernels,"Active Appearance Models with Rotation Invariant Kernels Onur C. Hamsici and Aleix M. Martinez Department of Electrical and Computer Engineering Ohio State University, Columbus, OH 43210" a1aac8e95cd262f974b26374ec8fe35c0f000185,Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning,"IJCV manuscript No. (will be inserted by the editor) Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning Aoxue Li · Zhiwu Lu · Jiechao Guan · Tao Xiang · Liwei Wang · Ji-Rong Wen Received: date / Accepted: date" a11a63e00c0e587adf4efc1425c0651c242263b7,Two More Strategies to Speed Up Connected Components Labeling Algorithms,"Two More Strategies to Speed Up Connected Components Labeling Algorithms Federico Bolelli, Michele Cancilla, Costantino Grana Dipartimento di Ingegneria “Enzo Ferrari” Universit`a degli Studi di Modena e Reggio Emilia Via Vivarelli 10, Modena MO 41125, Italy" a13dac9255dd738932f463a8f462c11419f072db,Use of Generative Adversarial Network for Cross-Domain Change Detection,"Use of Generative Adversarial Network for Cross-Domain Change Detection Yamaguchi Kousuke Tanaka Kanji Sugimoto Takuma Graduate School of Engineering, University of Fukui -9-1, bunkyo, fukui, fukui Email:" a1669fa7d3d8f0c0cafe770c79007949cd32b245,Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly,"TPAMI SUBMISSION Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly Michael Opitz, Georg Waltner, Horst Possegger, and Horst Bischof" a13a4e4cc8f4744b40668fe7cca660ae0e88537d,Explorer Multi 30 K : Multilingual English-German Image Descriptions,"Multi30K: Multilingual English-German Image Descriptions Citation for published version: Elliott, D, Frank, S, Sima'an, K & Specia, L 2016, Multi30K: Multilingual English-German Image Descriptions. in Proceedings of the 5th Workshop on Vision and Language, hosted by the 54th Annual Meeting of the Association for Computational Linguistics, 2016, August 12, Berlin, Germany. Association for Computational Linguistics (ACL), pp. 70-74. Link: Link to publication record in Edinburgh Research Explorer Document Version: Publisher's PDF, also known as Version of record Published In: Proceedings of the 5th Workshop on Vision and Language, hosted by the 54th Annual Meeting of the Association for Computational Linguistics, 2016, August 12, Berlin, Germany General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) nd / or other copyright owners and it is a condition of accessing these publications that users recognise and bide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer ontent complies with UK legislation. If you believe that the public display of this file breaches copyright please" a172653d4559ca848b9a85f9ef5230bc794b3c3c,Averaging Representation of Standard Face Images and Recognition by KPCA and GFMT,"Jagankumar K, Geetha K ; International Journal of Advance Research, Ideas and Innovations in Technology. ISSN: 2454-132X Impact factor: 4.295 (Volume3, Issue3) Available online at www.ijariit.com Averaging Representation of Standard Face Images and Recognition by KPCA and GFMT Jagan Kumar Garuda Aerospace Private Limited Geetha Plintron Global technology solutions Pvt Ltd" a15663e0c0a2427ac4da5161e4ed75d331a5a2be,Streaming spectral clustering,"Streaming Spectral Clustering Shinjae Yoo Computational Science Center Brookhaven National Laboratory Upton, New York 11973-5000 Email: Hao Huang Machine Learning Laboratory General Electric Global Research San Ramon, CA 94583 Email: Shiva Prasad Kasiviswanathan Samsung Research America Mountain View, CA 94043 Email:" a120cac99c85548d0749dd83b0450520949e6474,Unsupervised Eye Pupil Localization through Differential Geometry and Local Self-Similarity Matching,"Unsupervised Eye Pupil Localization through Differential Geometry and Local Self-Similarity Matching Marco Leo1*, Dario Cazzato1,2, Tommaso De Marco1, Cosimo Distante1 National Research Council of Italy, Institute of Optics, Arnesano, Lecce, Italy, 2 Faculty of Engineering, University of Salento, Lecce, Italy" a19de85fa1533a1a1929b98b5fc3b1fb618dc668,Towards Improving Abstractive Summarization via Entailment Generation, a125bc46fee1bd170a0654b8856d3b78d62e9d29,Learning weighted sparse representation of encoded facial normal information for expression-robust 3D face recognition,"Learning Weighted Sparse Representation of Encoded Facial Normal Information for Expression-Robust 3D Face Recognition Huibin Li1,2, Di Huang1,2, Jean-Marie Morvan1,3,4, Liming Chen1,2 Universit´e de Lyon, CNRS, 2Ecole Centrale de Lyon, LIRIS UMR5205, F-69134, Lyon, France Universit´e Lyon 1, Institut Camille Jordan, 43 blvd. du 11 Nov. 1918, F-69622 Villeurbanne - Cedex, France King Abdullah University of Science and Technology, GMSV Research Center, Bldg 1, Thuwal 23955-6900, Saudi Arabia" a147cec1434753777b3651101bdbda1489b09fd4,Individual differences in shifting decision criterion: a recognition memory study.,"Mem Cogn (2012) 40:1016–1030 DOI 10.3758/s13421-012-0204-6 Individual differences in shifting decision criterion: A recognition memory study Elissa M. Aminoff & David Clewett & Scott Freeman & Amy Frithsen & Christine Tipper & Arianne Johnson & Scott T. Grafton & Michael B. Miller Published online: 4 May 2012 # Psychonomic Society, Inc. 2012" a18c8f76f2599d6d61f26cb1d4025ea386919dfe,Video Event Detection: From Subvolume Localization To Spatio-Temporal Path Search.,"This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore. Title Video event detection : from subvolume localization to spatio-temporal path search Author(s) Tran, Du; Yuan, Junsong; Forsyth, David Citation Tran, D., Yuan, J., & Forsyth, D. (2014). Video Event Detection: From Subvolume Localization to Spatiotemporal Path Search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(2), 404- http://hdl.handle.net/10220/19322 Rights © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any" a1af05502eac70296ee22e5ab7e066420f5fe447,A Probabilistic Approach for Breast Boundary Extraction in Mammograms,"Hindawi Publishing Corporation Computational and Mathematical Methods in Medicine Volume 2013, Article ID 408595, 19 pages http://dx.doi.org/10.1155/2013/408595 Research Article A Probabilistic Approach for Breast Boundary Extraction in Mammograms Hamed Habibi Aghdam, Domenec Puig, and Agusti Solanas Department of Computer Engineering and Mathematics, Rovira i Virgili University, 43007 Tarragona, Spain Correspondence should be addressed to Domenec Puig; Received 31 May 2013; Revised 21 August 2013; Accepted 16 September 2013 Academic Editor: Reinoud Maex Copyright © 2013 Hamed Habibi Aghdam et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The extraction of the breast boundary is crucial to perform further analysis of mammogram. Methods to extract the breast boundary an be classified into two categories: methods based on image processing techniques and those based on models. The former use image transformation techniques such as thresholding, morphological operations, and region growing. In the second category, the oundary is extracted using more advanced techniques, such as the active contour model. The problem with thresholding methods is that it is a hard to automatically find the optimal threshold value by using histogram information. On the other hand, active ontour models require defining a starting point close to the actual boundary to be able to successfully extract the boundary. In this" a102edaa9fd458316637ce51a0b7aba2ee651637,Learning Human Poses from Actions,"ADITYA, JAWAHAR, PAWAN: LEARNING HUMAN POSES FROM ACTIONS Learning Human Poses from Actions IIIT Hyderabad University of Oxford & The Alan Turing Institute Aditya Arun1 C.V. Jawahar1 M. Pawan Kumar2" a14ae81609d09fed217aa12a4df9466553db4859,Face Identification Using Large Feature Sets,"REVISED VERSION, JUNE 2011 Face Identification Using Large Feature Sets William Robson Schwartz, Huimin Guo, Jonghyun Choi, and Larry S. Davis, Fellow, IEEE" a19f08d7b1ce8b451df67ec125dd9254b5a05d95,3D Face Recognition Using Multiview Keypoint Matching,"009 Advanced Video and Signal Based Surveillance D Face Recognition Using Multiview Keypoint Matching Michael Mayo, Edmond Zhang Department of Computer Science, University of Waikato, New Zealand {mmayo," a14879e4326105502892fee66606a8998b1baad6,"- 1-Age-related differences in brain electrical activity during extended continuous face recognition in younger children , older children , and adults","Age-related differences in brain electrical activity during extended continuous face recognition in younger children, older children, and adults Jan W. Van Strien1 Johanna C. Glimmerveen2 Ingmar H.A. Franken1 Vanessa E.G. Martens3 Eveline A. de Bruin3 Institute of Psychology, Faculty of Social Sciences, Erasmus University Rotterdam, The Netherlands School of Social and Behavioral Sciences, Tilburg University, The Netherlands Sensation, Perception and Behaviour, Unilever R&D Vlaardingen, The Netherlands" a139c62c27a884cf447ad020cb7b154e63477681,A Data-driven Model for Interaction-Aware Pedestrian Motion Prediction in Object Cluttered Environments,"A Data-driven Model for Interaction-aware Pedestrian Motion Prediction in Object Cluttered Environments Mark Pfeiffer, Giuseppe Paolo, Hannes Sommer, Juan Nieto, Roland Siegwart, and Cesar Cadena" a133374b9630bbe6eb2b7de8c3204aa57e75c582,A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping.,"A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping Wenguan Wang, Jianbing Shen, Senior Member, IEEE, and Haibin Ling" a1030e6e0e6995768dbcafedc712a59db090d2b4,Bayesian Sparsification of Recurrent Neural Networks,"Bayesian Sparsification of Recurrent Neural Networks Ekaterina Lobacheva * 1 2 Nadezhda Chirkova * 1 3 Dmitry Vetrov 1 4" a1f1120653bb1bd8bd4bc9616f85fdc97f8ce892,Latent Embeddings for Zero-Shot Classification,"Latent Embeddings for Zero-shot Classification Yongqin Xian1, Zeynep Akata1, Gaurav Sharma1,2,∗, Quynh Nguyen3, Matthias Hein3 and Bernt Schiele1 MPI for Informatics IIT Kanpur Saarland University" a157ebc849d57ccff00a52a68b24e4ac8eba9536,The Contextual Loss for Image Transformation with Non-aligned Data,"The Contextual Loss for Image Transformation with Non-Aligned Data Roey Mechrez(cid:63) , Itamar Talmi(cid:63), Lihi Zelnik-Manor Technion - Israel Institute of Technology Fig. 1. Our Contextual loss is effective for many image transformation tasks: It can make a Trump cartoon imitate Ray Kurzweil, give Obama some of Hillary’s features, nd, turn women more masculine or men more feminine. Mutual to these tasks is the bsence of ground-truth targets that can be compared pixel-to-pixel to the generated images. The Contextual loss provides a simple solution to all of these tasks." a1c6f88330762cc97f26585c124c6b3ac791eb89,Confidence Sets for Fine-Grained Categorization and Plant Species Identification,"Int J Comput Vis DOI 10.1007/s11263-014-0743-3 Confidence Sets for Fine-Grained Categorization and Plant Species Identification Asma Rejeb Sfar · Nozha Boujemaa · Donald Geman Received: 1 January 2014 / Accepted: 20 June 2014 © Springer Science+Business Media New York 2014" a1e1bd4dacddc703a236681e987a09601ee1016d,Embedding Visual Hierarchy With Deep Networks for Large-Scale Visual Recognition,"Embedding Visual Hierarchy with Deep Networks for Large-Scale Visual Recognition Tianyi Zhao, Baopeng Zhang, Wei Zhang, Ning Zhou, Jun Yu, Jianping Fan" a1ff747cf512c8156620d9c17cb6ed8d21a76ad6,KonIQ-10k: Towards an ecologically valid and large-scale IQA database,"KonIQ-10K: TOWARDS AN ECOLOGICALLY VALID AND LARGE-SCALE IQA DATABASE Hanhe Lin*, Vlad Hosu* and Dietmar Saupe Department of Computer and Information Science, University of Konstanz, Germany Email: {hanhe.lin, vlad.hosu," a158c1e2993ac90a90326881dd5cb0996c20d4f3,Symmetry as an Intrinsically Dynamic Feature,"OPEN ACCESS ISSN 2073-8994 Article Vito Di Gesu 1,2,†, Marco E. Tabacchi 1,3,* and Bertrand Zavidovique 4 DMA, Università degli Studi di Palermo, via Archirafi 34, 90123 Palermo, Italy CITC, Università degli Studi di Palermo, via Archirafi 34, 90123 Palermo, Itlay Istituto Nazionale di Ricerche Demopolis, via Col. Romey 7, 91100 Trapani, Italy IEF, Université Paris IX–Orsay, Paris, France; E-Mail: (B.Z.) Deceased on 15 March 2009. * Author to whom correspondence should be addressed; E-Mail: Received: 4 March 2010; in revised form: 23 March 2010 / Accepted: 29 March 2010 / Published: 1 April 2010" a11f5e74b13a6353d14e024d06a902b9afa728b3,Yum-me: Personalized Healthy Meal Recommender System,"Yum-me: Personalized Healthy Meal Recommender System Longqi Yang Cornell Tech Nicola Dell Cornell Tech Cheng-Kang Hsieh Serge Belongie Cornell Tech Hongjian Yang Cornell Tech Deborah Estrin Cornell Tech" a1b7b23bd8f2b2ef37a9113e6b8499f0069aac85,Performance assessment of face recognition using super-resolution,"Performance Assessment of Face Recognition Using Super-Resolution Shuowen Hu Robert Maschal S. Susan Young U.S. Army Research Laboratory U.S. Army Research Laboratory U.S. Army Research Laboratory 800 Powder Mill Rd. Adelphi, MD 20783 (301)394-2526 800 Powder Mill Rd. Adelphi, MD 20783 (301)394-0437 800 Powder Mill Rd. Adelphi, MD 20783 (301)394-0230 Tsai Hong Hong Jonathon P. Phillips National Institute of Standards and" a1e198454bd0868b4da9bca7a35218dd235cfdda,3d‐facial Expression Synthesis and Its Application to Face Recognition Systems,"D‐Facial Expression Synthesis and its Application to Face Recognition Systems Leonel Ramírez‐Valdez1, Rogelio Hasimoto‐Beltran2 ,2Centro de Investigación en Matemáticas(CIMAT) Jalisco s/n, Col. Mineral de Valenciana, Guanajuato, Gto., México 36240" a15f4e3adb56dbbdd6f922489efef48fc5efa003,Grounding Semantic Roles in Images,"Grounding Semantic Roles in Images Carina Silberer†♣ Manfred Pinkal† Department of Computational Linguistics Saarland University, Saarbr¨ucken, Germany ♣Universitat Pompeu Fabra Barcelona, Spain" a10f734e30d8dcb8506c9ea5b1074e6c668904e2,Learning Features and Parts for Fine-Grained Recognition,"Learning Features and Parts for Fine-Grained Recognition (Invited Paper) Jonathan Krause∗, Timnit Gebru∗, Jia Deng †, Li-Jia Li ‡, Li Fei-Fei∗ Stanford University: {jkrause, tgebru, University of Michigan: Yahoo! Research:" a15d9d2ed035f21e13b688a78412cb7b5a04c469,Object detection using strongly-supervised deformable part models,"Object Detection Using Strongly-Supervised Deformable Part Models Hossein Azizpour1 and Ivan Laptev2 Computer Vision and Active Perception Laboratory (CVAP), KTH, Sweden INRIA, WILLOW, Laboratoire d’Informatique de l’Ecole Normale Superieure" a14260cd8c607afc6a9bd0c4df2ee22162e6d8c0,Discriminative Dictionary Learning With Ranking Metric Embedded for Person Re-Identification,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) d1082eff91e8009bf2ce933ac87649c686205195,Pruning of Error Correcting Output Codes by optimization of accuracy–diversity trade off,"(will be inserted by the editor) Pruning of Error Correcting Output Codes by Optimization of Accuracy-Diversity Trade off S¨ureyya ¨Oz¨o˘g¨ur Aky¨uz · Terry Windeatt · Raymond Smith Received: date / Accepted: date" d1f58798db460996501f224fff6cceada08f59f9,Transferrable Representations for Visual Recognition,"Transferrable Representations for Visual Recognition Jeffrey Donahue Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2017-106 http://www2.eecs.berkeley.edu/Pubs/TechRpts/2017/EECS-2017-106.html May 14, 2017" d19df82c5ea644937bf182fabdc0e36e78ea6867,Emotional Facial Expression Recognition from Two Different Feature Domains,"EMOTIONAL FACIAL EXPRESSION RECOGNITION FROM TWO DIFFERENT FEATURE DOMAINS Jonghwa Kim and Frank Jung Institute of Computer Science, University of Augsburg, Germany Keywords:" d1a0425f764ce8847d20d278e4a4267c8258c4dc,3D Human Pose Estimation with Siamese Equivariant Embedding,"D Human Pose Estimation with Siamese Equivariant Embedding M´arton V´egesa,∗, Viktor Vargaa, Andr´as L˝orincza E¨otv¨os Lor´and University, Budapest, Hungary" d170adb2c508edaedb731ada8cb995172a839a1f,Cascade of Boolean detector combinations,"Mahkonen et al. EURASIP Journal on Image and Video Processing (2018) 2018:61 https://doi.org/10.1186/s13640-018-0303-9 EURASIP Journal on Image nd Video Processing RESEARCH Open Access Cascade of Boolean detector ombinations Katariina Mahkonen* , Tuomas Virtanen and Joni Kämäräinen" d1ade6a8c3a4c929efb70810a171c62a39e6f195,Review on Latest Approaches used in Natural Language Processing for Generation of Image Captioning,"SSRG International Journal of Computer Science and Engineering (SSRG-IJCSE) – volume 4 Issue 6 – June 2017 Review on Latest Approaches used in Natural Language Processing for Generation of Image Captioning M. A. Bhalekar , Dr. M. V. Bedekar Department of Computer Engineering, MAEER’S Maharashtra Institute of Technology, Pune, Maharashtra, India." d1a43737ca8be02d65684cf64ab2331f66947207,IJB – S : IARPA Janus Surveillance Video Benchmark ∗,"IJB–S: IARPA Janus Surveillance Video Benchmark (cid:3) Nathan D. Kalka y Stephen Elliott z Brianna Maze y Kaleb Hebert y James A. Duncan y Julia Bryan z Kevin O’Connor z Anil K. Jain x" d16c8ac2d194a6e862be0d1c4edf1ca2cdf5dc18,Robust Subspace Approaches to Visual Learning and recognition,"Univerza v Ljubljani Fakulteta za raˇcunalniˇstvo in informatiko Danijel Skoˇcaj Robustni pristopi k vizualnemu uˇcenju in razpoznavanju na osnovi podprostorov DOKTORSKA DISERTACIJA Ljubljana, 2003 Mentor: prof. dr. Aleˇs Leonardis" d198b5bc5eae22f7a788729c0ea15b6b60b62f36,Transfer Learning for Estimating Causal Effects using Neural Networks,"Transfer Learning for Estimating Causal Effects using Neural Networks Sören R. Künzel∗ UC Berkeley Varsha Ramakrishnan UC Berkeley Bradly C. Stadie∗ UC Berkeley Nikita Vemuri UC Berkeley Jasjeet S. Sekhon UC Berkeley Pieter Abbeel UC Berkeley" d111faa1990f80e3351ea1eef0e5fc177d4e44b4,Iteratively Training Look-Up Tables for Network Quantization,"Iteratively Training Look-Up Tables for Network Quantization Fabien Cardinaux∗ Sony Europe Ltd.† Stefan Uhlich∗ Sony Europe Ltd.† Kazuki Yoshiyama∗ Sony Corporation‡ Javier Alonso García Sony Europe Ltd.† Stephen Tiedemann Sony Europe Ltd.† Thomas Kemp Sony Europe Ltd.† Akira Nakamura Sony Corporation‡" d1c103c63d930d3ae7397618f486117a48e35f16,Does gaze direction modulate facial expression processing in children with autism spectrum disorder?,"BIROn - Birkbeck Institutional Research Online Enabling open access to Birkbeck’s published research output Does gaze direction modulate facial expression processing in children with autism spectrum disorder? Journal Article http://eprints.bbk.ac.uk/2561 Version: Accepted (Refereed) Citation: © 2009 Wiley Blackwell Publisher version ______________________________________________________________ All articles available through Birkbeck ePrints are protected by intellectual property law, including opyright law. Any use made of the contents should comply with the relevant law. ______________________________________________________________ Akechi, H.; Senju, A.; Kikuchi, Y.; Tojo, Y.; Osanai, H.; Hasegawa, T. (2009) Does gaze direction modulate facial expression processing in children with autism spectrum disorder? Deposit Guide Contact:" d1e66107eb084ea0ef5a97f3363f8787b8df91ed,Max-Margin Regularization for Reducing Accidentalness in Chamfer Matching,"Max-margin Regularization for Reducing Accidentalness in Chamfer Matching Angela Eigenstetter*, Pradeep Yarlagadda* and Bj¨orn Ommer Interdisciplinary Center for Scientific Computing, University of Heidelberg, Germany" d1295a93346411bb833305acc0e092c9e3b2eff1,The eMPaThy iMBalance hyPoThesis oF aUTisM : a TheoReTical aPPRoach To cogniTiVe and eMoTional eMPaThy in aUTisTic deVeloPMenT,"the Psychological record, 2009, 59, 489-510 The eMPaThy iMBalance hyPoThesis oF aUTisM: TheoReTical aPPRoach To cogniTiVe and eMoTional eMPaThy in aUTisTic deVeloPMenT Adam Smith Dundee, Scotland There has been a widely held belief that people with autism spectrum disorders lack empathy. This article examines the empathy imbalance hypothesis (EIH) of utism. According to this account, people with autism have a deficit of cognitive empathy but a surfeit of emotional empathy. The behavioral characteristics of utism might be generated by this imbalance and a susceptibility to empathic overarousal. The EIH builds on the theory of mind account and provides an lternative to the extreme-male-brain theory of autism. Empathy surfeit is a re- urrent theme in autistic narratives, and empirical evidence for the EIH is grow- ing. A modification of the pictorial emotional Stroop paradigm could facilitate n experimental test of the EIH. Autism is a pervasive developmental disorder that continues to fascinate researchers, challenge clinicians, and distress affected families. empathy is a set of processes and outcomes at the heart of human social behavior. Fascination with autism is often interwoven with the study of empathy because" d1a9ce4a250ede36ff1bfae090a905e7795f0e26,Chapter 3 – Available Technologies 3.1 Speech Processing 3.1.1 Speech Coding,"Chapter 3 – AVAILABLE TECHNOLOGIES Speech technology is traditionally divided into speech processing and natural (i.e. written) language processing. This chapter presents these and their combination, followed by some related technologies. .1 SPEECH PROCESSING Modern speech technology is based on digital signal processing, probabilistic theory and search lgorithms. These techniques make it possible to perform significant data reduction for coding and transmission of speech signals, speech synthesis and automatic recognition of speech, speaker or language. In this section the state-of-the-art is presented and related to realistic military applications. .1.1 Speech Coding When digital systems became available, it was obvious that the transmission of digital signals was more efficient than the transmission of analogue signals. If analogue signals are transmitted under adverse onditions, it is not easy to reconstruct the received signal, because the possible signal values are not known in advance. For digital signals discrete levels are used. This allows, within certain limits, the reconstruction of distorted signals. The first digital transmission systems were based on coding the waveform of the speech signal. This results in bit rates between 8000 to 64000 Bps (bits per second). The higher the bit rate the better the quality. Later, more advanced coding systems were used where basic properties of the speech were determined and encoded, resulting in a more efficient coding (bit rates etween 300 and 4800 Bps) but also in reduced intelligibility. These methods are discussed in this section. The first technique used to convert an analogue signal into a digital signal was based on the work of Shannon. He converted the instantaneous signal value at discrete moments into a binary number" d1dc5a8b4d13d2c51eec7bcb29d08f471d3b65dc,Adversarially Occluded Samples for Person Re-identification ( Supplementary Material ) 1 . Improvement of Ranking Results,"Adversarially Occluded Samples for Person Re-identification Houjing Huang 1 Dangwei Li 1 Zhang Zhang 1 Xiaotang Chen 1 Kaiqi Huang 1 CRIPAC & NLPR, CASIA 2 University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology {houjing.huang, dangwei.li, zzhang, xtchen," d10b03ddae7348ea8de079f6175d6833c885a991,"A Graph Based People Silhouette Segmentation Using Combined Probabilities Extracted from Appearance, Shape Template Prior, and Color Distributions","A Graph Based People Silhouette Segmentation Using Combined Probabilities Extracted from Appearance, Shape Template Prior, nd Color Distributions Christophe Coniglio1,2(B), Cyril Meurie1,2, Olivier L´ezoray3, nd Marion Berbineau1,2 Univ Lille Nord de France, 59000 Lille, France IFSTTAR, COSYS, LEOST, 59650 Villeneuve d’Ascq, France Normandie Univ., UNICAEN, ENSICAEN, GREYC UMR CNRS 6072, Caen, France" d1dfdc107fa5f2c4820570e369cda10ab1661b87,Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation,"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation Huaizu Jiang1 Deqing Sun2 Varun Jampani2 Ming-Hsuan Yang3,2 Erik Learned-Miller1 Jan Kautz2 UMass Amherst NVIDIA 3UC Merced" d1a9f71e5563a1bb2f956b9b805cfc6aafe4a6e6,Robust Methods for Visual Tracking and Model Alignment, d1443d18d40c323d5ad01277675ee00c8decdb99,EXPERIMENTAL EVALUATION OF TEXT-INDEPENDENT SPEAKER VERIFICATION ON LABORATORY AND FIELD TEST DATABASES IN THE M2VTS PROJECT,"EXPERIMENTAL EVALUATION OF TEXT-INDEPENDENT SPEAKER VERIFICATION ON LABORATORY AND FIELD TEST DATABASES IN THE M2VTS PROJECT L. Besacie , J. Luett , G. Maîtr , E. Meurv (1) IMT, Neuchâtel (CH) - (2) IDIAP, Martigny (CH) - (3) now at EIV, Sion (CH) - (4) now at EPFL, Lausanne (CH) -" d1d4c49e764a200bc90113b0ba9c34664d0f9462,"Memo No . 082 May 10 , 2018 Scene Graph Parsing as Dependency Parsing","CBMM Memo No. 082 May 10, 2018 Scene Graph Parsing as Dependency Parsing Yu-Siang Wang1, Chenxi Liu2, Xiaohui Zeng3, Alan Yuille2 : National Taiwan University : Johns Hopkins University : Hong Kong University of Science and Technology" d1c0592f4f9f0ff2e14e0591d87539e5141b7361,Mobile Emotion Recognition Engine,"Mobile Emotion Recognition Engine Alberto Scicali1" d122d66c51606a8157a461b9d7eb8b6af3d819b0,AUTOMATED RECOGNITION OF FACIAL EXPRESSIONS,"Vol-3 Issue-4 2017 IJARIIE-ISSN(O)-2395-4396 AUTOMATED RECOGNITION OF FACIAL EXPRESSIONS Pavan S. Ahire, PG Student, Dept. of Computer Engineering, METs Institute of Engineering, Prof. R. P. Dahake, Dept. of Computer Engineering, METs Institute of Engineering, Adgoan,Nashik,Maharashtra. Adgoan, Nashik, Maharashtra." d102f18d319d9545588075010f5d10b1ff77f967,Effects of Degradations on Deep Neural Network Architectures,"Effects of Degradations on Deep Neural Network Architectures Prasun Roy∗, Subhankar Ghosh∗, Saumik Bhattacharya∗ and Umapada Pal Indian Statistical Institute Kolkata, India - 700108" d142e74c6a7457e77237cf2a3ded4e20f8894e1a,EEG AND F ACE U SING S TATISTICAL F EATURES AND SVM,"HUMAN EMOTION ESTIMATION FROM EEG AND FACE USING STATISTICAL FEATURES AND SVM Strahil Sokolov1, Yuliyan Velchev2, Svetla Radeva3 and Dimitar Radev4 ,3Department of Information Technologies, University of telecommunications and post, Sofia, Bulgaria 2,4Department of Telecommunications, University of telecommunications and post, Sofia, Bulgaria" d1c091bf9402f1caf13892a3fae39326507401be,Speeding up Semantic Segmentation for Autonomous Driving,"Speeding up Semantic Segmentation for Autonomous Driving Michael Treml ∗1, José Arjona-Medina∗1, Thomas Unterthiner∗1, Rupesh Durgesh2, Felix Friedmann2, Peter Schuberth2, Andreas Mayr1, Martin Heusel1, Markus Hofmarcher1, Michael Widrich1, Bernhard Nessler1, Sepp Hochreiter1 Institute of Bioinformatics, Johannes Kepler University Linz, Austria Audi Electronics Venture GmbH, Germany {treml, arjona, unterthiner, nessler, {rupesh.durgesh, felix.friedmann," d1d6f1d64a04af9c2e1bdd74e72bd3ffac329576,Neural Face Editing with Intrinsic Image Disentangling,"Neural Face Editing with Intrinsic Image Disentangling Zhixin Shu1 Ersin Yumer2 Sunil Hadap2 Kalyan Sunkavalli2 Eli Shechtman 2 Dimitris Samaras1,3 Stony Brook University 2Adobe Research 3 CentraleSup´elec, Universit´e Paris-Saclay" 6f3391fda6b25796b5e051f822f91243f69276cb,Performance Comparison of Various Face Detection Techniques,"International Journal of Scientific Research Engineering & Technology (IJSRET) Volume 2 Issue1 pp 019-0027 April 2013 ISSN 2278 - 0882 www.ijsret.org Performance Comparison of Various Face Detection Techniques Mohammed Javed, 2Bhaskar Gupta M.Tech. Student, Jamia Hamdard, New Delhi Associate Professor,ECE,BBDIT,Ghaziabad,UP Corresponding Author" 6f089f9959cc711e16f1ebe0c6251aaf8a65959a,Improvement in object detection using Super Pixels,"International Journal of Engineering Research in Electronic and Communication Engineering (IJERECE) Vol 3, Issue 5, May 2016 Improvement in object detection using Super Pixels [1] Shruti D Kadam [2] H.Mallika Dept. of Electronics and communication M. S. Ramaiah Institute of Technology, Bangalore, Karnataka [1] [2]" 6fe2efbcb860767f6bb271edbb48640adbd806c3,Soft Biometrics; Human Identification Using Comparative Descriptions,"SOFT BIOMETRICS: HUMAN IDENTIFICATION USING COMPARATIVE DESCRIPTIONS Soft Biometrics; Human Identification using Comparative Descriptions Daniel A. Reid, Mark S. Nixon, Sarah V. Stevenage" 6fe8386b88d8a2162250b899b73bf1e72eb545f9,Cascade Learning by Optimally Partitioning,"Cascade Learning by Optimally Partitioning Yanwei Pang, Senior Member, IEEE, Jiale Cao, and Xuelong Li, Fellow, IEEE," 6f5d57460e0e156497c4667a875cc5fa83154e3a,Retinal Verification Using a Feature Points-Based Biometric Pattern,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2009, Article ID 235746, 13 pages doi:10.1155/2009/235746 Research Article Retinal Verification Using a Feature Points-Based Biometric Pattern M. Ortega,1 M. G. Penedo,1 J. Rouco,1 N. Barreira,1 and M. J. Carreira2 VARPA Group, Faculty of Informatics, Department of Computer Science, University of Coru˜na, 15071 A Coru˜na, Spain Department of Electronics and Computer Science, University of Santiago de Compostela, 15782 Santiago de Compostela, Spain Correspondence should be addressed to M. Ortega, Received 14 October 2008; Accepted 12 February 2009 Recommended by Natalia A. Schmid Biometrics refer to identity verification of individuals based on some physiologic or behavioural characteristics. The typical uthentication process of a person consists in extracting a biometric pattern of him/her and matching it with the stored pattern for the authorised user obtaining a similarity value between patterns. In this work an ef‌f‌icient method for persons authentication is showed. The biometric pattern of the system is a set of feature points representing landmarks in the retinal vessel tree. The pattern extraction and matching is described. Also, a deep analysis of similarity metrics performance is presented for the biometric system. A database with samples of retina images from users on different moments of time is used, thus simulating a hard and real environment of verification. Even in this scenario, the system allows to establish a wide confidence band for the metric threshold" 6f9873e2a7bc279c4f0a45c1a6e831ef3ba78ae7,Improving GAN Training via Binarized Representation Entropy (BRE) Regularization,"Published as a conference paper at ICLR 2018 IMPROVING GAN TRAINING VIA BINARIZED REPRESENTATION ENTROPY (BRE) REGULARIZATION Yanshuai Cao, Gavin Weiguang Ding, Kry Yik-Chau Lui, Ruitong Huang Borealis AI Canada" 6f79c4b82f9ccdee918659a8f7091b8ab99fe889,Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filtering,"Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filtering Samuel Scheidegger∗†, Joachim Benjaminsson∗†, Emil Rosenberg†, Amrit Krishnan∗, Karl Granstr¨om† Zenuity, †Department of Electrical Engineering, Chalmers University of Technology" 6fd3bafa25bf6d376bc9d1cc1311eb260d10d024,Facial Recognition Utilizing Patch Based Game Theory,"International Journal of Machine Learning and Computing, Vol. 5, No. 4, August 2015 Facial Recognition Utilizing Patch Based Game Theory Foysal Ahmad, Kaushik Roy, Brian O‟Connor, Joseph Shelton, Pablo Arias, Albert Esterline, and Gerry Dozier theory. Texture based" 6f1be86c77492af422e936028858c9180b52b698,Indoor Scene Understanding in 2.5/3D: A Survey,"JOURNAL OF LATEX CLASS FILES, VOL. 6, NO. 1, JULY 2015 Indoor Scene Understanding in 2.5/3D: A Survey Muzammal Naseer, Salman H Khan, Fatih Porikli" 6f7ce89aa3e01045fcd7f1c1635af7a09811a1fe,A novel rank order LoG filter for interest point detection,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 6f5151c7446552fd6a611bf6263f14e729805ec7,Facial Action Unit Recognition Using Filtered Local Binary Pattern Features with Bootstrapped and Weighted ECOC Classifiers,".=?E= )?JE 7EJ 4A?CEJE KIEC ?= *E=HO 2=JJAH .A=JKHAI MEJD -++ +=IIEAHI 55EJD +AJHA BH 8EIE 5FAA?D 5EC= 2H?AIIEC 7ELAHIEJO B 5KHHAO 5KHHAO /7 %:0 7 )>IJH=?J 9EJDE JDA ?JANJ B=?A ANFHAIIE ?=IIE?=JE KIEC JDA B=?E= =?JE IOIJA .)+5 MA JDA FH>A B EC B=?E= =?JE KEJI )7I 6DA EI J JH=E = IECA AHHH?HHA?JEC KJFKJ -++ KJE?=II ?=IIEAH J AIJE=JA JDA FH>=>EEJEAI JD=J A=?D A B IALAH= ?O ??KHHEC )7 CHKFI EI FHAIAJ E JDA FH>A E=CA 2=JJ I?=EC EI J ?=E>H=JA JDA -++ KJFKJI J FH>=>EEJEAI =FFHFHE=JA IKI B JDAIA FH>=>EEJEAI =HA J=A J >J=E = IAF=H=JA FH>=>EEJO BH A=?D )7 .A=JKHA ANJH=?JE EI >O CAAH=JEC = =HCA K>AH B ?= >E=HO F=J JAH *2 BA=JKHAI JDA IAA?JEC BH JDAIA KIEC B=IJ ?HHA=JE JAHEC .+*. 6DA >E=I L=HE=?A FHFAHJEAI B JDA ?=IIEAH =HA MA IDM JD=J >JD JDAIA IKH?AI B AHHH ?= >A HA >O AD=?EC -++ JDHKCD JDA =FFE?=JE B >JIJH=FFEC ?=IIIAF=H=>EEJO MAECDJEC" 6f5a3c34360caad4644aea897b8fe7dd72076d0f,Self-calibrating Marker Tracking in 3D with Event-Based Vision Sensors,"Self-Calibrating Marker Tracking in 3D with Event-Based Vision Sensors Georg R. Müller, Jörg Conradt Technische Universität München, Arcisstr. 21, 80290 München, Germany" 6f7d06ced04ead3b9a5da86b37e7c27bfcedbbdd,Multi-Scale Fully Convolutional Network for Fast Face Detection,"Pages 51.1-51.12 DOI: https://dx.doi.org/10.5244/C.30.51" 6f35b6e2fa54a3e7aaff8eaf37019244a2d39ed3,Learning probabilistic classifiers for human–computer interaction applications,"DOI 10.1007/s00530-005-0177-4 R E G U L A R PA P E R Nicu Sebe · Ira Cohen · Fabio G. Cozman · Theo Gevers · Thomas S. Huang Learning probabilistic classifiers for human–computer interaction applications Published online: 10 May 2005 (cid:1) Springer-Verlag 2005 intelligent interaction," 6f8fc12004fa068c424369793fd39426e772b07d,Demystifying Core Ranking in Pinterest Image Search,"Demystifying Core Ranking in Pinterest Image Search Linhong Zhu Pinterest & USC/ISI" 6fc129d384431d17eb7aa22afd6ab68f1084f038,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 6fdc0bc13f2517061eaa1364dcf853f36e1ea5ae,DAISEE: Dataset for Affective States in E-Learning Environments,"DAISEE: Dataset for Affective States in E-Learning Environments Abhay Gupta1, Richik Jaiswal2, Sagar Adhikari2, Vineeth Balasubramanian2 Microsoft India R&D Pvt. Ltd. Department of Computer Science, IIT Hyderabad {cs12b1032, cs12b1034," 6fa9bae381274518d3972294d81e460f0c63900b,Personalized Recommendations in Police Photo Lineup Assembling Task,"S. Krajˇci (ed.): ITAT 2018 Proceedings, pp. 157–160 CEUR Workshop Proceedings Vol. 2203, ISSN 1613-0073, c(cid:13) 2018 Ladislav Peška and Hana Trojanová" 6f8ea33c29de7ef94f674c4c847185a127c6ea2f,Cue Integration by Similarity Rank List Coding - Application to Invariant Object Recognition,"nd IEEE International Workshops on Foundations and Applications of Self* Systems nd IEEE International Workshops on Foundations and Applications of Self* Systems Cue Integration by Similarity Rank List Coding — Application to Invariant Object Recognition Raul Grieben and Rolf P. W¨urtz Institut f¨ur Neuroinformatik, Ruhr-Universit¨at Bochum,44780 Bochum, Germany" 6fa3857faba887ed048a9e355b3b8642c6aab1d8,Face Recognition in Challenging Environments: An Experimental and Reproducible Research Survey,"Face Recognition in Challenging Environments: An Experimental and Reproducible Research Survey Manuel G¨unther and Laurent El Shafey and S´ebastien Marcel" 6f77ff9990973a6cdad6b5b6022323bff9d03965,Action Recognition in Still Images Using Word Embeddings from Natural Language Descriptions,"017 IEEE Winter Conference on Applications of Computer Vision Workshops Action Recognition in Still Images Using Word Embeddings from Natural Language Descriptions Karan Sharma Arun CS Kumar Department of Computer Science, The University of Georgia, Athens, GA 30602-7404, USA E-mails: Suchendra M. Bhandarkar" 6f206b46c26b70b3be0b1e89b1d4b6518b601005,Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights,"Published as a conference paper at ICLR 2017 INCREMENTAL NETWORK QUANTIZATION: TOWARDS LOSSLESS CNNS WITH LOW-PRECISION WEIGHTS Aojun Zhou∗, Anbang Yao, Yiwen Guo, Lin Xu, and Yurong Chen Intel Labs China {aojun.zhou, anbang.yao, yiwen.guo, lin.x.xu," 6feb0d42232c31eecee5d90290287afe803e88a5,Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks,"Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks Andreas K¨olsch∗†, Ashutosh Mishra∗, Saurabh Varshneya∗†, Muhammad Zeshan Afzal∗†, Marcus Liwicki∗†‡§ {a koelsch12, a ashutosh16, s MindGarage, University of Kaiserslautern, Germany Insiders Technologies GmbH, Kaiserslautern, Germany University of Fribourg, Switzerland §Lule˚a, University of Technology, Sweden" 6f5ce5570dc2960b8b0e4a0a50eab84b7f6af5cb,Low Resolution Face Recognition Using a Two-Branch Deep Convolutional Neural Network Architecture,"Low Resolution Face Recognition Using a Two-Branch Deep Convolutional Neural Network Architecture Erfan Zangeneh, Mohammad Rahmati, and Yalda Mohsenzadeh" 6f1a784ebb8df0689361afe26a2e5f7a1f4c66ca,A unified probabilistic framework for measuring the intensity of spontaneous facial action units,"A Unified Probabilistic Framework For Measuring The Intensity of Spontaneous Facial Action Units Yongqiang Li1, S. Mohammad Mavadati2, Mohammad H. Mahoor and Qiang Ji (AU)," 6f8fa219ea82ded79757de59250b7213f9f5a104,OriNet: A Fully Convolutional Network for 3D Human Pose Estimation,"Chenxu Luo1 Xiao Chu2 Alan Yuille1 Department of Computer Science The Johns Hopkins University Baltimore, MD 21218, USA Baidu Research (USA) Sunnyvale, CA 94089, USA LUO ET AL.: ORINET: A FULLY CONVOLUTIONAL NETWORK FOR 3D HUMAN POSE OriNet: A Fully Convolutional Network for 3D Human Pose Estimation" 6f08885b980049be95a991f6213ee49bbf05c48d,Author ' s personal copy Multi-Kernel Appearance Model ☆,"This article appeared in a journal published by Elsevier. The attached opy is furnished to the author for internal non-commercial research nd education use, including for instruction at the authors institution nd sharing with colleagues. Other uses, including reproduction and distribution, or selling or licensing copies, or posting to personal, institutional or third party websites are prohibited. In most cases authors are permitted to post their version of the rticle (e.g. in Word or Tex form) to their personal website or institutional repository. Authors requiring further information regarding Elsevier’s archiving and manuscript policies are encouraged to visit: http://www.elsevier.com/authorsrights" 6f41e2ba877ec690bd1c9e5e8742c4088f95c346,Video Frames Segmentation time Modular Network Clock Fires Executed,"Clockwork Convnets for Video Semantic Segmentation Evan Shelhamer(cid:63) Kate Rakelly(cid:63) Judy Hoffman(cid:63) Trevor Darrell UC Berkeley" 6f3054f182c34ace890a32fdf1656b583fbc7445,Age Estimation Robust to Optical and Motion Blurring by Deep Residual CNN,"Article Age Estimation Robust to Optical and Motion Blurring by Deep Residual CNN Jeon Seong Kang, Chan Sik Kim, Young Won Lee, Se Woon Cho and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro, 1-gil, Jung-gu, Seoul 100-715, Korea; (J.S.K.); (C.S.K.); (Y.W.L.); (S.W.C.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 9 March 2018; Accepted: 10 April 2018; Published: 13 April 2018" 6f2819172d270ceb568bf7586d812b298266bcbf,Edge Fields for Robust Object Proposal,"Edge Fields for Robust Object Proposal Junseok Kwon, Andrii Grygoriev, Yusun Lim, Youngki Hong, and Hansung Lee(cid:63) SW R&D Center, Samsung Electronics, Co. Ltd., Suwon, Rep. of Korea" 6f613ae524066802efb1b46a8673e62f9fc63321,An Energy-Efficient Hardware Implementation of HOG-Based Object Detection at 1080HD 60 fps with Multi-Scale Support,"(will be inserted by the editor) An Energy-ef‌f‌icient Hardware Implementation of HOG-based Object Detection at 1080HD 60 fps with Multi-scale Support Amr Suleiman · Vivienne Sze Received: date / Accepted: date" 6f42cb23262066b4034aba99bf674783ed6cac8b,An Empirical Evaluation of various Deep Learning Architectures for Bi-Sequence Classification Tasks,"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2762–2773, Osaka, Japan, December 11-17 2016." 6f6b4e2885ea1d9bea1bb2ed388b099a5a6d9b81,"Structured Output SVM Prediction of Apparent Age, Gender and Smile from Deep Features","Structured Output SVM Prediction of Apparent Age, Gender and Smile From Deep Features Michal Uˇriˇc´aˇr CMP, Dept. of Cybernetics FEE, CTU in Prague Radu Timofte Computer Vision Lab D-ITET, ETH Zurich Rasmus Rothe Computer Vision Lab D-ITET, ETH Zurich Luc Van Gool PSI, ESAT, KU Leuven CVL, D-ITET, ETH Zurich Jiˇr´ı Matas CMP, Dept. of Cybernetics FEE, CTU in Prague" 6fd4048bfe3123e94c2648e53a56bc6bf8ff4cdd,Micro-facial movement detection using spatio-temporal features,"Micro-Facial Movement Detection Using Spatio-Temporal Features Adrian Keith Davison A thesis submitted in partial fulfillment for the degree of Doctor of Philosophy Supervised by Dr. Moi Hoon Yap, Mr. Cliff Lansley, Dr. Nicholas Costen and Dr. Kevin Tan Faculty of Science and Engineering School of Computing, Mathematics and Digital Technology MANCHESTER METROPOLITAN UNIVERSITY February 2016" 6f3a8528841ea323d965d558195710fd8f916ffd,Knowledge Factorization,"Knowledge Factorization Anubhav Ashok Khushi Gupta Nishant Agrawal" 4893ce89df7afde71534af9b9fd5becb947f112e,Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network,"Noname manuscript No. (will be inserted by the editor) Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network Peng Lu∗ · Hangyu Lin∗ · Yanwei Fu† · Shaogang Gong · Yu-Gang Jiang · Xiangyang Xue the date of receipt and acceptance should be inserted later" 486f08c875e88b3f1f157e7de1ae2cf5176f5431,STRUCTURE-FROM-MOTION FOR CALIBRATION OF A VEHICLE CAMERA SYSTEM WITH NON-OVERLAPPING FIELDS-OF-VIEW IN AN URBAN ENVIRONMENT,"STRUCTURE-FROM-MOTION FOR CALIBRATION OF A VEHICLE CAMERA SYSTEM WITH NON-OVERLAPPING FIELDS-OF-VIEW IN AN URBAN ENVIRONMENT Photogrammetry & Remote Sensing, Technische Universitaet Muenchen, Germany - (alexander.hanel, A. Hanela, U. Stillaa Commission I, WG 9 KEY WORDS: vehicle cameras, camera calibration, structure from motion, bundle adjustment" 485eb41be3ce1600e9934167808b0319a6c3ec2f,A Novel Structural-Description Approach for Image Retrieval.,"A Novel Structural-Description Approach For Image Retrieval Christoph Rasche, Constantin Vertan Laboratorul de Analiza si Prelucrarea Imaginilor Universitatea Politehnica din Bucuresti Bucuresti 061071, RO" 48fb35946641351f7480a5b88567aae59e526d82,Generating faces for affect analysis,"Noname manuscript No. (will be inserted by the editor) Generating faces for affect analysis Dimitrios Kollias (cid:63) · Shiyang Cheng † · Evangelos Ververas ∗ · Irene Kotsia1 · Stefanos Zafeiriou2 Received: Sept 30th 2018 / Accepted: date" 48a42303559ea518ba06f54a8cfce4226bb0e77e,Urban tribes: Analyzing group photos from a social perspective,"Urban Tribes: Analyzing Group Photos from a Social Perspective Ana C. Murillo†, Iljung S. Kwak‡, Lubomir Bourdev§∗, David Kriegman‡, Serge Belongie‡ DIIS - Instituto de Ingenier´ıa de Arag´on. Universidad de Zaragoza, Spain §Facebook. 1601 Willow Road, Menlo Park, CA 94025, USA Computer Science and Engineering Department. University of California, San Diego, USA" 4850e40b0e69e30723cb027fdc4a38ee1322589b,Detecç̃ao de Landmarks Faciais Usando SVM,"XXIX SIMP ´OSIO BRASILEIRO DE TELECOMUNICAC¸ ˜OES - SBrT’11, 02-05 DE OUTUBRO DE 2011, CURITIBA, PR Detecc¸ ˜ao de Landmarks Faciais Usando SVM Gabriel M. Ara´ujo, Waldir S. S. J´unior, Eduardo A. B. da Silva, Siome K. Goldenstein Resumo— Este artigo aborda o problema de detecc¸ ˜ao de landmarks faciais. Neste contexto, n´os apresentamos um sistema de detecc¸ ˜ao de landmarks baseado em SVM (Support Vectors Machine) com kernel gaussiano. O m´etodo proposto ´e comparado om outros encontrados na literatura, sendo a avaliac¸ ˜ao feita em duas bases de dados, a BioID e a Color FERET. Os experimentos indicam que o m´etodo proposto supera os demais em precis˜ao e taxa de acerto. Como o sistema proposto possui uma complexidade computacional maior que os demais m´etodos, podemos utiliz´a-lo em aplicac¸ ˜oes off-line. Palavras-Chave— Reconhecimento de Padr˜oes, landmarks faci- is, M´aquina de Vetor Suporte." 48ac5466c5d0c90fa2c6c38c51c22627f966d687,Real Time People Detection Combining Appearance and Depth Image Spaces Using Boosted Random Ferns,"Real Time People Detection Combining Appearance and Depth Image Spaces using Boosted Random Ferns Victor Vaquero, Michael Villamizar, and Alberto Sanfeliu Institut de Robotica i Informatica Industrial - CSIC-UPC http://www.iri.upc.edu" 48705017d91a157949cfaaeb19b826014899a36b,PROBABILISTIC MULTI-PERSON TRACKING USING DYNAMIC BAYES NETWORKS,"PROBABILISTIC MULTI-PERSON TRACKING USING DYNAMIC BAYES NETWORKS T. Klinger, F. Rottensteiner, C. Heipke Institute of Photogrammetry and GeoInformation, Leibniz Universit¨at Hannover, Germany - (klinger, rottensteiner, KEY WORDS: Bayes network, Classification, Pedestrians, Tracking, Online, Video" 48c0059feb14ca3deedfa7e3b53fbc34bd6d8efb,Facial Expression Retrieval Using 3-Dimensional Mesh Sequences,"Facial Expression Retrieval Using -Dimensional Mesh Sequences Danelakis E. Antonios* National and Kapodistrian University of Athens Department of Informatics and Telecommunications" 48b7b474af1e86ee6e9db66972155c10cbbdace6,A new benchmark for vision-based cyclist detection,"Gothenburg, Sweden, June 19-22, 2016 978-1-5090-1820-8/16/$31.00 ©2016 IEEE" 483ca50670c5f7d33f7c722dd71105327a30ea60,Improving object classification using semantic attributes,"SU, ALLAN, JURIE: SEMANTIC ATTRIBUTES Improving object classification using semantic attributes Yu Su http://users.info.unicaen.fr/~ysu/ Moray Allan http://users.info.unicaen.fr/~mallan/ Frédéric Jurie http://users.info.unicaen.fr/~jurie/ GREYC Université de Caen 4032 Caen Cedex France" 489decd84645b77d31001d17a66abb92bb96c731,Learning View-Specific Deep Networks for Person Re-Identification,"Learning View-Specific Deep Networks for Person Re-Identification Zhanxiang Feng, Jianhuang Lai, and Xiaohua Xie" 48b38d157272f03f6b44c0df61130534d11d8569,Natural Language Guided Visual Relationship Detection,"oard)(person-behind-kid)(skate board-on-street)(person-sit on-street)...ImageVisual relationshipsFigure1:Visualrelationshipsrepresenttheinteractionsbe-tweenobservedobjects.Eachrelationshiphasthreeele-ments:subject,predicateandobject.HereisanexampleimagefromVisualGenome[17].Ourproposedmethodisabletoeffectivelydetectnumerouskindsofdifferentrela-tionshipsfromsuchimage.objectsinimages.Therelationshipscanberepresentedinatripletformofhsubject-predicate-objecti,e.g.,hkid-on-skateboardi,asshowninFig.1.Anaturalapproachforthistaskistotreatitasaclassificationproblem:eachkindofrelationships/phraseisarelationcategory[32],asshowninFig.2.Totrainsuchreliableandrobustmodel,suffi-cienttrainingsamplesforeachpossiblehsubject-predicate-objecticombinationareessential.ConsidertheVisualRe-lationshipDataset(VRD)[24],withN=100objectcate-goriesandK=70predicates,thenthereareN2K=700kcombinationsintotal.However,itcontainsonly38kre-lationships,whichmeansthateachcombinationhaslessthan1sampleonaverage.Thepreviousclassification-basedworkscanonlydetectthemostcommonrelationships,e.g.,[32]studiedonly13frequentrelationships.Anotherpopularstrategyistodetecttherelationshippredicatesandtheobjectcategoriesindependently.Al-thoughthenumberofcategoriesdecreasesdramatically,thesemanticrelationshipbetweentheobjectsandthepredi-catesareignored.Consequently,thephrasewhichhasthesamepredicatebutdifferentagentsisconsideredasthesametypeofrelationship.Forinstance,the”clock-on-1" 483f85e1ebef9d10a951b3c01751892aca92a2c2,Adaptive Classification for Person Re-identification Driven by Change Detection,"Adaptive Classification for Person Re-Identification Driven by Change Detection C. Pagano1, E. Granger1, R. Sabourin1, G. L. Marcialis2 and F. Roli2 Lab. d’imagerie, de vision et d’intelligence artificielle, ´Ecole de technologie sup´erieure, Universit´e du Qu´ebec, Montreal, Canada Pattern Recognition and Applications Group, Dept. of Electrical and Electronic Engineering, {eric.granger, University of Cagliari, Cagliari, Italy Keywords: Multi-Classifier Systems, Incremental Learning, Adaptive Biometrics, Change Detection, Face Recognition, Video Surveillance." 488676e61fcf7b79d83c25fb103c8d8a854d8987,Leveraging Convolutional Pose Machines for Fast and Accurate Head Pose Estimation,"Leveraging Convolutional Pose Machines for Fast and Accurate Head Pose Estimation Yuanzhouhan Cao1, Olivier Can´evet 1 and Jean-Marc Odobez1,2" 48394fa271cd182372c6fb82342d7080554f735c,Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing,"Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing Noha Radwan, Abhinav Valada and Wolfram Burgard Journal Title XX(X):1–21 (cid:13)The Author(s) 2018 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/ToBeAssigned www.sagepub.com/" 48b4f49ec708677fc9f70edc74fd0f92ef986406,CS 168 : The Modern Algorithmic Toolbox Lecture # 6 : Stochastic Gradient Descent and Regularization,"CS168: The Modern Algorithmic Toolbox Lecture #6: Stochastic Gradient Descent and Regularization Tim Roughgarden & Gregory Valiant∗ April 13, 2016 Context Last lecture we covered the basics of gradient descent, with an emphasis on the intuition ehind and geometry underlying the method, plus a concrete instantiation of it for the problem of linear regression (fitting the best hyperplane to a set of data points). This basic method is already interesting and useful in its own right (see Homework #3). This lecture we’ll cover two extensions that, while simple, will bring your knowledge a step loser to the state-of-the-art in modern machine learning. The two extensions have different haracters. The first concerns how to actually solve (computationally) a given unconstrained minimization problem, and gives a modification of basic gradient descent — “stochastic gradient descent” — that scales to much larger data sets. The second extension concerns problem formulation rather than implementation, namely the choice of the unconstrained optimization problem to solve (i.e., the objective function f ). Here, we introduce the idea of “regularization,” with the goal of avoiding overfitting the function learned to the data set t hand, even for very high-dimensional data. Recap" 48d299fe3303c80f840816fc76971a42b4a8b624,Predicting Important Objects for Egocentric Video Summarization,"http://dx.doi.org/10.1007/s11263-014-0794-5 Predicting Important Objects for Egocentric Video Summarization Yong Jae Lee · Kristen Grauman Received: date / Accepted: date" 4875bed500321dec353959a556541715da5c9d18,A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation,"A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation R. Romijnders Eindhoven, University of Technology P. Meletis G. Dubbelman" 48f45accce6a4a22e4ead41fe292a915f3531f5b,Active Learning for Visual Question Answering: An Empirical Study,"Active Learning for Visual Question Answering: An Empirical Study Xiao Lin Virginia Tech Devi Parikh Georgia Tech" 485e0d178bafa959ac956aa8de6556a2439c6663,Learning from Examples to Generalize over Pose and Illumination,"Learning from Examples to Generalize over Pose nd Illumination Marco K. M¨uller and Rolf P. W¨urtz Institute f¨ur Neural Computation, Ruhr-University, 44780 Bochum, Germany" 48499deeaa1e31ac22c901d115b8b9867f89f952,Interim Report of Final Year Project HKU-Face : A Large Scale Dataset for Deep Face Recognition,"Interim Report of Final Year Project HKU-Face: A Large Scale Dataset for Deep Face Recognition Haicheng Wang 035140108 Haoyu Li 035141841 COMP4801 Final Year Project Project Code: 17007" 4871300f1e5a58ce920e6b5be14e89c5da4aa4c4,Manifold Learning for Video-to-Video Face Recognition,"Manifold Learning for Video-to-Video Face Recognition" 48be9300acdc484100436f32bd409a89a7dc1ef7,Chapter 4 FACE RECOGNITION AND ITS APPLICATIONS,"Chapter 4 FACE RECOGNITION AND ITS APPLICATIONS {aws, Andrew W. Senior and Ruud M. Bolle IBM T.J.Watson Research Center, P.O. Box 704, Yorktown Heights, NY 10598, USA." 484c4eec34e985d8ca0c20bf83efc56881180709,Efficient semantic image segmentation with superpixel pooling,"Ef‌f‌icient semantic image segmentation with superpixel pooling Mathijs Schuurmans Maxim Berman Matthew B. Blaschko Dept. ESAT, Center for Processing Speech and Images KU Leuven, Belgium {maxim.berman, June 8, 2018" 48103763fa317cf769e783966f02af9a18030765,YOLO 4 D : A Spatio-temporal Approach for Real-time Multi-object Detection and Classification from LiDAR Point Clouds,"YOLO4D: A Spatio-temporal Approach for Real-time Multi-object Detection and Classification from LiDAR Point Clouds Anonymous Author(s) Affiliation Address email" 484c2617471fd742c4806f9281e5add45c6831a7,LSTM Self-Supervision for Detailed Behavior Analysis,"LSTM Self-Supervision for Detailed Behavior Analysis Biagio Brattoli1∗, Uta B¨uchler1∗, Anna-Sophia Wahl2, Martin E. Schwab2, Bj¨orn Ommer1 HCI / IWR, Heidelberg University, Germany Department of HST, ETH Zurich, Switzerland" 488493dc29c844b36660395266d8d347c7cfa9ce,Towards Flexible Classification : Cost-Aware Online Query of Cascades and Operating Points,"Towards Flexible Classification: Cost-Aware Online Query of Cascades and Operating Points Brandyn White, Andrew Miller, Tom Yeh, and Larry S. Davis University of Maryland: College Park" 48186494fc7c0cc664edec16ce582b3fcb5249c0,P-CNN: Pose-Based CNN Features for Action Recognition,"P-CNN: Pose-based CNN Features for Action Recognition Guilhem Ch´eron∗ † Ivan Laptev∗ INRIA Cordelia Schmid†" 48c474ab86920c70d0a404a80d68096a8fa9723f,Multiband Curvelet-Based Technique for Audio Visual Recognition over Internet Protocol,"Multiband Curvelet-Based Technique for Audio Visual Recognition over Internet Protocol Sue Inn Ch’ng1, KahPhooi Seng2, Fong Tien Ong1, and Li-Minn Ang1 University of Nottingham Malaysia Campus JalanBroga, 43500 Semenyih, Selangor, Malaysia Sunway University No. 5, JalanUniversiti, Bandar Sunway, 46150 PetalingJaya, Selangor, Malaysia" 4874daed0f6a42d03011ed86e5ab46f231b02c13,GridFace: Face Rectification via Learning Local Homography Transformations,"GridFace: Face Rectification via Learning Local Homography Transformations Erjin Zhou, Zhimin Cao, and Jian Sun Face++, Megvii Inc." 4850af6b54391fc33c8028a0b7fafe05855a96ff,Discovering useful parts for pose estimation in sparsely annotated datasets,"Discovering Useful Parts for Pose Estimation in Sparsely Annotated Datasets Mikhail Breslav1, Tyson L. Hedrick2, Stan Sclaroff1, and Margrit Betke1 Department of Computer Science and 2Department of Biology Boston University and 2University of North Carolina" 480810001ed845ec04a20b00461a8a82fcffbb52,Autistic Traits and Brain Activation during Face-to-Face Conversations in Typically Developed Adults,"Autistic Traits and Brain Activation during Face-to-Face Conversations in Typically Developed Adults Masashi Suda, Yuichi Takei, Yoshiyuki Aoyama, Kosuke Narita, Noriko Sakurai, Masato Fukuda*, Masahiko Mikuni Department of Psychiatry and Neuroscience, Gunma University Graduate School of Medicine, Gunma, Japan" 48bc87ccc6b6e2d318f91d5f1886432806fec553,Multiaccuracy: Black-Box Post-Processing for Fairness in Classification,"Multiaccuracy: Black-Box Post-Processing for Fairness in Michael P. Kim∗† Classification Amirata Ghorbani∗ James Zou" 486a0044b9c86c6f648f153f3d3f2e534342b754,Trajectories and Maneuvers of Surrounding Vehicles With Panoramic Camera Arrays,"Trajectories and Maneuvers of Surrounding Vehicles with Panoramic Camera Arrays Jacob V. Dueholm, Miklas S. Kristoffersen, Ravi K. Satzoda, Thomas B. Moeslund, and Mohan M. Trivedi" 48cfc5789c246c6ad88ff841701204fc9d6577ed,Age Invariant Face Recognition Based on DCT Feature Extraction and Kernel Fisher Analysis,"J Inf Process Syst, Vol.12, No.3, pp.392~409, September 2016 ISSN 1976-913X (Print) ISSN 2092-805X (Electronic) Age Invariant Face Recognition Based on DCT Feature Extraction and Kernel Fisher Analysis Leila Boussaad*, Mohamed Benmohammed**, and Redha Benzid***" f4373f5631329f77d85182ec2df6730cbd4686a9,Recognizing Gender from Human Facial Regions using Genetic Algorithm,"Soft Computing manuscript No. (will be inserted by the editor) Recognizing Gender from Human Facial Regions using Genetic Algorithm Avirup Bhattacharyya · Rajkumar Saini · Partha Pratim Roy · Debi Prosad Dogra · Samarjit Kar Received: date / Accepted: date" f439f9a0bd535eab00cbb93c1fa7083615a08d1a,Procedural Modeling and Physically Based Rendering for Synthetic Data Generation in Automotive Applications,"Procedural Modeling and Physically Based Rendering for Synthetic Data Generation in Automotive Applications Apostolia Tsirikoglou1,∗ Joel Kronander1 Magnus Wrenninge2,† Jonas Unger1,‡ Link¨oping University, Sweden 7D Labs Figure 1: Example images produced using our method for synthetic data generation." f4ebbeb77249d1136c355f5bae30f02961b9a359,Human Computation for Attribute and Attribute Value Acquisition,"Human Computation for Attribute and Attribute Value Acquisition Edith Law, Burr Settles, Aaron Snook, Harshit Surana, Luis von Ahn, Tom Mitchell School of Computer Science Carnegie Melon University" f47404424270f6a20ba1ba8c2211adfba032f405,Identification of Face Age range Group using Neural Network,"International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (ISSN 2250-2459, Volume 2, Issue 5, May 2012) Identification of Face Age range Group using Neural Network Sneha Thakur1, Ligendra Verma2 1M.Tech scholar, CSE, RITEE Raipur 2 Reader, MCA dept, RITEE Raipur" f47518fcd69cdbb43dc88fe5259f4f4c61921313,A Compact Embedding for Facial Expression Similarity,"A Compact Embedding for Facial Expression Similarity Raviteja Vemulapalli Google AI Aseem Agarwala Google AI" f4dce4266a4249596d4454d73c1f0fd629c7fcd6,Distributed Compressive Sensing based Near Infrared and Visible Images Fusion for Face Recognition,"International Journal of Signal Processing, Image Processing and Pattern Recognition Vol.9, No.4 (2016), pp.281-292 http://dx.doi.org/10.14257/ijsip.2016.9.4.26 Distributed Compressive Sensing based Near Infrared and Visible Images Fusion for Face Recognition Dan Wei Shanghai University of Engineering Science" f4f6fc473effb063b7a29aa221c65f64a791d7f4,Facial expression recognition in the wild based on multimodal texture features,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 4/20/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use FacialexpressionrecognitioninthewildbasedonmultimodaltexturefeaturesBoSunLiandongLiGuoyanZhouJunHeBoSun,LiandongLi,GuoyanZhou,JunHe,“Facialexpressionrecognitioninthewildbasedonmultimodaltexturefeatures,”J.Electron.Imaging25(6),061407(2016),doi:10.1117/1.JEI.25.6.061407." f442a2f2749f921849e22f37e0480ac04a3c3fec,Critical Features for Face Recognition in Humans and Machines,"Critical Features for Face Recognition in Humans and Machines Naphtali Abudarham1, Lior Shkiller1, Galit Yovel1,2 1School of Psychological Sciences, 2Sagol School of Neuroscience Tel Aviv University, Tel Aviv, Israel Correspondence regarding this manuscript should be addressed to: Galit Yovel School of Psychological Sciences & Sagol School of Neuroscience Tel Aviv University Tel Aviv, 69978, Israel Email:" f423e2072441925a16d95e7092005abf602b7145,Survey on 2D and 3D Human Pose Recovery.,"Survey on 2D and 3D Human Pose Recovery Xavier Perez-Sala, Email: a;c, Sergio Escalera, Email: b;c and Cecilio Angulo, Email: a CETpD-UPC Technical Research Center for Dependency Care and Autonomous Living, Universitat Polit(cid:18)ecnica de Catalunya, Ne(cid:18)apolis, Rambla de l’Exposici(cid:19)o, 59-69, 08800 Vilanova i la Geltru, Spain Dept. Mathematics, Universitat de Barcelona, Gran Via de les Corts Catalanes Computer Vision Center, Campus UAB, Edi(cid:12)ci 0, 08193, Bellaterra, Spain 585, 08007, Barcelona, Spain" f4ce7c36586c27783a1b0e737c2834f39f9d029d,Advanced non linear dimensionality reduction methods for multidimensional time series : applications to human motion analysis,"Advanced Nonlinear Dimensionality Reduction Methods for Multidimensional Time Series: Application to Human Motion Analysis Michał Lewandowski Submitted in partial fulfilment of the requirements of Kingston University for the degree of Doctor of Philosophy June, 2011" f412d9d7bc7534e7daafa43f8f5eab811e7e4148,Running Head : Anxiety and Emotional Faces in WS 2,"Durham Research Online Deposited in DRO: 6 December 2014 Version of attached le: Accepted Version Peer-review status of attached le: Peer-reviewed Citation for published item: Kirk, H. E. and Hocking, D. R. and Riby, D. M. and Cornish, K. M. (2013) 'Linking social behaviour and nxiety to attention to emotional faces in Williams syndrome.', Research in developmental disabilities., 34 (12). pp. 4608-4616. Further information on publisher's website: http://dx.doi.org/10.1016/j.ridd.2013.09.042 Publisher's copyright statement: NOTICE: this is the author's version of a work that was accepted for publication in Research in Developmental Disabilities. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reected in this document. Changes may have been made to this work since it was submitted for publication. A denitive version was subsequently published in Research in Developmental Disabilities, 34, 12, December 2013, 10.1016/j.ridd.2013.09.042. Additional information:" f4e65ab81a0f4ffa50d0c9bc308d7365e012cc75,Deep Active Learning for Video-based Person Re-identification,"Deep Active Learning for Video-based Person Re-identification Menglin Wang1, Baisheng Lai2, Zhongming Jin2, Xiaojin Gong1, Jianqiang Huang2, Xiansheng Hua2 Zhejiang University; 2 Alibaba Group {menglinwang, {baisheng.lbs, zhongming.jinzm, jianqiang.hjq," f43327075c17e71ee713ad727aa473230a432a90,Geometry meets semantics for semi-supervised monocular depth estimation,"Geometry meets semantics for semi-supervised monocular depth estimation Pierluigi Zama Ramirez, Matteo Poggi, Fabio Tosi, Stefano Mattoccia, and Luigi Di Stefano University of Bologna, Viale del Risorgimento 2, Bologna, Italy" f42dca4a4426e5873a981712102aa961be34539a,Next-Flow: Hybrid Multi-Tasking with Next-Frame Prediction to Boost Optical-Flow Estimation in the Wild,"Next-Flow: Hybrid Multi-Tasking with Next-Frame Prediction to Boost Optical-Flow Estimation in the Wild Nima Sedaghat University of Freiburg Germany" f43b60a33c585827bfa354d3d49fb148a1c26c3f,Identifying Well-formed Natural Language Questions,"Identifying Well-formed Natural Language Questions Manaal Faruqui Dipanjan Das Google AI Language" f41ae7b47391f10f30368c519d8fe3e904e3a35f,A Random Extension for Discriminative Dimensionality Reduction and Metric Learning,"A Random Extension for Discriminative Dimensionality Reduction and Metric Learning Adrian Perez-Suay, Francesc J. Ferri, and Jes´us V. Albert Dept. Inform`atica, Universitat de Val`encia. Spain" f445493badf53febbaeab340a4fca98d9e4ab7f7,Do CIFAR-10 Classifiers Generalize to CIFAR-10?,"Do CIFAR-10 Classifiers Generalize to CIFAR-10? Benjamin Recht UC Berkeley Rebecca Roelofs UC Berkeley Ludwig Schmidt Vaishaal Shankar UC Berkeley June 4, 2018" f4808e78bc648f9e1829c83a68a3e8ed4e7cf325,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" f4b40b3dc27897fdc40f419a42d64fd1ff80cc9d,A Dual-Source Approach for 3D Human Pose Estimation from a Single Image,"SUBMITTED TO COMPUTER VISION AND IMAGE UNDERSTANDING. A Dual-Source Approach for 3D Human Pose Estimation from a Single Image Umar Iqbal*, Andreas Doering*, Hashim Yasin, Björn Krüger, Andreas Weber, and Juergen Gall" f44af3b10a67fe62fd26eb82dd228a3cdeb980e1,"Understand, Compose and Respond - Answering Visual Questions by a Composition of Abstract Procedures","Understand, Compose and Respond Understand, Compose and Respond - Answering Visual" f49f1028052baa1588376a78a9dc64812748555e,Feature Fusion using Extended Jaccard Graph and Stochastic Gradient Descent for Robot,"JOURNAL OF LATEX CLASS FILES Feature Fusion using Extended Jaccard Graph and Stochastic Gradient Descent for Robot Shenglan Liu, Muxin Sun, Wei Wang, Feilong Wang" 0ad4a9fad873e9c4914fd2464404b211f295d7b6,New insights into Laplacian similarity search,"New Insights into Laplacian Similarity Search Xiao-Ming Wu1, Zhenguo Li2, Shih-Fu Chang1 Department of Electrical Engineering, Columbia University. 2Huawei Noah’s Ark Lab, Hong Kong. (a) Λ = I, AP = 0.14 (b) Λ = D, AP = 0.67 (c) Λ = H, AP = 0.67 (a) Λ = I, AP = 0.27 (b) Λ = D, AP = 0.17 (c) Λ = H, AP = 0.27 Figure 1: Top 40 retrieved images on extended YaleB, with false images highlighted in blue box (query on top left comes from the sparsest cluster). Figure 2: Top 40 retrieved images on CIFAR-10, with positive images high- lighted in magenta box (query on top left comes from the densest cluster). Similarity metrics are important building blocks of many visual applica- tions such as image retrieval, image segmentation, and manifold learning. Well-known similarity metrics include personalized PageRank, hitting and ommute times, and the pseudo-inverse of graph Laplacian. Despite their popularity, the understanding of their behaviors is far from complete, and their use in practice is mostly guided by empirical trials and error analy- sis. This paper bridges this gap by investigating the fundamental design of" 0ae3182836b1b962902d664ddd524e8554b742cf,Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model,"Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model Bo Li1,2, Tianfu Wu2,(cid:2), and Song-Chun Zhu2 Beijing Lab of Intelligent Information Technology, Beijing Institute of Technology Department of Statistics, University of California, Los Angeles" 0a481d2472958ca243a79161af97544adc67f4fe,Facial Image Processing,"EURASIP Journal on Image and Video Processing Facial Image Processing Guest Editors: Christophe Garcia, Jörn Ostermann, and Tim Cootes" 0a2d2b79ba39e2140c93543b8ce873f106c08e3d,Semi-Supervised Sparse Representation Based Classification for Face Recognition With Insufficient Labeled Samples,"Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples Yuan Gao, Jiayi Ma, and Alan L. Yuille Fellow, IEEE" 0a60e76e6983e1647469172a50907023913b0c9f,Longitudinal study of amygdala volume and joint attention in 2- to 4-year-old children with autism.,"ORIGINAL ARTICLE Longitudinal Study of Amygdala Volume and Joint Attention in 2- to 4-Year-Old Children With Autism Matthew W. Mosconi, PhD; Heather Cody-Hazlett, PhD; Michele D. Poe, PhD; Guido Gerig, PhD; Rachel Gimpel-Smith, BA; Joseph Piven, MD Context: Cerebral cortical volume enlargement has been reported in 2- to 4-year-olds with autism. Little is known bout the volume of subregions during this period of de- velopment. The amygdala is hypothesized to be abnormal in volume and related to core clinical features in autism. Objectives: To examine amygdala volume at 2 years with follow-up at 4 years of age in children with autism and to explore the relationship between amygdala volume and selected behavioral features of autism. Design: Longitudinal magnetic resonance imaging study. Setting: University medical setting. Participants: Fifty autistic and 33 control (11 devel- opmentally delayed, 22 typically developing) children be- tween 18 and 35 months (2 years) of age followed up at 2 to 59 months (4 years) of age." 0a3051c8dde80975640d42dca21fac17ed60f987,A Hierarchical Switching Linear Dynamical System Applied to the Detection of Sepsis in Neonatal Condition Monitoring, 0a6a25ee84fc0bf7284f41eaa6fefaa58b5b329a,Neural Networks Regularization Through Representation Learning,"THÈSEPour obtenir le diplôme de doctorat Spécialité Informatique Préparée au sein de « l'INSA Rouen Normandie » Présentée et soutenue parSoufiane BELHARBIThèse dirigée par Sébastien ADAM, laboratoire LITIS Neural Networks Regularization Through Representation LearningThèse soutenue publiquement le 06 Juillet 2018 devant le jury composé deSébastien ADAMProfesseur à l'Université de Rouen NormandieDirecteur de thèseClément CHATELAINMaître de conférence à l'INSA Rouen NormandieEncadrant de thèseRomain HÉRAULTMaître de conférence à l'INSA Rouen NormandieEncadrant de thèseElisa FROMONTProfesseur à l'Université de Rennes 1Rapporteur de thèseThierry ARTIÈRESProfesseur à l'École Centrale MarseilleRapporteur de thèseJohn LEEProfesseur à l'Université Catholique de LouvainExaminateur de thèseDavid PICARDMaître de conférences à l'École Nationale Supérieure de l'Électronique et de ses ApplicationsExaminateur de thèseFrédéric JURIEProfesseur à l' Université de Caen NormandieInvité" 0a1e3d271fefd506b3a601bd1c812a9842385829,Face Recognition Using 3D Directional Corner Points,"Face Recognition using 3D Directional Corner Points Author Yu, Xun, Gao, Yongsheng, Zhou, Jun Published Conference Title Pattern Recognition (ICPR), 2014 22nd International Conference on https://doi.org/10.1109/ICPR.2014.483 Copyright Statement © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Downloaded from http://hdl.handle.net/10072/66408 Link to published version http://www.icpr2014.org/index.htm Griffith Research Online https://research-repository.griffith.edu.au" 0aa9872daf2876db8d8e5d6197c1ce0f8efee4b7,Timing is everything : a spatio-temporal approach to the analysis of facial actions,"Imperial College of Science, Technology and Medicine Department of Computing Timing is everything A spatio-temporal approach to the analysis of facial ctions Michel Fran¸cois Valstar Submitted in part fulfilment of the requirements for the degree of Doctor of Philosophy in Computing of Imperial College, February 2008" 0afb2e3db5b8ffefe6a52fdfc5ee813c25353382,Semi-supervised Learning on Real-time Pedestrian Detection System,"3rd ITS World Congress, Melbourne, Australia, 10–14 October 2016 Paper number ITS-0236 Semi-supervised Learning on Real-time Pedestrian Detection System Kuo-Ching Chang1*, Zhen-Wei Zhu1, Han-Wen Huang1, Chuan-Ren Lee1 . Automotive Research and Testing Center, Taiwan * No.6, Lugong S. 7th Rd., Lukang, Changhua County, +886-4-7811222 #2323," 0ad0a1293f80c838c843726eeddf5a97f33f0c89,Understanding image virality,"Understanding Image Virality Arturo Deza UC Santa Barbara Devi Parikh Virginia Tech" 0ae07f24251946b2086fb992031c298ada2805de,Exemplar-AMMs: Recognizing Crowd Movements From Pedestrian Trajectories,"JOURNAL OF LATEX CLASS FILES, VOL. 13, NO. 9, SEPTEMBER 2014 Exemplar-AMMs: Recognizing Crowd Movements from Pedestrian Trajectories Wenxi Liu, Rynson W.H. Lau, Xiaogang Wang, Dinesh Manocha" 0a4639e09fc051c726da7feb2b3af51ffb278e3a,Endogenous Testosterone Modulates Prefrontal–Amygdala Connectivity during Social Emotional Behavior,"Cerebral Cortex October 2011;21:2282--2290 doi:10.1093/cercor/bhr001 Advance Access publication February 21, 2011 Endogenous Testosterone Modulates Prefrontal--Amygdala Connectivity during Social Emotional Behavior Inge Volman1,2, Ivan Toni1, Lennart Verhagen1,3 and Karin Roelofs2,4,1 Donders Institute for Brain, Cognition and Behaviour, Radboud University Nijmegen, 6500 HB Nijmegen, the Netherlands, 2Leiden University, Institute of Psychology & Leiden Institute for Brain and Cognition (LIBC), 2300 RB Leiden the Netherlands, Experimental Psychology, Helmholtz Institute, Utrecht University, 3508 TC, Utrecht, the Netherlands and 4Behavioral Science Institute (BSI), Radboud University Nijmegen, 6500 HE Nijmegen, the Netherlands Address correspondence to Inge Volman, Donders Institute for Brain, Cognition and Behaviour, Centre for Cognitive Neuroimaging, PO Box 9101, 6500 HB Nijmegen, the Netherlands. Email: respectively. Affect-congruent It is clear that the steroid hormone testosterone plays an important role in the regulation of social emotional behavior, but it remains unknown which neural circuits mediate these hormonal influences in humans. We investigated the modulatory effects of endogenous testosterone on the control of social emotional behavior by applying functional magnetic resonance imaging while healthy male participants performed a social approach--avoidance task. This" 0a5bcd1c9e88ec6b2fcf4699a8a0a93547bd07b2,Courteous Autonomous Cars,"Courteous Autonomous Cars Liting Sun1, Wei Zhan1, Masayoshi Tomizuka1, and Anca D. Dragan2" 0a23bdc55fb0d04acdac4d3ea0a9994623133562,Large-scale Bisample Learning on ID vs. Spot Face Recognition,"Noname manuscript No. (will be inserted by the editor) Large-scale Bisample Learning on ID vs. Spot Face Recognition Xiangyu Zhu∗ · Hao Liu∗ · Zhen Lei · Hailin Shi · Fan Yang · Dong Yi · Stan Z. Li Received: date / Accepted: date" 0a773ed20a5920897788dd6f0d63c20defca8ab0,ConceptLearner: Discovering visual concepts from weakly labeled image collections,"ConceptLearner: Discovering Visual Concepts from Weakly Labeled Image Collections Bolei Zhou†, Vignesh Jagadeesh‡, Robinson Piramuthu‡ MIT ‡eBay Research Labs" 0a6d344112b5af7d1abbd712f83c0d70105211d0,Constrained Local Neural Fields for Robust Facial Landmark Detection in the Wild,"Constrained Local Neural Fields for robust facial landmark detection in the wild Tadas Baltruˇsaitis Peter Robinson University of Cambridge Computer Laboratory USC Institute for Creative Technologies 5 JJ Thomson Avenue Louis-Philippe Morency 2015 Waterfront Drive" 0ab1fa904323c440ec6e185e2d607ccc45225df6,Paper on Face Recognition Techniques,"ISSN: 2278 – 1323 International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) Volume 1, Issue 8, October 2012 A Review Paper on Face Recognition Techniques Sujata G. Bhele1 and V. H. Mankar2 in real interesting area" 0a8ab703839ae585c2f27099616c40974cbeeda2,"Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs","Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs Siddhartha Chandra Iasonas Kokkinos INRIA GALEN & Centrale Sup´elec, Paris, France" 0a85bdff552615643dd74646ac881862a7c7072d,Beyond frontal faces: Improving Person Recognition using multiple cues,"Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues Ning Zhang1,2, Manohar Paluri2, Yaniv Taigman2, Rob Fergus2, Lubomir Bourdev2 {mano, yaniv, robfergus, UC Berkeley Facebook AI Research" 0a66015112da542b9b6687e4b3c9ff73565d0844,A k-NN Approach for Scalable Image Annotation Using General Web Data,"A k-NN Approach for Scalable Image Annotation Using General Web Data Mauricio Villegas and Roberto Paredes Institut Tecnol`ogic d’Inform`atica Universitat Polit`ecnica de Val`encia Cam´ı de Vera s/n, 46022 Val`encia, Spain" 0a40415bdfe4bc9ef7e019e4f1442a9fb61f58b2,Automatic Discovery and Geotagging of Objects from Street View Imagery,"Automatic Discovery and Geotagging of Objects from Street View Imagery Vladimir A. Krylov Eamonn Kenny Rozenn Dahyot ADAPT Centre, School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland" 0a6a173a1d1d36285bae97f98f4b901067d40097,Similarity learning on an explicit polynomial kernel feature map for person re-identification,"Similarity Learning on an Explicit Polynomial Kernel Feature Map for Person Re-Identification Dapeng Chen y, Zejian Yuan y, Gang Huaz, Nanning Zhengy, Jingdong Wang x y Xi’an Jiaotong University zStevens Institute of Technology xMicrosoft Research" 0aaa66501298c3df27293eca7906e93d8013b729,Fast HOG based person detection devoted to a mobile robot with a spherical camera,"Fast HOG based Person Detection devoted to a Mobile Robot with a Spherical Camera A. A. Mekonnen1, C. Briand1, F. Lerasle1, A. Herbulot1" 0ad17977977a5ed3219e763696c6b4267b36c1f4,PERSISTENT OBJECT TRACKING WITH RANDOMIZED FORESTS,"PERSISTENT OBJECT TRACKING WITH RANDOMIZED FORESTS Tobias Klinger and Daniel Muhle Institute of Photogrammetry and GeoInformation Nienburger Strasse 1, 30167 Hannover, Germany Leibniz Universitaet Hannover http://www.ipi.uni-hannover.de/ KEY WORDS: Learning, Detection, Decision Support, Tracking, Real-time, Video Commission III/5" 0a55e4191c90ec1edb8d872237a2dacd5f6eda90,"Intentional Minds: A Philosophical Analysis of Intention Tested through fMRI Experiments Involving People with Schizophrenia, People with Autism, and Healthy Individuals","HUMAN NEUROSCIENCE Intentional minds: a philosophical analysis of intention tested through fMRI experiments involving people with schizophrenia, people with autism, and healthy individuals Review ARticle published: 02 February 2011 doi: 10.3389/fnhum.2011.00007 Bruno G. Bara1,2*, Angela Ciaramidaro1, Henrik Walter 3 and Mauro Adenzato1,2 Department of Psychology, Center for Cognitive Science, University of Turin, Turin, Italy Neuroscience Institute of Turin, University of Turin, Turin, Italy Department of Psychiatry and Psychotherapy, Charité Universitätsmedizin Berlin, Berlin, Germany Edited by: Ivan Toni, Radboud University, Netherlands Reviewed by: Ivan Toni, Radboud University, Netherlands Roel M. Willems, University of California Berkeley, USA *Correspondence:" 0ae9cc6a06cfd03d95eee4eca9ed77b818b59cb7,"Multi-task, multi-label and multi-domain learning with residual convolutional networks for emotion recognition","Noname manuscript No. (will be inserted by the editor) Multi-task, multi-label and multi-domain learning with residual convolutional networks for emotion recognition Gerard Pons · David Masip Received: date / Accepted: date" 0a20e2fbe52efdb794b7566ce5233c41f4c5efc9,Monocular Visual Scene Understanding from Mobile Platforms,"Monocular Visual Scene Understanding from Mobile Platforms A dissertation for the degree of Doktor-Ingenieur (Dr.-Ing.) pproved by TECHNISCHE UNIVERSITÄT DARMSTADT Fachbereich Informatik presented by CHRISTIAN ALEXANDER WOJEK Dipl.-Inform. orn in Schillingsfürst, Germany Examiner: Prof. Dr. Bernt Schiele Co-examiner: Prof. Dr. Luc Van Gool Date of Submission: 14th of May, 2010 0th of June, 2010 Date of Defense: Darmstadt, 2010" 0a811063cfd674275f91006d28cb8620c781e817,Image recognition based on hidden Markov eigen-image models using variational Bayesian method,"IMAGE RECOGNITION BASED ON HIDDEN MARKOV EIGEN-IMAGE MODELS USING VARIATIONAL BAYESIAN METHOD Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda Nagoya Institute of Technology APSIPA ASC 10/30/2013" 0a572c16e635312f118d1a53f0ff6446402d3c32,Learning with proxy supervision for end-to-end visual learning,"Learning with Proxy Supervision for End-To-End Visual Learning Jiˇr´ı ˇCerm´ak1∗ Anelia Angelova2" 0adc3ad7c40c475d5878f9bdfeb3c8b59e482c17,Learning local embedding deep features for person re-identification in camera networks,"Zhang and Huang EURASIP Journal on Wireless Communications and Networking (2018) 2018:85 https://doi.org/10.1186/s13638-018-1101-x RESEARCH Open Access Learning local embedding deep features for person re-identification in camera networks Zhong Zhang1,2* and Meiyan Huang1,2" 0a8c6b40d6ca75bc1995083825e362137b130624,Nonparametric Method for Data-driven Image Captioning,"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 592–598, Baltimore, Maryland, USA, June 23-25 2014. c(cid:13)2014 Association for Computational Linguistics" 0a87d781fe2ae2e700237ddd00314dbc10b1429c,"Distribution Statement "" A "" ( Approved for public release , Distribution Unlimited ) Working Paper An Artificial Intelligence / Machine Learning Perspective on Social Simulation New Data and New Challenges","Distribution Statement A: Approved for public release; distribution unlimited. Multi-scale HOG Prescreening Algorithm for Detection of Buried Explosive Hazards in FL-IR and FL-GPR Data *University of Missouri, Electrical and Computer Engineering Department, Columbia, MO K. Stone*, J. M. Keller*, D. Shaw*" 0ad545407966e1630b5e51ad8f7dbd2780de966e,Multimodal Authentication Using Asynchronous HMMs,"Multimodal Authentication using Asynchronous Samy Bengio Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP), CP 592, rue du Simplon 4, 1920 Martigny, Switzerland http://www.idiap.ch/~bengio" 0af65df112db18248ed24a1c0fb5fe8524015336,Contour Segment Analysis for Human Silhouette Pre-segmentation,"Author manuscript, published in ""5th International Conference on Computer Vision Theory and Applications (VISAPP 2010), Angers : France (2010)""" 0adffd02029363c204a561092e1e0cc05cacfee7,A New Method for Static Video Summarization Using Local Descriptors and Video Temporal Segmentation,"A New Method for Static Video Summarization Using Local Descriptors and Video Temporal Segmentation Edward J. Y. Cayllahua Cahuina Computer Research Center San Pablo Catholic University Arequipa, Peru Email: Guillermo Camara Chavez Department of Computer Science Federal university of Ouro Preto Ouro Preto, Brazil Email:" 0a7a7b3f05918fb4fc33f04cb7e31232fa197f76,Fitting a Morphable Model to 3D Scans of Faces,"Fitting a Morphable Model to 3D Scans of Faces Volker Blanz Universit¤at Siegen, Siegen, Germany Kristina Scherbaum MPI Informatik, Saarbr¤ucken, Germany Hans-Peter Seidel MPI Informatik, Saarbr¤ucken, Germany" 0a3863a0915256082aee613ba6dab6ede962cdcd,Early and Reliable Event Detection Using Proximity Space Representation,"Early and Reliable Event Detection Using Proximity Space Representation Maxime Sangnier LTCI, CNRS, T´el´ecom ParisTech, Universit´e Paris-Saclay, 75013, Paris, France J´erˆome Gauthier LADIS, CEA, LIST, 91191, Gif-sur-Yvette, France Alain Rakotomamonjy Normandie Universit´e, UR, LITIS EA 4108, Avenue de l’universit´e, 76801, Saint-Etienne-du-Rouvray, France" 0a81810af97e8ab5b8c483209b4d0ff7210436f9,Human Joint Angle Estimation and Gesture Recognition for Assistive Robotic Vision,"Human Joint Angle Estimation and Gesture Recognition for Assistive Robotic Vision Alp Guler1, Nikolaos Kardaris2, Siddhartha Chandra1, Vassilis Pitsikalis2, Christian Werner3, Klaus Hauer3, Costas Tzafestas2, Petros Maragos2, Iasonas Kokkinos1 (1) INRIA GALEN & Centrale Sup´elec Paris, (2) National Technical University of Athens, (3) University of Heidelberg" 0a9d38f74095c6840540dabb00c754f4b0c2d131,Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph,"Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph Amir Zadeh1, Paul Pu Liang2, Jonathan Vanbriesen1, Soujanya Poria3, Edmund Tong1, Erik Cambria4, Minghai Chen1, Louis-Philippe Morency1 {1- Language Technologies Institute, 2- Machine Learning Department}, CMU, USA {3- A*STAR, 4- Nanyang Technological University}, Singapore" 0ac7488dfbab703fad126dbe8e5e1ed0e9f6629f,Pedestrian Detection via Classification on Riemannian Manifolds,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Pedestrian Detection Via Classification on Riemannian Manifolds Oncel Tuzel, Fatih Porikli, Peter Meer TR2008-037 August 2008" 0af9141cdb644ea4eea659ec664d49cd083b9dc7,"Multibiometric Systems : Overview , Case Studies and Open Issues","Chapter 11 Multibiometric Systems: Overview, Case Studies nd Open Issues Arun Ross and Norman Poh" 26f5b8a79fac681ffb132c4863c51a55bc2b20e2,Visual speech synthesis from 3D mesh sequences driven by combined speech features,"VISUAL SPEECH SYNTHESIS FROM 3D MESH SEQUENCES DRIVEN BY COMBINED SPEECH FEATURES Felix Kuhnke and J¨orn Ostermann Institut f¨ur Informationsverarbeitung, Leibniz Universit¨at Hannover, Germany" 2671d7085cb32fa3fe55672d9472ba22808e6fe3,An Integrative Approach to Face and Expression Recognition from 3D Scans,"An Integrative Approach to Face and Expression Recognition from 3D Scans An Integrative Approach to Face and Expression Recognition from 3D Scans Chao Li Florida A&M University . Introduction Face recognition, together with fingerprint recognition, speaker recognition, etc., is part of the research area known as ‘biometric identification’ or ‘biometrics’, which refers to identifying an individual based on his or her distinguishing characteristics. More precisely, iometrics is the science of identifying, or verifying the identity of, a person based on physiological or behavioral characteristics (Bolle et al., 2003). Biometric characteristics include something that a person is or produces. Examples of the former are fingerprints, the iris, the face, the hand/finger geometry or the palm print, etc. The latter include voice, handwriting, signature, etc. (Ortega-Garcia et al., 2004). Face recognition is a particularly compelling biometric approach because it is the one used every day by nearly everyone as the primary means for recognition of other humans. Because of its natural character, face recognition is more acceptable than most other iometric methods. Face recognition also has the advantage of being noninvasive. Face recognition has a wide range of potential applications for commercial, security, and forensic purposes. These applications include automated crowd surveillance, access control," 266b5b038750e1ab1311e38554e4c2c8ba6564fd,SLIC Superpixels Compared to State-of-the-Art Superpixel Methods,"JOURNAL OF LATEX CLASS FILES, VOL. 6, NO. 1, DECEMBER 2011 SLIC Superpixels Compared to State-of-the-art Superpixel Methods Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine S¨usstrunk" 267595dd40cd109c93e67874a1cf49ce79871f3a,A Compromise Principle in Deep Monocular Depth Estimation,"A Compromise Principle in Deep Monocular Depth Estimation Huan Fu, Mingming Gong, Chaohui Wang, and Dacheng Tao, Fellow, IEEE" 2677a79b6381f3e7787c5dca884fa53d0b28dfe2,Supplementary Document : Single-Shot Multi-Person 3 D Pose Estimation From Monocular RGB 1,"Supplementary Document: Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB . Read-out Process An algorithmic description of the read-out process is provided in Alg. 1. Algorithm 1 3D Pose Inference : Given: P 2D, C2D, M : for all i ∈ (1..m) do if C2D [k] > thresh, k ∈ {pelvis, neck} then Person i is detected for all joints j ∈ (1..n) do rloc = P2D Pi[:, j] = ReadLocMap(j, rloc) limbs {arml, armr, legl, legr, head} do {pelvis, neck}; j = parent(j) do j = getExtremity(l); j if isValidReadoutLoc(i, j) then" 2690264001ccd4b682b7b4c0334c80af6f5e9c9c,Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation,"Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation Alexandra Carlson1, Katherine A. Skinner1, Ram Vasudevan2 and Matthew Johnson-Roberson3" 26a32691321574ac1c90c58f47ec73fdfbc8507a,SATURN (Situational awareness tool for urban responder networks),"SATURN (Situational Awareness Tool for Urban Responder Networks) Heather Zwahlen Aaron Yahr Danielle Berven Michael T. Chan Maximilian Merfeld Christine Russ Jason Thornton MIT Lincoln Laboratory Lexington, MA {heatherz | ayahr | danielle.berven | mchan | max.merfeld | christine russ |" 266766818dbc5a4ca1161ae2bc14c9e269ddc490,Boosting a Low-Cost Smart Home Environment with Usage and Access Control Rules,"Article Boosting a Low-Cost Smart Home Environment with Usage and Access Control Rules Paolo Barsocchi * ID , Antonello Calabrò, Erina Ferro, Claudio Gennaro ID and Eda Marchetti and Claudio Vairo Institute of Information Science and Technologies of CNR (CNR-ISTI)-Italy, 56124 Pisa, Italy; (A.C.); (E.F.); (C.G.); (E.M.); (C.V.) * Correspondence: Tel.: +39-050-315-2965 Received: 27 April 2018; Accepted: 31 May 2018; Published: 8 June 2018" 26e425781e4090abfae65b5d68eac72282dd2e31,Image Captioning with Deep Bidirectional LSTMs,"Image Captioning with Deep Bidirectional LSTMs Cheng Wang, Haojin Yang, Christian Bartz, Christoph Meinel Hasso Plattner Institute, University of Potsdam Prof.-Dr.-Helmert-Str. 2-3, 14482 Potsdam, Germany {cheng.wang," 2603efdc673e9c7cfa0c1e1dfda512b6ef54ea2c,On the Use of Simple Geometric Descriptors Provided by RGB-D Sensors for Re-Identification,"Sensors 2013, 13, 8222-8238; doi:10.3390/s130708222 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article On the Use of Simple Geometric Descriptors Provided by RGB-D Sensors for Re-Identification Javier Lorenzo-Navarro *, Modesto Castrill´on-Santana and Daniel Hern´andez-Sosa SIANI, Universidad de Las Palmas de Gran Canaria, Campus de Tafira, Las Palmas de Gran Canaria 35017, Spain; E-Mails: (M.C.-S.); (D.H.-S.) * Author to whom correspondence should be addressed; E-Mail: Tel.: +34-928-458-747. Received: 25 March 2013; in revised form: 7 June 2013 / Accepted: 20 June 2013 / Published: 27 June 2013" 2608a2499819053468f4e6f77a715c2dbfefdfb0,Object Classification using Hybrid Holistic Descriptors: Application to Building Detection in Aerial Orthophotos,"Object Classification using Hybrid Holistic Descriptors: Application to Building Detection in Aerial Orthophotos Fadi Dornaika, Abdelmalik Moujahid, Alireza Bosaghzadeh, Youssef El Merabet, and Yassine Ruichek" 26172460c2c47886f8b0e141c15de29c9766bfbe,An Iterative Co-Saliency Framework for RGBD Images,"An Iterative Co-Saliency Framework for RGBD Images Runmin Cong, Jianjun Lei, Senior Member, IEEE, Huazhu Fu, Weisi Lin, Fellow, IEEE, Qingming Huang, Senior Member, IEEE, Xiaochun Cao, Senior Member, IEEE, and Chunping Hou" 2663fa2f1777dc779a73d678c7919cce37b5fb61,Relevance-Weighted ( 2 D ) 2 LDA Image Projection Technique for Face Recognition,"Relevance-Weighted (2D)2LDA Image Projection Technique for Face Recognition In this paper, a novel image projection technique for face recognition application is proposed which is based on linear discriminant analysis (LDA) combined with the relevance-weighted (RW) method. The projection is performed through 2-directional and 2-dimensional LDA, or (2D)2LDA, which simultaneously works in row and olumn directions to solve the small sample size problem. Moreover, a weighted discriminant hyperplane is used in the between-class scatter matrix, and an RW method is used in the within-class scatter matrix to weigh the information to resolve confusable data in these classes. This technique is called the relevance-weighted (2D)2LDA, or RW(2D)2LDA, which is used for a more accurate discriminant decision than that produced by the onventional LDA or 2DLDA. The proposed technique has been successfully tested on four face databases. Experimental results the proposed" 26c8cac8c6320bf49e2898e46bdf1504333fa257,Deep Predictive Models for Collision Risk Assessment in Autonomous Driving,"Deep Predictive Models for Collision Risk Assessment in Autonomous Driving Mark Strickland1, Georgios Fainekos1, Heni Ben Amor1" 26ad6ceb07a1dc265d405e47a36570cb69b2ace6,"Neural Correlates of Cross-Cultural Adaptation September , 2015 How to Improve the Training and Selection for Military Personnel Involved in Cross-Cultural Interactions","RESEARCH AND EXPLOR ATORY DEVELOPMENT DEPARTMENT REDD-2015-384 Neural Correlates of Cross-Cultural How to Improve the Training and Selection for Military Personnel Involved in Cross-Cultural Operating Under Grant #N00014-12-1-0629/113056 Adaptation September, 2015 Interactions Jonathon Kopecky Jason Spitaletta Mike Wolmetz Alice Jackson Prepared for: Office of Naval Research" 267e695d33c556164983014f1aec1552aa0388bc,Using Linear Kernel Entropy Component Analysis as a Feature Extraction Method in Face Recognition in video surveillance systems,"Using Linear Kernel Entropy Component Analysis as a Feature Extraction Method in Face Recognition in video surveillance systems Sepehr Damavandinejadmonfared1, Sina Ashooritootkaboni2, and 3Taha Bahraminezhad Jooneghani , 2 School of Electrical and Electronic Engineering, UniversitiSains Malaysia (USM), Penang, Malaysia School of Software Engeenering, Jaber Ebn Hayan University, Rasht, Iran" 2603d8578a6c95a9b9d4cb8a73bc66f18d523f37,Deep Parts Similarity Learning for Person Re-Identification, 26679e1885b1ce186e80551befdf82e57b3f7455,TA RGETED BIOMETRIC IMPERSONATION,"TA RGETED BIOMETRIC IMPERSONATION John D. Bustard, John N. Carter, Mark S. Nixon School of Electronics nd Computer Science, University of Southampton" 26ad124271c118e207113ae42f0fd3d30f204ea1,State of the Art Report on Video-Based Graphics and Video Visualization,"General Copyright Notice The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the uthors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that ll persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder. R. Borgo, M. Chen, B. Daubney, E. Grundy, G. Heidemann, B. Höferlin, M. Höferlin, H. Leitte, D. Weiskopf, X. Xie: State of the Art Report on Video-Based Graphics and Video Visualization, Computer Graphics Forum, Vol. 31, No. 8, 2450-2477, 2012. DOI: 10.1111/j.1467-8659.2012.03158.x This is the author’s personal copy of the final, accepted version of the paper, which slightly differs from the version published in Computer Graphics Form. Copyright © 2012 The Eurographics Association and Blackwell Publishing Ltd. Preprint" 26a72e9dd444d2861298d9df9df9f7d147186bcd,Collecting and annotating the large continuous action dataset,"DOI 10.1007/s00138-016-0768-4 ORIGINAL PAPER Collecting and annotating the large continuous action dataset Daniel Paul Barrett1 · Ran Xu2 · Haonan Yu1 · Jeffrey Mark Siskind1 Received: 18 June 2015 / Revised: 18 April 2016 / Accepted: 22 April 2016 / Published online: 21 May 2016 © The Author(s) 2016. This article is published with open access at Springerlink.com" 269c1f9df4a36b361d32bfdc81457b0a32b60966,Dimensionality reduction of visual features for efficient retrieval and classification,"SIP (2016), vol. 5, e14, page 1 of 14 © The Authors, 2016. This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unre- stricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited. doi:10.1017/ATSIP.2016.14 industrial technology advances Dimensionality reduction of visual features for efficient retrieval and classification petros t. boufounos1, hassan mansour1, shantanu rane2 and anthony vetro1 Visual retrieval and classification are of growing importance for a number of applications, including surveillance, automotive, s well as web and mobile search. To facilitate these processes, features are often computed from images to extract discriminative spects of the scene, such as structure, texture or color information. Ideally, these features would be robust to changes in per- spective, illumination, and other transformations. This paper examines two approaches that employ dimensionality reduction for fast and accurate matching of visual features while also being bandwidth-efficient, scalable, and parallelizable. We focus on two classes of techniques to illustrate the benefits of dimensionality reduction in the context of various industrial applications. The first method is referred to as quantized embeddings, which generates a distance-preserving feature vector with low rate. The second method is a low-rank matrix factorization applied to a sequence of visual features, which exploits the temporal redun- dancy among feature vectors associated with each frame in a video. Both methods discussed in this paper are also universal in that they do not require prior assumptions about the statistical properties of the signals in the database or the query. Further- more, they enable the system designer to navigate a rate versus performance trade-off similar to the rate-distortion trade-off in onventional compression." 263607a635d33d26612dce8af14682fb76d0550f,Improving Landmark Localization With Semi-Supervised Learning,"Improving Landmark Localization with Semi-Supervised Learning Sina Honari1∗, Pavlo Molchanov2, Stephen Tyree2, Pascal Vincent1,4,5, Christopher Pal1,3, Jan Kautz2 MILA-University of Montreal, 2NVIDIA, 3Ecole Polytechnique of Montreal, 4CIFAR, 5Facebook AI Research. {honaris, {pmolchanov, styree," 26288af02d522e50308ef8deb2def5cd3fe9878b,Learning to See by Moving,"Learning to See by Moving Pulkit Agrawal UC Berkeley Jo˜ao Carreira UC Berkeley Jitendra Malik UC Berkeley" 26861e41e5b44774a2801e1cd76fd56126bbe257,Personalized Tour Recommendation Based on User Interests and Points of Interest Visit Durations,"Personalized Tour Recommendation based on User Interests and Points of Interest Visit Durations Kwan Hui Lim*†, Jeffrey Chan*, Christopher Leckie*† and Shanika Karunasekera* *Department of Computing and Information Systems, The University of Melbourne, Australia Victoria Research Laboratory, National ICT Australia, Australia" 26d3887193808875115f68c7fd8ef9e86659fd3b,Don't Look Back: Robustifying Place Categorization for Viewpoint- and Condition-Invariant Place Recognition,"© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtainedfor all other uses, in any current or future media, including reprinting/republishing this materialfor advertising or promotional purposes, creating new collective works, for resale or redistributionto servers or lists, or reuse of any copyrighted component of this work in other works.Pre-print of article that will appear at the 2018 IEEE International Conference on Robotics and Automation.Please cite this paper as:S. Garg, N. Suenderhauf, and M. Milford, “Don't Look Back: Robustifying Place Categorization for Viewpoint- and Condition-Invariant Place Recognition,” in IEEE International Conference on Robotics and Automation (ICRA), title={Don't Look Back: Robustifying Place Categorization for Viewpoint- and Condition-Invariant Place Recognition}, author={Garg, Sourav and Suenderhauf, Niko and Milford, Michael}, booktitle={IEEE International Conference on Robotics and Automation (ICRA)}, year={2018} }" 2661f38aaa0ceb424c70a6258f7695c28b97238a,Multilayer Architectures for Facial Action Unit Recognition,"IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, VOL. 42, NO. 4, AUGUST 2012 Multilayer Architectures for Facial Action Unit Recognition Tingfan Wu, Nicholas J. Butko, Paul Ruvolo, Jacob Whitehill, Marian S. Bartlett, and Javier R. Movellan" 26cdb9b6d94c1d6c6a01792fee3c176585f594ac,Hybrid Person Detection and Tracking in H.264/AVC Video Streams,"Hybrid Person Detection and Tracking in H.264/AVC Video Streams Philipp Wojaczek1, Marcus Laumer1,2, Peter Amon2, Andreas Hutter2 and André Kaup1 Multimedia Communications and Signal Processing, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany Imaging and Computer Vision, Siemens Corporate Technology, Munich, Germany Keywords: Object Detection, Person Detection, Tracking, Compressed Domain, Pixel Domain, H.264/AVC, Mac- roblocks, Compression, Color Histogram, Hue, HSV, Segmentation." 26a07311397d47ccc438783eb256cb97309edbb2,Face Recognition using Feature of Integral Gabor-Haar Transformation,"-4244-1437-7/07/$20.00 ©2007 IEEE IV - 505 ICIP 2007" 265af79627a3d7ccf64e9fe51c10e5268fee2aae,A Mixture of Transformed Hidden Markov Models for Elastic Motion Estimation,"A Mixture of Transformed Hidden Markov Models for Elastic Motion Estimation Huijun Di, Linmi Tao, and Guangyou Xu, Senior Member, IEEE" 26a6b2051fe7970f94584e9efbfcf7bdcfd1d6d6,Diffeomorphic image registration with applications to deformation modelling between multiple data sets,"Diffeomorphic image registration with applications to deformation modelling between multiple data sets Bartłomiej Władysław Papież A thesis submitted in partial fulfilment for the requirements of the degree of Doctor of Philosophy The research presented in this thesis was carried out at the Applied Digital Signal and Image Processing Research Centre, School of Computing, Engineering and Physical Sciences, University of Central Lancashire, October 2012" 2606e6a5759c030e259ebf3f4261b9c04a36a609,Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval,"Proceedings of the 2015 Workshop on Vision and Language (VL’15), pages 70–80, Lisbon, Portugal, 18 September 2015. c(cid:13)2015 Association for Computational Linguistics." 265644f1b6740ca34bfbe9762b90b33021adde62,Deep Learning in Medical Imaging: General Overview.,"Review Article | Experiment, Engineering, and Physics https://doi.org/10.3348/kjr.2017.18.4.570 pISSN 1229-6929 · eISSN 2005-8330 Korean J Radiol 2017;18(4):570-584 Deep Learning in Medical Imaging: General Overview June-Goo Lee, PhD1, Sanghoon Jun, PhD2, 3, Young-Won Cho, MS2, 3, Hyunna Lee, PhD2, 3, Guk Bae Kim, PhD2, 3, Joon Beom Seo, MD, PhD2*, Namkug Kim, PhD2, 3* Biomedical Engineering Research Center, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Korea; 2Department of Radiology, Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Korea; 3Department of Convergence Medicine, Biomedical Engineering Research Center, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Korea The artificial neural network (ANN)–a machine learning technique inspired by the human neuronal synapse system–was introduced in the 1950s. However, the ANN was previously limited in its ability to solve actual problems, due to the vanishing gradient and overfitting problems with training of deep architecture, lack of computing power, and primarily the absence of sufficient data to train the computer system. Interest in this concept has lately resurfaced, due to the availability of big data, enhanced computing power with the current graphics processing units, and novel algorithms to train the deep neural network. Recent studies on this technology suggest its potentially to perform better than humans in some visual and auditory recognition tasks, which may portend its applications in medicine and healthcare, especially in medical imaging, in the foreseeable future. This review article offers perspectives on the history, development, and applications of deep learning technology, particularly regarding its applications in medical imaging. Keywords: Artificial intelligence; Machine learning; Convolutional neural network; Recurrent Neural Network; Computer-aided;" 264a84f4d27cd4bca94270620907cffcb889075c,Deep motion features for visual tracking,"Deep Motion Features for Visual Tracking Susanna Gladh, Martin Danelljan, Fahad Shahbaz Khan, Michael Felsberg Computer Vision Laboratory, Department of Electrical Engineering, Link¨oping University, Sweden" 26d52680d610a2a19483e5fe9bb1421cc26207e6,An Asynchronous Hidden Markov Model for Audio-Visual Speech Recognition,"An Asynchronous Hidden Markov Model for Audio-Visual Speech Recognition Samy Bengio Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP) CP 592, rue du Simplon 4, 920 Martigny, Switzerland" 2675a66b3f8743cf0551f284244af4f24537c19b,Learning Visually Grounded Sentence Representations,"Learning Visually Grounded Sentence Representations Douwe Kiela Facebook AI Research Allan Jabri1 UC Berkeley" 26c7eda262dfda1c3a3597a3bf1f2f1cc4013425,Some Like It Hot — Visual Guidance for Preference Prediction,"Some like it hot - visual guidance for preference prediction Rasmus Rothe CVL, ETH Zurich Radu Timofte CVL, ETH Zurich Luc Van Gool KU Leuven, ETH Zurich" 26e570049aaedcfa420fc8c7b761bc70a195657c,Hybrid Facial Regions Extraction for Micro-expression Recognition System,"J Sign Process Syst DOI 10.1007/s11265-017-1276-0 Hybrid Facial Regions Extraction for Micro-expression Recognition System Sze-Teng Liong1,2,3 · John See4 · Raphael C.-W. Phan2 · KokSheik Wong5 · Su-Wei Tan2 Received: 2 February 2016 / Revised: 20 October 2016 / Accepted: 10 August 2017 © Springer Science+Business Media, LLC 2017" 264dcfb5be3f89dc0950472a2a274ef7b641b1af,Dynamic Objects Segmentation for Visual Localization in Urban Environments,"Dynamic Objects Segmentation for Visual Localization in Urban Environments G. Zhou1, B. Bescos2, M. Dymczyk1, M. Pfeiffer1, J. Neira2, R. Siegwart1" 26437fb289cd7caeb3834361f0cc933a02267766,Innovative Assessment Technologies : Comparing ‘ Face-to-Face ’ and Game-Based Development of Thinking Skills in Classroom Settings,"012 International Conference on Management and Education Innovation IPEDR vol.37 (2012) © (2012) IACSIT Press, Singapore Innovative Assessment Technologies: Comparing ‘Face-to-Face’ and Game-Based Development of Thinking Skills in Classroom Settings Gyöngyvér Molnár 1 + and András Lőrincz 2 University of Szeged, 2 Eötvös Loránd University" 268afd5de8fa32cadd4a90bf0bb1c9938a245ab4,Image Compression Effects in Face Recognition Systems,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 260081528f19f6f7e8e5ae16a776b62ad8c2ed0d,An Agent Based WCET Analysis for Top-View Person Re-Identification,"An agent-based WCET analysis for Top-View Person Re-Identification Marina Paolanti, Valerio Placidi, Michele Bernardini, Andrea Felicetti, Rocco Pietrini, and Emanuele Frontoni Department of Information Engineering, Universit`a Politecnica delle Marche, Via Brecce Bianche 12, 60131, Ancona, Italy" 151b6c519c77cda9ff5542fecee166a166e0928f,Mobile Applications Scene Text Recognition by Character Descriptor and Structure Configuration,"International Journal of Research Available at https://edupediapublications.org/journals p-ISSN: 2348-6848 e-ISSN: 2348-795X Volume 03 Issue 04 February 2016 Mobile Applications Scene Text Recognition by Character Descriptor and Structure Configuration Ch.Lakshmi Prasad 1 & Koteswarao.M. 2 1.M.Tech student,Amara Institute of Engineering&Technology,JNTUK,NRT,AP. . Assistant professor,Amara Institute of Engineering&Technology,JNTUK,NRT,AP." 153c8715f491272b06dc93add038fae62846f498,On Clustering Images of Objects,"(cid:13) Copyright by Jongwoo Lim, 2005" 15605634feb1a5770182a8f2c3515daf102ed463,Real-time human pose recognition in parts from single depth images,"Real-Time Human Pose Recognition in Parts from Single Depth Images Mark Finocchio Jamie Shotton Andrew Fitzgibbon Toby Sharp Andrew Blake Richard Moore Mat Cook Alex Kipman Microsoft Research Cambridge & Xbox Incubation" 15f57134b42638cbd57d0d8c4437e8b6b6a8bac4,Learning Visual Reasoning Without Strong Priors,"Learning Visual Reasoning Without Strong Priors Ethan Perez12, Harm de Vries1, Florian Strub3, Vincent Dumoulin1, Aaron Courville14 MILA, Universit´e of Montr´eal, Canada; 2Rice University, U.S.A. Univ. Lille, CNRS, Centrale Lille, Inria, UMR 9189 CRIStAL France CIFAR Fellow, Canada" 15e6c983e74dcf70d8a557b75bdc172e36692191,VSO: Visual Semantic Odometry,"VSO: Visual Semantic Odometry Konstantinos-Nektarios Lianos 1,⋆, Johannes L. Sch¨onberger 2, Marc Pollefeys 2,3, Torsten Sattler 2 Geomagical Labs, Inc., USA 3 Microsoft, Switzerland Department of Computer Science, ETH Z¨urich, Switzerland" 152a7ca3a93d41c78ccb50687d8277e9a9247e26,Benchmarks in Robotics Research,"Lecture Notes for IROS 2006 Workshop II (WS-2) Tuesday, October 10, 2006 Benchmarks in Robotics Research Organizer Angel P. del Pobil Universitat Jaume I" 153f5ad54dd101f7f9c2ae17e96c69fe84aa9de4,Overview of algorithms for face detection and tracking,"Overview of algorithms for face detection and tracking Nenad Markuˇs" 15f51d51c05c22e1dca3a40fb1af46941d91f598,Modeling Visual Compatibility through Hierarchical Mid-level Elements.,"Modeling Visual Compatibility through Hierarchical Mid-level Elements Jose Oramas M., Tinne Tuytelaars KU Leuven, ESAT-PSI, iMinds" 15e6e1551ce9a4094c57db70985e420e57c6997a,Asymmetric cross-view dictionary learning for person re-identification,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" 155033f2f096934042d659d10912ef29aa1cdbd1,Visual classification of coarse vehicle orientation using Histogram of Oriented Gradients features,"Visual Classification of Coarse Vehicle Orientation using Histogram of Oriented Gradients Features Paul E. Rybski and Daniel Huber and Daniel D. Morris and Regis Hoffman" 15f82c3a7f12b82281aca77d519403086611ae69,Comparative Study of Human Age Estimation Based on Hand-Crafted and Deep Face Features,"Máster Universitario en Ingeniería Computacional y Sistemas Inteligentes Master Thesis Comparative Study of Human Age Estimation Based on Hand-crafted and Deep Face Features Carlos Belver Director: Fadi Dornaika Co-director: Ignacio Arganda Carreras" 15f3d47b48a7bcbe877f596cb2cfa76e798c6452,Automatic face analysis tools for interactive digital games,"Automatic face analysis tools for interactive digital games Anonymised for blind review Anonymous Anonymous Anonymous" 15623fe8875a36cac5283ff2f08cd50998599725,Semantic Instance Segmentation for Autonomous Driving Bert,"Semantic Instance Segmentation for Autonomous Driving Bert De Brabandere Davy Neven ESAT-PSI, KU Leuven Luc Van Gool" 15ebec3796a2e23d31c8c8ddf6d21555be6eadc6,Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks,"Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks Shivang Agarwal(∗ ,1), Jean Ogier du Terrail(∗ ,1,2), Fr´ed´eric Jurie(1) (∗) equal contribution (1)Normandie Univ, UNICAEN, ENSICAEN, CNRS (2)Safran Electronics and Defense September 11, 2018" 15c8443f8d9f1f6537fa8ff470ac407bf2185b0e,Learning Binary Code Representations for Effective and Efficient Image Retrieval, 15ec1faddbd61a9d50925c7b9b0c76642abe94e7,EFFICIENT TECHNIQUES FOR RECOVERING 2 D HUMAN BODY POSES FROM IMAGES,"EFFICIENT TECHNIQUES FOR RECOVERING 2D HUMAN BODY POSES FROM IMAGES TAI-PENG TIAN Dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy BOSTON UNIVERSITY" 15292f380f5996f539f4d5e93dba3082d53338fb,Feature Space Optimization for Semantic Video Segmentation,"Feature Space Optimization for Semantic Video Segmentation Abhijit Kundu∗ Georgia Tech Vibhav Vineet∗ Vladlen Koltun Intel Labs Intel Labs Figure 1. Semantic video segmentation on the Cityscapes dataset [6]. Input frame on the left, semantic segmentation computed by our pproach on the right." 159b52158512481df7684c341401efbdbc5d8f02,Object Detection with Active Sample Harvesting,"Object Detection with Active Sample Harvesting Thèse no 7312 présentée le 5 Octobre 2016 à la Faculté des Sciences et Techniques de l'Ingénieur Laboratoire LIDIAP (Idiap Research Institute) École Polytechnique Fédérale de Lausanne pour l'obtention du grade de Docteur ès Sciences Olivier Canévet devant le jury composé de : Prof. Pascal Frossard, président du jury Prof. Gilles Blanchard, rapporteur Prof. Raphael Sznitman, rapporteur Dr Mathieu Salzmann, rapporteur Dr François Fleuret, directeur de thèse Lausanne, EPFL, 2016" 155448563c354b01d12610b5864b511644cfeb27,Mapping Images to Sentiment Adjective Noun Pairs with Factorized Neural Nets,"Mapping Images to Sentiment Adjective Noun Pairs with Factorized Neural Nets Takuya Narihira Sony / ICSI Damian Borth DFKI / ICSI Stella X. Yu UC Berkeley / ICSI Karl Ni In-Q-Tel Trevor Darrell UC Berkeley / ICSI" 15aa6c457678e25f6bc0e818e5fc39e42dd8e533,Conditional Image Generation for Learning the Structure of Visual Objects, 15dea987f66386be14b7811f1f27784f3ed9e9c0,Face Detection with Mixtures of Boosted Discriminant Features,"Face Detection with Mixtures of Boosted Discriminant Features Julien Meynet, Vlad popovici and Jean-Philippe Thiran Ecole Polytechnique F´ed´erale de Lausanne (EPFL) Signal Processing Institute CH-1015 Lausanne, Switzerland. Technical report TR-ITS-2005.35 November 23, 2005" 157ee7498320119f6f5da2d9c592448986edea7e,Learning Multiple Non-linear Sub-spaces Using K-RBMs,"Learning Multiple Non-Linear Sub-Spaces using K-RBMs Siddhartha Chandra1, Shailesh Kumar2 & C. V. Jawahar3 CVIT, IIIT Hyderabad, 2Google, Hyderabad" 15c63e01ac051f01edcf76bf809ae41db0663d97,Wavelet Frame Accelerated Reduced Support Vector Machines,"IEEE TRANSACTION ON IMAGE PROCESSING, VOL. X, NO. XX, XXXXXX 2005 Wavelet Frame Accelerated Reduced Support Vector Machines Matthias R¨atsch, Gerd Teschke, Sami Romdhani, and Thomas Vetter Member, IEEE" 1565bf91f8fdfe5f5168a5050b1418debc662151,One-pass Person Re-identification by Sketch Online Discriminant Analysis,"One-pass Person Re-identification by Sketch Online Discriminant Analysis Wei-Hong Li, Zhuowei Zhong, and Wei-Shi Zheng∗" 15cd05baa849ab058b99a966c54d2f0bf82e7885,Structured Sparse Subspace Clustering: A unified optimization framework,"Structured Sparse Subspace Clustering: A Unified Optimization Framework Chun-Guang Li1, René Vidal2 SICE, Beijing University of Posts and Telecommunications. 2Center for Imaging Science, Johns Hopkins University. In many real-world applications, we need to deal with high-dimensional datasets, such as images, videos, text, and more. In practice, such high- dimensional datasets can be well approximated by multiple low-dimensional subspaces corresponding to multiple classes or categories. For example, the feature point trajectories associated with a rigidly moving object in a video lie in an affine subspace (of dimension up to 4), and face images of a subject under varying illumination lie in a linear subspace (of dimension up to 9). Therefore, the task, known in the literature as subspace clustering [6], is to segment the data into the corresponding subspaces and finds multiple pplications in computer vision. State of the art approaches [1, 2, 3, 4, 5, 7] for solving this problem fol- low a two-stage approach: a) Construct an affinity matrix between points by exploiting the ‘self-expressiveness’ property of the data, which allows any data point to be represented as a linear (or affine) combination of the other data points; b) Apply spectral clustering on the affinity matrix to recover the data segmentation. Dividing the problem in two steps is, on the one hand, appealing because the first step can be solved using convex optimiza-" 15728d6fd5c9fc20b40364b733228caf63558c31,EXPANDING THE BREADTH AND DETAIL OF OBJECT RECOGNITION,(cid:13) 2013 Ian N. Endres 15383ae2d86eb8c5e172168f94ef915a7a238b72,Learning Semantic Prediction using Pretrained Deep Feedforward Networks,"Learning Semantic Prediction using Pretrained Deep Feedforward Networks J¨org Wagner1,2, Volker Fischer1, Michael Herman1 and Sven Behnke2 - Robert Bosch GmbH - 70442 Stuttgart - Germany - University of Bonn, Computer Science VI, Autonomous Intelligent Systems Friedrich-Ebert-Allee 144, 53113 Bonn - Germany" 153e5cddb79ac31154737b3e025b4fb639b3c9e7,Active Dictionary Learning in Sparse Representation Based Classification,"PREPRINT SUBMITTED TO IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS Active Dictionary Learning in Sparse Representation Based Classification Jin Xu, Haibo He, Senior Member, IEEE, and Hong Man, Senior Member, IEEE" 15d1326f054f4fadea463f217ce54bad6908705a,Sensor fusion in smart camera networks for Ambient Intelligence - Report on PhD Thesis and Defense,"Sensor fusion in smart camera networks for ambient intelligence Maatta, T.T. 0.6100/IR755363 Published: 01/01/2013 Document Version Publisher’s PDF, also known as Version of Record (includes final page, issue and volume numbers) Please check the document version of this publication: • A submitted manuscript is the author's version of the article upon submission and before peer-review. There can be important differences etween the submitted version and the official published version of record. People interested in the research are advised to contact the uthor for the final version of the publication, or visit the DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication Citation for published version (APA): Maatta, T. T. (2013). Sensor fusion in smart camera networks for ambient intelligence Eindhoven: Technische Universiteit Eindhoven DOI: 10.6100/IR755363 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights." 155ce5d596c7b525110ca24db11e47d521b487ce,STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation,"STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Xiaohui Shen, Ming-Ming Cheng, Jiashi Feng, Yao Zhao, Senior Member, IEEE and Shuicheng Yan Senior Member, IEEE" 158a8037ce1c577620550da385d2275a31b9ccaa,Combining motion detection and hierarchical particle filter tracking in a multi-player sports environment,"Combining motion detection and hierarchical particle filter tracking in a multi-player sports environment Robbie Vos, Willie Brink Department of Mathematical Sciences University of Stellenbosch, South Africa" 15e0b9ba3389a7394c6a1d267b6e06f8758ab82b,The OU-ISIR Gait Database comprising the Large Population Dataset with Age and performance evaluation of age estimation,"Xu et al. IPSJ Transactions on Computer Vision and Applications (2017) 9:24 DOI 10.1186/s41074-017-0035-2 IPSJ Transactions on Computer Vision and Applications TECHNICAL NOTE Open Access The OU-ISIR Gait Database comprising the Large Population Dataset with Age and performance evaluation of age estimation Chi Xu1,2, Yasushi Makihara2*, Gakuto Ogi2, Xiang Li1,2, Yasushi Yagi2 and Jianfeng Lu1" 159b87e6e68b18f4daa3505bfc415be9b21a7db6,Tracking The Invisible Man - Hidden-object Detection for Complex Visual Scene Understanding, 150326137da214210b46e0b7f22e30f7e6529006,Pedestrian Detection at Warp Speed: Exceeding 500 Detections per Second,"Pedestrian Detection at Warp Speed: Exceeding 500 Detections per Second Floris De Smedt∗, Kristof Van Beeck∗, Tinne Tuytelaars and Toon Goedem´e EAVISE, ESAT-PSI-VISICS, KU Leuven, Belgium" 1550c3835822843a02b2144cef8abc534441f5d4,Human Pose Classification within the Context of Near-IR Imagery Tracking,"Human Pose Classification within the Context of Near-IR Imagery Tracking Jiwan Han, Anna Gaszczak, Ryszard Maciol, Stuart E. Barnes, Toby P. Breckon School of Engineering, Cranfield University, Bedfordshire, UK" 15ff6356e3552b4dd7bd6bdd65090d988a7ce61f,PI-Edge: A Low-Power Edge Computing System for Real-Time Autonomous Driving Services,"π-Edge: A Low-Power Edge Computing System for Real-Time Autonomous Driving Services Jie Tang, Shaoshan Liu, Bo Yu, and Weisong Shi Fellow, IEEE the DragonFly Pod (Figure 1), has been developed by us, for a total cost under $10,000 when mass-produced and for low- speed scenarios, such as university campuses, industrial parks, nd areas with limited traffic. The DragonFly pod supports three basic services, real-time localization through Simultaneous Localization And Mapping (SLAM), real-time obstacle detection through computer vision, and speech recognition for user interaction [28]." 15eff32ccbf0f89e888df5a5128d89cea3e0060e,On preserving non-discrimination when combining expert advice,"On preserving non-discrimination when combining expert advice Avrim Blum ∗ Suriya Gunasekar † Thodoris Lykouris‡ Nathan Srebro §" 1546b65e5e95543cf2dc0ead92b758fb31a5f4d6,An inexpensive monocular vision system for tracking humans in industrial environments,"An Inexpensive Monocular Vision System for Tracking Humans in Industrial Environments Centre for Applied Autonomous Sensor Systems (AASS), ¨Orebro University, Sweden Rafael Mosberger and Henrik Andreasson" 15136c2f94fd29fc1cb6bedc8c1831b7002930a6,Deep Learning Architectures for Face Recognition in Video Surveillance,"Deep Learning Architectures for Face Recognition in Video Surveillance Saman Bashbaghi, Eric Granger, Robert Sabourin and Mostafa Parchami" 15c7fe9c9154113f9824f68ca1870564600b66d6,Better Appearance Models for Pictorial Structures,"EICHNER, FERRARI: BETTER APPEARANCE MODELS FOR PICTORIAL STRUCTURES Better appearance models for pictorial structures Marcin Eichner Vittorio Ferrari Computer Vision Laboratory Zürich, Switzerland" 15cf11ddfc046b2ed2766c375e8ad067baaf8347,Active Pedestrian Safety by Automatic Braking and Evasive Steering,"Active Pedestrian Safety y Automatic Braking and Evasive Steering C. Keller, T. Dang, H. Fritz, A. Joos, C. Rabe and D. M. Gavrila" 15696370ff33b6e5a81bf5131d80065d6e59804f,Semantically guided location recognition for outdoors scenes,"Semantically Guided Location Recognition for Outdoors Scenes Arsalan Mousavian and Jana Koˇseck´a and Jyh-Ming Lien" 157eb982da8fe1da4c9e07b4d89f2e806ae4ceb6,Connecting the dots in multi-class classification: From nearest subspace to collaborative representation,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Connecting the Dots in Multi-Class Classification: From Nearest Subspace to Collaborative Representation Chi, Y.; Porikli, F. TR2012-043 June 2012" 15667845de2531b59736d866531728a771500d34,3-D Face Recognition Using Local Appearance-Based Models,"[4] L. Lee and W. E. L. Grimson, “Gait analysis for recognition and classi- fication,” in Proc. IEEE Int. Conf. Automatic Face and Gesture Recog- nition, Washington, DC, May 2002, pp. 734–742. [5] L. Wang, H. Ning, W. Hu, and T. Tan, “Gait recognition based on pro- rustes shape analysis,” in Proc. Int. Conf. Image Processing, 2002, pp. 33–436. [6] L. Wang, H. Ning, T. Tan, and W. Hu, “Fusion of static and dynamic ody biometrics for gait recognition,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 2, pp. 149–158, Feb. 2004. [7] D. Cunado, M. S. Nixon, and J. N. Carter, “Automatic extraction and description of human gait models for recognition purposes,” in Comput. Vis. Image Understand., Apr. 2003, vol. 90, pp. 1–41. [8] P. J. Phillips, S. Sarkar, I. R. Vega, P. Grother, and K. W. Bowyer, “The gait identification challenge problem: Data sets and baseline al- gorithm,” in Proc. Int. Conf. Pattern Recognition, Quebec City, QC, Canada, Aug. 2002, vol. 1, pp. 385–388. [9] S. Sarkar, P. J. Phillips, Z. Liu, I. R. Vega, P. Grother, and K. W. Bowyer, “The human ID gait challenge problem: Data sets, perfor- mance, and analysis,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 2, pp. 162–177, Feb. 2005." 15e024d8f5625ec03c8ac592fbc093687cfb5f02,The Visual Object Tracking VOT2015 Challenge Results,"013 IEEE International Conference on Computer Vision Workshops 013 IEEE International Conference on Computer Vision Workshops The Visual Object Tracking VOT2013 challenge results Matej Kristan a Luka ˇCehovin a Roman Pflugfelder b Georg Nebehay b Aleˇs Leonardis c Gustavo Fernandez b Jiri Matas d Tom´aˇs Voj´ıˇr d Fatih Porikli e Adam Gatt f Ahmad Khajenezhad g Alfredo Petrosino i Chee Seng Chan m Dorothy Monekosso n Jin Gao q Ahmed Salahledin h Anthony Milton j" bef2854893462ae28bdb2243bba4d010d3909289,TUBITAK UZAY at TRECVID 2010: Content-Based Copy Detection and Semantic Indexing,"TÜBİTAK UZAY at TRECVID 2010: Content-Based Copy Detection and Semantic Indexing Ahmet Saracoğlu1,2, Ersin Esen1,2, Medeni Soysal1,2, Tuğrul K. Ateş1,2, Berker Loğoğlu1, Mashar Tekin1, Talha Karadeniz1, Müge Sevinç1, Hakan Sevimli1, Banu Oskay Acar1, Ezgi C. Ozan1,2, Duygu Oskay Onur1, Sezin Selçuk1, A. Aydın Alatan2, Tolga Çiloğlu2 TÜBİTAK Space Technologies Research Institute Department of Electrical and Electronics Engineering, M.E.T.U. {ahmet.saracoglu, ersin.esen, medeni.soysal, tugrul.ates, berker.logoglu, mashar.tekin, talha.karadeniz, muge.sevinc, hakan.sevimli, banu.oskay, ezgican.ozan, duygu.oskay, sezin.selcuk Content-Based Copy Detection Task .1 Visual Copy Detection Mainline approaches for content description for copy detection utilize global or local descriptors from video and comparing these descriptors for similarity. In the literature [16], it has been shown that local features perform better in terms of robustness on the other hand global features are computationally simpler. Local features for content description can be extracted around pixels returned by interest point detectors [17]. Thus, an interest point detector followed by a feature extractor is enough for describing most local aspects of a video scene. Our approach to CCD is based on the clustering of SIFT descriptors and comparing video scenes by their" bea185a15d5df7bbfce83bc684c316412703efbb,PIXELNN: EXAMPLE-BASED IMAGE SYNTHESIS,"Under review as a conference paper at ICLR 2018 PIXELNN: EXAMPLE-BASED IMAGE SYNTHESIS Anonymous authors Paper under double-blind review" be48780eb72d9624a16dd211d6309227c79efd43,Interactive Visual and Semantic Image Retrieval,"Interactive Visual and Semantic Image Retrieval Joost van de Weijer, Fahad Khan and Marc Masana Castrillo Introduction One direct consequence of recent advances in digital visual data generation and the direct availability of this information through the World-Wide Web, is a urgent demand for efficient image retrieval systems. The disclosure of the content of these millions of photos available on the internet is of great importance. The objective of image retrieval is to allow users to efficiently browse through this abundance of images. Due to the non-expert nature of the majority of the internet users, such systems should be user friendly, and therefore avoid complex user interfaces. Traditionally, two sources of information are exploited in the description of im- ges on the web. The first approach, called text-based image retrieval, describes images by a set of labels or keywords [1]. These labels can be automatically ex- tracted from for example the image name (e.g. ’car.jpg’ would provide information bout the presence of a car in the image), or alternatively from the webpage text surrounding the image. Another, more expensive way would be to manually label images with a set of keywords. Shortcomings of the text-based approach to image retrieval are obvious: many objects in the scene will not be labeled, words suffer from the confusions in case of synonyms or homonyms, and words often fall short in describing the esthetics, composition and color scheme of a scene. However, un-" be707bf7c7096df0fcf5bb07ef0fa53494d6a781,Effective classifiers for detecting objects,"Effective Classifiers for Detecting Objects Michael Mayo Dept. of Computer Science University of Waikato Private Bag 3105, Hamilton, New Zealand in the literature: Introduction image. Many image databases such as Caltech-101 [1] onsist of images with the objects of interest in a dominant foreground position, occupying most of the image." be5b455abd379240460d022a0e246615b0b86c14,"The MR2: A multi-racial, mega-resolution database of facial stimuli.","Behav Res DOI 10.3758/s13428-015-0641-9 The MR2: A multi-racial, mega-resolution database of facial stimuli Nina Strohminger1,6 · Kurt Gray2 · Vladimir Chituc3 · Joseph Heffner4 · Chelsea Schein2 · Titus Brooks Heagins5 © Psychonomic Society, Inc. 2015" be2d326fa588b4ffd1d8d3d4408ae680e1a26277,JOURNA A Survey on Modern Era ’ s Online Object Tracking Algorithms,"[Deshmukh, 2(3): March, 2013] ISSN: 2277 ISSN: 2277-9655 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH INTERNATIONAL JOURNA ENCES & RESEARCH TECHNOLOGY A Survey on Modern Era’s Online Object Tracking Algorithms A Survey on Modern Era’s Online Object Tracking Algorithms A Survey on Modern Era’s Online Object Tracking Algorithms Khemraj Deshmukh*1, Vishal Moyal2 Khemraj Deshmukh" bed7834ae7d371171977a590872f60d137c2f951,GuessWhat?! Visual Object Discovery through Multi-modal Dialogue,"GuessWhat?! Visual object discovery through multi-modal dialogue Harm de Vries University of Montreal Florian Strub Univ. Lille, CNRS, Centrale Lille, Inria, UMR 9189 CRIStAL Sarath Chandar University of Montreal Olivier Pietquin DeepMind Hugo Larochelle Twitter Aaron Courville University of Montreal" befa14324bb71e5d0f30808e54abc970d52f758c,A Convex Approach for Image Hallucination,"OAGM/AAPR Workshop 2013 (arXiv:1304.1876) A Convex Approach for Image Hallucination Institute for Computer Graphics and Vision, University of Technology Graz Peter Innerhofer, Thomas Pock" bef7d5d2c5951ae9ae85fcec4a7eaf5dfd8196c9,Self-learning Trajectory Prediction with Recurrent Neural Networks at Intelligent Intersections, be13f17ca05bb0f80f1689254e516130874c6f6e,"Face Recognition using PCA , Deep Face Method","Gurpreet Kaur et al, International Journal of Computer Science and Mobile Computing, Vol.5 Issue.5, May- 2016, pg. 359-366 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320–088X IMPACT FACTOR: 5.258 IJCSMC, Vol. 5, Issue. 5, May 2016, pg.359 – 366 Face Recognition using PCA, Deep Face Method Gurpreet Kaur1, Sukhvir Kaur2, Amit Walia3 Department of CSE, I.K.G Punjab Technical University 2 3" be25d7bff3b5928adf6c0a7f5495d47113f80997,LEARNING TO DRIVE: PERCEPTION FOR AUTONOMOUS CARS A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"LEARNING TO DRIVE: PERCEPTION FOR AUTONOMOUS CARS A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY David Michael Stavens May 2011" be24e5fd1ec27d444c66183e89b5033db9155de9,"A Continuous, Full-scope, Spatio-temporal Tracking Metric based on KL-divergence","A Continuous, Full-scope, Spatio-temporal Tracking Metric based on KL-divergence Terry Adams U.S. Government Suite 6587 Ft. Meade, MD 20755 Email:" bee609ea6e71aba9b449731242efdb136d556222,Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets,"Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets Yonatan Tariku Tesfaye*, Student Member, IEEE, Eyasu Zemene*, Student Member, IEEE, Andrea Prati, Senior member, IEEE, Marcello Pelillo, Fellow, IEEE, and Mubarak Shah, Fellow, IEEE" be6f29e129a99529f7ed854384d1f4da04c4ca1f,Spatially Consistent Nearest Neighbor Representations for Fine-Grained Classification. (Représentations d'images basées sur un principe de voisins partagés pour la classification fine),"Spatially Consistent Nearest Neighbor Representations for Fine-Grained Classification Valentin Leveau To cite this version: Valentin Leveau. Spatially Consistent Nearest Neighbor Representations for Fine-Grained Classifica- tion. Computer Science [cs]. Université Montpellier, 2016. English. HAL Id: tel-01410137 https://hal.archives-ouvertes.fr/tel-01410137 Submitted on 6 Dec 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" be4c2b6fdde83179dd601541f57ee5d14fe1e98a,Graphical Generative Adversarial Networks,"Graphical Generative Adversarial Networks Chongxuan Li 1 Max Welling 2 Jun Zhu 1 Bo Zhang 1" be313072e9706df300d86bfac54079acfb9c1ef0,Descripteurs à divers niveaux de concepts pour la classification d ’ images multi-objets,"Descripteurs à divers niveaux de concepts pour la classification d’images multi-objets Y. Tamaazousti1 3 H. Le Borgne1 C. Hudelot2 3 CentraleSupélec, Laboratoire de Mathématiques et Informatique pour la Complexité et les Systèmes CEA LIST, Laboratoire Vision et Ingénierie des Contenus Université Paris-Saclay, Laboratoire MICS {Youssef.tamaazousti, Résumé La classification d’images au moyen de descripteurs sé- mantiques repose sur des caractéristiques formées par les sorties de classifieurs binaires, chacun détectant un oncept visuel dans l’image. Les approches existantes onsidèrent souvent les concepts visuels indépendam- ment les uns des autres, alors qu’ils sont souvent liés. Ces relations sont parfois prises en compte, au moyen d’un schéma ascendant dépendant fortement de descrip- teurs bas-niveaux, induisant des relations non-pertinentes" bebea83479a8e1988a7da32584e37bfc463d32d4,Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning,"Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning Supasorn Suwajanakorn∗ Noah Snavely Jonathan Tompson Mohammad Norouzi {supasorn, snavely, tompson, Google AI" be62019734554152c4feef62ba3092894b402efb,ARISTA - image search to annotation on billions of web photos,"The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition Poster Spotlights Session: Thursday Poster Session, Thurs 17 June 2010, 10:30 - 12:10 am ARISTA - Image Search to Annotation on Billions of Web Photos Xin-Jing Wang, Lei Zhang, Ming Liu, Yi Li, Wei-Ying Ma" be0bd420b78be8dfc0aad65dddae10ff1ec30a94,People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees,"People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees Davide Baltieri, Roberto Vezzani, and Rita Cucchiara DIEF - University of Modena and Reggio Emilia Via Vignolese 905, 41125 - Modena, Italy http://imagelab.ing.unimore.it" becb704450c6b2f7f57f03955036a5b66380b816,A Software Architecture for RGB-D People Tracking Based on ROS Framework for a Mobile Robot,"A software architecture for RGB-D people tracking based on ROS framework for a mobile robot Matteo Munaro, Filippo Basso, Stefano Michieletto, Enrico Pagello, and Emanuele Menegatti" bec439c2a9a597c3aeb3f2932adc348d191ccba0,Zero-Shot Kernel Learning,"Zero-Shot Kernel Learning Hongguang Zhang∗,2,1 Piotr Koniusz∗,1,2 Data61/CSIRO, 2Australian National University nu.edu.au2}" beab0d01cdbbbfdc52482b9ef65d6634e4f21b7e,Monocular Semantic Occupancy Grid Mapping With Convolutional Variational Encoder–Decoder Networks,"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks Chenyang Lu1, Marinus Jacobus Gerardus van de Molengraft2, and Gijs Dubbelman1" beeeade98988e55afe81faaedf06dc00848ec751,ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild,"Int J Comput Vis manuscript No. (will be inserted by the editor) ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild Yu Luo · Jianbo Ye · Reginald B. Adams, Jr. · Jia Li · Michelle G. Newman · James Z. Wang Received: date / Accepted: date" beab10d1bdb0c95b2f880a81a747f6dd17caa9c2,DeepDeblur: Fast one-step blurry face images restoration.,"DeepDeblur: Fast one-step blurry face images restoration Lingxiao Wang, Yali Li, Shengjin Wang Tsinghua Unversity" bed06e7ff0b510b4a1762283640b4233de4c18e0,Face Interpretation Problems on Low Quality Images,"Bachelor Project Czech Technical University in Prague Faculty of Electrical Engineering Department of Cybernetics Face Interpretation Problems on Low Quality Images Adéla Šubrtová Supervisor: Ing. Jan Čech, Ph.D May 2018" beb7a0329c3042c2ce63b5789e2581bb8e2dbbea,Generating Visual Representations for Zero-Shot Classification,"Generating Visual Representations for Zero-Shot Classification Maxime Bucher, St´ephane Herbin ONERA - The French Aerospace Lab Palaiseau, France Normandie Univ, UNICAEN, ENSICAEN, CNRS Fr´ed´eric Jurie Caen, France" befd21f74248ca5f22f608043d64cdea67829737,Decoupled Access-Execute on ARM big.LITTLE,"Decoupled Access-Execute on ARM big.LITTLE Anton Weber Uppsala University nton.weber.0295 Kim-Anh Tran Uppsala University kim-anh.tran Stefanos Kaxiras Uppsala University stefanos.kaxiras Alexandra Jimborean lexandra.jimborean Uppsala University" be9dde86ebd10ecb05808e034e3cadd210fe0bfb,SLAMIT : A Sub-map based SLAM system On-line creation of multi-leveled map,"Master of Science Thesis in Electrical Engineering Department of Electrical Engineering, Linköping University, 2016 SLAMIT: A Sub-map based SLAM system On-line creation of multi-leveled map Karl Holmquist" be75a0ff3999754f20e63fde90f4c68b4af22d60,R4-A.1: Dynamics-Based Video Analytics,"R4-A.1: Dynamics-Based Video Analytics PARTICIPANTS Octavia Camps Mario Sznaier Title Co-PI Co-PI Faculty/Staff Institution Graduate, Undergraduate and REU Students Oliver Lehmann Mengran Gou Yongfang Cheng Yin Wang Sadjad Asghari-Esfeden Angels Rates Degree Pursued Institution Email Month/Year of Graduation" be07f2950771d318a78d2b64de340394f7d6b717,3D HMM-based Facial Expression Recognition using Histogram of Oriented Optical Flow,"See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/290192867 D HMM-based Facial Expression Recognition using Histogram of Oriented Optical Flow ARTICLE in SYNTHESIS LECTURES ON ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING · DECEMBER 2015 DOI: 10.14738/tmlai.36.1661 READS AUTHORS, INCLUDING: Sheng Kung Oakland University Djamel Bouchaffra Institute of Electrical and Electronics Engineers PUBLICATION 0 CITATIONS 57 PUBLICATIONS 402 CITATIONS SEE PROFILE SEE PROFILE All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately. Available from: Djamel Bouchaffra Retrieved on: 11 February 2016" beec0138d21271379bdfa89317a0a1d648733bad,Model-Free Multiple Object Tracking with Shared Proposals,"Model-Free Multiple Object Tracking with Shared Proposals Gao Zhu1, Fatih Porikli1,2,3, Hongdong Li1,3 Australian National University1, Data61/CSIRO2, ARC Centre of Excellence for Robotic Vision3" be21529c47b79b688b420c5e296086698ba11350,CNN-Based Multimodal Human Recognition in Surveillance Environments,"Article CNN-Based Multimodal Human Recognition in Surveillance Environments Ja Hyung Koo, Se Woon Cho, Na Rae Baek, Min Cheol Kim and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pil-dong-ro, 1-gil, Jung-gu, Seoul 100-715, Korea; (J.H.K.); (S.W.C.); (N.R.B.); (M.C.K.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 7 August 2018; Accepted: 8 September 2018; Published: 11 September 2018" beff22ec87148ce4eac32fde45ceb5368c735381,Boosted Projection: An Ensemble of Transformation Models,"Boosted Projection: An Ensemble of Transformation Models Ricardo Barbosa Kloss, Artur Jord˜ao, and William Robson Schwartz Smart Surveillance Interest Group, Department of Computer Science Universidade Federal de Minas Gerais, Belo Horizonte, Brazil {rbk," bea5780d621e669e8069f05d0f2fc0db9df4b50f,Convolutional Deep Belief Networks on CIFAR-10,"Convolutional Deep Belief Networks on CIFAR-10 Alex Krizhevsky Introduction We describe how to train a two-layer convolutional Deep Belief Network (DBN) on the 1.6 million tiny images dataset. When training a convolutional DBN, one must decide what to do with the edge pixels of teh images. As the pixels near the edge of an image contribute to the fewest convolutional lter outputs, the model may see it t to tailor its few convolutional lters to better model the edge pixels. This is undesirable becaue it usually comes at the expense of a good model for the interior parts of the image. We investigate several ways of dealing with the edge pixels when training a convolutional DBN. Using a combination of locally-connected onvolutional units and globally-connected units, as well as a few tricks to reduce the eects of overtting, we achieve state-of-the-art performance in the classication task of the CIFAR-10 subset of the tiny images dataset. The dataset Throughout this paper we employ two subsets of the 80 million tiny images dataset [2]. The 80 million tiny images dataset is a collection of 32 × 32 color images obtained by searching various online image search" beb4546ae95f79235c5f3c0e9cc301b5d6fc9374,A Modular Approach to Facial Expression Recognition,"A Modular Approach to Facial Expression Recognition Michal Sindlar Cognitive Artificial Intelligence, Utrecht University, Heidelberglaan 6, 3584 CD, Utrecht Marco Wiering Intelligent Systems Group, Utrecht University, Padualaan 14, 3508 TB, Utrecht" be437b53a376085b01ebd0f4c7c6c9e40a4b1a75,Face Recognition and Retrieval Using Cross Age Reference Coding,"ISSN (Online) 2321 – 2004 ISSN (Print) 2321 – 5526 INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN ELECTRICAL, ELECTRONICS, INSTRUMENTATION AND CONTROL ENGINEERING Vol. 4, Issue 5, May 2016 IJIREEICE Face Recognition and Retrieval Using Cross Age Reference Coding Sricharan H S1, Srinidhi K S1, Rajath D N1, Tejas J N1, Chandrakala B M2 BE, DSCE, Bangalore1 Assistant Professor, DSCE, Bangalore2" be8c517406528edc47c4ec0222e2a603950c2762,CHAPTER 2 MEASURING FACIAL ACTION,"Harrigan / The new handbook of methods in nonverbal behaviour research 02-harrigan-chap02 Page Proof page 7 7.6.2005 5:45pm B A S I C R E S E A RC H M E T H O D S A N D P RO C E D U R E S" 199aabb19ea78576a74d573739a7f35cf04fac6e,Fast globally optimal 2D human detection with loopy graph models,"Fast Globally Optimal 2D Human Detection with Loopy Graph Models Paper by T.-P. Tian and S. Sclaroff Slides by A. Vedaldi" 19359fb238888c0eb012a4ab5c6f0fa0e9be493b,Enhanced Facial Expression Recognition using 2DPCA Principal component Analysis and Gabor Wavelets,"Enhanced Facial Expression Recognition using 2DPCA Principal component Analysis nd Gabor Wavelets. (1)Laboratory of Automatic and Signals Annaba (LASA) , Department of electronics, Faculty of Engineering, Zermi.Narima(1), Saaidia.Mohammed(2), Badji-Mokhtar University, P.O.Box 12, Annaba-23000, Algeria. E-Mail : (2) Département de Génie-électrique, Université M.C.M. Souk-Ahras, Algeria" 1962e4c9f60864b96c49d85eb897141486e9f6d1,Locality preserving embedding for face and handwriting digital recognition,"Neural Comput & Applic (2011) 20:565–573 DOI 10.1007/s00521-011-0577-7 O R I G I N A L A R T I C L E Locality preserving embedding for face and handwriting digital recognition Zhihui Lai • MingHua Wan • Zhong Jin Received: 3 December 2008 / Accepted: 11 March 2011 / Published online: 1 April 2011 Ó Springer-Verlag London Limited 2011 supervised manifold the local sub-manifolds." 19aa506d04d3f7241fc71b595d28b5f1bb99edad,Compact Generalized Non-local Network,"Compact Generalized Non-local Network Kaiyu Yue1,3 Ming Sun1 Yuchen Yuan1 Feng Zhou2 Errui Ding1 Fuxin Xu3 Baidu VIS 2Baidu Research Central South University {yuekaiyu, sunming05, yuanyuchen02, zhoufeng09," 1936a73920c5a7eb97e8b73cb9a6096aa509e402,Robust Multi-Person Tracking from Moving Platforms,"Robust Multi-Person Tracking from Moving Platforms Andreas Ess1, Konrad Schindler1, Bastian Leibe1,2 and Luc van Gool1,3 ETH Z¨urich KU Leuven, IBBT RWTH Aachen" 195d331c958f2da3431f37a344559f9bce09c0f7,Parsing occluded people by flexible compositions,"Parsing Occluded People by Flexible Compositions Xianjie Chen, Alan Yuille University of California, Los Angeles. Figure 1: An illustration of the flexible compositions. Each connected sub- tree of the full graph (include the full graph itself) is a flexible composition. The flexible compositions that do not have certain parts are suitable for the people with those parts occluded. Figure 2: The absence of body parts evidence can help to predict occlusion. However, absence of evidence is not evidence of absence. It can fail in some challenging scenes. The local image measurements near the occlusion oundary (i.e., around the right elbow and left shoulder) can reliably provide evidence of occlusion. This paper presents an approach to parsing humans when there is signifi- ant occlusion. We model humans using a graphical model which has a tree structure building on recent work [1, 6] and exploit the connectivity prior that, even in presence of occlusion, the visible nodes form a connected sub- tree of the graphical model. We call each connected subtree a flexible com- position of object parts. This involves a novel method for learning occlusion ues. During inference we need to search over a mixture of different flexible" 194af94f1ea9357bebb0aab5ab98aa0daa21ddbd,Snapshot Distillation: Teacher-Student Optimization in One Generation,"Snapshot Distillation: Teacher-Student Optimization in One Generation Chenglin Yang1 Lingxi Xie1 Chi Su2 Alan L. Yuille1 Johns Hopkins University 2Kingsoft" 19fcb95815e4c225b250f7deed9be3e90963933d,Evaluación de la calidad de las imágenes de rostros utilizadas para la identificación de las personas,"ISSN: 1405-5546 Instituto Politécnico Nacional México Méndez-Vázquez, Heydi; Chang, Leonardo; Rizo-Rodríguez, Dayron; Morales-González, Annette Evaluación de la calidad de las imágenes de rostros utilizadas para la identificación de las personas Instituto Politécnico Nacional Distrito Federal, México Disponible en: http://www.redalyc.org/articulo.oa?id=61523309003 Cómo citar el artículo Número completo Más información del artículo Página de la revista en redalyc.org Sistema de Información Científica Red de Revistas Científicas de América Latina, el Caribe, España y Portugal Proyecto académico sin fines de lucro, desarrollado bajo la iniciativa de acceso abierto" 191beb87f84326d2cc9c427efe2a5abee8f67574,Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery,"Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery Alina Marcu and Marius Leordeanu 1" 19cfe13e8196872b81d6f31d2849dc540d146f7c,A Bayesian Framework for Sparse Representation-Based 3-D Human Pose Estimation,"A Bayesian Framework for Sparse Representation-Based 3D Human Pose Estimation Behnam Babagholami-Mohamadabadi, Amin Jourabloo, Ali Zarghami, and Shohreh Kasaei Senior Member, IEEE" 193ec7bb21321fcf43bbe42233aed06dbdecbc5c,Automatic 3D Facial Expression Analysis in Videos,"UC Santa Barbara UC Santa Barbara Previously Published Works Title Automatic 3D facial expression analysis in videos Permalink https://escholarship.org/uc/item/3g44f7k8 Authors Chang, Y Vieira, M Turk, M et al. Publication Date 005-01-01 Peer reviewed eScholarship.org Powered by the California Digital Library University of California" 19fd089807f8925b9384bae6e66cbfe7e6d318aa,Acume: A new visualization tool for understanding facial expression and gesture data,"Acume: A New Visualization Tool for Understanding Facial Expression and Gesture Daniel McDuff - MIT Media Lab March 24, 2011" 193c9bd069e9457ac8650a8dfd4319bb3f4afd56,Improving Person Tracking Using an Inexpensive Thermal Infrared Sensor,"Improving Person Tracking Using an Inexpensive Thermal Infrared Sensor Suren Kumar Univ. of SUNY-Buffalo Tim K. Marks Mitsubishi Electric Research Labs Michael Jones Mitsubishi Electric Research Labs" 19296e129c70b332a8c0a67af8990f2f4d4f44d1,Is that you? Metric learning approaches for face identification,"Metric Learning Approaches for Face Identification Is that you? M. Guillaumin, J. Verbeek and C. Schmid LEAR team, INRIA Rhˆone-Alpes, France Supplementary Material" 19a3374ac2f917b408b4bcdca33fc9e9fd7ff260,Visual Fixation Patterns during Reciprocal Social Interaction Distinguish a Subgroup of 6-Month-Old Infants At-Risk for Autism from Comparison Infants.,"J Autism Dev Disord (2007) 37:108–121 DOI 10.1007/s10803-006-0342-4 O R I G I N A L P A P E R Visual Fixation Patterns during Reciprocal Social Interaction Distinguish a Subgroup of 6-Month-Old Infants At-Risk for Autism from Comparison Infants Noah Merin Æ Gregory S. Young Æ Sally Ozonoff Æ Sally J. Rogers Published online: 27 December 2006 Ó Springer Science+Business Media, LLC 2006" 19666b9eefcbf764df7c1f5b6938031bcf777191,Common and Individual Features Analysis: Beyond Canonical Correlation Analysis,"IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS Group Component Analysis for Multi-block Data: Common and Individual Feature Extraction Guoxu Zhou, Andrzej Cichocki Fellow, IEEE, Yu Zhang, and Danilo Mandic Fellow, IEEE" 1927d86d26a1afdd4bb988b26ba89a8589675473,Traffic analysis using discrete wavelet transform and Bayesian regression,"IOSR Journal of Electronics & Communication Engineering (IOSR-JECE) ISSN(e) : 2278-1684 ISSN(p) : 2320-334X, PP 39-58 www.iosrjournals.org TRAFFIC ANALYSIS USING DISCRETE WAVELET TRANSFORM AND BAYESIAN REGRESSION Nishidha.T, Dr. P.Janardhanan (Electronics & Communication, KMCT College of Engineering / University of Calicut, India) (Electronics & Communication, KMCT College of Engineering / University of Calicut, India)" 19b9583d0c1fa3ac86ac02fe5c10d8d4a59fc459,Dynamic Texture Feature Extraction Using Weber Local Descriptor,"D.G.Agrawal et al. Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 4, Issue 3( Version 1), March 2014, pp.502-506 RESEARCH ARTICLE OPEN ACCESS Dynamic Texture Feature Extraction Using Weber Local Descriptor D.G.Agrawal*, Pranoti M. Jangale** *(Department of Electronics and Communication Engineering, North Maharashtra University, Maharashtra-19) **(Department of Electronics and Communication Engineering, North Maharashtra University, Maharashtra-19)" 1916a795d293aa3ddd9802ad5b5d50bb4a59b98f,Fast Multiple-Part Based Object Detection Using KD-Ferns,"Fast multiple-part based object detection using KD-Ferns Dan Levi Shai Silberstein Aharon Bar-Hillel General Motors R&D, Advanced Technical Center - Israel" 190d8bd39c50b37b27b17ac1213e6dde105b21b8,Mining Weakly Labeled Web Facial Images for Search-Based Face Annotation,"This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore. Title Mining weakly labeled web facial images for search- ased face annotation Author(s) Wang, Dayong; Hoi, Steven C. H.; He, Ying; Zhu, Jianke Citation Wang, D., Hoi, S. C. H., He, Y., & Zhu, J. (2014). Mining weakly labeled web facial images for search-based face nnotation. IEEE Transactions on Knowledge and Data Engineering, 26(1), 166-179. http://hdl.handle.net/10220/18955 Rights © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any opyrighted component of this work in other works." 19766585a701749fc297a5ca6b8cdc0c62d4ba1b,A Bottom-Up Approach for Pancreas Segmentation Using Cascaded Superpixels and (Deep) Image Patch Labeling,"A Bottom-up Approach for Pancreas Segmentation using Cascaded Superpixels and (Deep) Image Patch Labeling Amal Faraga, Le Lua, Holger R. Rotha, Jiamin Liua, Evrim Turkbeya, Ronald M. Summersa,∗ Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Building 10 Room 1C224D, MSC 1182, Bethesda, MD 20892-1182, United States" 192e439b19824d06bb21ad6bd63cc7a55772549f,Face recognition using SURF features,"MIPPR 2009: Pattern Recognition and Computer Vision, edited by Mingyue Ding, Bir Bhanu, Friedrich M. Wahl, Jonathan Roberts, Proc. of SPIE Vol. 7496, 749628 © 2009 SPIE · CCC code: 0277-786X/09/$18 · doi: 10.1117/12.832636 Proc. of SPIE Vol. 7496 749628-1 Downloaded from SPIE Digital Library on 22 Dec 2009 to 140.116.214.41. Terms of Use: http://spiedl.org/terms" 197c64c36e8a9d624a05ee98b740d87f94b4040c,Regularized Greedy Column Subset Selection,"Regularized Greedy Column Subset Selection Bruno Ordozgoiti*a, Alberto Mozoa, Jes´us Garc´ıa L´opez de Lacalleb Department of Computer Systems, Universidad Polit´ecnica de Madrid Department of Applied Mathematics, Universidad Polit´ecnica de Madrid" 19c53302bda8a82ec40d314a85b1713f43058a1a,Deep learning models of biological visual information processing,"Turcsány, Diána (2016) Deep learning models of iological visual information processing. PhD thesis, University of Nottingham. Access from the University of Nottingham repository: http://eprints.nottingham.ac.uk/35561/1/thesis_DianaTurcsany.pdf Copyright and reuse: The Nottingham ePrints service makes this work by researchers of the University of Nottingham available open access under the following conditions. This article is made available under the University of Nottingham End User licence and may e reused according to the conditions of the licence. For more details see: http://eprints.nottingham.ac.uk/end_user_agreement.pdf For more information, please contact" 19af008599fb17bbd9b12288c44f310881df951c,Discriminative Local Sparse Representations for Robust Face Recognition,"Discriminative Local Sparse Representations for Robust Face Recognition Yi Chen, Umamahesh Srinivas, Thong T. Do, Vishal Monga, and Trac D. Tran" 19841b721bfe31899e238982a22257287b9be66a,S KIP RNN : L EARNING TO S KIP S TATE U PDATES IN R ECURRENT N EURAL N ETWORKS,"Published as a conference paper at ICLR 2018 SKIP RNN: LEARNING TO SKIP STATE UPDATES IN RECURRENT NEURAL NETWORKS V´ıctor Campos∗†, Brendan Jou‡, Xavier Gir´o-i-Nieto§, Jordi Torres†, Shih-Fu ChangΓ Barcelona Supercomputing Center, ‡Google Inc, §Universitat Polit`ecnica de Catalunya, ΓColumbia University {victor.campos," 19158dfe2815e7f9eebc5822687e83d0a89ae147,Semantic Regularisation for Recurrent Image Annotation,[cs.CV] 16 Nov 2016 19d583bf8c5533d1261ccdc068fdc3ef53b9ffb9,FaceNet: A unified embedding for face recognition and clustering,"FaceNet: A Unified Embedding for Face Recognition and Clustering Florian Schroff Dmitry Kalenichenko James Philbin Google Inc. Google Inc. Google Inc." 191674c64f89c1b5cba19732869aa48c38698c84,FACE IMAGE RETRIEVAL USING ATTRIBUTE-ENHANCED SPARSE CODEWORDS,"International Journal of Advanced Technology in Engineering and Science www.ijates.com Volume No.03, Issue No. 03, March 2015 ISSN (online): 2348 – 7550 FACE IMAGE RETRIEVAL USING ATTRIBUTE - ENHANCED SPARSE CODEWORDS E.Sakthivel1 , M.Ashok kumar2 PG scholar, Communication Systems, Adhiyamaan College of Engineeing,Hosur,(India) Asst. Prof., Electronics And Communication Engg., Adhiyamaan College of Engg.,Hosur,(India)" 19911c7e66b05d5aa28673608fdfc50ef00591dd,Recognizing Human Faces: Physical Modeling and Pattern Classification, 19a30ad283f2ab2d84f1c666d17492da14056d75,Visuomotor Coordination in Reach-To-Grasp Tasks: From Humans to Humanoids and Vice Versa,"Visuomotor Coordination in Reach-To-Grasp Tasks: From Humans to Humanoids and Vice Versa THÈSE NO 6695 (2015) PRÉSENTÉE LE 4 JUIN 2015 À L’ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE À LA FACULTÉ DES SCIENCES ET TECHNIQUES DE L'INGÉNIEUR LABORATOIRE D'ALGORITHMES ET SYSTÈMES D'APPRENTISSAGE À L’INSTITUTO SUPERIOR TÉCNICO (IST) DA UNIVERSIDADE DE LISBOA INSTITUTO DE SISTEMA E ROBOTICA PROGRAMME DOCTORAL EN GÉNIE ÉLECTRIQUE DOUTORAMENTO EM ENGENHARIA ELECTROTÉCNICA E DE COMPUTADORES POUR L’OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES (PhD) Luka LUKIC Prof. A. Billard, Prof. J. Santos-Victor, directeurs de thèse cceptée sur proposition du jury: Prof. J. Faria, président du jury Prof. D. Vernon, rapporteur Prof. E. Bicho, rapporteuse Prof. A. Bernardino, rapporteur Prof. G. Sandini, rapporteur" 19dc5a1156819230e6ae425e9c9d56e898d6bcb9,Comparing human and machine face recognition 1 Face Recognition Algorithms Surpass Humans,"Comparing human and machine face recognition1 Face Recognition Algorithms Surpass Humans Matching Faces Over Changes in Illumination Alice J. O’TOOLE, P. Jonathon PHILLIPS, Fang JIANG, Janet AYYAD, Nils PENARD, nd Hervé ABDI*" 198b6beb53e0e61357825d57938719f614685f75,Vaulted Verification : A Scheme for Revocable Face Recognition,"Vaulted Verification: A Scheme for Revocable Face Recognition Michael Wilber University of Colorado, Colorado Springs" 19cfec264e863793dd96a5f308a3b603c6b9912e,Attention-Based Ensemble for Deep Metric Learning,"Attention-based Ensemble for Deep Metric Learning Wonsik Kim, Bhavya Goyal, Kunal Chawla, Jungmin Lee, Keunjoo Kwon Samsung Research, Samsung Electronics {wonsik16.kim, bhavya.goyal, kunal.chawla, jm411.lee," 197eafb6abb6b7d2813eec0891b143e27fc57386,Smile! Studying expressivity of happiness as a synergic factor in collaborative information seeking,"Smile! Studying expressivity of happiness as a synergic factor in collaborative information seeking. Rutgers University has made this article freely available. Please share how this access benefits you. Your story matters. [https://rucore.libraries.rutgers.edu/rutgers-lib/47408/story/] This work is the AUTHOR'S ORIGINAL (AO) This is the author's original version of a work, which may or may not have been subsequently published. The author accepts full responsibility for the article. Content and layout is as set out by the author. Citation to this Version: Shah, Chirag, González-Ibáñez, Roberto & Córdova-Rubio, Natalia. (2011). Smile! Studying expressivity of happiness as a synergic factor in collaborative information seeking.. New Orleans (La.). Retrieved from doi:10.7282/T3NK3GWF. Terms of Use: Copyright for scholarly resources published in RUcore is retained by the copyright holder. By virtue of its appearance in this open ccess medium, you are free to use this resource, with proper attribution, in educational and other non-commercial settings. Other uses, such as reproduction or republication, may require the permission of the copyright holder. Article begins on next page SOAR is a service of RUcore, the Rutgers University Community Repository RUcore is developed and maintained by Rutgers University Libraries" 197a3c1863c780507798c9550dd6faadeb65caaa,0 Processing and Recognising Faces in 3 D Images,",300+OPEN ACCESS BOOKS107,000+INTERNATIONALAUTHORS AND EDITORS113+ MILLIONDOWNLOADSBOOKSDELIVERED TO151 COUNTRIESAUTHORS AMONGTOP 1%MOST CITED SCIENTIST12.2%AUTHORS AND EDITORSFROM TOP 500 UNIVERSITIESSelection of our books indexed in theBook Citation Index in Web of Science™Core Collection (BKCI)Chapter from the book New Approaches to Characterization and Recognition of FacesDownloaded from: http://www.intechopen.com/books/new-approaches-to-characterization-and-recognition-of-facesPUBLISHED BYWorld's largest Science,Technology & Medicine Open Access book publisherInterested in publishing with InTechOpen?Contact us at" 197598af5be60fc75535c2f90849e60ac7122871,Fast multi-view face tracking with pose estimation,"Fast Multiview Face Tracking with Pose Estimation Julien Meynet∗, Taner Arsan∗∗, Javier Cruz Mota∗ and Jean-Philippe Thiran∗ Ecole Polytechnique F´ed´erale de Lausanne (EPFL) Signal Processing Institute 015 Lausanne, Switzerland Kadir Has University Computer Engineering Department Istanbul 34230, Turkey Technical report TR-ITS.2007.01 January 26, 2007" 19d4855f064f0d53cb851e9342025bd8503922e2,Learning SURF Cascade for Fast and Accurate Object Detection,"Learning SURF Cascade for Fast and Accurate Object Detection Jianguo Li, Yimin Zhang Intel Labs China" 19f7654f22416e6fdf430c1c873ad3e8c15e64f8,Zero-crossing based image projections encoding for eye localization,"0th European Signal Processing Conference (EUSIPCO 2012) © EURASIP, 2012 - ISSN 2076-1465 . INTRODUCTION" 19fb5e5207b4a964e5ab50d421e2549ce472baa8,Online emotional facial expression dictionary,"International Conference on Computer Systems and Technologies - CompSysTech’14 Online Emotional Facial Expression Dictionary Léon Rothkrantz" 19b9e5127155730c618c0e1b41e1c723f143651d,Face Verification for Mobile Personal Devices,"Face Verification for Mobile Personal Devices Qian Tao" 193a69489230de1013dff9af1232e5379cc5282f,Intelligent Multimodal Framework for Human Assistive Robotics Based on Computer Vision Algorithms,"Article Intelligent Multimodal Framework for Human Assistive Robotics Based on Computer Vision Algorithms Eugenio Ivorra 1,* Luis Daniel Lledó 2, Nicolás Garcia-Aracil 2 , Mario Ortega 1, José M. Catalán 2,* nd Mariano Alcañiz 1 , Santiago Ezquerro 2, Institute for Research and Innovation in Bioengineering, Universitat Politècnica de València, 6022 Valencia, Spain; (M.O.); (M.A.) Biomedical Neuroengineering Group, Universidad Miguel Hernández de Elche, 03202 Elche, Spain; (S.E.); (L.D.L.); (N.G.-A.) * Correspondence: or (E.I.); (J.M.C.) Received: 4 July 2018; Accepted: 23 July 2018; Published: 24 July 2018" 194ea22b54f9aee6e0eb5d0dee100d46438b3cea,"Structured Tracking for Safety , Security , and Privacy : Algorithms for Fusing Noisy Estimates from Sensor , Robot , and Camera Networks","Structured Tracking for Safety, Security, and Privacy: Algorithms for Fusing Noisy Estimates from Sensor, Robot, and Camera Networks Jeremy Ryan Schiff Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2009-104 http://www.eecs.berkeley.edu/Pubs/TechRpts/2009/EECS-2009-104.html July 23, 2009" 19f4020db2a37102ec3236ff72d8c7d3a0992ef9,Face Recognition by Kernel Independent Component Analysis,"Face Recognition by Kernel Independent Component Analysis T. Martiriggiano, M. Leo, T. D’Orazio, A. Distante, CNR- ISSIA via Amendoda 122/D-I 70126 BARI ITALY Abtract. In this paper, we introduce a new feature representation method for face recognition. The proposed method, referred as Kernel ICA, combines the strengths of the Kernel and Independent Component Analysis approaches. For performing Kernel ICA, we employ an algorithm developed by F. R. Bach and M. I. Jordan. This algorithm has proven successful for separating randomly mixed auditory signals, but it has never been applied on bidimensional signals such as images. We compare the performance of Kernel ICA with classical al- gorithms such as PCA and ICA within the context of appearance-based face recognition problem using the FERET database. Experimental results show that oth Kernel ICA and ICA representations are superior to representations based on PCA for recognizing faces across days and changes in expressions. Introduction Face recognition has become one of most important biometrics technologies during the past 20 years. It has a wide range of applications such as identity authentication, ccess control, and surveillance." e1966f234ad3f30302af3ddea70ed9eb5dcbe120,Entropy-Based Localization of Textured Regions,"Entropy-based Localization of Textured Regions Liliana Lo Presti and Marco La Cascia University of Palermo" e17783170ecc48253fa16123a041ae298184f4ff,Graph Embedding Algorithms Based on Neighborhood Discriminant Embedding for Face Recognition,"International Journal of Computer Information Systems and Industrial Management Applications. ISSN 2150-7988 Volume 4 (2012) pp. 374–382 (cid:13) MIR Labs, www.mirlabs.net/ijcisim/index.html Graph Embedding Algorithms Based on Neighborhood Discriminant Embedding for Face Recognition Dexing Zhong1,2, Jiuqiang Han1, Yongli Liu1 and Shengbin Li2 Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi’an Jiaotong University, 8 Xianning West Road, Xian, 710049 P. R. China State Key Laboratory of Ministry of Health for Forensic Sciences, Xian Jiaotong University, 76 Yanta West Road, Xian, 710061 P. R. China" e1e5d64318ec0a493995fb83ef4f433ddde82e77,1 INTROVERSION / EXTRAVERSION AFFECTS THE GAZE-CUEING EFFECT,"(cid:5)(cid:36)(cid:57)(cid:50)(cid:44)(cid:39)(cid:44)(cid:49)(cid:42)(cid:3)(cid:50)(cid:53)(cid:3)(cid:36)(cid:51)(cid:51)(cid:53)(cid:50)(cid:36)(cid:38)(cid:43)(cid:44)(cid:49)(cid:42)(cid:3)(cid:40)(cid:60)(cid:40)(cid:54)(cid:5)(cid:34)(cid:3)(cid:44)(cid:49)(cid:55)(cid:53)(cid:50)(cid:57)(cid:40)(cid:53)(cid:54)(cid:44)(cid:50)(cid:49)(cid:18)(cid:40)(cid:59)(cid:55)(cid:53)(cid:36)(cid:57)(cid:40)(cid:53)(cid:54)(cid:44)(cid:50)(cid:49) (cid:36)(cid:41)(cid:41)(cid:40)(cid:38)(cid:55)(cid:54)(cid:3)(cid:55)(cid:43)(cid:40)(cid:3)(cid:42)(cid:36)(cid:61)(cid:40)(cid:16)(cid:38)(cid:56)(cid:40)(cid:44)(cid:49)(cid:42)(cid:3)(cid:40)(cid:41)(cid:41)(cid:40)(cid:38)(cid:55) (cid:16)(cid:16)(cid:48)(cid:68)(cid:81)(cid:88)(cid:86)(cid:70)(cid:85)(cid:76)(cid:83)(cid:87)(cid:3)(cid:39)(cid:85)(cid:68)(cid:73)(cid:87)(cid:16)(cid:16) (cid:38)(cid:82)(cid:74)(cid:81)(cid:76)(cid:87)(cid:76)(cid:89)(cid:72)(cid:3)(cid:51)(cid:85)(cid:82)(cid:70)(cid:72)(cid:86)(cid:86)(cid:76)(cid:81)(cid:74) (cid:3) (cid:3) (cid:48)(cid:68)(cid:81)(cid:88)(cid:86)(cid:70)(cid:85)(cid:76)(cid:83)(cid:87)(cid:3)(cid:49)(cid:88)(cid:80)(cid:69)(cid:72)(cid:85)(cid:29) (cid:41)(cid:88)(cid:79)(cid:79)(cid:3)(cid:55)(cid:76)(cid:87)(cid:79)(cid:72)(cid:29) (cid:36)(cid:85)(cid:87)(cid:76)(cid:70)(cid:79)(cid:72)(cid:3)(cid:55)(cid:92)(cid:83)(cid:72)(cid:29) (cid:46)(cid:72)(cid:92)(cid:90)(cid:82)(cid:85)(cid:71)(cid:86)(cid:29) (cid:38)(cid:82)(cid:85)(cid:85)(cid:72)(cid:86)(cid:83)(cid:82)(cid:81)(cid:71)(cid:76)(cid:81)(cid:74)(cid:3)(cid:36)(cid:88)(cid:87)(cid:75)(cid:82)(cid:85)(cid:29) (cid:38)(cid:82)(cid:85)(cid:85)(cid:72)(cid:86)(cid:83)(cid:82)(cid:81)(cid:71)(cid:76)(cid:81)(cid:74)(cid:3)(cid:36)(cid:88)(cid:87)(cid:75)(cid:82)(cid:85)(cid:3)(cid:54)(cid:72)(cid:70)(cid:82)(cid:81)(cid:71)(cid:68)(cid:85)(cid:92) (cid:44)(cid:81)(cid:73)(cid:82)(cid:85)(cid:80)(cid:68)(cid:87)(cid:76)(cid:82)(cid:81)(cid:29) (cid:38)(cid:82)(cid:85)(cid:85)(cid:72)(cid:86)(cid:83)(cid:82)(cid:81)(cid:71)(cid:76)(cid:81)(cid:74)(cid:3)(cid:36)(cid:88)(cid:87)(cid:75)(cid:82)(cid:85)(cid:10)(cid:86)(cid:3)(cid:44)(cid:81)(cid:86)(cid:87)(cid:76)(cid:87)(cid:88)(cid:87)(cid:76)(cid:82)(cid:81)(cid:29) (cid:38)(cid:82)(cid:85)(cid:85)(cid:72)(cid:86)(cid:83)(cid:82)(cid:81)(cid:71)(cid:76)(cid:81)(cid:74)(cid:3)(cid:36)(cid:88)(cid:87)(cid:75)(cid:82)(cid:85)(cid:10)(cid:86)(cid:3)(cid:54)(cid:72)(cid:70)(cid:82)(cid:81)(cid:71)(cid:68)(cid:85)(cid:92) (cid:44)(cid:81)(cid:86)(cid:87)(cid:76)(cid:87)(cid:88)(cid:87)(cid:76)(cid:82)(cid:81)(cid:29) (cid:41)(cid:76)(cid:85)(cid:86)(cid:87)(cid:3)(cid:36)(cid:88)(cid:87)(cid:75)(cid:82)(cid:85)(cid:29) (cid:41)(cid:76)(cid:85)(cid:86)(cid:87)(cid:3)(cid:36)(cid:88)(cid:87)(cid:75)(cid:82)(cid:85)(cid:3)(cid:54)(cid:72)(cid:70)(cid:82)(cid:81)(cid:71)(cid:68)(cid:85)(cid:92)(cid:3)(cid:44)(cid:81)(cid:73)(cid:82)(cid:85)(cid:80)(cid:68)(cid:87)(cid:76)(cid:82)(cid:81)(cid:29) (cid:50)(cid:85)(cid:71)(cid:72)(cid:85)(cid:3)(cid:82)(cid:73)(cid:3)(cid:36)(cid:88)(cid:87)(cid:75)(cid:82)(cid:85)(cid:86)(cid:29) (cid:50)(cid:85)(cid:71)(cid:72)(cid:85)(cid:3)(cid:82)(cid:73)(cid:3)(cid:36)(cid:88)(cid:87)(cid:75)(cid:82)(cid:85)(cid:86)(cid:3)(cid:54)(cid:72)(cid:70)(cid:82)(cid:81)(cid:71)(cid:68)(cid:85)(cid:92)(cid:3)(cid:44)(cid:81)(cid:73)(cid:82)(cid:85)(cid:80)(cid:68)(cid:87)(cid:76)(cid:82)(cid:81)(cid:29)" e151c99b5e55bfc03047a2c6c2118cd9e4ad829b,Perspectives on Deep Multimodel Robot Learning,"Perspectives on Deep Multimodel Robot Learning Wolfram Burgard, Abhinav Valada, Noha Radwan, Tayyab Naseer, Jingwei Zhang, Johan Vertens, Oier Mees, Andreas Eitel and Gabriel Oliveira" e19ebad4739d59f999d192bac7d596b20b887f78,Learning Gating ConvNet for Two-Stream based Methods in Action Recognition,"Learning Gating ConvNet for Two-Stream based Methods in Action Recognition Jiagang Zhu1,2, Wei Zou1, Zheng Zhu1,2" e1cb5ff731dfb84ee46d8469c68964b7c4c0f3ea,Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition.,"SUBMISSION FOR IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018 Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition Xiangbo Shu, Jinhui Tang, Senior Member, IEEE, Guo-Jun Qi, Wei Liu and Jian Yang" e16311bf88192e1588826984d6761f7f26efe542,Image Segmentation Based Face Recognition Using Enhanced SPCA-KNN Method,"Image Segmentation Based Face Recognition Using Enhanced SPCA-KNN Method Mrs.J.Savitha M.Sc.,M.Phil., Ph.D Research Scholar,Karpagam University, Coimbatore, Tamil Nadu, India. Dr.A.V.Senthil Kumar., Director, Hindustan College of Arts and Science, Coimbatore, Tamil Nadu, India." e1cb110c45c4416f7aff490db2674abe1460259e,Hard-Aware Point-to-Set Deep Metric for Person Re-identification,"Hard-AwarePoint-to-SetDeepMetricforPersonRe-identificationRuiYu1,ZhiyongDou1,SongBai1,ZhaoxiangZhang2,YongchaoXu1( ),andXiangBai1(" e10662a59b5f8e1f5684409023f11ca727647320,Performance Evaluation of Deep Learning Networks for Semantic Segmentation of Traffic Stereo-Pair Images,"Performance Evaluation of Deep Learning Networks for Semantic Segmentation of Traffic Stereo-Pair Images Vlad Taran, Nikita Gordienko, Yuriy Kochura, Yuri Gordienko, Alexandr Rokovyi, Oleg Alienin, Sergii Stirenko National Technical University of Ukraine ""Igor Sikorsky Kyiv Polytechnic Institute"", Kyiv, Ukraine Semantic image segmentation is one the most demanding task, especially for analysis of traffic conditions for self-driving cars. Here the results of application of several deep learning architectures (PSPNet and ICNet) for semantic image segmentation of traffic stereo-pair images are presented. The images from Cityscapes dataset and custom urban images were analyzed as to the segmentation accuracy and image inference time. For the models pre-trained on Cityscapes dataset, the inference time was equal in the limits of standard deviation, but the segmentation accuracy was different for various cities and stereo channels even. The distributions of accuracy (mean intersection over union — mIoU) values for each city and channel re asymmetric, long-tailed, and have many extreme outliers, especially for PSPNet network in comparison to ICNet network. Some statistical properties of these distributions (skewness, kurtosis) allow us to distinguish these two networks and open the question about relations between architecture of deep learning networks and statistical distribution of the predicted results (mIoU here). The results obtained demonstrated the different sensitivity of these networks to: (1) the local street view peculiarities in different cities that should be taken into account during the targeted fine tuning the models before their practical applications, (2) the right and left data channels in stereo-pairs. For both networks, the difference in the predicted results" e181aca6e4b7142d2254a93477170e75c335d616,A Combined SIFT / SURF Descriptor for Automatic Face Recognition,"A Combined SIFT/SURF Descriptor for Automatic Face Recognition Ladislav Lenc, Pavel Král Dept. of Computer Science & Engineering Faculty of Applied Sciences University of West Bohemia Plzeň, Czech Republic NTIS - New Technologies for the Information Society Faculty of Applied Sciences University of West Bohemia Plzeň, Czech Republic" e1cee76d2f9120e603b8c7fc586e6c346cf6476f,Automatic Detection and Recognition of Man-made Objects in High Resolution Remote Sensing Images Using Hierarchical Semantic Graph Model,"International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XL-1/W1, ISPRS Hannover Workshop 2013, 21 – 24 May 2013, Hannover, Germany" e1d726d812554f2b2b92cac3a4d2bec678969368,Human Action Recognition Bases on Local Action Attributes,"J Electr Eng Technol.2015; 10(?): 30-40 http://dx.doi.org/10.5370/JEET.2015.10.2.030 ISSN(Print) 975-0102 ISSN(Online) 2093-7423 Human Action Recognition Bases on Local Action Attributes Jing Zhang*, Hong Liu*, Weizhi Nie† Lekha Chaisorn**, Yongkang Wong** nd Mohan S Kankanhalli**" e1fb8ab53996f06e9a35de6b553333bd6279bcbd,Learning Multilayer Channel Features for Pedestrian Detection,"Learning Multilayer Channel Features for Pedestrian Detection Jiale Cao, Yanwei Pang, and Xuelong Li" e1e5d903887f8e1c412fab041726c4b34ffa820a,Failing to Learn: Autonomously Identifying Perception Failures for Self-Driving Cars,"Failing to Learn: Autonomously Identifying Perception Failures for Self-driving Cars Manikandasriram Srinivasan Ramanagopal1, Cyrus Anderson1, Ram Vasudevan2 and Matthew Johnson-Roberson3" e1e6e6792e92f7110e26e27e80e0c30ec36ac9c2,Ranking with Adaptive Neighbors,"TSINGHUA SCIENCE AND TECHNOLOGY ISSNll1007-0214 0?/?? pp???–??? DOI: 10.26599/TST.2018.9010000 Volume 1, Number 1, Septembelr 2018 Ranking with Adaptive Neighbors Muge Li, Liangyue Li, and Feiping Nie∗" e1c0beb01462d37a77c34909a02a29725c187f5e,GA-fisher: a new LDA-based face recognition algorithm with selection of principal components,"IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, VOL. 35, NO. 5, OCTOBER 2005 GA-Fisher: A New LDA-Based Face Recognition Algorithm With Selection of Principal Components Wei-Shi Zheng, Jian-Huang Lai, and Pong C. Yuen" e163118b4a5b8016754134215433eee1f2c0065a,3-D Shape Matching for Face Analysis and Recognition,"-D Shape Matching for Face Analysis and Recognition Wei Quan, Bogdan J. Matuszewski and Lik-Kwan Shark Robotics and Computer Vision Research Laboratory, Applied Digital Signal and Image Processing (ADSIP) Research Centre, University of Central Lancashire, Preston PR1 2HE, U.K. Keywords: Face Recognition, Shape Matching and Modelling, Isometric Embedding Representation, Non-Rigid Deformation Registration." e1e2b6a8944a4e6f195b6f7371ee9e6b0684ae6b,Generating Personalized Virtual Agent in Speech Dialogue System for People with Dementia,"Generating Personalized Virtual Agent in Speech Dialogue System for People with Dementia Shota Nakatani1(B), Sachio Saiki1, Masahide Nakamura1, and Kiyoshi Yasuda2 Graduate School of System Informatics Kobe University, -1 Rokkodai, Nada, Kobe, Japan Chiba Rosai Hospital, 2-16 Tatsumidai-higashi, Ichihara, Japan" e135f8118145b6a2e2a6a2088c04c26ca6d38642,Dynamic Biometrics Fusion at Feature Level for Video-Based Human Recognition, e1f794bacd01eecb623bead652bdc9f86e17944e,Affective Environment for Java Programming Using Facial and EEG Recognition,"Affective Environment for Java Programming Using Facial and EEG Recognition María Lucía Barrón-Estrada, Ramón Zatarain-Cabada, Claudia Guadalupe Aispuro-Gallegos, Catalina de la Luz Sosa-Ochoa, Mario Lindor-Valdez Instituto Tecnológico de Culiacán, Culiacán, Sinaloa, Mexico {lbarron, rzatarain, m03171007, m07170739," e19b60e5b8083828285a2baa781ceaad27f6353c,The accuracy and value of machine-generated image tags: design and user evaluation of an end-to-end image tagging system,"The Accuracy and Value of Machine-Generated Image Tags Design and User Evaluation of an End-to-End Image Tagging System Lexing Xie, Apostol Natsev, Matthew Hill, John R. Smith IBM Watson Research Center, Hawthorne, NY, USA {xlx, natsev, mh, Alex Phillips IBM Global Business Services, United Kingdom" e1e1b3683ac278386cf1569e97f9aced0923f4a0,Hyperdrive: A Systolically Scalable Binary-Weight CNN Inference Engine for mW IoT End-Nodes,"Hyperdrive: A Systolically Scalable Binary-Weight CNN Inference Engine for mW IoT End-Nodes Renzo Andri∗, Lukas Cavigelli∗, Davide Rossi†, Luca Benini∗† Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland DEI, University of Bologna, Bologna, Italy" e18cc09c3d3d79df6cd40ea5cf13ad40eacb8a73,Visual Transfer Learning: Informal Introduction and Literature Overview,"Visual Transfer Learning: Informal Introduction nd Literature Overview Erik Rodner University of Jena, Germany August 2011" e1371af87f6d5e22ef6d8c5f9977f5e924f176f6,Bidirectional Retrieval Made Simple Jônatas Wehrmann,"Bidirectional Retrieval Made Simple Jˆonatas Wehrmann School of Technology Rodrigo C. Barros School of Technology Pontif´ıcia Universidade Cat´olica Pontif´ıcia Universidade Cat´olica do Rio Grande do Sul do Rio Grande do Sul" e1e1ae77cf37855ddc3493ac240551c28cfc5f7e,Face Detection with Skin Color Segmentation & Reorganization using Genetic Algorithm,"Advance in Electronic and Electric Engineering. ISSN 2231-1297, Volume 3, Number 9 (2013), pp. 1197-1208 © Research India Publications http://www.ripublication.com/aeee.htm Face Detection with Skin Color Segmentation& Reorganization using Genetic Algorithm Mr.Tushar Gajame and 2Prof. C.L. Chandrakar M.E. Scholar, Electronics Dept, S.S.G.I, BHILAI (C.G.), INDIA. Associate, Prof. (E & I), S.S.G.I, BHILAI (C.G.), INDIA." b9fb66f09b358a4ce167b54eed8c596772a392d9,Modal Regression based Atomic Representation for Robust Face Recognition,"Modal Regression based Atomic Representation for Robust Face Recognition Yulong Wang, Yuan Yan Tang, Life Fellow, IEEE, Luoqing Li, and Hong Chen" b98aec5bbe7116fa3ae5f9b4d77cb1f1141eaabd,Appearance-Based 3D Upper-Body Pose Estimation and Person Re-identification on Mobile Robots,"Appearance-Based 3D Upper-Body Pose Estimation nd Person Re-Identification on Mobile Robots Christoph Weinrich, Michael Volkhardt, Horst-Michael Gross Neuroinformatics and Cognitive Robotics Lab Ilmenau University of Technology Ilmenau, Germany" b95acfe00686cc6f6526fcd1f30b6f38061d3a29,Revisiting Multiple-Instance Learning Via Embedded Instance Selection,"Revisiting Multiple-Instance Learning via Embedded Instance Selection James Foulds and Eibe Frank Department of Computer Science, University of Waikato, New Zealand" b97f694c2a111b5b1724eefd63c8d64c8e19f6c9,Group Affect Prediction Using Multimodal Distributions,"Group Affect Prediction Using Multimodal Distributions Saqib Nizam Shamsi Aspiring Minds Bhanu Pratap Singh Univeristy of Massachusetts, Amherst Manya Wadhwa Johns Hopkins University" b9f2a755940353549e55690437eb7e13ea226bbf,Unsupervised Feature Learning from Videos for Discovering and Recognizing Actions,"Unsupervised Feature Learning from Videos for Discovering and Recognizing Actions Carolina Redondo-Cabrera Roberto J. López-Sastre" b941d4a85be783a6883b7d41c1afa7a9db451831,Radiofrequency ablation planning for cardiac arrhythmia treatment using modeling and machine learning approaches,"Radiofrequency ablation planning for cardiac rrhythmia treatment using modeling and machine learning approaches Roc´ıo Cabrera Lozoya To cite this version: Roc´ıo Cabrera Lozoya. Radiofrequency ablation planning for cardiac arrhythmia treatment using modeling and machine learning approaches. Other. Universit´e Nice Sophia Antipolis, 015. English. . HAL Id: tel-01206478 https://tel.archives-ouvertes.fr/tel-01206478v2 Submitted on 15 Dec 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," b9bd9cab426f4d4a0b0d0077f6d9dca2ec01ce3c,Propositionalisation of Multi-instance Data Using Random Forests,"Propositionalisation of Multi-instance Data using Random Forests Eibe Frank and Bernhard Pfahringer Department of Computer Science, University of Waikato" b971266b29fcecf1d5efe1c4dcdc2355cb188ab0,On the Reconstruction of Face Images from Deep Face Templates.,"MAI et al.: ON THE RECONSTRUCTION OF FACE IMAGES FROM DEEP FACE TEMPLATES On the Reconstruction of Face Images from Deep Face Templates Guangcan Mai, Kai Cao, Pong C. Yuen∗, Senior Member, IEEE, and Anil K. Jain, Life Fellow, IEEE" b9a0aff228a697b87d89f5dfdfacc0dc9ac28fdb,A Deep Spatial Contextual Long-Term Recurrent Convolutional Network for Saliency Detection,"A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection Nian Liu and Junwei Han, Senior Member, IEEE" b92a057606a47eb7de6ecc180e4dbf53c4a8d4b7,Face Recognition Based on 2D and 3D Features,"Face Recognition Based on 2D and 3D Features Stefano Arca, Ra(cid:11)aella Lanzarotti, and Giuseppe Lipori Dipartimento di Scienze dell’Informazione Universit(cid:18)a degli Studi di Milano Via Comelico, 39/41 20135 Milano, Italy farca, lanzarotti," b9128ff3b0b96815ff41a7d5fb2b4bef69f635ca,Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation,"Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation Hyo-Eun Kim and Sangheum Hwang Lunit Inc., Seoul, South Korea {hekim," b9e82ee9bb4cf016b5ed44b7acd2b42e1a5a6be2,Face recognition by applying wavelet subband representation and kernel associative memory,"Face Recognition by Applying Wavelet Subband Representation and Kernel Associative Memory Bai-Ling Zhang, Haihong Zhang, and Shuzhi Sam Ge, Senior Member, IEEE" b9f8c8db31ab3882f513246b8d39386cea8cf764,Near Real-Time Object Recognition for Pepper based on Deep Neural Networks Running on a Backpack,"Near Real-Time Object Recognition for Pepper ased on Deep Neural Networks Running on a Backpack Esteban Reyes1, Cristopher G´omez1, Esteban Norambuena1 and Javier Ruiz-del-Solar1,2 Department of Electrical Engineering, Universidad de Chile Advanced Mining Technology Center, Universidad de Chile" b92175bf063bd73cabe8b222268c153e4466a82a,Background Subtraction with Dirichlet Process Mixture Models,"Background Subtraction with Dirichlet Process Mixture Models Tom S. F. Haines and Tao Xiang" b955969e1077ca328018c9e4dcf27b87ed9f5076,Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning,"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning Jiasen Lu2∗†, Caiming Xiong1†, Devi Parikh3, Richard Socher1 Salesforce Research, 2Virginia Tech, 3Georgia Institute of Technology {cxiong," b9cad920a00fc0e997fc24396872e03f13c0bb9c,Face liveness detection under bad illumination conditions,"FACE LIVENESS DETECTION UNDER BAD ILLUMINATION CONDITIONS Bruno Peixoto, Carolina Michelassi, and Anderson Rocha University of Campinas (Unicamp) Campinas, SP, Brazil" b9953824b3d4cd2be77ecbc5db3f7dec3dfa031e,Guided Attention for Large Scale Scene Text Verification,"Large Scale Scene Text Verification with Guided Attention Dafang He1(cid:63), Yeqing Li2∗, Alexander Gorban2, Derrall Heath2, Julian Ibarz2, Qian Yu2, Daniel Kifer1, C. Lee Giles1 The Pennsylvania State University1, Google Inc2." b9696bdba6e16959258bad17ce26e6a643be5faf,Using Photometric Stereo for Face Recognition,"International Journal of Bio-Science and Bio-Technology Vol. 3, No. 3, September, 2011 Using Photometric Stereo for Face Recognition Gary A. Atkinson and Melvyn L. Smith University of the West of England, Bristol, BS16 1QY, UK" b9cedd1960d5c025be55ade0a0aa81b75a6efa61,Inexact Krylov Subspace Algorithms for Large Matrix Exponential Eigenproblem from Dimensionality Reduction,"INEXACT KRYLOV SUBSPACE ALGORITHMS FOR LARGE MATRIX EXPONENTIAL EIGENPROBLEM FROM DIMENSIONALITY REDUCTION GANG WU∗, TING-TING FENG† , LI-JIA ZHANG‡ , AND MENG YANG§" b94e57ee9278f06c65a96ce1b586cb7a5b2b7fbb,Group Re-identification via Unsupervised Transfer of Sparse Features Encoding,"Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding Giuseppe Lisanti∗,1, Niki Martinel∗,2, Alberto Del Bimbo1 and Gian Luca Foresti2 MICC - University of Firenze, Italy AViReS Lab - University of Udine, Italy" b9d0774b0321a5cfc75471b62c8c5ef6c15527f5,Fishy Faces: Crafting Adversarial Images to Poison Face Authentication,"Fishy Faces: Crafting Adversarial Images to Poison Face Authentication Giuseppe Garofalo Vera Rimmer Tim Van hamme imec-DistriNet, KU Leuven imec-DistriNet, KU Leuven imec-DistriNet, KU Leuven Davy Preuveneers Wouter Joosen imec-DistriNet, KU Leuven imec-DistriNet, KU Leuven" b908edadad58c604a1e4b431f69ac8ded350589a,Deep Face Feature for Face Alignment,"Deep Face Feature for Face Alignment Boyi Jiang, Juyong Zhang, Bailin Deng, Yudong Guo and Ligang Liu" 40377a1bc15a9ec28ea54cc53d5cf0699365634f,Строительство автомобильных дорог на основе 3D-моделей,"НЕКООПЕРАТИВНАЯ БИОМЕТРИЧЕСКАЯ ИДЕНТИФИКАЦИЯ ПО 3D- МОДЕЛЯМ ЛИЦА С ИСПОЛЬЗОВАНИЕМ ВИДЕОКАМЕР ВЫСОКОГО РАЗРЕШЕНИЯ А.И. Манолов, А.Ю. Соколов, О.В. Степаненко, А.C. Тумачек, А.В.Тяхт, А. К. Цискаридзе, Д.Н. Заварикин, А.А. Кадейшвили, Компания Vocord Аннотация Получены результаты по распознаванию лиц, основанные на 3D реконструкции без использования какой-либо структурированной подсветки. 3D реконструкция основана на использовании камер высокого разрешения. Вероятность распознавания составляет 92-98%. Ключевые слова: 3D реконструкция, 3D распознавание . ВВЕДЕНИЕ Системам распознавания лиц, основанным на двумерных изображениях, присущи определенные недостатки. Такие системы чувствительны к изменениям яркости. Свет, собранный с лица, является функцией геометрии лица, отражательной способности лица, свойствами источника света и свойствами камеры. С учетом этого, сложно создать" 4071778aef122d2ba9f2525a56e375e072a4b186,Questioning the assumptions behind fairness solutions,"Questioning the assumptions behind fairness solutions∗ Rebekah Overdorf Bogdan Kulynych EPFL SPRING Lab Ero Balsa imec-COSIC KU Leuven Carmela Troncoso EPFL SPRING Lab Seda G¨urses imec-COSIC KU Leuven" 40d4fab85e2e1557e61d03b92429d64c6efba101,Detection-based multi-human tracking using a CRF model,"Detection-Based Multi-Human Tracking Using a CRF Model Alexandre Heili1,2 Jean-Marc Odobez1,2 Idiap Research Institute – CH-1920 Martigny, Switzerland Cheng Chen1 ´Ecole Polytechnique F´ed´erale de Lausanne – CH-1015, Lausanne, Switzerland" 40b86ce698be51e36884edcc8937998979cd02ec,Finding Faces in News Photos Using Both Face and Name Information,"Yüz ve İsim İlişkisi kullanarak Haberlerdeki Kişilerin Bulunması Finding Faces in News Photos Using Both Face and Name Information Derya Ozkan, Pınar Duygulu Bilgisayar Mühendisliği Bölümü, Bilkent Üniversitesi, 06800, Ankara Özetçe Bu çalışmada, haber fotoğraflarından oluşan geniş veri kümelerinde kişilerin sorgulanmasını sağlayan bir yöntem sunulmuştur. Yöntem isim ve yüzlerin ilişkilendirilmesine dayanmaktadır. Haber başlığında kişinin ismi geçiyor ise fotoğrafta da o kişinin yüzünün bulunacağı varsayımıyla, ilk olarak sorgulanan isim ile ilişkilendirilmiş, fotoğraflardaki tüm yüzler seçilir. Bu yüzler arasında sorgu kişisine ait farklı koşul, poz ve zamanlarda çekilmiş pek çok resmin yanında, haberde ismi geçen başka kişilere ait yüzler ya da kullanılan yüz bulma yönteminin hatasından kaynaklanan yüz olmayan resimler de bulunabilir. Yine de, çoğu zaman, sorgu kişisine it resimler daha çok olup, bu resimler birbirine diğerlerine olduğundan daha çok benzeyeceklerdir. Bu nedenle, yüzler rasındaki benzerlikler çizgesel olarak betimlendiğinde , irbirine en çok benzeyen yüzler bu çizgede en yoğun bileşen" 4003b21fb29585ae55db154a5b3fa9945b1af88e,AN IMPROVED DOUBLE CODING LOCAL BINARY PATTERN ALGORITHM FOR FACE RECOGNITION,"IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308 AN IMPROVED DOUBLE CODING LOCAL BINARY PATTERN ALGORITHM FOR FACE RECOGNITION Saurabh Asija1, Rakesh Singh2 Research Scholar (Computer Engineering Department), Punjabi University, Patiala. Asst. Professor (Computer Engineering Department), Punjabi University, Patiala." 400aa5cb2fec558f7827c3638993bae34752ff31,Assessing post-detection filters for a generic pedestrian detector in a tracking-by-detection scheme,"(cid:13)2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Assessing Post-Detection Filters for a Generic Pedestrian Detector in a Tracking-By-Detection Scheme Volker Eiselein, Erik Bochinski and Thomas Sikora Communication Systems Group, Technische Universit¨at Berlin" 40be718f23c163f12f88384a9ceb703578f89af4,Itinerary Recommendation for Cruises: User Study,"Itinerary Recommendation for Cruises: User Study Diana Nurbakova, L´ea Laporte, Sylvie Calabretto, J´erˆome Gensel To cite this version: Diana Nurbakova, L´ea Laporte, Sylvie Calabretto, J´erˆome Gensel. Itinerary Recommenda- tion for Cruises: User Study. Julia Neidhardt; Daniel Fesenmaier; Tsvi Kuflik; Wolfgang W¨orndl. RecTour 2017: 2nd Workshop on Recommenders in Tourism, Aug 2017, Como, Italy. Proceedings of the 2nd Workshop on Recommenders in Tourism co-located with 11th ACM Conference on Recommender Systems (RecSys 2017). Como, Italy, August 27, 2017. Vol-1906 (urn:nbn:de:0074-1906-6), pp.31-34, 2017, CEUR Workshop Proceedings. . HAL Id: hal-01577228 https://hal.archives-ouvertes.fr/hal-01577228 Submitted on 25 Aug 2017 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est" 40a63746a710baf4a694fd5a4dd8b5a3d9fc2846,Invertible Conditional GANs for image editing,"Invertible Conditional GANs for image editing Guim Perarnau, Joost van de Weijer, Bogdan Raducanu Computer Vision Center Barcelona, Spain Jose M. Álvarez Data61 CSIRO Canberra, Australia" 40248cd4a742cb33c14e835fe6b847ad3f8d5b96,Learning View-Specific Deep Networks for Person Re-Identification,"Learning View-Specific Deep Networks for Person Re-Identification Zhanxiang Feng, Jianhuang Lai, and Xiaohua Xie" 4026dc62475d2ff2876557fc2b0445be898cd380,An affective user interface based on facial expression recognition and eye-gaze tracking,"An Affective User Interface Based on Facial Expression Recognition and Eye-Gaze Tracking Soo-Mi Choi and Yong-Guk Kim School of Computer Engineering, Sejong University, Seoul, Korea" 40010e1918e1f342b14c8ec74e570101f07471b2,Flower Categorization using Deep Convolutional Neural Networks,"Flower Categorization using Deep Convolutional Neural Networks Ayesha Gurnani Viraj Mavani Vandit Gajjar Yash Khandhediya L. D. College of Engineering L. D. College of Engineering L. D. College of Engineering L. D. College of Engineering" 40fb4e8932fb6a8fef0dddfdda57a3e142c3e823,A mixed generative-discriminative framework for pedestrian classification,"A Mixed Generative-Discriminative Framework for Pedestrian Classification Markus Enzweiler1 Dariu M. Gavrila2,3 Image & Pattern Analysis Group, Dept. of Math. and Comp. Sc., Univ. of Heidelberg, Germany Environment Perception, Group Research, Daimler AG, Ulm, Germany Intelligent Systems Lab, Faculty of Science, Univ. of Amsterdam, The Netherlands" 40389b941a6901c190fb74e95dc170166fd7639d,Automatic Facial Expression Recognition,"Automatic Facial Expression Recognition Jacob Whitehill, Marian Stewart Bartlett, and Javier R. Movellan Emotient http://emotient.com February 12, 2014 Imago animi vultus est, indices oculi. (Cicero) Introduction The face is innervated by two different brain systems that compete for control of its muscles: cortical brain system related to voluntary and controllable behavior, and a sub-cortical system responsible for involuntary expressions. The interplay between these two systems generates a wealth of information that humans constantly use to read the emotions, inten- tions, and interests [25] of others. Given the critical role that facial expressions play in our daily life, technologies that can interpret and respond to facial expressions automatically are likely to find a wide range of pplications. For example, in pharmacology, the effect of new anti-depression drugs could e assessed more accurately based on daily records of the patients’ facial expressions than sking the patients to fill out a questionnaire, as it is currently done [7]. Facial expression recognition may enable a new generation of teaching systems to adapt to the expression of their students in the way good teachers do [61]. Expression recognition could be used to assess the fatigue of drivers and air-pilots [58, 59]. Daily-life robots with automatic" 403e7fed4fa1785af8309b1c4c736d98fa75be5b,Supplemental Data : Social status gates social attention in monkeys,"Magazine Social status gates social ttention in monkeys Stephen V. Shepherd1, Robert O. Deaner1 and Michael L. Platt1,2,3 Humans rapidly shift attention in the direction other individuals are looking, following gaze in a manner suggestive of an obligatory social reflex [1–4]. Monkeys’ attention also follows gaze, and the similar magnitude nd time-course of gaze- following in rhesus macaques and humans [5] is indicative of shared neural mechanisms. Here we show that low-status male rhesus" 40f6c9355dbf01a240b4c26b0fd00b5cfbd5f67d,An eye-tracking method to reveal the link between gazing patterns and pragmatic abilities in high functioning autism spectrum disorders,"ORIGINAL RESEARCH ARTICLE published: 14 January 2015 doi: 10.3389/fnhum.2014.01067 An eye-tracking method to reveal the link between gazing patterns and pragmatic abilities in high functioning autism spectrum disorders Ouriel Grynszpan 1* and Jacqueline Nadel 2 Institut des Systèmes Intelligents et de Robotique (ISIR), Université Pierre et Marie Curie, Centre National de la Recherche Scientifique, Paris, France Centre Emotion, Hôpital de La Salpêtrière, Paris, France Edited by: John J. Foxe, Albert Einstein College of Medicine, USA Reviewed by: Hans-Peter Frey, Albert Einstein College of Medicine, USA Julia Irwin, Haskins Laboratories, Karri Gillespie-Smith, University of West of Scotland, UK *Correspondence: Ouriel Grynszpan, Institut des" 404c7839afe2fec48a06f83d2a532c05ad8ba0d3,Vehicle Classification using Transferable Deep Neural Network Features,"Vehicle Classification using Transferable Deep Neural Network Features Yiren Zhou, Ngai-Man Cheung" 405b43f4a52f70336ac1db36d5fa654600e9e643,What can we learn about CNNs from a large scale controlled object dataset?,"What can we learn about CNNs from a large scale controlled object dataset? Ali Borji Saeed Izadi Laurent Itti" 406caefc7f51e8a16833402e4757704d5d84a1f8,Dual-Tree Complex Wavelets Transform Based Facial Expression Recognition using Principal Component Analysis ( PCA ) and Local Binary Pattern ( LBP ),"ISSN XXXX XXXX © 2017 IJESC Research Article Volume 7 Issue No.4 Dual-Tree Complex Wavelets Transform Based Facial Expression Recognition using Principal Component Analysis (PCA) and Local Binary Pattern(LBP) Fahad Abdu Jibrin1, Abubakar Sadiq Muhammad2 Department of Electrical Engineering1, Department of Computer Engineering2 School of Technology, Kano State Polytechnic, Nigeria" 40b87d3b1e3dbbc82fb7d786004fe202e131c045,Multi-modal Egocentric Activity Recognition using Audio-Visual Features,"Submitted to IEEE Transactions on Human-Machine Systems Multi-modal Egocentric Activity Recognition using Audio-Visual Features Mehmet Ali Arabacı, Fatih Özkan, Elif Surer, Peter Jančovič, Alptekin Temizel" 403b3d0594989629c95e5bc5230d4ccb1691f255,Automatic detection of pain from spontaneous facial expressions,"Meawad, F., Yang, S.-Y. and Loy, F. L. (2017) Automatic Detection of Pain from Spontaneous Facial Expressions. In: 19th ACM International Conference on Multimodal Interaction (ICMI 2017), Glasgow, Scotland, 3-17 Nov 2017, pp. 397-401. ISBN 9781450355438 (doi:10.1145/3136755.3136794) This is the author’s final accepted version. There may be differences between this version and the published version. You are advised to consult the publisher’s version if you wish to cite from http://eprints.gla.ac.uk/151491/ Deposited on: 22 December 2017 Enlighten – Research publications by members of the University of Glasgow http://eprints.gla.ac.uk" 401f056e1017151018e83d2b13b5eaec573b4dbc,Rapid and accurate face depth estimation in passive stereo systems,"Noname manuscript No. (will be inserted by the editor) Rapid and accurate face depth estimation in passive stereo systems Amel AISSAOUI · Jean MARTINET · Chaabane DJERABA Received: date / Accepted: date" 4053e3423fb70ad9140ca89351df49675197196a,Robust Face Detection Using the Hausdorff Distance,"(cid:13) In Proc. Third International Conference on Audio- and Video-based Biometric Person Authentication, Springer, Lecture Notes in Computer Science, LNCS-2091, pp. 90–95, Halmstad, Sweden, 6–8 June 2001. Robust Face Detection Using the Hausdorff Distance Oliver Jesorsky, Klaus J. Kirchberg, and Robert W. Frischholz BioID AG, Berlin, Germany WWW home page: http://www.bioid.com" 40205181ed1406a6f101c5e38c5b4b9b583d06bc,Using Context to Recognize People in Consumer Images,"Using Context to Recognize People in Consumer Images Andrew C. Gallagher and Tsuhan Chen" 40a34d4eea5e32dfbcef420ffe2ce7c1ee0f23cd,Bridging Heterogeneous Domains With Parallel Transport For Vision and Multimedia Applications,"Bridging Heterogeneous Domains With Parallel Transport For Vision and Multimedia Applications Raghuraman Gopalan Dept. of Video and Multimedia Technologies Research AT&T Labs-Research San Francisco, CA 94108" 40f2b3af6b55efae7992996bd0c474a9c1574008,Oxytocin Increases Retention of Social Cognition in Autism,"ARTICLE IN PRESS Oxytocin Increases Retention of Social Cognition in Autism Eric Hollander, Jennifer Bartz, William Chaplin, Ann Phillips, Jennifer Sumner, Latha Soorya, Evdokia Anagnostou, and Stacey Wasserman Background: Oxytocin dysfunction might contribute to the development of social deficits in autism, a core symptom domain and potential target for intervention. This study explored the effect of intravenous oxytocin administration on the retention of social information in autism. Methods: Oxytocin and placebo challenges were administered to 15 adult subjects diagnosed with autism or Asperger’s disorder, and omprehension of affective speech (happy, indifferent, angry, and sad) in neutral content sentences was tested. Results: All subjects showed improvements in affective speech comprehension from pre- to post-infusion; however, whereas those who received placebo first tended to revert to baseline after a delay, those who received oxytocin first retained the ability to accurately assign emotional significance to speech intonation on the speech comprehension task. Conclusions: These results are consistent with studies linking oxytocin to social recognition in rodents as well as studies linking oxytocin to prosocial behavior in humans and suggest that oxytocin might facilitate social information processing in those with autism. These findings also provide preliminary support for the use of oxytocin in the treatment of autism. Key Words: Autism, oxytocin, neuropeptide, social cognition, ffective speech A utism is a developmental disorder characterized by ab- normalities in speech and communication, impaired so-" 40b0fced8bc45f548ca7f79922e62478d2043220,Do Convnets Learn Correspondence?,"Do Convnets Learn Correspondence? Trevor Darrell Jonathan Long {jonlong, nzhang, University of California – Berkeley Ning Zhang" 40f7ea135907d2f4abeae0475d9a88477239d504,Multimodal Explanations: Justifying Decisions and Pointing to the Evidence,"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence Dong Huk Park1, Lisa Anne Hendricks1, Zeynep Akata2,3, Anna Rohrbach1,3, Bernt Schiele3, Trevor Darrell1, and Marcus Rohrbach4 EECS, UC Berkeley, 2University of Amsterdam, 3MPI for Informatics, 4Facebook AI Research" 401e6b9ada571603b67377b336786801f5b54eee,Active image clustering: Seeking constraints from humans to complement algorithms,"Active Image Clustering: Seeking Constraints from Humans to Complement Algorithms November 22, 2011" 40000b058cf80b7983a2c0f96562368a40a04580,Predicting human mobility through the assimilation of social media traces into mobility models,"Predicting human mobility through the assimilation of social media traces into mobility models Mariano G. Beir´o1 Andr´e Panisson1 Michele Tizzoni1 Ciro Cattuto1 ISI Foundation, Turin, Italy" 409220cf5137d6dc6c85f440d618e44d244f402e,Randomized Algorithms for Large-scale Strongly Over-determined Linear Regression Problems a Dissertation Submitted to the Institute for Computational and Mathematical Engineering and the Committee on Graduate Studies of Stanford University in Partial Fulfillment of the Requirements for the Degree Of,"RANDOMIZED ALGORITHMS FOR LARGE-SCALE STRONGLY OVER-DETERMINED LINEAR REGRESSION PROBLEMS A DISSERTATION SUBMITTED TO THE INSTITUTE FOR COMPUTATIONAL AND MATHEMATICAL ENGINEERING AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Xiangrui Meng June 2014" 409ff083816d8357fe839e3ea0e62d648a5532aa,Proceedings of the 20 th Workshop on the Semantics and Pragmatics of Dialogue,"SEMDIAL 2016 JerSem Proceedings of the 20th Workshop on the Semantics and Pragmatics of Dialogue Julie Hunter, Mandy Simons, and Matthew Stone (eds.) New Brunswick, NJ, 16–18 July 2016" 40b10e330a5511a6a45f42c8b86da222504c717f,Implementing the Viola-Jones Face Detection Algorithm,"Implementing the Viola-Jones Face Detection Algorithm Ole Helvig Jensen Kongens Lyngby 2008 IMM-M.Sc.-2008-93" 40041b80cef6dc23946ffa9628b6ac3b8dcc971a,Parallel Separable 3D Convolution for Video and Volumetric Data Understanding,"GONDA, WEI, PARAG, PFISTER: PARALLEL SEPARABLE 3D CONVOLUTION Parallel Separable 3D Convolution for Video nd Volumetric Data Understanding Harvard John A. Paulson School of Engineering and Applied Sciences Camabridge MA, USA Felix Gonda Donglai Wei Toufiq Parag Hanspeter Pfister" 40932ccdd7cda22e90c1e16b4a4dc4930b122a9c,Learning to Look around Objects for Top-View Representations of Outdoor Scenes,"Learning to Look around Objects for Top-View Representations of Outdoor Scenes Samuel Schulter1,† Menghua Zhai2,† Nathan Jacobs2 Manmohan Chandraker1,3 NEC-Labs1, Computer Science University of Kentucky2, UC San Diego3" 40c6a2b1cb312f11f8225a733545fdabd436e347,Deep Co-Training for Semi-Supervised Image Recognition,"Deep Co-Training for Semi-Supervised Image Recognition Siyuan Qiao1 Wei Shen1,2 Zhishuai Zhang1 Bo Wang3 Alan Yuille1 Johns Hopkins University 2Shanghai University 3Hikvision Research Institute" 40dd2b9aace337467c6e1e269d0cb813442313d7,Localizing spatially and temporally objects and actions in videos. (Localiser spatio-temporallement des objets et des actions dans des vidéos),"This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e.g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use: This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author. The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author. When referring to this work, full bibliographic details including the author, title, warding institution and date of the thesis must be given." 40dab43abef32deaf875c2652133ea1e2c089223,Facial Communicative Signals: valence recognition in task-oriented human-robot Interaction,"Noname manuscript No. (will be inserted by the editor) Facial Communicative Signals Valence Recognition in Task-Oriented Human-Robot Interaction Christian Lang · Sven Wachsmuth · Marc Hanheide · Heiko Wersing Received: date / Accepted: date" 40c72f5699f87db0f4f5505e6fcf79254dfd13bd,Exploiting Multiple Cameras for Environmental Pathlets,"Exploiting Multiple Cameras for Environmental Pathlets(cid:63) Kevin Streib and James W. Davis Dept. of Computer Science and Engineering Ohio State University, Columbus, OH, 43210" 40229a034d2fcddc3df32f906ec4ef6a3b3e017e,A semi-automated system for accurate gaze coding in natural dyadic interactions,"A Semi-Automated System for Accurate Gaze Coding in Natural Dyadic Interactions Kenneth A. Funes-Mora, Laurent Nguyen, Daniel Gatica-Perez, Jean-Marc Odobez Idiap Research Institute and École Polytechnique Fédérale de Lausanne (EPFL), Switzerland" 40ce2567ccc2552287f8a1c25e9f6086efa6bf8f,Identification and evaluation of children with autism spectrum disorders.,"CLINICAL REPORT Identification and Evaluation of Children With Autism Spectrum Disorders Chris Plauche´ Johnson, MD, MEd, Scott M. Myers, MD, and the Council on Children With Disabilities Guidance for the Clinician in Rendering Pediatric Care" 40012a8e480a1724cce1a71e2b8584332225492b,Greedy algorithm for subspace clustering from corrupted and incomplete data,"Fast Greedy Algorithm for Subspace Clustering from Corrupted and Incomplete Data Alexander Petukhov, Inna Kozlov" 402f6db00251a15d1d92507887b17e1c50feebca,3D Facial Action Units Recognition for Emotional Expression,"D Facial Action Units Recognition for Emotional Expression Norhaida Hussain1, Hamimah Ujir, Irwandi Hipiny and Jacey-Lynn Minoi2 Department of Information Technology and Communication, Politeknik Kuching, Sarawak, Malaysia Faculty of Computer Science and Information Technology, Universiti Malaysia Sarawak, Kota Samarahan, Sarawak, Malaysia The muscular activities caused the activation of certain AUs for every facial expression at the certain duration of time throughout the facial expression. This paper presents the methods to recognise facial Action Unit (AU) using facial distance of the facial features which activates the muscles. The seven facial action units involved are AU1, AU4, AU6, AU12, AU15, AU17 and AU25 that characterises happy and sad expression. The recognition is performed on each AU according to rules defined based on the distance of each facial points. The facial distances chosen are extracted from twelve facial features. Then the facial distances are trained using Support Vector Machine (SVM) and Neural Network (NN). Classification result using SVM is presented with several different SVM kernels while result using NN is presented for each training, validation nd testing phase. Keywords: Facial action units recognition, 3D AU recognition, facial expression" 3cb8128b41b419a1fdc7a95bf8e65a37aff79676,Shifting the Baseline: Single Modality Performance on Visual Navigation&QA,"Single Modality Performance on Visual Navigation & QA Shifting the Baseline: Jesse Thomason Yonatan Bisk Paul G. Allen School of Computer Science and Engineering Daniel Gordan" 3c0420a0dd90d0900613ac1f1a1174b626df26d9,Learning Discriminative Chamfer Regularization,"YARLAGADDA ∗, EIGENSTETTER ∗, OMMER: CHAMFER REGULARIZATION Learning Discriminative Chamfer Regularization Pradeep Yarlagadda ∗ Angela Eigenstetter ∗ Björn Ommer Interdisciplinary Center for Scientific Computing (IWR) University of Heidelberg Germany" 3cfbe1f100619a932ba7e2f068cd4c41505c9f58,A Realistic Simulation Tool for Testing Face Recognition Systems under Real-World Conditions,"A Realistic Simulation Tool for Testing Face Recognition Systems under Real-World Conditions∗ M. Correa, J. Ruiz-del-Solar, S. Parra-Tsunekawa, R. Verschae Department of Electrical Engineering, Universidad de Chile Advanced Mining Technology Center, Universidad de Chile" 3caebf3075e52483c7a7179b3491882af0aaaa37,Lateralization of Cognitive Functions : The Visual Half-Field Task Revisited,"Lateralization of Cognitive Functions: The Visual Half-Field Task Revisited Ark Verma Promotor: Prof. Dr. Marc Brysbaert Proefschrift ingediend tot het behalen van de academische graad van Doctor in de Psychologie" 3c374cb8e730b64dacb9fbf6eb67f5987c7de3c8,Measuring Gaze Orientation for Human-Robot Interaction,"Measuring Gaze Orientation for Human-Robot Interaction R. Brochard∗, B. Burger∗, A. Herbulot∗†, F. Lerasle∗† CNRS; LAAS; 7 avenue du Colonel Roche, 31077 Toulouse Cedex, France Universit´e de Toulouse; UPS; LAAS-CNRS : F-31077 Toulouse, France Introduction In the context of Human-Robot interaction estimating gaze orientation brings useful information about human focus of attention. This is a contextual infor- mation : when you point something you usually look at it. Estimating gaze orientation requires head pose estimation. There are several techniques to esti- mate head pose from images, they are mainly based on training [3, 4] or on local face features tracking [6]. The approach described here is based on local face features tracking in image space using online learning, it is a mixed approach since we track face features using some learning at feature level. It uses SURF features [2] to guide detection and tracking. Such key features can be matched etween images, used for object detection or object tracking [10]. Several ap- proaches work on fixed size images like training techniques which mainly work on low resolution images because of computation costs whereas approaches based on local features tracking work on high resolution images. Tracking face features such as eyes, nose and mouth is a common problem in many applications such as" 3c8e16de72af3f96af31b26aeeb01c8bf41148fd,Face Recognition: A Comparison of Appearance-Based Approaches,"Proc. VIIth Digital Image Computing: Techniques and Applications, Sun C., Talbot H., Ourselin S. and Adriaansen T. (Eds.), 10-12 Dec. 2003, Sydney Face Recognition: A Comparison of Appearance-Based Approaches Thomas Heseltine1, Nick Pears, Jim Austin, Zezhi Chen Advanced Computer Architectures Group, Department of Computer Science, The University of York, York, England http://www.cs.york.ac.uk/~tomh" 3c917f071bfc1244c75fca3ceed0a8c46bb975cc,Reduced acetylcholinesterase activity in the fusiform gyrus in adults with autism spectrum disorders.,"ORIGINAL ARTICLE Reduced Acetylcholinesterase Activity in the Fusiform Gyrus in Adults With Autism Spectrum Disorders Katsuaki Suzuki, MD, PhD; Genichi Sugihara, MD, PhD; Yasuomi Ouchi, MD, PhD; Kazuhiko Nakamura, MD, PhD; Masatsugu Tsujii, MA; Masami Futatsubashi, BS; Yasuhide Iwata, MD, PhD; Kenji J. Tsuchiya, MD, PhD; Kaori Matsumoto, MA; Kiyokazu Takebayashi, MD, PhD; Tomoyasu Wakuda, MD, PhD; Yujiro Yoshihara, MD, PhD; Shiro Suda, MD, PhD; Mitsuru Kikuchi, MD, PhD; Nori Takei, MD, PhD, MSc; Toshirou Sugiyama, MD, PhD; Toshiaki Irie, PhD; Norio Mori, MD, PhD Context: Both neuropsychological and functional mag- netic resonance imaging studies have shown deficien- ies in face perception in subjects with autism spectrum disorders (ASD). The fusiform gyrus has been regarded s the key structure in face perception. The cholinergic system is known to regulate the function of the visual pathway, including the fusiform gyrus. Objectives: To determine whether central acetylcho- linesterase activity, a marker for the cholinergic system, is altered in ASD and whether the alteration in acetyl- holinesterase activity, if any, is correlated with their so-" 3cb2841302af1fb9656f144abc79d4f3d0b27380,When 3 D-Aided 2 D Face Recognition Meets Deep Learning : An extended UR 2 D for Pose-Invariant Face Recognition,"See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/319928941 When 3D-Aided 2D Face Recognition Meets Deep Learning: An extended UR2D for Pose-Invariant Face Recognition Article · September 2017 CITATIONS authors: READS Xiang Xu University of Houston Pengfei Dou University of Houston 8 PUBLICATIONS 10 CITATIONS 9 PUBLICATIONS 29 CITATIONS SEE PROFILE SEE PROFILE Ha Le University of Houston 7 PUBLICATIONS 2 CITATIONS Ioannis A Kakadiaris" 3c9ad25e91cace6ac93069480745d4578b7f29f5,Automatic Article Commenting: the Task and Dataset,"Automatic Article Commenting: the Task and Dataset Lianhui Qin1∗, Lemao Liu2, Victoria Bi2, Yan Wang2, Xiaojiang Liu2, Zhiting Hu, Hai Zhao1, Shuming Shi2 Department of Computer Science and Engineering, Shanghai Jiao Tong University1, Tencent AI Lab2," 3ca4ce8ab704b44701bf7ef8dda01c8dbb226fac,On-the-fly hand detection training with application in egocentric action recognition,"On-the-Fly Hand Detection Training with Application in Egocentric Action Recognition Jayant Kumar∗, Qun Li∗, Survi Kyal, Edgar A. Bernal, and Raja Bala {Jayant.Kumar, Qun.Li, Survi.Kyal, Edgar.Bernal, PARC, A Xerox Company 800 Phillips Road, Webster, NY 14580" 3c2f1d13b284823597c2c366312a6ae6ac6c7147,Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-identification,"FeaturesSpatial  AttentionTemporal  Attention1                      2                      3                              N‘face’‘torso’‘bag’Figure1.SpatiotemporalAttention.Inchallengingvideore-identificationscenarios,apersonisrarelyfullyvisibleinallframes.However,framesinwhichonlypartofthepersonisvis-ibleoftencontainusefulinformation.Forexample,thefaceisclearlyvisibleintheframes1and2,thetorsoinframe2,andthehandbaginframes2,3andN.Insteadofaveragingfullframefeaturesacrosstime,weproposeanewspatiotemporalapproachwhichlearnstodetectasetofKdiversesalientimageregionswithineachframe(superimposedheatmaps).Anaggregaterep-resentationofeachbodypartisthenproducedbycombiningtheextractedper-frameregionsacrosstime(weightsshownaswhitetext).Ourspatiotemporalapproachcreatesacompactencodingofthevideothatexploitsusefulpartialinformationineachframebyleveragingmultiplespatialattentionmodels,andcombiningtheiroutputsusingmultipletemporalattentionmodels.personre-identification,whichisageneralizationofthestandardimage-basedre-identificationtask.InsteadofarXiv:1803.09882v1 [cs.CV] 27 Mar 2018" 3c793fa4d7f673f1e9f6799729ec266ce573ec60,Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification,"Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification Qiqi Xiao , Hao Luo , Chi Zhang" 3c4f6d24b55b1fd3c5b85c70308d544faef3f69a,A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics,"A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics Seyed Ali Ossia(cid:63), Ali Shahin Shamsabadi(cid:63), Ali Taheri(cid:63), Hamid R. Rabiee(cid:63), Nic Lane‡, Hamed Haddadi† (cid:63)Sharif University of Technology, ‡University College London, †Queen Mary University of London" 3c8da376576938160cbed956ece838682fa50e9f,Aiding face recognition with social context association rule based re-ranking,"Chapter 4 Aiding Face Recognition with Social Context Association Rule ased Re-Ranking Humans are very ef‌f‌icient at recognizing familiar face images even in challenging condi- tions. One reason for such capabilities is the ability to understand social context between individuals. Sometimes the identity of the person in a photo can be inferred based on the identity of other persons in the same photo, when some social context between them is known. This chapter presents an algorithm to utilize the co-occurrence of individuals as the social context to improve face recognition. Association rule mining is utilized to infer multi-level social context among subjects from a large repository of social transactions. The results are demonstrated on the G-album and on the SN-collection pertaining to 4675 identities prepared by the authors from a social networking website. The results show that ssociation rules extracted from social context can be used to augment face recognition and improve the identification performance. Introduction Face recognition capabilities of humans have inspired several researchers to understand the science behind it and use it in developing automated algorithms. Recently, it is also rgued that encoding social context among individuals can be leveraged for improved utomatic face recognition [175]. As shown in Figure 4.1, often times a person’s identity" 3c70360a4ba30b860d337308633842acbb908ee4,Because better detections are still possible: Multi-aspect Object Detection with Boosted Hough Forest,"REDONDO-CABRERA ET AL.: OBJECT DETECTION WITH BOOSTED HOUGH FOREST Because better detections are still possible: Multi-aspect Object Detection with Boosted Hough Forest Carolina Redondo-Cabrera Roberto López-Sastre University of Alcalá Alcalá de Henares, ES" 3c5f390f99272c59fcf822ab78c90ee6bfa7926a,iCub : Learning Emotion Expressions using Human Reward,"iCub: Learning Emotion Expressions using Human Reward Nikhil Churamani, Francisco Cruz, Sascha Griffiths and Pablo Barros" 3c1c8e171450a9b279df939d4c9209d8dbf6b2fe,Large scale mining and retrieval of visual data in a multimodal context,"Diss. ETH No. 18190 Large-Scale Mining and Retrieval of Visual Data in Multimodal Context A dissertation submitted to the SWISS FEDERAL INSTITUTE OF TECHNOLOGY ZURICH for the degree of Doctor of Technical Sciences presented by Till Quack MSc. ETH Zuerich orn 15. September 1978 itizen of Germany ccepted on the recommendation of Prof. Dr. Luc Van Gool, examiner Prof. Dr. Andrew Zisserman, co-examiner September 2008" 3ca194773fe583661b988fbdf33f7680764438b3,Exploring Nearest Neighbor Approaches for Image Captioning,"Exploring Nearest Neighbor Approaches for Image Captioning Jacob Devlin, Saurabh Gupta, Ross Girshick, Margaret Mitchell, C. Lawrence Zitnick" 3cd10f6f24c49ce677a18f0984ff4466333d8d13,Correcting rolling-shutter distortion of CMOS sensors using facial feature detection,"© 2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, reating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Pre-print of article that appeared at BTAS 2010. The published article can be accessed from: http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5634528" 3ca983d40b9de7dc12b989fce213b4abee652c9e,Will the Pedestrian Cross? A Study on Pedestrian Path Prediction,"Will the Pedestrian Cross? A Study on Pedestrian Path Prediction Christoph G. Keller and Dariu M. Gavrila" 3cd7b15f5647e650db66fbe2ce1852e00c05b2e4,"ACTIVE, an Extensible Cataloging Platform for Automatic Indexing of Audiovisual Content", 3c68763caa67dee55bca76f0f71dd4530f3fd57c,Ranking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition Applications,"Ranking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition Applications Giorgio Roffo Submitted to the Department of Computer Science in partial fulfillment of the requirements for the degree of European Doctor of Philosophy S.S.D. ING-INF05 Cycle XXIX/2014 t the Universit`a degli Studi di Verona May 2017 (cid:13) Universit`a degli Studi di Verona 2017. All rights reserved. Author . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Department of Computer Science May 25, 2017 Certified by . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Prof. Marco Cristani Associate Professor Thesis Tutor Accepted by . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ." 3cb0ef5aabc7eb4dd8d32a129cb12b3081ef264f,Absolute Head Pose Estimation From Overhead Wide-Angle Cameras,"Absolute Head Pose Estimation From Overhead Wide-Angle Cameras Ying-Li Tian, Lisa Brown, Jonathan Connell, Sharat Pankanti, Arun Hampapur, Andrew Senior, Ruud Bolle IBM T.J. Watson Research Center 9 Skyline Drive, Hawthorne, NY 10532 USA { yltian,lisabr,jconnell,sharat,arunh,aws,bolle" 3ceef6572b00bef961c0246a220edcc48553ed2d,Descriptor learning for omnidirectional image matching,"Descriptor learning for omnidirectional image matching Jonathan Masci1,2,3 Davide Migliore1,4 Michael M. Bronstein2 J¨urgen Schmidhuber1,2,3 Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), Manno, Switzerland Faculty of Informatics, Universit`a della Svizzera Italiana (USI), Lugano, Switzerland Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Lugano, Switzerland Evidence Srl, Pisa, Italy" 3c2819dae899559f1c61b3b34aeb5d41a6398440,A Stable and Invariant Three-polar Surface Representation : Application to 3 D Face Description,"A Stable and Invariant Three-polar Surface Representation: Application to 3D Face Description Majdi Jribi Faouzi Ghorbel CRISTAL Laboratory, GRIFT research group ENSI,La Manouba University 010, La manouba, Tunisia CRISTAL Laboratory, GRIFT research group ENSI,La Manouba University 010, La manouba, Tunisia" 3cbdb3c9eb3e97a9d12d84d2b62b76884cc0003d,State of the Art in Fair ML: From Moral Philosophy and Legislation to Fair Classifiers,"State of the Art in Fair ML: From Moral Philosophy and Legislation to Fair Classifiers Elias Baumann and Josef Lorenz Rumberger Humboldt University Berlin" 3cba45bd70741f38ebf375fec33a9c077288d575,Efficient and Robust Pedestrian Detection using Deep Learning for Human-Aware Navigation,"Efficient and Robust Pedestrian Detection using Deep Learning for Human-Aware Navigation Andr´e Mateus, David Ribeiro, Pedro Miraldo, and Jacinto C. Nascimento Instituto de Sistemas e Rob´otica (LARSyS), Instituto Superior T´ecnico, Lisboa, Torre Norte - 6 Piso Av.Rovisco Pais, 1 1049-001 Lisboa, Portugal. Corresponding author:" 3ce8a74b47f81ec66046f2486afa1a89e3165dfd,LSH banding for large-scale retrieval with memory and recall constraints,"978-1-4244-2354-5/09/$25.00 ©2009 IEEE ICASSP 2009" 3c3eb65a936296d6ae5058b564f6d0e0c07772cf,A metric for sets of trajectories that is practical and mathematically consistent,"A metric for sets of trajectories that is practical and mathematically consistent Jos´e Bento Jia Jie Zhu" 3cea9573c592fc42c9f4c01535c1c3f26d42af8a,White and relaxed noises in optimal velocity models for pedestrian flow with stop-and-go waves,"White and relaxed noises in optimal velocity models for pedestrian flow with stop-and-go waves Antoine Tordeux1,2,∗ and Andreas Schadschneider3 J¨ulich Supercomputing Centre, Forschungszentrum J¨ulich GmbH, Germany Computer Simulation for Fire Safety and Pedestrian Traffic, Bergische Universit¨at Wuppertal, Germany Institut f¨ur Theoretische Physik, Universit¨at zu K¨oln, Germany" 3cec488a0910b69f50811cebe8c655dca22078d5,Evidence Extraction for Machine Reading Comprehension with Deep Probabilistic Logic,"Confidential TACL submission. DO NOT DISTRIBUTE. Evidence Extraction for Machine Reading Comprehension with Deep Probabilistic Logic Anonymous TACL submission" 3c0bbfe664fb083644301c67c04a7f1331d9515f,The Role of Color and Contrast in Facial Age Estimation Paper,"The Role of Color and Contrast in Facial Age Estimation Paper ID: 7 No Institute Given" 3c94f3380206bf4f53a6d971f9195d3811fab8f5,Exploiting Test Time Evidence to Improve Predictions of Deep Neural Networks,"Exploiting Test Time Evidence to Improve Predictions of Deep Neural Networks Dinesh Khandelwal Indian Institute of Technology Delhi Suyash Agrawal Parag Singla Chetan Arora" 3ca1e06dfbaeed0f8dc49bf345369fb8e43da53d,Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification,"Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification Hong-Xing Yu, Ancong Wu, Wei-Shi Zheng Code is available at the project page: https://github.com/KovenYu/CAMEL For reference of this work, please cite: Hong-Xing Yu, Ancong Wu, Wei-Shi Zheng. “Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification.” Proceedings of the IEEE International Conference on Computer Vision. 2017. title={Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification}, uthor={Yu, Hong-Xing and Wu, Ancong and Zheng, Wei-Shi}, ooktitle={Proceedings of the IEEE International Conference on Computer Vision}, year={2017}" 3c8aa33ccff8f959df28e4e883867af32e7b4b78,The impact of task relevance and degree of distraction on stimulus processing,"Biehl et al. BMC Neuroscience 2013, 14:107 http://www.biomedcentral.com/1471-2202/14/107 R ES EAR CH A R T I C LE The impact of task relevance and degree of distraction on stimulus processing Stefanie C Biehl1,2*, Ann-Christine Ehlis3, Laura D Müller1, Andrea Niklaus1,5, Paul Pauli4 and Martin J Herrmann1 Open Access" 3c709c648f40158af31199aeb0733890ddf2bc58,A DATASET TO SUPPORT AND BENCHMARK COMPUTER VISION DEVELOPMENT FOR CLOSE RANGE ON-ORBIT SERVICING,"A DATASET TO SUPPORT AND BENCHMARK COMPUTER VISION DEVELOPMENT FOR CLOSE RANGE ON-ORBIT SERVICING Martin Lingenauber1, Simon Kriegel1, Michael Kaßecker1, and Giorgio Panin1 German Aerospace Center (DLR) - Institute of Robotics and Mechatronics - Departement of Perception and Cognition, M¨unchener Str. 20, 82234 Wessling, Germany, Email:" 3c04bf7324eaf6a77822f0fb35f85dfa79eff781,EpicFlow: Edge-preserving interpolation of correspondences for optical flow,"EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow Jerome Revauda Philippe Weinzaepfela Inria∗ Zaid Harchaouia,b NYU Cordelia Schmida" 3cc0d9c1f690addd2c82e60f2a460e3c557ff242,Sort Story: Sorting Jumbled Images and Captions into Stories,"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 925–931, Austin, Texas, November 1-5, 2016. c(cid:13)2016 Association for Computational Linguistics" 3c49dafc82ee24e70e338b896868cd9f82f0edd7,BIOLOGICALLY MOTIVATED 3 D FACE RECOGNITION by,"BIOLOGICALLY MOTIVATED 3D FACE RECOGNITION Albert Ali Salah B.S, in Computer Engineering, Bo˘gazi¸ci University, 1998 M.S, in Computer Engineering, Bo˘gazi¸ci University, 2000 Submitted to the Institute for Graduate Studies in Science and Engineering in partial fulfillment of the requirements for the degree of Doctor of Philosophy Graduate Program in Bo˘gazi¸ci University" e6e5a6090016810fb902b51d5baa2469ae28b8a1,Title Energy-Efficient Deep In-memory Architecture for NAND Flash Memories,"Title Energy-Efficient Deep In-memory Architecture for NAND Flash Memories Archived version Accepted manuscript: the content is same as the published paper but without the final typesetting by the publisher Published version Published paper Authors (contact) 0.1109/ISCAS.2018.8351458" e66c1950de149e0ccf90d3796dacce8b4886544d,Thèse A contribution to mouth structure segmentation in images aimed towards automatic mouth gesture recognition,"Th`eseAcontributiontomouthstructuresegmentationinimagesaimedtowardsautomaticmouthgesturerecognitionPr´esent´eedevantL’institutnationaldessciencesappliqu´eesdeLyonPourobtenirLegradededocteur´Ecoledoctorale´Ecoledoctoraleelectronique,electrotechnique,automatique(EEA)ParJuanBernardoG´omez-Mendoza(Ing´enieur)Souten´uele15mai2012devantlaCommissiond’examenJuryMM.P.BOLONProfesseur(PolytechAnnecy-Chamb´ery)C-A.PARRA-RODR´IGUEZProfesseur(UniversidadJaveriana)M.ORKISZProfesseur(Universit´eLyonI)J-W.BRANCH-BEDOYAProfesseur(UniversidadNacionaldeColombia)H-T.REDARCEProfesseur(INSAdeLyon)F-A.PRIETO-ORTIZProfesseur(UniversidadNacionaldeColombia)Cette thèse est accessible à l'adresse : http://theses.insa-lyon.fr/publication/2012ISAL0074/these.pdf © [J. Gómez-Mendoza], [2012], INSA de Lyon, tous droits réservés" e66304d30125a7adac3b1c9cce345c164c0317d7,Incremental Place Recognition in 3 D Point Clouds,"Research Collection Master Thesis Incremental Place Recognition in 3D Point Clouds Author(s): Gollub, Mattia Publication Date: Permanent Link: https://doi.org/10.3929/ethz-b-000202826 Rights / License: In Copyright - Non-Commercial Use Permitted This page was generated automatically upon download from the ETH Zurich Research Collection. For more information please consult the Terms of use. ETH Library" e6bbe7feb5633a361ffb6ed4c674d54574eb531e,Image quality and position variability assessment in minutiae-based fingerprint verification,"BIOMETRICS ON THE INTERNET Image quality and position variability assessment in minutiae-based fingerprint verification D. Simon-Zorita, J. Ortega-Garcia, J. Fierrez-Aguilar and J. Gonzalez-Rodriguez" e6fa9d4658610e699c71ac281762abf471983430,Simultaneous Perception and Path Generation Using Fully Convolutional Neural Networks,"Simultaneous Perception and Path Generation Using Fully Convolutional Neural Networks Luca Caltagirone∗, Mauro Bellone, Lennart Svensson, Mattias Wahde" e6178de1ef15a6a973aad2791ce5fbabc2cb8ae5,Improving Facial Landmark Detection via a Super-Resolution Inception Network,"Improving Facial Landmark Detection via a Super-Resolution Inception Network Martin Knoche, Daniel Merget, Gerhard Rigoll Institute for Human-Machine Communication Technical University of Munich, Germany" e6d50d65a87425e7f0b4ec08c53d200f12f75590,The Neural Dynamics of Facial Identity Processing: Insights from EEG-Based Pattern Analysis and Image Reconstruction,"New Research Sensory and Motor Systems The Neural Dynamics of Facial Identity Processing: Insights from EEG-Based Pattern Analysis and Image Reconstruction Dan Nemrodov,1 Matthias Niemeier,1 Ashutosh Patel,1 and Adrian Nestor1 DOI:http://dx.doi.org/10.1523/ENEURO.0358-17.2018 Department of Psychology, University of Toronto Scarborough, 1265 Military Trail, Toronto, Ontario M1C1A4, Canada" e679d7d4a43b7549c0439bf00c05dc844e9ecfc6,Image Set Classification for Low Resolution Surveillance,"Image Set Classification for Low Resolution Surveillance Uzair Nadeem, Syed Afaq Ali Shah, Mohammed Bennamoun, Roberto Togneri nd Ferdous Sohel" e6e5949464c38ecea94c3c295ea65220bc19f338,BOP: Benchmark for 6D Object Pose Estimation,"BOP: Benchmark for 6D Object Pose Estimation Tom´aˇs Hodaˇn1∗, Frank Michel2∗, Eric Brachmann3, Wadim Kehl4 Anders Glent Buch5, Dirk Kraft5, Bertram Drost6, Joel Vidal7, Stephan Ihrke2 Xenophon Zabulis8, Caner Sahin9, Fabian Manhardt10, Federico Tombari10 Tae-Kyun Kim9, Jiˇr´ı Matas1, Carsten Rother3 CTU in Prague, 2TU Dresden, 3Heidelberg University, 4Toyota Research Institute 5University of Southern Denmark, 6MVTec Software, 7Taiwan Tech 8FORTH Heraklion, 9Imperial College London, 10TU Munich" e605242319ba495bc5f47abe9f1c08d508d83627,Importance-Aware Semantic Segmentation for Autonomous Driving System,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) e63a0ea338dfc7293ddd68074baf250e99d0c6d5,Nonlinear Supervised Dimensionality Reduction via Smooth Regular Embeddings,"Nonlinear Supervised Dimensionality Reduction via Smooth Regular Embeddings Department of Electrical and Electronics Engineering, METU, Ankara Cem ¨Ornek and Elif Vural" e688a6535dbdd6ce6928bc4eb2978f39628e5302,Hand Drawn Sketch Classification Using Convolutional Neural Networks,"SUPPLEMENT ISSUE ARTICLE HAND DRAWN SKETCH CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS Habibollah Agh Atabay* Department of Computer, Gonbad Kavous University, Gonbad Kavous, IRAN" e6868f172df3736e052fec4c00b63780b3d739fe,Effects of a Common Variant in the CD38 Gene on Social Processing in an Oxytocin Challenge Study: Possible Links to Autism,"Effects of a Common Variant in the CD38 Gene on Social Processing in an Oxytocin Challenge Study: Possible Links to Autism Carina Sauer*,1, Christian Montag2, Christiane Wo¨ rner1, Peter Kirsch1,3 and Martin Reuter2,3 Department of Clinical Psychology, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany; Department of Differential and Biological Psychology, Rheinische Friedrich-Wilhelms-University, Bonn, Germany The intranasal application of oxytocin (OT) has been shown to influence behavioral and neural correlates of social processing. These effects are probably mediated by genetic variations within the OT system. One potential candidate could be the CD38 gene, which codes for a transmembrane protein engaged in OT secretion processes. A common variation in this gene (rs3796863) was recently found to e associated with autism spectrum disorders (ASD). Using an imaging genetics approach, we studied differential effects of an intranasal OT application on neural processing of social stimuli in 55 healthy young men depending on their CD38 gene variant in a double-blind placebo-controlled crossover design. Genotype had a significant influence on both behavioral and neuronal measures of social processing. Homozygotic risk allele carriers showed slower reaction times (RT) and higher activation of left fusiform gyrus during visual processing of social stimuli. Under OT activation differences between genotypes were more evident (though not statistically significantly increased) and RT were accelerated in homozygotic risk allele carriers. According to our data, rs3796863 mainly influences fusiform gyrus activation, an rea which has been widely discussed in ASD research. OT seems to modulate this effect by enhancing activation differences between llele groups, which suggests an interaction between genetic makeup and OT availability on fusiform gyrus activation. These results support recent approaches to apply OT as a pharmacological treatment of ASD symptoms. Keywords: oxytocin; CD38; social processing; imaging genetics; autism INTRODUCTION" e6b45d5a86092bbfdcd6c3c54cda3d6c3ac6b227,Pairwise Relational Networks for Face Recognition,"Pairwise Relational Networks for Face Recognition Bong-Nam Kang1[0000−0002−6818−7532], Yonghyun Kim2[0000−0003−0038−7850], nd Daijin Kim1,2[0000−0002−8046−8521] Department of Creative IT Engineering, POSTECH, Korea Department of Computer Science and Engineering, POSTECH, Korea" e68b1fdc4e515f947c96f65ec7ac2521edbc06b2,ROS Wrapper for Real-Time Multi-Person Pose Estimation with a Single Camera,"Technical Report IRI--TR-17-02 ROS Wrapper for Real-Time Multi-Person Pose Estimation with a Single Camera Autor Miguel Arduengo Sven Jens Jorgensen Supervisors Kimberly Hambuchen Luis Sentis Francesc Moreno Guillem Alenyà July 2017 Institut de Robòtica i Informàtica Industrial" e6d8218e9859ecb4a0aab781493a2cac19632a63,Dynamic Models for Entity Trajectory Prediction Using Deep Learning,"Journal of Computers Dynamic Models for Entity Trajectory Prediction Using Deep Learning Dhanya Raghu1*, Apoorva K H2, Anjana Anil Kumar3, S Natarajan4 PES Institute of Technology; Vijayanagar, Bangalore, Karnataka, India. PES Institute of Technology; Rajarajeshwarinagar, Bangalore, Karnataka, India. PES Institute of Technology; Rajajinagar, Bangalore, Karnataka, India. PES University; Banashankari, Bangalore, Karnataka, India. * Corresponding author. Tel.: +91-9731054855; email: Manuscript submitted May 15, 2018; accepted July 8, 2018." e624c73e3057a1de75e9d6d7e813771154ff1375,Incorporating Scalability in Unsupervised Spatio- Temporal Feature Learning,"INCORPORATING SCALABILITY IN UNSUPERVISED SPATIO-TEMPORAL FEATURE LEARNING Sujoy Paul, Sourya Roy and Amit K. Roy-Chowdhury Dept. of Electrical and Computer Engineering, University of California, Riverside, CA 92521" e654320739770029ec5cb22174772c935478b237,Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition,"Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition Myeongjun Jang 1 Pilsung Kang 1" e6aadde93aedc06525523415e574507cf5c8cc44,End-to-end optimization of goal-driven and visually grounded dialogue systems,"End-to-end optimization of goal-driven and visually grounded dialogue systems Florian Strub Univ. Lille, CNRS, Centrale Lille, Inria, UMR 9189 - CRIStAL, F-59000 Lille, France Harm de Vries University of Montreal Jeremie Mary Univ. Lille, CNRS, Centrale Lille, Inria, UMR 9189 - CRIStAL, F-59000 Lille, France Bilal Piot DeepMind" e63f4867c73eff9ff7cdf31246585a6915acef57,Digging Into Self-Supervised Monocular Depth Estimation,"Digging Into Self-Supervised Monocular Depth Estimation Cl´ement Godard Oisin Mac Aodha Gabriel J. Brostow" e6af98d1567dad534262ec0863264bb26157533f,ON MULTI-SCALE DIFFERENTIAL FEATURES AND THEIR REPRESENTATIONS FOR IMAGE RETRIEVAL AND RECOGNITION,"ON MULTI-SCALE DIFFERENTIAL FEATURES AND THEIR REPRESENTATIONS FOR IMAGE RETRIEVAL AND RECOGNITION A Dissertation Presented SRINIVAS S. RAVELA Submitted to the Graduate School of the University of Massachusetts Amherst in partial fulfillment of the requirements for the degree of DOCTOR OF PHILOSOPHY February 2003 Department of Computer Science" e6d8f332ae26e9983d5b42af4466ff95b55f2341,Pose-Normalized Image Generation for Person Re-identification,"Pose-Normalized Image Generation for Person Re-identification Xuelin Qian1, Yanwei Fu1, Tao Xiang2, Wenxuan Wang1 Jie Qiu3, Yang Wu3, Yu-Gang Jiang1, Xiangyang Xue1 Fudan University; 2Queen Mary University of London; Nara Institute of Science and Technology;" e6d8ebfd88ee333deccce32b09ee41d271af6dc4,Grasp2Vec: Learning Object Representations from Self-Supervised Grasping,"Grasp2Vec: Learning Object Representations from Self-Supervised Grasping Eric Jang *,1, Coline Devin *,2,†, Vincent Vanhoucke1, and Sergey Levine1,2 *Both authors contributed equally Google Brain Department of Electrical Engineering and Computer Sciences, UC Berkeley Work done while author was interning at Google Brain {ejang, vanhoucke," e6ca412a05002b51d358c2e3061913c3dab6b810,MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction, e64b683e32525643a9ddb6b6af8b0472ef5b6a37,Face Recognition and Retrieval in Video,"Face Recognition and Retrieval in Video Caifeng Shan" e6865b000cf4d4e84c3fe895b7ddfc65a9c4aaec,The critical role of the cold-start problem and incentive systems in emotional Web 2 . 0 services,"Tobias Siebenlist, Kathrin Knautz Chapter 15. The critical role of the old-start problem and incentive systems in emotional Web 2.0 services" e6d689054e87ad3b8fbbb70714d48712ad84dc1c,Robust Facial Feature Tracking,"Robust Facial Feature Tracking Fabrice Bourel, Claude C. Chibelushi, Adrian A. Low School of Computing, Staffordshire University Stafford ST18 0DG" e6808679870e52a0945603a37d810146b1e2bada,Tı́tulo : Acquisition Scenario Analysis for Face Recognition at a Distance,"UNIVERSIDAD AUT ´ONOMA DE MADRID ESCUELA POLIT´ECNICA SUPERIOR DEPARTAMENTO DE TECNOLOG´IA Y DE LAS COMUNICACIONES ACQUISITION SCENARIO ANALYSIS FOR FACE RECOGNITION AT A DISTANCE –TRABAJO FIN DE M ´ASTER– AN ´ALISIS DEL ESCENARIO DE ADQUISICI ´ON PARA RECONOCIMIENTO BIOM ´ETRICO FACIAL A DISTANCIA Author: Pedro Tom´e Gonz´alez Ingeniero de Telecomunicaci´on, Universidad Aut´onoma de Madrid A Thesis submitted for the degree of: M´aster Oficial en Ingenier´ıa Inform´atica y de Telecomunicaci´on (Master of Science) Madrid, October 2010" e6beb5d95fa262b8717cc264d79a879285db15d4,Towards Transparent AI Systems: Interpreting Visual Question Answering Models,"Towards Transparent AI Systems: Interpreting Visual Question Answering Models Yash Goyal, Akrit Mohapatra, Devi Parikh, Dhruv Batra {ygoyal, akrit, parikh, Virginia Tech" 10ce3a4724557d47df8f768670bfdd5cd5738f95,Fisher Light-Fields for Face Recognition across Pose and Illumination,"Fihe igh Fied f Face Recgii Ac e ad  iai Rah G ai ahew ad Si Bake The Rbic i e Caegie e Uiveiy 5000 Fbe Ave e ib gh A 15213 Abac.  ay face ecgii ak he e ad i iai dii f he be ad gaey iage ae di(cid:11)ee.  he cae  ie gaey  be iage ay be avaiabe each ca ed f di(cid:11)ee e ad de a di(cid:11)ee i iai. We e a face ecgii agih which ca e ay  be f gaey iage e  bjec ca ed a abiay e ad de abiay i iai d ay  be f be iage agai ca ed a abiay e ad de abiay i iai. The agih eae by eiaig he Fihe igh (cid:12)ed f he  bjec head f he i  gaey  be iage. achig bewee he be ad gaey i he efed ig he Fihe igh (cid:12)ed. d ci  ay face ecgii ceai he e f he be ad gaey iage ae di(cid:11)ee. The gaey cai he iage ed d ig aiig f he agih. The agih ae eed wih he iage i he be e. F exae he" 10a285260e822b49023c4324d0fbbca7df8e128b,Objects2action: Classifying and Localizing Actions without Any Video Example,"Objects2action: Classifying and localizing actions without any video example Mihir Jain(cid:63) Jan C. van Gemert(cid:63)‡ Thomas Mensink(cid:63) Cees G. M. Snoek(cid:63)† (cid:63)University of Amsterdam ‡Delft University of Technology Qualcomm Research Netherlands" 10773e5c1bc8a9a901a8baf4d0b891397975ea9d,Group encoding of local features in image classification,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-1-6 ©2012 IAPR" 10554bc4fb045d303abee266bc2c548dae5e187d,Identifying Synapses Using Deep and Wide Multiscale Recursive Networks.,"Identifying Synapses using Deep and Wide Multiscale Recursive Networks Gary B. Huang and Stephen Plaza Janelia Farm Research Campus Howard Hughes Medical Institute 9700 Helix Drive, Ashburn, VA, USA {huangg," 10b3afc6a10149cd88bc6f4007b41895d661d5fe,SAN: Learning Relationship Between Convolutional Features for Multi-scale Object Detection,"SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection Yonghyun Kim1[0000−0003−0038−7850], Bong-Nam Kang2[0000−0002−6818−7532], nd Daijin Kim1[0000−0002−8046−8521] Department of Computer Science and Engineering, POSTECH, Korea Department of Creative IT Engineering, POSTECH, Korea" 105fdf31d14ec55fda91c05059ec83162ba7ce3a,Automatic feature generation and selection in predictive analytics solutions,AutomaticfeaturegenerationandselectioninpredictiveanalyticssolutionsSuzannevandenBosch 10413ae7de5b234f5bdc5560a168fa2c2964a1c4,Public Document Title of Deliverable : Validation of a 'chimeric' Approach to Biometric Data Distribution Document Evolution Executive Summary,"Project N° IST-2002-507634 - BioSecure D2.1.5– Revision: b3 9 July 2007 Contract Number : Project Acronym : Project Title : Instrument : Start Date of Project : Duration : Deliverable Number : Title of Deliverable : Contractual Due Date : Actual Date of Completion : IST-2002-507634 BioSecure Biometrics for Secure Authentication Network of Excellence 01 June, 2004 6 months D2.1.5" 10f641aabdd8bc1eb87fae74c63b814d8ef274a5,Automatic Single-Image People Segmentation and Removal for Cultural Heritage Imaging,"Automatic Single-Image People Segmentation nd Removal for Cultural Heritage Imaging Marco Manfredi, Costantino Grana, and Rita Cucchiara Universit`a degli Studi di Modena e Reggio Emilia, Modena MO 41125, Italy" 10554295addeae86571a26de6c2ad7e274963953,Re-ranking Object Proposals for Object Detection in Automatic Driving,"Re-ranking Object Proposals for Object Detection in Automatic Driving Zhun Zhong1, Mingyi Lei1, Shaozi Li1, Jianping Fan2" 104dd4963f7f0ef03fe09d505d31966666f9281d,Salient Object Subitizing,"Noname manuscript No. (will be inserted by the editor) Salient Object Subitizing Jianming Zhang · Shugao Ma · Mehrnoosh Sameki · Stan Sclaroff · Margrit Betke · Zhe Lin · Xiaohui Shen · Brian Price · Radom´ır Mˇech Received: date / Accepted: date" 10d8a48deae967b627839cc95c98b6c080ba9966,Overview of the ImageCLEF 2013 Scalable Concept Image Annotation Subtask,"Overview of the ImageCLEF 2013 Scalable Concept Image Annotation Subtask Mauricio Villegas,† Roberto Paredes† and Bart Thomee‡ ITI/DSIC, Universitat Polit`ecnica de Val`encia Cam´ı de Vera s/n, 46022 Val`encia, Spain Yahoo! Research Avinguda Diagonal 177, 08018 Barcelona, Spain" 1068f6eca07c35426ca67961f00c3cac4866f155,Bilinear Models for 3-D Face and Facial Expression Recognition,"Bilinear Models for 3D Face and Facial Expression Recognition Iordanis Mpiperis, Sotiris Malassiotis and Michael G. Strintzis, Fellow," 101c7bfc56091b627886636afcf1103c1cecccf6,Rapid Clothing Retrieval via Deep Learning of Binary Codes and Hierarchical Search,"Rapid Clothing Retrieval via Deep Learning of Binary Codes and Hierarchical Search Kevin Lin Academia Sinica, Taiwan Huei-Fang Yang Academia Sinica, Taiwan Kuan-Hsien Liu Academia Sinica, Taiwan Jen-Hao Hsiao Yahoo! Taiwan Chu-Song Chen Academia Sinica, Taiwan" 1042683cf5733244238198ff486d3a65e70c9621,End-to-End Instance Segmentation with Recurrent Attention,"End-to-End Instance Segmentation with Recurrent Attention Mengye Ren1, Richard S. Zemel1,2 University of Toronto1, Canadian Institute for Advanced Research2" 10ca3d8802ab0cc6ce000682a42fd9f6575a2006,Embedding Semantic Information into the Content of Natural Scenes Images,"http://dx.doi.org/10.5755/j01.eee.18.9.2808 ELEKTRONIKA IR ELEKTROTECHNIKA, ISSN 1392-1215, VOL. 18, NO. 9, 2012 Embedding Semantic Information into the Content of Natural Scenes Images G. Kazakeviciute-Januskeviciene1, E. Januskevicius2 Department of Graphical systems, Vilnius Gediminas Technical University, Saulėtekio av.11, Vilnius, Lithuania, phone: +370 5 2744848 Department of Building Structures, Vilnius Gediminas Technical University, Pylimo St. 26/1, Vilnius, Lithuania; phone: +370 5 2745205" 102e374347698fe5404e1d83f441630b1abf62d9,Facial Image Analysis for Fully Automatic Prediction of Difficult Endotracheal Intubation,"Facial Image Analysis for Fully-Automatic Prediction of Difficult Endotracheal Intubation Gabriel L. Cuendet, Student Member, IEEE, Patrick Schoettker, Anıl Y¨uce Student Member, IEEE, Matteo Sorci, Hua Gao, Christophe Perruchoud, Jean-Philippe Thiran, Senior Member, IEEE" 102b27922e9bd56667303f986404f0e1243b68ab,Multiscale recurrent regression networks for face alignment,"Wang et al. Appl Inform (2017) 4:13 DOI 10.1186/s40535-017-0042-5 RESEARCH Multiscale recurrent regression networks for face alignment Open Access Caixun Wang1,2,3, Haomiao Sun1,2,3, Jiwen Lu1,2,3*, Jianjiang Feng1,2,3 and Jie Zhou1,2,3 *Correspondence: State Key Lab of Intelligent Technologies and Systems, Beijing 100084, People’s Republic of China Full list of author information is available at the end of the rticle" 10384cbe0ed2c44c4d0059745d8bf1509be75941,iQIYI-VID: A Large Dataset for Multi-modal Person Identification,"iQIYI-VID: A Large Dataset for Multi-modal Person Identification Yuanliu Liu, Peipei Shi, Bo Peng, He Yan, Yong Zhou, Bing Han, Yi Zheng, Chao Lin, Jianbin Jiang,Yin Fan, Tingwei Gao, Ganwen Wang, Jian Liu, Xiangju Lu, Danming Xie iQIYI, Inc." 1099d475ee0807fc0e4aec55b636db4abc01dcb6,Perceptual Principles for Video Classification With Slow Feature Analysis,"Perceptual principles for video classification with Slow Feature Analysis Christian Th´eriault(1), Nicolas Thome(1), Matthieu Cord(1), Patrick P´erez(2) (1)UPMC-Sorbonne Universities, Paris, France (2)Technicolor, France" 10be82098017fc2d60b0572cea8032afabad5d1a,A Dataset for Multimodal Question Answering in the Cultural Heritage Domain,"Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities (LT4DH), pages 10–17, Osaka, Japan, December 11-17 2016." 10d710c01acb10c4aea702926d21697935656c3d,Infrared Colorization Using Deep Convolutional Neural Networks,"Infrared Colorization Using Deep Convolutional Neural Networks Matthias Limmer∗, Hendrik P.A. Lensch† Daimler AG, Ulm, Germany Department of Computer Graphics, Eberhard Karls Universität, Tübingen, Germany" 100641ed8a5472536dde53c1f50fa2dd2d4e9be9,Visual attributes for enhanced human-machine communication,"Visual Attributes for Enhanced Human-Machine Communication* Devi Parikh1" 10114df7ddbb221337cc1e99e1de0eab8e47c95d,Evaluating Feature Importance for Re-identification,"Chapter 9 Evaluating Feature Importance for Re-Identification Chunxiao Liu, Shaogang Gong, Chen Change Loy, and Xinggang Lin" 109df0e8e5969ddf01e073143e83599228a1163f,Scheduling heterogeneous multi-cores through performance impact estimation (PIE),"Scheduling Heterogeneous Multi-Cores through Performance Impact Estimation (PIE) Kenzo Van Craeynest•∗ Aamer Jaleel† Lieven Eeckhout• Paolo Narvaez† Joel Emer†‡ Ghent University• Ghent, Belgium {kenzo.vancraeynest, Intel Corporation, VSSAD† {aamer.jaleel,paolo.narvaez, Hudson, MA Cambridge, MA" 1060e223710a9472ffa5bb68bbb4d629014f7dbf,Title of thesis: REAL-TIME POSE BASED HUMAN DETECTION AND RE-IDENTIFICATION WITH A SINGLE CAMERA FOR ROBOT PERSON FOLLOWING, 10678172baa93d8318dd1945d09f38721a0c1ffa,A Comparison of Adaptive Appearance Methods for Tracking Faces in Video Surveillance,"A Comparison of Adaptive Appearance Methods for Tracking Faces in Video Surveillance M. Ali Akber Dewan*, E. Granger*, F. Roli†, R. Sabourin*, and G. L. Marcialis† *Laboratoire d’imagerie, de vision et d’intelligence artificielle, École de technologie supérieure, Université du Québec, Montréal, Canada Department of Electrical and Electronic Engineering, University of Cagliari, Piazza d'Armi, Cagliari, Italy Keywords: Biometrics, Face Tracking, Spatiotemporal Face Recognition, Video Surveillance, On-Line and Incremental Learning, Adaptive Appearance Methods." 103590b36d026928a90eae7ade9d7da318202168,Indoor Scene Recognition Using Local Semantic Concepts,"Indoor Scene Recognition Using Local Semantic Concepts Elham Seifossadat1, Niloofar Gheissari2 and Ali Fanian3 Electrical and Computer Department,Isfahan University of Technology Isfahan, Iran Electrical and Computer Department,Isfahan University of Technology Isfahan, Iran 3 Electrical and Computer Department,Isfahan University of Technology Isfahan, Iran" 1048c753e9488daa2441c50577fe5fdba5aa5d7c,Recognising faces in unseen modes: A tensor based approach,"Recognising faces in unseen modes: a tensor based approach Santu Rana, Wanquan Liu, Mihai Lazarescu and Svetha Venkatesh {santu.rana, wanquan, m.lazarescu, Dept. of Computing, Curtin University of Technology GPO Box U1987, Perth, WA 6845, Australia." 10177800e4d1dfc0c88460b52e746b336bd393db,Discovering objects and their location in images with Latent Dirichlet Allocation,"Discovering objects and their location in images with Latent Dirichlet Allocation Bryan C. Russell∗ Research Supervisor: William T. Freeman" 1059729bcca57731c81d8a9c866ceb8ed3547d8d,Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles,"Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles Bastian Leibe, Konrad Schindler, Nico Cornelis, and Luc Van Gool" 106150b707a31f0825bdae44eca4139b715547d6,Robust Semantic Segmentation with Ladder-DenseNet Models,"Robust Semantic Segmentation with Ladder-DenseNet Models Ivan Kreˇso Marin Orˇsi´c Petra Bevandi´c Siniˇsa ˇSegvi´c Faculty of Electrical Engineering and Computing University of Zagreb, Croatia" 10fb32ef34f815e9056ba71bc4b67a9951b4475b,End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features,"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features Chiori Hori†, Huda Alamri∗†, Jue Wang†, Gordon Wichern†, Vincent Cartillier∗, Raphael Gontijo Lopes∗, Abhishek Das∗, Takaaki Hori†, Anoop Cherian†, Tim K. Marks†, Irfan Essa∗, Dhruv Batra∗ Devi Parikh∗, Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA School of Interactive Computing, Georgia Tech" 10c4b2489d7e1ee43a1d19724d3c1e9c33ca3f29,A Question-Answering framework for plots using Deep learning,"A Question-Answering framework for plots using Deep learning Revanth Reddy1, Rahul Ramesh1, Ameet Deshpande1 and Mitesh M. Khapra1 Indian Institute of Technology Madras" 10916d4eeacbf63a178c229868160189c6ce8850,Extraction of Illumination Invariant Features using Fuzzy Threshold based Approach,"International Conference on Intelligent Systems and Data Processing (ICISD) 2011 Special Issue published by International Journal of Computer Applications® (IJCA) Extraction of Illumination Invariant Features using Fuzzy Threshold based Approach R. M. Makwana V. K. Thakar N.C. Chauhan Dept. of Computer Engineering A. D. Patel Inst. of Technology, S.P. University, New V.V. Nagar Dept. of Electronics and Commu. A. D. Patel Inst. of Technology S.P. University, New V.V. Nagar Dept. of Information Technology A. D. Patel Inst. of Technology S.P. University, New V.V. Nagar in unconstrained environment" 10261848b16292a5c8c700de6c6c9f692867c9c8,Cleaning Training-Datasets with Noise-Aware Algorithms,"Cleaning Training-Datasets with Noise-Aware Algorithms Instituto Nacional de Astrof´ısica ´Optica y Electr´onica, H. Jair Escalante Computer Science Department Tonantzintla, Puebla, 72840, M´exico" 10d3f77225eca1d576268ba84ed83f230a5e47c4,Crafting a multi-task CNN for viewpoint estimation,"F. MASSA ET AL.: CRAFTING A MULTI-TASK CNN FOR VIEWPOINT ESTIMATION Crafting a multi-task CNN for viewpoint estimation Francisco Massa http://imagine.enpc.fr/~suzano-f/ Renaud Marlet http://imagine.enpc.fr/~marletr/ Mathieu Aubry http://imagine.enpc.fr/~aubrym/ LIGM, UMR 814, Imagine, Ecole des Ponts ParisTech, UPEM,ESIEE Paris, CNRS, UPE Champs-sur-Marne, France" 100f57d2eb737d6cb467bfac6e4bbfa9b39e774f,Mixing Body-Part Sequences for Human Pose Estimation,"Mixing Body-Part Sequences for Human Pose Estimation Anoop Cherian∗ Julien Mairal∗ Karteek Alahari∗ Cordelia Schmid∗ Inria" 1040a32d5bd5e6f4c8bc1932345ef93671e2c019,Real-time RGB-D based template matching pedestrian detection,"Real-Time RGB-D based Template Matching Pedestrian Detection Omid Hosseini jafari and Michael Ying Yang" 101569eeef2cecc576578bd6500f1c2dcc0274e2,Multiaccuracy: Black-Box Post-Processing for Fairness in Classification,"Multiaccuracy: Black-Box Post-Processing for Fairness in Michael P. Kim∗† Classification Amirata Ghorbani∗ James Zou" 10c7575e7db69a208bfb21e3fc0cbc3f7698e99d,New sparse representation methods; application to image compression and indexing. (Nouvelles méthodes de représentations parcimonieuses ; application à la compression et l'indexation d'images),"New sparse representation methods; application to image compression and indexing Joaquin Zepeda Salvatierra To cite this version: Joaquin Zepeda Salvatierra. New sparse representation methods; application to image compression nd indexing. Human-Computer Interaction [cs.HC]. Université Rennes 1, 2010. English. HAL Id: tel-00567851 https://tel.archives-ouvertes.fr/tel-00567851 Submitted on 22 Feb 2011 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 10bb4ef7a6719ea132e00f0ab5680919a4131d99,BAM: Bottleneck Attention Module,"PARK, WOO, LEE, KWEON: BOTTLENECK ATTENTION MODULE BAM: Bottleneck Attention Module Jongchan Park*†1 Sanghyun Woo*2 Joon-Young Lee3 In So Kweon2 Lunit Inc. Seoul, Korea Korea Advanced Institute of Science nd Technology (KAIST) Daejeon, Korea Adobe Research San Jose, CA, USA" 10c077bf2dd1bed928926feb37837862ab786808,"Multiple Target Tracking and Identity Linking under Split, Merge and Occlusion of Targets and Observations","Multiple target tracking and identity linking under split, merge and occlusion of targets and observations nonymous submission Keywords: Tracking, graphical models, MAP inference, particle tracking, live cell tracking, intelligent headlights." 10e3b9fe646c6e81ec824cdc2391cc412a1b2730,Solving Three Czech NLP Tasks End-to-End with Neural Models,"S. Krajˇci (ed.): ITAT 2018 Proceedings, pp. 138–143 CEUR Workshop Proceedings Vol. 2203, ISSN 1613-0073, c(cid:13) 2018 Jindˇrich Libovický, Rudolf Rosa, Jindˇrich Helcl, and Martin Popel" 1038aa6c1f63c1de9045f10e47ed573810cb4a52,A Video-Based Method for Objectively Rating Ataxia,"A Video-Based Method for Objectively Rating Ataxia Ronnachai Jaroensri∗1, Amy Zhao∗1, Guha Balakrishnan1, Derek Lo2, Jeremy Schmahmann3, John Guttag1, and Fr´edo Durand1 MIT CSAIL 2Yale University 3Massachusetts General Hospital" 10cdb31a23c3233527ad2f8beebe7803b7a51a8c,Altered Neocortical Microcircuitry in the Valproic Acid Rat Model of Autism,"Altered Neocortical Microcircuitry in the Valproic Acid Rat Model of Autism THÈSE N° 3701 (2006) PRÉSENTÉE LE 20 NOVEMBRE À LA FACULTÉ DES SCIENCES DE LA VIE LABORATOIRE DE NEUROSCIENCE DES MICROCIRCUITS PROGRAMME DOCTORAL EN NEUROSCIENCES ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE POUR L’OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES Tania Rinaldi ingénieur chimiste diplômée EPF de nationalité suisse et originaire de Vouvry (VS) cceptée sur proposition du jury: Prof. R. Schneggenburger, président du jury Prof. H. Markram, directeur de thèse Prof. B. Gähwiler, rapporteur Prof. A. Lüthi, rapporteur Prof. C. Petersen, rapporteur Suisse (2006) année d’impression" 10d39dedfaf34d862e3ca7216521c6290044ff87,Synthesized Classifiers for Zero-Shot Learning,"Synthesized Classifiers for Zero-Shot Learning Soravit Changpinyo∗, Wei-Lun Chao∗ U. of Southern California Los Angeles, CA Boqing Gong U. of Central Florida Orlando, FL schangpi, Fei Sha U. of California Los Angeles, CA" 4c1ef2a628627798939dccc072d33f9e12b48640,Advanced Hybrid Color Space Normalization for Human Face Extraction and Detection,"IJSRD - International Journal for Scientific Research & Development| Vol. 1, Issue 4, 2013 | ISSN (online): 2321-0613 Advanced Hybrid Color Space Normalization for Human Face Extraction and Detection Jayakrishna.V1 Akhila G.P.2 Shafeena Basheer3 , 2Faculty 3PG Student , 3Amal Jyothi College of Engineering, Kanjirappally UKF College of Engineering &Technology,Parippally S.P.B.Patel Engineering College, Mehsana, Gujarat (CSN) technique enhancing is contained in Y component, and" 4cdfef0fec0918dcf5c40b9b53c9e3f48be0462b,Unsupervised robotic sorting: Towards autonomous decision making robots,"Unsupervised robotic sorting: Towards autonomous decision making robots Joris Gu´erin, St´ephane Thiery, Eric Nyiri and Olivier Gibaru Arts et M´etiers ParisTech, Lille, FRANCE" 4c500c84e16e5ebb50b33f9bcff36854e5131c16,All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification,"All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification Yoshihide Sawada1 and Yoshikuni Sato2 and Toru Nakada2 and Kei Ujimoto2 and Nobuhiro Hayashi3" 4c39000bbd6761dd9e5609fe310af51facb835a9,Kinects and human kinetics : A new approach for studying pedestrian behavior,"This paper might be a pre-copy-editing or a post-print author-produced .pdf of an article accepted for publication. For the definitive publisher-authenticated version, please refer directly to publishing house’s archive system." 4c81789b13b016afc5ef47591268533674c2a3f6,Mapless Online Detection of Dynamic Objects in 3D Lidar,"Mapless Online Detection of Dynamic Objects in 3D Lidar David J. Yoon, Tim Y. Tang, and Timothy D. Barfoot model-free," 4ca8ff09f24f0838022f1d0b94af4331f6e538cd,Semantic Parsing to Probabilistic Programs for Situated Question Answering,"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 160–170, Austin, Texas, November 1-5, 2016. c(cid:13)2016 Association for Computational Linguistics" 4cfa2fe87c250534fd2f285c2300e7ca2cd9e325,"Visual, Auditory, and Cross Modal Sensory Processing in Adults with Autism: An EEG Power and BOLD fMRI Investigation","ORIGINAL RESEARCH published: 19 April 2016 doi: 10.3389/fnhum.2016.00167 Visual, Auditory, and Cross Modal Sensory Processing in Adults with Autism: An EEG Power and BOLD fMRI Investigation Elizabeth’ C. Hames1, Brandi Murphy2, Ravi Rajmohan3, Ronald C. Anderson1, Mary Baker1*, Stephen Zupancic2, Michael O’Boyle4 and David Richman5 Department of Electrical and Computer Engineering, Texas Tech University, Lubbock, TX, USA, 2 Department of Audiology, Texas Tech University Health Sciences Center, Lubbock, TX, USA, 3 Department of Pharmacology and Neuroscience, Texas Tech University Health Sciences Center, Lubbock, TX, USA, 4 College of Human Sciences, Texas Tech University, Lubbock, TX, USA, 5 Burkhart Center for Autism Education and Research, Texas Tech University, Lubbock, TX, USA Electroencephalography (EEG) and blood oxygen level dependent functional magnetic resonance imagining (BOLD fMRI) assessed the neurocorrelates of sensory processing of visual and auditory stimuli in 11 adults with autism (ASD) and 10 neurotypical (NT) ontrols between the ages of 20–28. We hypothesized that ASD performance on ombined audiovisual trials would be less accurate with observable decreased EEG power across frontal, temporal, and occipital channels and decreased BOLD fMRI" 4c4e49033737467e28aa2bb32f6c21000deda2ef,Improving Landmark Localization with Semi-Supervised Learning,"Improving Landmark Localization with Semi-Supervised Learning Sina Honari1∗, Pavlo Molchanov2, Stephen Tyree2, Pascal Vincent1,4,5, Christopher Pal1,3, Jan Kautz2 MILA-University of Montreal, 2NVIDIA, 3Ecole Polytechnique of Montreal, 4CIFAR, 5Facebook AI Research. {honaris, {pmolchanov, styree," 4cfd15e9d3c01028bcda22e68791a95aa54c2a7c,"DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations","DeepLesion: Automated Deep Mining, Categorization nd Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations Ke Yan(cid:63), Xiaosong Wang(cid:63), Le Lu, and Ronald M. Summers Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD 20892 {ke.yan, xiaosong.wang, le.lu," 4c05dc45b82b79e87f7b337ccf9f48d537c0e6e2,Exploring Heterogeneity within a Core for Improved Power Efficiency,"Exploring Heterogeneity within a Core for Improved Power Efficiency Sudarshan Srinivasan, Nithesh Kurella, Israel Koren, Fellow, IEEE, and Sandip Kundu, Fellow, IEEE" 4c822705edd305d04f2c02ac9b1b73421e857961,Towards fully automated person re-identification,"Towards Fully Automated Person Re-Identification Matteo Taiana, Dario Figueira, Athira Nambiar, Jacinto Nascimento and Alexandre Bernardino Institute for Systems and Robotics, IST, Lisboa, Portugal Re-Identification, Pedestrian Detection, Camera Networks, Video Surveillance Keywords:" 4c5a07ab1700a67afaf16fc9a7a2647f51358255,DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection,"DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection Xi Li, Liming Zhao, Lina Wei, Ming-Hsuan Yang, Fei Wu, Yueting Zhuang, Haibin Ling, and Jingdong Wang" 4c477ba5513ec9c629ca3442c1fee15612259905,Complex Relations in a Deep Structured Prediction Model for Fine Image Segmentation,"Complex Relations in a Deep Structured Prediction Model for Fine Image Segmentation Cristina Mata, Guy Ben-Yosef, Boris Katz Computer Science and Artificial Intelligence Laboratory {cfmata, gby, Center for Brains, Minds and Machines" 4c6d6bb5bafba9e04d8f2ce128be71fba1d1e0e8,Human parsing with a cascade of hierarchical poselet based pruners,"HUMAN PARSING WITH A CASCADE OF HIERARCHICAL POSELET BASED PRUNERS Duan Tran† Yang Wang‡ University of Illinois at Urbana Champaign† David Forsyth† University of Manitoba‡" 4c4454aa7a2a244c678f507a982fe8827ba419bb,Adversarial Examples for Semantic Image Segmentation,"Workshop track - ICLR 2017 ADVERSARIAL EXAMPLES FOR SEMANTIC IMAGE SEGMENTATION Volker Fischer1, Mummadi Chaithanya Kumar2, Jan Hendrik Metzen1 & Thomas Brox2 Bosch Center for Artificial Intelligence, Robert Bosch GmbH University of Freiburg {volker.fischer," 4c797506d610525591288f813621b271ce879452,The automaticity of face perception is influenced by familiarity,"Atten Percept Psychophys (2017) 79:2202–2211 DOI 10.3758/s13414-017-1362-1 The automaticity of face perception is influenced by familiarity Xiaoqian Yan 1 & Andrew W. Young 1 & Timothy J. Andrews 1 Published online: 5 July 2017 # The Author(s) 2017. This article is an open access publication" 4cf5437ef31e587435ba1531da9109d714c0ee3e,Vehicle Re-identification Using Quadruple Directional Deep Learning Features,"Vehicle Re-identification Using Quadruple Directional Deep Learning Features Jianqing Zhu, Huanqiang Zeng, Jingchang Huang, Shengcai Liao, Zhen Lei, Canhui Cai and LiXin Zheng" 4cbb370f0bb6af0052bad6855cf1d9776376ceb3,Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection,"Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection Di Feng1, Lars Rosenbaum1, Klaus Dietmayer2" 4cfdd0c8313ac4f92845dcd658115beb115b97ce,Multi-Task Learning as Multi-Objective Optimization,"Multi-Task Learning as Multi-Objective Optimization Ozan Sener Intel Labs Vladlen Koltun Intel Labs" 4c0d7c0c4b0a1dd2fd11853ab98ea1fa79e0716b,Feature Extraction for Human Detection using HOG and CS-LBP methods,"International Journal of Computer Applications (0975 – 8887) National Conference “Electronics, Signals, Communication and Optimization"" (NCESCO 2015) Feature Extraction for Human Detection using HOG and CS-LBP methods Srujana B.J. PG Student Dept. of Computer Science and Engineering PES College of Engineering, Mandya The Histogram of Oriented Gradient (HOG) [2] [5] is a good descriptor for human detection. HOG features are now widely used in object recognition and detection [6]. They describe ody shape through the extraction of edge directions or gradient directions in the window. Each region of the window is divided into 64 blocks with each block having 32*32 in dimensions. Each block is composed of 2*2 cells. A histogram of oriented gradients is computed for each cell. The final descriptor is obtained by combining all the block features in a window. The main drawback of HOG is that, it produces too many feature patterns and is time consuming. The drawback of HOG is overcome with the use of CS-LBP" 4c710141c3800b91d099893fc2ef5d902a5a3f9b,An Eye Detection System Based on Neural Autoassociators,"An eye detection system ased on neural autoassociators Monica Bianchini and Lorenzo Sarti Dipartimento di Ingegneria dell’Informazione Universit`a degli Studi di Siena Via Roma 56 — 53100 Siena, ITALY" 4c60815ea05ff4b9f7301b28b8dd6017d64877bd,LIDAR-camera fusion for road detection using fully convolutional neural networks,"LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks Luca Caltagirone∗, Mauro Bellone, Lennart Svensson, Mattias Wahde {luca.caltagirone, mauro.bellone, lennart.svensson," 4c7659079b3df5bc746f76b2b1685b0b539832d6,Domain Adaptive Faster R-CNN for Object Detection in the Wild,"Domain Adaptive Faster R-CNN for Object Detection in the Wild Yuhua Chen1 Wen Li1 Christos Sakaridis1 Dengxin Dai1 Luc Van Gool1,2 Computer Vision Lab, ETH Zurich VISICS, ESAT/PSI, KU Leuven" 4cd30e654deedb5cab98ad73096ac73c9645860d,Data Imputation Through the Identification of Local Anomalies,"Data Imputation through the Identification of Local Anomalies Huseyin Ozkan, Ozgun S. Pelvan and Suleyman S. Kozat, Senior Member, IEEE" 4c73baaf624280b49eb73e5d72406fab5ae05011,On the impact of outliers on high-dimensional data analysis methods for face recognition,"On the Impact of Outliers on High-Dimensional Data Analysis Methods for Face Recognition Sid-Ahmed Berrani France Telecom R&D – TECH/IRIS , rue du Clos Courtel – BP 91226 5512 Cesson Sévigné Cedex, France Christophe Garcia France Telecom R&D – TECH/IRIS , rue du Clos Courtel – BP 91226 5512 Cesson Sévigné Cedex, France" 4c0ce0ed9cc92115874be4397f6240769d3ed84f,The effect of familiarity on face adaptation.,"doi:10.1068/p6774 The effect of familiarity on face adaptation Sarah Laurence, Graham Hole School of Psychology, University of Sussex, Falmer, Brighton BN1 9QH, Sussex, UK; e-mail: Received 14 July 2010, in revised form 30 March 2011" 4cc5fb6cf48b2c58b283460b19f3beeb7e5b6a22,Clickage: towards bridging semantic and intent gaps via mining click logs of search engines,"Clickage: Towards Bridging Semantic and Intent Gaps via Mining Click Logs of Search Engines Xian-Sheng Hua, Linjun Yang, Jingdong Wang, Jing Wang Ming Ye, Kuansan Wang, Yong Rui, Jin Li Microsoft Corporation, One Microsoft Way, Redmond WA 98052, USA {xshua; linjuny; jingdw; v-wangji; mingye; kuansanw; yongrui;" 4c1e47ba68b81d210718f837b197253164decaf0,Evaluation of Quality Factors for the Captured Facial Image,"International Journal of Computer Applications (0975 – 8887) Volume 142 – No.10, May 2016 Evaluation of Quality Factors for the Captured Facial Image Abhay Goyal M.Tech. Student Department of ECE SBSSTC, Ferozepur, Pujnab" 4ce68170f85560942ee51465e593b16560f9c580,Practical Matrix Completion and Corruption Recovery Using Proximal Alternating Robust Subspace Minimization,"(will be inserted by the editor) Practical Matrix Completion and Corruption Recovery using Proximal Alternating Robust Subspace Minimization Yu-Xiang Wang · Choon Meng Lee · Loong-Fah Cheong · Kim-Chuan Toh Introduction Completing a low-rank matrix from partially observed entries, also known as matrix completion, is a central task in many real-life applications. The same abstrac- tion of this problem has appeared in diverse fields such s signal processing, communications, information re- trieval, machine learning and computer vision. For in- stance, the missing data to be filled in may correspond to plausible movie recommendations (Koren et al 2009; Funk 2006), occluded feature trajectories for rigid or non-rigid structure from motion, namely SfM (Hart- ley and Schaffalitzky 2003; Buchanan and Fitzgibbon 005) and NRSfM (Paladini et al 2009), relative dis- tances of wireless sensors (Oh et al 2010), pieces of un- ollected measurements in DNA micro-array (Friedland et al 2006), just to name a few." 4c60a78722404bcbcd9afab4636993e79cf96c72,Learning Invariant Representations Of Planar Curves,"Published as a conference paper at ICLR 2017 LEARNING INVARIANT REPRESENTATIONS OF PLANAR CURVES Gautam Pai, Aaron Wetzler & Ron Kimmel Department of Computer Science Technion-Israel Institute of Technology" 4c863a15c4da0d0ccd20c5897a4e33fb771fe3eb,The effect of forced choice on facial emotion recognition: a comparison to open verbal classification of emotion labels,"OPEN ACCESS Research Article The effect of forced choice on facial emotion recognition: comparison to open verbal classification of emotion labels Der Effekt eines geschlossenen Antwortformats auf die mimische Emotionserkennung: ein Vergleich mit der freien verbale Zuordnung von Emotionswörtern Kerstin Limbrecht-Ecklundt1 Andreas Scheck1 Lucia Jerg-Bretzke1 Steffen Walter1 Holger Hoffmann1 Harald C. Traue1 University of Ulm, University Clinic of Psychosomatic Medicine and Psychotherapy, Medical Psychology, Ulm, Germany" 4c815f367213cc0fb8c61773cd04a5ca8be2c959,Facial expression recognition using curvelet based local binary patterns,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010" 4c5041f8b93fd71a851445e84bfca0d7d0c3bb9b,Enhancing Memory-Based Particle Filter with Detection-Based Memory Acquisition for Robustness under Severe Occlusion,"ENHANCING MEMORY-BASED PARTICLE FILTER WITH DETECTION-BASED MEMORY ACQUISITION FOR ROBUSTNESS UNDER SEVERE OCCLUSION Dan Mikami, Kazuhiro Otsuka, Shiro Kumano and Junji Yamato NTT Communication Science Laboratories, NTT, 3-1 Morinosato-Wakamiya, Atsugi, Kanagawa, 243-0198, Japan Keywords: Pose Tracking, Face Pose, Memory-based Prediction, Memory Acquisition." 4c88e41424022c7c5f111d34d931fae15f52a551,"CUR Decompositions, Similarity Matrices, and Subspace Clustering","CUR Decompositions, Similarity Matrices, and Subspace Clustering Akram Aldroubi, Keaton Hamm, Ahmet Bugra Koku, and Ali Sekmen" 4cfe0a11f11a2b8f9d16c4226280774de9a43f07,Can Object Detectors Aid Internet Video Event Retrieval ?,"Can Object Detectors Aid Internet Video Event Retrieval? , b University of Amsterdam, Science Park 904, 1098 XG, Amsterdam, The Netherlands; Davide Modolo a and Cees G.M. Snoekb" 4c6e1840451e1f86af3ef1cb551259cb259493ba,HAND POSTURE DATASET CREATION FOR GESTURE RECOGNITION,"HAND POSTURE DATASET CREATION FOR GESTURE RECOGNITION Instituto de Sistemas Inteligentes y Aplicaciones Numericas en Ingenieria Luis Anton-Canalis Campus Universitario de Tafira, 35017 Gran Canaria, Spain Elena Sanchez-Nielsen Departamento de E.I.O. y Computacion 8271 Universidad de La Laguna, Spain Keywords: Image understanding, Gesture recognition, Hand dataset." 4c987baaf0587798a40b56d4fdc9e2518bdc139b,TuringBox: An Experimental Platform for the Evaluation of AI Systems,"TuringBox: An Experimental Platform for the Evaluation of AI Systems Ziv Epstein * 1 Blakeley H. Payne * 1 Judy Hanwen Shen 1 Casey Jisoo Hong 1 Bjarke Felbo 1 Abhimanyu Dubey 1 Matthew Groh 1 Nick Obradovich 1 Manuel Cebrian 1 Iyad Rahwan 1" 4cf74211e635c73ca5816199ef33d10c3462beae,OF FACIAL EXPRESSION RECOGNITION SYSTEM AND USED DATASETS,"IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308 REVIEW OF FACIAL EXPRESSION RECOGNITION SYSTEM AND USED DATASETS Shyna Dutta1, V.B. Baru2, ME Student, Department of Electronics and Telecommunication, Sinhgad College of Engineering Vadgaon, Pune, Associate Professor, Department of Electronics and Telecommunication, Sinhgad College of Engineering Vadgaon," 4ce18536eec7917da848be6b5f783d3ee3d49677,Fast Face Detection in One Line of Code,"Fast Face Detection in One Line of Code Michael Zucchi, B.E. (Comp. Sys. Eng.) Unaliated, unfunded, personal research." 4c69da79843016d5d934464d3777030741978180,Neuromorphic Atomic Switch Networks,"Neuromorphic Atomic Switch Networks Audrius V. Avizienis1. Adam Z. Stieg2,3*, James K. Gimzewski1,2,3 , Henry O. Sillin1. , Cristina Martin-Olmos1, Hsien Hang Shieh2, Masakazu Aono3, Department of Chemistry and Biochemistry, University of California Los Angeles, Los Angeles, California, United States of America, 2 California NanoSystems Institute, University of California Los Angeles, Los Angeles, California, United States of America, 3 World Premier International Center for Materials Nanoarchitectonics, National Institute for Materials Science, Tsukuba, Ibaraki, Japan" 4c55ea9c04d46d60ec5789f4e4c3224c41360768,Dimensionality Reduction Using Similarity-Induced Embeddings,"IEEE Copyright Notice Copyright c(cid:13)2017 IEEE Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or fu- ture media, including reprinting/republishing this material for dvertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Published in: IEEE Transactions on Neural Networks and Learning Systems URL: http://ieeexplore.ieee.org/document/8004500 DOI: 10.1109/TNNLS.2017.2728818 DOI 10.1109/TNNLS.2017.2728818 c(cid:13)2017 IEEE" 4c81c76f799c48c33bb63b9369d013f51eaf5ada,Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs,"Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs Heysem Kaya1, Furkan G¨urpınar2, and Albert Ali Salah2 Department of Computer Engineering, Namık Kemal University, Tekirda˘g, Turkey Department of Computer Engineering, Bo˘gazic¸i University, Istanbul, Turkey" 86b105c3619a433b6f9632adcf9b253ff98aee87,A Mutual Information based Face Clustering Algorithm for Movies,"­4244­0367­7/06/$20.00 ©2006 IEEE ICME 2006" 869a2fbe42d3fdf40ed8b768edbf54137be7ac71,Relative Attributes for Enhanced Human-Machine Communication,"Relative Attributes for Enhanced Human-Machine Communication Devi Parikh1, Adriana Kovashka3, Amar Parkash2, and Kristen Grauman3 Toyota Technological Institute, Chicago Indraprastha Institute of Information Technology, Delhi University of Texas, Austin" 8645fe95f3f503f854b08096c2874a3f7ea6b79b,BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition,"BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition Jakub Sochor∗, Adam Herout, Jiˇr´ı Havel Brno University of Technology Brno, Czech Republic" 86dd8db0587b570ea2237c03cb0126ab3a53317c,A Novel Face Detection and Facial Feature Detection Algorithm using Skin Colour and Back Propagation Neural Network,"A Novel Face Detection and Facial Feature Detection Algorithm using Skin Colour and Back Propagation International Journal of Computer Applications (0975 – 8887) Volume 90 – No 2, March 2014 Neural Network Pijush Chakraborty Student, Computer Science and Engineering, Calcutta Institute of Engineering and Management, Kolkata Akashdeep Ghosh Student, Information Technology, RCC Institute of Information Technology, Kolkata" 86904aee566716d9bef508aa9f0255dc18be3960,Learning Anonymized Representations with Adversarial Neural Networks,"Learning Anonymized Representations with Adversarial Neural Networks Cl´ement Feutry, Pablo Piantanida, Yoshua Bengio, and Pierre Duhamel" 869df5e8221129850e81e77d4dc36e6c0f854fe6,A metric for sets of trajectories that is practical and mathematically consistent,"A metric for sets of trajectories that is practical and mathematically consistent Jos´e Bento Jia Jie Zhu" 8646f22a46b65c2018bc39ad3cbdb939e788a1fc,Learning a Confidence Measure for Optical Flow,"Learning a Confidence Measure for Optical Flow Oisin Mac Aodha, Ahmad Humayun, Marc Pollefeys and Gabriel J. Brostow" 8629c779581a0f46452bc4ca45b571bfbd3cd063,Defoiling Foiled Image Captions,"Defoiling Foiled Image Captions Pranava Madhyastha, Josiah Wang and Lucia Specia Department of Computer Science University of Sheffield, UK {p.madhyastha, j.k.wang," 863b96896ffa920bf5ae6f41c4997741d47c3e17,Multithreading cascade of SURF for facial expression recognition,"Chen et al. EURASIP Journal on Image and Video Processing (2016) 2016:37 DOI 10.1186/s13640-016-0140-7 EURASIP Journal on Image nd Video Processing RESEARCH Open Access Multithreading cascade of SURF for facial expression recognition Jinhui Chen1* , Zhaojie Luo2, Tetsuya Takiguchi3 and Yasuo Ariki3" 8623945e67548becb658ac2866c2fd28ad0aebac,Studying Human Face Recognition with the Gaze-Contingent Window Technique,"UC Merced Proceedings of the Annual Meeting of the Cognitive Science Society Title Studying Human Face Recognition with the Gaze-Contingent Window Technique Permalink https://escholarship.org/uc/item/5rt9n3c7 Journal Proceedings of the Annual Meeting of the Cognitive Science Society, 26(26) Authors Maw, Naing Naing Pomplun, Marc Publication Date 004-01-01 Peer reviewed eScholarship.org Powered by the California Digital Library University of California" 867fd4914a265b5dd4494f14273b8d28257c7b5b,A Comparison of FPGA and GPGPU Designs for Bayesian Occupancy Filters,"Article A Comparison of FPGA and GPGPU Designs for Bayesian Occupancy Filters Luis Medina 1, Miguel Diez-Ochoa 2, Raul Correal 2, Sergio Cuenca-Asensi 1, Alejandro Serrano 1 ID , Jorge Godoy 3, Antonio Martínez-Álvarez 1 and Jorge Villagra 3,* ID University Institute for Computing Research, University of Alicante, 03690 San Vicente del Raspeig, Spain; (L.M.); (S.C.-A.); (A.S.); (A.M.-Á.) Ixion Industry & Aerospace SL, Julian Camarilo 21B, 28037 Madrid, Spain; (M.D.-O.); (R.C.) Centre for Automation and Robotics (UPM-CSIC), 28500 Arganda del Rey, Spain; * Correspondence: Tel.: +34-918-711-900 Received: 15 September 2017 ; Accepted: 6 November 2017 ; Published: 11 November 2017" 86e1bdbfd13b9ed137e4c4b8b459a3980eb257f6,The Kinetics Human Action Video Dataset,"The Kinetics Human Action Video Dataset Will Kay Jo˜ao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev Mustafa Suleyman Andrew Zisserman" 862f19f8317971fabc46cf0f994f4a8616f17b78,Human Re-identification through Distance Metric Learning based on Jensen-Shannon Kernel,"HUMAN RE-IDENTIFICATION THROUGH DISTANCE METRIC LEARNING BASED ON JENSEN-SHANNON KERNEL Yoshihisa Ijiri1, Shihong Lao2, Tony X. Han3 and Hiroshi Murase4 Corporate R&D, OMRON Corp., Kizugawa, Kyoto, Japan OMRON Social Solutions Co. Ltd., Kizugawa, Kyoto, Japan Electrical & Computer Engineering Dept., Univ. of Missouri, Columbia, MO, U.S.A. Graduate School of Information Science, Nagoya Univ., Chigusaku, Nagoya, Japan Keywords: Human Re-identification, Distance Metric Learning, Jensen-Shannon Kernel." 8641593c67d87d81e528448a527e45fc9a5aa145,Complex Urban LiDAR Data Set,"Complex Urban LiDAR Data Set Jinyong Jeong1, Younggun Cho1, Young-Sik Shin1, Hyunchul Roh1 and Ayoung Kim1 Fig. 1: This paper provides the complex urban data set including metropolitan area, apartment building complex and underground parking lot. Sample scenes from the data set can be found in https://youtu.be/IguZjmLf5V0." 864f0e5e317a7d304dcc1dfca176b7afd230f4c2,Focal loss dense detector for vehicle surveillance,"Focal Loss Dense Detector for Vehicle Surveillance Xiaoliang Wang, Peng Cheng, Xinchuan Liu, Benedict Uzochukwu" 86e19f1899e67f4bdab015ad46cb72d0fb9b01a1,A Computer-Aided System for Indexing People in Historical Images,"A Computer-Aided System for Indexing People in Historical Images David Lunardi Flam, Camillo Jorge Santos Oliveira, Arnaldo de Albuquerque Araújo Núcleo de Processamento Digital de Imagens – NPDI Departamento de Ciência da Computação – DCC/ICEX Universidade Federal de Minas Gerais - UFMG {david, arnaldo," 86519cfb71135dd15eb6be3769052ef11e5ab257,DPC-Net: Deep Pose Correction for Visual Localization,"PERETROUKHIN et al.: DPC-NET: DEEP POSE CORRECTION FOR VISUAL LOCALIZATION DPC-Net: Deep Pose Correction for Visual Localization Valentin Peretroukhin1, and Jonathan Kelly1" 8627248c6e3c3e316e3964d12e0a44e23aa969f3,Automated Annotations,"Automated Annotations Richard Brath and Martin Matusiak* Uncharted Software Inc." 86ae83ce79f05952bd4a5448e901e626b8ba1af4,Structure-aware classification using supervised dictionary learning,"STRUCTURE-AWARE CLASSIFICATION USING SUPERVISED DICTIONARY LEARNING Yael Yankelevsky and Michael Elad Computer Science Department Technion - Israel Institute of Technology Haifa 32000, Israel" 869abfc258f5512fd95da179f7d92b624900eadd,Autonomous face recognition,"Autonomous Face Recognition Dissertation zur Erlangung des akademischen Grades eines Doktor-Ingenieurs (Dr.-Ing.) der Fakultät für Ingenieurwissenschaften der Universität Ulm Mou, Dengpan us China . Gutachter: Prof. Dr.-Ing. Albrecht Rothermel . Gutachter: Prof. Dr. Heiko Neumann Amtierender Dekan: Prof. Dr.-Ing. Hans-Jörg Pfleiderer Datum der Promotion: 2. August, 2005" 86e71e8cb5bd15a6530cbe684be0775249665f3c,Extended Patch Prioritization for Depth Filling Within Constrained Exemplar-Based RGB-D Image Completion,"Extended Patch Prioritization for Depth Filling within Constrained Exemplar-based RGB-D Image Completion Amir Atapour-Abarghouei and Toby P. Breckon Computer Science and Engineering, Durham University, UK" 86a417327acd84980a72cc6205174b4d58e5287b,Web Enabled Based Face Recognition Using Partitioned Iterated Function System,"Web Enabled Based Face Recognition using Partitioned Iterated Function System {tag} {/tag} International Journal of Computer Applications © 2010 by IJCA Journal Number 2 - Article 6 Year of Publication: 2010 Authors: Amol D.Potgantwar Dr.S.G.Bhirud 10.5120/57-159" 86c1bf121851aa901e3e7eb11a3b8cc5a08a921b,"Motion , Blur , Illumination based Face Recognition","ISSN: 2455-5797 International Journal of Innovative Works in Engineering and Technology (IJIWET) Motion, Blur, Illumination based Face Recognition Anand M.S PG Student Department of ECE Satyam College of Engineering E-mail :" 860196a306c9303ddaf323d702dacba68db658d2,Open-Ended Content-Style Recombination Via Leakage Filtering,"OPEN-ENDED CONTENT-STYLE RECOMBINATION VIA LEAKAGE FILTERING Karl Ridgeway+∗ & Michael C. Mozer+† + Department of Computer Science, University of Colorado, Boulder Sensory, Inc. presently at Google Brain, Mountain View" 86e87d276b5b01a6b4b09b5487781fab740aca2e,Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification,"Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification Jiayun Wanga, Sanping Zhoua, Jinjun Wanga,∗, Qiqi Houa The institute of artificial intelligence and robotic, Xi’an Jiaotong University, Xianning West Road No.28, Shaanxi, 710049, P.R. China" 86614c2d2f6ebcb9c600d4aef85fd6bf6eab6663,Benchmarks for Cloud Robotics,"Benchmarks for Cloud Robotics Arjun Singh Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2016-142 http://www.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-142.html August 12, 2016" 861802ac19653a7831b314cd751fd8e89494ab12,"Time-of-Flight and Depth Imaging. Sensors, Algorithms, and Applications","Marcin Grzegorzek, Christian Theobalt, Reinhard Koch, Andreas Kolb Time-of-Flight and Depth Imaging. Sensors, Algorithms nd Applications: Dagstuhl Seminar 2012 and GCPR Workshop on Imaging New Modalities (Lecture ... Vision, Pattern Recognition, and Graphics) Publisher: Springer; 2013 edition (November 8, 2013) Language: English Pages: 320 ISBN: 978-3642449635 Size: 20.46 MB Format: PDF / ePub / Kindle Cameras for 3D depth imaging, using either time-of-flight (ToF) or structured light sensors, have received lot of attention recently and have een improved considerably over the last few years. The present techniques..." 86c053c162c08bc3fe093cc10398b9e64367a100,Cascade of forests for face alignment,"Cascade of Forests for Face Alignment Heng Yang, Changqing Zou, Ioannis Patras" 86b1751b265b289b09de79956e77a01d82e12086,Face recognition in multi-camera surveillance videos,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-1-6 ©2012 IAPR" 8602b2ef26a0f851f1f6f2f2ae0ce142eb64300a,Is it a face ? How to find and validate a face on 3 D scans,"Is it a face ? How to find and validate a face on 3D scans Przemyslaw Szeptycki, Mohsen Ardabilian, Liming Chen Ecole Centrale de Lyon, 36 av. Guy de Collongue, 69134 Lyon, France {przemyslaw.szeptycki, mohsen.ardabilian, Introduction" 86585bd7288f41a28eeda883a35be6442224110a,A Variational Observation Model of 3 D Object for Probabilistic Semantic SLAM,"A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM H. W. Yu and B. H. Lee" 8609035f1b9fa5bddfbbffd287a98ba47a1ecba0,Making Bertha See,"Making Bertha See Uwe Franke, David Pfeiffer, Clemens Rabe, Carsten Knoeppel, Markus Enzweiler, Fridtjof Stein, and Ralf G. Herrtwich Daimler AG - Research & Development, 71059 Sindelfingen, Germany" 867d3aa95bb6a764ce3a03cfb5e99a81aea4a980,Computer-based recognition of dysmorphic faces,"& 2003 Nature Publishing Group All rights reserved 1018-4813/03 $25.00 www.nature.com/ejhg ARTICLE Computer-based recognition of dysmorphic faces Hartmut S Loos1, Dagmar Wieczorek*,2, Rolf P Wu¨rtz1, Christoph von der Malsburg1 and Bernhard Horsthemke2 Institut fu¨r Neuroinformatik, Ruhr-Universita¨t Bochum, Germany; 2Institut fu¨r Humangenetik, Universita¨tsklinikum Essen, Germany Genetic syndromes often involve craniofacial malformations. We have investigated whether a computer an recognize disease-specific facial patterns in unrelated individuals. For this, 55 photographs (256 256 pixel) of patients with mucopolysaccharidosis type III (n¼ 6), Cornelia de Lange (n¼ 12), fragile X (n¼ 12), Prader –Willi (n¼ 12), and Williams–Beuren (n¼ 13) syndromes were preprocessed by a Gabor wavelet transformation. By comparing the feature vectors at 32 facial nodes, 42/55 (76%) of the patients were orrectly classified. In another four patients (7%), the correct and an incorrect diagnosis scored equally well. Clinical geneticists who were shown the same photographs achieved a recognition rate of 62%. Our results prove that certain syndromes are associated with a specific facial pattern and that this pattern can e described in mathematical terms. Keywords: face recognition; facial pattern Introduction Humans have a remarkable ability to recognize and" 8616ff1d0fd7bcfc5fd81d1e8a9b189c21f3b93d,Visual Reference Resolution using Attention Memory for Visual Dialog,"Visual Reference Resolution using Attention Memory for Visual Dialog Paul Hongsuck Seo† POSTECH Andreas Lehrmann§ {hsseo, {andreas.lehrmann, Bohyung Han† §Disney Research Leonid Sigal§" da995212c9c8a933307cd893d862f5bf7d99f3ec,Elephant Panda Lion Dolphin Dog Monkey ... ... Classes Elephant Dolphin Lion Classifier Training Data Synthesizing Prediction,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) EmbeddingSample EmbeddingElephantLionPandaMonkeyDolphinDog0.140.490.660.721.060.59Figure1:FrameworkofembeddingbasedZSLapproaches.occurfrequentlyenough,andthenewconceptsemergeev-erydayespeciallyintheWeb,whichmakesitdifficultandex-pensivetocollectandlabelasufficientlylargetrainingsetformodellearning[Changpinyoetal.,2016].Howtotraineffec-tiveclassificationmodelsfortheuncommonclasseswithoutusingthelabeledsamplesbecomesanimportantandpracti-calproblemandhasgatheredconsiderableresearchinterestsfromthemachinelearningandcomputervisioncommunities.Itisestimatedthathumanscanrecognizeapproximate30;000basicobjectcategoriesandmanymoresubordinateonesandtheyareabletoidentifynewclassesgivenanat-tributedescription[Lampertetal.,2014].Basedonthisob-servation,manyzero-shotlearning(ZSL)approacheshavebeenproposed[Akataetal.,2015;Romera-ParedesandTorr,2015;ZhangandSaligrama,2016a;Guoetal.,2017a].ThegoalofZSListobuildclassifiersfortargetunseenclassesgivennolabeledsamples,withclassattributesassidein-formationandfullylabeledsourceseenclassesasknowl-edgesource.Differentfrommanysupervisedlearningap-proacheswhichtreateachclassindependently,ZSLasso-ciatesclasseswithanintermediaryattributeorsemantics-paceandthentransfersknowledgefromthesourceseenclassestothetargetunseenclassesbasedontheassocia-tion.Inthisway,onlytheattributevectorofatarget(un-seen)classisrequiredandtheclassificationmodelcanbebuiltevenwithoutanylabeledsamplesforthisclass.Inparticular,anembeddingfunctionislearnedusingthela-beledsamplesofsourceseenclassesthatmapstheimagesandclassesintoacommonembeddingspacewherethedis-tanceorsimilaritybetweenthemcanbemeasured.Becausetheattributesaresharedbybothsourceandtargetclass-es,theembeddingfunctionlearnedbysourceclassescanbedirectlyappliedtotargetclasses[Farhadietal.,2009;Socheretal.,2013].Finally,givenatestimage,wemapit" da61e3f62eda5e1cea027f73a156da36262722b0,Un nouvel ensemble de descripteurs de Fourier Clifford pour les images couleur. Les GCFD3,"Un nouvel ensemble de descripteurs de Fourier Clifford pour les images couleur : les GCFD3 José Mennesson, Christophe Saint-Jean, Laurent Mascarilla To cite this version: José Mennesson, Christophe Saint-Jean, Laurent Mascarilla. Un nouvel ensemble de descripteurs (3-4-5), pp.359-382. <10.3166/TS.29.359-382>. HAL Id: hal-00808069 https://hal.archives-ouvertes.fr/hal-00808069 Submitted on 4 Apr 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" daef6fa60c7d79930ad0a341aab69f1f4fa80442,Supplement for BIER,"Supplement for BIER . Introduction In this document we provide further insights into Boost- ing Independent Embeddings Robustly (BIER). First, in Section 2 we describe our method for loss functions op- erating on triplets. Next, in Section 3 we show how our method behaves when we vary the embedding size and the number of groups. In Section 4 we summarize the effect of our boosting based training approach and our initialization pproach. We provide an experiment evaluating the impact of end-to-end training in Section 5. Further, in Section 6 we demonstrate that our method is applicable to generic im- ge classification problems. Finally, we show a qualitative omparison of the different embeddings in our ensemble in Section 7 and some qualitative results in Section 8. . BIER for Triplets For loss functions operating on triplets of samples, we illustrate our training method in Algorithm 1. In contrast to our tuple based algorithm, we sample triplets x(1), x(2) nd x(3) which satisfy the constraint that the first pair (x(1)," da523ee3b7e8077713ebb7d903c3dc3bcb78921a,Multi-person tracking-by-detection based on calibrated multi-camera systems,"Multi-Person Tracking-by-Detection based on Calibrated Multi-Camera Systems Xiaoyan Jiang, Erik Rodner, and Joachim Denzler Computer Vision Group Jena Friedrich Schiller University of Jena http://www.inf-cv.uni-jena.de" da9080d5b433f73444078ac79c3a8a4515ad958e,IIS at ImageCLEF 2015: Multi-label Classification Task,"IIS at ImageCLEF 2015: Multi-label classification task Antonio J Rodr´ıguez-S´anchez1, Sabrina Fontanella1,2, Justus Piater1, and Sandor Szedmak1 Intelligent and Interactive Systems, Department of Computer Science, University of Innsbruck, Austria Department of Computer Science, University of Salerno, Italy https://iis.uibk.ac.at/" dabd3f276bc815865ab7c9f375368a1e31903860,Deformable face mapping for person identification,"DEFORMABLE FACE MAPPING FOR PERSON IDENTIFICATION Florent Perronnin , Jean-Luc Dugelay Institut Eurecom Multimedia Communications Department BP 193, F-06904 Sophia Antipolis Cedex  perronni, dugelay" da1e0b9e445493d3e6dc0e3c23be194228c5d796,Video Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting,"Video Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting Mennatullah Siam1, Chen Jiang1, Steven Lu1, Laura Petrich1, Mahmoud Gamal2, Mohamed Elhoseiny3, Martin Jagersand1" da013b84a93cc89d78f2d9a346fc275e3c159565,Affordable Self Driving Cars and Robots with Semantic Segmentation,"Affordable Self Driving Cars and Robots with Semantic Segmentation Gaurav Bansal Jeff Chen Evan Darke" da288fca6b3bcaee87a034529da5621bb90123d1,Aesthetics and Emotions in Images,"[ Dhiraj Joshi, Ritendra Datta, Elena Fedorovskaya, Quang-Tuan Luong, James Z. Wang, Jia Li, and Jiebo Luo] PUBLICDOMAINPICTURES.NET & © BRAND X PICTURES [ A computational perspective] In this tutorial, we define and discuss key aspects of the problem of computational inference of aesthetics nd emotion from images. We begin with a background discussion on philosophy, photography, paintings, visual arts, and psychology. This is followed by introduction of a set of key computational problems that the research community has been striving to solve and the computational framework required for solving them. We also describe data sets available for performing assessment and outline several real-world applica- tions where research in this domain can be employed. A significant number of papers that have attempted to solve problems in aesthetics and emotion inference are surveyed in this tutorial. We also discuss future direc- tions that researchers can pursue and make a strong case for seriously attempting to solve problems in this research domain. Digital Object Identifier 10.1109/MSP.2011.941851 Date of publication: 22 August 2011" da55917aa3a8a95179bae92c5b01e4c8f2f61b75,What makes a place? Building bespoke place dependent object detectors for robotics,"What Makes a Place? Building Bespoke Place Dependent Object Detectors for Robotics Jeffrey Hawke, Alex Bewley, Ingmar Posner" dae420b776957e6b8cf5fbbacd7bc0ec226b3e2e,RECOGNIZING EMOTIONS IN SPONTANEOUS FACIAL EXPRESSIONS,"RECOGNIZING EMOTIONS IN SPONTANEOUS FACIAL EXPRESSIONS Michael Grimm, Dhrubabrata Ghosh Dastidar, and Kristian Kroschel Institut f¨ur Nachrichtentechnik Universit¨at Karlsruhe (TH), Germany" da1ba46027b7236c937d276fb54e99906036c4ef,Using 3 D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition,"Using 3D Representations of the Nasal Region for Improved Landmarking and Expression Robust Recognition Jiangning Gao1 Adrian N Evans1 Department of Electronic and Electrical Engineering, University of Bath, Bath, UK, BA2 7AY." dac07680925b6c56b7ddf184dbdaf143a5d4816d,Object Ordering with Bidirectional Matchings for Visual Reasoning,"Object Ordering with Bidirectional Matchings for Visual Reasoning Hao Tan and Mohit Bansal UNC Chapel Hill {haotan," dae35f1f2c581d9e632cccb8d279b56a4f1deb79,Contribution to the Fusion of Biometric Modalities by the Choquet Integral,"I.J. Image, Graphics and Signal Processing, 2012, 10, 1-7 Published Online September 2012 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijigsp.2012.10.01 Contribution to the Fusion of Biometric Modalities by the Choquet Integral Research Unit of Advanced Systems in Electrical Engineering, National Engineering School of Sousse, Tunisia. Anouar Ben Khalifa1 , Research Unit of Advanced Systems in Electrical Engineering, National Engineering School of Sousse, Tunisia. e-mail: Najoua Essoukri BenAmara2 e-mail: to a digital fingerprint [8]. It is presented as a reliable means of authentication. Convenient, even more difficult to borrow, steal, forget or falsify [7]. However, the performance of authentication systems associated with these biometrics are still weak to even consider their large scale use [18]. In this context, multimodality ppears a promising way to improve the performance of biometric system. However, multimodality poses problems at the level of information fusion." dabd413deabad57bef8d426f7016db0b25ccbeb7,Face Recognition System Using Doubly Truncated Multivariate Gaussian Mixture Model and DCT Coefficients Under Logarithm Domain,"I.J. Image, Graphics and Signal Processing, 2012, 10, 8-17 Published Online September 2012 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijigsp.2012.10.02 Face Recognition System Using Doubly Truncated Multivariate Gaussian Mixture Model nd DCT Coefficients Under Logarithm Domain University college of Engineering, Jawaharlal Nehru Technological University Kakinada, Kakinada D. Haritha E-mail: K.Srinivasa Rao Department of Statistics, Andhra University, Visakhapatnam. E-mail: Ch. Satyanarayana University college of Engineering, Jawaharlal Nehru Technological University Kakinada, Kakinada E-mail:" dac3fcb9fd51a22ea27cb911b95051387c5885ba,Extraction of object from the video,"(cid:1)(cid:2)(cid:3)(cid:4)(cid:5)(cid:6)(cid:7)(cid:8)(cid:9)(cid:7)(cid:10)(cid:2)(cid:11)(cid:7)(cid:12)(cid:9)(cid:7)(cid:13)(cid:6)(cid:14)(cid:15)(cid:16)(cid:17)(cid:18)(cid:15)(cid:7)(cid:19)(cid:20)(cid:8)(cid:20)(cid:7) ISSN No. 0976-5697 (cid:21)(cid:22)(cid:15)(cid:6)(cid:23)(cid:22)(cid:24)(cid:15)(cid:25)(cid:2)(cid:22)(cid:24)(cid:3)(cid:7)(cid:26)(cid:2)(cid:4)(cid:23)(cid:22)(cid:24)(cid:3)(cid:7)(cid:2)(cid:27)(cid:7)(cid:28)(cid:29)(cid:30)(cid:24)(cid:22)(cid:18)(cid:6)(cid:29)(cid:7)(cid:31)(cid:6) (cid:6)(cid:24)(cid:23)(cid:18)!(cid:7)(cid:25)(cid:22)(cid:7)""(cid:2)(cid:5)(cid:14)(cid:4)(cid:15)(cid:6)(cid:23)(cid:7)(cid:13)(cid:18)(cid:25)(cid:6)(cid:22)(cid:18)(cid:6)(cid:7) (cid:31)#(cid:13)#(cid:28)(cid:31)""$(cid:7)%(cid:28)%#(cid:31)(cid:7) (cid:28)(cid:30)(cid:24)(cid:25)(cid:3)(cid:24)&(cid:3)(cid:6)(cid:7)(cid:17)(cid:22)(cid:3)(cid:25)(cid:22)(cid:6)(cid:7)(cid:24)(cid:15)(cid:7)’’’(cid:11)(cid:25)((cid:24)(cid:23)(cid:18) (cid:11)(cid:25)(cid:22)(cid:27)(cid:2)(cid:7) Extraction of object from the video Dr. M. Mohamed Sathik* Associate Professor in Computer Science, Sadakathullah Appa College, Thirunelveli, India-627 011. Ms. M. Parveen Research Scholar in Computer Science, Research and Development Centre, Bharathiyar University, Coimbatore, India. Ms. P. Peer Fatima Research Scholar in Computer Science, M.S.University, Thirunelveli, India." dadb7ddfde3478238d23a8bacf5eddecc59e84c9,Vocabulary Image Captioning with Constrained Beam Search,"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 947–956 Copenhagen, Denmark, September 7–11, 2017. c(cid:13)2017 Association for Computational Linguistics image containing previously unseen object (‘suitcase’)CNN-RNNCaptioning ModelA catsitting insideofa suitcase.cat, suitcase, insideConstrainedBeamSearchBeamSearchA cat sitting on top ofa refrigerator.Image TagsFigure1:Wesuccessfullycaptionimagescontain-ingpreviouslyunseenobjectsbyincorporatingse-manticattributes(i.e.,imagetags)duringRNNde-coding.ActualexamplefromSection4.2.prisingly,modelstrainedonthesedatasetsdonotgeneralizewelltoout-of-domainimagescontain-ingnovelscenesorobjects(Tranetal.,2016).Thislimitationseverelyhinderstheuseofthesemodelsinrealworldapplicationsdealingwithim-agesinthewild.Althoughavailableimage-captiontrainingdataislimited,manyimagecollectionsareaugmentedwithground-truthtextfragmentssuchassemanticattributes(i.e.,imagetags)orobjectannotations.Eveniftheseannotationsdonotexist,theycanbegeneratedusing(potentiallytaskspecific)imagetaggers(Chenetal.,2013;Zhangetal.,2016)orobjectdetectors(Renetal.,2015;Krauseetal.,2016),whichareeasiertoscaletonewconcepts.Inthispaperourgoalistoincorporatetextfrag-mentssuchastheseduringcaptiongeneration,toimprovethequalityofresultingcaptions.Thisgoalposestwokeychallenges.First,RNNsaregenerallyopaque,anddifficulttoinfluenceattesttime.Second,textfragmentsmayincludewords" da833d8ec9c91d55256effccd370b2e62a896ccb,Front-view Gait Recognition,"Front-view Gait Recognition Michela Goffredo, John N. Carter and Mark S. Nixon" dab6921a578c9ded6904a5a18bdd054aee62d2ad,Learning to Recognize Faces by Successive Meetings,"Learning to recognize faces y successive meetings M. Castrill´on-Santana, O. D´eniz-Su´arez, J. Lorenzo-Navarro and M. Hern´andez-Tejera IUSIANI Edif. Ctral. del Parque Cient´ıfico Tecnol´ogico Universidad de Las Palmas de Gran Canaria Las Palmas de Gran Canaria, 35017 Spain" daefac0610fdeff415c2a3f49b47968d84692e87,Multimodal Frame Identification with Multilingual Evaluation,"New Orleans, Louisiana, June 1 - 6, 2018. c(cid:13)2018 Association for Computational Linguistics Proceedings of NAACL-HLT 2018, pages 1481–1491" dad7b8be074d7ea6c3f970bd18884d496cbb0f91,Super-Sparse Regression for Fast Age Estimation from Faces at Test Time,"Super-Sparse Regression for Fast Age Estimation From Faces at Test Time Ambra Demontis, Battista Biggio, Giorgio Fumera, and Fabio Roli Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d’Armi, 09123 Cagliari, Italy WWW home page: http://prag.diee.unica.it" da8d0855e7760e86fbec47a3cfcf5acd8c700ca8,F 2 ConText : How to Extract Holistic Contexts of Persons of Interest for Enhancing Exploratory Analysis,"Accepted on 15 Sep 2018. To appear in Knowledge and Information Systems. Under consideration for publication in Knowledge and Information Sys- F2ConText: How to Extract Holistic Contexts of Persons of Interest for Enhancing Exploratory Analysis Md Abdul Kader1, Arnold P. Boedihardjo2 and M. Shahriar Hossain3 IBM Innovation Center, Austin, TX 78758 Radiant Solutions, Herndon, VA 20171 The University of Texas at El Paso, El Paso, TX 79968" da7ffe21508ad8d6dd9de7da378e184cb43a56c8,D Landmark Localisation,"D Landmark Localisation Luke Gahan, Supervised by Prof. Paul F. Whelan" dabf269f516adc6bf87a7ceb455cceda4466917a,Investigation of Facial Artifacts on Face Biometrics using Eigenface based Single and Multiple Neural Networks,"Investigation of Facial Artifacts on Face Biometrics using Eigenface based Single and Multiple Neural Networks K. Sundaraj University Malaysia Perlis (UniMAP) School of Mechatronics Engineering 02600 Jejawi - Perlis MALAYSIA" bff354d05823c83215183c8824faefbc093de011,A new efficient SVM and its application to real-time accurate eye localization,"Proceedings of International Joint Conference on Neural Networks, San Jose, California, USA, July 31 – August 5, 2011 A New Efficient SVM and Its Application to Real-time Accurate Eye Localization Shuo Chen and Chengjun Liu" bf4825474673246ae855979034c8ffdb12c80a98,"UNIVERSITY OF CALIFORNIA RIVERSIDE Active Learning in Multi-Camera Networks, With Applications in Person Re-Identification A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy in Electrical Engineering by","UNIVERSITY OF CALIFORNIA RIVERSIDE Active Learning in Multi-Camera Networks, With Applications in Person Re-Identification A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Electrical Engineering Abir Das December 2015 Dissertation Committee: Professor Amit K. Roy-Chowdhury, Chairperson Professor Anastasios Mourikis Professor Walid Najjar" bf1e0279a13903e1d43f8562aaf41444afca4fdc,Different Viewpoints of Recognizing Fleeting Facial Expressions with DWT,"International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 04 Issue: 10 | Oct -2017 www.irjet.net p-ISSN: 2395-0072 Different Viewpoints of Recognizing Fleeting Facial Expressions with VAIBHAV SHUBHAM1, MR. SANJEEV SHRIVASTAVA2, DR. MOHIT GANGWAR3 information to get desired information Introduction ---------------------------------------------------------------------***---------------------------------------------------------------------" bf514f38c6549700fd51355bdc6b86ff4707d4dd,Performance Analysis of Joint EM/SAGE Estimation and Multistage Detection in UTRA/WCDMA Uplink,"Publications L. Vandendorpe Laboratoire de T´el´ecommunications et T´el´ed´etection Universit´e catholique de Louvain December 2006" bf9d47987943e8c763ea42fbfd4b71c08ffda266,LECTURE ATTENDANCE SYSTEM WITH FACE RECOGNITION AND IMAGE PROCESSING,"International Journal Of Advance Research In Science And Engineering http://www.ijarse.com IJARSE, Vol. No.2, Issue No.3, March, 2013 ISSN-2319-8354(E) LECTURE ATTENDANCE SYSTEM WITH FACE RECOGNITION AND IMAGE PROCESSING" bf4f76c3da8a46783dfd2b72651e2300901ced25,Robust aggregation of GWAP tracks for local image annotation,"Robust aggregation of GWAP tracks for local image annotation C. Bernaschina, P. Fraternali, L. Galli, D. Martinenghi, M. Tagliasacchi Dipartimento di Elettronica, Informazione e Bioingegneria Politecnico di Milano, Italy" bfbee49e2c193fd0aa0f119bb2603450895dbf14,Rethinking Monocular Depth Estimation with Adversarial Training,"Rethinking Monocular Depth Estimation with Adversarial Training Richard Chen1, Faisal Mahmood2, Alan Yuille1 and Nicholas J. Durr2 Department of Computer Science 2Department of Biomedical Engineering Johns Hopkins University, Baltimore, MD {rchen40, faisalm, ayuille," bfa763e7cec812f855c712895fa48eae89a34a00,Face Retrieval using Frequency Decoded Local Descriptor,"PREPRINT: ACCEPTED IN MULTIMEDIA TOOLS AND APPLICATIONS, SPRINGER Face Retrieval using Frequency Decoded Local Descriptor Shiv Ram Dubey" bf86c65a4a3d81ca422600fdbc5d31eb56e098b9,Fusion Algorithms for Face Localization,"Algorithms Fusion for Face Localization R. BELAROUSSI L. PREVOST M. MILGRAM Institute of Intelligent Systems and Robotics–PRC University Pierre and Marie Curie Face localization is a face detection problem where the number of people is known. We present a comparison between different lgorithms fusion methods dedicated to the localization of faces in olor images. Data to combine result from an appearance model supported by an auto-associative network, an ellipse model based on Generalized Hough Transform, and a skin color model. We intro- duce and compare several fusion methods like the Bayesian classi- fier with parametric or non-parametric technique, a fuzzy inference system, and a weighted average. Given an input image, we compute kind of probability map on it using a sliding window. The face position is then determined as the location of the absolute maximum over this map. Improvement of basic detectors localization rates is learly shown and prevalence of the weighted average is reported." bf4fcd80083f3145176b64d15bab78456a7e5e43,Title Fast Randomized Algorithms for Convex Optimization and Statistical Estimation Permalink,"Fast Randomized Algorithms for Convex Optimization and Statistical Estimation Mert Pilanci Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2016-147 http://www.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-147.html August 14, 2016" bf3aae7293f664d512c0904916d804327af22f52,STDnet: A ConvNet for Small Target Detection,"BOSQUET, MUCIENTES, BREA: STDNET FOR SMALL TARGET DETECTION STDnet: A ConvNet for Small Target Detection Brais Bosquet Manuel Mucientes Víctor M. Brea Centro Singular de Investigación en Tecnoloxías da Información (CiTIUS) University of Santiago de Compostela Santiago de Compostela, Spain" bfa71537839a81a03569a702a7cdc07647f7de4d,Target re-identification in low-quality camera networks,"Target Re-Identi(cid:12)cation in Low Quality Camera Networks Federica Battisti, Marco Carli, Giovanna Farinella, Alessandro Neri (cid:3) Applied Electronics Department Universit(cid:19)a degli Studi Roma TRE Rome, Italy" bf8bcda2e4d04b6bd6f5e70622e972baf525a1c7,Three decades of Cognition & Emotion: A brief review of past highlights and future prospects.,"COGNITION AND EMOTION, 2018 VOL. 32, NO. 1, 1–12 https://doi.org/10.1080/02699931.2018.1418197 nd future prospects Klaus Rothermunda and Sander L. Kooleb Institute of Psychology, Friedrich-Schiller-Universität Jena, Jena, Germany; bDepartment of Psychology, VU Amsterdam, Amsterdam, the Netherlands" bfa6ad4d71008505729274d008a9b4a7d92b2985,Semantic Understanding of Scenes Through the ADE20K Dataset,"Semantic Understanding of Scenes through the ADE20K Dataset Bolei Zhou · Hang Zhao · Xavier Puig · Tete Xiao · Sanja Fidler · Adela Barriuso · Antonio Torralba" bf39babab5648ff64cc4b79bfec96e8c6c93b812,The Impact of Disappointment in Decision Making: Inter-Individual Differences and Electrical Neuroimaging,"(cid:65)(cid:114)(cid:116)(cid:105)(cid:99)(cid:108)(cid:101) (cid:84)(cid:104)(cid:101)(cid:32)(cid:73)(cid:109)(cid:112)(cid:97)(cid:99)(cid:116)(cid:32)(cid:111)(cid:102)(cid:32)(cid:68)(cid:105)(cid:115)(cid:97)(cid:112)(cid:112)(cid:111)(cid:105)(cid:110)(cid:116)(cid:109)(cid:101)(cid:110)(cid:116)(cid:32)(cid:105)(cid:110)(cid:32)(cid:68)(cid:101)(cid:99)(cid:105)(cid:115)(cid:105)(cid:111)(cid:110)(cid:32)(cid:77)(cid:97)(cid:107)(cid:105)(cid:110)(cid:103)(cid:58)(cid:32)(cid:73)(cid:110)(cid:116)(cid:101)(cid:114)(cid:45)(cid:73)(cid:110)(cid:100)(cid:105)(cid:118)(cid:105)(cid:100)(cid:117)(cid:97)(cid:108) (cid:68)(cid:105)(cid:102)(cid:102)(cid:101)(cid:114)(cid:101)(cid:110)(cid:99)(cid:101)(cid:115)(cid:32)(cid:97)(cid:110)(cid:100)(cid:32)(cid:69)(cid:108)(cid:101)(cid:99)(cid:116)(cid:114)(cid:105)(cid:99)(cid:97)(cid:108)(cid:32)(cid:78)(cid:101)(cid:117)(cid:114)(cid:111)(cid:105)(cid:109)(cid:97)(cid:103)(cid:105)(cid:110)(cid:103) (cid:84)(cid:90)(cid:73)(cid:69)(cid:82)(cid:79)(cid:80)(cid:79)(cid:85)(cid:76)(cid:79)(cid:83)(cid:44)(cid:32)(cid:72)(cid:233)(cid:108)(cid:232)(cid:110)(cid:101)(cid:44)(cid:32)(cid:101)(cid:116)(cid:32)(cid:97)(cid:108)(cid:46)" bf05e710dae791f82cc639a09dbe5ec66fed2008,Generating Video Description using Sequence-to-sequence Model with Temporal Attention,"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 44–52, Osaka, Japan, December 11-17 2016." bf4ec5068e6ff0b008a09f0c94bfaac290ae7d3b,Co-attention CNNs for Unsupervised Object Co-segmentation,Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) bf96a0f037e7472e4b6cb1dae192a5fedbbbd88a,Visual Listening In: Extracting Brand Image Portrayed on Social Media,"Visual Listening In: Extracting Brand Image Portrayed on Social Media Liu Liu NYU Stern School of Business, Daria Dzyabura NYU Stern School of Business, University of Washington - Foster School of Business, Natalie Mizik Marketing academics and practitioners recognize the importance of monitoring consumer online conversations bout brands. The focus so far has been on user generated content in the form of text. However, images are on their way to surpassing text as the medium of choice for social conversations. In these images, consumers often tag brands. We propose a “visual listening in” approach to measuring how brands are portrayed on social media (Instagram), by mining visual content posted by users. Our approach consists of two stages. We first use two supervised machine learning methods, traditional support vector machine classifiers and deep onvolutional neural networks, to measure brand attributes (glamorous, rugged, healthy, fun) from images. We then apply the classifiers to brand-related images posted on social media to measure what consumers re visually communicating about brands. We study 56 brands in the apparel and beverages categories, and ompare their portrayal in consumer-created images with images on the firm’s of‌f‌icial Instagram account, as well as with consumer brand perceptions measured in a national brand survey. Although the three measures exhibit convergent validity, we find key differences between how consumers and firms portray the brands on" bfb98423941e51e3cd067cb085ebfa3087f3bfbe,Sparseness helps: Sparsity Augmented Collaborative Representation for Classification,"Sparseness helps: Sparsity Augmented Collaborative Representation for Classification Naveed Akhtar, Faisal Shafait, and Ajmal Mian" bfef76d0e287fc6401d69a9f65ff174e4fbf0970,Nonnegative Matrix Factorization with Outliers,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" bfcba38d563a4a75f69f892a9638f464049723b9,Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos,"Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos Vincent Casser∗1 Soeren Pirk Reza Mahjourian2 Anelia Angelova Institute for Applied Computational Science, Harvard University; Google Brain Google Brain University of Texas at Austin; Google Brain {pirk, rezama," bf15ba4db09fd805763738ec2cb48c09481785dd,Training Deep Neural Network in Limited Precision,"Training Deep Neural Network in Limited Precision Hyunsun Park∗, Jun Haeng Lee∗, Youngmin Oh, Sangwon Ha, Seungwon Lee Samsung Advanced Institute of Technology Samsung-ro 130, Suwon-si, Republic of Korea {h-s.park," bf4e6ec60e5603324f6a40d2a060420322dbdd62,Kinects and Human Kinetics: A New Approach for Studying Crowd Behavior,"Kinects and Human Kinetics: A New Approach for Studying Crowd Behavior Stefan Seera,b,∗, Norbert Br¨andlea, Carlo Rattib Austrian Institute of Technology (AIT), Giefinggasse 2, 1210 Vienna, Austria MIT Senseable City Lab, Massachusetts Institute of Technology (MIT), 77 Massachusetts Avenue, 02139 Cambridge, MA, USA" 448efcae3b97aa7c01b15c6bc913d4fbb275f644,Style Finder : Fine-Grained Clothing Style Recognition and Retrieval,"Style Finder: Fine-Grained Clothing Style Recognition and Retrieval Wei Di2, Catherine Wah1, Anurag Bhardwaj2, Robinson Piramuthu2, and Neel Sundaresan2 Department of Computer Science and Engineering, University of California, San Diego eBay Research Labs, 2145 Hamilton Ave. San Jose, CA" 446a99fdedd5bb32d4970842b3ce0fc4f5e5fa03,A Pose-Adaptive Constrained Local Model for Accurate Head Pose Tracking,"A Pose-Adaptive Constrained Local Model For Accurate Head Pose Tracking Lucas Zamuner Eikeo 1 rue Leon Jouhaux, F-75010, Paris, France Kevin Bailly Sorbonne Universit´es UPMC Univ Paris 06 CNRS UMR 7222, ISIR F-75005, Paris, France Erwan Bigorgne Eikeo 1 rue Leon Jouhaux, F-75010, Paris, France" 4419215162eb6ec20206fb70f6890c5286ced188,Audiovisual Speech SynchronyMeasure : Application to Biometrics,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2007, Article ID 70186, 11 pages doi:10.1155/2007/70186 Research Article Audiovisual Speech Synchrony Measure: Application to Biometrics Herv ´e Bredin and G ´erard Chollet D´epartement Traitement du Signal et de l’Image, ´Ecole Nationale Sup´erieure des T´el´ecommunications, CNRS/LTCI, 46 rue Barrault, 75013 Paris Cedex 13, France Received 18 August 2006; Accepted 18 March 2007 Recommended by Ebroul Izquierdo Speech is a means of communication which is intrinsically bimodal: the audio signal originates from the dynamics of the articu- lators. This paper reviews recent works in the field of audiovisual speech, and more specifically techniques developed to measure the level of correspondence between audio and visual speech. It overviews the most common audio and visual speech front-end processing, transformations performed on audio, visual, or joint audiovisual feature spaces, and the actual measure of correspon- dence between audio and visual speech. Finally, the use of synchrony measure for biometric identity verification based on talking faces is experimented on the BANCA database. Copyright © 2007 H. Bredin and G. Chollet. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly" 4452c36dc4c5e9f11d041489c8ff2e7006d33c80,"A Computational Analysis of Recent Multi-Object Tracking Methods Based on Particle Filter , HMM and Appearance Information of Objects","International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 3, Issue 02, February 2013) A Computational Analysis of Recent Multi-Object Tracking Methods Based on Particle Filter, HMM and Appearance Information of Objects Raksha Shrivastava1, Professor Rajesh Nema 2 ,2Department of Electronics and Communication, NRI Institute of Information Science and Technology, Bhopal (M.P)" 4430d41c36c731c16020037d25df3dcd237fd863,IJATRD 2012019 ) THERMAL RECOGNITION IN BIOMETRICS AUTHENTICATION Mr,"International Journal for Advancements in Technical Research & Development (IJATRD2012019) THERMAL RECOGNITION IN BIOMETRICS AUTHENTICATION Mr. Gopal Sakarkar Asst. Prof. MCA Dept., haracteristic the biometric system is based on, can e either central or distributed. In the case of a distributed database, each individual has a magnetic or smart card in which his biometric characteristic is recorded. The techniques of user authentication are linked to passwords, user IDs, identification cards and PINs (personal identification numbers). These techniques suffer from several limitations: Passwords and PINs an be guessed, stolen or illicitly acquired by covert observation[2]. The biometrics systems provide a more accurate and reliable user authentication method. Existing user authentication techniques include:" 44e3d382ce8d765f705706d40716cb81575281e8,Automatic Parameter Adaptation for Multi-object Tracking,"Automatic Parameter Adaptation for Multi-Object Tracking Duc Phu CHAU, Monique THONNAT, and Fran¸cois BREMOND {Duc-Phu.Chau, Monique.Thonnat, STARS team, INRIA Sophia Antipolis, France http://team.inria.fr/stars" 44736c0c7cfced2c0f06c5ae8dd0111d9ea0dc20,On the Robustness of Speech Emotion Recognition for Human-Robot Interaction with Deep Neural Networks,"On the Robustness of Speech Emotion Recognition for Human-Robot Interaction with Deep Neural Networks Egor Lakomkin1, Mohammad Ali Zamani1, Cornelius Weber1, Sven Magg1 and Stefan Wermter1" 449f93b4be37087236c6a13e9db4c1c323683a58,Abnormalities in early visual processes are linked to hypersociability and atypical evaluation of facial trustworthiness: An ERP study with Williams syndrome,"Cogn Affect Behav Neurosci (2017) 17:1002–1017 DOI 10.3758/s13415-017-0528-6 Abnormalities in early visual processes are linked to hypersociability and atypical evaluation of facial trustworthiness: An ERP study with Williams syndrome Danielle M. Shore 1 & Rowena Ng 2 & Ursula Bellugi 3 & Debra L. Mills 4 Published online: 6 July 2017 # The Author(s) 2017. This article is an open access publication" 44682707bf06626bb1f0d9b181fb5c45cb446d30,Stable Affine Frames on Isophotes,"Stable Af‌f‌ine Frames on Isophotes Michal Perd’och Jiˇr´ı Matas ˇStˇep´an Obdrˇz´alek Center for Machine Perception, CTU in Prague, Czech Republic" 44880df54e6caa3e7263db7a4d5cb77838f4698f,Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions,"Learning Optimal Parameters for Multi-target Tracking with Contextual Interactions Shaofei Wang · Charless C. Fowlkes" 44bb6ccb3526bb38364550263bc608116910da32,Model-Driven Simulations for Computer Vision,"017 IEEE Winter Conference on Applications of Computer Vision Model-driven Simulations for Computer Vision VSR Veeravasarapu1, Constantin Rothkopf2, Ramesh Visvanathan1 Center for Cognition and Computation, Dept. of Computer Science, Goethe University, Frankfurt Center for Cognitive Science & Dept. of Psychology, Technical University Darmstadt. (a) Lambertian (Direct-lighting based rendering) (b) Ray tracing (appearance-driven rendering) (c) Monte-Carlo rendering (physics-driven rendering) (d) Semantic labels (e) Day light (f) Night Figure 1: Rendering fidelity and Virtual scene diversity. This work aims to quantify the impact of photorealism and physics fidelity on transfer learning from virtual reality. (a)-(c): Images of same scene state rendered with different rendering engines. (e)-(g): Same scene under different lighting. (d) and (h) semantic labels. Color coding scheme for labels is same as [5]. (g) Rain (h) Semantic labels" 44993de87bbbce71f14d7917944d055700217696,A late fusion approach to combine multiple pedestrian detectors,"A Late Fusion Approach to Combine Multiple Pedestrian Detectors Artur Jord˜ao, Jessica Sena de Souza, William Robson Schwartz Smart Surveillance Interest Group, Computer Science Department Universidade Federal de Minas Gerais, Minas Gerais, Brazil" 44703dea094eb9558965db9439a07b9a74fd36b5,"Multiculturalism, Colorblindness, and Prejudice: Examining How Diversity Ideologies Impact Intergroup Attitudes","University of Arkansas, Fayetteville Theses and Dissertations 8-2018 Multiculturalism, Colorblindness, and Prejudice: Examining How Diversity Ideologies Impact Intergroup Attitudes David Sparkman University of Arkansas, Fayetteville Follow this and additional works at: https://scholarworks.uark.edu/etd Part of the Social Psychology Commons Recommended Citation Sparkman, David, ""Multiculturalism, Colorblindness, and Prejudice: Examining How Diversity Ideologies Impact Intergroup Attitudes"" (2018). Theses and Dissertations. 2923. https://scholarworks.uark.edu/etd/2923 This Dissertation is brought to you for free and open access by It has been accepted for inclusion in Theses and Dissertations by n authorized administrator of For more information, please contact" 44984f97c8c5ff0a734dc4496116df195789beba,Random Forest with Adaptive Local Template for Pedestrian Detection,"Publishing CorporationMathematical Problems in EngineeringVolume 2015, Article ID 767423, 11 pageshttp://dx.doi.org/10.1155/2015/767423" 44f4b1b90f8d5515f2486e07e4cb4b9589c27518,Deep Learning and Its Applications to Machine Health Monitoring: A Survey,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Deep Learning and Its Applications to Machine Health Monitoring: A Survey Rui Zhao, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, and Robert X. Gao" 4439746eeb7c7328beba3f3ef47dc67fbb52bcb3,An Efficient Face Detection Method Using Adaboost and Facial Parts,"YASAMAN HEYDARZADEH at al: AN EFFICIENT FACE DETECTION METHOD USING ADABOOST . . . An Efficient Face Detection Method Using Adaboost and Facial Parts Yasaman Heydarzadeh, Abolfazl Toroghi Haghighat Computer, IT and Electronic department Azad University of Qazvin Tehran, Iran qiau.ac.ir ," 44241248f16c172a1c2fb90e48fd728ba26220fc,Expression-invariant Non-rigid 3 D Face Recognition : A Robust Approach to Expression-aware Morphing,"Expression-invariant Non-rigid 3D Face Recognition: A Robust Approach to Expression-aware Morphing F. R. Al-Osaimi M. Bennamoun A. Mian" 44a3ec27f92c344a15deb8e5dc3a5b3797505c06,A Taxonomy of Part and Attribute Discovery Techniques,"A Taxonomy of Part and Attribute Discovery Techniques Subhransu Maji" 44b30a1048465cd56904cdcbec8e79dffab693bd,Semantic based Query Approach For Web Image Search Through reranking algorithm,"Scientific Journal of Impact Factor (SJIF): 3.134 E-ISSN (O): 2348-4470 P-ISSN (P): 2348-6406 International Journal of Advance Engineering and Research Development Volume 2,Issue 12,December -2015 Semantic based Query Approach For Web Image Search Through reranking algorithm Pushpak Waghmare1, Shubham Katkamwan2, Abhijeet Markand3, Abuj Pratiksha4, Prof. Navale Girish Jaysingh5 -5Department Of Computer,All India shri Shivaji Memorial Society’s" 4414a328466db1e8ab9651bf4e0f9f1fe1a163e4,Weighted voting of sparse representation classifiers for facial expression recognition,"© EURASIP, 2010 ISSN 2076-1465 8th European Signal Processing Conference (EUSIPCO-2010) INTRODUCTION" 44f65e3304bdde4be04823fd7ca770c1c05c2cef,On the use of phase of the Fourier transform for face recognition under variations in illumination,"SIViP DOI 10.1007/s11760-009-0125-4 ORIGINAL PAPER On the use of phase of the Fourier transform for face recognition under variations in illumination Anil Kumar Sao · B. Yegnanarayana Received: 17 November 2008 / Revised: 20 February 2009 / Accepted: 7 July 2009 © Springer-Verlag London Limited 2009" 446dc1413e1cfaee0030dc74a3cee49a47386355,Recent Advances in Zero-shot Recognition,"Recent Advances in Zero-shot Recognition Yanwei Fu, Tao Xiang, Yu-Gang Jiang, Xiangyang Xue, Leonid Sigal, and Shaogang Gong" 4461a1b70e461ec298d7066ba103deda48d4ba22,Classification via Minimum Incremental Coding Length,"Vol. 2, No. 2, pp. 367–395 (cid:2) 2009 Society for Industrial and Applied Mathematics Classification via Minimum Incremental Coding Length John Wright , Yi Ma , Yangyu Tao , Zhouchen Lin , and Heung-Yeung Shum" 442cc39db208a66acf3acc22589b13981bb303fd,Design of Non-Linear Discriminative Dictionaries for Image Classification,"CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. Design of Non-Linear Discriminative Dictionaries for Image Classi(cid:12)cation Anonymous ACCV 2012 submission Paper ID 662" 4443ee5eaa56e41acddb62cacbc2f6d8c84ccd59,Multiple Objects Fusion Tracker Using a Matching Network for Adaptively Represented Instance Pairs,"Article Multiple Objects Fusion Tracker Using a Matching Network for Adaptively Represented Instance Pairs Sang-Il Oh and Hang-Bong Kang * Department of Media Engineering, Catholic University of Korea, 43-1, Yeoggok 2-dong, Wonmmi-gu, Bucheon-si, Gyeonggi-do 14662, Korea; * Correspondence: Tel.: +82-2-2164-4598 Academic Editor: Simon X. Yang Received: 27 February 2017; Accepted: 14 April 2017; Published: 18 April 2017" 4425df6cc10917644c44a7f4177a5d7cc1c8b7bc,Object Localization based on Structural SVM using Privileged Information,"Object Localization based on Structural SVM using Privileged Information Jan Feyereisl, Suha Kwak∗, Jeany Son, Bohyung Han Dept. of Computer Science and Engineering, POSTECH, Pohang, Korea" 447a5e1caf847952d2bb526ab2fb75898466d1bc,LEARNING NON-LINEAR TRANSFORM WITH DISCRIM- INATIVE AND MINIMUM INFORMATION LOSS PRIORS,"Under review as a conference paper at ICLR 2018 LEARNING NON-LINEAR TRANSFORM WITH DISCRIM- INATIVE AND MINIMUM INFORMATION LOSS PRIORS Anonymous authors Paper under double-blind review" 383f874ba7975c83b55c694ec0a70f51dc3a0ee5,Towards Automatic Image Understanding and Mining via Social Curation,"Towards Automatic Image Understanding and Mining via Social Curation Katsuhiko Ishiguro, Akisato Kimura, and Koh Takeuchi NTT Communication Science Laboratories NTT Corporation, Kyoto, Japan" 38215c283ce4bf2c8edd597ab21410f99dc9b094,The SEMAINE Database: Annotated Multimodal Records of Emotionally Colored Conversations between a Person and a Limited Agent,"The SEMAINE Database: Annotated Multimodal Records of Emotionally Colored Conversations between a Person and a Limited Agent McKeown, G., Valstar, M., Cowie, R., Pantic, M., & Schröder, M. (2012). The SEMAINE Database: Annotated Multimodal Records of Emotionally Colored Conversations between a Person and a Limited Agent. IEEE Transactions on Affective Computing, 3(1), 5-17. DOI: 10.1109/T-AFFC.2011.20 Published in: Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to ensure that content in the Research Portal does not infringe any person's rights, or applicable UK laws. If you discover content in the Research Portal that you believe breaches copyright or violates any law, please contact Download date:05. Nov. 2018" 38b0a67727dea3fe563e8662517bd0fda2fd5e06,Perceiving and expressing feelings through actions in relation to individual differences in empathic traits: the Action and Feelings Questionnaire (AFQ),"Cogn Affect Behav Neurosci (2016) 16:248–260 DOI 10.3758/s13415-015-0386-z Perceiving and expressing feelings through actions in relation to individual differences in empathic traits: the Action nd Feelings Questionnaire (AFQ) Justin H. G. Williams 1,4 & Isobel M. Cameron 1 & Emma Ross 2 & Lieke Braadbaart 3 & Gordon D Waiter 3 Published online: 20 October 2015 # The Author(s) 2015. This article is published with open access at Springerlink.com" 389b2390fd310c9070e72563181547cf23dceea3,β-VAE : L EARNING B ASIC,"Published as a conference paper at ICLR 2017 β-VAE: LEARNING BASIC VISUAL CONCEPTS WITH A CONSTRAINED VARIATIONAL FRAMEWORK Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, Alexander Lerchner Google DeepMind {irinah,lmatthey,arkap,cpburgess,glorotx," 3837f81524286ed5f9142d245743733766aa4017,Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples,"Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples Moustapha Cisse Facebook AI Research Natalia Neverova* Facebook AI Research" 3898a9dcb22f87413f08bb44c656f4129e1c42df,On binary representations for biometric template protection,"ON BINARY REPRESENTATIONS FOR BIOMETRIC TEMPLATE PROTECTION Chun Chen" 38cc2896058131e4656443aedfb1b9dae61b99cd,Functional Connectivity Imaging Analysis : Interhemispheric Integration in Autism,"Functional Connectivity Imaging Analysis: Interhemispheric Integration in Autism Daniel J. Kelley" 38eea307445a39ee7902c1ecf8cea7e3dcb7c0e7,Multi-distance Support Matrix Machines,"Noname manuscript No. (will be inserted by the editor) Multi-distance Support Matrix Machine Yunfei Ye1 · Dong Han1 Received: date / Accepted: date" 3824a648507000b7f319b9bf2ec0b7d07bcdfee4,A performance evaluation of local descriptors,"A performance evaluation of local descriptors K. Mikolajczyk C. Schmid INRIA Rhône-Alpes, GRAVIR-CNRS 655, av. de l’Europe, 38330 Montbonnot, France" 38679355d4cfea3a791005f211aa16e76b2eaa8d,Title Evolutionary cross-domain discriminative Hessian Eigenmaps,"Title Evolutionary cross-domain discriminative Hessian Eigenmaps Author(s) Si, S; Tao, D; Chan, KP Citation Ieee Transactions On Image Processing, 2010, v. 19 n. 4, p. 1075- Issued Date http://hdl.handle.net/10722/127357 Rights IEEE Transactions on Image Processing. Copyright © IEEE.; This work is licensed under a Creative Commons Attribution- NonCommercial-NoDerivatives 4.0 International License.; ©2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any opyrighted component of this work in other works must be obtained from the IEEE." 38d56ddcea01ce99902dd75ad162213cbe4eaab7,Sense Beauty by Label Distribution Learning,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 38a3611138388490c2cd60dfbf795932d5e55a79,2 D pose estimation in the Restaurant of the Future,"D pose estimation in the Restaurant of the Future Frederik (Frank) Evers supervision by dr. ir. Nico P. van der Aa Noldus IT B.V. Wageningen, NL dr. Robby T. Tan University of Utrecht Utrecht, NL March 29, 2012" 3807f0c1b7360f99fe2d30d2fd1722fbddd276b0,Czech Technical University in Prague F 3 Faculty of Electrical EngineeringDepartment of Cybernetics Object Scene Flow in Video Sequences,"Master Thesis Czech Technical University in Prague Faculty of Electrical Engineering Department of Cybernetics Object Scene Flow in Video Sequences Bc. Michal Neoral Supervisor: Mgr. Jan Šochman, Ph.D. Field of study: Open Informatics Subfield: Computer Vision and Image Processing May 2017" 382f1ebe6009e580949d5513bc298cb253a1eeda,Interpreting Complex Regression Models,"Interpreting Complex Regression Models Noa Avigdor-Elgrabli∗, Alex Libov†, Michael Viderman∗, Ran Wolff∗ Yahoo Research, Haifa, Israel, Amazon Research, Haifa, Israel," 389363432ee9fcf0e0cfe67b7b4f62618e1f4b59,Performing content-based retrieval of humans using gait biometrics,"Performing Content-Based Retrieval of Humans Using Gait Biometrics Sina Samangooei and Mark S. Nixon School of Electronics and Computer Science, Southampton University, Southampton, SO17 1BJ, United Kingdom" 384f972c81c52fe36849600728865ea50a0c4670,"Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition","Multi-Fold Gabor, PCA and ICA Filter Convolution Descriptor for Face Recognition Cheng Yaw Low, Andrew Beng Jin Teoh, Senior Member, IEEE, Cong Jie Ng" 38998d58a0c1048ad4c08d0022066e22ba6d1201,RE-IDENTIFICATION THROUGH A VIDEO,"UNIVERSIT´EDENICE-SOPHIAANTIPOLIS´ECOLEDOCTORALESTICSCIENCESETTECHNOLOGIESDEL’INFORMATIONETDELACOMMUNICATIONTH`ESEpourl’obtentiondugradedeDocteurenSciencesdel’Universit´edeNice-SophiaAntipolisMention:AUTOMATIQUETRAITEMENTDUSIGNALETDESIMAGESpr´esent´eeetsoutenueparMalikSOUDEDPEOPLEDETECTION,TRACKINGANDRE-IDENTIFICATIONTHROUGHAVIDEOCAMERANETWORKTh`esedirig´eeparFranc¸oisBR´EMONDSoutenancepr´evuele20/12/2013Jury:MoniqueTHONNATDirectrice,INRIASophia-Antipolis,FrancePr´esidenteJamesFERRYMANProfesseur,UniversityofReading,UKRapporteurCarloREGAZZONIProfesseur,UniversityofGenova,ItalyRapporteurPatrickBOUTHEMYDirecteur,INRIARennes,FranceExaminateurFranc¸oisBREMONDDirecteur,INRIASophia-Antipolis,FranceDirecteurdeth`eseMarie-ClaudeFRASSONDirectrice,DigitalBarriers,Sophia-Antipolis,FranceInvit´ee" 380d5138cadccc9b5b91c707ba0a9220b0f39271,Deep Imbalanced Learning for Face Recognition and Attribute Prediction,"Deep Imbalanced Learning for Face Recognition nd Attribute Prediction Chen Huang, Yining Li, Chen Change Loy, Senior Member, IEEE and Xiaoou Tang, Fellow, IEEE" 386a5c06d334d20227e8b2daf5433a2bef385648,Cross and Learn: Cross-Modal Self-Supervision,"Cross and Learn: Cross-Modal Self-Supervision Nawid Sayed1, Biagio Brattoli2, and Bj¨orn Ommer2 Heidelberg University, HCI / IWR, Germany" 3805d47da61527137b6f44b92af3017a2dfe7bd5,Greedy column subset selection for large-scale data sets,"(will be inserted by the editor) Greedy Column Subset Selection for Large-scale Data Sets Ahmed K. Farahat · Ahmed Elgohary · Ali Ghodsi · Mohamed S. Kamel Received: date / Accepted: date" 380b8df0f340e5bbc3a953c62f9bc573ce073b92,Joint Image-Text News Topic Detection and Tracking by Multimodal Topic And-Or Graph,"Joint Image-Text News Topic Detection and Tracking by Multimodal Topic And-Or Graph Weixin Li, Jungseock Joo, Hang Qi, and Song-Chun Zhu" 38a169b6e67ef7768f91fa208c9b5544f6f57f16,Object Bank: An Object-Level Image Representation for High-Level Visual Recognition,"Int J Comput Vis DOI 10.1007/s11263-013-0660-x Object Bank: An Object-Level Image Representation for High-Level Visual Recognition Li-Jia Li · Hao Su · Yongwhan Lim · Li Fei-Fei Received: 2 January 2012 / Accepted: 11 September 2013 © Springer Science+Business Media New York 2013" 38b18585e4bdb78347d44caa561e69a0045ade8d,Differential Attention for Visual Question Answering,"Differential Attention for Visual Question Answering Badri Patro, Vinay P. Namboodiri IIT Kanpur { badri,vinaypn" 3858e5175799b97805b2b70ff54e8a7e0718870f,Deep Learning For Smile Recognition,"July 26, 2017 WSPC - Proceedings Trim Size: 9in x 6in paper Deep Learning For Smile Recognition Patrick O. Glauner Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg 721 Luxembourg, Luxembourg Email: snt.uni.lu Inspired by recent successes of deep learning in computer vision, we propose novel application of deep convolutional neural networks to facial expression recognition, in particular smile recognition. A smile recognition test accuracy of 99.45% is achieved for the Denver Intensity of Spontaneous Facial Action (DISFA) database, significantly outperforming existing approaches based on hand-crafted features with accuracies ranging from 65.55% to 79.67%. The novelty of this approach includes a comprehensive model selection of the ar- hitecture parameters, allowing to find an appropriate architecture for each expression such as smile. This is feasible because all experiments were run on a Tesla K40c GPU, allowing a speedup of factor 10 over traditional computations on a CPU." 3802da31c6d33d71b839e260f4022ec4fbd88e2d,Deep Attributes for One-Shot Face Recognition,"Deep Attributes for One-Shot Face Recognition Aishwarya Jadhav1,3, Vinay P. Namboodiri2, and K. S. Venkatesh 3 Xerox Research Center India, 2Department of Computer Science, Department of Electrical Engineering, IIT Kanpur" 38e3c26829e38c6b56f7c541e0c4445820fab0fe,BOLD5000: A public fMRI dataset of 5000 images,"BOLD5000 A public fMRI dataset of 5000 images Nadine Chang1, John A. Pyles1, Abhinav Gupta1, Michael J. Tarr1, Elissa M. Aminoff2* September 6, 2018 thor: Elissa Aminoff" 38e509fc0d94e954a512128760f7a1f0d6fbc384,A Framework for Application-Guided Task Management on Heterogeneous Embedded Systems,"A Framework for Application Guided Task Management on Heterogeneous Embedded Systems FRANCISCO GASPAR, INESC-ID, Instituto Superior T´ecnico, Universidade de Lisboa LUIS TANIC¸ A, INESC-ID, Instituto Superior T´ecnico, Universidade de Lisboa PEDRO TOM ´AS, INESC-ID, Instituto Superior T´ecnico, Universidade de Lisboa ALEKSANDAR ILIC, INESC-ID, Instituto Superior T´ecnico, Universidade de Lisboa LEONEL SOUSA, INESC-ID, Instituto Superior T´ecnico, Universidade de Lisboa In this paper, we propose a general framework for fine-grain application-aware task management in hetero- geneous embedded platforms, which allows integration of different mechanisms for an efficient resource uti- lization, frequency scaling and task migration. The proposed framework incorporates several components for ccurate run-time monitoring by relying on the OS facilities and performance self-reporting for parallel and iterative applications. The framework efficiency is experimentally evaluated on a real hardware platform, where significant power and energy savings are attained for SPEC CPU2006 and PARSEC benchmarks, by guiding frequency scaling and inter-cluster migrations according to the run-time application behavior and predefined performance targets. CCS Concepts:rComputer systems organization → Multicore architectures; Heterogeneous (hybrid) systems;rSoftware and its engineering → Process management; Additional Key Words and Phrases: Heterogeneous multi processor; scheduling; embedded systems; quality of service; big.LITTLE; task migration; dynamic voltage and frequency control ACM Reference Format:" 3837f3faa722c91aa21d6f17ea1ac1cb5187bda1,Human Action Attribute Learning From Video Data Using Low-Rank Representations,"Human Action Attribute Learning From Video Data Using Low-Rank Representations Tong Wu, Student Member, IEEE, Prudhvi Gurram, Senior Member, IEEE, Raghuveer M. Rao, Fellow, IEEE, and Waheed U. Bajwa, Senior Member, IEEE" 383d64b27fb3cdf2beff43f3beb8caac8c21a886,Detecting activities of daily living in first-person camera views,"Detecting Activities of Daily Living in First-person Camera Views Hamed Pirsiavash Deva Ramanan Department of Computer Science, University of California, Irvine" 38f56240c642677f2245aebe94fb846988487570,Mining patterns of orientations and magnitudes for face recognition,"Mining patterns of orientations and magnitudes for face recognition Ngoc-Son Vu, Alice Caplier Gipsa-lab, Grenoble Institute of Technology" 3810b6299140bf2c7d6d0cced765c0777d603923,Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?,"Do Deep Features Generalize from Everyday Objects to Remote Sensing and Aerial Scenes Domains? Ot´avio A. B. Penatti Advanced Technologies Group SAMSUNG Research Institute Campinas, SP, 13097-160, Brazil Keiller Nogueira, Jefersson A. dos Santos Department of Computer Science Universidade Federal de Minas Gerais Belo Horizonte, MG, 31270-010, Brazil" 38f1fac3ed0fd054e009515e7bbc72cdd4cf801a,Finding Person Relations in Image Data of the Internet Archive,"Finding Person Relations in Image Data of the Internet Archive Eric M¨uller-Budack1,2[0000−0002−6802−1241], Kader Pustu-Iren1[0000−0003−2891−9783], Sebastian Diering1, and Ralph Ewerth1,2[0000−0003−0918−6297] Leibniz Information Centre for Science and Technology (TIB), Hannover, Germany L3S Research Center, Leibniz Universit¨at Hannover, Germany" 38d26057acdae8d66378db4b1a2fbebed0a14f27,Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment,"Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment Davood Rafiei and Fan Deng" 389334e9a0d84bc54bcd5b94b4ce4c5d9d6a2f26,Facial parameter extraction system based on active contours,"FACIAL PARAMETER EXTRACTION SYSTEM BASED ON ACTIVE CONTOURS Montse Pardàs, Marcos Losada Universitat Politècnica de Catalunya, Barcelona, Spain" 38192f06ac19172299ab543483d2e0eca2f889c0,Mining Mid-level Features for Image Classification,"(will be inserted by the editor) Mining Mid-level Features for Image Classification Basura Fernando · Elisa Fromont · Tinne Tuytelaars Received: date / Accepted: date" 3851ed2e3c00083f68c2811694736ebdaa9ed8b5,DeepStory: Video Story QA by Deep Embedded Memory Networks,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) d008e8662b7e482b88e6dee7c50bd939d28e7628,"People detection, tracking and re-identification through a video camera network. (Détection, suivi et ré-identification de personnes à travers un réseau de caméra vidéo)","People detection, tracking and re-identification through video camera network Malik Souded To cite this version: Malik Souded. People detection, tracking and re-identification through a video camera network. Other [cs.OH]. Université Nice Sophia Antipolis, 2013. English. . HAL Id: tel-00913072 https://tel.archives-ouvertes.fr/tel-00913072v2 Submitted on 29 Jan 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" d03e4e938bcbc25aa0feb83d8a0830f9cd3eb3ea,Face Recognition with Patterns of Oriented Edge Magnitudes,"Face Recognition with Patterns of Oriented Edge Magnitudes Ngoc-Son Vu1,2 and Alice Caplier2 Vesalis Sarl, Clermont Ferrand, France Gipsa-lab, Grenoble INP, France" d03f1257066ce5dd843c6977858a1daef0671f3d,Stories for Images-in-Sequence by using Visual and Narrative Components,"Stories for Images-in-Sequence by using Visual nd Narrative Components (cid:63) Marko Smilevski1,2, Ilija Lalkovski2, and Gjorgji Madjarov1,3 Ss. Cyril and Methodius University, Skopje, Macedonia Pendulibrium, Skopje, Macedonia Elevate Global, Skopje, Macedonia" d03265ea9200a993af857b473c6bf12a095ca178,Multiple deep convolutional neural networks averaging for face alignment,"Multiple deep convolutional neural networks averaging for face lignment Shaohua Zhang Hua Yang Zhouping Yin Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 05/28/2015 Terms of Use: http://spiedl.org/terms" d0b936f643f7462068517e0a840e775d6bd4abfb,Improving Video Generation for Multi-functional Applications,"Improving Video Generation for Multi-functional Applications Bernhard Kratzwald, Zhiwu Huang, Danda Pani Paudel, Acharya Dinesh, Luc Van Gool ETH Zurich" d0e20aa3d61b77d17f005a1d24d7cf47600836ef,Rethinking Atrous Convolution for Semantic Image Segmentation,"Rethinking Atrous Convolution for Semantic Image Segmentation Liang-Chieh Chen George Papandreou Florian Schroff Hartwig Adam {lcchen, gpapan, fschroff, Google Inc." d0a9bbd3bd9dcb62f9874fc1378a7f1a17f44563,Prototype Generation Using Self-Organizing Maps for Informativeness-Based Classifier,"Hindawi Computational Intelligence and Neuroscience Volume 2017, Article ID 4263064, 15 pages https://doi.org/10.1155/2017/4263064 Research Article Prototype Generation Using Self-Organizing Maps for Informativeness-Based Classifier Leandro Juvêncio Moreira1 and Leandro A. Silva2 Graduate Program in Electrical Engineering and Computing, Mackenzie Presbyterian University, Sao Paulo, SP, Brazil Computing and Informatics Faculty & Graduate Program in Electrical Engineering and Computing, Mackenzie Presbyterian University, Sao Paulo, SP, Brazil Correspondence should be addressed to Leandro A. Silva; Received 31 January 2017; Revised 13 June 2017; Accepted 15 June 2017; Published 25 July 2017 Academic Editor: Toshihisa Tanaka Copyright © 2017 Leandro Juvˆencio Moreira and Leandro A. Silva. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The 𝑘 nearest neighbor is one of the most important and simple procedures for data classification task. The 𝑘NN, as it is called, requires only two parameters: the number of𝑘 and a similarity measure. However, the algorithm has some weaknesses that make it nalysis and all training dataset is necessary. Another weakness is the optimal choice of 𝑘 parameter when the object analyzed" d01e65591745fc46a3f69a6c9387be17caf55c16,State-Driven Particle Filter for Multi-person Tracking,"State-Driven Particle Filter for Multi-Person Tracking David Gerónimo1, Frédéric Lerasle2,3, and Antonio M. López1 Computer Vision Center and Department of Computer Science Edifici O, 08193 Campus Universitat Autònoma de Barcelona, Bellaterra, Spain. CNRS-LAAS, 7 avenue du Colonel Roche, F-31077 Toulouse, France Université de Toulouse (UPS), F-31077 Toulouse, France" d0a6a700779ac8cb70d7bb95f9a5afdda60152d9,Pyramid Mean Representation of Image Sequences for Fast Face Retrieval in Unconstrained Video Data,"Pyramid Mean Representation of Image Sequences for Fast Face Retrieval in Unconstrained Video Data Christian Herrmann1,2 and J¨urgen Beyerer1,2 Vision and Fusion Lab, Karlsruhe Institute of Technology KIT, Karlsruhe, Germany Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, Karlsruhe, Germany" d041c8cb05a5555046f6e62a4efbb964fb560c31,Generating faces for affect analysis,"Noname manuscript No. (will be inserted by the editor) Generating faces for affect analysis Dimitrios Kollias (cid:63) · Shiyang Cheng † · Evangelos Ververas ∗ · Irene Kotsia1 · Stefanos Zafeiriou2 Received: Sept 30th 2018 / Accepted: date" d0d186779ae4a4e53101a26dc741254e822e07ab,Multi Camera for Surveillance System Ground Detection and 3 D Reconstruction,"Multi Camera for Surveillance System Ground Detection and International Journal of Smart Home Vol. 9, No. 1 (2015), pp. 103-110 http://dx.doi.org/10.14257/ijsh.2015.9.1.11 D Reconstruction Xu Yongzhe1 and Byungsoo Lee1 Department of Computer Engineering, University of Incheon, Korea" d00787e215bd74d32d80a6c115c4789214da5edb,Faster and Lighter Online Sparse Dictionary Learning Project report,"Faster and Lighter Online Sparse Dictionary Learning Project report By: Shay Ben-Assayag, Omer Dahary Supervisor: Jeremias Sulam" d00c335fbb542bc628642c1db36791eae24e02b7,Deep Learning-Based Gaze Detection System for Automobile Drivers Using a NIR Camera Sensor,"Article Deep Learning-Based Gaze Detection System for Automobile Drivers Using a NIR Camera Sensor Rizwan Ali Naqvi, Muhammad Arsalan, Ganbayar Batchuluun, Hyo Sik Yoon and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro, 1-gil, Jung-gu, Seoul 100-715, Korea; (R.A.N.); (M.A.); (G.B.); (H.S.Y.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 5 January 2018; Accepted: 1 February 2018; Published: 3 February 2018" d0a21f94de312a0ff31657fd103d6b29db823caa,Facial Expression Analysis,"Facial Expression Analysis Fernando De la Torre and Jeffrey F. Cohn" d0de92865a53576af3dd118f4d1fa73be12aee9b,PCANet-II: When PCANet Meets the Second Order Pooling,"PCANet-II:WhenPCANetMeetstheSecondOrderPoolingLeiTian,XiaopengHong" d07e9b04c1480d65e37e44bec3be95fc3206c17b,Combining classifiers for face recognition,- 130-7803-7965-9/03/$17.00 ©2003 IEEEICME 2003(cid:224) d02f45670fa6eb1fbac7ed7ed3eaa442579c73b2,Covariance Pooling for Facial Expression Recognition,"Covariance Pooling for Facial Expression Recognition Computer Vision Lab, ETH Zurich, Switzerland VISICS, KU Leuven, Belgium Dinesh Acharya†, Zhiwu Huang†, Danda Pani Paudel†, Luc Van Gool†‡ {acharyad, zhiwu.huang, paudel," d00f6ec074bbe777ba2e419b39729283a28101c5,Hashtag Recommendation for Multimodal Microblog Using Co-Attention Network,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) d0462aa7754ffdf39962e2003344937258a0e42e,You Can ’ t Gamble on Others : Dissociable Systems for Strategic Uncertainty and Risk in the Brain,"You Can’t Gamble on Others: Dissociable Systems for Strategic Uncertainty and Risk in the Brain W. Gavin Ekins1, Ricardo Caceda, C. Monica Capra1, and Gregory S. Berns1* 1Center for Neuropolicy and Economics Department, Emory University, Atlanta, GA 30322 USA *Correspondance:" d0eab36a4c76da09d2393ff549c2d6de2106a4cb,"Semantic Segmentation via Multi-task, Multi-domain Learning","Semantic Segmentation via Multi-task, Multi-domain Learning Damien Fourure1 & R´emi Emonet1 & Elisa Fromont 1 Damien Muselet1 & Alain Tr´emeau 1 & Christian Wolf2 Univ Lyon, UJM, CNRS, Lab Hubert Curien UMR5516, F-42000 Universite de Lyon, CNRS, France, INSA-Lyon, LIRIS, UMR5205, F-69621" d05825a394f11a391c8815f6b0d394cdb4cfaa95,I2T2I: Learning text to image synthesis with textual data augmentation, d02c54192dbd0798b43231efe1159d6b4375ad36,3 D Reconstruction and Face Recognition Using Kernel-Based ICA and Neural Networks,"D Reconstruction and Face Recognition Using Kernel-Based ICA and Neural Networks Cheng-Jian Lin Ya-Tzu Huang Chi-Yung Lee Dept. of Electrical Dept. of CSIE Dept. of CSIE Engineering Chaoyang University Nankai Institute of National University of Technology Technology of Kaohsiung" d0e1ad4f3f608124cd3efc2d5bd01b421ffc3274,Suppressing behaviour related to discomfort induced with a cold pressure task does not influence working memory capacity in a 2-back task,"Running head: SUPPRESSING BEHAVIOUR INFLUENCE WORKING MEMORY CAPACITY DEPARTMENT OF PSYCHOLOGY Suppressing behaviour related to discomfort induced with a cold pressure task does not influence working memory capacity in a 2-back task. Erik Danielski Master thesis spring 2013 Supervisors: Martin Wolgast & Emelie Stiernströmer" d0ad7324fab174609f26c617869fa328960617e2,Person Identification From Text Independent Lip Movement Using the Longest Matching Segment Method,"Person Identification From Text Independent Lip Movement Using the Longest Matching Segment Method Paul C. Brown, Ji Ming, Daryl Stewart Institute of ECIT, Electronics and Computer Engineering Cluster, Queen(cid:48)s University Belfast, Belfast BT7 1NN, UK" d096bdd5743cbb33f0cd0ae984d188b2c302f054,EXTRACTIVE AND ABSTRACTIVE CAPTION GENERATION MODEL FOR NEWS IMAGES,"ISSN:2321-1156 International Journal of Innovative Research in Technology & Science(IJIRTS)" d0f709ab39e280467d854064132570c1d5316de5,Multi-Object Tracking and Identification over Sets,"Multi-Object Tracking and Identification over Sets Aijun Bai UC Berkeley" d0144d76b8b926d22411d388e7a26506519372eb,Improving Regression Performance with Distributional Losses,"Improving Regression Performance with Distributional Losses Ehsan Imani 1 Martha White 1" d0631ba22add59684fff926d80d2e6948dfb7d7e,MUTT: Metric Unit TesTing for Language Generation Tasks,"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1935–1943, Berlin, Germany, August 7-12, 2016. c(cid:13)2016 Association for Computational Linguistics" d0765e76ea93e70ad6873560541531b5f572fb4f,ANALÝZA POHYBU OSOB STACIONÁRNÍ KAMEROU ANALYSIS OF MOTION OF PEOPLE BY A STATIONARY CAMERA,"VYSOKE´ UCˇ ENI´ TECHNICKE´ V BRNEˇ BRNO UNIVERSITY OF TECHNOLOGY FAKULTA INFORMACˇ NI´CH TECHNOLOGII´ U´ STAV POCˇ I´TACˇ OVE´ GRAFIKY A MULTIME´ DII´ FACULTY OF INFORMATION TECHNOLOGY DEPARTMENT OF COMPUTER GRAPHICS AND MULTIMEDIA ANALY´ ZA POHYBU OSOB STACIONA´ RNI´ KAMEROU ANALYSIS OF MOTION OF PEOPLE BY A STATIONARY CAMERA BAKALA´ Rˇ SKA´ PRA´ CE BACHELOR’S THESIS AUTOR PRA´ CE AUTHOR VEDOUCI´ PRA´ CE SUPERVISOR BRNO 2014 STANISLAV SMATANA Ing. ADAM HEROUT, Ph.D." 5f02e49aa0fe467bbeb9de950e4abb6c99133feb,"Enhancing person re-identification by late fusion of low-, mid- and high-level features","Aalborg Universitet Enhancing Person Re-identification by Late Fusion of Low-, Mid-, and High-Level Features Lejbølle, Aske Rasch; Nasrollahi, Kamal; Moeslund, Thomas B. Published in: DOI (link to publication from Publisher): 0.1049/iet-bmt.2016.0200 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Lejbølle, A. R., Nasrollahi, K., & Moeslund, T. B. (2018). Enhancing Person Re-identification by Late Fusion of General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain ? You may freely distribute the URL identifying the publication in the public portal ? Take down policy" 5f344a4ef7edfd87c5c4bc531833774c3ed23542,Semisupervised Learning of Classifiers with Application to Human-computer Interaction," Copyright by Ira Cohen, 2003" 5f4a873118e033e5e168ee99d64474b4cc4d94a3,Lessons Learned from Crime Caught on Camera,"Article Lessons Learned from Crime Caught on Camera Marie Rosenkrantz Lindegaard1,2 nd Wim Bernasco1,3 Journal of Research in Crime and Delinquency 018, Vol. 55(1) 155-186 ª The Author(s) 2018 Reprints and permission: sagepub.com/journalsPermissions.nav DOI: 10.1177/0022427817727830 journals.sagepub.com/home/jrc" 5f34c96ddcf992e1b8660b5cb01e3c311b05023c,Towards Online Iris and Periocular Recognition Under Relaxed Imaging Constraints,"IEEE Trans. Image Processing, 2013 Towards Online Iris and Periocular Recognition under Relaxed Imaging Constraints Chun-Wei Tan, Ajay Kumar" 5f71adb3df33e1dac408e1c211043aa95e75988c,A Novel Characterization of the Alternative Hypothesis Using Kernel Discriminant Analysis for LLR-Based Speaker Verification,"Computational Linguistics and Chinese Language Processing Vol. 12, No. 3, September 2007, pp. 255-272 255 © The Association for Computational Linguistics and Chinese Language Processing A Novel Characterization of the Alternative Hypothesis Using Kernel Discriminant Analysis for LLR-Based Speaker Verification Yi-Hsiang Chao∗+ , Hsin-Min Wang∗ and Ruei-Chuan Chang∗+" 5fac23560b5ba4d45045f1edd837ed4bb6c1f5ca,Optimization of a Face Verification System using Bayesian Screening Techniques.,"OPTIMIZATION OF A FACE VERIFICATION SYSTEM USING BAYESIAN SCREENING TECHNIQUES Raquel Montes Diez, Cristina Conde, Ángel Serrano, Licesio J. Rodríguez-Aragón, Enrique Cabello Universidad Rey Juan Carlos (URJC) Escuela Superior de Ciencias Experimentales y Tecnología (ESCET) Face Recognition & Artificial Vision Group (FRAV) C/ Tulipán, s/n. Móstoles E-29833, Madrid, Spain {r.montes, cristina.conde, aserranos, ljrodriguez, http://frav.escet.urjc.es/ the 150 most" 5f3a513351a75f4eb86dd57e1651e33691c62417,Gender Recognition via Face Area Analysis, 5f0f8c9acc3e8eb50ca6e7d9c33cf3d9a8a54985,Structured Inhomogeneous Density Map Learning for Crowd Counting,"Structured Inhomogeneous Density Map Learning for Crowd Counting Hanhui Li, Xiangjian He, Hefeng Wu, Saeed Amirgholipour Kasmani, Ruomei Wang, Xiaonan Luo, Liang Lin" 5fa6e4a23da0b39e4b35ac73a15d55cee8608736,RED-Net: A Recurrent Encoder–Decoder Network for Video-Based Face Alignment,"IJCV special issue (Best papers of ECCV 2016) manuscript No. (will be inserted by the editor) RED-Net: A Recurrent Encoder-Decoder Network for Video-based Face Alignment Xi Peng · Rogerio S. Feris · Xiaoyu Wang · Dimitris N. Metaxas Submitted: April 19 2017 / Revised: December 12 2017" 5feb32a73dd1bd9e13f84a7b3344497a5545106b,FastText.zip: Compressing text classification models,"Under review as a conference paper at ICLR 2017 FASTTEXT.ZIP: COMPRESSING TEXT CLASSIFICATION MODELS Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Herv´e J´egou & Tomas Mikolov Facebook AI Research" 5f5906168235613c81ad2129e2431a0e5ef2b6e4,A Unified Framework for Compositional Fitting of Active Appearance Models,"Noname manuscript No. (will be inserted by the editor) A Unified Framework for Compositional Fitting of Active Appearance Models Joan Alabort-i-Medina · Stefanos Zafeiriou Received: date / Accepted: date" 5f769ba95ffea0ce76ac9d8e7cd47e2d1c91e1bf,Localizing antipodal grasps in point clouds,"Localizing antipodal grasps in point clouds Andreas ten Pas and Robert Platt" 5f0e9cc18374a670dfea4698424c9d48494f3093,Online Domain Adaptation for Multi-Object Tracking,"GAIDON & VIG: ONLINE DOMAIN ADAPTATION FOR MULTI-OBJECT TRACKING Online Domain Adaptation for Multi-Object Tracking Computer Vision Group Xerox Research Centre Europe Meylan, France Adrien Gaidon Eleonora Vig" 5fdb3533152f9862e3e4c2282cd5f1400af18956,A Variational U-Net for Conditional Appearance and Shape Generation,"A Variational U-Net for Conditional Appearance and Shape Generation Patrick Esser∗, Ekaterina Sutter∗, Bj¨orn Ommer Heidelberg Collaboratory for Image Processing IWR, Heidelberg University, Germany" 5ffd74d2873b7cba2cbc5fd295cc7fbdedca22a2,The Cityscapes Dataset,"The Cityscapes Dataset Marius Cordts1,2 Mohamed Omran3 Rodrigo Benenson3 Sebastian Ramos1,4 Uwe Franke1 Timo Scharw¨achter1,2 Markus Enzweiler1 Stefan Roth2 Bernt Schiele3 Daimler AG R&D, 2TU Darmstadt, 3MPI Informatics, 4TU Dresden www.cityscapes-dataset.net" 5f6116b6e5f21da66a304e9f59f3e224e188caef,Behavior Is Everything: Towards Representing Concepts with Sensorimotor Contingencies,"Behavior is Everything – Towards Representing Concepts with Sensorimotor Contingencies Nicholas Hay, Michael Stark, Alexander Schlegel, Carter Wendelken, Dennis Park, Eric Purdy, Tom Silver, D. Scott Phoenix, and Dileep George Vicarious AI, San Francisco, CA, USA" 5f7354634e13c9fad64163d53beb0a8eb5df30e1,Sketch-Based Image Retrieval: Benchmark and Bag-of-Features Descriptors,"Sketch-Based Image Retrieval: Benchmark nd Bag-of-Features Descriptors Mathias Eitz, Kristian Hildebrand, Tamy Boubekeur and Marc Alexa" 5f943f9bfe3154fbd368034903ea11620d2946eb,Cascade Category-Aware Visual Search,"MiniManuscript.com The one stop shop for academic literature. 07:00am 8 Dec, 2018 Cascade Category-Aware Visual Search. Authors Zhang S, Tian Q, Huang Q, Gao W, Rui Y Volume Issue Pages" 5fc621cdef59c38ef898a2adc2b4472a8396119a,Elephant Panda Lion Dolphin Dog Monkey ... ... Classes Elephant Dolphin Lion Classifier Training Data Synthesizing,"Synthesizing Samples for Zero-shot Learning IJCAI Anonymous Submission 2625" 5f96af88dfef2bff4ed8a49ceca909efb701d1d5,Addressing the Dark Side of Vision Research: Storage,"Addressing the Dark Side of Vision Research: Storage Vishakha Gupta-Cledat Intel Labs Luis Remis Intel Labs Christina R. Strong Intel Labs" 5fc664202208aaf01c9b62da5dfdcd71fdadab29,Automatic Face Recognition from Video,rXiv:1504.05308v1 [cs.CV] 21 Apr 2015 5f58bf2c25826cb6ee927a1461aa72bd623157ff,Tasting Families of Features for Image Classification,"ICCV 2011 Submission #549. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. Tasting Families of Features for Image Classification Anonymous ICCV submission Paper ID 549" 5fd147f57fc087b35650f7f3891d457e4c745d48,Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields,"Published as a conference paper at ICLR 2018 COULOMB GANS: PROVABLY OPTIMAL NASH EQUI- LIBRIA VIA POTENTIAL FIELDS Thomas Unterthiner1 Bernhard Nessler1 Calvin Seward1,2 Günter Klambauer1 Martin Heusel1 Hubert Ramsauer1 Sepp Hochreiter1 LIT AI Lab & Institute of Bioinformatics, Johannes Kepler University Linz, Austria Zalando Research, Mühlenstraße 25, 10243 Berlin, Germany" 5fff61302adc65d554d5db3722b8a604e62a8377,Additive Margin Softmax for Face Verification,"Additive Margin Softmax for Face Verification Feng Wang UESTC Weiyang Liu Georgia Tech Haijun Liu UESTC Jian Cheng UESTC haijun" 5fa1724a79a9f7090c54925f6ac52f1697d6b570,The Development of Multimodal Lexical Resources,"Proceedings of the Workshop on Grammar and Lexicon: Interactions and Interfaces, pages 41–47, Osaka, Japan, December 11 2016." 5fa587381a9e4308163b3a5395985f0375c3cf7d,Deep Extreme Cut: From Extreme Points to Object Segmentation,"Deep Extreme Cut: From Extreme Points to Object Segmentation K.-K. Maninis* S. Caelles∗ Computer Vision Lab, ETH Z¨urich, Switzerland J. Pont-Tuset L. Van Gool Figure 1. Example results of DEXTR: The user provides the extreme clicks for an object, and the CNN produces the segmented masks." 5f534bacc658f620a15b5647adecb0ea813286c8,Reliable object detection and segmentation using inpainting,"Reliable Object Detection and Segmentation using Inpainting Ji Hoon Joung, M. S. Ryoo, Sunglok Choi, and Sung-Rak Kim" 5fcde9236d654a0f92a76c1a3f07c0cad954985c,Personality-Dependent Referring Expression Generation,"Personality-dependent Referring Expression Generation Ivandr´e Paraboni, Danielle Sampaio Monteiro, and Alex Gwo Jen Lan University of S˜ao Paulo, School of Arts, Sciences and Humanities, S˜ao Paulo, Brazil" 5f5164cf998a10d2bef37741adb562ab07fac413,A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/TPAMI.2016.2545669, IEEE Transactions on Pattern Analysis and Machine Intelligence A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs Zifeng Wu, Yongzhen Huang, Liang Wang, Xiaogang Wang, and Tieniu Tan" d904f945c1506e7b51b19c99c632ef13f340ef4c,0 ° 15 ° 30 ° 45 ° 60 ° 75 ° 90 °,"A scalable 3D HOG model for fast object detection and viewpoint estimation Marco Pedersoli Tinne Tuytelaars KU Leuven, ESAT/PSI - iMinds Kasteelpark Arenberg 10 B-3001 Leuven, Belgium" d9f9b35800da98e7bde1966225b8734d2ca5e94f,ASSESSMENT OF THE EFFICIENCY OF CORRELATION COEFFICIENT FOR FACE AUTHENTICATION,"International Journal of Advance Research In Science And Engineering http://www.ijarse.com IJARSE, Vol. No.3, Issue No.8, August 2014 ISSN-2319-8354(E) ASSESSMENT OF THE EFFICIENCY OF CORRELATION COEFFICIENT FOR FACE AUTHENTICATION Sheela Shankar, 2V.R Udupi Department of Electronics & Communication Engg, KLE Dr. M. S. Sheshgiri CET, Udyambag, Belgaum, (India) Department of Electronics and Communication Engg, Gogte Institute of Technology, Belgaum, (India)" d9984fac91cb4f469cf36f140b6c8c07c45afe6f,Face Recognition Using LAPP Algorithm,"International Journal of Engineering Trends and Applications (IJETA) – Volume 2 Issue 5, Sep-Oct 2015 RESEARCH ARTICLE OPEN ACCESS Face Recognition Using LAPP Algorithm Priyanka Kumbham [1], Dr. G. R. Sakthidharan[2] M.Tech Student [1], Associate Professor [2] Department of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Telangana – India" d950c5b7be9e46cba46f6811845c9f45189e900c,Correlation Method Based PCA Subspace using Accelerated Binary Particle Swarm Optimization for Enhanced Face Recognition,"ISSN: 2321-8169 International Journal on Recent and Innovation Trends in Computing and Communication Volume: 4 Issue: 9 69- 72 _______________________________________________________________________________________________ Correlation Method Based PCA Subspace using Accelerated Binary Particle Swarm Optimization for Enhanced Face Recognition Ms. Navpreet Kaur M.Tech Scholar Ms. Rasleen Kaur Assistant professor Depar tmen t of Computer Scien ce An d Engin eer ing, Depar tmen t of Computer Scien ce An d Engin eer ing Global Institute of Management And Emerging Technologies,Amritsar,punjab,India. Global Institute of Management And Emerging Technologies,Amritsar,punjab,India." d98c7dd22a7927b377e523a3a36408729a523f42,Extended Abstract Object Recognition via Robust Learning, d9433ba8bc58a94dffbfebe85e1aca1b6229d6c4,Audio‐Visual Speaker Tracking,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,900 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." d930d20ba42a5d868dd78dd73bac0f72110e0bc5,Multivariate Shape Modeling and Its Application to Characterizing Abnormal Amygdala Shape in Autism,"Multivariate Shape Modeling and Its Application to Characterizing Abnormal Amygdala Shape in Autism Moo K. Chunga,b∗,Keith J. Worsleyd, Brendon, M. Nacewiczb, Kim M. Daltonb, Richard J. Davidsonb,c Department of Biostatistics and Medical Informatics Waisman Laboratory for Brain Imaging and Behavior Department of Psychology and Psychiatry University of Wisconsin, Madison, WI 53706, USA dDepartment of Statistics University of Chicago, Chicago, IL 60637, USA September 22, 2009" d944ff789af84cecc0a913da964e017408687d62,"Image Parsing: Segmentation, Detection, and Recognition","Image Parsing: Segmentation, Detection, and Recognition. Zhuowen Tu Department of Statistics Alex Chen Department of Statistics University of California at Los Angeles University of California at Los Angeles Los Angeles, CA 90095 Los Angeles, CA 90095 Alan Yuille Department of Statistics Song-Chun Zhu Department of Statistics University of California at Los Angeles University of California at Los Angeles Los Angeles, CA 90095 Los Angeles, CA 90095 In International Conference of Computer Vision. Nice, France. pp 18-25. October. 2003." d9ee64038aea3a60120e9f7de16eb4130940a103,Message Passing Multi-Agent GANs,"Message Passing Multi-Agent GANs Arnab Ghosh∗, Viveka Kulharia∗, Vinay Namboodiri IIT Kanpur" d9f0640716ec25278e6f1a4fdda5596660504c54,A Correlated Parts Model for Object Detection in Large 3D Scans,"EUROGRAPHICS 2013 / I. Navazo, P. Poulin (Guest Editors) Volume 32 (2013), Number 2 A Correlated Parts Model for Object Detection in Large 3D Scans M. Sunkel1, S. Jansen1, M. Wand1,2, H.-P. Seidel1 MPI Informatik Saarland University Figure 1: Based on sparse user annotations a shape model is learned. The detected instances are transformed into descriptors for the second hierarchy level. Hierarchical detections shown on the right are obtained using only the example marked red." d9cc8bc5c4a4b29ab40f75b721bd9e5140d2baf6,Object Detection for Crime Scene Evidence Analysis Using Deep Learning,"Object Detection for Crime Scene Evidence Analysis Using Deep Learning Surajit Saikia1,2(B), E. Fidalgo1,2, Enrique Alegre1,2, nd Laura Fern´andez-Robles2,3 Department of Electrical, Systems and Automation, University of Le´on, Le´on, Spain INCIBE (Spanish National Cybersecurity Institute), Le´on, Spain Department of Mechanical, Informatics and Aerospace Engineering, University of Le´on, Le´on, Spain" d9fe0b257ec50a12ba1af749fad56a6f705d16a4,HIGH FREQUENCY REGIONS FOR FACE RECOGNITION,"The International Journal of Multimedia & Its Applications (IJMA) Vol.4, No.1, February 2012 FEATURE IMAGE GENERATION USING LOW, MID AND HIGH FREQUENCY REGIONS FOR FACE RECOGNITION Vikas Maheshkar1, Sushila Kamble2, Suneeta Agarwal3 and Vinay Kumar Srivastava4 -3Department of Computer Science and Engineering, MNNIT, Allahabad Department of Electronics & Communication Engineering, MNNIT, Allahabad" d929534024614e3153c986e55d758ea7471d3fff,How Not to Evaluate a Developmental System,"How Not to Evaluate a Developmental System Frederick Shic and Brian Scassellati" d9bc16dcbc13502389704e4a0bdd8ee7af618069,Learning pullback HMM distances for action recognition,Learning pullback HMM distances for action recognition d94b37958657aa703d8a3d02a66ee251b4c3f597,Learning deep features from body and parts for person re-identification in camera networks,"Zhang and Si EURASIP Journal on Wireless Communications and Networking (2018) 2018:52 https://doi.org/10.1186/s13638-018-1060-2 RESEARCH Open Access Learning deep features from body and parts for person re-identification in camera networks Zhong Zhang1,2* and Tongzhen Si1,2" d94d7ff6f46ad5cab5c20e6ac14c1de333711a0c,Face Album: Towards automatic photo management based on person identity on mobile phones,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" d94c7a89adf6f568bbe1510910850d5083a58b4f,Deep Cross Modal Learning for Caricature Verification and Identification (CaVINet),"Deep Cross Modal Learning for Caricature Verification and Identification(CaVINet) https://lsaiml.github.io/CaVINet/ Jatin Garg∗ Indian Institute of Technology Ropar Himanshu Tolani∗ Indian Institute of Technology Ropar Skand Vishwanath Peri∗ Indian Institute of Technology Ropar Narayanan C Krishnan Indian Institute of Technology Ropar" d9810786fccee5f5affaef59bc58d2282718af9b,Adaptive Frame Selection for Enhanced Face Recognition in Low-Resolution Videos,"Adaptive Frame Selection for Enhanced Face Recognition in Low-Resolution Videos Raghavender Reddy Jillela Thesis submitted to the College of Engineering and Mineral Resources t West Virginia University in partial fulfillment of the requirements for the degree of Master of Science Electrical Engineering Arun Ross, PhD., Chair Xin Li, PhD. Donald Adjeroh, PhD. Lane Department of Computer Science and Electrical Engineering Morgantown, West Virginia Keywords: Face Biometrics, Super-Resolution, Optical Flow, Super-Resolution using Optical Flow, Adaptive Frame Selection, Inter-Frame Motion Parameter, Image Quality, Image-Level Fusion, Score-Level Fusion Copyright 2008 Raghavender Reddy Jillela" d9c4b1ca997583047a8721b7dfd9f0ea2efdc42c,Learning Inference Models for Computer Vision,Learning Inference Models for Computer Vision d97c4da8cbc6b3c5de06eb457acfdf5c7241a522,Monocular Depth Estimation by Learning from Heterogeneous Datasets,"Monocular Depth Estimation by Learning from Heterogeneous Datasets Akhil Gurram1,2, Onay Urfalioglu2, Ibrahim Halfaoui2, Fahd Bouzaraa2 and Antonio M. L´opez1" d9fda0030ca349da7b1dafca015bea95a6aabea0,ISA2: Intelligent Speed Adaptation from Appearance,"ISA2: Intelligent Speed Adaptation from Appearance Carlos Herranz-Perdiguero1 and Roberto J. L´opez-Sastre1" d97e7799142e2c66b63fe63bc52632fdf305f313,Lanczos Vectors versus Singular Vectors for Effective Dimension Reduction,"Lanczos Vectors versus Singular Vectors for Effective Dimension Reduction Jie Chen and Yousef Saad" d914c53cdf26acc64259d381fbd45c4e150633ee,Pedestrian Tracking in the Compressed Domain Using Thermal Images,"Pedestrian Tracking in the Compressed Domain Using Thermal Images Ichraf Lahouli1,2,3, Robby Haelterman1, Zied Chtourou2, Geert De Cubber1, nd Rabah Attia3 Royal Military Academy, Brussels, Belgium VRIT Lab, Military Academy of Tunisia, Nabeul, Tunisia SERCOM Lab, Tunisia Polytechnic School, La Marsa, Tunisia" d9bad7c3c874169e3e0b66a031c8199ec0bc2c1f,"It All Matters: Reporting Accuracy, Inference Time and Power Consumption for Face Emotion Recognition on Embedded Systems","It All Matters: Reporting Accuracy, Inference Time and Power Consumption for Face Emotion Recognition on Embedded Systems Jelena Milosevic Institute of Telecommunications, TU Wien Andrew Forembsky Movidius an Intel Company Dexmont Pe˜na Movidius an Intel Company David Moloney Movidius an Intel Company Miroslaw Malek ALaRI, Faculty of Informatics, USI" d92581c452e780710938cfbfa0f1ca2ffccc5d5e,Facial Feature Extraction Based on Local Color and Texture for Face Recognition using Neural Network,"International Journal of Science and Engineering Applications Volume 2 Issue 4, 2013, ISSN-2319-7560 (Online) Facial Feature Extraction Based on Local Color and Texture for Face Recognition using Neural Network S.Cynthia Christabel M.Annalakshmi Sethu Institute of Technology. Sethu Institute of Technology. Kariapatti. Kariapatti. Mr.D.Prince Winston Aruppukottai." d930ec59b87004fd172721f6684963e00137745f,Face Pose Estimation using a Tree of Boosted Classifiers,"Face Pose Estimation using a Tree of Boosted Classifiers Javier Cruz Mota Project Assistant: Julien Meynet Professor: Jean-Philippe Thiran Signal Processing Institute, ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL) September 11, 2006" d951ff5f378b2a5f878423029123ad6b3491b444,Foveal Vision for Instance Segmentation of Road Images,"Foveal Vision for Instance Segmentation of Road Images Benedikt Ortelt1, Christian Herrmann2,3, Dieter Willersinn2, J¨urgen Beyerer2,3 Robert Bosch GmbH, Leonberg, Germany Fraunhofer IOSB, Karlsruhe, Germany Karlsruhe Institute of Technology KIT, Vision and Fusion Lab, Karlsruhe, Germany Keywords: Instance Segmentation, Multi-Scale Analysis, Foveated Imaging, Cityscapes." 9679d15c6699b521740408b2e899c03af89390ac,ARTICULATED BODY TRACKING AND HUMAN ACTION ANALYSIS,"DIMENSIONALITY REDUCTION FOR 3D ARTICULATED BODY TRACKING AND HUMAN ACTION ANALYSIS Leonid Raskin Research Supervisors: Prof. Ehud Rivlin, Dr. Michael Rudzsky Prof. Michael Lindenbaum Submitted in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy Technion IIT - Israel Institute of Technology Haifa, Israel March 2010 (cid:176) Copyright by Leonid Raskin, 2010 Technion - Computer Science Department - Ph.D. Thesis PHD-2010-11 - 2010" 9696b172d66e402a2e9d0a8d2b3f204ad8b98cc4,Region-Based Facial Expression Recognition in Still Images,"J Inf Process Syst, Vol.9, No.1, March 2013 pISSN 1976-913X eISSN 2092-805X Region-Based Facial Expression Recognition in Still Images Gawed M. Nagi*, Rahmita Rahmat*, Fatimah Khalid* and Muhamad Taufik*" 96dfa2a7630fc6800ba8a546df526b8174f54b5c,Appearance-Based Facial Recognition Using Visible and Thermal Imagery : A Comparative Study ∗,"Appearance-Based Facial Recognition Using Visible and Thermal Imagery: A Comparative Study ∗ Andrea Selinger† Diego A. Socolinsky‡ Equinox Corporation 07 East Redwood Street Equinox Corporation 9 West 57th Street New York, NY 10019 Baltimore, MD 21202" 96e9bc6b54d1c79406cf37ae45fd35ef04d647c6,A Fully Automated System for Sizing Nasal PAP Masks Using Facial Photographs,"A Fully Automated System for Sizing Nasal PAP Masks Using Facial Photographs Benjamin Johnston Student Member, IEEE and Philip de Chazal Senior Member, IEEE" 96a7f2faf4baa09184deb458a03146805d62beed,Passive Three Dimensional Face Recognition Using Iso-Geodesic Contours and Procrustes Analysis,"Int J Comput Vis (2013) 105:87–108 DOI 10.1007/s11263-013-0631-2 Passive Three Dimensional Face Recognition Using Iso-Geodesic Contours and Procrustes Analysis Sina Jahanbin · Rana Jahanbin · Alan C. Bovik Received: 11 November 2011 / Accepted: 11 May 2013 / Published online: 19 June 2013 © Springer Science+Business Media New York 2013" 96390f95a73a6bd495728b6cd2a97554ef187f76,Pan Olympus : Sensor Privacy through Utility Aware,"Proceedings on Privacy Enhancing Technologies ..; .. (..):1–21 Nisarg Raval, Ashwin Machanavajjhala, and Jerry Pan Olympus: Sensor Privacy through Utility Aware Obfuscation" 964e43f4983a42ef3790c265bdce42c1fce56d79,A virtual environment tool for benchmarking face analysis systems,"A Virtual Environment Tool for Benchmarking Face Analysis Systems Mauricio Correa+,*, Javier Ruiz-del-Solar+,*, Rodrigo Verschae* +Department of Electrical Engineering, Universidad de Chile *Advanced Mining Technology Center, Universidad de Chile {macorrea," 966541dca2aa4fe5ddd1a371a1c999073fa0d737,Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network,"Article Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network Husan Vokhidov, Hyung Gil Hong, Jin Kyu Kang, Toan Minh Hoang and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (H.V.); (H.G.H.); (J.K.K.); (T.M.H.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Academic Editor: Felipe Jimenez Received: 31 October 2016; Accepted: 14 December 2016; Published: 16 December 2016" 9691055b1fcbe626b5bce9d8d43903094a5c0339,Generating an item pool for translational social cognition research: methodology and initial validation.,"Behav Res (2015) 47:228–234 DOI 10.3758/s13428-014-0464-0 Generating an item pool for translational social cognition research: Methodology and initial validation Michael K. Keutmann & Samantha L. Moore & Adam Savitt & Ruben C. Gur Published online: 10 April 2014 # Psychonomic Society, Inc. 2014" 96f4a1dd1146064d1586ebe86293d02e8480d181,COMPARATIVE ANALYSIS OF RERANKING TECHNIQUES FOR WEB IMAGE SEARCH,"COMPARATIVE ANALYSIS OF RERANKING TECHNIQUES FOR WEB IMAGE SEARCH Suvarna V. Jadhav1, A.M.Bagade2 ,2Department of Information Technology, Pune Institute of Computer Technology, Pune,( India)" 9645e8b4829c04879a642d8dd6b3cdf5cf264afb,Finding Beans in Burgers: Deep Semantic-Visual Embedding with Localization,"Finding beans in burgers: Deep semantic-visual embedding with localization Martin Engilberge1,2, Louis Chevallier2, Patrick P´erez2, Matthieu Cord1 Sorbonne universit´e, Paris, France 2Technicolor, Cesson S´evign´e, France {martin.engilberge," 9626bcb3fc7c7df2c5a423ae8d0a046b2f69180c,A deep learning approach for action classification in American football video sequences,"UPTEC STS 17033 Examensarbete 30 hp November 2017 A deep learning approach for ction classification in American football video sequences Jacob Westerberg" 96fdc0131dc80ffa6d7b9c526e07f080414c54ec,1 Paying More A ention to Saliency : Image Captioning with Saliency and Context A ention,"Paying More A(cid:130)ention to Saliency: Image Captioning with Saliency and Context A(cid:130)ention MARCELLA CORNIA, University of Modena and Reggio Emilia LORENZO BARALDI, University of Modena and Reggio Emilia GIUSEPPE SERRA, University of Udine RITA CUCCHIARA, University of Modena and Reggio Emilia Image captioning has been recently gaining a lot of a(cid:138)ention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural Networks to generate the corresponding captions. At the same time, signi(cid:128)cant research e(cid:130)ort has been dedicated to the development of saliency prediction models, which an predict human eye (cid:128)xations. Even though saliency information could be useful to condition an image aptioning architecture, by providing an indication of what is salient and what is not, research is still struggling to incorporate these two techniques. In this work, we propose an image captioning approach in which a generative recurrent neural network can focus on di(cid:130)erent parts of the input image during the generation of the caption, by exploiting the conditioning given by a saliency prediction model on which parts of the image re salient and which are contextual. We show, through extensive quantitative and qualitative experiments on large scale datasets, that our model achieves superior performances with respect to captioning baselines with nd without saliency, and to di(cid:130)erent state of the art approaches combining saliency and captioning. CCS Concepts: •Computing methodologies →Scene understanding; Natural language generation; Additional Key Words and Phrases: saliency, visual saliency prediction, image captioning, deep learning." 96f0da034d090a3ecadd0fb92333bb681f23ab14,Temporal-Spatial Mapping for Action Recognition,"Temporal-Spatial Mapping for Action Recognition Xiaolin Song, Cuiling Lan, Wenjun Zeng, Junliang Xing, Jingyu Yang, and Xiaoyan Sun" 96788880589a514c3ae9de29695c0127d6e76b8f,Attention-Based Multimodal Fusion for Video Description,"Attention-Based Multimodal Fusion for Video Description Chiori Hori Takaaki Hori Teng-Yok Lee Kazuhiro Sumi∗ John R. Hershey Tim K. Marks Mitsubishi Electric Research Laboratories (MERL) {chori, thori, tlee, sumi, hershey," 96813c14f3de1b8f7472caff7a99b4145267f25c,Argus: the digital doorman,"A p p l i c a t i o n s : C o m p u t e r V i s i o n Argus: The Digital Doorman Rahul Sukthankar, Just Research and Carnegie Mellon University Robert Stockton, Just Research W hen you’ve visited someone in a large apartment or office complex, chances are that a security guard in the lobby granted you access. Perhaps over time, the guard has learned to associate you with the person you plan to visit and immediately notifies that person over the uilding intercom when you arrive. Argus, named after the vigilant watchman from Greek mythology, is an auto- mated version of such a security guard: a system for auto- matic visitor identification. We successfully implemented nd tested Argus at Just Research. To detect visitors, Argus’s digital camera photographs the building entrance at regular intervals, and a motion detection algorithm identifies potential scenes containing visitors. Using a neural-network-based face detector,1 Argus extracts faces from these images. A memory-based face recognition system2 examines these faces and at-" 9606b1c88b891d433927b1f841dce44b8d3af066,Principal Component Analysis with Tensor Train Subspace,"Principal Component Analysis with Tensor Train Subspace Wenqi Wang, Vaneet Aggarwal, and Shuchin Aeron" 96881897605eb3d9575c5379b29083b793a24bd2,Application of bidirectional two-dimensional principal component analysis to curvelet feature based face recognition,"Application of Bidirectional Two-dimensional Principal Component Analysis to Curvelet Feature Based Face Recognition Abdul A. Mohammed, Q. M. Jonathan Wu, Maher A. Sid-Ahmed Department of Electrical and Computer Engineering Windsor, Ontario, Canada {mohammea, jwu," 9634348d3bc7b86d0b644f6c14ab0c4294341905,Investigating Redundancy in Emoji Use: Study on a Twitter Based Corpus,"Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 118–126 Copenhagen, Denmark, September 7–11, 2017. c(cid:13)2017 Association for Computational Linguistics" 968f472477a8afbadb5d92ff1b9c7fdc89f0c009,Firefly-based Facial Expression Recognition: Extended Abstract,Firefly-based Facial Expression Recognition 968c62bb2927ca300ef953644e652ba7d2c2e5e6,Learning person-object interactions for action recognition in still images,"Learning person-object interactions for ction recognition in still images Vincent Delaitre∗ ´Ecole Normale Sup´erieure Josef Sivic* INRIA Paris - Rocquencourt Ivan Laptev* INRIA Paris - Rocquencourt" 96e7142ab905c54c033696ac3692e85692c43bf3,Sparse Illumination Learning and Transfer for Single-Sample Face Recognition with Image Corruption and Misalignment,"Noname manuscript No. (will be inserted by the editor) Sparse Illumination Learning and Transfer for Single-Sample Face Recognition with Image Corruption and Misalignment Liansheng Zhuang · Tsung-Han Chan · Allen Y. Yang · S. Shankar Sastry · Yi Ma Received: date / Accepted: date" a726858df7c9503116504206577a938df1a67815,Unsupervised Vehicle Re-Identification using Triplet Networks,"Unsupervised Vehicle Re-Identification using Triplet Networks Pedro Antonio Mar´ın-Reyes Andrea Palazzi University of Las Palmas de Gran Canaria University of Modena and Reggio Emilia Luca Bergamini Simone Calderara University of Modena and Reggio Emilia University of Modena and Reggio Emilia Javier Lorenzo-Navarro Rita Cucchiara University of Las Palmas de Gran Canaria University of Modena and Reggio Emilia" a7eee3222623778294461102d0dc770d4e09a7c5,A novel fusion-based method for expression-invariant gender classification,"978-1-4244-2354-5/09/$25.00 ©2009 IEEE ICASSP 2009" a71106ef95103276fac010c10291f6dd6fd9d9f5,Social status level and dimension interactively influence person evaluations indexed by P300s.,"ISSN: 1747-0919 (Print) 1747-0927 (Online) Journal homepage: http://www.tandfonline.com/loi/psns20 Social status level and dimension interactively influence person evaluations indexed by P300s Ivo Gyurovski, Jennifer Kubota, Carlos Cardenas-Iniguez & Jasmin Cloutier To cite this article: Ivo Gyurovski, Jennifer Kubota, Carlos Cardenas-Iniguez & Jasmin Cloutier (2017): Social status level and dimension interactively influence person evaluations indexed by To link to this article: http://dx.doi.org/10.1080/17470919.2017.1326400 Accepted author version posted online: 02 May 2017. Published online: 15 May 2017. Submit your article to this journal Article views: 11 View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=psns20 Download by: [University of Chicago Library] Date: 22 May 2017, At: 09:19" a75ee7f4c4130ef36d21582d5758f953dba03a01,Human face attributes prediction with Deep Learning,"DD2427 Final Project Report Mohamed Abdulaziz Ali Haseeb DD2427 Final Project Report Human face attributes prediction with Deep Learning Mohamed Abdulaziz Ali Haseeb" a77d9e54bf6917e56054c2b70836b535dcfbcbac,Semi-supervised learning for image classification,"Semi-Supervised Learning for Image Classification A dissertation for the degree of Doktor-Ingenieur (Dr.-Ing.) pproved by Saarland University Computer Science presented by Sandra Ebert Dipl.-Inform. orn in Leipzig, Germany Saarbrücken, 2012" a7e8ce268c16ea8c10e4c5ccd8d6e53702423faa,The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment,"The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment Angus Galloway∗, Graham W. Taylor∗, Aaron Ramsay†, Medhat Moussa∗ School of Engineering University of Guelph Guelph, ON, Canada {gallowaa, gwtaylor, Department of Agriculture and Fisheries Government of PEI Montague, PEI, Canada" a7066c13ba21817abcf8ff955740493adf95b02c,Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks,"Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks Stefan Milz 1 * Martin Simon 1 * Kai Fischer 1 * Maximillian Poepperl 1" a7e78f80e0e37d0c17bc09058c27996e32e4454e,UNAM at SemEval-2018 Task 10: Unsupervised Semantic Discriminative Attribute Identification in Neural Word Embedding Cones,"Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 977–984 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics" a76d471a409904c084746a56334453450f1c6c1a,Study of the Changing Trends in Facial Expression Recognition,"Study of the Changing Trends in Facial Expression Recognition {tag} {/tag} International Journal of Computer Applications © 2011 by IJCA Journal Number 5 - Article 3 Year of Publication: 2011 Authors: Dr. S. Ravi Mahima S 10.5120/2509-3397" a73a16203b644353a287a4759bc951450e67d700,BodyNet: Volumetric Inference of 3D Human Body Shapes,"BodyNet: Volumetric Inference of D Human Body Shapes G¨ul Varol1,* Ersin Yumer2,‡ Duygu Ceylan2 Bryan Russell2 Jimei Yang2 Ivan Laptev1,* Cordelia Schmid1,† Inria, France Adobe Research, USA" a7e274db8f1389b95469588995f18c1c42b62534,VideoStory Embeddings Recognize Events when Examples are Scarce, a7a1d3036c542824f2c681c3bf08f5b85f05d9e9,A Fast and Precise HOG-Adaboost Based Visual Support System Capable to Recognize Pedestrian and Estimate Their Distance,"A fast and precise HOG-Adaboost based based visual support system capable to recognize Pedestrian and estimate their distance. Yokohama City University, Graduate School of Nanobioscience, 22-2 Seto Kanazawa-ku, 236-0027 Yokohama, Japan Takahisa Kishino1, Sun Zhe1,Ruggero Micheletto1" a7663528eb6c9b79a68b94800e30da952c0b6bb2,IFQ-Net : Integrated Fixed-point Quantization Networks for Embedded Vision,"IFQ-Net: Integrated Fixed-point Quantization Networks for Embedded Vision Hongxing Gao, Wei Tao, Dongchao Wen Canon Information Technology (Beijing) Co., LTD Tse-Wei Chen, Kinya Osa, Masami Kato Device Technology Development Headquarters, Canon Inc." a7d23c699a5ae4ad9b8a5cbb8c38e5c3b5f5fb51,A Summary of literature review : Face Recognition,"Postgraduate Annual Research Seminar 2007 (3-4 July 2007) A Summary of literature review : Face Recognition Kittikhun Meethongjan & Dzulkifli Mohamad Faculty of Computer Science & Information System, University Technology of Malaysia, 81310 Skudai, Johor, Malaysia." a759570e6ef674cd93068020c2e6bd036961f7c6,SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set,"SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set William N. Havard1, Laurent Besacier1, Olivier Rosec2 Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, F-38000 Grenoble, France Voxygen, France" a77091cee259e37536196238096bc1753b4c0027,FIELD ESTIMATION USING BRIGHTNESS CONSTANCY ASSUMPTION AND EPIPOLAR GEOMETRY CONSTRAINT,"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume II-1, 2014 ISPRS Technical Commission I Symposium, 17 – 20 November 2014, Denver, Colorado, USA ontribution has been peer-reviewed. The double-blind peer-review was conducted on the basis of the full paper.doi:10.5194/isprsannals-II-1-9-20149" a7bfb6426359140a0bc0c84741ad9a3ac83eff04,Object-Level Context Modeling For Scene Classification with Context-CNN,"Object-Level Context Modeling For Scene Classification with Context-CNN Syed Ashar Javed1 and Anil Kumar Nelakanti2 IIIT Hyderabad, 2Amazon" a75db530b5a905c87aba6b65676809b35f9614f5,Dynamic Eye Gaze Tracking for Foveated Rendering and Retinal Blur,"Dynamic Eye Gaze Tracking for Foveated Rendering and Retinal Blur Kushagr Gupta, Suleman Kazi, Terry Kong" a73bc57fb0aa429ba5f7f12b6d02e2c6274cabdd,A Superior Tracking Approach: Building a Strong Tracker through Fusion,"A Superior Tracking Approach: Building a Strong Tracker through Fusion Christian Bailer1, Alain Pagani1, and Didier Stricker1,2 German Research Center for Artificial Intelligence, Kaiserslautern, Germany University of Kaiserslautern, Germany" a764cba765648c6e36782b02393ea2eed5cd69c7,Contributions to large-scale learning for image classification. (Contributions à l'apprentissage grande échelle pour la classification d'images),"CONTRIBUTIONSTOLARGE-SCALELEARNINGFORIMAGECLASSIFICATIONZeynepAkataPhDThesisl’´EcoleDoctoraleMath´ematiques,SciencesetTechnologiesdel’Information,InformatiquedeGrenoble" a71e3cf566de457336aab9dd6a5f5d6282b4a6af,Visual Abstraction for Zero-Shot Learning, a705b6b6de4ed62891099cbe5734fb7d3d3044cc,Enhancing the retrieval performance by combing the texture and edge features,"Enhancing the retrieval performance by combing the (IJCSIS) International Journal of Computer Science and Information Security, Vol. XXX, No. XXX, 2010 texture and edge features Mohamed Eisa Amira Eletrebi Ebrahim Elhenawy Computer Science Department Computer Science Department Computer Science Department PortSaid University Mansoura University Zagazig University" a7664247a37a89c74d0e1a1606a99119cffc41d4,Modal Consistency based Pre-Trained Multi-Model Reuse,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) a70fa8af52e4cc32dae09e6e753f1dd3ec198327,Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer,"Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer Sujay Kumar Jauhar Microsoft Research AI Redmond, WA, USA Michael Gamon Microsoft Research AI Redmond, WA, USA Patrick Pantel∗ Facebook Inc. Seattle, WA, USA" a7152589980ec27375023d719eec6acc04b7d4fd,Generating Facial Expressions,"Generating Facial Expressions Jonathan Suit Georgia Tech" a7887d32c86cda13872c5408713b21a27d0fc17a,Detecting Drivable Area for Self-driving Cars: An Unsupervised Approach,"Detecting Drivable Area for Self-driving Cars: An Unsupervised Approach Ziyi Liu, Siyu Yu, Xiao Wang and Nanning Zheng∗ Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, P.R.China National Engineering Laboratory for Visual Information Processing and Applications, Xi’an Jiaotong University, Xi’an, Shannxi, P.R.China to locate road surface by using lane line," a7267bc781a4e3e79213bb9c4925dd551ea1f5c4,Proceedings of eNTERFACE 2015 Workshop on Intelligent Interfaces,"Proceedings of eNTERFACE’15 The 11th Summer Workshop on Multimodal Interfaces August 10th - September 4th, 2015 Numediart Institute, University of Mons Mons, Belgium" a702fc36f0644a958c08de169b763b9927c175eb,Facial expression recognition using Hough forest,"FACIAL EXPRESSION RECOGNITION USING HOUGH FOREST Chi-Ting Hsu1, Shih-Chung Hsu1, and Chung-Lin Huang1,2 . Department of Electrical Engineering, National Tsing-Hua University, Hsin-Chu, Taiwan Email: . Department of Applied Informatics and Multimedia, Asia University, Taichung, Taiwan" a760ce8baddf2da7946d2ed6f02ac3927f39a9da,Face Recognition Using a Unified 3D Morphable Model,"Face Recognition Using a Unified 3D Morphable Model Hu, G., Yan, F., Chan, C-H., Deng, W., Christmas, W., Kittler, J., & Robertson, N. M. (2016). Face Recognition Using a Unified 3D Morphable Model. In Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII (pp. 73-89). (Lecture Notes in Computer Science; Vol. 9912). Springer Verlag. DOI: 10.1007/978-3-319-46484-8_5 Published in: Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 016, Proceedings, Part VIII Document Version: Peer reviewed version Queen's University Belfast - Research Portal: Link to publication record in Queen's University Belfast Research Portal Publisher rights The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-46484-8_5 General rights Copyright for the publications made accessible via the Queen's University Belfast Research Portal is retained by the author(s) and / or other opyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The Research Portal is Queen's institutional repository that provides access to Queen's research output. Every effort has been made to" 5ad88a16e2efe9bb67c20cdbd9b003ffb79c12ef,Real-Time Video Event Detection in Crowded Scenes using MPEG Derived Features : a Multiple,"Elsevier Editorial System(tm) for Pattern Recognition Letters Manuscript Draft Manuscript Number: PRLETTERS-D-13-00222R2 Title: Real-Time Video Event Detection in Crowded Scenes using MPEG Derived Features: a Multiple Instance Learning Approach Article Type: Special Issue: SIPRCA Keywords: Event Detection; Crowded Scene; Multiple Instance Learning; MPEG domain; Sparse Approximation; Random Matrix; Traffic Surveillance; Naive Bayes Model Corresponding Author: Mr. Jingxin Xu, M.D Corresponding Author's Institution: Queensland University of Technology First Author: Jingxin Xu, M.D Order of Authors: Jingxin Xu, M.D; Simon Denman, PhD; Vikas Reddy, PhD; Clinton Fookes, PhD; Sridha Sridhran, PhD" 5a14209a5241877f92743d04282598f41fd3e50f,From BoW to CNN: Two Decades of Texture Representation for Texture Classification,"From BoW to CNN: Two Decades of Texture Representation for Texture Classification Li Liu 1,2 · Jie Chen 2 · Paul Fieguth 3 · Guoying Zhao 2 · Rama Chellappa 4 · Matti Pietik¨ainen 2 Received: date / Accepted: date" 5a3da29970d0c3c75ef4cb372b336fc8b10381d7,CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images.,"CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images Yudong Guo, Juyong Zhang†, Jianfei Cai, Boyi Jiang and Jianmin Zheng" 5abaaf9c222398caea40d62e45b81a847436b784,An adaptive gamma correction for image enhancement,"Rahman et al. EURASIP Journal on Image and Video Processing (2016) 2016:35 DOI 10.1186/s13640-016-0138-1 EURASIP Journal on Image nd Video Processing RESEARCH Open Access An adaptive gamma correction for image enhancement Shanto Rahman1*, Md Mostafijur Rahman1, M. Abdullah-Al-Wadud2, Golam Dastegir Al-Quaderi3 nd Mohammad Shoyaib1" 5af1e8a38b64c6694b9a34cd0b1596f2c905d3ff,Context-based trajectory descriptor for human activity profiling,"Context-based Trajectory Descriptor for Human Activity Profiling Eduardo M. Pereira INESC TEC and Faculty of Engineering of the University of Porto Rua Dr. Roberto Frias, 378 Porto, Portugal 4200 - 465 Email: Lucian Ciobanu INESC TEC Rua Dr. Roberto Frias, 378 Porto, Portugal 4200 - 465 Email: Jaime S. Cardoso INESC TEC and Faculty of Engineering of the University of Porto Rua Dr. Roberto Frias, 378 Porto, Portugal 4200 - 465" 5aeaee0e3a324970c02ae8463e1b358597457d03,Towards a Types-As-Classifiers Approach to Dialogue Processing in Human-Robot Interaction,"Towards a Types-As-Classifiers Approach to Dialogue Processing in Human-Robot Interaction HOUGH, J; JAMONE, L; Schlangen, D; Walck, G; Haschke, R; Workshop on Dialogue and Perception (DaP 2018) © The Author(s) 2018 For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle/123456789/45947 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 5a1669abdc4f958c589843cff2f4d83a11fe8007,Robust Recognition via ` 1-Minimization April,"Robust Recognition via ‘1-Minimization April 13, 2007" 5a6e624b35175fa031dce373c906a340f668407e,Holistic Processing in the Composite Task Depends on Face Size.,"This article was downloaded by: [David Ross] On: 15 July 2015, At: 09:13 Publisher: Routledge Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: 5 Howick Place, London, SW1P 1WG Publication details, including instructions for authors nd subscription information: http://www.tandfonline.com/loi/pvis20 Holistic processing in the omposite task depends on face David A. Rossab & Isabel Gauthiera Department of Psychology, University of Massachusetts Amherst, Amherst, MA, USA Department of Psychological and Brain Sciences, Vanderbilt University, Nashville, TN, USA Published online: 19 Jun 2015. Click for updates To cite this article: David A. Ross & Isabel Gauthier (2015): Holistic 0.1080/13506285.2015.1049678 To link to this article: http://dx.doi.org/10.1080/13506285.2015.1049678" 5ad4e9f947c1653c247d418f05dad758a3f9277b,WLFDB: Weakly Labeled Face Databases,"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (TPAMI) WLFDB: Weakly Labeled Face Databases Dayong Wang†, Steven C.H. Hoi∗, and Jianke Zhu‡" 5ab2791fbd8d39d02eb8ee76b0f03f5d64371309,A Methodology for Empirical Performance Evaluation of Page Segmentation Algorithms Song Mao and Tapas Kanungo a Methodology for Empirical Performance Evaluation of Page Segmentation Algorithms,"LAMP-TR- December CAR-TR-  CS-TR-  AMethodologyforEmpirical PerformanceEvaluation ofPageSegmentationAlgorithms SongMaoandTapasKanungo" 5a4c6246758c522f68e75491eb65eafda375b701,Contourlet structural similarity for facial expression recognition,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010" 5aad5e7390211267f3511ffa75c69febe3b84cc7,Driver Gaze Estimation Without Using Eye Movement,"Driver Gaze Estimation Without Using Eye Movement Lex Fridman, Philipp Langhans, Joonbum Lee, Bryan Reimer MIT AgeLab" 5a6b2f3a542322be153fc9104f3064f2a1bc76eb,"A French-Spanish Multimodal Speech Communication Corpus Incorporating Acoustic Data, Facial, Hands and Arms Gestures Information","Interspeech 2018 -6 September 2018, Hyderabad 0.21437/Interspeech.2018-2212" 5a86842ab586de9d62d5badb2ad8f4f01eada885,Facial Emotion Recognition and Classification Using Hybridization Method,"International Journal of Engineering Research and General Science Volume 3, Issue 3, May-June, 2015 ISSN 2091-2730 Facial Emotion Recognition and Classification Using Hybridization Method Anchal Garg , Dr. Rohit Bajaj Deptt. of CSE, Chandigarh Engg. College, Mohali, Punjab, India. 07696449500" 5a3092b266ddf97ac9dc9a07a0ae7c40b54470cd,HSM: A New Color Space used in the Processing of Color Images,"HSM: A New Color Space used in the Processing of Color Images Severino Jr, Osvaldo1 and Gonzaga, Adilson2 Department of Electrical Engineering School of Engineering - USP Av. Trabalhador S˜ao-carlense, 400 ZIP Code 13566-590, S˜ao Carlos, Brazil . 2." 5a1bf442073b95a3392e673dd14bf73fc1e99f6b,Internal Report 96{08 Face Recognition by Elastic Bunch Graph Matching Face Recognition by Elastic Bunch Graph Matching,"InternalReport { FaceRecognitionbyElasticBunchGraphMatching LaurenzWiskott,Jean-MarcFellous,NorbertKr(cid:127)uger, ndChristophvonderMalsburg IR-INI { Ruhr-Universit(cid:127)atBochum April  Institutf(cid:127)urNeuroinformatik ISSN - Bochum (cid:13) Institutf(cid:127)urNeuroinformatik,Ruhr-Universit(cid:127)atBochum,FRG" 5ac707ab88c565b1ed34fac89939f0cd2451eb22,Automated Object Recognition in Baggage Screening using Multiple X-ray Views,"Automated Object Recognition in Baggage Screening using Multiple X-ray Views Domingo Mery and Vladimir Riffo Department of Computer Science – Pontificia Universidad Cat´olica de Chile Av. Vicu˜na Mackenna 4860(143) – Santiago de Chile http://dmery.ing.puc.cl" 5ac18d505ed6d10e8692cbb7d33f6852e6782692,"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","IJCV submission in review The Open Images Dataset V4 Unified image classification, object detection, and visual relationship detection at scale Alina Kuznetsova Hassan Rom Neil Alldrin Shahab Kamali Stefan Popov Matteo Malloci Tom Duerig Vittorio Ferrari Jasper Uijlings Ivan Krasin Jordi Pont-Tuset" 5a8d20ecd92d22bf077208a5e7b1bb008a9b7dbc,A new manifold distance measure for visual object categorization,"A New Manifold Distance Measure for Visual Object Categorization Fengfu Li, Xiayuan Huang, Hong Qiao and Bo Zhang index. The proposed distance is more robust" 5aaa84090c50da903ea1d61495c0fe96a5470909,Image-embodied Knowledge Representation Learning,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) of armourhas partFigure1:Examplesofentityimages.Fig.1demonstratessomeexamplesofentityimages.Eachentityhasmultipleimageswhichcanprovidesignificantvisu-alinformationthatintuitivelydescribestheappearancesandbehavioursofthisentity.Toutilizetherichinformationinimages,weproposetheImage-embodiedKnowledgeRepre-sentationLearningmodel(IKRL).Morespecifically,wefirstproposeanimageencoderwhichconsistsofaneuralrep-resentationmoduleandaprojectionmoduletogeneratetheimage-basedrepresentationforeachimageinstance.Second,weconstructtheaggregatedimage-basedrepresentationforeachentityjointlyconsideringallitsimageinstanceswithanattention-basedmethod.Finally,wejointlylearntheknowl-edgerepresentationswithtranslation-basedmethods.WeevaluatetheIKRLmodelonknowledgegraphcom-pletionandtripleclassification.Experimentalresultsdemon-stratethatourmodelachievesthestate-of-the-artperfor-mancesonbothtasks,whichconfirmsthesignificanceofvi-sualinformationinknowledgerepresentationlearning.ItalsoindicatesthatourIKRLmodeliscapableofencodingimageinformationwellintoknowledgerepresentations.Wedemon-stratethemaincontributionsofthisworkasfollows:(cid:15)WeproposeanovelIKRLmodelconsideringvisualin-formationinentityimagesforknowledgerepresentationlearning.Tothebestofourknowledge,thisisthefirstattempttocombineimageswithknowledgegraphsforknowledgerepresentationlearning.(cid:15)Weevaluateourmodelsonareal-worlddatasetandre-ceivepromisingperformancesonbothknowledgegraph" 5a4ec5c79f3699ba037a5f06d8ad309fb4ee682c,Automatic age and gender classification using supervised appearance model,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 12/17/2017 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use AutomaticageandgenderclassificationusingsupervisedappearancemodelAliMainaBukarHassanUgailDavidConnahAliMainaBukar,HassanUgail,DavidConnah,“Automaticageandgenderclassificationusingsupervisedappearancemodel,”J.Electron.Imaging25(6),061605(2016),doi:10.1117/1.JEI.25.6.061605." 5ae9e0cd2debd9e1b114bd44d9311c07a08e693a,JÚNIOR A SCALABLE AND VERSATILE FRAMEWORK FOR SMART VIDEO SURVEILLANCE,"A SCALABLE AND VERSATILE FRAMEWORK FOR SMART VIDEO SURVEILLANCE" 5a9126f4478384f6615bf57b6da7299dc17b9a6b,3-D Facial Landmark Localization With Asymmetry Patterns and Shape Regression from Incomplete Local Features,"JOURNAL OF LATEX CLASS FILES, VOL. 11, NO. 4, DECEMBER 2012 D Facial Landmark Localization with Asymmetry Patterns and Shape Regression from Incomplete Local Features Federico M. Sukno, John L. Waddington, and Paul F. Whelan" 5acd67f9102db0bed8c8465a0ea0e85efe89bcec,CalibNet: Self-Supervised Extrinsic Calibration using 3D Spatial Transformer Networks,"CalibNet: Self-Supervised Extrinsic Calibration using 3D Spatial Transformer Networks Ganesh Iyer, Karnik Ram R., J. Krishna Murthy, and K. Madhava Krishna Fig. 1: CalibNet estimates the extrinsic calibration parameters between a 3D LiDAR and a 2D camera. It takes as input an RGB image (a) from a calibrated camera, a raw LiDAR point cloud (b), and outputs a 6-DoF rigid-body transformation T that best aligns the two inputs. (c) shows the colorized point cloud output for a mis-calibrated setup, and (d) shows the output after calibration using our network. As shown, using the mis-calibrated point cloud to recover a colorized 3D map of the world results in an incoherent reconstruction. Notice how the 3D structures highlighted in (c) using red rectangles fail to project to their 2D counterparts. However, using the extrinsic calibration parameters predicted by CalibNet produces more consistent and accurate reconstructions (d), even for large initial mis-calibrations." 5a93f9084e59cb9730a498ff602a8c8703e5d8a5,Face Recognition using Local Quantized Patterns,"HUSSAIN ET. AL: FACE RECOGNITION USING LOCAL QUANTIZED PATTERNS Face Recognition using Local Quantized Patterns Sibt ul Hussain Thibault Napoléon Fréderic Jurie GREYC — CNRS UMR 6072, University of Caen Basse-Normandie, Caen, France" 5a363ac89f93377bb72af4346957ce36a01090c8,Face Recognition of Database of Compressed Images using Local Binary Patterns,"International Journal of Computer Applications (0975 – 8887) Volume 74– No.16, July 2013 Face Recognition of Database of Compressed Images using Local Binary Patterns Padmaja Vijay Kumar M.N.Giri Prasad,Ph.D Padmaja.K.V,Ph.D Jawaharlal Nehru Technological HOD and Professor-EC Professor, IT University, JNTU-AP JNTU-Anantapur-A.P R.V.C.E-Bangalore" 5a0209515ab62e008efeca31f80fa0a97031cd9d,Dataset fingerprints: Exploring image collections through data mining,"Dataset Fingerprints: Exploring Image Collections Through Data Mining Konstantinos Rematas1, Basura Fernando1, Frank Dellaert2, and Tinne Tuytelaars1 KU Leuven, ESAT-PSI, iMinds Georgia Tech Figure 1: Given an image collection, our system extracts patterns of discriminative mid level features and uses the connection etween them to enable structure specific browsing." 5ad65c6474c135a6c15e7127d8bb91de8c8a55a1,Designing Empathetic Animated Agents for a B-Learning Training Environment within the Electrical Domain,"Hernández, Y., Pérez-Ramírez, M., Zatarain-Cabada, R., Barrón-Estrada, L., & Alor-Hernández, G. (2016). Designing Empathetic Animated Agents for a B-Learning Training Environment within the Electrical Domain. Educational Technology & Society, 19 (2), 116–131. Designing Empathetic Animated Agents for a B-Learning Training Environment within the Electrical Domain Yasmín Hernández1*, Miguel Pérez-Ramírez1, Ramón Zatarain-Cabada2, Lucía Barrón- Estrada2 and Giner Alor-Hernández3 Instituto de Investigaciones Eléctricas, Gerencia de Tecnologías de la Información, Cuernavaca, México // 2Instituto Tecnológico de Culiacán, Departamento de Posgrado, Culiacán, México // 3Instituto Tecnológico de Orizaba, División de Estudios de Posgrado e Investigación, Orizaba, México // // // // // *Corresponding author" 5afd6c5eb5cc1e8496bb78b8f7b3a00b2900deb3,Self-Supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos,"Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos ¨Omer S¨umer∗ Tobias Dencker∗ Bj¨orn Ommer Heidelberg Collaboratory for Image Processing IWR, Heidelberg University, Germany" 5aa29373a59c60b01df4f8986ed4902e6dd60b96,GENDER CLASSIFICATION USING SUPPORT VECTOR MACHINES,"GENDER CLASSIFICATION USING SUPPORT VECTOR MACHINES Ashwin Swaminathan ENEE633: Statistical and Neural Pattern Recognition Instructor : Prof. Rama Chellappa Project 2, Part (a) . INTRODUCTION Gender classification has been known as one of the most important tasks for humans [13]. Recently, the field of gender classification has caught considerable attention due to its emerging applications in the rea of human computer interactions systems [14] and other applications. The problem of gender classification has been widely studied in psychology where they try to model the human recognition system to classify gender. Over the past few years, there have been a few learning ased algorithms proposed for gender classification. Most of these methods use neural networks for gender classification [16, 17]. In these works, the authors perform tests over 30 images and show that the neural network can help determine gender from 8x8 images with an average accuracy of 92%. RBF type networks have been widely used for this purpose. The use of Support vector machines for gender classification was proposed by Moghaddam et al. in [14]. It is well known that SVM can provide superior performace and hence it has been widely used in many classification problems. Specifically, it has been very helpful in cases where it is difficult to estimate the density model such as in classification of images e.g. face recognition, etc. The support vector machines employing kernel functions have been useful in cases where the data are not linearly" 5ade87a54c8baec555c37d59071c6fb4a9a55cf7,Deep Learning For Video Saliency Detection,"Deep Learning For Video Saliency Detection Wenguan Wang, and Jianbing Shen, Senior Member, IEEE, and Ling Shao, Senior Member," 5acfacbe8bf93ab1ee17bd6f65667abe0d6e1b5e,Where Should We Place LiDARs on the Autonomous Vehicle? - An Optimal Design Approach,"Where Should We Place LiDARs on the Autonomous Vehicle? - An Optimal Design Approach Zuxin Liu1 , Mansur Arief2 and Ding Zhao2,∗" 5ab9f00a707a55f4955b378981ad425aa1cb8ea3,Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets,"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. XX, NO. YY, NOVEMBER 2018 Forecasting People Trajectories and Head Poses y Jointly Reasoning on Tracklets and Vislets Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Vasileios Belagiannis, Sikandar Amin, Alessio Del Bue, Marco Cristani, and Fabio Galasso" 5ac8edd62fe23911e19d639287135f91e22421cc,Gender and 3D facial symmetry: What's the relationship?,"Gender and 3D Facial Symmetry: What’s the Relationship? Baiqiang Xia, Boulbaba Ben Amor, Hassen Drira, Mohamed Daoudi, Lahoucine Ballihi To cite this version: Baiqiang Xia, Boulbaba Ben Amor, Hassen Drira, Mohamed Daoudi, Lahoucine Ballihi. Gender nd 3D Facial Symmetry: What’s the Relationship?. 10th IEEE Conference on Automatic Face and Gesture Recognition (FG 2013), Apr 2013, shanghai, China. 2013. HAL Id: hal-00771988 https://hal.archives-ouvertes.fr/hal-00771988 Submitted on 9 Jan 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 5aed0f26549c6e64c5199048c4fd5fdb3c5e69d6,Human Expression Recognition using Facial Features,"International Journal of Computer Applications® (IJCA) (0975 – 8887) International Conference on Knowledge Collaboration in Engineering, ICKCE-2014 Human Expression Recognition using Facial Features G.Saranya Post graduate student, Dept. of ECE Parisutham Institute of Technology & Science Thanjavur. Affiliated to Anna university, Chennai recognition can be used" 185360fe1d024a3313042805ee201a75eac50131,Person De-Identification in Videos,"Person De-Identification in Videos Prachi Agrawal and P. J. Narayanan" 182df40034d937c74df0edb0acb295088e63f1ed,University of Michigan North Campus long-term vision and lidar dataset,"University of Michigan North Campus Long-Term Vision and Lidar Dataset The International Journal of Robotics Research 000(00):1–16 ©The Author(s) 2010 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI:doi number http://mms.sagepub.com Nicholas Carlevaris-Bianco∗, Arash K. Ushani†, and Ryan M. Eustice‡" 18dd7bf12de78f8d9afa4d107ddbf814d5a8ad49,PROBE-GK: Predictive robust estimation using generalized kernels,"PROBE-GK: Predictive Robust Estimation using Generalized Kernels Valentin Peretroukhin1, William Vega-Brown2, Nicholas Roy2 and Jonathan Kelly1" 1888bf50fd140767352158c0ad5748b501563833,A GUIDED TOUR OF FACE PROCESSING,"PA R T 1 THE BASICS" 1883387726897d94b663cc4de4df88e5c31df285,Measures of Effective Video Tracking,"Measures of effective video tracking Tahir Nawaz, Fabio Poiesi, Andrea Cavallaro" 18fcbf5c7f83aff072feb116b8a561d40afa11e9,COMS 4701 Artificial Intelligence Final Project Report Applications of Machine Learning to Facial Recognition in Video,"in Video David Lariviere John Petrella Jian Pan COMS 4701 Artificial Intelligence Final Project Report Applications of Machine Learning to Facial Recognition" 181045164df86c72923906aed93d7f2f987bce6c,T R ] 2 8 Se p 20 15 Correctness of Backtest Engines,"RHEINISCH-WESTFÄLISCHE TECHNISCHE HOCHSCHULE AACHEN KNOWLEDGE-BASED SYSTEMS GROUP PROF. GERHARD LAKEMEYER, PH. D. Detection and Recognition of Human Faces using Random Forests for a Mobile Robot MASTER OF SCIENCE THESIS VAISHAK BELLE MATRICULATION NUMBER: 26 86 51 SUPERVISOR: SECOND SUPERVISOR: PROF. GERHARD LAKEMEYER, PH. D. PROF. ENRICO BLANZIERI, PH. D. ADVISERS: STEFAN SCHIFFER, THOMAS DESELAERS" 18d51a366ce2b2068e061721f43cb798177b4bb7,Looking into your eyes: observed pupil size influences approach-avoidance responses.,"Cognition and Emotion ISSN: 0269-9931 (Print) 1464-0600 (Online) Journal homepage: http://www.tandfonline.com/loi/pcem20 Looking into your eyes: observed pupil size influences approach-avoidance responses Marco Brambilla, Marco Biella & Mariska E. Kret To cite this article: Marco Brambilla, Marco Biella & Mariska E. Kret (2018): Looking into your eyes: observed pupil size influences approach-avoidance responses, Cognition and Emotion, DOI: 0.1080/02699931.2018.1472554 To link to this article: https://doi.org/10.1080/02699931.2018.1472554 View supplementary material Published online: 11 May 2018. Submit your article to this journal View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pcem20" 1856e71437886af2366b620bcfe4caf891425f7b,Analyzing the Distribution of a Large-Scale Character Pattern Set Using Relative Neighborhood Graph,"Analyzing the Distribution of Large-scale Character Pattern Set Using Relative Neighborhood Graph Masanori Goto(cid:3), Ryosuke Ishiday, Yaokai Fengy and Seiichi Uchiday (cid:3)GLORY LTD., Hyogo, Japan Email: yKyushu University, Fukuoka, Japan Email:" 18de899c853120a1a2cd502ebc3e970b92e1882f,Age Regression from Soft Aligned Face Images Using Low Computational Resources,"Age regression from soft aligned face images using low computational resources Juan Bekios-Calfa1, Jos´e M. Buenaposada2, and Luis Baumela3 Dept. de Ingenier´ıa de Sistemas y Computaci´on, Universidad Cat´olica del Norte Av. Angamos 0610, Antofagasta, Chile Dept. de Ciencias de la Computaci´on, Universidad Rey Juan Carlos Calle Tulip´an s/n, 28933, M´ostoles, Spain Dept. de Inteligencia Artificial, Universidad Polit´ecnica de Madrid Campus Montegancedo s/n, 28660 Boadilla del Monte, Spain" 180cf5ab4e021e64b9bf08f2ffc4a4712acd9a30,Multi-view anchor graph hashing,"MULTI-VIEW ANCHOR GRAPH HASHING Saehoon Kim1 and Seungjin Choi1,2 Department of Computer Science and Engineering, POSTECH, Korea Division of IT Convergence Engineering, POSTECH, Korea {kshkawa," 18f348d56a2ff1c0904685ce8b6818b84867b7a4,ML-o-scope : a diagnostic visualization system for deep machine learning pipelines,"ML-o-scope: a diagnostic visualization system for deep machine learning pipelines Daniel Bruckner Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2014-99 http://www.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-99.html May 16, 2014" 18ab703c9959fbea7ad253a4062eb705b245552c,Efficient trajectory extraction and parameter learning for data-driven crowd simulation,"Efficient Trajectory Extraction and Parameter Learning for Data-Driven Crowd Simulation Aniket Bera∗ Sujeong Kim† Dinesh Manocha‡ The University of North Carolina at Chapel Hill" 1832204e7a0a17390e1335cba7be9b922ee4fa57,Bilateral random projections,"Bilateral Random Projections December 23, 2011" 188d43b5be038c705c0e552d5cc3e59980899a4d,Zero-Shot Recognition with Unreliable Attributes ( Supplementary material ),"Zero-Shot Recognition with Unreliable Attributes (Supplementary material) Dinesh Jayaraman Kristen Grauman In this document, we provide supplementary material for our NIPS 2014 paper “Zero-Shot Recognition with Unreliable Attributes”. Sec 1 shows how unlearnable attributes are avoided by our method. Sec 2 discusses the details of the signature uncertainty model introduced in Sec 3.2.3 of the paper. Sec 3 gives additional details for our controlled noise experiments (Sec 4.1 of the paper). Sec 4 lists the 10 SUN database test classes chosen at random. Sec 5 shows more few-shot results, as a continuation of Sec 4.2 in the paper. Sec 6 contains pseudocode for our proposed method, and Sec 7 contains schematics illustrating our method and its ablated variants. Unlearnable attributes As a sanity check, we show how accounting for classifier unreliability as detailed in Sec 3.2.2 of the paper also inherently avoids unlearnable attributes. For the extreme case of completely unlearnable attributes, the classifier annot tell between positives and negatives, so that TPR=FPR (regardless of threshold). If a candidate split (m, t) tested at any node involves such an attribute m, then signatures of all classes are equally likely to propagate to the left or right, i.e., I(cid:48) l and r are multiples of I(cid:48) I(cid:48)" 1819d9a9099dafc987dd236c2174945e7922be13,Eigenfeature Regularization and Extraction in Face Recognition,"Eigenfeature Regularization and Extraction in Face Recognition Xudong Jiang, Senior Member, IEEE, Bappaditya Mandal, and Alex Kot, Fellow, IEEE" 18cc17c06e34baaa3e196db07e20facdbb17026d,Describing Videos by Exploiting Temporal Structure,"Describing Videos by Exploiting Temporal Structure Li Yao Universit´e de Montr´eal Atousa Torabi Universit´e de Montr´eal Kyunghyun Cho Universit´e de Montr´eal Nicolas Ballas Universit´e de Montr´eal Christopher Pal ´Ecole Polytechnique de Montr´eal Hugo Larochelle Universit´e de Sherbrooke Aaron Courville Universit´e de Montr´eal" 1824b1ccace464ba275ccc86619feaa89018c0ad,One millisecond face alignment with an ensemble of regression trees,"One Millisecond Face Alignment with an Ensemble of Regression Trees Vahid Kazemi and Josephine Sullivan KTH, Royal Institute of Technology Computer Vision and Active Perception Lab Teknikringen 14, Stockholm, Sweden" 18d0f6445abeecf1fd2ce2b79924916d5f635af2,� BY Matthew Turk,"There are still obstacles to achieving general, robust, high-performance computer vision systems. The last decade, however, has seen significant progress in vision technologies for human-computer interaction. Computer Vision IN THE INTERFACE V isual information is clearly important as people onverse and interact with one another. Through the modality of vision, we can instantly determine number of salient facts and features about oth- ers, including their location, identity, approximate ge, focus of attention, facial expression, posture, gestures, and general activity. These visual cues affect the content nd flow of conversation, and they impart contextual informa- tion different from, but related to, speech—for example, a ges- ture or facial expression may be a key signal, or the direction of gaze may disambiguate the object referred to in speech as “this” or the direction “over there.” In other words, vision and speech re co-expressive and complementary channels in human-human interaction [6]. Just as automatic speech recognition seeks to" 18858cc936947fc96b5c06bbe3c6c2faa5614540,Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification,"Proceedings of Machine Learning Research 81:1–15, 2018 Conference on Fairness, Accountability, and Transparency Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification∗ Joy Buolamwini MIT Media Lab 75 Amherst St. Cambridge, MA 02139 Timnit Gebru Microsoft Research 641 Avenue of the Americas, New York, NY 10011 Editors: Sorelle A. Friedler and Christo Wilson" 18d7684c6b96caf51adb519738720eceb1b13050,Hidden Relationships: Bayesian Estimation With Partial Knowledge,"Hidden Relationships: Bayesian Estimation with Partial Knowledge Tomer Michaeli and Yonina C. Eldar, Senior Member, IEEE the joint probability function of" 18f9a6045ba01cb079c4fa49a630d71bbd27cd92,A dataset of clinically generated visual questions and answers about radiology images,"www.nature.com/scientificdata Received: 18 June 2018 Accepted: 16 September 2018 Published: 20 November 2018 Data Descriptor: A dataset of linically generated visual questions and answers about radiology images Jason J. Lau, Soumya Gayen, Asma Ben Abacha & Dina Demner-Fushman Radiology images are an essential part of clinical decision making and population screening, e.g., for cancer. Automated systems could help clinicians cope with large amounts of images by answering questions about the image contents. An emerging area of artificial intelligence, Visual Question Answering (VQA) in the medical domain explores approaches to this form of clinical decision support. Success of such machine learning tools hinges on availability and design of collections composed of medical images augmented with question-answer pairs directed at the content of the image. We introduce VQA-RAD, the first manually onstructed dataset where clinicians asked naturally occurring questions about radiology images and provided reference answers. Manual categorization of images and questions provides insight into clinically relevant tasks and the natural language to phrase them. Evaluating with well-known algorithms, we demonstrate the rich quality of this dataset over other automatically constructed ones. We propose VQA- RAD to encourage the community to design VQA tools with the goals of improving patient care." 1868aeb7f13e64ebc78869b371ef321572d6167f,Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes,"Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes David V´azquez1, Jiaolong Xu1, Sebastian Ramos1, Antonio M. L´opez1,2 and Daniel Ponsa1,2 Computer Vision Center Dept. of Computer Science Autonomous University of Barcelona 08193 Bellaterra, Barcelona, Spain {dvazquez, jiaolong, sramosp, antonio," 1806665f9571bbdcf654f3bdf5e009bcb8eac799,Markov random field terrain classification for autonomous robots in unstructured terrain,"Fachbereich 4: Informatik Arbeitsgruppe Aktives Sehen MARKOV RANDOM FIELD TERRAIN CLASSIFICATION FOR AUTONOMOUS ROBOTS IN UNSTRUCTURED TERRAIN Vom Promotionsausschuss des Fachbereichs 4: Informatik n der Universität Koblenz-Landau zur Verleihung des akademischen Grades Doktor der Naturwissenschaften (Dr. rer. nat.) genehmigte DISSERTATION Dipl.-Inform. Marcel Häselich Koblenz - 2014 Datum der Einreichung: Datum der wissenschaftlichen Aussprache: 7. Juni 2014 7. Dezember 2014 Vorsitzender des Promotionsausschusses:" 18d5b0d421332c9321920b07e0e8ac4a240e5f1f,Collaborative Representation Classification Ensemble for Face Recognition.,"Collaborative Representation Classification Ensemble for Face Recognition Xiao Chao Qu, Suah Kim, Run Cui and Hyoung Joong Kim" 18bca470bf51f5cc42148cd7e34fa58280be8eb2,Face Expressional Recognition using Geometry and Behavioral Traits,"IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.8, August 2009 Face Expressional Recognition using Geometry and Behavioral Traits J. K. Kani Mozhi, Sr. Lect / Dept. of MCA, K. S. Rangasamy College of Technology, Tiruchengode. India. J. K. Kani Mozhi 1 and Dr. R. S. D. Wahida Banu 2 Dr. R. S. D. Wahida Banu, Prof. & Head / Dept. of ECE, Govt. College of Engg., Salem, India. recognition" 18fe745e0840b7b086fb7d14850a95ebbd5ae57b,Evaluation and Acceleration of High-Throughput Fixed-Point Object Detection on FPGAs,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI Evaluation and Acceleration of High-Throughput Fixed-Point Object Detection on FPGAs Xiaoyin Ma, Student Member, IEEE, Walid A. Najjar, Fellow, IEEE, Amit K. Roy-Chowdhury, Sr. Member, IEEE" 18bf90d6f77bb3731cdae14315c0cf4724f0e6c1,When VLAD Met Hilbert,"When VLAD met Hilbert Mehrtash Harandi NICTA and Australian National University Canberra, Australia Mathieu Salzmann NICTA and Australian National University Canberra, Australia Fatih Porikli NICTA and Australian National University Canberra, Australia" 18727adf3e63de90674fcafd8b1f5e0059669e84,"A COMPARATIVE STUDY OF PCA , ICA AND LDA","A COMPARATIVE STUDY OF PCA, ICA AND LDA Kresimir Delac 1, Mislav Grgic 2 and Sonja Grgic 2 Croatian Telecom, Savska 32, Zagreb, Croatia, e-mail: University of Zagreb, FER, Unska 3/XII, Zagreb, Croatia implementations in all possible algorithm" 1885acea0d24e7b953485f78ec57b2f04e946eaf,Combining Local and Global Features for 3D Face Tracking,"Combining Local and Global Features for 3D Face Tracking Pengfei Xiong, Guoqing Li, Yuhang Sun Megvii (face++) Research {xiongpengfei, liguoqing," 18ccd8bd64b50c1b6a83a71792fd808da7076bc9,Object detection and segmentation from joint embedding of parts and pixels,"Object Detection and Segmentation from Joint Embedding of Parts and Pixels Michael Maire1, Stella X. Yu2, Pietro Perona1 California Institute of Technology - Pasadena, CA 91125 Boston College - Chestnut Hill, MA 02467" 18babfe4c7230522527a068654eeea10b1a827fd,Discriminative Label Propagation for Multi-object Tracking with Sporadic Appearance Features,"Discriminative Label Propagation for Multi-Object Tracking with Sporadic Appearance Features Amit Kumar K.C. and Christophe De Vleeschouwer ISPGroup, ELEN Department, ICTEAM Institute Universit´e catholique de Louvain Louvain-la-Neuve, B-1348, Belgium {amit.kc," 189fa973bc09cf3f3416e875fc853c3c489edeb0,Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks,"Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks Henggang Cui, Vladan Radosavljevic, Fang-Chieh Chou, Tsung-Han Lin, Thi Nguyen, Tzu-Kuo Huang, Jeff Schneider and Nemanja Djuric1" 18a7edd0bfe5a3d6ceb4d2053081e479cfa1e920,Transductive Kernel Map Learning and Its Application Image Annotation,"TRANSDUCTIVE LEARNING, KERNEL MAP, IMAGE ANNOTATION: BMVC SUBMISSION 1 Transductive Kernel Map Learning nd its Application to Image Annotation Dinh-Phong Vo Hichem Sahbi LTCI CNRS Telecom ParisTech 6 rue Barrault, 75013, Paris, France" 18269fcaba9feba85552b039a9052cd67e6d9c8b,Emotional facial sensing and multimodal fusion in a continuous 2D affective space,"J Ambient Intell Human Comput (2012) 3:31–46 DOI 10.1007/s12652-011-0087-6 O R I G I N A L R E S E A R C H Emotional facial sensing and multimodal fusion in a continuous D affective space Eva Cerezo • Isabelle Hupont • Sandra Baldassarri • Sergio Ballano Received: 3 February 2011 / Accepted: 24 September 2011 / Published online: 30 October 2011 Ó Springer-Verlag 2011" 18a849b1f336e3c3b7c0ee311c9ccde582d7214f,"Efficiently Scaling Up Crowdsourced Video Annotation A Set of Best Practices for High Quality , Economical Video Labeling","Int J Comput Vis DOI 10.1007/s11263-012-0564-1 Efficiently Scaling up Crowdsourced Video Annotation A Set of Best Practices for High Quality, Economical Video Labeling Carl Vondrick · Donald Patterson · Deva Ramanan Received: 31 October 2011 / Accepted: 20 August 2012 © Springer Science+Business Media, LLC 2012" 182c91f619e0b7a8cd2120139d530750aa0b85a7,Compressing the Input for CNNs with the First-Order Scattering Transform,"Compressing the Input for CNNs with the First-Order Scattering Transform Edouard Oyallon,1,4,5 Eugene Belilovsky,2 Sergey Zagoruyko,3 Michal Valko4 CentraleSupelec, Universit´e Paris-Saclay MILA, University of Montreal WILLOW – Inria Paris, 4SequeL – Inria Lille, 5GALEN – Inria Saclay" 85188c77f3b2de3a45f7d4f709b6ea79e36bd0d9,"Combined model for detecting , localizing , interpreting and recognizing faces","Author manuscript, published in ""Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recognition, Marseille : France (2008)""" 85387549277d6131dc8596ffacc7a21aeee0c6d1,Attribute Enhanced Face Aging with Wavelet-based Generative Adversarial Networks,"Attribute Enhanced Face Aging with Wavelet-based Generative Adversarial Networks Yunfan Liu, Qi Li, and Zhenan Sun∗ Center for Research on Intelligent Perception and Computing, CASIA National Laboratory of Pattern Recognition, CASIA {qli," 851e78906e1307773b664953bf2830f32b28511f,Lie Algebra-Based Kinematic Prior for 3D Human Pose Tracking,"Lie Algebra-Based Kinematic Prior for 3D Human Pose Tracking Edgar Simo-Serra, Carme Torras, and Francesc Moreno-Noguer Institut de Rob`otica i Inform`atica Industrial (CSIC-UPC). Barcelona, Spain" 8518b501425f2975ea6dcbf1e693d41e73d0b0af,Relative Hidden Markov Models for Evaluating Motion Skill,"Relative Hidden Markov Models for Evaluating Motion Skills Qiang Zhang and Baoxin Li Computer Science and Engineering Arizona State Univerisity, Tempe, AZ 85281" 8502c089c9affe5955810073b4c814457790065c,Learning Single-view 3D Reconstruction of Objects and Scenes,"UC Berkeley UC Berkeley Electronic Theses and Dissertations Title Learning Single-view 3D Reconstruction of Objects and Scenes Permalink https://escholarship.org/uc/item/3dc5m39p Author Tulsiani, Shubham Publication Date Peer reviewed|Thesis/dissertation eScholarship.org Powered by the California Digital Library University of California" 853bd61bc48a431b9b1c7cab10c603830c488e39,Learning Face Representation from Scratch,"Learning Face Representation from Scratch Dong Yi, Zhen Lei, Shengcai Liao and Stan Z. Li Center for Biometrics and Security Research & National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences (CASIA) dong.yi, zlei, scliao," 85956f6431543d1bf62bb5d5143de4348f14a95c,Detecting Adversarial Perturbations Through Spatial Behavior in Activation Spaces,"Detecting Adversarial Perturbations Through Spatial Behavior in Activation Spaces Ziv Katzir Yuval Elovici Department of Software and Information Department of Software and Information Systems Engineering, Ben-Gurion University Systems Engineering, Ben-Gurion University of the Negev of the Negev" 8562ca7f86e7cc144aa2d34a9cce41431b9e13e9,BioMechanical Enginering Face Recognition for Cognitive Robots,"Face Recognition for Cognitive Robots F. Gaisser BioMechanical Enginering" 856b8576999517c0cb7d95aef0159432604a8447,The 19 th Meeting on Image Recognition and Understanding Weighted Heterogeneous Learning for Deep Convolutional Neural Network Based Facial Image Analysis,The 19th Meeting on Image Recognition and Understanding 8558ea46c8f7e56c57073b27408c6638e81293f0,Morphable crowds, 85955fe6cdf4f9f35fc9eab6cc4fccbb819e68a1,3D Face Reconstruction by Learning from Synthetic Data,"D Face Reconstruction by Learning from Synthetic Data Elad Richardson* Matan Sela* Ron Kimmel Department of Computer Science, Technion - Israel Institute of Technology" 852998c60e4a62d0508de11b6297e6e97a0d3fac,Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice,"THIS WORK HAS BEEN SUBMITTED TO THE IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS. Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice Amir Rasouli and John K. Tsotsos" 85fd2bda5eb3afe68a5a78c30297064aec1361f6,"Are You Smiling, or Have I Seen You Before? Familiarity Makes Faces Look Happier.","702003 PSSXXX10.1177/0956797617702003Carr et al.Are You Smiling, or Have I Seen You Before? research-article2017 Research Article Are You Smiling, or Have I Seen You Before? Familiarity Makes Faces Look Happier 017, Vol. 28(8) 1087 –1102 © The Author(s) 2017 Reprints and permissions: sagepub.com/journalsPermissions.nav DOI: 10.1177/0956797617702003 https://doi.org/10.1177/0956797617702003 www.psychologicalscience.org/PS Evan W. Carr1, Timothy F. Brady2, and Piotr Winkielman2,3,4 Columbia Business School, Columbia University; 2Psychology Department, University of California, San Diego; Behavioural Science Group, Warwick Business School, University of Warwick; and 4Faculty of Psychology, SWPS University of Social Sciences and Humanities" 8558fc2016fc9b3db3248b2e75b81d9aa9cfc390,Spatial orientations of visual word pairs to improve Bag-of-Visual-Words model,"KHAN et al.: SP. ORIENTATIONS OF VIS. WORD PAIRS TO IMPROVE BOVW MOD. Spatial orientations of visual word pairs to improve Bag-of-Visual-Words model Rahat Khan Cecile Barat Damien Muselet Christophe Ducottet Université de Lyon, F-42023, Saint-Etienne, France, CNRS, UMR5516, Laboratoire Hubert Curien, F-42000, Saint-Etienne, France, Université de Saint-Etienne, Jean Mon- net, F-42000, Saint-Etienne, France." 858901405086056361f8f1839c2f3d65fc86a748,ON TENSOR TUCKER DECOMPOSITION : THE CASE FOR AN ADJUSTABLE CORE SIZE,"ON TENSOR TUCKER DECOMPOSITION: THE CASE FOR AN ADJUSTABLE CORE SIZE BILIAN CHEN ∗, ZHENING LI † , AND SHUZHONG ZHANG ‡" 858ddff549ae0a3094c747fb1f26aa72821374ec,"Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-Related Applications","Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-related Applications Ciprian A. Corneanu, Marc Oliu, Jeffrey F. Cohn, and Sergio Escalera" 857fb344977e5181bf5a99593ceba09a158d412c,VCI 2 R at the NTCIR-13 Lifelog-2 Lifelog Semantic Access Task,"VCI2R at the NTCIR-13 Lifelog-2 Lifelog Semantic Access Jie Lin Institute for Infocomm Research, A*STAR, Singapore Ana Garcia del Molino Institute for Infocomm Research, A*STAR, Singapore Nanyang Technological University, Singapore star.edu.sg Qianli Xu Institute for Infocomm Research, A*STAR, Singapore Fen Fang Vigneshwaran Subbaraju Joo Hwee Lim Institute for Infocomm Research, A*STAR, Singapore star.edu.sg Institute for Infocomm" 853feff8674f4a856e6568c9ddce5eace014de8c,NISTIR 8045 Performance Evaluation Methods for Human Detection and Tracking Systems for Robotic Applications,"NISTIR 8045 Performance Evaluation Methods for Human Detection and Tracking Systems for Robotic Applications Michael Shneier Tsai Hong Geraldine Cheok Kamel Saidi Will Shackleford This publication is available free of charge from: http://dx.doi.org/10.6028/NIST.IR.8045" 8566231abd7e5bc71ee0bc0da84b8d76ce07a501,On The Stability of Video Detection and Tracking,"On The Stability of Video Detection and Tracking Hong Zhang Chinese University of Hong Kong Naiyan Wang TuSimple LLC" 85c1926ea23ff4f472774fec8c6a993bb499e4f4,Eigenbands fusion for frontal face recognition,"EIGENBANDS FUSION FOR FRONTAL FACE RECOGNITION George D. C. Cavalcanti1s2 and Edson C. B. Cawalho Filho’ ’ UFPE-Universidade Federal de Pemambuco, 50732-970, Recife, PE, Brad FIR-Faculdade Integrada do Recife 50720-635 Recife, PE, Brad" 8575adafc04a7915bd71c3733e379577da0c4406,Sistema tutor afectivo para la enseñanza de lógica algorítmica y programación,"Sistema tutor afectivo para la enseñanza de lógica lgorítmica y programación Ramón Zatarain-Cabada1, María Lucia Barrón-Estrada1, José Mario Ríos-Félix1, Giner Alor-Hernandez2 Instituto Tecnológico de Culiacán, Culiacán Sinaloa, México Instituto Tecnológico de Orizaba, División de Estudios de Posgrado e Investigación, Orizaba, Veracruz, México {rzatarain, lbarron, Resumen. La creciente demanda de herramientas de software que motiven y poyen a los estudiantes en el aprendizaje de diseño e implementación de lgoritmos y programas, ha motivado la creación de este tipo de sistemas de software. En este artículo presentamos un nuevo e innovador sistema tutor fectivo de lógica algorítmica y programación, basado en la técnica de bloques. Nuestro enfoque combina la interfaz de Google Blockly con técnicas de gamificación y ejercicios que son monitoreados para obtener el estado afectivo del estudiante. Dependiendo de la emoción manifestada (aburrido, enganchado, frustrado y neutral), el sistema evalúa una serie de variables, para determinar si el estudiante requiere asistencia. En base a las pruebas preliminares con varios" 85cad2b23e2ed7098841285bae74aafbff921659,Pa-gan: Improving Gan Training by Progressive Augmentation,"Under review as a conference paper at ICLR 2019 PA-GAN: IMPROVING GAN TRAINING BY PROGRESSIVE AUGMENTATION Anonymous authors Paper under double-blind review" 85401b669a989da15bb3d2b37d4598c21d9d061b,"The effect of intranasal oxytocin versus placebo treatment on the autonomic responses to human sounds in autism: a single-blind, randomized, placebo-controlled, crossover design study","Lin et al. Molecular Autism 2014, 5:20 http://www.molecularautism.com/content/5/1/20 Open Access R ES EAR CH The effect of intranasal oxytocin versus placebo treatment on the autonomic responses to human sounds in autism: a single-blind, randomized, placebo-controlled, crossover design study I-Fan Lin1*, Makio Kashino1,2, Haruhisa Ohta3, Takashi Yamada3, Masayuki Tani3, Hiromi Watanabe3, Chieko Kanai3, Taisei Ohno3, Yuko Takayama3, Akira Iwanami3 and Nobumasa Kato3,4" 8529c0b98ab4f6eb21715a54395420988dd69633,Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective,"Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective Wei Zhou, Alex Zyner, Stewart Worrall, and Eduardo Nebot" 857fface5ccd0fd4f30d6b1b3d2cd25a2b471501,Head pose estimation via probabilistic high-dimensional regression,"Head Pose Estimation Via Probabilistic High-Dimensional Regression Vincent Drouard 1 Sil`eye Ba 1 Georgios Evangelidis 1 Antoine Deleforge 2 Radu Horaud 1 Team Perception - Inria Grenoble Rhˆone-Alpes, France Friedrich-Alexander-Universit¨at, Erlangen, Germany September 28, 2015, Qu´ebec, Canada Work supported by EU-FP7 ERC Advanced Grant VHIA (#340113) and STREP project EARS (#609645)" 858b51a8a8aa082732e9c7fbbd1ea9df9c76b013,Can Computer Vision Problems Benefit from Structured Hierarchical Classification?,"Can Computer Vision Problems Benefit from Structured Hierarchical Classification? Thomas Hoyoux1, Antonio J. Rodr´ıguez-S´anchez2, Justus H. Piater2, and Sandor Szedmak2 INTELSIG, Montefiore Institute, University of Li`ege, Belgium Intelligent and Interactive Systems, Institute of Computer Science, University of Innsbruck, Austria" 85b1ca3089d503781af9de23d24567461cbb65c6,A Mobile Real Time Interactive Communication Assistant for Cerebral Palsy,"A Mobile Real Time Interactive Communication Assistant for Cerebral Palsy LAU BEE THENG & HII KIING SHI* Swinburne University of Technology Sarawak Campus, Malaysia LOW TIONG KIE University Malaysia Sarawak, Malaysia" 8509abbde2f4b42dc26a45cafddcccb2d370712f,A way to improve precision of face recognition in SIPP without retrain of the deep neural network model,"Improving precision and recall of face recognition in SIPP with combination of modified mean search and LSH Xihua.Li" 850c5d1f97eee47a1fdaefc0894b52e51a3145fc,Improved Semantic Stixels via Multimodal Sensor Fusion,"Improved Semantic Stixels via Multimodal Sensor Fusion Florian Piewak(cid:63)1,2, Peter Pinggera1, Markus Enzweiler1, David Pfeiffer(cid:63)(cid:63)1, and Marius Z¨ollner2,3 Daimler AG, R&D, Stuttgart, Germany Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany Forschungszentrum Informatik (FZI), Karlsruhe, Germany" 85489639f395608174f686d634d6e27ef44c9d77,Social ‘wanting’ dysfunction in autism: neurobiological underpinnings and treatment implications,"Kohls et al. Journal of Neurodevelopmental Disorders 2012, 4:10 http://www.jneurodevdisorders.com/content/4/1/10 RE VI E W Open Access Social ‘wanting’ dysfunction in autism: neurobiological underpinnings and treatment implications Gregor Kohls*, Coralie Chevallier, Vanessa Troiani and Robert T Schultz" 854f9fb21853d1e50302dddcc1fd5c2e933ed8f4,Information Constraints on Auto-Encoding Variational Bayes,"Information Constraints on Auto-Encoding Variational Bayes Romain Lopez1, Jeffrey Regier1, Michael I. Jordan1,2, and Nir Yosef1,3,4 {romain_lopez, regier, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley Department of Statistics, University of California, Berkeley Ragon Institute of MGH, MIT and Harvard Chan-Zuckerberg Biohub" 854cfc218b506b54edeee15d32b0869e77755006,Preserving privacy in structural neuroimages,"Preserving Privacy in Structural Neuroimages Nakeisha Schimke, Mary Kuehler, and John Hale Institute of Bioinformatics and Computational Biology The University of Tulsa 800 South Tucker Drive Tulsa, Oklahoma 74104" 854890f35fc7955d94777395f6a66da433426d98,Human Gaze Following for Human-Robot Interaction,"Human Gaze Following for Human-Robot Interaction Akanksha Saran1, Srinjoy Majumdar2, Elaine Schaertl Short2, Andrea Thomaz2 and Scott Niekum1" 35692e80fa2fc17a1d37a40b3d4ffca28a1bcc7b,Appearance-based people recognition by local dissimilarity representations,"Appearance-based People Recognition by Local Dissimilarity Representations Riccardo Satta, Giorgio Fumera, Fabio Roli Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d’Armi, 09123 Cagliari, Italy riccardo.satta, fumera," 35c0954acde9c86df8bbcb6edccbcd702796f5eb,"Multimodal Database of Emotional Speech , Video and Gestures","World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:12, No:10, 2018 Multimodal Database of Emotional Speech, Video nd Gestures Tomasz Sapi´nski, Dorota Kami´nska, Adam Pelikant, Egils Avots, Cagri Ozcinar, Gholamreza Anbarjafari" 3516d0c6918bcf977ad004b337fb066a9d5a8e17,A Novel Face Hallucination with an Error Regression Model and MPCA in RGB Color Space,"International Journal of Future Computer and Communication, Vol. 2, No. 4, August 2013 A Novel Face Hallucination with an Error Regression Model and MPCA in RGB Color Space Krissada Asavaskulkiet and Phumin Kirawanich framework, many color" 35e4b6c20756cd6388a3c0012b58acee14ffa604,Gender Classification in Large Databases,"Gender Classification in Large Databases E. Ram´on-Balmaseda, J. Lorenzo-Navarro, and M. Castrill´on-Santana (cid:63) Universidad de Las Palmas de Gran Canaria SIANI Spain" 353a89c277cca3e3e4e8c6a199ae3442cdad59b5,Title of dissertation : LEARNING FROM MULTIPLE VIEWS OF DATA, 35d94887e4eb075f2603b2c69b19d31471351ff7,People detection and tracking from aerial thermal views, 3555d849b85e9416e9496c9976084b0e692b63cd,TOWARDS EFFECTIVE GANS,"Under review as a conference paper at ICLR 2018 TOWARDS EFFECTIVE GANS FOR DATA DISTRIBUTIONS WITH DIVERSE MODES Anonymous authors Paper under double-blind review" 35047c9667a4c5160f9f40f16b455839e63662ff,Color Object Recognition Based on a Clifford Fourier Transform,"Author manuscript, published in ""Guide to Geometric Algebra in Practice, Leo Dorst and Joan Lasenby (Ed.) (2011) 175-191"" DOI : 10.1007/978-0-85729-811-9_9" 35e730f7967155b9394f9e5d3cadf2b955ce9a7b,Deep Affinity Network for Multiple Object Tracking,"JOURNAL OF LATEX CLASS FILES, VOL. 13, NO. 9, SEPTEMBER 2017 Deep Affinity Network for Multiple Object Tracking ShiJie Sun, Naveed Akhtar, HuanSheng Song, Ajmal Mian, Mubarak Shah" 352d61eb66b053ae5689bd194840fd5d33f0e9c0,Analysis Dictionary Learning based Classification: Structure for Robustness,"Analysis Dictionary Learning based Classification: Structure for Robustness Wen Tang, Ashkan Panahi, Hamid Krim, and Liyi Dai" 35f345ebe3831e4741dcdc1931da59043acf4b83,Towards High Performance Video Object Detection for Mobiles 3 2 Revisiting Video Object Detection Baseline,"Towards High Performance Video Object Detection for Mobiles Xizhou Zhu(cid:63) Jifeng Dai Xingchi Zhu(cid:63) Yichen Wei Lu Yuan Microsoft Research Asia" 35e6f6e5f4f780508e5f58e87f9efe2b07d8a864,Summarization of User-Generated Sports Video by Using Deep Action Recognition Features,"This paper is a preprint (IEEE accepted status). IEEE copyright notice. 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for dvertising or promotional purposes, creating new collective works, for resale or redistribu- tion to servers or lists, or reuse of any copyrighted. A. Tejero-de-Pablos, Y. Nakashima, T. Sato, N. Yokoya, M. Linna and E. Rahtu, ”Sum- marization of User-Generated Sports Video by Using Deep Action Recognition Features,” in doi: 10.1109/TMM.2018.2794265 keywords: Cameras; Feature extraction; Games; Hidden Markov models; Semantics; Three-dimensional displays; 3D convolutional neural networks; Sports video summarization; ction recognition; deep learning; long short-term memory; user-generated video, URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8259321&isnumber=4456689" 35ebe95db7ab148e25904604d3b06a9412f6b4a4,Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search,"Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search Jamie Ryan Kiros* William Chan* Geoffrey E. Hinton {kiros, williamchan, Google Brain Toronto" 35308a3fd49d4f33bdbd35fefee39e39fe6b30b7,Efficient and effective human action recognition in video through motion boundary description with a compact set of trajectories,"biblio.ugent.be The UGent Institutional Repository is the electronic archiving and dissemination platform for allUGent research publications. Ghent University has implemented a mandate stipulating that allacademic publications of UGent researchers should be deposited and archived in this repository.Except for items where current copyright restrictions apply, these papers are available in OpenAccess. This item is the archived peer-reviewed author-version of: Efficient and effective human action recognition in video through motion boundary description witha compact set of trajectories Jeong-Jik Seo, Jisoo Son, Hyung-Il Kim, Wesley De Neve, and Yong Man Ro In: 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition,1, 1-6, 2015. To refer to or to cite this work, please use the citation to the published version: Seo, J., Son, J., Kim, H., De Neve, W., and Ro, Y. M. (2015). Efficient and effective human actionrecognition in video through motion boundary description with a compact set of trajectories. 11thIEEE International Conference and Workshops on Automatic Face and Gesture Recognition 1 1-6.http://dx.doi.org/10.1109/FG.2015.7163123" 35800a537017803dd08274710388734db66b54f0,Sliced Wasserstein Generative Models,"Sliced Wasserstein Generative Models Jiqing Wu * 1 Zhiwu Huang * 1 Wen Li 1 Janine Thoma 1 Luc Van Gool 1 2" 3596c23a0f13c36d2c71c4cba4351363954dd02a,PathFinder : An autonomous mobile robot guided by Computer Vision,"PathFinder: An autonomous mobile robot guided by Computer Vision Andre R. de Geus1,2, Marcelo H. Stoppa1, Sergio F. da Silva1,2 Modeling and Optimization Program, Federal University of Goias, Catalao, Goias, Brazil Biotechnology Institute, Federal University of Goias, Catalao, Goias, Brazil Email:" 357df3ee0f0c30d5c8abc5a1bdf70122322d6fbd,O BJECT DETECTORS EMERGE IN D EEP S CENE CNN S,"Under review as a conference paper at ICLR 2015 OBJECT DETECTORS EMERGE IN DEEP SCENE CNNS Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Department of Computer Science and Artificial Intelligence, MIT" 35410a58514cd5fd66d9c43d42e8222526170c1b,Shared mechanism for emotion processing in adolescents with and without autism,"Received: 04 August 2016 Accepted: 05 January 2017 Published: 20 February 2017 Shared mechanism for emotion processing in adolescents with and without autism Christina Ioannou1, Marwa El Zein1, Valentin Wyart1, Isabelle Scheid2,3, Frédérique Amsellem3,4, Richard Delorme3,4, Coralie Chevallier1,* & Julie Grèzes1,* Although, the quest to understand emotional processing in individuals with Autism Spectrum Disorders (ASD) has led to an impressive number of studies, the picture that emerges from this research remains inconsistent. Some studies find that Typically Developing (TD) individuals outperform those with ASD in emotion recognition tasks, others find no such difference. In this paper, we move beyond focusing on potential group differences in behaviour to answer what we believe is a more pressing question: do individuals with ASD use the same mechanisms to process emotional cues? To this end, we rely on model-based analyses of participants’ accuracy during an emotion categorisation task in which displays of anger and fear are paired with direct vs. averted gaze. Behavioural data of 20 ASD nd 20 TD adolescents revealed that the ASD group displayed lower overall performance. Yet, gaze direction had a similar impact on emotion categorisation in both groups, i.e. improved accuracy for salient combinations (anger-direct, fear-averted). Critically, computational modelling of participants’ ehaviour reveals that the same mechanism, i.e. increased perceptual sensitivity, underlies the" 35b1c1f2851e9ac4381ef41b4d980f398f1aad68,Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning,"Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning Chuang Gan1, Boqing Gong2, Kun Liu3, Hao Su 4, Leonidas J. Guibas 5 MIT-IBM Watson AI Lab , 2 Tencent AI Lab, 3 BUPT, 4 UCSD, 5 Stanford University" 3597ca03bded3717f5c88273e4b7dbf24545ff83,Mouse Pose Estimation From Depth Images,"Mouse Pose Estimation From Depth Images Ashwin Nanjappa1, Li Cheng∗1, Wei Gao1, Chi Xu1, Adam Claridge-Chang2, and Zoe Bichler3 Bioinformatics Institute, A*STAR, Singapore Institute of Molecular and Cell Biology, A*STAR, Singapore National Neuroscience Institute, Singapore" 35035f79256a3f19a111fff34df6d14876d83fab,Satyam: Democratizing Groundtruth for Machine Vision,"SATYAM: DEMOCRATIZING GROUNDTRUTH FOR MACHINE VISION Hang Qiu?, Krishna Chintalapudi†, Ramesh Govindan?" 35794480e556b946c82d498ce868fa62235befa7,Real-Time Detection and Tracking of Multiple Humans from High Bird's-Eye Views in the Visual and Infrared Spectrum,"Real-Time Detection and Tracking of Multiple Humans from High Bird’s-Eye Views in the Visual and Infrared Spectrum Julius K¨ummerle, Timo Hinzmann, Anurag Sai Vempati and Roland Siegwart Autonomous Systems Lab, ETH Zurich" 35fd6c9f2e651259ee565475f88faeb523511d4e,On the Performance of Kernel Methods for Skin Color Segmentation,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2009, Article ID 856039, 13 pages doi:10.1155/2009/856039 Research Article On the Performance of Kernel Methods for Skin Color Segmentation A. Guerrero-Curieses,1 J. L. Rojo- ´Alvarez,1 P. Conde-Pardo,2 I. Landesa-V´azquez,2 J. Ramos-L ´opez,1 and J. L. Alba-Castro2 Departamento de Teor´ıa de la Se˜nal y Comunicaciones, Universidad Rey Juan Carlos, 28943 Fuenlabrada, Spain Departamento de Teor´ıa de la Se˜nal y Comunicaciones, Universidad de Vigo, 36200 Vigo, Spain Correspondence should be addressed to A. Guerrero-Curieses, Received 26 September 2008; Revised 23 March 2009; Accepted 7 May 2009 Recommended by C.-C. Kuo Human skin detection in color images is a key preprocessing stage in many image processing applications. Though kernel-based methods have been recently pointed out as advantageous for this setting, there is still few evidence on their actual superiority. Specifically, binary Support Vector Classifier (two-class SVM) and one-class Novelty Detection (SVND) have been only tested in some example images or in limited databases. We hypothesize that comparative performance evaluation on a representative pplication-oriented database will allow us to determine whether proposed kernel methods exhibit significant better performance than conventional skin segmentation methods. Two image databases were acquired for a webcam-based face recognition" 35e855b0c1af4cc7bf62a8eb459c949776fbe7ee,Local Features and Kernels for Classification of Texture and Object Categories : An In-Depth Study,"INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE Local Features and Kernels for Classi(cid:2)cation of Texture and Object Categories: An In-Depth Study Jianguo Zhang (cid:151) Marcin Marsza(cid:7)ek (cid:151) Svetlana Lazebnik (cid:151) Cordelia Schmid N(cid:176) 5737 Novembre 2005 Th(cid:30)eme COG p p o r t (cid:13) (cid:13)d e r e c h e r c h e (cid:13)" 35be5bea87c465c97127c64919d115e235d62e82,"The automatic detection of chronic pain-related expression : requirements , challenges and a multimodal dataset","IEEE TRANSACTIONS ON JOURNAL NAME, MANUSCRIPT ID The automatic detection of chronic pain- related expression: requirements, challenges nd a multimodal dataset Min S. H. Aung, Sebastian Kaltwang, Bernardino Romera-Paredes, Brais Martinez, Aneesha Singh, Matteo Cella, Michel Valstar, Hongying Meng, Andrew Kemp, Moshen Shafizadeh, Aaron C. Elkins, Natalie Kanakam, Amschel de Rothschild, Nick Tyler, Paul J. Watson, Amanda C. de C. Williams, Maja Pantic, and Nadia Bianchi-Berthouze* face videos, head mounted and room audio signals," 35197862aed9a73415bdaea2fb8ad29d66675604,Mixture of SVMs for Face Class Modeling,"Mixture of SVMs for Face Class Modeling Julien Meynet1, Vlad Popovici, and Jean-Philippe Thiran Signal Processing Institute, Swiss Federal Institute of Technology Lausanne, CH-1015 Lausanne, Switzerland http://itswww.epfl.ch" 35570297681daa3973498eabead361d0be961672,Configuration Estimates Improve Pedestrian Finding,"Configuration Estimates Improve Pedestrian Finding Duan Tran∗ U.Illinois at Urbana-Champaign Urbana, IL 61801 USA D.A. Forsyth U.Illinois at Urbana-Champaign Urbana, IL 61801 USA" 355c8c0dbd80de9d23affb37ac102179b6b2a908,“A Distorted Skull Lies in the Bottom Center...” Identifying Paintings from Text Descriptions,"Anupam Guha, Mohit Iyyer, and Jordan Boyd-Graber. A Distorted Skull Lies in the Bottom Center: Identifying Paintings from Text Descriptions. NAACL Human-Computer Question Answering Workshop, 2016. Title = {A Distorted Skull Lies in the Bottom Center: Identifying Paintings from Text Descriptions}, Author = {Anupam Guha and Mohit Iyyer and Jordan Boyd-Graber}, Booktitle = {NAACL Human-Computer Question Answering Workshop}, Year = {2016}, Location = {San Diego, CA}, Url = {docs/2016_naacl_paintings.pdf}, Links: • Data [http://www.cs.umd.edu/~aguha/data/paintdata.rar] Downloaded from http://cs.colorado.edu/~jbg/docs/2016_naacl_paintings.pdf" 355de7460120ddc1150d9ce3756f9848983f7ff4,Midge: Generating Image Descriptions From Computer Vision Detections,"Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 747–756, Avignon, France, April 23 - 27 2012. c(cid:13)2012 Association for Computational Linguistics" 35f3c4012e802332faf0a1426e9acf8365601551,Bidirectional Conditional Generative Adversarial Networks,"Bidirectional Conditional Generative Adversarial Networks Ayush Jaiswal, Wael AbdAlmageed, Yue Wu, and Premkumar Natarajan USC Information Sciences Institute, Marina del Rey, CA, USA {ajaiswal, wamageed, yue wu," 35b9ded80ce2b30ee115b8198d146890b9028d51,Regularizing max-margin exemplars by reconstruction and generative models,"Regularizing Max-Margin Exemplars by Reconstruction and Generative Models Jose C. Rubio and Bj¨orn Ommer Heidelberg Collaboratory for Image Processing IWR, Heidelberg University, Germany" 3538d2b5f7ab393387ce138611ffa325b6400774,A DSP-BASED APPROACH FOR THE IMPLEMENTATION OF FACE RECOGNITION ALGORITHMS,"A DSP-BASED APPROACH FOR THE IMPLEMENTATION OF FACE RECOGNITION ALGORITHMS A. U. Batur B. E. Flinchbaugh M. H. Hayes IIl Center for Signal and Image Proc. Georgia Inst. Of Technology Atlanta, GA Imaging and Audio Lab. Texas Instruments Dallas, TX Center for Signal and Image Proc. Georgia Inst. Of Technology Atlanta, CA" 351de1f7862bd13a82fcfcaa698b4efd53bc2c35,Automatic 3D face verification from range data,- 1930-7803-7663-3/03/$17.00 ©2003 IEEEICASSP 2003(cid:224) 35fe83665c61adb513781c7208b92706ae2a1578,Answering Visual What-If Questions: From Actions to Predicted Scene Descriptions, 3506ef7168e07840187ec978b47f3a05a753101d,Robust 3D Face Landmark Localization Based on Local Coordinate Coding,"Robust 3D Face Landmark Localization based on Local Coordinate Coding Mingli Song, Senior Member, IEEE, Dacheng Tao, Senior Member, IEEE, Shengpeng Sun, Chun Chen, and Stephen J. Maybank Fellow, IEEE," 35e87e06cf19908855a16ede8c79a0d3d7687b5c,Strategies for MultiView Face Recognition for Identification of Human Faces : A Review,"Strategies for Multi-View Face Recognition for Identification of Human Faces: A Review Pritesh G. Shah Department of Computer Science Mahatma Gandhi Shikshan Mandal’s, Arts, Science and Commerce College, Chopda Dist: Jalgaon (M.S) Dr. R.R.Manza Department of Computer Science and IT Dr. Babasaheb Ambedkar Marathwada University Aurangabad." 3533a7714b19396bba8297e0ca22f85ac68ca18a,Dense Captioning with Joint Inference and Visual Context,"Dense Captioning with Joint Inference and Visual Context Linjie Yang Kevin Tang Jianchao Yang Li-Jia Li {linjie.yang, kevin.tang, Snap Inc." 3574bd487622fc1d6d88cda4ba31d87f3d1a5bd6,Automatic Pose Correction for Local Feature-Based Face Authentication,"Automatic Pose Correction for Local Feature-Based Face Authentication Daniel Gonz´alez-Jim´enez1, Federico Sukno2, Jos´e Luis Alba-Castro1, and Alejandro Frangi2 Departamento de Teor´ıa de la Se˜nal y Comunicaciones, Universidad de Vigo, Spain {danisub, Departamento de Tecnolog´ıa, Universidad Pompeu Fabra, Barcelona, Spain {federico.sukno," 35f084ddee49072fdb6e0e2e6344ce50c02457ef,A bilinear illumination model for robust face recognition,"A Bilinear Illumination Model for Robust Face Recognition The Harvard community has made this rticle openly available. Please share how this access benefits you. Your story matters Citation Lee, Jinho, Baback Moghaddam, Hanspeter Pfister, and Raghu Machiraju. 2005. A bilinear illumination model for robust face recognition. Proceedings of the Tenth IEEE International Conference on Computer Vision: October 17-21, 2005, Beijing, China. 1177-1184. Los Almamitos, C.A.: IEEE Computer Society. Published Version doi:10.1109/ICCV.2005.5 Citable link http://nrs.harvard.edu/urn-3:HUL.InstRepos:4238979 Terms of Use This article was downloaded from Harvard University’s DASH repository, and is made available under the terms and conditions pplicable to Other Posted Material, as set forth at http:// nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-" 35e808424317cf03b51516df7d083f45791311ae,A Survey for Action Recognition Research,"A Survey for Action Recognition Research Yuancheng Ye" 359a4142f6a55a58a3e18628e3ee52c76744fcb0,Prevalence of face recognition deficits in middle childhood.,"ISSN: 1747-0218 (Print) 1747-0226 (Online) Journal homepage: http://www.tandfonline.com/loi/pqje20 Prevalence of face recognition deficits in middle hildhood Rachel J Bennetts, Ebony Murray, Tian Boyce & Sarah Bate To cite this article: Rachel J Bennetts, Ebony Murray, Tian Boyce & Sarah Bate (2016): Prevalence of face recognition deficits in middle childhood, The Quarterly Journal of Experimental Psychology, DOI: 10.1080/17470218.2016.1167924 To link to this article: http://dx.doi.org/10.1080/17470218.2016.1167924 View supplementary material Accepted author version posted online: 21 Mar 2016. Submit your article to this journal View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pqje20 Download by: [Rachel Bennetts] Date: 22 March 2016, At: 07:06" 353480b21d5745590db5f70b016a27e25f5b9aec,Cross-Modal and Hierarchical Modeling of Video and Text,"Cross-Modal and Hierarchical Modeling of Video nd Text Bowen Zhang(cid:63)1, Hexiang Hu(cid:63)1, and Fei Sha2 Dept. of Computer Science, U. of Southern California, Los Angeles, CA 90089 Netflix, 5808 Sunset Blvd, Los Angeles, CA 90028" 3521904cced380b849325d6fda2a4d855edbe405,Finding Images of Rare and Ambiguous Entities,"Finding Images of Rare and Ambiguous Entities Bilyana Taneva Mouna Kacimi Gerhard Weikum MPI–I–2011–5–002 May 2011" 3504907a2e3c81d78e9dfe71c93ac145b1318f9c,An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks,"Noname manuscript No. (will be inserted by the editor) Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks Jun-Cheng Chen∗ Kumar∗ · Ching-Hui Chen∗ · Vishal M. Patel · Carlos D. Castillo · Rama Chellappa · Rajeev Ranjan∗ · Swami Sankaranarayanan∗ · Amit Received: date / Accepted: date" 359c9b9282424f198ef7b348a2fbab38c0c8f4fc,Supervised learning and evaluation of KITTI's cars detector with DPM,"Supervised learning and evaluation of KITTI’s cars detector with DPM J. Javier Yebes, Luis M. Bergasa, Roberto Arroyo and Alberto Lázaro" 35457de70ea13415b8abd3898a4a83021946501f,Learning Robust and Discriminative Subspace With Low-Rank Constraints,"Calhoun: The NPS Institutional Archive Faculty and Researcher Publications Funded by Naval Postgraduate School Learning Robust and Discriminative Subspace With Low-Rank Constraints Sheng Li http://hdl.handle.net/10945/52406" 35ccf703df2dd37fc857ab9b438e18c9a65ba5b9,Two-step supervised confidence measure for automatic face recognition,"TWO-STEP SUPERVISED CONFIDENCE MEASURE FOR AUTOMATIC FACE RECOGNITION Ladislav Lenc1 , Pavel Kr´al1 Dept. of Computer Science & Engineering 2New Technologies for the Information Society Faculty of Applied Sciences University of West Bohemia Plzeˇn, Czech Republic Faculty of Applied Sciences University of West Bohemia Plzeˇn, Czech Republic" 53078a5692d493685fd2d63abf297a39b2edb36d,Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking,"Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking Filip Radenovi´c1 Ahmet Iscen1 Giorgos Tolias1 Yannis Avrithis2 Ondˇrej Chum1 VRG, FEE, CTU in Prague Inria Rennes" 53079196041fedeb5f1e236b1c76c7108fd8346e,"Multiple Object Detection, Tracking and Long-Term Dynamics Learning in Large 3D Maps","Multiple Object Detection, Tracking nd Long-Term Dynamics Learning in Large 3D Maps Local D Maps Object Posteriors Learn Dynamics Location l1 Location l3 Object jump probability: pjump = 0.036 Object spatial process variance: q = 0.137 Measurement ovariance:  0.14 −0.03 0.02" 53c5f995e76ead002f1b0a78bfd50de3b1faf593,Enhancing the Symmetry and Proportion of 3D Face Geometry,"Enhancing the symmetry and proportion of 3D face geometry Qiqi Liao, Xiaogang Jin, Wenting Zeng" 53a41c711b40e7fe3dc2b12e0790933d9c99a6e0,Recurrent Memory Addressing for Describing Videos,"Recurrent Memory Addressing for describing videos Arnav Kumar Jain∗ Abhinav Agarwalla∗ Kumar Krishna Agrawal∗ Pabitra Mitra {arnavkj95, abhinavagarawalla, kumarkrishna, Indian Institute of Technology Kharagpur" 53bed2d3d75c4320ad5af4a85e31bf92e3c704ef,Reinforced Video Captioning with Entailment Rewards,"Reinforced Video Captioning with Entailment Rewards Ramakanth Pasunuru and Mohit Bansal UNC Chapel Hill {ram," 5357e6e5d5fe06934bfe693d18b9f44bbd98f73b,Landmark Detection for Unconstrained Face Recognition,"Landmark Detection for Unconstrained Face Recognition Panagiotis B. Perakis (cid:63) National and Kapodistrian University of Athens Department of Informatics and Telecommunications" 53ac22fff7ae3ed08565439ac30656846cac2465,Learning 3D Human Pose from Structure and Motion,"Learning 3D Human Pose from Structure and Motion Rishabh Dabral1, Anurag Mundhada1, Uday Kusupati1, Safeer Afaque1, Abhishek Sharma2, Arjun Jain1 {rdabral, safeer, {anuragmundhada, Indian Institute of Technology Bombay, 2Gobasco AI Labs kusupatiuday," 5365892b23db7e8bd526441d339c9165657f7efb,MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation,"MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation Xucong Zhang, Yusuke Sugano∗, Mario Fritz, Andreas Bulling" 53f0b39c88f3973f74f65455d0d77dfe6feede84,Fine-grained sketch-based image retrieval by matching deformable part models,"Fine-grained sketch-based image retrieval by matching deformable part models Li, Y; Hospedales, TM; Song, YZ; Gong, S For additional information about this publication click this link. http://qmro.qmul.ac.uk/jspui/handle/123456789/6440 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 53baabad70915a852477c2191b8bdb005b8cc4a5,Temporal-Enhanced Convolutional Network for Person Re-Identification,"The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) Temporal-Enhanced Convolutional Network for Person Re-identification Yang Wu, Jie Qiu, Jun Takamatsu, Tsukasa Ogasawara Nara Institute of Science and Technology 8916-5 Takayama-cho, Ikoma, Nara, 630-0192, Japan {qiu.jie.qf3, j-taka," 53bb52eb910c3a0ac5dc7f379b1f3f7c29af529d,Pain recognition using spatiotemporal oriented energy of facial muscles,"Pain Recognition using Spatiotemporal Oriented Energy of Facial Muscles Ramin Irani, Kamal Nasrollahi, and Thomas B. Moeslund Visual Analysis of People (VAP) Laboratory Rendsburggade 14, 9000 Aalborg, Denmark {ri, kn," 5345822a30293c9989fd1ec19b5a2da96956347b,Acoustic-labial Speaker Verication 1,"Acoustic(cid:0)Labial Speaker Veri(cid:1)cation  P(cid:0) Jourlin a (cid:0) (cid:1) J(cid:0) Luettin a(cid:1) D(cid:0) Genoud a(cid:1) H(cid:0) Wassner a IDIAP(cid:0) rue du Simplon (cid:0) CP  (cid:0) CH(cid:5)  Martigny(cid:0) Switzerland LIA(cid:0)  chemin des Meinajari(cid:9)es(cid:0) BP (cid:0)   Avignon Cedex (cid:0) France" 5322f56b8768f8053e8b0c4944d81377d1d60411,MEE 09 : 79 FACE ALIGNMENT USING BOOSTED APPEARANCE MODEL ( Discriminative Appearance Model ),"MEE09:79 FACE ALIGNMENT USING BOOSTED APPEARANCE MODEL (Discriminative Appearance Model) Satya Mahesh Muddamsetty This thesis is presented as part of Degree of Master of Science in Electrical Engineering Blekinge Institute of Technology November 2009 Blekinge Institute of Technology School of Engineering Department of Applied Signal Processing Supervisor: Mr. Tommaso Gritti, PHILIPS RESEARCH, Eindhoven, Netherlands Examiner: Mr. Mikael Nilsson" 5367610430dc0380dfbe8344e08537267875968c,Tracking 3 D Surfaces Using Multiple Cameras : A Probabilistic Approach,"Tracking 3D Surfaces Using Multiple Cameras: A Probabilistic Approach Thomas Popham Thesis Submitted to the University of Warwick for the degree of Doctor of Philosophy Department of Computer Science August 2010" 537061f3601965b5aab9f402763d9dcf451e1cef,A Deep Neural Model Of Emotion Appraisal,"Noname manuscript No. (will be inserted by the editor) A Deep Neural Model Of Emotion Appraisal Pablo Barros · Emilia Barakova · Stefan Wermter Received: date / Accepted: date" 53f8f1ddd83a9e0e0821aaa883fbf7c1f7f5426e,Face Recognition using Principal Component Analysis and Log-Gabor Filters,"Face Recognition using Principal Component Analysis and Log-Gabor Filters Vytautas Perlibakas Image Processing and Analysis Laboratory, Computational Technologies Centre, Kaunas University of Technology, Studentu st. 56-305, LT-51424 Kaunas, Lithuania" 53d0cef0b415f0cab8b82e1f62a66f9511ea6eab,Similarity Function Learning with Data Uncertainty, 531b211d4cbe766e0b86c4bb6f24e924494360c5,"SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation","SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation Sudeep Pillai, Rares, Ambrus,, Adrien Gaidon Toyota Research Institute (TRI)" 53492cb14b33a26b10c91102daa2d5a2a3ed069d,Improving Online Multiple Object tracking with Deep Metric Learning,"Improving Online Multiple Object tracking with Deep Metric Learning Michael Thoreau, Navinda Kottege" 534551fe2c4ce76c9a9a752364cd9c3af0dc9093,Gait Dynamics for Recognition and Classification,"m a s s a c h u s e t t s i n s t i t u t e o f t e c h n o l o g y — a r t i f i c i a l i n t e l l i g e n c e l a b o r a t o r y Gait Dynamics for Recognition nd Classification Lily Lee AI Memo 2001-019 September 2001 © 2 0 0 1 m a s s a c h u s e t t s i n s t i t u t e o f t e c h n o l o g y, c a m b r i d g e , m a 0 2 1 3 9 u s a — w w w. a i . m i t . e d u" 538f735450463f40c78f60797899fcee47df72bc,Discriminative Dictionary Learning With Motion Weber Local Descriptor for Violence Detection,"© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for ll other uses, in any current or future media, including reprinting/republishing this material for dvertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works." 53881bb35cb98c788f75fbc8c76198ccbc50edbf,Selective experience replay in reinforcement learning for reidentification,"SELECTIVE EXPERIENCE REPLAY IN REINFORCEMENT LEARNING FOR REIDENTIFICATION Ninad Thakoor , Bir Bhanu Center for Research in Intelligent Systems, University of California, Riverside, Riverside, CA 92521, USA" 537a00082b413b40fbdd02b5584791614f5071d2,Face Recognition Using Principal Component Analysis for Security Based System,"International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013): 6.14 | Impact Factor (2013): 4.438 Face Recognition Using Principal Component Analysis for Security Based System Madhuri M. Ghodake1, Parul S. Arora2 Savitribai Phule Pune University, G.H.Raisoni College of Engg & Management, Domkhel Road, Wagholi, Pune Assistant Professor, G.H.Raisoni College of Engg & Management, Domkhel Road, Wagholi, Pune, Savitribai Phule University, Pune" 53993c7fabf631cbd8a44ab3e42c6bdf784db456,Understanding and Predicting Image Memorability at a Large Scale,"Understanding and Predicting Image Memorability at a Large Scale Aditya Khosla Akhil S. Raju Antonio Torralba Aude Oliva" 535919a5ffa0f214df2ad39e80015ecba174a10d,k-fold Subsampling based Sequential Backward Feature Elimination, 5366573e96a1dadfcd4fd592f83017e378a0e185,"Server, server in the cloud. Who is the fairest in the crowd?","Böhlen, Chandola and Salunkhe Server, server in the cloud. Who is the fairest in the crowd?" 5383473d1a669beb0089f72a9a5075e943f0270f,Higher-order Occurrence Pooling on Mid-and Low-level Features : Visual Concept Detection, 533d5e62a983325cdbd44010018696ece433ea67,A Novel Georeferenced Dataset for Stereo Visual Odometry,"Proceedings of the Croatian Computer Vision Workshop, Year 1 September 19, 2013, Zagreb, Croatia A novel georeferenced dataset for stereo visual odometry Ivan Kreˇso Marko ˇSevrovi´c Siniˇsa ˇSegvi´c University of Zagreb Faculty of Electrical Engineering and Computing University of Zagreb Faculty of Transport and Traffic Engineering University of Zagreb Faculty of Electrical Engineering and Computing Zagreb, HR-10000, Croatia Zagreb, HR-10000, Croatia Zagreb, HR-10000, Croatia Email: Email: Email:" 539b66c91f41719ef94f50e6d42ab470f2a2702c,Agreeing to cross: How drivers and pedestrians communicate,"Agreeing To Cross: How Drivers and Pedestrians Communicate* Amir Rasouli, Iuliia Kotseruba and John K. Tsotsos1" 53822d61e829ef02a95a6c89fea082114fd3e16b,A General Framework for Tracking Multiple People from a Moving Camera,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese" 53819049f41998a5a1587dfccccc2db8612b45af,Deep Semantic Lane Segmentation for Mapless Driving,"018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Madrid, Spain, October 1-5, 2018 978-1-5386-8093-3/18/$31.00 ©2018 IEEE" 53c8f841cbf2c8f09c6ece9d7f164504fe39409b,Deep Clustering for Unsupervised Learning of Visual Features,"Deep Clustering for Unsupervised Learning of Visual Features Mathilde Caron, Piotr Bojanowski, Armand Joulin, and Matthijs Douze Facebook AI Research" 53e081f5af505374c3b8491e9c4470fe77fe7934,Unconstrained realtime facial performance capture,"Unconstrained Realtime Facial Performance Capture Pei-Lun Hsieh⇤ ⇤ University of Southern California Chongyang Ma⇤ Jihun Yu† Hao Li⇤ Industrial Light & Magic Figure 1: Calibration-free realtime facial performance capture on highly occluded subjects using an RGB-D sensor." 5357bdaf7c54619016bdb7ebfa991a65a6cc8353,"Infants’ Temperament and Mothers’, and Fathers’ Depression Predict Infants’ Attention to Objects Paired with Emotional Faces","J Abnorm Child Psychol (2016) 44:975–990 DOI 10.1007/s10802-015-0085-9 Infants’ Temperament and Mothers’, and Fathers’ Depression Predict Infants’ Attention to Objects Paired with Emotional Faces Evin Aktar 1,2 & Dorothy J. Mandell 1 & Wieke de Vente 2 & Mirjana Majdandžić 2 & Maartje E. J. Raijmakers 1,3 & Susan M. Bögels 2 Published online: 8 October 2015 # The Author(s) 2015. This article is published with open access at Springerlink.com" 5305a899c3f45e312f2ae583fd3abb2d1fede458,Absolute Localization using Visual Data for Autonomous Vehicles, 53f981cb6f1cf19b08255c571d62cc1073fd792b,Deconvolutional networks for point-cloud vehicle detection and tracking in driving scenarios,"Deconvolutional Networks for Point-Cloud Vehicle Detection nd Tracking in Driving Scenarios V´ıctor Vaquero∗, Ivan del Pino∗, Francesc Moreno-Noguer, Joan Sol`a, Alberto Sanfeliu and Juan Andrade-Cetto" 89742f28108330f97df94df98f73b459b02ca33d,Query Specific Semantic Signature for Improved Web Image Re-Ranking Joshith,"International Journal of Engineering and Technical Research (IJETR) ISSN: 2321-0869, Volume-3, Issue-3, March 2015 Query Specific Semantic Signature for Improved Web Image Re-Ranking Joshith.K, S.Krishnamoorthi" 8949563597276246f9f480d4b38b3b7851fd5495,Toward Efficient and Robust Large-scale Structure-from-motion Systems,"TOWARD EFFICIENT AND ROBUST LARGE-SCALE STRUCTURE-FROM-MOTION SYSTEMS Jared S. Heinly A dissertation submitted to the faculty of the University of North Carolina at Chapel Hill in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Department of Computer Science. Chapel Hill Approved by: Jan-Michael Frahm Enrique Dunn Alexander C. Berg Marc Niethammer Sameer Agarwal" 89588a4055b69abf99de321ce36b03ad5e8f8f05,Huffman Code Function and Mahalanobis Distance-base Face Recognition,"Huffman Code Function and Mahalanobis Distance-base Face Recognition {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 153 Number 5 Year of Publication: 2016 Authors: Babatunde R. S., Ajao. J. F., Balogun B. F. 10.5120/ijca2016911784 {bibtex}2016911784.bib{/bibtex}" 8948e9dce2dfaeb1d93ce146fab5364b6cd342c9,Dual Attention Network for Scene Segmentation,"Dual Attention Network for Scene Segmentation Jun Fu, Jing Liu, Haijie Tian, Zhiwei Fang, Hanqing Lu {jun.fu, jliu, zhiwei.fang, CASIA IVA" 89d3a57f663976a9ac5e9cdad01267c1fc1a7e06,Neural Class-Specific Regression for face verification,"Neural Class-Specific Regression for face verification Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj" 89c51f73ec5ebd1c2a9000123deaf628acf3cdd8,Face Recognition Based on Nonlinear Feature Approach,"American Journal of Applied Sciences 5 (5): 574-580, 2008 ISSN 1546-9239 © 2008 Science Publications Face Recognition Based on Nonlinear Feature Approach Eimad E.A. Abusham, 1Andrew T.B. Jin, 1Wong E. Kiong and 2G. Debashis Faculty of Information Science and Technology, Faculty of Engineering and Technology, Multimedia University (Melaka Campus), Jalan Ayer Keroh Lama, 75450 Bukit Beruang, Melaka, Malaysia" 89d7cc9bbcd2fdc4f4434d153ecb83764242227b,Face-Name Graph Matching For The Personalities In Movie Screen Einstein,"Einstein.J, DivyaBaskaran / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 3, Issue 2, March -April 2013, pp.351-355 Face-Name Graph Matching For The Personalities In Movie Screen *(Asst. Professor, Dept. of IT, VelTech HighTech Dr. Rangarajan Dr.Sakunthala Engineering College, Einstein.J*, DivyaBaskaran** ** (Final Year Student, M.Tech IT, Vel Tech Dr. RR &Dr. SR Technical University, Chennai.) Chennai.)" 89967f456c7680c193d7c2d18d2ec267ec59dbf6,Biometrics of Asymmetrical Face,"Biometrics of Asymmetrical Face Leonid Kompanets Czestochowa University of Technology Institute of Computer and Information Sciences Center for Intelligent Multimedia Techniques Dabrowski str., 69, 42-200 Czestochowa, Poland" 89d02ceae9e972eca633ae6ff9da9ee8a85fb171,Using Explanations to Improve Ensembling of Visual Question Answering Systems,"In Proceedings of the IJCAI 2017 Workshop on Explainable Artificial Intelligence (XAI), pp. 43-47, Melbourne, Australia, August 2017." 89670862270d31fe7a02d863be51fbe83324ece2,Ear Recognition Based on Statistical Shape Model,"Ear Recognition Based on Statistical Shape Model LU Lu, ZHANG Xiaoxun, ZHAO Youdong and JIA Yunde Department of computer science and engineering, Beijing Institute of Technology, Beijing 100081, PR China" 89f9225a7223133fa687e1c44bb758c3567f4f26,F 3F : A System Theoretic Approach to Robust Detection Of Potential Threats From Video,"F3-F: A System Theoretic Approach to Robust Detection Of Potential Threats from Video" 891b10c4b3b92ca30c9b93170ec9abd71f6099c4,2 New Statement for Structured Output Regression Problems,"Facial landmark detection using structured output deep neural networks Soufiane Belharbi ∗1, Cl´ement Chatelain∗1, Romain H´erault∗1, and S´ebastien Adam∗2 LITIS EA 4108, INSA de Rouen, Saint ´Etienne du Rouvray 76800, France LITIS EA 4108, UFR des Sciences, Universit´e de Rouen, France. September 24, 2015" 8966af6a8049192556e9c9356886a135595c19b8,Temporally Coherent CRP: A Bayesian Non-Parametric Approach for Clustering Tracklets with applications to Person Discovery in Videos,"Temporally Coherent CRP: A Bayesian Non-Parametric Approach for Clustering Tracklets with applications to Person Discovery in Videos Adway Mitra∗ Soma Biswas† Chiranjib Bhattacharyya‡" 8935ffe454758e2e5def0b5190de6e28c350b3b8,Learning to Reconstruct Face Geometries Research,"Learning to Reconstruct Face Geometries Elad Richardson Technion - Computer Science Department - M.Sc. Thesis MSC-2017-11 - 2017" 89945b7cd614310ebae05b8deed0533a9998d212,Divide-and-Conquer Method for L1 Norm Matrix Factorization in the Presence of Outliers and Missing Data,"Divide-and-Conquer Method for L1 Norm Matrix Factorization in the Presence of Outliers and Missing Data Deyu Meng and Zongben Xu" 898a66979c7e8b53a10fd58ac51fbfdb6e6e6e7c,Dynamic vs. Static Recognition of Facial Expressions,"Dynamic vs. Static Recognition of Facial Expressions No Author Given No Institute Given" 8961677300a9ee30ca51e1a3cf9815b4a162265b,Deep Representation Learning with Part Loss for Person Re-Identification,"Deep Representation Learning with Part Loss for Person Re-Identification Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian" 890103cb8d3d869298421da817d0a181487ec79a,Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorization,"Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorization Jinshi Yu, Guoxu Zhou, Andrzej Cichocki IEEE Fellow, and Shengli Xie IEEE Senior Member" 89c73b1e7c9b5e126a26ed5b7caccd7cd30ab199,Application of an Improved Mean Shift Algorithm in Real-time Facial Expression Recognition,"Application of an Improved Mean Shift Algorithm in Real-time Facial Expression Recognition School of Computer and Communication, Hunan University of Technology, Hunan, Zhuzhou, 412008，china School of Electrical and Information Engineering, Hunan University of Technology, Hunan, Zhuzhou, 412008，china School of Computer and Communication, Hunan University of Technology, Hunan, Zhuzhou, 412008，china Zhao-yi PENG Yu ZHOU Yan-hui ZHU Email: Zhi-qiang WEN Email: School of Computer and Communication, Hunan University of Technology, Hunan, Zhuzhou, 412008，china facial real-time expression" 895c5a6f2915d95d518e78d6a0224dad7399492b,Beyond Bounding Boxes: Precise Localization of Objects in Images,"UC Berkeley UC Berkeley Electronic Theses and Dissertations Title Beyond Bounding Boxes: Precise Localization of Objects in Images Permalink https://escholarship.org/uc/item/54v2z91n Author Hariharan, Bharath Publication Date Peer reviewed|Thesis/dissertation eScholarship.org Powered by the California Digital Library University of California" 894f1e924dfb8dfb843c42835fa79e386ac07383,Dimensional emotion recognition using visual and textual cues,"Dimensional emotion recognition using visual and textual cues Pedro M. Ferreira1, Diogo Pernes2, Kelwin Fernandes1, Ana Rebelo3 and Jaime S. Cardoso1" 89ef75b43bc329f21fd3e81d36235d4824478831,A real-time Deep Learning pedestrian detector for robot navigation,"A Real-Time Deep Learning Pedestrian Detector for Robot Navigation David Ribeiro, Andr´e Mateus, Pedro Miraldo, and Jacinto C. Nascimento Instituto de Sistemas e Rob´otica, Instituto Superior T´ecnico, Universidade de Lisboa, Lisboa, Portugal" 8913a5b7ed91c5f6dec95349fbc6919deee4fc75,BigBIRD: A large-scale 3D database of object instances,"BigBIRD: A Large-Scale 3D Database of Object Instances Arjun Singh, James Sha, Karthik S. Narayan, Tudor Achim, Pieter Abbeel" 89bc311df99ad0127383a9149d1684dfd8a5aa34,Towards ontology driven learning of visual concept detectors.,"Towards ontology driven learning of visual concept detectors Sanchit ARORA, Chuck CHO, Paul FITZPATRICK, Franc¸ois SCHARFFE 1 Dextro Robotics, Inc. 101 Avenue of the Americas, New York, USA" 89d590d7013433304aae1c97debd257b8dd801fa,Outdoor Human Motion Capture by Simultaneous Optimization of Pose and Camera Parameters,"Volume xx (200y), Number z, pp. 1–13 Outdoor Human Motion Capture by Simultaneous Optimization of Pose and Camera Parameters A. Elhayek C. Stoll K. I. Kim and C. Theobalt Max-Planck-Institute for Informatics, Saarbrücken, Germany Figure 1: Examples of multi-person tracking with moving cameras. (Left two images) two actors, and two moving and 3 static ameras (Soccer1). (Right two images) One actor, and three moving and two static cameras (Walk2)." 89ed007d1dc8cd26033e71dfad7698c835b7336f,"Statistical modeling, level-set and ensemble learning for automatic segmentation of 3D high-frequency ultrasound data : towards expedited quantitative ultrasound in lymph nodes from cancer patients. (Modélisation statistique, méthodes d'ensemble de niveaux et apprentissage automatique pour la segmen","Statistical modeling, level-set and ensemble learning for utomatic segmentation of 3D high-frequency ultrasound data : towards expedited quantitative ultrasound in lymph nodes from cancer patients Thanh Bui Minh To cite this version: Thanh Bui Minh. Statistical modeling, level-set and ensemble learning for automatic segmen- tation of 3D high-frequency ultrasound data : towards expedited quantitative ultrasound in lymph nodes from cancer patients. Medical Imaging. Universit´e Pierre et Marie Curie - Paris VI, 2016. English. ¡ NNT : 2016PA066146 ¿. HAL Id: tel-01408283 https://tel.archives-ouvertes.fr/tel-01408283 Submitted on 4 Dec 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est" 8954d46e1d7a11b20b2c688e5fb8bce4901650d6,Looking at movies and cartoons: eye-tracking evidence from Williams syndrome and autism.,"Looking at Movies and Cartoons: Eye-tracking evidence from Williams syndrome nd Autism Deborah M Riby and Peter J B Hancock Journal of Intellectual Disability Research http://dx.doi.org/10.1111/j.1365-2788.2008.01142.x" 89d967cb778cc99ff9b3f3e26257b0636f522af1,Decision tree simplification for classifier ensembles,"7305629 UNIVERSITY OF SURREY LIBRARY" 8929e704b6af7f09ad027714b75972cb9df57483,Image Inpainting for Irregular Holes Using Partial Convolutions, 893239f17dc2d17183410d8a98b0440d98fa2679,UvA-DARE ( Digital Academic Repository ) Expression-Invariant Age Estimation,"UvA-DARE (Digital Academic Repository) Expression-Invariant Age Estimation Alnajar, F.; Lou, Z.; Alvarez Lopez, J.M.; Gevers, T. Published in: Proceedings of the British Machine Vision Conference 2014 0.5244/C.28.14 Link to publication Citation for published version (APA): Alnajar, F., Lou, Z., Alvarez, J., & Gevers, T. (2014). Expression-Invariant Age Estimation. In M. Valstar, A. French, & T. Pridmore (Eds.), Proceedings of the British Machine Vision Conference 2014 (pp. 14.1-14.11). BMVA Press. DOI: 10.5244/C.28.14 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Download date: 04 Aug 2017" 8988384f492b1b277be41a894a2c911ed884e095,Reliability evaluation and error mitigation in pedestrian detection algorithms for embedded GPUs,"UNIVERSIDADE FEDERAL DO RIO GRANDE DO SUL INSTITUTO DE INFORMÁTICA PROGRAMA DE PÓS-GRADUAÇÃO EM COMPUTAÇÃO FERNANDO FERNANDES DOS SANTOS Reliability evaluation and error mitigation in pedestrian detection algorithms for embedded GPUs Thesis presented in partial fulfillment of the requirements for the degree of Master of Computer Science Advisor: Prof. Dr. Paolo Rech Porto Alegre May 2017" 89f44f756c230e104cdf2ec0152d5f015586399c,WIDE-AREA BASED TRAFFIC SITUATION DETECTION AT AN UNGATED LEVEL CROSSING,"M. Junghans, et al., Int. J. of Safety and Security Eng., Vol. 6, No. 2 (2016) 383–393 WIDE-AREA BASED TRAFFIC SITUATION DETECTION AT AN UNGATED LEVEL CROSSING M. JUNGHANS, A. LEICH, K. KOZEMPEL, H. SAUL & S. KNAKE-LANGHORST Institute of Transportation Systems, German Aerospace Center (DLR), Berlin, Germany." 89358e65aec4d6665098c7dbbe3975296cc7a2fc,Discriminative Feature Based Algorithm for Detecting And Classifying Frames In Image Sequences,"M. A. A Victoria et al. Int. Journal of Engineering Research and Applications www.ijera.com Vol. 3, Issue 5, Sep-Oct 2013, pp.446-450 RESEARCH ARTICLE OPEN ACCESS Discriminative Feature Based Algorithm for Detecting And Classifying Frames In Image Sequences M. Antony Arockia Victoria, R. Sahaya Jeya Sutha B.E,M.E. Assistant Professor, Department of MCA, Dr.Sivanthi Aditanar College of Engineering, MCA,M.Phil. Assistant Professor, Department of MCA, Dr. Sivanthi Aditanar College of Engineering" 89a245eae1e7eda7aa8e360c0cdb4bf6a72da225,A Survey of Pedestrian Detection in Video,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 5, No. 10, 2014 A Survey of Pedestrian Detection in Video Achmad Solichin Department of Informatics Budi Luhur University Jakarta, Indonesia Agus Harjoko Agfianto Eko Putra Dept. of Computer Science and Dept. of Computer Science and Electronics Gadjah Mada University Electronics Gadjah Mada University Yogyakarta, Indonesia Yogyakarta, Indonesia" 89174737423d87258d3b9d5a660236a0bb66a470,On the usage of Sensor Pattern Noise for Picture-to-Identity linking through social network accounts,"On the usage of Sensor Pattern Noise for Picture-to-Identity linking through social network accounts Riccardo Satta1 and Pasquale Stirparo1,2 Institute for the Protection and Security of the Citizen Joint Research Centre (JRC), European Commission, Ispra (VA), Italy Royal Institute of Technology (KTH), Stockholm, Sweden {riccardo.satta, Keywords: social network, account, Sensor Pattern Noise, identity, linking, digital image forensics, multimedia forensics" 89e324b9c64a800e57ad82eddecc03f2cc0b7cc5,Long-Term Identity-Aware Multi-Person Tracking for Surveillance Video Summarization.,"Long-Term Identity-Aware Multi-Person Tracking for Surveillance Video Summarization Shoou-I Yu, Yi Yang, Xuanchong Li, and Alexander G. Hauptmann" d2b86b6dc93631990e21a12278e77f002fb4b116,Aalborg Universitet Attention in Multimodal Neural Networks for Person Re-identification,"Aalborg Universitet Attention in Multimodal Neural Networks for Person Re-identification Lejbølle, Aske Rasch; Krogh, Benjamin; Nasrollahi, Kamal; Moeslund, Thomas B. Published in: 018 IEEE Computer Vision and Pattern Recognition Workshops: Visual Understanding of Humans in Crowd Scene Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Lejbølle, A. R., Krogh, B., Nasrollahi, K., & Moeslund, T. B. (2018). Attention in Multimodal Neural Networks for Person Re-identification. In 2018 IEEE Computer Vision and Pattern Recognition Workshops: Visual Understanding of Humans in Crowd Scene (pp. 179-187). IEEE. General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain ? You may freely distribute the URL identifying the publication in the public portal ?" d2f3ba37ef34d5d39f799f8dd3557f1eb795aedd,Learning Unified Embedding for Apparel Recognition,"Learning Unified Embedding for Apparel Recognition Yang Song Google Yuan Li Google Xiao Zhang Google Bo Wu Google Chao-Yeh Chen Google Hartwig Adam Google" d29cc6d2007920beaa47b24d222981a1e6802ff9,Modeling Affection Mechanisms using Deep and Self-Organizing Neural Networks,"Modeling Affection Mechanisms using Deep and Self-Organizing Neural Networks Dissertation zur Erlangung des Doktorgrades n der Fakult¨at f¨ur Mathematik, Informatik und Naturwissenschaften Fachbereich Informatik der Universit¨at Hamburg eingereicht beim Fach-Promotionsausschuss Informatik von Pablo Vinicius Alves de Barros Hamburg, August 2016" d2bc2c3c933131c1e4b4fedd5e3db1734244b220,City-Scale Road Audit System using Deep Learning,"City-Scale Road Audit System using Deep Learning Sudhir Yarram Girish Varma C.V. Jawahar" d2384ce437e4e6ec82aaade981cda79db13b4dc3,Removing Algorithmic Discrimination (With Minimal Individual Error),"Removing Algorithmic Discrimination (With Minimal Individual Error) El Mahdi El Mhamdi, Rachid Guerraoui, Lˆe Nguyˆen Hoang and Alexandre Maurer" d2df37ecfbf914d5b81e2e5e342e3907c6f55a14,Can Convolution Neural Network ( CNN ) Triumph in Ear Recognition of Uniform Illumination Invariant ?,"Indonesian Journal of Electrical Engineering and Computer Science Vol. 11, No. 2, August 2018, pp. 558~566 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v11.i2.pp558-566  558 Can Convolution Neural Network (CNN) Triumph in Ear Recognition of Uniform Illumination Invariant? Nursuriati Jamil1, Ali Abd Almisreb2, Syed Mohd Zahid Syed Zainal Ariffin3, N. Md Din4, Raseeda Hamzah5 ,3,5Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia ,4College of Graduate Studies, Universiti Tenaga Nasional, Jalan IKRAM-UNITEN, 43000 Kajang, Malaysia Article Info Article history: Received Mar 1, 2018 Revised Apr 21, 2018 Accepted May 1, 2018 Keywords: Convolution Neural Network Ear Recognition Uniform Illumination Invariant" d2518b01092160cecec2e986935b0129b0bbff45,Looking around the Backyard Helps to Recognize Handwritten Digits Anonymous CVPR submission Paper ID 2611,"#2611 CVPR 2008 Submission #2611. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. #2611 Looking around the Backyard Helps to Recognize Handwritten Digits Anonymous CVPR submission Paper ID 2611" d20e7d7ab8e767dc1c170ca2141d8ba64a4d092b,“ Please Draw Me a Face ... ” Atypical Face Mental Concept in Autism,"Psychology, 2014, 5, 1392-1403 Published Online August 2014 in SciRes. http://www.scirp.org/journal/psych http://dx.doi.org/10.4236/psych.2014.511150 “Please Draw Me a Face…” Atypical Face Mental Concept in Autism Emilie Meaux1*, David Bakhos2, Frédérique Bonnet-Brilhault1, Patrice Gillet3, Emmanuel Lescanne4, Catherine Barthélémy1, Magali Batty1 UMRS Imagerie et Cerveau, Inserm U930 Equipe 1, CNRS ERL 3106, Université François Rabelais de Tours, CHRU de Tours, Tours, France Unité Pédiatrique d’ORL et CCF, Centre Hospitalier Régional Universitaire de Tours, Université François Rabelais de Tours, CHRU de Tours, Tours, France Université François Rabelais de Tours, CHRU de Tours, Tours, France Service d’ORL et CCF Pédiatrique, CHU de Tours Gatien-de-Clocheville, Université François Rabelais de Tours, Tours, France Email: Received 16 May 2014; revised 12 June 2014; accepted 5 July 2014 Copyright © 2014 by authors and Scientific Research Publishing Inc. This work is licensed under the Creative Commons Attribution International License (CC BY). http://creativecommons.org/licenses/by/4.0/" d231a81b38fde73bdbf13cfec57d6652f8546c3c,SUPERRESOLUTION TECHNIQUES FOR FACE RECOGNITION FROM VIDEO by,"SUPERRESOLUTION TECHNIQUES FOR FACE RECOGNITION FROM VIDEO Osman Gökhan Sezer B.S., E.E., Boğaziçi University, 2003 Submitted to the Graduate School of Engineering and Natural Sciences in partially fulfillment of the requirement for the degree of Master of Science Graduate Program in Electronics Engineering and Computer Science Sabancı University Spring 2005" d2eb1079552fb736e3ba5e494543e67620832c52,DeSTNet: Densely Fused Spatial Transformer Networks,"ANNUNZIATA, SAGONAS, CALÌ: DENSELY FUSED SPATIAL TRANSFORMER NETWORKS1 DeSTNet: Densely Fused Spatial Transformer Networks1 Roberto Annunziata Christos Sagonas Jacques Calì Onfido Research Finsbury Avenue London, UK" d24a7a7ceb2ddce42ac64d1d07ccebc2a55ed053,A Bayesian Architecture for Combining Saliency Detectors,"A Bayesian Architecture for Combining Saliency Detectors Dashan Gao and Nuno Vasconcelos SVCL-TR 2005/01 June 2005" d24a30ed78b749f3730e25dcef89472dd5fb439c,Improving Face Recognition Performance Using a Hierarchical Bayesian Model,"Improving Face Recognition Performance Using a Hierarchical Bayesian Model Ashwini Shikaripur Nadig Submitted to the graduate degree program in Electrical Engineering & Computer Science and the Graduate Faculty of the University of Kansas School of Engineering in partial fulfillment of the requirements for the degree of Master of Science Thesis Committee: Dr. Brian Potetz: Chairperson Dr. Prasad Kulkarni Dr. Luke Huan Date Defended" d250e57f6b7e06bb1dac41c8b89700086a85999e,Self-Supervised Generalisation with Meta Auxiliary Learning,"Self-Supervised Generalisation with Meta Auxiliary Learning Shikun Liu 1 Andrew J. Davison 1 Edward Johns 1" d2b2b56dd8c1daa61152595caf759a62596a85c9,Revocable and Non-Invertible Multibiometric Template Protection based on Matrix Transformation,"Pertanika J. Sci. & Technol. 26 (1): 133 - 160 (2018) Revocable and Non-Invertible Multibiometric Template Protection based on Matrix Transformation Jegede, A.1,2*, Udzir, N. I.1, Abdullah, A.1 and Mahmod, R.1 Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, 43400 UPM, Serdang, Selangor, Malaysia Department of Computer Science, University of Jos, 930001 Nigeria" d2f254780699bafff02eafc92e00822ee597c864,A comparative evaluation of global representation-based schemes for face verification,"A Comparative Evaluation of Global Representation-Based Schemes for Face Verification S. Cruz-Llanas, J. Fierrez-Aguilar, J. Ortega-Garcia, J. Gonzalez-Rodriguez Biometrics Research Lab. – Universidad Politecnica de Madrid" d28c12e270a06e977b59194cc6564787c87caa7e,HUMAN ACTION POSELETS ESTIMATION VIA COLOR G-SURF IN STILL IMAGES,"HUMAN ACTION POSELETS ESTIMATION VIA COLOR G-SURF IN STILL IMAGES M. Favorskaya *, D. Novikov, Y. Savitskaya Institute of Informatics and Telecommunications, Siberian State Aerospace University, 31 Krasnoyarsky Rabochy av., Krasnoyarsk, 660014 Russian Federation - (favorskaya, Commission WG V/5, WG III/3 KEY WORDS: Human Action, Poselets, Gauge-SURF, Random Forest, Still Image" d2f717d1799b5cec5f1f426511527bd7e6e05d9d,Image-Based Synthesis for Deep 3D Human Pose Estimation,"Noname manuscript No. (will be inserted by the editor) Image-based Synthesis for Deep 3D Human Pose Estimation Grégory Rogez · Cordelia Schmid Received: date / Accepted: date" d27ea28543cc55d84b0700a74743fb1ccd205135,Lernen mit wenigen Beispielen für die visuelle Objekterkennung,"Lernen mit wenigen Beispielen f¨ur die visuelle Objekterkennung Erik Rodner Lehrstuhl Digitale Bildverarbeitung Friedrich-Schiller Universit¨at Jena" d2ada7d9424c056cc555f331dbb23ddab84eeee7,Background Subtraction with Dirichlet Processes,"Background Subtraction with Dirichlet Processes Tom S. F. Haines and Tao Xiang Electronic Engineering and Computer Science, Queen Mary, Uni. of London" d2860bb05f747e4628e95e4d84018263831bab0d,Learning to Generate Samples from Noise through Infusion Training,"Published as a conference paper at ICLR 2017 LEARNING TO GENERATE SAMPLES FROM NOISE THROUGH INFUSION TRAINING Florian Bordes, Sina Honari, Pascal Vincent∗ Montreal Institute for Learning Algorithms (MILA) D´epartement d’Informatique et de Recherche Op´erationnelle Universit´e de Montr´eal Montr´eal, Qu´ebec, Canada" d259d3652f03c7b80e29c986e9540ab00b1f1133,3 D Face Detection and Recognition under Occlusion,"Dr.V.Ramaswamy1, Parashuram Baraki2 Research Guide, Jain University, Bangalore, Doctoral Student, Jain University, Bangalore & Asst.Professor , CS&E, Dept, GM Institute of Technology, Davanagere D Face Detection and Recognition under Occlusion is very vital. Three-dimensional" d2cda0dbb8b2e83ce3e70d818f78d2add803c661,Automatic Video Captioning via Multi-channel Sequential Encoding,"Automatic Video Captioning via Multi-channel Sequential Encoding Chenyang Zhang and Yingli Tian Department of Electrical Engineering The City College of New York New York, NY 10031" d2b8459b41172dc332cf00dc18a309c442347a7d,Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach,"Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach Lingxiao He∗1,2, Jian Liang∗1,2, Haiqing Li1,2, and Zhenan Sun1,2,3 CRIPAC & NLPR, CASIA 2 University of Chinese Academy of Sciences, Beijing, P.R. China Center for Excellence in Brain Science and Intelligence Technology, CAS {lingxiao.he, jian.liang, hqli," d23ac99cdab20a9a3eca2784a5b262649c717988,Rotation Invariant Angular Descriptor Via A Bandlimited Gaussian-like Kernel,"Rotation Invariant Angular Descriptor Via A Bandlimited Gaussian-like Kernel Michael T. McCann, Matthew Fickus, Jelena Kovaˇcevi´c" cda08b49c91c805c4820238f30a5118f30e55bfe,SFS Based View Synthesis for Robust Face Recognition,"SFSBasedViewSynthesisforRobustFaceRecognition WenYiZhao RamaChellappa CenterforAutomationResearch UniversityofMaryland CollegePark,MD- seemtohavereceivedmuchattentioninthecontext" cd0f7b3f545cc4bfa5e2d7185789e8ead7e3cee2,"Children ’ s and Adults ’ Predictions of Black , White , and Multiracial Friendship Patterns","Journal of Cognition and Development ISSN: 1524-8372 (Print) 1532-7647 (Online) Journal homepage: http://www.tandfonline.com/loi/hjcd20 Children’s and Adults’ Predictions of Black, White, nd Multiracial Friendship Patterns Steven O. Roberts, Amber D. Williams & Susan A. Gelman To cite this article: Steven O. Roberts, Amber D. Williams & Susan A. Gelman (2017) Children’s nd Adults’ Predictions of Black, White, and Multiracial Friendship Patterns, Journal of Cognition nd Development, 18:2, 189-208, DOI: 10.1080/15248372.2016.1262374 To link to this article: http://dx.doi.org/10.1080/15248372.2016.1262374 Accepted author version posted online: 22 Nov 2016. Published online: 22 Nov 2016. Submit your article to this journal Article views: 91 View related articles View Crossmark data Citing articles: 1 View citing articles Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=hjcd20 Download by: [University of Michigan]" cd9666858f6c211e13aa80589d75373fd06f6246,A Novel Time Series Kernel for Sequences Generated by LTI Systems,"A Novel Time Series Kernel for Sequences Generated by LTI Systems Liliana Lo Presti, Marco La Cascia V.le delle Scienze Ed.6, DIID, Universit´a degli studi di Palermo, Italy" cdd3b727a8c3129d265ddccd01112655e45c0f4c,Bio-Inspired Pedestrian Detection and Tracking,"Proc. of the Third Intl. Conf. Advances in Bio-Informatics, Bio-Technology and Environmental Engineering- ABBE 2015 Copyright © Institute of Research Engineers and Doctors, USA .All rights reserved. ISBN: 978-1-63248-060-6 doi: 10.15224/ 978-1-63248-060-6-07 Bio-Inspired Pedestrian Detection and Tracking Miguel Farrajota, João M.F. Rodrigues and J.M.H. du Buf" cd827a9dbf82240cb711f049989decada01c8ac7,"Object Localization , Segmentation , and Classification in 3 D Images by","City University of New York (CUNY) CUNY Academic Works Dissertations, Theses, and Capstone Projects Graduate Center -2018 Object Localization, Segmentation, and Classification in 3D Images Allan Zelener The Graduate Center, City University of New York How does access to this work benefit you? Let us know! Follow this and additional works at: https://academicworks.cuny.edu/gc_etds Part of the Artificial Intelligence and Robotics Commons Recommended Citation Zelener, Allan, ""Object Localization, Segmentation, and Classification in 3D Images"" (2018). CUNY Academic Works. https://academicworks.cuny.edu/gc_etds/2531 This Dissertation is brought to you by CUNY Academic Works. It has been accepted for inclusion in All Dissertations, Theses, and Capstone Projects y an authorized administrator of CUNY Academic Works. For more information, please contact" cd855c776240150f4dba7a5975c7011a9c6737ac,On Accurate and Reliable Anomaly Detection for Gas Turbine Combustors : A Deep Learning Approach,"On Accurate and Reliable Anomaly Detection for Gas Turbine Combustors: A Deep Learning Approach Weizhong Yan1 and Lijie Yu2 General Electric Global Research Center, Niskayuna, New York 12309, USA General Electric Power & Water Engineering, Atlanta, Georgia 30339, USA" cd516ae100bcb698ce90b7d588ee06a27284c1a8,FaceID-Grid : A Grid Platform for Face Detection and Identification in Video Storage,"FaceID-Grid: A Grid Platform for Face Detection and Identification in Video Storage Filipe Rodrigues Instituto Superior T´ecnico" cd2c1e542ae8c08cfb8baea3dff788d143232de8,Multiview Human Synthesis From a Single View,"Multiview Human Synthesis From a Singleview Si Wen (06246679), Tiancong Zhou (06247022), Honghao Qiu (06246258) {wensi, longztc," cd4252d1f0a124dcc91af28f527ad1fa7be3a195,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" cd32ea4eae50f60584fac6001d2af22a8c1d8648,HEVC Inter Coding Using Deep Recurrent Neural Networks and Artificial Reference Pictures,"HEVC INTER CODING USING DEEP RECURRENT NEURAL NETWORKS AND ARTIFICIAL REFERENCE PICTURES Felix Haub, Thorsten Laude and J¨orn Ostermann Leibniz University Hannover, Institut f¨ur Informationsverarbeitung, Appelstr. 9a, 30167 Hannover, Germany" cd0a04c0af9b6c523884415ba54bff370fd02fab,Generalized Sparselet Models for Real-Time Multiclass Object Recognition,"Generalized Sparselet Models for Real-Time Multiclass Object Recognition Hyun Oh Song, Ross Girshick, Stefan Zickler, Christopher Geyer, Pedro Felzenszwalb, and Trevor Darrell" cd36768795c696c990ff5c89be8d8b3b205858bd,CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension,"CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension∗ Simon ˇSuster and Walter Daelemans Computational Linguistics & Psycholinguistics Research Center, University of Antwerp, Belgium" cdba015be9db1e047a51b7e06403528b3551587e,SHOG - Spherical HOG Descriptors for Rotation Invariant 3D Object Detection,"SHOG - Spherical HOG Descriptors for Rotation Invariant 3D Object Detection Henrik Skibbe1,3, Marco Reisert2 and Hans Burkhardt1,3 Department of Computer Science, University of Freiburg, Germany Dept. of Diagnostic Radiology, Medical Physics, University Medical Center, Freiburg Center for Biological Signalling Studies (BIOSS), University of Freiburg" cd01a0018f2b8f1211e8dfe311c28e32773c58dc,Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence,"Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence Dylan Campbell1,2, Lars Petersson1,2, Laurent Kneip1 and Hongdong Li1 Australian National University* Data61 – CSIRO" cda4fb9df653b5721ad4fe8b4a88468a410e55ec,Gabor wavelet transform and its application,"Gabor wavelet transform and its application Wei-lun Chao R98942073" cd6978bf6b98794552bd52d166b5e04626fb6d6d,A Review on Face Recognition in various Illuminations,"A Review on Face Recognition in various Illuminations Saurabh D. Parmar , Vaishali j. kalariya CE/IT Department-School of Engineering,R.K. University,Rajkot" cd444ee7f165032b97ee76b21b9ff58c10750570,Table of Contents.,"UNIVERSITY OF CALIFORNIA, IRVINE Relational Models for Human-Object Interactions and Object Affordances DISSERTATION submitted in partial satisfaction of the requirements for the degree of DOCTOR OF PHILOSOPHY in Computer Science Chaitanya Desai Dissertation Committee: Professor Deva Ramanan, Chair Professor Charless Fowlkes Professor Padhraic Smyth Professor Serge Belongie" cd5ef3aeebc231e2c833ef55cf0571aa990c5ff8,IMAGE QUALITY ASSESSMENT TECHNIQUES IMPROVE TRAINING,"Under review as a conference paper at ICLR 2018 IMAGE QUALITY ASSESSMENT TECHNIQUES IMPROVE TRAINING AND EVALUATION OF ENERGY-BASED GENERATIVE ADVERSARIAL NETWORKS Anonymous authors Paper under double-blind review" cdf817a64c389615c2d3098ea1c4f48d10ca24cd,Recognizing faces with single sample per subject using fusion of transforms,"Recognizing faces with single sample per subject using fusion of transforms Sujata G. Bhele Priyadarshini College of Engineering, CRPF gate, Nagpur Vijay H. Mankar Government Polytechnic, Bramhapuri" cd3005753012409361aba17f3f766e33e3a7320d,Multilinear Biased Discriminant Analysis: A Novel Method for Facial Action Unit Representation,"Multilinear Biased Discriminant Analysis: A Novel Method for Facial Action Unit Representation Mahmoud Khademi†, Mehran Safayani†and Mohammad T. Manzuri-Shalmani† : Sharif University of Tech., DSP Lab," cd8398e82e0c0cc4276a1694fd333214ede337ea,Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation,"Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation Tianyi Zhang, Guosheng Lin, Jianfei Cai, Tong Shen, Chunhua Shen, Alex C. Kot," cd687ddbd89a832f51d5510c478942800a3e6854,A game to crowdsource data for affective computing,"A Game to Crowdsource Data for Affective Computing Chek Tien Tan Hemanta Sapkota Daniel Rosser Yusuf Pisan Games Studio, Faculty of Engineering and IT, University of Technology, Sydney" cd596a2682d74bdfa7b7160dd070b598975e89d9,Mood Detection : Implementing a facial expression recognition system,"Mood Detection: Implementing a facial expression recognition system Neeraj Agrawal, Rob Cosgriff and Ritvik Mudur . Introduction Facial expressions play a significant role in human dialogue. As a result, there has been onsiderable work done on the recognition of emotional expressions and the application of this research will be beneficial in improving human-machine dialogue. One can imagine the improvements to computer interfaces, automated clinical (psychological) research or even interactions between humans and autonomous robots. Unfortunately, a lot of the literature does not focus on trying to achieve high recognition rates cross multiple databases. In this project we develop our own mood detection system that ddresses this challenge. The system involves pre-processing image data by normalizing and pplying a simple mask, extracting certain (facial) features using PCA and Gabor filters and then using SVMs for classification and recognition of expressions. Eigenfaces for each class are used to determine class-specific masks which are then applied to the image data and used to train multiple, one against the rest, SVMs. We find that simply using normalized pixel intensities works well with such an approach. Figure 1 – Overview of our system design . Image pre-processing We performed pre-processing on the images used to train and test our algorithms as follows:" b20ccf72adae61b3c0831eae137a45c55d7f7a32,AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation,"DomainAdaDepthPredicted DepthSynthetic DomainResnet-50EncoderDecoder CNNFigure1.Illustrationoftheproposeddomainadaptationmethodwithinputimagedomaindiscrepancy(redandbluebackground)followedbydepth-mapprediction.ColorcodedarrowsrepresentcorrespondingRGBimageanddepthpredictionsforthesynthetic-trainedencoder(redandpinkbordered)andfortheadapteden-coder(bluebordered);indicatingthatsynthetic-trainedmodelshowssub-optimalperformanceonnaturalimages.oftenperformsub-optimallywhentestedonrealscenes,showinglackofgeneralization[19,35].Fromaprobabilis-ticperspective,consideringinputsamplesforanetworkbe-ingdrawnfromacertainsourcedistribution,thenetworkcanperformsufficientlywellontestsetonlyifthetestdataisalsosampledfromthesamedistribution.Hence,thegen-eralapproachhasbeentotransferlearnedrepresentationsfromsynthetictorealdatasetsbyfine-tuningthemodelonamixedsetofsamples[42].Fordepthestimationtasks,theground-truthacquiredus-ingdeviceslikeKinectorotherdepthsensorsexhibitsnoisyartifacts[40]andhenceseverelylimitstheperformanceofasuperviseddepthpredictionnetwork.InthewidelyusedNYUDepthDataset[34],suchcasesareaddressedbyman-uallyinpaintingthedepthvaluesinthedistortedregions.Butthedatasethasonlyahandfulofsuchcraftedsamples,mainlybecausetheprocessislaboriousandpronetopixel-levelannotationerrors.Theseshortcomingsshowtheneedforaframeworkthatisminimallydependentonscarceclean" b2026f7ba664e976afe8d83560d7538e47e9af5e,Generalizing multistain immunohistochemistry tissue segmentation using one-shot color deconvolution deep neural networks,"Generalizing multistain immunohistochemistry tissue segmentation using one-shot color deconvolution deep neural networks Amal Lahiani1,3, Jacob Gildenblat2, Irina Klaman1, Nassir Navab3, and Eldad Klaiman1 Pathology and Tissue Analytics, Pharma Research and Early Development, Roche Innovation Computer Aided Medical Procedures, Technische Universität München, Germany {amal.lahiani, irina.klaman, Center Munich SagivTech LTD., Israel" b2e1b3b2342d29b1abbe92caffca703622ee4274,Automating the Processes Involved in Facial Composite Production and Identification,"Automating the Processes Involved in Facial Composite Production and Identification Charlie Frowd*, Anna Petkovic, Kamran Nawaz and Yasmeen Bashir School of Psychology, University of Central Lancashire, Preston, UK *Corresponding author: Dr Charlie Frowd, School of Psychology, University of Central Lancashire, Preston PR1 2HE. Email: Phone: (01772) 893439." b2624c3cb508bf053e620a090332abce904099a1,Dynamic Memory Networks for Visual and Textual Question Answering,"Dynamic Memory Networks for Visual and Textual Question Answering Caiming Xiong*, Stephen Merity*, Richard Socher MetaMind, Palo Alto, CA USA {CMXIONG,SMERITY,RICHARD}METAMIND.IO *indicates equal contribution." b261439b5cde39ec52d932a222450df085eb5a91,Facial Expression Recognition using Analytical Hierarchy Process,"International Journal of Computer Trends and Technology (IJCTT) – volume 24 Number 2 – June 2015 Facial Expression Recognition using Analytical Hierarchy Process MTech Student 1 , Assistant Professor 2 , Department of Computer Science and Engineeringt1, 2, Disha Institute of Management and Technology, Raipur Chhattisgarh, India1, 2 Vinita Phatnani1, Akash Wanjari2, its significant contribution" b277bde51641d6b08693c171aea761beb14af800,FACE KERNEL EXTRACTION FROM LOCAL FEATURES,"FACE KERNEL EXTRACTION FROM LOCAL FEATURES A thesis submitted to the University of Manchester for the degree of Doctor of Philosophy in the Faculty of Engineering and Physical Sciences Maria Pavlou School of Electrical Engineering and Electronics" b2abaffc4d68ebf910dd85c0f7a367895ab90e2a,Iris recognition using scattering transform and textural features,"IRIS RECOGNITION USING SCATTERING TRANSFORM AND TEXTURAL FEATURES Shervin Minaee, AmirAli Abdolrashidi and Yao Wang ECE Department, NYU Polytechnic School of Engineering, USA {shervin.minaee, abdolrashidi," b2504b0b2a7e06eab02a3584dd46d94a3f05ffdf,Conditional Neural Processes,"Conditional Neural Processes Marta Garnelo 1 Dan Rosenbaum 1 Chris J. Maddison 1 Tiago Ramalho 1 David Saxton 1 Murray Shanahan 1 2 Yee Whye Teh 1 Danilo J. Rezende 1 S. M. Ali Eslami 1" b28e142376a2dd639f58935f2f63a9dc7651131e,Investigation of Gait Representations in Lower Knee Gait Recognition, b235b4ccd01a204b95f7408bed7a10e080623d2e,Regularizing Flat Latent Variables with Hierarchical Structures,"Regularizing Flat Latent Variables with Hierarchical Structures Rongcheng Lin(cid:117) , Huayu Li(cid:117) , Xiaojun Quan† , Richang Hong(cid:63) , Zhiang Wu∓ , Yong Ge(cid:117) (cid:117)UNC Charlotte. Email: {rlin4, hli38, (cid:63) Hefei University of Technology. Email: Institute for Infocomm Research. Email: ∓ Nanjing University of Finance and Economics. Email:" b285e50220fb6c09cf3c724c7e48093373df3c58,Semisupervised Classifier Evaluation and Recalibration,"Semisupervised Classifier Evaluation nd Recalibration Peter Welinder∗, Max Welling†, and Pietro Perona‡ October 7, 2012" b29d70f38bd4759cd9d8c2fdc9312f7f807f4fa9,Face Recognition in Subspaces,"Chapter 2 Face Recognition in Subspaces Gregory Shakhnarovich and Baback Moghaddam .1 Introduction Images of faces, represented as high-dimensional pixel arrays, often belong to a manifold of intrinsically low dimension. Face recognition, and computer vision re- search in general, has witnessed a growing interest in techniques that capitalize on this observation and apply algebraic and statistical tools for extraction and analy- sis of the underlying manifold. In this chapter, we describe in roughly chronologic order techniques that identify, parameterize, and analyze linear and nonlinear sub- spaces, from the original Eigenfaces technique to the recently introduced Bayesian method for probabilistic similarity analysis. We also discuss comparative experi- mental evaluation of some of these techniques as well as practical issues related to the application of subspace methods for varying pose, illumination, and expression. .2 Face Space and Its Dimensionality Computer analysis of face images deals with a visual signal (light reflected off the surface of a face) that is registered by a digital sensor as an array of pixel values. The pixels may encode color or only intensity. In this chapter, we assume the latter ase (i.e., gray-level imagery). After proper normalization and resizing to a fixed m-by-n size, the pixel array can be represented as a point (i.e., vector) in an mn-" b2c25af8a8e191c000f6a55d5f85cf60794c2709,A novel dimensionality reduction technique based on kernel optimization through graph embedding,"Noname manuscript No. (will be inserted by the editor) A Novel Dimensionality Reduction Technique based on Kernel Optimization Through Graph Embedding N. Vretos, A. Tefas and I. Pitas the date of receipt and acceptance should be inserted later" b2444e837095706998b03fa5fed223411b9d4d55,Color Based Tracing in Real-Life Surveillance Data,"Color Based Tracing in Real-life Surveillance Michael J. Metternich, Marcel Worring, and Arnold W.M. Smeulders ISLA-University of Amsterdam, Science Park 107, 1098 XG Amsterdam, The Netherlands http://www.science.uva.nl/research/isla/" b2e67e67e5bbb19a02524afcc217929b0a76a9a7,Chapter 12 Using Ocular Data for Unconstrained Biometric Recognition,"Face Recognition in Adverse ConditionsMaria De MarsicoSapienza University of Rome, ItalyMichele NappiUniversity of Salerno, ItalyMassimo TistarelliUniversity of Sassari, ItalyA volume in the Advances in Computational Intelligence and Robotics (ACIR) Book Series" b2f4871cf9f61c44b16c733369d8730e90d9cc0d,The role of emotion in problem solving: first results from observing chess,"The Role of Emotion in Problem Solving: First Results from Observing Chess Thomas Guntz1, James L. Crowley1, Dominique Vaufreydaz1, Raffaella Balzarini1, Philippe Dessus1,2 Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LIG, 38000 Grenoble, France Univ. Grenoble Alpes, LaRAC, 38000 Grenoble, France Author version" b2e2260b8d811948e71898d3adfa8aa6b64fe125,Learning Arbitrary Potentials in CRFs with Gradient Descent,"Learning Arbitrary Potentials in CRFs with Gradient Descent M˚ans Larsson1 Fredrik Kahl1,2 Chalmers Univ. of Technology 2Lund Univ. Shuai Zheng3 Anurag Arnab3 Oxford Univ. Philip Torr3 Richard Hartley4 Australian National Univ." b26f6e3cad2b3d129c0e70e9307ce9197cad2123,Robust Wearable Camera Localization as a Target Tracking Problem on SE(3),"G.BOURMAUD ET AL.: ROBUST WEARABLE CAMERA LOCALIZATION Robust Wearable Camera Localization as a Target Tracking Problem on SE(3) Guillaume Bourmaud Audrey Giremus IMS Laboratory CNRS UMR 5218 University of Bordeaux France" b266be4d9fab8bf307ee2e6fdd6180ac7f6ef893,Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark,"Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark Xiaodan Liang, Ke Gong, Xiaohui Shen, and Liang Lin" b2891e43c7b5dcd889f1a270721209a9cb9cfb49,Human Emotion Detection and Recognition from Still Images,"Human Emotion Detection and Recognition from Still Images Zareena Student, VTU RC, Mysore E-mail ID-" b22b4817757778bdca5b792277128a7db8206d08,SCAN: Learning Hierarchical Compositional Visual Concepts,"Published as a conference paper at ICLR 2018 SCAN: LEARNING HIERARCHICAL COMPOSITIONAL VISUAL CONCEPTS Irina Higgins, Nicolas Sonnerat, Loic Matthey, Arka Pal, Christopher P Burgess, Matko Bošnjak, Murray Shanahan, Matthew Botvinick, Demis Hassabis, Alexander Lerchner DeepMind, London, UK {irinah,sonnerat,lmatthey,arkap,cpburgess," b288353fcd8da86e9c55f9f82768492b2de25596,DATA PROCESSING AND RECORDING USING A VERSATILE MULTI-SENSOR VEHICLE,"DATA PROCESSING AND RECORDING USING A VERSATILE MULTI-SENSOR VEHICLE Bj¨orn Borgmann∗, Volker Schatz, Hilke Kieritz, Clemens Scherer-Kl¨ockling, Marcus Hebel, Michael Arens Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, Gutleuthausstr. 1, 76275 Ettlingen, Germany (bjoern.borgmann, volker.schatz, clemens.scherer-kloeckling, marcus.hebel, Commission I, WG 6 KEY WORDS: Mobile, Multi-sensor, System, LiDAR, Camera" b20a5427d79c660fe55282da2533071629bfc533,Deep Learning Advances on Different 3D Data Representations: A Survey,"Deep Learning Advances on Different 3D Data Representations: A Survey Eman Ahmed, Alexandre Saint, Abd El Rahman Shabayek, Kseniya Cherenkova, Rig Das, Gleb Gusev, Djamila Aouada and Bj¨orn Ottersten" b2f63863e73a8565895ca3d9d7d6a1e10a7695b1,Efficient Neural Network Compression via Transfer Learning for Industrial Optical Inspection,"Efficient Neural Network Compression via Transfer Learning for Industrial Optical Inspection Anonymous Author(s) Affiliation Address email" 0ec17d929f62660fb3d1bcdd791f9639034f5344,How Do We Evaluate Facial Emotion Recognition ?,"Psychology & Neuroscience 016, Vol. 9, No. 2, 153–175 983-3288/16/$12.00 © 2016 American Psychological Association http://dx.doi.org/10.1037/pne0000047 How Do We Evaluate Facial Emotion Recognition? Ana Idalina de Paiva-Silva Universidade de Brasília and Universidade Federal de Goiás Marta Kerr Pontes, Juliana Silva Rocha Aguiar, and Wânia Cristina de Souza Universidade de Brasília The adequate interpretation of facial expressions of emotion is crucial for social functioning and human interaction. New methods are being applied, and a review of the methods that are used to evaluate facial emotion recognition is timely for the field. An extensive review was conducted using the Web of Science, PsycINFO, and PubMed databases. The following keywords were used to identify articles that were published within the past 20 years: emotion recognition, face, expression, and assessment. The initial search yielded 291 articles. After applying the exclusion criteria, 115 articles" 0ef40a21edf2b48c73fd51c21d213ee69ca30a4b,Hidden Markov model as a framework for situational awareness, 0e5640677feb2e1d78639b516f7977e80d9d394f,Volume-based Human Re-identification with RGB-D Cameras,"Cosar, S., Coppola, C. and Bellotto, N. Volume-based Human Re-identification with RGB-D Cameras. In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017) - Volume 4: VISAPP, pages 89-397 ISBN: 978-989-758-225-7 Copyright c(cid:13) 2017 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved" 0e78af9bd0f9a0ce4ceb5f09f24bc4e4823bd698,Spontaneous Subtle Expression Recognition: Imbalanced Databases and Solutions,"Spontaneous Subtle Expression Recognition: Imbalanced Databases & Solutions (cid:63) Anh Cat Le Ngo1, Raphael Chung-Wei Phan1, John See2 Faculty of Engineering, Multimedia University (MMU), Cyberjaya, Malaysia Faculty of Computing & Informatics, Multimedia University (MMU), Cyberjaya, Malaysia" 0e986f51fe45b00633de9fd0c94d082d2be51406,"Face detection, pose estimation, and landmark localization in the wild","Face Detection, Pose Estimation, and Landmark Localization in the Wild Xiangxin Zhu Deva Ramanan Dept. of Computer Science, University of California, Irvine" 0e2c88bc1c7e79d6759b3ed26d78746d0c848373,HUMAN FACIAL ILLUSTRATIONS : CREATION AND EVALUATION USING BEHAVIORAL STUDIES AND FUNCTIONAL MAGNETIC RESONANCE IMAGING,"HUMAN FACIAL ILLUSTRATIONS: CREATION AND EVALUATION USING BEHAVIORAL STUDIES AND FUNCTIONAL MAGNETIC RESONANCE IMAGING Bruce Gooch A dissertation submitted to the faculty of The University of Utah in partial ful(cid:12)llment of the requirements for the degree of Doctor of Philosophy Computer Science School of Computing The University of Utah July 2003" 0efdd82a4753a8309ff0a3c22106c570d8a84c20,LDA WITH SUBGROUP PCA METHOD FOR FACIAL IMAGE RETRIEVAL,"LDA WITH SUBGROUP PCA METHOD FOR FACIAL IMAGE RETRIEVAL Wonjun Hwang, Tae-Kyun Kim, Seokcheol Kee Human Computer Interaction Lab., Samsung Advanced Institute of Technology, Korea." 0ef99317c2ab67923c1657c05f2eba5a280a54eb,Incremental adaptation of fuzzy ARTMAP neural networks for video-based face classification,"Proceedings of the 2009 IEEE Symposium on Computational Intelligence in Security and Defense Applications (CISDA 2009) Incremental Adaptation of Fuzzy ARTMAP Neural Networks for Video-Based Face Classification Jean-Franc¸ois Connolly, Eric Granger, and Robert Sabourin" 0edd3517579a110da989405309e4235e47dd8937,Performance and security analysis of Gait-based user authentication,"Performance and Security Analysis of Gait-based User Authentication Doctoral Dissertation by Davrondzhon Gafurov Submitted to the Faculty of Mathematics and Natural Sciences at the University of Oslo in partial fulfillment of the requirements for the degree Philosophiae Doctor (PhD) in Computer Science" 0eac652139f7ab44ff1051584b59f2dc1757f53b,Efficient Branching Cascaded Regression for Face Alignment under Significant Head Rotation,"Efficient Branching Cascaded Regression for Face Alignment under Significant Head Rotation Brandon M. Smith Charles R. Dyer University of Wisconsin–Madison" 0e13f7fc698cbe78ddbf3412b13ca27a4d878fa8,Greater need to belong predicts a stronger preference for extraverted faces ☆,"See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/306357929 Greater need to belong predicts a stronger preference for extraverted faces ☆ Article in Personality and Individual Differences · January 2017 DOI: 10.1016/j.paid.2016.08.012 CITATION authors, including: READS Mitch Brown University of Southern Mississippi 6 PUBLICATIONS 5 CITATIONS SEE PROFILE Some of the authors of this publication are also working on these related projects: Metaphor and Disease View project Limbal Rings View project All content following this page was uploaded by Mitch Brown on 10 November 2016. The user has requested enhancement of the downloaded file." 0e8f529458db2fbede1274758f4651580ef5fda4,Chapter 1 Talking-face authentication,"Chapter 1 Talking-face authentication Herv´e Bredin, Aur´elien Mayoue and G´erard Chollet .1 Introduction Numerous studies have exposed the limits of biometric identity verification based on single modality (such as fingerprint, iris, handwritten signature, voice, face). The talking face modality, that includes both face recognition and speaker verification, is a natural choice for multimodal biometrics. Talking faces provide richer opportu- nities for verification than does any ordinary multimodal fusion. The signal contains not only voice and image but also a third source of information: the simultaneous dynamics of these features. Natural lip motion and the corresponding speech signal re synchronized. However, this specificity is often forgotten and most of the existing talking-face au- thentication systems are based on the fusion of the scores of two separate modules of face verification and speaker verification. Even though this prevalent paradigm may lead to the best performance on widespread evaluation frameworks based on ran- dom impostor scenarios, the question of its performance against real life impostor ttacks has to be studied. .2 State of the art In the existing literature, talking-face identity verification is often refered to as" 0ee1916a0cb2dc7d3add086b5f1092c3d4beb38a,The Pascal Visual Object Classes (VOC) Challenge,"Int J Comput Vis (2010) 88: 303–338 DOI 10.1007/s11263-009-0275-4 The PASCAL Visual Object Classes (VOC) Challenge Mark Everingham · Luc Van Gool · Christopher K. I. Williams · John Winn · Andrew Zisserman Received: 30 July 2008 / Accepted: 16 July 2009 / Published online: 9 September 2009 © Springer Science+Business Media, LLC 2009" 0efa6a6f385ce1d9eff6410ffc43e1f5a3c24f21,A minimax approach to Bayesian estimation with partial knowledge of the observation model,"A MINIMAX APPROACH TO BAYESIAN ESTIMATION WITH PARTIAL KNOWLEDGE OF THE OBSERVATION MODEL Tomer Michaeli and Yonina C. Eldar Department of Electrical Engineering Technion–Israel Institute of Technology, Haifa, Israel" 0eb45876359473156c0d4309f548da63470d30ee,A Deeply-Initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment,"A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment Roberto Valle1[0000−0003−1423−1478], Jos´e M. Buenaposada2[0000−0002−4308−9653], Antonio Vald´es3, and Luis Baumela1 Univ. Polit´ecnica de Madrid, Spain. Univ. Rey Juan Carlos, Spain. Univ. Complutense de Madrid, Spain." 0e2ea7af369dbcaeb5e334b02dd9ba5271b10265,Multi-Level Feature Abstraction from Convolutional Neural Networks for Multimodal Biometric Identification, 0ed91520390ebdee13a0ac13d028f65d959bdc10,Hard Example Mining with Auxiliary Embeddings,"Hard Example Mining with Auxiliary Embeddings Evgeny Smirnov Speech Technology Center Aleksandr Melnikov ITMO University Andrei Oleinik ITMO University melnikov Elizaveta Ivanova Ilya Kalinovskiy Speech Technology Center Speech Technology Center Eugene Luckyanets ITMO University" 0ef93418f420f1f0f71d6a66d54d13b143179cc4,Intrinsic image decomposition from multiple photographs,"UNIVERSITYOFNICE-SOPHIAANTIPOLISDOCTORALSCHOOLSTICSCIENCESETTECHNOLOGIESDEL’INFORMATIONETDELACOMMUNICATIONPHDTHESIStoobtainthetitleofPhDofScienceoftheUniversityofNice-SophiaAntipolisSpecialty:COMPUTERSCIENCEDefendedbyPierre-YvesLAFFONTIntrinsicimagedecompositionfrommultiplephotographsThesisAdvisor:GeorgeDRETTAKISCo-Advisor:AdrienBOUSSEAUpreparedatINRIASophiaAntipolis,REVESTeamdefendedonOctober12,2012Reviewers:BrianCURLESS-UniversityofWashingtonHendrikP.A.LENSCH-UniversitätTübingenAdvisor:GeorgeDRETTAKIS-REVES/INRIASophiaAntipolisCo-advisor:AdrienBOUSSEAU-REVES/INRIASophiaAntipolisPresident:FrédéricPRECIOSO-Polytech’Nice-SophiaExaminer:DiegoGUTIERREZ-UniversidaddeZaragoza" 0e49a23fafa4b2e2ac097292acf00298458932b4,Unsupervised Detection of Outlier Images Using Multi-Order Image Transforms,"Theory and Applications of Mathematics & Computer Science 3 (1) (2013) 13–31 Unsupervised Detection of Outlier Images Using Multi-Order Image Transforms Lior Shamira,∗ Lawrence Technological University, 21000 W Ten Mile Rd., Southfield, MI 48075, United States." 0e767d8a88cdeea1a4338817c0e6ea3640ba4232,Deep Learning Architectures for Face Recognition in Video Surveillance,"Deep Learning Architectures for Face Recognition in Video Surveillance Saman Bashbaghi, Eric Granger, Robert Sabourin and Mostafa Parchami" 0ecaabbf846bbc78c91bf7ff71b998b61c0082d8,Automated Visual Fin Identification of Individual Great White Sharks,"Noname manuscript No. (will be inserted by the editor) Automated Visual Fin Identification of Individual Great White Sharks Benjamin Hughes and Tilo Burghardt Received: date / Accepted: date" 0eff410cd6a93d0e37048e236f62e209bc4383d1,Learning discriminative MspLBP features based on Ada-LDA for multi-class pattern classification,"Anchorage Convention District May 3-8, 2010, Anchorage, Alaska, USA 978-1-4244-5040-4/10/$26.00 ©2010 IEEE" 0e7862580028aa80c409b52ef1fa683444afcbcd,Reducing the Dimensionality of Face Space in a Sparse Distributed Local-Features Representation,"(cid:3) Reducing the Dimensionality of Face Space in a Sparse Distributed Local-Features Representation Laboratory of Computational Neuroscience 230 York Avenue, New York, NY 10021 The Rockefeller University Penio S. Penev" 0e9f7d8554e065a586163845dd2bfba26e55cefb,Registration of 3 D Face Scans with Average Face Models ∗,"Registration of 3D Face Scans with Average Face Models Albert Ali Salah1,2, Ne¸se Aly¨uz1, Lale Akarun1 {salah, nese.alyuz, Bo˘gazi¸ci University, 4342 Bebek, ˙Istanbul, Turkey Phone: +90 212 359 4523-24 Fax: +90 212 287 2461 Centrum voor Wiskunde en Informatica, Kruislaan 413, 1098 SJ, 94079, The Netherlands Phone: +31 020 592 4214 Fax: +31 020 592 4199" 0e50fe28229fea45527000b876eb4068abd6ed8c,Angle Principal Component Analysis,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 0efb7d1413ada560ab1aee1ea4cc94d80737e662,Performance Analysis of Eye localization Methods for Real Time Vision Interface using Low Grade Video Camera,"International Journal of Computer Applications (0975 – 8887) Volume 114 – No. 2, March 2015 Performance Analysis of Eye localization Methods for Real Time Vision Interface using Low Grade Video Krupa Jariwala Assistant Professor Computer Engineering Department SVNIT, Surat Camera Upena Dalal, Ph.D. Associate Professor Electronics Engineering Department SVNIT, Surat" 0e031312cb6e1634e3115e428505e2be9ef46b75,Explicit Knowledge-based Reasoning for Visual Question Answering,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) giraffe people people Attributes: glass house room standing walking wall zoo Scenes: museum indoor Visual Question: How many giraffes are there in the image? Answer: Two. Common-Sense Question: Is this image related to zoology? Answer: Yes. Reason: Object/Giraffe --> Herbivorous animals --> Animal --> Zoology; Attribute/Zoo --> Zoology. KB-Knowledge Question: What are the common properties between the animal in this image and zebra? Answer: Herbivorous animals; Animals; Megafauna of Africa. Figure1:ArealexampleoftheproposedKB-VQAdatasetandtheresultsgivenbyAhab,theproposedVQAapproach.Ourapproachanswersquestionsbyextractingseveraltypesofvisualconceptsfromanimageandaligningthemtolarge-scalestructuredknowl-edgebases.Apartfromanswers,ourapproachcanalsoproviderea-sonsandexplanationsforcertaintypesofquestions.itisansweringthequestionbasedonimageinformation,orjusttheprevalenceofaparticularanswerinthetrainingset.Thesecondproblemisthatbecausethemodelistrainedonindividualquestion/answerpairs,therangeofquestionsthatcanbeaccuratelyansweredislimited.Answeringgeneralquestionsposedbyhumansaboutimagesinevitablyrequiresreferencetoadiversevarietyofinformationnotcontainedintheimageitself.CapturingsuchlargeamountofinformationwouldrequireanimplausiblylargeLSTM,andacompletelyimpracticalamountoftrainingdata.Thethird,andmajor,problemwiththeLSTMapproachisthatitisincapableofex-plicitreasoningexceptinverylimitedsituations[Rockt¨ascheletal.,2016].OurmaincontributionisamethodwecallAhab1foran-sweringawidevarietyofquestionsaboutimagesthatrequire1Ahab,thecaptaininthenovelMobyDick,iseitherabrilliantvisionary,oradeludedfanatic,dependingonyourperspective." e9c8594ce3b8c555df59ff32b1a71eb62722b38c,On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach,"On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach Nikolai Smolyanskiy {nsmolyanskiy, akamenev, Alexey Kamenev NVIDIA Stan Birchfield" e9af96d478b487fec9a06dde9e43b2ed3355ea7b,Automatic thresholding of SIFT descriptors,"AUTOMATIC THRESHOLDING OF SIFT DESCRIPTORS Matthew R. Kirchner Image and Signal Processing Branch, Research Office, Code 4F0000D Naval Air Warfare Center Weapons Division, China Lake, CA 93555 USA" e941ee2d584938e6509c0676466023f8b43b9486,Appearance based tracking with background subtraction,"The 8th International Computer Science April 26-28, 2013. Colombo, Sri Lanka & Education (ICCSE 2013) Conference on SuD1.4 Appearance Based Tracking with Background Dileepa Joseph Jayamanne Subtraction Jayathu Samarawickrama Ranga Rodrigo Electronic Engineering Telecommunication Electronic Engineering Telecommunication Telecommunication Electronic" e917bb1f7efdfc448b8b63c52e8f643e68630a11,3 D information is valuable for the detection of humans in video streams,"D information is valuable for the detection of humans in video streams Sébastien Piérard Antoine Lejeune Marc Van Droogenbroeck INTELSIG Laboratory Montefiore Institute University of Liège, Belgium INTELSIG Laboratory Montefiore Institute University of Liège, Belgium INTELSIG Laboratory Montefiore Institute University of Liège, Belgium Email : Email : Email :" e9fcd15bcb0f65565138dda292e0c71ef25ea8bb,Analysing Facial Regions for Face Recognition Using Forensic Protocols,"Repositorio Institucional de la Universidad Autónoma de Madrid https://repositorio.uam.es Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: Highlights on Practical Applications of Agents and Multi-Agent Systems: International Workshops of PAAMS. Communications in Computer and Information Science, Volumen 365. Springer, 2013. 223-230 DOI: http://dx.doi.org/10.1007/978-3-642-38061-7_22 Copyright: © 2013 Springer-Verlag El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription" e909b9e0bbfc37d0b99acad5014e977daac7e2bd,Adversarial Training of Variational Auto-Encoders for High Fidelity Image Generation,"Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation Salman H. Khan†, Munawar Hayat ‡, Nick Barnes † Data61 - CSIRO and ANU, Australia, ‡University of Canberra, Australia," e91c7dbd33a3047c70d550e201ebdf4353cbe929,Re-identification for Online Person Tracking by Modeling Space-Time Continuum,"Re-identification for Online Person Tracking by Modeling Space-Time Continuum Neeti Narayan, Nishant Sankaran, Srirangaraj Setlur and Venu Govindaraju University at Buffalo, SUNY {neetinar, n6, setlur," e952994fbcd3b6ad9bc52101ee0240e9de6095c8,"Comparative study of speaker verification techniques based on vector quantization , sphericity models and dynamic time warping ∗","Comparative study of speaker verification techniques ased on vector quantization, sphericity models and dynamic time warping Sofia Tsekeridou† C. Kotropoulos† A. Xafopoulos† I. Pitas†" e9c9da57bbf9a968489cb90ec7252319bcab42fb,Hard Mixtures of Experts for Large Scale Weakly Supervised Vision,"Hard Mixtures of Experts for Large Scale Weakly Supervised Vision Sam Gross, Marc’Aurelio Ranzato, and Arthur Szlam Facebook AI Research (FAIR)" e939fb6b762de242b22e295940e0d9d7d259e442,Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos,"Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos Vincent Casser∗1 Soeren Pirk Reza Mahjourian2 Anelia Angelova Institute for Applied Computational Science, Harvard University; Google Brain Google Brain University of Texas at Austin; Google Brain {pirk, rezama," e988be047b28ba3b2f1e4cdba3e8c94026139fcf,Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition,"Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition Xi Yin and Xiaoming Liu Member, IEEE," e9ac109c395ededb23dfc78fe85d76eeb772ee7e,A Multilevel Mixture-of-Experts Framework for Pedestrian Classification,"A Multilevel Mixture-of-Experts Framework for Pedestrian Classification Markus Enzweiler and Dariu M. Gavrila" e991ff3b28c46279a3bee2446d989326a682bd33,Robust non-negative matrix factorization,"Front. Electr. Electron. Eng. China 2011, 6(2): 192–200 DOI 10.1007/s11460-011-0128-0 Lijun ZHANG, Zhengguang CHEN, Miao ZHENG, Xiaofei HE Robust non-negative matrix factorization (cid:2) Higher Education Press and Springer-Verlag Berlin Heidelberg 2011" e9d43231a403b4409633594fa6ccc518f035a135,Deformable Part Models with CNN Features,"Deformable Part Models with CNN Features Pierre-Andr´e Savalle1, Stavros Tsogkas1,2, George Papandreou3, Iasonas Kokkinos1,2 Ecole Centrale Paris,2 INRIA, 3TTI-Chicago (cid:63)" e9891ca60aa39df5819e5c417a6f00d56335ffb9,A dataset of stereoscopic images and ground-truth disparity mimicking human fixations in peripersonal space,"www.nature.com/scientificdata Received: 05 September 2016 Accepted: 13 January 2017 Published: 28 March 2017 Data Descriptor: A dataset of stereoscopic images and ground- truth disparity mimicking human fixations in peripersonal space Andrea Canessa1,*, Agostino Gibaldi1,*, Manuela Chessa1, Marco Fato1, Fabio Solari1 & Silvio P. Sabatini1 Binocular stereopsis is the ability of a visual system, belonging to a live being or a machine, to interpret the different visual information deriving from two eyes/cameras for depth perception. From this perspective, the ground-truth information about three-dimensional visual space, which is hardly available, is an ideal tool both for evaluating human performance and for benchmarking machine vision algorithms. In the present work, we implemented a rendering methodology in which the camera pose mimics realistic eye pose for a fixating observer, thus including convergent eye geometry and cyclotorsion. The virtual environment we developed relies on highly accurate 3D virtual models, and its full controllability allows us to obtain the stereoscopic pairs together with the ground-truth depth and camera pose information. We thus created a stereoscopic dataset: GENUA PESTO—GENoa hUman Active fixation database: PEripersonal space STereoscopic images and grOund truth disparity. The dataset aims to provide a unified framework" 54c5e9cded7da1f9dc695f5397d9d1a5ac5350af,Person Re-identification Based on Color Histogram and Spatial Configuration of Dominant Color Regions,"Person Re-identification Based on Color Histogram and Spatial Configuration of Dominant Color Regions Kwangchol Jang, Sokmin Han, Insong Kim College of Computer Science, KIM IL SUNG University, Pyongyang, D.P.R of Korea illumination, pose and viewpoint, camera parameters. Being related" 54f0fa07dee7bd270d3bd8da9011ca90df78af59,Comparison of Laser-Based Person Tracking at Feet and Upper-Body Height,"Comparison of Laser-based Person Tracking at Feet and Upper-Body Height Konrad Schenk, Markus Eisenbach, Alexander Kolarow, and Horst-Michael Gross (cid:63) Neuroinformatics and Cognitive Robotics Ilmenau University of Technologies" 54b309443f53ed960f588f64d6aefe53f87504b6,TVD: A Reproducible and Multiply Aligned TV Series Dataset,"TVD: a reproducible and multiply aligned TV series dataset Anindya Roy1, Camille Guinaudeau1,2, Herv´e Bredin1, Claude Barras1,2 Spoken Language Processing Group, CNRS-LIMSI, B.P. 133, Orsay, France. Universit´e Paris Sud, Orsay, France. {roy, guinaudeau, bredin," 54983972aafc8e149259d913524581357b0f91c3,ReSEED: social event dEtection dataset,"ReSEED: Social Event dEtection Dataset Timo Reuter Universität Bielefeld, CITEC Bielefeld, Germany ielefeld.de Symeon Papadopoulos CERTH-ITI Thermi, Greece Vasilios Mezaris CERTH-ITI Thermi, Greece Philipp Cimiano Universität Bielefeld, CITEC Bielefeld, Germany ielefeld.de" 549c719c4429812dff4d02753d2db11dd490b2ae,YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video,"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video Esteban Real Google Brain Jonathon Shlens Google Brain Stefano Mazzocchi Google Research Xin Pan Google Brain Vincent Vanhoucke Google Brain" 54d78ad2ed30557474fabd1d3a9e5db1c76fbeaa,Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking,"Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking Brian H. Wang1, Yan Wang2, Kilian Q. Weinberger2, and Mark Campbell1" 541b13515480c0371bb8bb79cf17120645edccc7,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 5456166e3bfe78a353df988897ec0bd66cee937f,Improved boosting performance by exclusion of ambiguous positive examples,"Improved Boosting Performance by Exclusion of Ambiguous Positive Examples Miroslav Kobetski, Josephine Sullivan Computer Vision and Active Perception, KTH, Stockholm 10800, Sweden {kobetski, Keywords: Boosting, Image Classification, Algorithm Evaluation, Dataset Pruning, VOC2007." 546cef6f86fb5a9fd59d40d9df63301c8a9d7d15,PathTrack: Fast Trajectory Annotation with Path Supervision,"PathTrack: Fast Trajectory Annotation with Path Supervision Santiago Manen1 Michael Gygli1 Dengxin Dai1 Luc Van Gool1,2 Computer Vision Laboratory ESAT - PSI / IBBT {smanenfr, gygli, daid, ETH Zurich K.U. Leuven" 54969bcd728b0f2d3285866c86ef0b4797c2a74d,Learning for Video Compression,"IEEE TRANSACTION SUBMISSION Learning for Video Compression Zhibo Chen, Senior Member, IEEE, Tianyu He, Xin Jin, Feng Wu, Fellow, IEEE" 54ed052738ca0f4570c74931857b3275fca9993b,Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation,"Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation Guanghan Ning, Student Member, IEEE, Zhi Zhang, Student Member, IEEE, and Zhihai He, Fellow, IEEE" 54830a1cf8606a5183561357b4004088718e4141,Deep Watershed Detector for Music Object Recognition,"DEEP WATERSHED DETECTOR FOR MUSIC OBJECT RECOGNITION Lukas Tuggener1,3 J¨urgen Schmidhuber3 Ismail Elezi1,2 Thilo Stadelmann1 ZHAW Datalab, Zurich University of Applied Sciences, Winterthur, Switzerland Dept. of Environmental Sciences, Informatics and Statistics, Ca’Foscari University of Venice, Italy Faculty of Informatics, Universit`a della Svizzera Italiana, Lugano, Switzerland" 540b39ba1b8ef06293ed793f130e0483e777e278,Biologically Inspired Emotional Expressions for Artificial Agents,"ORIGINAL RESEARCH published: 13 July 2018 doi: 10.3389/fpsyg.2018.01191 Biologically Inspired Emotional Expressions for Artificial Agents Beáta Korcsok 1*, Veronika Konok 2, György Persa 3, Tamás Faragó 2, Mihoko Niitsuma 4, Ádám Miklósi 2,5, Péter Korondi 1, Péter Baranyi 6 and Márta Gácsi 2,5 Department of Mechatronics, Optics and Engineering Informatics, Budapest University of Technology and Economics, Budapest, Hungary, 2 Department of Ethology, Eötvös Loránd University, Budapest, Hungary, 3 Institute for Computer Science nd Control, Hungarian Academy of Sciences, Budapest, Hungary, 4 Department of Precision Mechanics, Chuo University, Tokyo, Japan, 5 MTA-ELTE Comparative Ethology Research Group, Budapest, Hungary, 6 Department of Telecommunications nd Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary A special area of human-machine interaction, the expression of emotions gains importance with the continuous development of artificial agents such as social robots or" 5458ccf22bdea7197e28b433ef06d5225fb030a7,Video Description using Bidirectional Recurrent Neural Networks,"Video Description using Bidirectional Recurrent Neural Networks ´Alvaro Peris1, Marc Bola˜nos2,3, Petia Radeva2,3, and Francisco Casacuberta1 PRHLT Research Center, Universitat Polit`ecnica de Val`encia, Valencia (Spain) Universitat de Barcelona, Barcelona (Spain) Computer Vision Center, Bellaterra (Spain)" 542289d1acfebb9d79ea7a10c8e1516924e09973,Video Highlight Prediction Using Audience Chat Reactions,"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 972–978 Copenhagen, Denmark, September 7–11, 2017. c(cid:13)2017 Association for Computational Linguistics" 5454c5900b6b6a0cf36df65d667129fcbd5262dc,Benchmarking asymmetric 3D-2D face recognition systems,"Benchmarking Asymmetric 3D-2D Face Recognition Systems Xi Zhao, Wuming Zhang, Georgios Evangelopoulos, Di Huang, Shishir K. Shah, Yunhong Wang, Ioannis A. Kakadiaris and Liming Chen" 5478a70badcf4d6da383d86163f0acc2c28b6bd3,Enhancing pedestrian detection using optical flow for surveillance,"Int. J. Computational Vision and Robotics, Vol. 7, Nos. 1/2, 2017 Enhancing pedestrian detection using optical flow for surveillance Redwan A.K. Noaman*, Mohd Alauddin Mohd Ali and Nasharuddin Zainal Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 3600 Bandar Baru Bangi, Selangor, Malaysia Email: Email: Email: *Corresponding author" 548bc4203770450c21133bfb72c58f5fae0fbdf2,Visual-Inertial-Semantic Scene Representation for 3D Object Detection,"Visual-Inertial-Semantic Scene Representation for 3D Object Detection Jingming Dong∗ Xiaohan Fei∗ Stefano Soatto UCLA Vision Lab, University of California, Los Angeles, CA 90095 {dong, feixh," 54756f824befa3f0c2af404db0122f5b5bbf16e0,Statement Computer Vision — Visual Recognition,"Research Statement Computer Vision — Visual Recognition Alexander C. Berg Computational visual recognition concerns identifying what is in an image, video, or other visual data, enabling pplications such as measuring location, pose, size, activity, and identity as well as indexing for search by content. Recent progress in making economical sensors and improvements in network, storage, and computational power make visual recognition practical and relevant in almost all experimental sciences and commercial applications such as image search. My work in visual recognition brings together machine learning, insights from psychology nd physiology, computer graphics, algorithms, and a great deal of computation. While I am best known for my work on general object category detection – creating techniques and building systems for some of the best performing approaches to categorizing and localizing objects in images, recognizing ction in video, and searching large collections of video and images – my research extends widely across visual recognition including: • Creating low-level image descriptors – procedures for converting pixel values to features that can be used to model appearance for recognition. These include widely used descriptors for category recognition in images [4, 2], object detection in images and video [11, 10, 2], and optical flow based descriptors for action recognition in video [8]. • Developing models for recognition – ranging from what is becoming seminal work in recognizing human ctions in video [8], to formulating object localization as approximate subgraph isomorphism [2], to models for parsing architectural images [3], to a novel approach for face recognition based on high level describable" 543c601f8ebc0995040f4b8de4a339fd4c860cbb,Eye localization : a survey,"Eye localization: a survey Paola CAMPADELLI, Raffaella LANZAROTTI, Giuseppe LIPORI 1 Dipartimento di Scienze dell’Informazione. Università degli Studi di Milano. Via Comelico, 39/41 - 20135 Milano (Italy)" 5479da1038a530beb760a38dbb5b08947dfaefbd,Fusing continuous spectral images for face recognition under indoor and outdoor illuminants,"DOI 10.1007/s00138-008-0151-1 ORIGINAL PAPER Fusing continuous spectral images for face recognition under indoor and outdoor illuminants H. Chang · A. Koschan · B. Abidi · M. Abidi Received: 4 December 2007 / Accepted: 14 May 2008 / Published online: 17 June 2008 © Springer-Verlag 2008 image fusion approaches," 545b2ce4bc5ed7b1c1089020b3e53c1d67186370,CONVOLUTIONAL NEURAL NETWORKS IN AUTONOMOUS VEHICLE CONTROL SYSTEMS,"Session C11 Paper #77 Disclaimer—This paper partially fulfills a writing requirement for first year (freshman) engineering students at the University of Pittsburgh Swanson School of Engineering. This paper is a student, not a professional, paper. This paper is ased on publicly available information and may not provide complete analyses of all relevant data. If this paper is used for ny purpose other than these authors’ partial fulfillment of a writing requirement for first year (freshman) engineering students at the University of Pittsburgh Swanson School of Engineering, the user does so at his or her own risk. CONVOLUTIONAL NEURAL NETWORKS IN AUTONOMOUS VEHICLE CONTROL SYSTEMS Erin Welling, Mahboobin 4:00, Maddie Oppelt, Vidic 2:00" 541c68e2c65f6dce6179801c9f92dc7803dc71b5,Unsupervised and Transfer Learning under Uncertainty - From Object Detections to Scene Categorization,"Unsupervised and Transfer Learning under Uncertainty: from Object Detections to Scene Categorization Gr´egoire Mesnil1,2, Salah Rifai1, Antoine Bordes3, Xavier Glorot1, Yoshua Bengio1 and Pascal Vincent1 LISA, Universit´e de Montr´eal, Qu´ebec, Canada LITIS, Universit´e de Rouen, France CNRS - Heudiasyc UMR 7253, Universit´e de Technologie de Compi`egne, France Keywords: Unsupervised Learning, Transfer Learning, Deep Learning, Scene Categorization, Object Detection" 548f94f82bf28efa299a64c2527aad36d76b81af,Adaptive Kernels for Texture Based Analysis of Object Based Classification of Forest Stands by Ziab Khan,"Adaptive Kernels for Texture Based Analysis of Object Based Classification of Forest Stands Ziab Khan A thesis submitted in partial fulfilment for the degree of Master of Philosophy in the Department of Geography University of Leicester August 26, 2014" 54bb3a17d536c7b88e56d294464f3d54de2ea9b3,Video surveillance online repository (ViSOR): www.openvisor.org,"Video Surveillance Online Repository (ViSOR) www.openvisor.org Roberto Vezzani, Rita Cucchiara Dipartimento di Ingegneria “Enzo Ferrari” University of Modena and Reggio Emilia, Italy" 54f0588b379b25ee6c22952e486d7da45bad7bab,Optimal feature selection for support vector machines,Author's personal copy 54f8a2cc202a65ede4da8593c9dd218eed0b0109,R 4-A . 3 : Human Detection and Re-Identifi cation for Mass Transit Environments,"R4-A.3: Human Detection and Re-Identifi cation for Mass Transit Environments PARTICIPANTS Rich Radke Title Faculty/Staff Institution Email Graduate, Undergraduate and REU Students Degree Pursued Srikrishna Karanam M.S. & PhD Austin Li Gyanendra Sharma Institution Month/Year of Graduation 2/2017 5/2015 5/2019 PROJECT DESCRIPTION Overview and Signi(cid:980)icance" 54509dbe70cd3015007bbd5fa1fd8793b388319e,Fast Pedestrian Detection by Cascaded Random Forest with Dominant Orientation Templates.,"TANG ET AL.: FAST PEDESTRIAN DETECTION BY RANDOM FORESTS WITH DOT Fast Pedestrian Detection by Cascaded Random Forest with Dominant Orientation Templates Danhang Tang http://www.iis.ee.ic.ac.uk/~dtang Yang Liu http://www.iis.ee.ic.ac.uk/~yliu Tae-Kyun Kim http://www.iis.ee.ic.ac.uk/~tkkim Department of Electrical Engineering, Imperial College, London, UK" 544829d3b2e878c8f28fae5aa0c226e65ba6242a,Human Body Segmentation with Multi-limb Error-Correcting Output Codes Detection and Graph Cuts Optimization,"Human Pose Recovery and Behavior Analysis Group Human Body Segmentation with Multi-limb Error-Correcting Output Codes Detection and Graph Cuts Optimization Daniel Sánchez, Juan Carlos Ortega, Miguel Ángel Bautista & Sergio Escalera All rights reserved HuBPA©" 5432392d916e730c53962be202c115133e6d7777,Face processing in a case of high functioning autism with developmental prosopagnosia.,"RESEARCH PAPER Acta Neurobiol Exp 2018, 78: 114–131 DOI: 10.21307/ane‑2018‑011 Face processing in a case of high functioning autism with developmental prosopagnosia Hanna B. Cygan1,3*, Hanna Okuniewska2, Katarzyna Jednoróg3, Artur Marchewka4, Marek Wypych4 and Anna Nowicka3 Laboratory of Social Psychology, Department of Ergonomics, Central Institute for Labour Protection, National Research Institute, Warsaw, Poland, 2 Faculty of Psychology, University of Warsaw, Warsaw, Poland, 3 Laboratory of Psychophysiology, Department of Neurophysiology, Nencki Institute of Experimental Biology, Polish Academy of Science, Warsaw, Poland, 4 Laboratory of Brain Imaging, Neurobiology Center, Nencki Institute of Experimental Biology, Polish Academy of Science, Warsaw, Poland, * Email: The ability to “read” the information about facial identity, expressed emotions, and intentions is crucial for non‑verbal social interaction. Neuroimaging and clinical studies consequently link face perception with fusiform gyrus (FG) and occipital face area (OFA) activity. Here we investigated face processing in an adult, patient PK, diagnosed with both high functioning autism spectrum disorder (ASD) and developmental prosopagnosia (DP). Both disorders have a significant impact on face perception and recognition, thus creating a unique neurodevelopmental condition. We used eye‑tracking and functional magnetic resonance imaging (fMRI) method. Eye‑tracking and fMRI results of PK were compared to results of control subjects. Patient PK showed atypical gaze‑fixation strategy during face perception and typical patterns of brain activations in the FG and OFA. However, a significant difference between PK and control subjects was found in the left anterior superior temporal sulcus/middle temporal gyrus (aSTS/MTG). In PK the left aSTS/MTG was hypo‑activated in comparison" 541bccf19086755f8b5f57fd15177dc49e77d675,A few days of a robot's life in the human's world: toward incremental individual recognition,"Computer Science and ArtificialIntelligence LaboratoryTechnical Reportmassachusetts institute of technology, cambridge, ma 02139 usa — www.csail.mit.eduMIT-CSAIL-TR-2007-022April 3, 2007A Few Days of A Robot’s Life in the Human’s World: Toward Incremental Individual RecognitionLijin Aryananda" 8b21c89b436e0aa540f7b9648e4344eb30a6e372,Robust coding schemes for indexing and retrieval from large face databases,"IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 9, NO. 1, JANUARY 2000 Correspondence________________________________________________________________________ Robust Coding Schemes for Indexing and Retrieval from Large Face Databases Chengjun Liu and Harry Wechsler" 8bb4d90d5b97e8d08d2aaa99e9c075a506b3108a,Generating Diverse Clusterings,"Generating Diverse Clusterings Anonymous Author(s)" 8b36c4675732249963b3e9294a0f52f26c6dd931,A Survey on Local Invariant Features,"FnT Computer Graphics and Vision 2:4 FnTCGV Foundations and Trends in Computer Graph- ics and Vision Vol. 1, No 1 (1) 1–94 (cid:13) 1 now Publishers Inc. A Survey on Local Invariant Features Tinne Tuytelaars1 and Krystian Mikolajczyk2 Kasteelpark Arenberg 0Leuven B-3001, Belgium, Surrey GU27XH, United Kingdom," 8b20737b454fa8c2848979b5c76be9915a65a75f,Automated Object Recognition Using Multiple X-ray Views,"Automated Object Recognition Using Multiple X-ray Views Domingo Mery1 – Vladimir Riffo1, 2 Department of Computer Science, Pontificia Universidad Católica de Chile. Department of Computer Engineering and Computer Science, Universidad de Atacama. Av. Vicuña Mackenna 4860(143) – Santiago de Chile. Av. Copayapu 485 – Copiapó, Chile. http://dmery.ing.puc.cl http://www.ing.puc.cl/~vriffo1" 8bff7353fa4f75629ea418ca8db60477a751db93,Invariance of Weight Distributions in Rectified MLPs,"Invariance of Weight Distributions in Rectified MLPs Russell Tsuchida 1 Farbod Roosta-Khorasani 2 3 Marcus Gallagher 1" 8b7724e2e5dec9a0a51e84a270c9b9db84b205a6,Analysis Dictionary Learning based Classification: Structure for Robustness,"Analysis Dictionary Learning based Classification: Structure for Robustness Wen Tang, Ashkan Panahi, Hamid Krim, and Liyi Dai" 8b5b8db6a2a2880c14894140ea70ceb5f96c3b9b,Learning a Text-Video Embedding from Incomplete and Heterogeneous Data,"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data Antoine Miech1,2 Ivan Laptev1,2 Josef Sivic1,2,3 ´Ecole Normale Sup´erieure(cid:63) Inria CIIRC(cid:63)(cid:63) http://www.di.ens.fr/willow/research/mee/" 8ba474aa327cd078c2b85f0c1ab752043253016a,Face Detection Based on Skin Color Segmentation Using Fuzzy Entropy,"Article Face Detection Based on Skin Color Segmentation Francisco A. Pujol 1,*, Mar Pujol 2, Antonio Jimeno-Morenilla 1 and María José Pujol 3 Department of Computer Technology, University of Alicante, Alicante 03690, Spain; Department of Computer Science and Artificial Intelligence, University of Alicante, Alicante 03690, Spain; Department of Applied Mathematics, University of Alicante, Alicante 03690, Spain; * Correspondence: Tel.: +34-96-590-3681 Academic Editor: Raúl Alcaraz Martínez Received: 14 November 2016; Accepted: 22 December 2016; Published: 11 January 2017" 8bbafa3efb7b96adb95128ea2a30a363bfe06812,Towards usable authentication on mobile phones : An evaluation of speaker and face recognition on off-the-shelf handsets,"Towards usable authentication on mobile phones: An evaluation of speaker and face recognition on off-the-shelf handsets Rene Mayrhofer University of Applied Sciences Upper Austria Softwarepark 11, A-4232 Hagenberg, Austria University of Applied Sciences Upper Austria Softwarepark 11, A-4232 Hagenberg, Austria Thomas Kaiser hagenberg.at" 8bba26895022749e2273729f96051571eabc7b99,Natural language acquisition in recurrent neural architectures,"Natural Language Acquisition in Recurrent Neural Architectures Dissertation submitted to the Universität Hamburg, Faculty of Mathematics, Informatics nd Natural Sciences, Department fulfilment of the requirements for the degree of Doctor rerum naturalium (Dr. rer. nat.) Informatics, in partial Dipl.-Inform. Stefan Heinrich Hamburg, 2016" 8b632db02220806cd62e35fdebb3ede58243dee0,Recognizing Partially Occluded Faces from a Single Sample Per Class Using String-Based Matching,"Recognizing Partially Occluded Faces from a Single Sample Per Class Using String-Based Matching Weiping Chen1 and Yongsheng Gao1,2 School of Engineering, Grif‌f‌ith University, Australia National ICT Australia, Queensland Research Lab" 8b2f99b0106143fd0193fcbf2b07eba80dc7f8dd,Enhancing Recommender Systems for TV by Face Recognition, 8b2c090d9007e147b8c660f9282f357336358061,Emotion Classification based on Expressions and Body Language using Convolutional Neural Networks,"Lake Forest College Lake Forest College Publications Senior Theses -23-2018 Student Publications Emotion Classification based on Expressions and Body Language using Convolutional Neural Networks Aasimah S. Tanveer Lake Forest College, Follow this and additional works at: https://publications.lakeforest.edu/seniortheses Part of the Neuroscience and Neurobiology Commons Recommended Citation Tanveer, Aasimah S., ""Emotion Classification based on Expressions and Body Language using Convolutional Neural Networks"" (2018). Senior Theses. This Thesis is brought to you for free and open access by the Student Publications at Lake Forest College Publications. It has been accepted for inclusion in Senior Theses by an authorized administrator of Lake Forest College Publications. For more information, please contact" 8b7e5be7faa1c78065baa21179c258697fcaa730,Detection of Complex Salient Regions,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2008, Article ID 451389, 11 pages doi:10.1155/2008/451389 Research Article Detection of Complex Salient Regions Sergio Escalera,1, 2 Oriol Pujol,1, 2 and Petia Radeva1, 2 Computer Vision Center, Campus UAB, Edifici O, 08193 Bellaterra, Barcelona, Spain Departamento de Matem`atica Aplicada i An`alisi, Universitat de Barcelona (UB), 08007 Barcelona, Spain Correspondence should be addressed to Sergio Escalera, Received 16 October 2007; Revised 8 February 2008; Accepted 12 March 2008 Recommended by Irene Gu The goal of interest point detectors is to find, in an unsupervised way, keypoints easy to extract and at the same time robust to image transformations. We present a novel set of saliency features based on image singularities that takes into account the region ontent in terms of intensity and local structure. The region complexity is estimated by means of the entropy of the gray-level information; shape information is obtained by measuring the entropy of significant orientations. The regions are located in their representative scale and categorized by their complexity level. Thus, the regions are highly discriminable and less sensitive to onfusion and false alarm than the traditional approaches. We compare the novel complex salient regions with the state-of-the-art keypoint detectors. The presented interest points show robustness to a wide set of image transformations and high repeatability as well as allow matching from different camera points of view. Besides, we show the temporal robustness of the novel salient regions" 8b1db0894a23c4d6535b5adf28692f795559be90,How Reliable are Your Visual Attributes ?,"Biometric and Surveillance Technology for Human and Activity Identification X, edited by Ioannis Kakadiaris, Walter J. Scheirer, Laurence G. Hassebrook, Proc. of SPIE Vol. 8712, 87120Q · © 2013 SPIE CCC code: 0277-786X/13/$18 · doi: 10.1117/12.2018974 Proc. of SPIE Vol. 8712 87120Q-1 From: http://proceedings.spiedigitallibrary.org/ on 06/07/2013 Terms of Use: http://spiedl.org/terms" 8bcee0c84759a2bf17d8f8e77b8a393c6f823ded,Optimized Performance of 2 DPCA Approach in Face Recognition System,"Internati onal Journal of Innovations & Advance me nt in Computer Science IJ IACS ISSN 2347 – 8616 Volume 3, Issue 5 July 2014 Optimized Performance of 2DPCA Approach in Face Recognition System in the face database. Today, several approaches like PCA, KPCA, MPCA and 2DPCA provide y researches but till date it is not completely solve issues. Therefore, it required to review these approaches one again. . LITERATURE SURVEY Abhishek Sharma M.Tech Research scholar Department of CSE, SET IFTMU Moradabad. provide redit/debit identification," 8b744786137cf6be766778344d9f13abf4ec0683,And Summarization by Sub-modular Inference,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 8b9db19d0d3e2a7d740be811810a043a04d6226a,An Attention-based Regression Model for Grounding Textual Phrases in Images,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 8b879863237d315997857a5585afb2bbbf78c622,Social network analysis as a tool for improving enterprise architecture,"Proceedings of the 5th International KES Symposium on Agents and Multi-agent Systems, KES-AMSTA 2011. Manchester, UK, June 29 - July 1, 2011 Lecture Notes in Artificial Intelligence LNAI, Volume 6682, 2011, pp. 651-660 DOI: 10.1007/978-3-642-22000-5_67 Social Network Analysis as a Tool for Improving Enterprise Architecture Przemysław Kazienko, Radosław Michalski, Sebastian Palus Institute of Informatics, Wrocław University of Technology Wybrzeże Wyspiańskiego 27, 50-370 Wrocław, Poland {kazienko, radoslaw.michalski," 8b9e94fb3bb64389e9765ffde365862231b5972c,Fast Eye Tracking and Feature Measurement using a Multi-stage Particle Filter, 8b3288421ee4fa7f9ff45ddc6adbf04698c4b8ba,On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation,"On the iterative refinement of densely connected representation levels for semantic segmentation Arantxa Casanova1,2 Guillem Cucurull1,2 Michal Drozdzal1,3 Adriana Romero1,3 Yoshua Bengio1 Montreal Institute for Learning Algorithms Computer Vision Center, Barcelona Facebook AI Research" 8bddd0afd064e2d45ab6cf9510f2631f7438c17b,Outlier Detection using Generative Models with Theoretical Performance Guarantees,"Outlier Detection using Generative Models with Theoretical Performance Guarantees∗ Jirong Yi† Anh Duc Le‡ Tianming Wang§ Xiaodong Wu¶ Weiyu Xu(cid:107) October 29, 2018" 8b29ee0a47efc11071ab8baec8369fd54970bfbb,Thèse présentée à la faculté des sciences pour l ’ obtention du grade de docteur ès sciences Features Extraction for Low-Power Face Verification,"Thèse présentée à la faculté des sciences pour l’obtention du grade de docteur ès sciences Features Extraction for Low-Power Face Verification Patrick Stadelmann Acceptée sur proposition du jury : Prof. Fausto Pellandini, directeur de thèse PD Dr. Michael Ansorge, co-directeur de thèse Prof. Pierre-André Farine, rapporteur Dr. Nicolas Blanc, rapporteur Soutenue le 23 mai 2008 Institut de Microtechnique Université de Neuchâtel" 8b64dbeac77fe8d6bf440311337451f9f61b9ea0,Image-based approaches to hair modeling,"Image-Based Approaches to Hair Modeling Dissertation Erlangung des Doktorgrades (Dr. rer. nat) Mathematisch-Naturwissenschaftlichen Fakult¨at Rheinischen Friedrich-Wilhelms-Universit¨at Bonn vorgelegt von Tom´as Lay Herrera Havanna Bonn, November 2012" 8b607928c7af70259a9f8af9e08e28e6037411c8,Bayesian teaching of image categories,"Bayesian teaching of image categories Wai Keen Vong∗ Ravi B. Sojitra* Newark, NJ, 07102 Anderson Reyes Scott Cheng-Hsin Yang Patrick Shafto Department of Mathematics and Computer Science, 110 Warren Street," 8bb21b1f8d6952d77cae95b4e0b8964c9e0201b0,Multimodal Interaction on a Social Robotic Platform,"Methoden t 11/2013 (cid:2)(cid:2)(cid:2) Multimodale Interaktion uf einer sozialen Roboterplattform Multimodal Interaction on a Social Robotic Platform Jürgen Blume Korrespondenzautor: , Tobias Rehrl, Gerhard Rigoll, Technische Universität München Zusammenfassung Dieser Beitrag beschreibt die multimo- dalen Interaktionsmöglichkeiten mit der Forschungsroboter- plattform ELIAS. Zunächst wird ein Überblick über die Ro- oterplattform sowie die entwickelten Verarbeitungskompo- nenten gegeben, die Einteilung dieser Komponenten erfolgt nach dem Konzept von wahrnehmenden und agierenden Mo- dalitäten. Anschließend wird das Zusammenspiel der Kom- ponenten in einem multimodalen Spieleszenario näher be- trachtet. (cid:2)(cid:2)(cid:2) Summary This paper presents the mul- timodal" 8b9f529700a93a2ff6e227c76a1333883a1f6213,PREMOC: Plataforma de reconocimiento multimodal de emociones,"PREMOC: Plataforma de reconocimiento multimodal de emociones Ramón Zatarain-Cabada, María Lucia Barrón-Estrada, Gilberto Muñoz-Sandoval Instituto Tecnológico de Culiacán, Culiacán, Sinaloa, México {rzaratain, lbarron, Resumen. En años recientes la computación afectiva ha venido a mejorar la interacción humano-computadora, pues ayuda a la computadora a conocer el estado afectivo del usuario para mejorar la toma de decisiones. Este artículo presenta los avances en el proyecto PREMOC, una plataforma que brinda un servicio web para el reconocimiento de emociones en texto, imágenes de rostros, sonidos de voz y señales EEG de manera mono-modal y multimodal. PREMOC yuda a los desarrolladores a integrar el reconocimiento de afecto a sus plicaciones o sistemas de software. Cada uno de los reconocedores se implementó aplicando diferentes técnicas tanto para extraer características como para clasificar emociones; además para el reconocimiento multimodal se integraron las emociones mediante un sistema difuso. Esta plataforma ya está siendo utilizada por diferentes proyectos en el laboratorio de la Maestría en Ciencias de la Computación del Instituto Tecnológico de Culiacán. Palabras claves: Computación afectiva, inteligencia artificial, reconocimiento" 8b547b87fd95c8ff6a74f89a2b072b60ec0a3351,Initial perceptions of a casual game to crowdsource facial expressions in the wild,"Initial Perceptions of a Casual Game to Crowdsource Facial Expressions in the Wild Chek Tien Tan Hemanta Sapkota Daniel Rosser Yusuf Pisan Games Studio, Faculty of Engineering and IT, University of Technology, Sydney" 8b9c53e7d65ba7a7be3d588d00481f2ff49b5ef4,Orienting in response to gaze and the social use of gaze among children with autism spectrum disorder.,23Journal of Autism andDevelopmental Disorders ISSN 0162-3257Volume 43Number 7 J Autism Dev Disord (2013)43:1584-1596DOI 10.1007/s10803-012-1704-8Orienting in Response to Gaze and theSocial Use of Gaze among Children withAutism Spectrum DisorderAdrienne Rombough & Grace Iarocci b774d7c951b9c444572085e15f6a81a063abf123,Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification,"FeaturesSpatial  AttentionTemporal  Attention1                      2                      3                              N‘face’‘torso’‘bag’Figure1.SpatiotemporalAttention.Inchallengingvideore-identificationscenarios,apersonisrarelyfullyvisibleinallframes.However,framesinwhichonlypartofthepersonisvis-ibleoftencontainusefulinformation.Forexample,thefaceisclearlyvisibleintheframes1and2,thetorsoinframe2,andthehandbaginframes2,3andN.Insteadofaveragingfullframefeaturesacrosstime,weproposeanewspatiotemporalapproachwhichlearnstodetectasetofKdiversesalientimageregionswithineachframe(superimposedheatmaps).Anaggregaterep-resentationofeachbodypartisthenproducedbycombiningtheextractedper-frameregionsacrosstime(weightsshownaswhitetext).Ourspatiotemporalapproachcreatesacompactencodingofthevideothatexploitsusefulpartialinformationineachframebyleveragingmultiplespatialattentionmodels,andcombiningtheiroutputsusingmultipletemporalattentionmodels.personre-identification,whichisageneralizationofthestandardimage-basedre-identificationtask.InsteadofarXiv:1803.09882v1 [cs.CV] 27 Mar 2018" b704f8360c369e65f0826ca23dac2d4e221d8997,A Knowledge Base for Automatic Feature Recognition from Point Clouds in an Urban Scene,"Article A Knowledge Base for Automatic Feature Recognition from Point Clouds in an Urban Scene Xu-Feng Xing 1,2,* ID , Mir-Abolfazl Mostafavi 1,2 ID and Seyed Hossein Chavoshi 1,2 Department of Geomatics Sciences, Université Laval, Québec, QC G1V 0A6, Canada; (M.-A.M.); (S.H.C.) Center for Research in Geomatics, Université Laval, Québec, QC G1V 0A6, Canada * Correspondence: Tel.: +1-581-888-9786 Received: 4 October 2017; Accepted: 11 January 2018; Published: 16 January 2018" b7f05d0771da64192f73bdb2535925b0e238d233,Robust Active Shape Model using AdaBoosted Histogram Classifiers,"MVA2005 IAPR Conference on Machine VIsion Applications, May 16-18, 2005 Tsukuba Science City, Japan Robust Active Shape Model using AdaBoosted Histogram Classifiers Yuanzhong Li W ataru Ito Imaging Software Technology Center Imaging Software Technology Center FUJI PHOTO FILM CO., LTD. fujifilm.co.jp FUJI PHOTO FILM CO., LTD. fujifilm.co.jp" b7b23814948afc5525975ed44f3dd247100e6722,Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images,"Relevant Feature Selection for Human Pose Estimation nd Localization in Cluttered Images Ryuzo Okada(cid:2) and Stefano Soatto Computer Science Department, University of California, Los Angeles" b7f7a4df251ff26aca83d66d6b479f1dc6cd1085,Handling missing weak classifiers in boosted cascade: application to multiview and occluded face detection,"Bouges et al. EURASIP Journal on Image and Video Processing 2013, 2013:55 http://jivp.eurasipjournals.com/content/2013/1/55 RESEARCH Open Access Handling missing weak classifiers in boosted ascade: application to multiview and occluded face detection Pierre Bouges1*, Thierry Chateau1*, Christophe Blanc1 and Gaëlle Loosli2" b7f0d1d65763fb57ee9a3624116a42a2fe763707,Predicting psychological attributions from face photographs with a deep neural network,"Predicting psychological attributions from face photographs with a deep neural network Edward Grant1∗, Stephan Sahm1∗, Mariam Zabihi1∗, Marcel van Gerven1 Radboud University, Nijmegen, the Netherlands Denotes equal contribution" b755505bdd5af078e06427d34b6ac2530ba69b12,NFRAD: Near-Infrared Face Recognition at a Distance,"To appear in the International Joint Conf. Biometrics, Washington D.C., October, 2011 NFRAD: Near-Infrared Face Recognition at a Distance Hyunju Maenga, Hyun-Cheol Choia, Unsang Parkb, Seong-Whan Leea and Anil K. Jaina,b Dept. of Brain and Cognitive Eng. Korea Univ., Seoul, Korea Dept. of Comp. Sci. & Eng. Michigan State Univ., E. Lansing, MI, USA 48824 {hjmaeng, ," b7cf7bb574b2369f4d7ebc3866b461634147041a,From NLDA to LDA/GSVD: a modified NLDA algorithm,"Neural Comput & Applic (2012) 21:1575–1583 DOI 10.1007/s00521-011-0728-x O R I G I N A L A R T I C L E From NLDA to LDA/GSVD: a modified NLDA algorithm Jun Yin • Zhong Jin Received: 2 August 2010 / Accepted: 3 August 2011 / Published online: 19 August 2011 Ó Springer-Verlag London Limited 2011" b7c2798e136feb85847c8a9aa693d75bc3f9b08c,Classifying a specific image region using convolutional nets with an ROI mask as input,"Classifying a specific image region using onvolutional nets with an ROI mask as input Sagi Eppel 1" b76af8fcf9a3ebc421b075b689defb6dc4282670,Face Mask Extraction in Video Sequence,"Face Mask Extraction in Video Sequence Yujiang Wang 1 · Bingnan Luo 1 · Jie Shen 1 · Maja Pantic 1" b73a6c7083f3dbc8b355f934aaf84438c10a7963,The 54th Annual Meeting of the Association for Computational Linguistics,"The54thAnnualMeetingoftheAssociationforComputationalLinguisticsProceedingsoftheConference,Vol.2(ShortPapers)August7-12,2016Berlin,Germany" b7c7721e5f19e02ef56c17cd74d24476a53856dd,Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance,"Noname manuscript No. (will be inserted by the editor) Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance Zechun Liu · Wenhan Luo · Baoyuan Wu · Xin Yang · Wei Liu · Kwang-Ting Cheng Received: date / Accepted: date" b7c4b22d44be82b2e1074c5c40b76461db4b0292,Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detections,"Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detections Ehsan Jahangiri, Alan L. Yuille Johns Hopkins University, Baltimore, USA" b701f11ecf5d465c7d5c427914db2ad8c97bb8a9,JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets,"JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets Yunchen Pu 1 Shuyang Dai 2 Zhe Gan 3 Weiyao Wang 2 Guoyin Wang 2 Yizhe Zhang 3 Ricardo Henao 2 Lawrence Carin 2" b797f3fa4e732d52092f9eb863350440d5de8bb1,Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database.,"Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database Xiaosong Wang Le Lu Hoo-chang Shin Lauren Kim Isabella Nogues Jianhua Yao Ronald Summers Imaging Biomarkers and Computer-aided Detection Laboratory Department of Radiology and Imaging Sciences National Institutes of Health Clinical Center 0 Center Drive, Bethesda, MD 20892" b705ca751a947e3b761e2305b41891051525d9df,Exploring Context with Deep Structured Models for Semantic Segmentation,"Exploring Context with Deep Structured models for Semantic Segmentation Guosheng Lin, Chunhua Shen, Anton van den Hengel, Ian Reid" b7d425ea6b476c4af208a6b6a9e84ab17921dab4,Heuristic-based automatic face detection,"HEURISTIC-BASED AUTOMATIC FACE DETECTION Geovany Ramírez1, Vittorio Zanella1,2, Olac Fuentes2 Universidad Popular Autónoma del Estado de Puebla 1 sur #1103 Col. Santiago Puebla 72160, México Instituto Nacional de Astrofísica Optica y Electrónica Luis Enrique Erro #1 Sta. María Tonantzintla Puebla 72840, México E-mail:" b7c4fe5c89df51ebd1f89a34c66b94cc6019d8e6,Model Cards for Model Reporting,"Model Cards for Model Reporting Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, Timnit Gebru" b7c7411eed2f3b6211abfe0aeea7c18adb028d11,Robust De-noising by Kernel PCA,"Robust De-noising by Kernel PCA Takashi Takahashi1 and Takio Kurita2 Department of Applied Mathematics and Informatics, Ryukoku University, Ootsu, Shiga 520–2194, JAPAN National Institute of Advanced Industrial Science and Technology(AIST), Tsukuba, Ibaraki 305–8568, JAPAN" b7a0e7dab11781c252e1145f3526aee388b4136d,Facing humanness: Facial width-to-height ratio predicts ascriptions of humanity.,"Journal of Personality and Social Psychology Facing Humanness: Facial Width-to-Height Ratio Predicts Ascriptions of Humanity Jason C. Deska, E. Paige Lloyd, and Kurt Hugenberg Online First Publication, August 28, 2017. http://dx.doi.org/10.1037/pspi0000110 CITATION Deska, J. C., Lloyd, E. P., & Hugenberg, K. (2017, August 28). Facing Humanness: Facial Width-to- Advance online publication. http://dx.doi.org/10.1037/pspi0000110" b7eead8586ffe069edd190956bd338d82c69f880,A VIDEO DATABASE FOR FACIAL BEHAVIOR UNDERSTANDING,"A VIDEO DATABASE FOR FACIAL BEHAVIOR UNDERSTANDING D. Freire-Obreg´on and M. Castrill´on-Santana. SIANI, Universidad de Las Palmas de Gran Canaria, Spain" b778c0e5ec6cebbabc77fc56f9b7438f2974a4ea,Altered activity of the primary visual area during gaze processing in individuals with high-functioning autistic spectrum disorder: a magnetoencephalography study.,"Altered Activity of the Primary Visual Area during Gaze Processing in Individuals with High-Functioning Autistic Spectrum Disorder: A Magnetoencephalography Study Naoya Hasegawaa, Hideaki Kitamuraa, Hiroatsu Murakamib, Shigeki Kameyamab, Mutsuo Sasagawac, Jun Egawaa, Ryu Tamuraa, Tarou Endoa, Toshiyuki Someyaa Department of Psychiatry, Niigata University Graduate School of Medical and Dental Sciences, -757 Asahimachi-dori, Chuo-ku, Niigata 951-8510, Japan Department of Neurosurgery, Epilepsy Center, Nishi-Niigata Chuo National Hospital, 1-14-1 Masago, Nishi-ku, Niigata 950-2085, Japan Department of Psychiatry, Epilepsy Center, Nishi-Niigata Chuo National Hospital, 1-14-1 Masago, Nishi-ku, Niigata 950-2085, Japan Short title: Altered activity of the primary visual area of autistic spectrum disorder during gaze processing Correspondence: Hideaki Kitamura Department of Psychiatry, Niigata University Graduate School of Medical and Dental Sciences, -757 Asahimachi-dori, Chuo-ku, Niigata 951-8510, Japan Tel: +81-25-227-2213; Fax: +81-25-227-0777; E-mail:" b7a09eaadcb21bf9ab234d87c954e329518580c5,Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation,"Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation Bugra Tekin Pablo M´arquez-Neila Mathieu Salzmann Pascal Fua EPFL, Switzerland" b7a827bb393361c309fbba652967dee11d16857c,Comparative Analysis of various Illumination Normalization Techniques for Face Recognition,"International Journal of Computer Applications (0975 – 8887) Volume 28– No.9, August 2011 Comparative Analysis of various Illumination Normalization Techniques for Face Recognition Tripti Goel GPMCE, Delhi Vijay Nehra BPSMV, Khanpur Virendra P.Vishwakarma JIIT, Noida explained" b788f1c013c6786cd44d6f35682a388975058488,Towards Collaborative Group Activity Recognition Using Mobile Devices,"Mobile Netw Appl DOI 10.1007/s11036-012-0415-x Towards Collaborative Group Activity Recognition Using Mobile Devices Dawud Gordon · Jan-Hendrik Hanne · Martin Berchtold · Ali Asghar Nazari Shirehjini · Michael Beigl © Springer Science+Business Media New York 2012" b7b461f82c911f2596b310e2b18dd0da1d5d4491,K-mappings and Regression trees,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE K-MAPPINGS AND REGRESSION TREES SAMSI and Duke University . INTRODUCTION rgminM1,...,MK P1,...PK Arthur Szlam† .1. Partitioning Y K(cid:2) (cid:2) (cid:3) (cid:4)" b7ac537d97efcb968ca8e353ff5b0563e26b9dbe,Object-Aware Dense Semantic Correspondence,"Object-aware Dense Semantic Correspondence Fan Yang1, Xin Li1 ∗, Hong Cheng2, Jianping Li1, Leiting Chen1 School of Computer Science & Engineering, UESTC Center for Robotics, School of Automation Engineering, UESTC fanyang xinli" b7216846c743d94fcd43e1b543c9d16ae11d3c48,Engaging Image Chat: Modeling Personality in Grounded Dialogue,"Engaging Image Chat: Modeling Personality in Grounded Dialogue Kurt Shuster Samuel Humeau Antoine Bordes Jason Weston {kshuster, samuelhumeau, abordes, jase} Facebook AI Research" b7c2173668a4c23b79450111887d8b1e4199f89c,Complex event recognition by latent temporal models of concepts,"COMPLEX EVENT RECOGNITION BY LATENT TEMPORAL MODELS OF CONCEPTS Ehsan Zare Borzeshi1, Afshin Dehghan2, Massimo Piccardi1, and Mubarak Shah2 School of Computing and Communications, University of Technology, Sydney (UTS)1, Centre for Research in Computer Vision, University of Central Florida (UCF)2" b79f3d9f8de4d1cc6679676146a40d2a8596f32d,Composing Simple Image Descriptions using Web-scale N-grams,"Proceedings of the Fifteenth Conference on Computational Natural Language Learning, pages 220–228, Portland, Oregon, USA, 23–24 June 2011. c(cid:13)2011 Association for Computational Linguistics" b73fdae232270404f96754329a1a18768974d3f6,International Journal of Advanced Robotic Systems Local Relation Map : A Novel Illumination Invariant Face Recognition Approach Regular Paper, b74c410ea8db3babb9a307d1fb8f08b90ce8b490,Automatic Visual Speech Recognition,"6 Automatic Visual Speech Recognition Alin Chiţu¹ and Léon J.M. Rothkrantz¹,² ¹Delft University of Technology ²Netherlands Defence Academy The Netherlands 1. Introduction Lip reading was thought for many years to be specific to hearing impaired persons. Therefore, it was considered that lip reading is one possible solution to an abnormal situation. Even the name of the domain suggests that lip reading was considered to be a rather artificial way of communication because it associates lip reading with the written language which is a relatively new cultural phenomenon and is not an evolutionary inherent ability. Extensive lip reading research was primarily done in order to improve the teaching methodology for hearing impaired persons to increase their chances for integration in the society. Later on, the research done in human perception and more exactly in speech perception proved that lip reading is actively employed in different degrees by all humans irrespective to their hearing capacity. The most well know study in this respect was performed by Harry McGurk and John MacDonald in 1976. In their experiment the two researchers were trying to understand the perception of speech by children. Their finding, now called the McGurk effect, published in Nature (Mcgurk & Macdonald, 1976), was that if a person is presented a video sequence with a certain utterance (i.e. in their experiments utterance 'ga'), but in the same time the acoustics present a different utterance (i.e. in their experiments the sound 'ba'), in a large majority of cases the person will perceive a third utterance (i.e. in this case 'da'). Subsequent experiments showed that this is true as well for longer utterances and that is not a particularity of the visual and aural senses but also true for other perception functions. Therefore, lip reading is part of our multi-sensory speech perception process and could be better named visual speech recognition. Being an evolutionary acquired capacity, same as speech perception, some scientists consider the lip reading's neural mechanism the one that enables humans to achieve high literacy skills with relative easiness (van Atteveldt, 2006). Another source of confusion is the “lip” word, because it implies that the lips are the only part of the speaker face that transmit information about what is being said. The teeth, the tongue and the cavity were shown to be of great importance for lip reading by humans (Williams et al., 1998). Also other face elements were shown to be important during face to face communication; however, their exact influence is not completely elucidated. During experiments in which a gaze tracker was used to track the speaker's areas of attention during communication it was found that the human lip readers focus on four major areas: the mouth, the eyes and the centre of the face depending on the task and the noise level (Buchan et al., 2007). In normal situations the listener scans the mouth and the other areas www.intechopen.com" b768cb6fc2616f3dbe9ef4e25dedd7d95781ba66,Distribution Matching in Variational Inference,"Distribution Matching in Variational Inference Mihaela Rosca Balaji Lakshminarayanan Shakir Mohamed DeepMind" b7aee9dfb027d6061c6a653684c0fa9a9bba750d,RECURRENT NEURAL NETWORKS,"Accepted as a workshop contribution at ICLR 2015 LEARNING LONGER MEMORY IN RECURRENT NEURAL NETWORKS Tomas Mikolov, Armand Joulin, Sumit Chopra, Michael Mathieu & Marc’Aurelio Ranzato Facebook Artificial Intelligence Research 770 Broadway New York City, NY, 10003, USA" b75df22c7c52b8d85dd7f155f7b495907ff3561f,Benchmark data and method for real-time people counting in cluttered scenes using depth sensors,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, APRIL 2018 Benchmark data and method for real-time people ounting in cluttered scenes using depth sensors ShiJie Sun, Naveed Akhtar, HuanSheng Song, ChaoYang Zhang, JianXin Li, Ajmal Mian Computer Vision techniques are well-suited to the problem of automatic people counting for public transportations. How- ever, using conventional RGB videos for this purpose is chal- lenged by multiple issues resulting from real-world conditions such as clutter, occlusions, illumination variations, handling shadows etc. In comparison to the conventional video systems, RGB-D cameras (e.g. Kinect V1 [4], Prime Sense Camera [5]) an mitigate these issues by providing ‘depth’ information of the scene in addition to its color video. Nevertheless, effective people counting in real-world conditions using depth information still remains a largely unsolved problem due to noise and occlusion [6]." b732393cd3877f7e6d3cf3ca033a42415bd6db56,Statistical and Geometric Modeling of Spatio-Temporal Patterns for Video Understanding, 2f23f7d08c7b8670289cfedd1e571f44a3bace8b,Contextual Information and Covariance Descriptors for People Surveillance: An Application for Safety of Construction Workers,"Hindawi Publishing Corporation EURASIP Journal on Image and Video Processing Volume 2011, Article ID 684819, 16 pages doi:10.1155/2011/684819 Research Article Contextual Information and Covariance Descriptors for People Surveillance: An Application for Safety of Construction Workers Giovanni Gualdi,1 Andrea Prati,2 and Rita Cucchiara1 DII, University of Modena and Reggio Emilia, 41122 Modena, Italy DISMI, University of Modena and Reggio Emilia, 42122 Reggio Emilia, Italy Correspondence should be addressed to Andrea Prati, Received 30 April 2010; Revised 7 October 2010; Accepted 10 December 2010 Academic Editor: Luigi Di Stefano Copyright © 2011 Giovanni Gualdi et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly ited. In computer science, contextual information can be used both to reduce computations and to increase accuracy. This paper discusses how it can be exploited for people surveillance in very cluttered environments in terms of perspective (i.e., weak scene alibration) and appearance of the objects of interest (i.e., relevance feedback on the training of a classifier). These techniques are pplied to a pedestrian detector that uses a LogitBoost classifier, appropriately modified to work with covariance descriptors which" 2fda164863a06a92d3a910b96eef927269aeb730,Names and faces in the news,"Names and Faces in the News Tamara L. Berg, Alexander C. Berg, Jaety Edwards, Michael Maire, Ryan White, Yee-Whye Teh, Erik Learned-Miller and D.A. Forsyth Computer Science Division U.C. Berkeley Berkeley, CA 94720" 2f8cf3747f3c7d8e230ad9ab3dbc5ea4e6b9cdf1,NIMBLE: a kernel density model of saccade-based visual memory.,"http://journalofvision.org/8/14/17/ NIMBLE: A kernel density model of saccade-based visual memory Luke Barrington Tim K. Marks Janet Hui-wen Hsiao Garrison W. Cottrell Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA, USA Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA, USA Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA, USA We present a Bayesian version of J. Lacroix, J. Murre, and E. Postma’s (2006) Natural Input Memory (NIM) model of saccadic visual memory. Our model, which we call NIMBLE (NIM with Bayesian Likelihood Estimation), uses a cognitively plausible image sampling technique that provides a foveated representation of image patches. We conceive of these memorized image fragments as samples from image class distributions and model the memory of these fragments using kernel density estimation. Using these models, we derive class-conditional probabilities of new image fragments and" 2fa4f66a7c3846a189ea1f962592d7c20d9683b1,Object Detection with YOLO on Artwork Dataset,"Object Detection with YOLO on Artwork Dataset Yihui He∗ Computer Science Department, Xi’an Jiaotong University" 2fa1fc116731b2b5bb97f06d2ac494cb2b2fe475,A novel approach to personal photo album representation and management,"A novel approach to personal photo album representation nd management Edoardo Ardizzone, Marco La Cascia, and Filippo Vella Universit`a di Palermo - Dipartimento di Ingegneria Informatica Viale delle Scienze, 90128, Palermo, Italy" 2fa3ad0329386bf9f55eb2c011e031ca71a11299,Weakly-supervised Semantic Parsing with Abstract Examples, 2f0d5cd2d25ea2f3add0139cf4b61f358435bab8,A New Effective System for Filtering Pornography Videos,"Tarek Abd El Hafeez / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 09, 2010, 2847-2852 A New Effective System for Filtering Pornography Videos Tarek Abd El-Hafeez Department of Computer Science, Faculty of Science, Minia University El-Minia, Egypt" 2f000034f040f6a23c756671477f5f573514af8a,Learning transferable distance functions for human action recognition and detection,"-)41/ 64)5.-4)*- ,156)+- .7+615 .4 07) )+61 4-+/161 ), ,-6-+61 9AEC ;=C *-C 5KJDA=IJ 7ELAHIEJO +DE= % = 6DAIEI E F=HJE= BKBEAJ B JDA HAGKEHAAJI BH JDA B =IJAH B 5?EA?A E JDA 5?D +FKJEC 5?EA?A ? 9AEC ;=C 51 .4)5-4 718-4516; 5FHEC ) HECDJI 0MALAH E MEJD JDA +FOHECDJ )?J B JDEI MH =O >A MEJDKJ =KJDHE=JE JDA BH .=EH ,A=EC 6DAHABHA B JDEI MH BH JDA FKHFIAI B FHEL=JA HAIA=H?D ?HEJE?EI HALEAM AMI HAFHJEC EI EAO J >A E MEJD JDA =M F=HJE?K=HO EB =FFHFHE=JAO" 2f1a5e5b2cc9d2b31913f1b873e2a617b6aaca05,A Particle Filter based Multi-person Tracking with Occlusion Handling, 2f0c30d6970da9ee9cf957350d9fa1025a1becb4,Deformable Convolutional Networks,"Deformable Convolutional Networks Jifeng Dai∗ Haozhi Qi∗,† Yuwen Xiong∗,† Yi Li∗,† Guodong Zhang∗,† Han Hu Yichen Wei Microsoft Research Asia" 2ffc045f48f25bfcf9fe6dbbc86d3f60ff7b112d,Selection of a Visible-Light vs . Thermal Infrared Sensor in Dynamic Environments Based on Confidence Measures,"Appl. Sci. 2014, 4, 331-350; doi:10.3390/app4030331 pplied sciences OPEN ACCESS ISSN 2076-3417 www.mdpi.com/journal/applsci Article Selection of a Visible-Light vs. Thermal Infrared Sensor in Dynamic Environments Based on Confidence Measures Juan Serrano-Cuerda 1, Antonio Fernández-Caballero 1;2;* and María T. López 1;2 Instituto de Investigación en Informática de Albacete, Albacete 02071, Spain; E-Mails: (J.S.-C.); (M.T.L.) Departamento de Sistemas Informáticos, Universidad de Castilla-La Mancha, Albacete 02071, Spain * Author to whom correspondence should be addressed; E-Mail: Tel.: +34-967-599-200; Fax: +34-967-599-224. Received: 16 June 2014; in revised form: 26 July 2014 / Accepted: 4 August 2014 / Published: 8 August 2014" 2fd9ecb40df6c7cd4f27c047223a1e45aae1bb95,Feature-based affine-invariant localization of faces,"Feature-based affine-invariant localization of faces M. Hamouz, J. Kittler, J.-K. Kamarainen, P. Paalanen, H. K¨alvi¨ainen, J. Matas" 2f1972f1fa665f3306a487de9d004dfece719c0b,A Deep Learning Perspective on the Origin of Facial Expressions,"BREUER, KIMMEL: A DEEP LEARNING PERSPECTIVE ON FACIAL EXPRESSIONS A Deep Learning Perspective on the Origin of Facial Expressions Ran Breuer Ron Kimmel Department of Computer Science Technion - Israel Institute of Technology Technion City, Haifa, Israel Figure 1: Demonstration of the filter visualization process." 2f005b31b41face8a8b157e2ce7f97ece5b61391,L 1 Graph Based Sparse Model for Label Denoising,"Pages 74.1-74.12 DOI: https://dx.doi.org/10.5244/C.30.74" 2f33884d0612fcc3f7eed66e1a4acc229860d6b5,Survey on Spatio-Temporal View Invariant Human Pose Recovery,"Survey on Spatio-Temporal View Invariant Human Pose Recovery Xavier Perez-Sala, Email: a;c, Sergio Escalera, Email: b;c and Cecilio Angulo, Email: a CETpD-UPC Technical Research Center for Dependency Care and Autonomous Living, Universitat Polit`ecnica de Catalunya, Ne`apolis, Rambla de l’Exposici´o, 59-69, Dept. Mathematics, Universitat de Barcelona, Gran Via de les Corts Catalanes 585, 08800 Vilanova i la Geltru, Spain Computer Vision Center, Campus UAB, Edifici 0, 08193, Bellaterra, Spain 08007, Barcelona, Spain" 2fa241edb56734539c3b3487eda159e0b3e0f31c,Kinematic Pose Rectification for Performance Analysis and Retrieval in Sports,"Kinematic Pose Rectification for Performance Analysis and Retrieval in Sports Dan Zecha, Moritz Einfalt, Christian Eggert and Rainer Lienhart Multimedia Computing and Computer Vision Lab University of Augsburg" 2f88d3189723669f957d83ad542ac5c2341c37a5,Attribute-correlated local regions for deep relative attributes learning,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 9/13/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use Attribute-correlatedlocalregionsfordeeprelativeattributeslearningFenZhangXiangweiKongZeJiaFenZhang,XiangweiKong,ZeJia,“Attribute-correlatedlocalregionsfordeeprelativeattributeslearning,”J.Electron.Imaging27(4),043021(2018),doi:10.1117/1.JEI.27.4.043021." 2f02328dc09396e37e159141c5e21bef3e6ff06e,Combining face detection and people tracking in video sequences,"Author manuscript, published in ""The 3rd International Conference on Imaging for Crime Detection and Prevention - ICDP09, Kingston Upon Thames (London) : Royaume-Uni (2009)""" 2ff9618ea521df3c916abc88e7c85220d9f0ff06,Facial Tic Detection Using Computer Vision,"Facial Tic Detection Using Computer Vision Christopher D. Leveille Advisor: Prof. Aaron Cass March 20, 2014" 2fc15f80080b4317cad60ad645300b49afddb19e,Low cognitive load strengthens distractor interference while high load attenuates when cognitive load and distractor possess similar visual characteristics.,"Atten Percept Psychophys DOI 10.3758/s13414-015-0866-9 Low cognitive load strengthens distractor interference while high load attenuates when cognitive load and distractor possess similar visual characteristics Takehiro Minamoto & Zach Shipstead & Naoyuki Osaka & Randall W. Engle # The Psychonomic Society, Inc. 2015" 2f29b13fcf7a92a3cc438014068f11f9e45d62be,"AMIGOS: A Dataset for Affect, Personality and Mood Research on Individuals and Groups","AMIGOS: A dataset for Mood, personality and ffect research on Individuals and GrOupS Juan Abdon Miranda-Correa, Student Member, IEEE, Mojtaba Khomami Abadi, Student Member, IEEE, Nicu Sebe, Senior Member, IEEE, and Ioannis Patras, Senior Member, IEEE" 2f529605ed776d4fbeac2d73054247b495504ac7,Person Re-identification for Real-world Surveillance Systems,"Person Re-identification for Real-world Surveillance Systems Furqan M. Khan and Fran¸cois Br´emond INRIA Sophia Antipolis - M´editerran´ee 004 Route des Lucioles, Sophia Antipolis {furqan.khan |" 2fc8f46ed3e679fa50ecddd7e394235d6b983b4e,AudioPairBank : towards a large-scale tag-pair-based audio content analysis,"IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, JULY 2017 AudioPairBank: Towards A Large-Scale Tag-Pair-Based Audio Content Analysis Sebastian S¨ager, and Benjamin Elizalde, and Damian Borth IEEE Member, and Christian Schulze, nd Bhiksha Raj IEEE Fellow, and Ian Lane IEEE Member" 2f7e9b45255c9029d2ae97bbb004d6072e70fa79,cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey,"Noname manuscript No. (will be inserted by the editor) vpaper.challenge in 2015 A review of CVPR2015 and DeepSurvey Hirokatsu Kataoka · Yudai Miyashita · Tomoaki Yamabe · Soma Shirakabe · Shin’ichi Sato · Hironori Hoshino · Ryo Kato · Kaori Abe · Takaaki Imanari · Naomichi Kobayashi · Shinichiro Morita · Akio Nakamura Received: date / Accepted: date" 2fda461869f84a9298a0e93ef280f79b9fb76f94,OpenFace: An open source facial behavior analysis toolkit,"OpenFace: an open source facial behavior analysis toolkit Tadas Baltruˇsaitis Peter Robinson Louis-Philippe Morency" 2faa09413162b0a7629db93fbb27eda5aeac54ca,Quantifying how lighting and focus affect face recognition performance,"NISTIR 7674 Quantifying How Lighting and Focus Affect Face Recognition Performance Phillips, P. J. Beveridge, J. R. Draper, B. Bolme, D. Givens, G. H. Lui, Y. M." 2f7452476910a7dbf6231b6b27aed67d9ed455d3,Seam carving for content-aware image resizing,"Seam Carving for Content-Aware Image Resizing Shai Avidan Mitsubishi Electric Research Labs Ariel Shamir The Interdisciplinary Center & MERL Figure 1: A seam is a connected path of low energy pixels in an image. On the left is the original image with one horizontal and one vertical seam. In the middle the energy function used in this example is shown (the magnitude of the gradient), along with the vertical and horizontal path maps used to calculate the seams. By automatically carving out seams to reduce image size, and inserting seams to extend it, we achieve ontent-aware resizing. The example on the top right shows our result of extending in one dimension and reducing in the other, compared to standard scaling on the bottom right." 2f988201fb8316772bca1b44cc0e42f774edd714,Conditional Random Field (CRF)-Boosting: Constructing a Robust Online Hybrid Boosting Multiple Object Tracker Facilitated by CRF Learning,"Article Conditional Random Field (CRF)-Boosting: Constructing a Robust Online Hybrid Boosting Multiple Object Tracker Facilitated by CRF Learning Ehwa Yang, Jeonghwan Gwak and Moongu Jeon * School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Korea; (E.Y.); (J.G.) * Correspondence: Tel.: +82-62-715-2406 Academic Editor: Joonki Paik Received: 6 December 2016; Accepted: 14 March 2017; Published: 17 March 2017" 2f8ef26bfecaaa102a55b752860dbb92f1a11dc6,A Graph Based Approach to Speaker Retrieval in Talk Show Videos with Transcript-Based Supervision,"A Graph Based Approach to Speaker Retrieval in Talk Show Videos with Transcript-Based Supervision Yina Han 1, Guizhong Liu, Hichem Sahbi, Gérard Chollet" 2fdb3576715829aa9bbaf74825236bbb71d06f1a,Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification,"Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification Lin Wu, Yang Wang, Junbin Gao, Xue Li" 2f78e471d2ec66057b7b718fab8bfd8e5183d8f4,An Investigation of a New Social Networks Contact Suggestion Based on Face Recognition Algorithm,"SOFTWARE ENGINEERING VOLUME: 14 | NUMBER: 5 | 2016 | DECEMBER An Investigation of a New Social Networks Contact Suggestion Based on Face Recognition Algorithm Ivan ZELINKA1,2, Petr SALOUN 2, Jakub STONAWSKI 2, Adam ONDREJKA2 Modeling Evolutionary Algorithms Simulation and Artificial Intelligence, Faculty of Electrical & Electronics Engineering, Ton Duc Thang University, 19 Nguyen Huu Tho Street, Ho Chi Minh City, Vietman Department of Computer Science, Faculty of Electrical Engineering and Computer Science, VSB–Technical University of Ostrava, 17. listopadu 15, 708 33 Ostrava, Czech Republic DOI: 10.15598/aeee.v14i5.1116" 2f184c6e2c31d23ef083c881de36b9b9b6997ce9,Polichotomies on imbalanced domains by one-per-class compensated reconstruction rule,"Polichotomies on Imbalanced Domains y One-per-Class Compensated Reconstruction Rule Roberto D’Ambrosio and Paolo Soda Integrated Research Centre, Universit´a Campus Bio-Medico of Rome, Rome, Italy" 2f3125bf303bca19d9cdc9ffe1de2aacf7a23023,In-Bed Pose Estimation: Deep Learning with Shallow Dataset,"JOURNAL OF , VOL. , NO. , MONTH YEAR In-Bed Pose Estimation: Deep Learning with Shallow Dataset Shuangjun Liu, Yu Yin, and Sarah Ostadabbas" 2fdc469096f72533726964260c80b4c14ae62fab,A KERNEL MAXIMUM UNCERTAINTY DISCRIMINANT ANALYSIS AND ITS APPLICATION TO FACE RECOGNITION,"A KERNEL MAXIMUM UNCERTAINTY DISCRIMINANT ANALYSIS AND ITS APPLICATION TO FACE RECOGNITION Department of Electrical Engineering, Centro Universitario da FEI, FEI, Sao Paulo, Brazil Carlos Eduardo Thomaz Gilson Antonio Giraldi Department of Computer Science, National Laboratory for Scientific Computing, LNCC, Rio de Janeiro, Brazil Keywords:" 2f43bfedb8cffc9e44de9f95db80b26395a29cc8,Generalized Hadamard-Product Fusion Operators for Visual Question Answering,"Generalized Hadamard-Product Fusion Operators for Visual Question Answering Brendan Duke∗†, Graham W. Taylor∗†‡ School of Engineering, University of Guelph Vector Institute for Artificial Intelligence Canadian Institute for Advanced Research" 2f04c7aaac3a884088be550d1be51b4a0b585a2e,"Robust, Real-Time 3D Tracking of Multiple Objects with Similar Appearances","Robust, Real-Time 3D Tracking of Multiple Objects with Similar Appearances Taiki Sekii Panasonic System Networks R&D Lab. Co., Ltd." 2f48f1cb1cfef964fa70d7868b87d81455e7be2e,A new image centrality descriptor for wrinkle frame detection in WCE videos,"MVA2013 IAPR International Conference on Machine Vision Applications, May 20-23, 2013, Kyoto, JAPAN A new image centrality descriptor for wrinkle frame detection in WCE videos. Santi Segu´ı1,2, Ekaterina Zaytseva1,2, Michal Drozdzal1,2, Carolina Malagelada3, Fernando Azpiroz3, Petia Radeva1,2 and Jordi Vitri`a1,2 Computer Vision Center (CVC), Universitat Aut`onoma de Barcelona, Barcelona, Spain Dept. Matem`atica Aplicada i An`alisis, Universitat de Barcelona, Barcelona, Spain Digestive System Research Unit, Hospital Vall dHebron, Barcelona, Spain" 2f59f28a1ca3130d413e8e8b59fb30d50ac020e2,Children Gender Recognition Under Unconstrained Conditions Based on Contextual Information,"Children Gender Recognition Under Unconstrained Conditions Based on Contextual Information Riccardo Satta, Javier Galbally and Laurent Beslay Joint Research Centre, European Commission, Ispra, Italy Email:" 2f3c60ebd92240099e52c1cb6d33832b0b8979d1,Spatial pyramid co-occurrence for image classification,"011 IEEE International Conference on Computer Vision 978-1-4577-1102-2/11/$26.00 c(cid:13)2011 IEEE" 2f3a67394deb32f265bcff9daf2c829d4be36336,Improving Visual Relationship Detection Using Semantic Modeling of Scene Descriptions,"Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions Stephan Baier1, Yunpu Ma1,2, and Volker Tresp1,2 Ludwig Maximilian University, 80538 Munich, Germany Siemens AG, Corporate Technology, Munich, Germany" 2feea7d50b312a6c07673fda325838139b2e7820,Analysis of technologies and resources for multimodal information kiosk for deaf users,"Analysis of Technologies and Resources for Multimodal Information Kiosk for Deaf Users Miloˇs ˇZelezn´y Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czech Republic" 2f587ab6694fdcfe6bd2977120ebeb758e28d77f,Coupled Generative Adversarial Nets,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Coupled Generative Adversarial Nets Liu, M.-Y.; Tuzel, O. TR2016-070 June 2016" 2fa1629d75a03b950c56bf9b3430b2983abd7881,Learning geometrical transforms between multi camera views using Canonical Correlation Analysis,"CONRAD, MESTER: LEARNING GEOMETRICAL TRANSFORMS USING CCA Learning geometrical transforms between multi camera views using Canonical Correlation Analysis Christian Conrad Rudolf Mester Visual Sensorics and Information Processing Lab, Goethe University Frankfurt am Main, Germany Computer Vision Laboratory Electr. Eng. Dept. (ISY) Linköping University, Sweden" 2f95340b01cfa48b867f336185e89acfedfa4d92,Face expression recognition with a 2-channel Convolutional Neural Network,"Face Expression Recognition with a 2-Channel Convolutional Neural Network Dennis Hamester, Pablo Barros, Stefan Wermter University of Hamburg — Department of Informatics Vogt-K¨olln-Straße 30, 22527 Hamburg, Germany http://www.informatik.uni-hamburg.de/WTM/" 2f489bd9bfb61a7d7165a2f05c03377a00072477,Structured Semi-supervised Forest for Facial Landmarks Localization with Face Mask Reasoning,"JIA, YANG: STRUCTURED SEMI-SUPERVISED FOREST Structured Semi-supervised Forest for Facial Landmarks Localization with Face Mask Reasoning Department of Computer Science The Univ. of Hong Kong, HK School of EECS Queen Mary Univ. of London, UK Xuhui Jia1 Heng Yang2 Angran Lin1 Kwok-Ping Chan1 Ioannis Patras2" 2fce767ad830e0203d62ce30bbe75213b959d19c,Histogram of Log-Gabor Magnitude Patterns for face recognition,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE School of Information and Communication Engineering, {yijun, Jun Yi†, Fei Su†‡ . INTRODUCTION" 2f77c0908716b0febfda19ff6a0e2970c23af440,A face recognition system dealing with expression variant faces,"A face recognition system dealing with expression variant faces Stefano Arca∗, Paola Campadelli, Raffaella Lanzarotti, Giuseppe Lipori Dipartimento di Scienze dell’Informazione Universit`a degli Studi di Milano Via Comelico, 39/41 20135 Milano, Italy" 2f13dd8c82f8efb25057de1517746373e05b04c4,Evaluation of state-of-the-art algorithms for remote face recognition,"EVALUATION OF STATE-OF-THE-ART ALGORITHMS FOR REMOTE FACE RECOGNITION Jie Ni and Rama Chellappa Department of Electrical and Computer Engineering and Center for Automation Research, University of Maryland, College Park, MD 20742, USA" 2fe5bea76853da079512595fb8bdd74ef4ccf12f,Face recognition using two-dimensional nonnegative principal component analysis,"Face recognition using two-dimensional nonnegative principal component nalysis Peng Ma Dan Yang Yongxin Ge Xiaohong Zhang Ying Qu Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 08/24/2012 Terms of Use: http://spiedl.org/terms" 2ff37f7e00c624066f596b71ca3331171d0f66d1,‘ vVISWa ’ – A Multilingual Multi-Pose Audio Visual Database for Robust Human Computer Interaction,"International Journal of Computer Applications (0975 – 8887) Volume 137 – No.4, March 2016 ‘vVISWa’ – A Multilingual Multi-Pose Audio Visual Database for Robust Human Computer Interaction Ramesh Manza Biomedical Image Processing Lab Dr. Babasaheb Ambedkar Bharti Gawali SpeechCommunication nd Machine Research Lab Dr. Babasaheb Ambedkar Pravin Yannawar Vision and Intelligent System Lab Dr. Babasaheb Ambedkar Prashant Borde" 2fc2250d843326f3eefab1941e5a6e54eef239b3,Appearance Based Facial Recognition System Using Dhmm with Linear Discriminant Analysis,"Daffodil International University Institutional Repository DIU Journal of Science and Technology Volume 10, Issue 1-2, July 2015 016-06-18 Appearance Based Facial Recognition System Using Dhmm with Linear Discriminant Analysis Islam, Md. Rabiul http://hdl.handle.net/20.500.11948/1487 Downloaded from http://dspace.library.daffodilvarsity.edu.bd, Copyright Daffodil International University Library" aa09ade36424fd83f067f234baffde294800e705,Is a Picture Worth Ten Thousand Words in a Review Dataset?,"Is a Picture Worth Ten Thousand Words in a Review Dataset? Roberto Camacho, Laura M. Rodriguez, Rebecca Urbina, and M. Shahriar Hossain Dept. of Computer Science, University of Texas at El Paso, El Paso, TX 79968 {lmrodriguez3," aabcbe3ee81ff4f696c7cefc49d28a41fb760987,Automated annotation of coral reef survey images,"Automated Annotation of Coral Reef Survey Images Oscar Beijbom† Peter J. Edmunds∗ David I. Kline‡ B. Greg Mitchell‡ David Kriegman† {obeijbom, dkline, gmitchell, {†Department of Computer Science and Engineering, ‡Scripps Institution of Oceanography}, University of California, San Diego. ∗Department of Biology, California State University Northridge." aad8d2e32f1cc21eedbdd5e8ebff9f367daa6d92,Online multi-target tracking by large margin structured learning,"Online Multi-Target Tracking y Large Margin Structured Learning Suna Kim, Suha Kwak, Jan Feyereisl, and Bohyung Han Department of Computer Science and Engineering POSTECH, Korea" aaa021feeec2f84c4a5f3c56b4c0fecb5a85a352,A Riemannian Network for SPD Matrix Learning,"A Riemannian Network for SPD Matrix Learning Zhiwu Huang and Luc Van Gool Computer Vision Lab, ETH Zurich, Switzerland {zhiwu.huang," aa261599d70a9e649501cae5cf46fbc56229fad8,The effect of the Distance in Pedestrian Detection,"Master in Computer Vision and Artificial Intelligence - Universitat Aut`onoma de Barcelona September 2009 The effect of the Distance in Pedestrian Detection David V´azquez Berm´udez Computer Vision Center Edifici O, Universitat Aut`onoma de Barcelona 08193, Bellaterra (Spain) Advisors: Dr. Antonio M. L´opez and David Ger´onimo" aaa82dfc7942ae16c1d7155a109582505ccee4ec,Properties of Datasets Predict the Performance of Classifiers,"AGHAZADEH, CARLSSON: PROPERTIES OF DATASETS PREDICT THE PERFORMANCE ... 1 Properties of Datasets Predict the Performance of Classifiers Omid Aghazadeh http://www.csc.kth.se/~omida Stefan Carlsson http://www.csc.kth.se/~stefanc Computer Vision Group Computer Vision and Active Perception Laboratory KTH, Sweden" aa17a5e76ae21d0d068c7f10a4bb24c19888b685,SPARSE BAYESIAN LEARNING IN CLASSIFYING FACE FEATURE VECTORS,"JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 9/2005, ISSN 1642-6037 Alina MOMOT, Michał KAWULOK * supervised learning, Bayesian inference, face recognition SPARSE BAYESIAN LEARNING IN CLASSIFYING FACE FEATURE VECTORS The Relevance Vector Machine (RVM), a Bayesian treatment of generalized linear model of identical functional form to the Support Vector Machine (SVM), is the recently developed machine learning framework apable of building simple models from large sets of candidate features. The paper describes the application of the RVM to a classification algorithm of face feature vectors, obtained by Eigenfaces method. Moreover, the results of the RVM classification are compared with those obtained by using both the Support Vector Machine method and the method based on the Euclidean distance. . INTRODUCTION The aim of the machine learning is extracting the structure from the data. Anyhow it is often difficult to solve problems like classification in the space, in which the underlying observations have been made. Kernel-based learning methods like the Support Vector Machine (SVM) [7] or the Relevance Vector Machine (RVM) [4] use implicit mapping of the input data into a high dimensional feature space defined by a kernel function and the learning takes place in the feature space. An interesting property of kernel-based systems is that, once a valid kernel function has been selected, one can practically work in spaces of any dimension without paying any computational ost, since feature mapping is never effectively performed." aac101dd321e6d2199d8c0b48c543b541c181b66,USING CONTEXT TO ENHANCE THE UNDERSTANDING OF FACE IMAGES,"USING CONTEXT TO ENHANCE THE UNDERSTANDING OF FACE IMAGES A Dissertation Presented VIDIT JAIN Submitted to the Graduate School of the University of Massachusetts Amherst in partial fulfillment of the requirements for the degree of DOCTOR OF PHILOSOPHY September 2010 Department of Computer Science" aa23d33983b1abd2d8a677040eb875e93c478a7f,Measuring the Objectness of Image Windows,"Measuring the objectness of image windows Bogdan Alexe, Thomas Deselaers, and Vittorio Ferrari" aad7f9eeb10d4f655c3e3d18d3542603ad3071b4,Deep Unsupervised Learning of Visual Similarities,"Deep Unsupervised Learning of Visual Similarities Artsiom Sanakoyeu∗, Miguel A. Bautista, Björn Ommer Heidelberg Collaboratory for Image Processing and Interdisciplinary Center for Scientific Computing, Heidelberg University, Germany" aad03480c30c0a3d917d171d8d6b914026fe5105,Affordances Provide a Fundamental Categorization Principle for Visual Scenes,"Affordances Provide Fundamental Categorization Principle Visual Scenes Michelle Greene Christopher Baldassano Andre Esteva Diane (1) Stanford University, Department Computer Science (2) Stanford" aa8cec9cec1f15f95bbe0ef4d7809e199de0f30b,Vitamin D hormone regulates serotonin synthesis. Part 1: relevance for autism.,"The FASEB Journal (cid:129) Review Vitamin D hormone regulates serotonin synthesis. Part 1: relevance for autism Rhonda P. Patrick1 and Bruce N. Ames1 Nutrition and Metabolism Center, Children’s Hospital Oakland Research Institute, Oakland, California, USA Serotonin and vitamin D have been pro-" aa9b924c88b75909871585cbadbed2d76df7dbdf,The effects of item familiarity on the neural correlates of successful associative memory encoding.,"Cogn Affect Behav Neurosci DOI 10.3758/s13415-015-0359-2 The effects of item familiarity on the neural correlates of successful associative memory encoding Nancy A. Dennis 1 & Indira C. Turney 1 & Christina E. Webb 1 & Amy A. Overman 2 # Psychonomic Society, Inc. 2015" aa5efcc4331da6b1902f2c900b79120226fdcf20,A ROBUST CLASS-BASED REFLECTANCE RENDERING FOR FACE IMAGES,A ROBUST CLASS-BASED REFLECTANCE RENDERING FOR FACE IMAGES aa5ed6ee0b2fd53df5cab952aa368f8c4908ffeb,REACH - Realtime crowd tracking using a hybrid motion model,"REACH - Realtime Crowd tracking using a Hybrid motion model Aniket Bera1 and Dinesh Manocha1 http://gamma.cs.unc.edu/REACH" aa2ad3df24d8d8c4a4d2fe85f0d4e635d595f0a2,PedCut: an iterative framework for pedestrian segmentation combining shape models and multiple data cues,"F. FLOHR, D. M. GAVRILA: PEDCUT PedCut: an iterative framework for pedestrian segmentation combining shape models and multiple data cues Fabian Flohr1,2 Dariu M. Gavrila1,2 www.gavrila.net Environment Perception Department, Daimler R&D, Ulm, Germany Intelligent Systems Laboratory, Univ. of Amsterdam, The Netherlands" aa36d50e7cb584d68a3eef0d3345954aa58f63df,Sub-Image Homomorphic Filtering Technique for Improving Facial Identification under Difficult Illumination Conditions,"International Conference on Systems, Signals and Image Processing (IWSSIP’06) September 21-23, 2006. Budapest, Hungary" aadfcaf601630bdc2af11c00eb34220da59b7559,Multi-view Hybrid Embedding: A Divide-and-Conquer Approach,"Multi-view Hybrid Embedding: A Divide-and-Conquer Approach Jiamiao Xu∗, Shujian Yu∗, Xinge You†, Senior Member, IEEE, Mengjun Leng, Xiao-Yuan Jing, and C. L. Philip Chen, Fellow, IEEE" aa782f4af587ee68936f0f5361fc1448ef61bdd9,Human Tracking using Wearable Sensors in the Pocket Double blind submission,"Human Tracking using Wearable Sensors in the Pocket Double blind submission Address e-mail address" aaa4c625f5f9b65c7f3df5c7bfe8a6595d0195a5,Biometrics in ambient intelligence,"Biometrics in Ambient Intelligence Massimo Tistarelli§ and Ben Schouten§§" aaaeca92457a72ec4e7e538cf6393c4c1dc8e670,Life-long Learning Perception using Cloud Database Technology,"Life-long Learning Perception using Cloud Database Technology Tim Niemueller Stefan Schiffer Gerhard Lakemeyer Knowledge-based Systems Group Safoura Rezapour Lakani Intelligent and Interactive Systems RWTH Aachen University (Aachen, Germany) University of Innsbruck (Innsbruck, Austria)" aa5c2ac60a288132efeeb85c5af1fd0b39294eed,Directed Markov Stationary Features for visual classification,"978-1-4244-2354-5/09/$25.00 ©2009 IEEE ICASSP 2009" aa49556ee4f1ee3fcc9f0f713c755da30b0f505c,Exactly Robust Kernel Principal Component Analysis,"Exactly Robust Kernel Principal Component Analysis Jicong Fan, Tommy W.S. Chow" aaf1d8237524ebe671b3e56f803747b7092dd1f8,Robust visual SLAM with point and line features,"Robust Visual SLAM with Point and Line Features Xingxing Zuo1, Xiaojia Xie1, Yong Liu1,2 and Guoquan Huang3" aa5fbe092f8a4dcb43c31ab93af0290900b4f0e2,Visual Question Answering using Natural Language Object Retrieval and Saliency Cues,"Visual Question Answering using Natural Language Object Retrieval and CS381V Final Project Report Saliency Cues Aishwarya Padmakumar Akanksha Saran" aa8cc8a80fe591676b09ef50b9cc695c28460c73,Sensing requirements for an automated vehicle for highway and rural environments,Sensingrequirementsforanautomatedvehicleforhigh-wayandruralenvironmentsMScthesisK.J.BussemakerTechnischeUniversiteitDelft aae1bf434983545c8a99a5dbfc2ce37435c76e03,SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data,"CHEN ET.AL: SAMPLEAHEAD – ONLINE CLASSIFIER-SAMPLER COMMUNICATION SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data Department of Computer Science, The Johns Hopkins Univerisity * This work is supported by IARPA via DOI/IBC contract #D17PC00345 and ONR grant N00014-15-1-2356. Qi Chen, Weichao Qiu, Yi Zhang Lingxi Xie(), Alan L. Yuille" aafb8dc8fda3b13a64ec3f1ca7911df01707c453,Excitation Backprop for RNNs,"Excitation Backprop for RNNs Sarah Adel Bargal∗1, Andrea Zunino∗ 2, Donghyun Kim1, Jianming Zhang3, Vittorio Murino2,4, Stan Sclaroff1 Department of Computer Science, Boston University 2Pattern Analysis & Computer Vision (PAVIS), Istituto Italiano di Tecnologia 3Adobe Research 4Computer Science Department, Universit`a di Verona Figure 1: Our proposed framework spatiotemporally highlights/grounds the evidence that an RNN model used in producing a class label or caption for a given input video. In this example, by using our proposed back-propagation method, the evidence for the activity class CliffDiving is highlighted in a video that contains CliffDiving and HorseRiding. Our model employs a single backward pass to produce saliency maps that highlight the evidence that a given RNN used in generating its outputs." aa2a4f7cf8866d513053873a410879ab5b34b53a,Improving robot manipulation with data-driven object-centric models of everyday forces,"Noname manuscript No. (will be inserted by the editor) Improving Robot Manipulation with Data-Driven Object-Centric Models of Everyday Forces Advait Jain · Charles C. Kemp Received: date / Accepted: date" aa420d32c48a3fd526a91285673cd55ca9fe2447,R 4-A . 1 : Dynamics-Based Video Analytics,"R4-A.1: Dynamics-Based Video Analytics PARTICIPANTS Octavia Camps Mario Sznaier Title Co-PI Co-PI Faculty/Staff Institution Graduate, Undergraduate and REU Students Oliver Lehmann Mengran Gou Yongfang Cheng Yin Wang Sadjad Ashari-Esfeden Tom Hebble Rachel Shaff er Burak Yilmaz Degree Pursued MSEE/ PhD" aa3e1824af497dc16ae27e6818a0e89c78a18371,Local Gray Code Pattern ( LGCP ) : A Robust Feature Descriptor for Facial Expression Recognition,"International Journal of Science and Research (IJSR), India Online ISSN: 2319-7064 Local Gray Code Pattern (LGCP): A Robust Feature Descriptor for Facial Expression Recognition Mohammad Shahidul Islam Atish Dipankar University of Science & Technology, School, Department of Computer Science and Engineering, Dhaka, Bangladesh." aa6854612062edff9978b33e0a410f2717bc3027,LPT: Eye Features Localizer in an N-Dimensional Image Space.,"LPT: Eye Features Localizer in an N-Dimensional Image Space Mohammad Mahdi Dehshibi1, Azam Bastanfard2, and Alireza Abdi3 Young Researchers Club, Islamic Azad University South Tehran Branch, Tehran, Iran IT Research Laboratory, Faculty of Engineering, Islamic Azad University Karaj Branch, Karaj, Iran Faculty of Electrical, Computer and IT, Islamic Azad University Qazvin Branch, Qazvin, Iran" aa94f214bb3e14842e4056fdef834a51aecef39c,Reconhecimento de padrões faciais : Um estudo,"Reconhecimento de padrões faciais: Um estudo Alex Lima Silva, Marcos Evandro Cintra Universidade Federal Rural do Semi-Árido Departamento de Ciências Naturais Mossoró, RN - 59625-900 Email: Resumo—O reconhecimento facial tem sido utilizado em di- versas áreas para identificação e autenticação de usuários. Um dos principais mercados está relacionado a segurança, porém há uma grande variedade de aplicações relacionadas ao uso pessoal, onveniência, aumento de produtividade, etc. O rosto humano possui um conjunto de padrões complexos e mutáveis. Para reconhecer esses padrões, são necessárias técnicas avançadas de reconhecimento de padrões capazes, não apenas de reconhecer, mas de se adaptar às mudanças constantes das faces das pessoas. Este documento apresenta um método de reconhecimento facial proposto a partir da análise comparativa de trabalhos encontra- dos na literatura. iométrica é o uso da biometria para reconhecimento, identi-" aa6f094f17d78380f927555a348ad514a505cc3b,SlowFast Networks for Video Recognition,"SlowFast Networks for Video Recognition Christoph Feichtenhofer Haoqi Fan Jitendra Malik Kaiming He Facebook AI Research (FAIR)" aa74e63360c341f47a921e0043c5d58d55807fe4,Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks,"SUBMITTED FOR PUBLICATION, 2016 Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks Masoud Abdi, and Saeid Nahavandi, Senior Member, IEEE" 74d4224989b5937ee6c97eec1955e64ab0699f57,Facial Emotional Classifier For Natural Interaction,"Electronic Letters on Computer Vision and Image Analysis 7(4):1-12, 2008 Facial Emotional Classifier For Natural Interaction Isabelle Hupont, Eva Cerezo, Sandra Baldassarri Departamento de Informática e Ingeniería de Sistemas, Instituto de Investigación en Ingeniería de Aragón, Universidad de Zaragoza (Spain) Received 29th November 2007, Revised 26th February 2008, Accepted 3rd June 2008 {478953, ecerezo," 74408cfd748ad5553cba8ab64e5f83da14875ae8,Facial Expressions Tracking and Recognition: Database Protocols for Systems Validation and Evaluation,"Facial Expressions Tracking and Recognition: Database Protocols for Systems Validation nd Evaluation" 74f21f2edfa985280be63f8a01aa00541f3a5625,People Groping by Spatio-Temporal Features of Trajectories,"4-13 MVA2013 IAPR International Conference on Machine Vision Applications, May 20-23, 2013, Kyoto, JAPAN People Groping by Spatio-Temporal Features of Trajectories Asami Okada†, Yusuke Moriguchi†, Norimichi Ukita†, nd Norihiro Hagita†‡ Nara Institute od Science and Technology Advanced Telecommunications Research Institute International e-mail" 74e6110466306f41f703d84bb3d136ba414b1998,Face Recognition System under Varying Lighting Conditions,"IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661, p- ISSN: 2278-8727Volume 14, Issue 3 (Sep. - Oct. 2013), PP 79-88 www.iosrjournals.org Face Recognition System under Varying Lighting Conditions P.Kalaiselvi1, S.Nithya2 (Asst. Professor, Department of ECE, NSN College of Engineering and Technology, Karur, Tamilnadu, India) (Asst. Professor, Department of ECE, NSN College of Engineering and Technology, Karur, Tamilnadu, India)" 7444adac0f4c0004fe557e7fd68fdc89c99ca10b,CUNI System for the WMT18 Multimodal Translation Task,"CUNI System for the WMT18 Multimodal Translation Task Jindˇrich Helcl and Jindˇrich Libovick´y and Duˇsan Variˇs Charles University, Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics Malostransk´e n´amˇest´ı 25, 118 00 Prague, Czech Republic {helcl, libovicky," 74dbe6e0486e417a108923295c80551b6d759dbe,An HMM based Model for Prediction of Emotional Composition of a Facial Expression using both Significant and Insignificant Action Units and Associated Gender Differences,"International Journal of Computer Applications (0975 – 8887) Volume 45– No.11, May 2012 An HMM based Model for Prediction of Emotional Composition of a Facial Expression using both Significant and Insignificant Action Units and Associated Gender Differences Suvashis Das Koichi Yamada Department of Management and Information Department of Management and Information Systems Science 603-1 Kamitomioka, Nagaoka Niigata, Japan Systems Science 603-1 Kamitomioka, Nagaoka Niigata, Japan" 74b0095944c6e29837c208307a67116ebe1231c8,Manifold learning using Euclidean k-nearest neighbor graphs [image processing examples]," beindependentandidenticallydis-tributed(i.i.d.)randomvectorswithvaluesinacompactsubsetof.The(-)nearestneighborof inisgivenby!""$%&(*,.%135 7 5where5 7 5istheusualEuclidean(<=)distanceinbe-tweenvector and .Forgeneralinteger?,the-nearestneighborofapointisdefinedinasimilarway.The-NNgraphputsanedgebetweeneachpointinandits-nearestneighbors.LetBCDBCDFHbethesetof-nearestneighborsof in.Thetotaledgelengthofthe-NNgraphisdefinedas: HAL Id: hal-00121790 https://hal.archives-ouvertes.fr/hal-00121790 Submitted on 22 Dec 2006 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 02ccd5f0eb9a48a6af088197b950fb30a8e3abcc,Scaling for Multimodal 3D Object Detection,"Scaling for Multimodal 3D Object Detection Andrej Karpathy Stanford" 02f038ed453de0551813159284746126168f5e15,Multi Channel-Kernel Canonical Correlation Analysis for Cross-View Person Re-Identification,"This is a pre-print version, the final version of the manuscript with more experiments can be found at: https://doi.org/10.1145/3038916 Analysis for Cross-View Person Re-Identification Giuseppe Lisanti, Svebor Karaman, Iacopo Masi" 022edc074693c52d4e689947bd2def8b2117fa8b,A super-resolution method for low-quality face image through RBF-PLS regression and neighbor embedding,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 02b72a5a4389cb32a7dd784b1c9084e8412e2e78,Hierarchical Bayesian Image Models,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,700 08,500 .7 M Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact" 0273414ba7d56ab9ff894959b9d46e4b2fef7fd0,Photographic home styles in Congress: a computer vision approach,"Photographic home styles in Congress: a omputer vision approach∗ L. Jason Anastasopoulos†. Dhruvil Badani‡ Crystal Lee§ Shiry Ginosar¶ Jake Williams(cid:107) December 1, 2016" 02fbf86b975c3f45b04de8288d1565cce8b53f62,A real-time pedestrian detection system based on structure and appearance classification,"Anchorage Convention District May 3-8, 2010, Anchorage, Alaska, USA 978-1-4244-5040-4/10/$26.00 ©2010 IEEE" 02cce8b08e4839d16f2142c5723fc009ccb4e3e1,Improving spatial codification in semantic segmentation,"IMPROVING SPATIAL CODIFICATION IN SEMANTIC SEGMENTATION Carles Ventura(cid:63) Kevin McGuinness† Xavier Gir´o-i-Nieto(cid:63) Ferran Marqu´es(cid:63) Ver´onica Vilaplana(cid:63) Noel E. O’Connor† (cid:63) Universitat Polit`ecnica de Catalunya (UPC), Barcelona, Spain Insight Centre for Data Analytics, Dublin City University (DCU), Ireland" 02aff7faf2f6b775844809805424417eed30f440,"A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models","QUARTERLY OF APPLIED MATHEMATICS VOLUME , NUMBER 0 XXXX XXXX, PAGES 000–000 A TALE OF THREE PROBABILISTIC FAMILIES: DISCRIMINATIVE, DESCRIPTIVE AND GENERATIVE MODELS YING NIAN WU (Department of Statistics, University of California, Los Angeles), RUIQI GAO (Department of Statistics, University of California, Los Angeles), TIAN HAN (Department of Statistics, University of California, Los Angeles), SONG-CHUN ZHU (Department of Statistics, University of California, Los Angeles)" 02b0bf28f34c3c403abecd2fb4fb7d4969c0e0db,Learning Disentangled Joint Continuous and Discrete Representations,"Learning Disentangled Joint Continuous and Discrete Representations Schlumberger Software Technology Innovation Center Emilien Dupont Menlo Park, CA, USA" 026ca771bd3995748b477e100ed4283a9bf8215a,Predicting Performance of a Face Recognition System Based on Image Quality,"Predicting Performance of a Face Recognition System Based on Image Quality Abhishek Dutta" 0278acdc8632f463232e961563e177aa8c6d6833,Selective Transfer Machine for Personalized Facial Expression Analysis,"Selective Transfer Machine for Personalized Facial Expression Analysis Wen-Sheng Chu, Fernando De la Torre, and Jeffrey F. Cohn INTRODUCTION Index Terms—Facial expression analysis, personalization, domain adaptation, transfer learning, support vector machine (SVM) A UTOMATIC facial AU detection confronts a number of" 028dc6a134f1204bd9ae28213e2e6665e82ddcb0,Integral Normalized Gradient Image A Novel Illumination Insensitive Representation,"Integral Normalized Gradient Image A Novel Illumination Insensitive Representation Samsung Advanced Institute of Technology E-mail:" 0297fbba5d7eacc48b2e1682d64d33a7dc6be88c,Face anti-spoofing methods,"REVIEW ARTICLES Face anti-spoofing methods Sajida Parveen1,3,*, Sharifah Mumtazah Syed Ahmad1,2, Marsyita Hanafi1 and Wan Azizun Wan Adnan1 Department of Computer and Communication Systems Engineering, and Wireless and Photonic Networks Research Centre of Excellence, Universiti Putra, Malaysia Department of Computer Systems Engineering, Quaid-e-Awam University of Engineering, Science and Technology, Nawabshah, Pakistan In recent years, facial biometric systems have received increased deployment in various applications such as surveillance, access control and forensic investiga- tions. However, one of the limitations of face recogni- tion system is the high possibility of the system being deceived or spoofed by non-real faces such as photo- graph, video clips or dummy faces. In order to identify the spoofing attacks on such biometric systems, face liveness detection approaches have been developed. Thus, the current approach is to integrate liveness de- tection within facial biometrics by using life sign indi- ators of individual features. This article presents a review of state-of-the-art techniques in face liveness" 02bee2cef6b04e6b57cfa3fd54cabc756f0c2e8d,Data-driven Methods for Interactive Visual Content Creation and Manipulation,"Data-driven Methods for Interactive Visual Content Creation nd Manipulation Dissertation zur Erlangung des Grades des Doktors der Ingenieurwissenschaften der Naturwissenschaftlich-Technischen Fakultäten der Universität des Saarlandes Vorgelegt durch Arjun Jain Max-Planck-Institut Informatik Campus E1 4 66123 Saarbrücken Germany m 4. February 2013 in Saarbrücken" 02a2c5b332d883d726929474060a7e62411c010a,Totally Corrective Multiclass Boosting with Binary Weak Learners,"SEPTEMBER 2010 with Binary Weak Learners Zhihui Hao, Chunhua Shen, Nick Barnes, and Bo Wang" 0252256fa23eceb54d9eea50c9fb5c775338d9ea,Application-driven Advances in Multi-biometric Fusion,"Application-driven Advances in Multi-biometric Fusion dem Fachbereich Informatik der Technischen Universität Darmstadt vorzulegende DISSERTATION zur Erlangung des akademischen Grades eines Doktor-Ingenieurs (Dr.-Ing.) M.Sc. Naser Damer geboren in Amman, Jordanien Referenten der Arbeit: Prof. Dr. Arjan Kuijper Technische Universität Darmstadt Prof. Dr. Dieter W. Fellner Technische Universität Darmstadt Prof. Dr. Raghavendra Ramachandra Norwegian University of Science and Technology Tag der Einreichung: Tag der mündlichen Prüfung: 2/01/2018" 02f1d5c896ced7f6f002eb7514ba49eca940b75c,A Comparison of Efficient Global Image Features for Localizing Small Mobile Robots,"A Comparison of Efficient Global Image Features for Localizing Small Mobile Robots Marius Hofmeister, Philipp Vorst and Andreas Zell Computer Science Department, University of Tübingen, Tübingen, Germany" 0241513eeb4320d7848364e9a7ef134a69cbfd55,Supervised translation-invariant sparse coding,"Supervised Translation-Invariant Sparse Coding ¹Jianchao Yang, ²Kai Yu, and ¹Thomas Huang ¹University of Illinois at Urbana Champaign ²NEC Laboratories America at Cupertino" 02a99a43670ab83e77de9d935eb8d3d164e1972c,Joint Segmentation and Pose Tracking of Human in Natural Videos,"Joint Segmentation and Pose Tracking of Human in Natural Videos∗ Taegyu Lim1,2 Seunghoon Hong2 Bohyung Han2 Joon Hee Han2 DMC R&D Center, Samsung Electronics, Korea Department of Computer Science and Engineering, POSTECH, Korea" 02e43d9ca736802d72824892c864e8cfde13718e,Transferring a semantic representation for person re-identification and search,"Transferring a Semantic Representation for Person Re-Identification and Search Shi, Z; Yang, Y; Hospedales, T; XIANG, T; IEEE Conference on Computer Vision and Pattern Recognition © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle/123456789/10075 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 02dd0af998c3473d85bdd1f77254ebd71e6158c6,PPP: Joint Pointwise and Pairwise Image Label Prediction,"PPP: Joint Pointwise and Pairwise Image Label Prediction Yilin Wang1 Suhang Wang1 Jiliang Tang2 Huan Liu1 Baoxin Li1 Department of Computer Science, Arizona State Univerity Yahoo Research" 026509ad687f9cdaba8f2dac0fe5720e0553a8bd,Integrated pedestrian classification and orientation estimation,"Integrated Pedestrian Classification nd Orientation Estimation Markus Enzweiler1 Dariu M. Gavrila2,3 Image & Pattern Analysis Group, Univ. of Heidelberg, Germany Environment Perception, Group Research, Daimler AG, Ulm, Germany Intelligent Autonomous Systems Group, Univ. of Amsterdam, The Netherlands" 02e9f1bb203a5ade98308eaff4f6a5c96a2c11e0,Self-Supervised Relative Depth Learning for Urban Scene Understanding,"Self-Supervised Relative Depth Learning for Urban Scene Understanding Huaizu Jiang1, Erik Learned-Miller1 Gustav Larsson2, Michael Maire3, Greg Shakhnarovich3 UMass Amherst University of Chicago TTI-Chicago" 026050f71175d235f3f91ca0e99e994c00f9b5a6,Supervised Discrete Hashing,"Supervised Discrete Hashing Fumin Shen1, Chunhua Shen2, Wei Liu3, Heng Tao Shen4 University of Electronic Science and Technology of China. 2 University of Adelaide; and Australian Centre for Robotic Vision. 3IBM Research. The University of Queensland. Recently, learning based hashing techniques have attracted broad research interests due to the resulting efficient storage and retrieval of images, videos, documents, etc. However, a major difficulty of learning to hash lies in han- dling the discrete constraints imposed on the needed hash codes. In general, the discrete constraints imposed on the binary codes that the target hash functions generate lead to mixed-integer optimization problems—which is generally NP hard. To simplify the optimization involved in a binary code learning procedure, most of the aforementioned methods choose to first solve a relaxed problem through directly discarding the discrete constraints, nd then threshold the continuous outputs to be binary. This greatly simpli- fies the optimization but, unfortunately, the approximated solution is typi- ally of low quality and often makes the final hash functions less effective, possibly due to the accumulated quantization errors. This is especially the ase when long-length codes are needed. Directly learning the binary codes without relaxations would be pre- ferred if (and only if) a tractable and scalable solver is available. The impor-" 023cc7f9f3544436553df9548a7d0575bb309c2e,Bag of Tricks for Efficient Text Classification,"Bag of Tricks for Efficient Text Classification Armand Joulin Edouard Grave Piotr Bojanowski Tomas Mikolov Facebook AI Research" 02f86370fd467f0d03948a94a346034d8a111ffd,Semantic Video Retrieval Using High Level Context,"SEMANTIC VIDEO RETRIEVAL USING HIGH LEVEL CONTEXT YUSUF AYTAR B.S. Ege University A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in the School of Electrical Engineering and Computer Science in the College of Engineering and Computer Science t the University of Central Florida Orlando, Florida Spring Term Major Professor: Mubarak Shah" 02da0cab1152eb1c43266687ebff8389c2d6b27b,Infrastructure Development for Integration of Lip Reading into the SUMMIT Speech,"fa c e Devee f egai f i Readig i he SUT Seech Recgize Chia a a S.B. aach e i e f Techgy 2002 S bied  he Deae f Eecica Egieeig ad C e Sciece i aia f (cid:12)e f he e iee f he degee f ae f Egieeig i Eecica Egieeig ad C e Sciece  he ASSACUSETTS STTUTE F TECGY ay 2003 (cid:13)aach e i e f Techgy . A igh eeved A h . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Deae f Eecica Egieeig ad C e Sciece ay 21 2003 Cei(cid:12)ed by . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Tihy . aze Reeach Sciei" 022d74ae2f8680e780b18e0cbb041d5c5a57c7a5,Video Salient Object Detection via Fully Convolutional Networks,"Video Salient Object Detection via Fully Convolutional Networks Wenguan Wang, Jianbing Shen, Senior Member, IEEE, and Ling Shao, Senior Member, IEEE" 027beed800f7d5e20194caf6d689345045e8d0d4,Smoothed Dilated Convolutions for Improved Dense Prediction,"Smoothed Dilated Convolutions for Improved Dense Prediction Zhengyang Wang Washington State University Pullman, Washington, USA Shuiwang Ji Washington State University Pullman, Washington, USA" 02a88a2f2765b17c9ea76fe13148b4b8a9050b95,DeepPose: Human Pose Estimation via Deep Neural Networks,"DeepPose: Human Pose Estimation via Deep Neural Networks Alexander Toshev Christian Szegedy Google 600 Amphitheatre Pkwy Mountain View, CA 94043 mainly by the first challenge, the need to search in the large space of all possible articulated poses. Part-based models lend themselves naturally to model articulations ([16, 8]) nd in the recent years a variety of models with efficient inference have been proposed ([6, 19]). The above efficiency, however, is achieved at the cost of limited expressiveness – the use of local detectors, which reason in many cases about a single part, and most impor- tantly by modeling only a small subset of all interactions etween body parts. These limitations, as exemplified in Fig. 1, have been recognized and methods reasoning about pose in a holistic manner have been proposed [15, 21] but with limited success in real-world problems. In this work we ascribe to this holistic view of human" 026e3363b7f76b51cc711886597a44d5f1fd1de2,Vision meets robotics: The KITTI dataset,"Vision meets Robotics: The KITTI Dataset Andreas Geiger, Philip Lenz, Christoph Stiller and Raquel Urtasun" 02086be014c4a276663e66ffde4d14f9c4cebe7e,BiggerPicture: data-driven image extrapolation using graph matching,"This is an Open Access document downloaded from ORCA, Cardiff University's institutional repository: http://orca.cf.ac.uk/67868/ This is the author’s version of a work that was submitted to / accepted for publication. Citation for final published version: Wang, Miao, Lai, Yukun, Liang, Yuan, Martin, Ralph Robert and Hu, Shi-Min 2014. Biggerpicture: data-driven image extrapolation using graph matching. ACM Transactions on Graphics 33 (6) , 173. 0.1145/2661229.2661278 file Publishers page: http://dx.doi.org/10.1145/2661229.2661278 Changes made as a result of publishing processes such as copy-editing, formatting and page numbers may not be reflected in this version. For the definitive version of this publication, please refer to the published source. You are advised to consult the publisher’s version if you wish to cite Please note: this paper. This version is being made available in accordance with publisher policies. See http://orca.cf.ac.uk/policies.html for usage policies. Copyright and moral rights for publications made available in ORCA are retained by the copyright holders." 02e97e65fd0ec9a6d98a255d0396eb796a5e444a,Online Multiple View Tracking: Targets Association Across Cameras,"Q.LE, D.CONTE, M.HIDANE: COLLABORATIVE TRACKING Online Multiple View Tracking: Targets Association Across Cameras Quoc Cuong LE1 Donatello CONTE1 Moncef HIDANE2 LIFAT University of Tours, Tours, France Computer Science Department INSA Centre Val de Loire, Blois, France" 02af5e40653b5a545b62aa6aebfaca6557f4173d,Sensor fusion for human safety in industrial workcells,"Sensor Fusion for Human Safety in Industrial Workcells* Paul Rybski1, Peter Anderson-Sprecher1, Daniel Huber1, Chris Niessl1, Reid Simmons1 Figure 1: An example of our approach. (a) The workcell as seen y one of the 3D sensors. The red region indicates the adaptive danger zone surrounding the moving robot arm. (b) As the person enters the workcell, the green region indicates the adaptive safety zone surrounding the person. (c) When the person gets too close to the robot, the safety zone and danger zones intersect (shown with a red circle), and the robot automatically halts. LIGHTEN THE CONTRAST ON THESE FIGURES TO MAKE THEM EASIER TO SEE" 02534fabd5ffbb98d1c09581eb410e29bec9da01,Fast Vehicle Detection in Aerial Imagery.,"Jennifer Carlet KeyW Corp. Beavercreek, OH" 027b940ef4de5aef8b2fd0bebc739445147baf1d,Secure remote matching with privacy: Scrambled support vector vaulted verification (S2V3),"Secure remote matching with privacy: Scrambled Support Vector Vaulted Verification (S2V 3) Michael J. Wilber and Terrance E. Boult Vision and Security Technology Lab, UCCS Colorado Springs, CO, 80918, USA" 02e133aacde6d0977bca01ffe971c79097097b7f,Convolutional Neural Fabrics, 023da8828f9c039c20ac9267a6b37813b74d4824,Free supervision from video games,"Free supervision from video games Philipp Kr¨ahenb¨uhl UT Austin" 029fa43a49a2f5df4bee8aa6a9574f8da5098f98,"Learning event representation: As sparse as possible, but not sparser","Learning event representation: As sparse as possible, but not sparser Tuan Do and James Pustejovsky Department of Computer Science Brandeis University Waltham, MA 02453 USA" 02e4025fd63f168810724156fb6b20b0b14dccdc,Local inter-session variability modelling for object classification,"This is the author’s version of a work that was submitted/accepted for pub- lication in the following source: Anantharajah, Kaneswaran, Ge, ZongYuan, McCool, Christopher, Den- man, Simon, Fookes, Clinton B., Corke, Peter, Tjondronegoro, Dian W., & Sridharan, Sridha (2014) Local inter-session variability modelling for object classification. In 014), 24-26 March 2014, Steamboat Springs, CO. This file was downloaded from: https://eprints.qut.edu.au/67786/ (cid:13) Copyright 2014 [please consult the author] Notice: Changes introduced as a result of publishing processes such as opy-editing and formatting may not be reflected in this document. For a definitive version of this work, please refer to the published source:" ba20e58fcca7537fe3cb46a7dea03b5915373ba7,Face Recognition by Extending Elastic Bunch Graph Matching with Particle Swarm Optimization,"Face Recognition by Extending Elastic Bunch Graph Matching with Particle Swarm Optimization Department of Mechanical Engineering, Melbourne School of Engineering, The University of Melbourne, Australia; Bioinformatics Division, The Walter and Eliza Hall Institute of Medical Research, Australia Rajinda Senaratne1, Saman Halgamuge1, Arthur Hsu2 Email: rajinda" ba051292ca6e8c689542831479e436be7035c147,Superpixel Sampling Networks,"Superpixel Sampling Networks Varun Jampani1, Deqing Sun1, Ming-Yu Liu1, Ming-Hsuan Yang1,2, Jan Kautz1 NVIDIA UC Merced" bafb8812817db7445fe0e1362410a372578ec1fc,Image-Quality-Based Adaptive Face Recognition,"Image-Quality-Based Adaptive Face Recognition Harin Sellahewa and Sabah A. Jassim" babc76d0550a647dc605dca9a69bda1af8e0c872,AN EFFECTIVE COLOR FACE RECOGNITION BASED ON BEST COLOR FEATURE SELECTION ALGORITHM USING WEIGHTED FEATURES FUSION SYSTEM,"ISSN 22773061 AN EFFECTIVE COLOR FACE RECOGNITION BASED ON BEST COLOR FEATURE SELECTION ALGORITHM USING WEIGHTED FEATURES FUSION SYSTEM J.Umadevi, B. Sankara gomathi, B. Sasi Kumar, Department of Computer Science, The Rajaas Engineering College Dean (Academic), National Engineering College Professor, Department of Computer Science, The Rajaas Engineering College" baeb207ea6f4b52eea129b9d8597d4b7a0891ad6,"Sparse , Smart Contours to Represent and Edit Images","Sparse, Smart Contours to Represent and Edit Images Tali Dekel 1 Chuang Gan 2 Dilip Krishnan 1 Ce Liu 1 William T. Freeman 1,3 Google Research 2 MIT-Watson AI Lab 3 MIT-CSAIL Reconstruction from Sparse Contour Represenation Editing in the Contour Domain .4% px .5% px (a) Source (b) Contours (c) Source Reconstuction (d) Edited/blended Contours (e) Recon. from Edit Reference Figure 1. Our method produces high quality reconstructions of images from information along a small number of contours: a source (512×512) image in (a) is reconstructed in (c) from gradient information stored at the set of colored contours in (b)2, which are less than 5% of the pixels. The model synthesizes hair texture, facial lines and shading even in regions where no input information is provided. Our model allows for semantically intuitive editing in the contour domain. Top-right: a caricature-like result (e) is created by moving and" ba1cf2d0493f25da61bd816f92712291999c0ef6,Simple online and realtime tracking with a deep association metric,"SIMPLE ONLINE AND REALTIME TRACKING WITH A DEEP ASSOCIATION METRIC Nicolai Wojke†, Alex Bewley(cid:5), Dietrich Paulus† University of Koblenz-Landau†, Queensland University of Technology(cid:5)" ba8a99d35aee2c4e5e8a40abfdd37813bfdd0906,Uporaba emotivno pogojenega računalništva v priporočilnih sistemih,"ELEKTROTEHNI ˇSKI VESTNIK 78(1-2): 12–17, 2011 EXISTING SEPARATE ENGLISH EDITION Uporaba emotivno pogojenega raˇcunalniˇstva v priporoˇcilnih sistemih Marko Tkalˇciˇc, Andrej Koˇsir, Jurij Tasiˇc Univerza v Ljubljani, Fakulteta za elektrotehniko, Trˇzaˇska 25, 1000 Ljubljana, Slovenija Univerza v Ljubljani, Fakulteta za raˇcunalniˇstvo in informatiko, Trˇzaˇska 25, 1000 Ljubljana, Slovenija E-poˇsta: Povzetek. V ˇclanku predstavljamo rezultate treh raziskav, vezanih na izboljˇsanje delovanja multimedijskih priporoˇcilnih sistemov s pomoˇcjo metod emotivno pogojenega raˇcunalniˇstva (ang. affective computing). Vsebinski priporoˇcilni sistem smo izboljˇsali s pomoˇcjo metapodatkov, ki opisujejo emotivne odzive uporabnikov. Pri skupinskem priporoˇcilnem sistemu smo dosegli znaˇcilno izboljˇsanje v obmoˇcju hladnega zagona z uvedbo nove mere podobnosti, ki temelji na osebnostnem modelu velikih pet (ang. five factor model). Razvili smo tudi sistem za neinvazivno oznaˇcevanje vsebin z emotivnimi parametri, ki pa ˇse ni zrel za uporabo v priporoˇcilnih sistemih. Kljuˇcne besede: priporoˇcilni sistemi, emotivno pogojeno raˇcunalniˇstvo, strojno uˇcenje, uporabniˇski profil, emocije Uporaba emotivnega raˇcunalniˇstva v priporoˇcilnih sistemih In this paper we present the results of three investigations of" ba87bcf4bf799001641b7afd7d1025600f57c4a1,A HYBRID ARCHITECTURE FOR TRACKING PEOPLE IN REAL-TIME USING A VIDEO SURVEILLANCE CAMERA: APPLICATION FOR BEHAVIOURAL MARKETING,"Signal & Image Processing : An International Journal (SIPIJ) Vol.6, No.6, December 2015 A HYBRID ARCHITECTURE FOR TRACKING PEOPLE IN REAL-TIME USING A VIDEO SURVEILLANCE CAMERA: APPLICATION FOR BEHAVIOURAL MARKETING Kheireddine AZIZ1, Djamal MERAD2, Jean-Luc DAMOISEAUX3 and Pierre DRAP2 SeaTech Toulon, Toulon University, La Gardes, France LSIS Lab, Aix-Marseille University, Marseille, France IUT R&T, Aix-Marseille University, Marseille, France" badcd992266c6813063c153c41b87babc0ba36a3,Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks,"Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks Shivang Agarwal(∗ ,1), Jean Ogier du Terrail(∗ ,1,2), Fr´ed´eric Jurie(1) (∗) equal contribution (1)Normandie Univ, UNICAEN, ENSICAEN, CNRS (2)Safran Electronics and Defense September 11, 2018" ba25c0c330da1460cc817a98e7c55a100c255039,A Two Level Face Recognition Algorithm For Efficient Attendance Marking,"IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-ISSN: 2278-2834,p- ISSN: 2278-8735.Volume 12, Issue 3, Ver. II (May - June 2017), PP 80-85 www.iosrjournals.org A Two Level Face Recognition Algorithm For Efficient Attendance Marking Bhaskar B1,Shwetha B2, Rashmi K3, Dr.K.V.Mahendra Prashanth4 Associate Professor, Postgraduate Student, Postgraduate Student, Professor Department of Electronics and communication S.J.B Institute of Technology, Bengaluru-60" ba51ce1ec7b18fa808985b919f4a201fe5e4bafb,Semantic parsing for priming object detection in indoors RGB-D scenes,"Semantic Parsing for Priming Object Detection in Indoors RGB-D Scenes∗ C´esar Cadena †and Jana Koˇseck´a ‡" ba0d84d97eeec7774534b91da78b10c5d924fdc8,Classification with Repulsion Tensors: A Case Study on Face Recognition,"Classification with Repulsion Tensors: A Case Study on Face Recognition Hawren Fang∗ March 16, 2016" bac5906adc227e390f2f70705e990a3e1ec369df,Active Control of Camera Parameters for Object Detection Algorithms,"Active Control of Camera Parameters for Object Detection Algorithms Yulong Wu, John Tsotsos Department of Electrical Engineering and Computer Science York Univeristy Toronto, ON M3J 1P3 Email: {yulong," bab69d0954213851bc4aae50ece0ce8ac52bdedf,' s personal copy Optimal feature selection for support vector machines,Author's personal copy bab47c7bf80c9310f947cbdaf71b3c983c497b68,Systematic Parameter Optimization and Application of Automated Tracking in Pedestrian Dominant Situations Date of submission : 2014-0801,"Systematic Parameter Optimization and Application of Automated Tracking in Pedestrian Dominant Situations Date of submission: 2014-08-01 Dariush Ettehadieh* M.Sc. Student, Polytechnique Montréal, 500, Chemin de Polytechnique, Montreal phone : 1-514-266-5544 Bilal Farooq Assistant Professor, Polytechnique Montréal 500, Chemin de Polytechnique, Montreal phone : 1-514-340-4711 ext. 4802 Nicolas Saunier Associate Professor, Polytechnique Montréal 500, Chemin de Polytechnique, Montreal phone : 1-514-340-4711 ext. 4962 5029 Words + 4 Figures + 3 Tables = 6779 Submitted for presentation to the 94th Annual Meeting of the Transportation Research Board and publication in" ba180547d0b1cf7de24248051ff87bf34f75783d,Video Surveillance and Sensor Networks,"Multimedia Surveillance Systems Dipartimento di Ingegneria dell’ Informazione University of Modena and Reggio Emilia Rita Cucchiara Italy" bade9b38c45afd4f988e246974427685f3ff599f,Pairwise Rotation Hashing for High-dimensional Features,"Pairwise Rotation Hashing for High-dimensional Features Kohta Ishikawa, Ikuro Sato, and Mitsuru Ambai Denso IT Laboratory, Inc." bad7254ae08f8bf1305e70c7de28374f67f151fd,Ré-identification de personnes à partir des séquences vidéo. (Person re-identification from video sequence),"Ré-identification de personnes à partir des séquences vidéo Mohamed Ibn Khedher To cite this version: Mohamed Ibn Khedher. Ré-identification de personnes à partir des séquences vidéo. Réseaux et télécommunications [cs.NI]. Institut National des Télécommunications, 2014. Français. . HAL Id: tel-01149691 https://tel.archives-ouvertes.fr/tel-01149691 Submitted on 7 May 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" bac748bf117cb5b06037413de92378b76ff358d0,Entropy-based sim(3) calibration of 2D lidars to egomotion sensors,"Entropy-Based Sim(3) Calibration of 2D Lidars to Egomotion Sensors Jacob Lambert1, Lee Clement1, Matthew Giamou2, and Jonathan Kelly1" ba816806adad2030e1939450226c8647105e101c,MindLAB at the THUMOS Challenge,"MindLAB at the THUMOS Challenge Fabi´an P´aez Jorge A. Vanegas Fabio A. Gonz´alez MindLAB Research Group MindLAB Research Group MindLAB Research Group Bogot´a, Colombia Bogot´a, Colombia Bogot´a, Colombia" ba09dd1844427cff803082dda7366bd966456932,Automated analysis of nonverbal behavior in depression View project Automated analysis of facial expressions View project,"See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/227031714 Facial Expression Recognition Chapter · January 2011 DOI: 10.1007/978-0-85729-932-1_19 CITATIONS authors: READS ,261 Yingli Tian City College of New York Takeo Kanade Carnegie Mellon University 89 PUBLICATIONS 4,076 CITATIONS 511 PUBLICATIONS 51,663 CITATIONS SEE PROFILE SEE PROFILE Jeffrey F Cohn University of Pittsburgh 30 PUBLICATIONS 18,287 CITATIONS SEE PROFILE" ba8e0bda11af08b6037666b67cf54ae1f780822d,1 Spatial Pyramid Matching,"Author manuscript, published in ""Object Categorization: Computer and Human Vision Perspectives Cambridge University Press (Ed.) (2009) 401--415""" baf0af0ac2f2fbbf0c04141e12886ff850d77413,Feature-based 3d Slam,"KERNEL{BASED CLASSIFIERS WITH APPLICATIONS TO FACE DETECTION TH(cid:18)ESE No 3141 (2004) PR(cid:19)ESENT(cid:19)EE (cid:18)A LA FACULT(cid:19)E SCIENCES ET TECHNIQUES DE L’ING(cid:19)ENIEUR INSTITUT DE TRAITEMENT DES SIGNAUX SECTION DE G(cid:19)ENIE (cid:19)ELECTRIQUE ET (cid:19)ELECTRONIQUE (cid:19)ECOLE POLYTECHNIQUE F(cid:19)ED(cid:19)ERALE DE LAUSANNE POUR L’OBTENTION DU GRADE DE DOCTEUR (cid:18)ES SCIENCES Vlad POPOVICI DEA de sciences des syst(cid:18)emes et des calculateurs, Universit(cid:19)e Technique de Cluj-Napoca, Roumanie et de nationalit(cid:19)e roumaine ccept(cid:19)ee sur proposition du jury: Prof. J.-P. Thiran, directeur de th(cid:18)ese Dr. S. Bengio, rapporteur Prof. J. Kittler, rapporteur Prof. M. Kunt, rapporteur Lausanne, EPFL D(cid:19)ecembre 2004" ba99c37a9220e08e1186f21cab11956d3f4fccc2,A Fast Factorization-Based Approach to Robust PCA,"A Fast Factorization-based Approach to Robust PCA Department of Computer Science, Southern Illinois University,Carbondale, IL 62901 USA Chong Peng, Zhao Kang, and Qiang Cheng Email:" ba85ccde9dd53a9c78a9dbb1fe1e34d7800ad1c1,ENHANCEMENT OF FAST PEDESTRIAN DETECTION USING HOG FEATURES,"International Journal of Industrial Electronics and Electrical Engineering, ISSN: 2347-6982 Volume-3, Issue-4, April-2015 ENHANCEMENT OF FAST PEDESTRIAN DETECTION USING HOG AHMAD BAGHDADI, 2SUHAIMI ABD LATIF ,2Electrical and Computer Engineering Department, IIUM E-mail: FEATURES reasons: first, HOG" 656f05741c402ba43bb1b9a58bcc5f7ce2403d9a,Supervised Learning Approaches for Automatic Structuring of Videos. (Méthodes d'apprentissage supervisé pour la structuration automatique de vidéos),"THÈSEPour obtenir le grade deDOCTEUR DE L’UNIVERSITÉ GRENOBLE ALPESSpécialité : Mathématiques et InformatiqueArrêté ministériel : 7 août 2006Présentée parDanila POTAPOVThèse dirigée par Cordelia SCHMID et codirigée par Zaid HARCHAOUIpréparée au sein de Inria Grenoble Rhône-Alpesdans l'École Doctorale Mathématiques, Sciences et technologies de l'information, InformatiqueSupervised Learning Approaches for Automatic Structuring of VideosThèse soutenue publiquement le « 22 Juillet 2015 »,devant le jury composé de : Prof. Cordelia SCHMID Inria Grenoble Rhône-Alpes, France, Directeur de thèseDr. Zaid HARCHAOUIInria Grenoble Rhône-Alpes, France, Co-encadrant de thèse Prof. Patrick PEREZTechnicolor Rennes, France, RapporteurProf. Ivan LAPTEVInria Paris Rocquencourt, France, Rapporteur, PrésidentDr. Florent PERRONNINFacebook AI Research, Paris, France, ExaminateurDr. Matthijs DOUZEInria Grenoble Rhône-Alpes, France, Examinateur" 65ec52a3e0a0f6a46fd140ff83bb82d7d02a2d45,Learning Hierarchical Features from Generative Models,"Learning Hierarchical Features from Generative Models Shengjia Zhao 1 Jiaming Song 1 Stefano Ermon 1" 65639b79576f22b705a601f062bb6905f0a396af,A Preliminary Investigation into the Impact of Training for Example-Based Facial Blendshape Creation,"EUROGRAPHICS 2018/ O. Diamanti and A. Vaxman Short Paper A Preliminary Investigation into the Impact of Training for Example-Based Facial Blendshape Creation Emma Carrigan1, Ludovic Hoyet2, Rachel McDonnell1 and Quentin Avril3 Graphics Vision and Visualisation Group, Trinity College Dublin, Ireland Inria Rennes, France 3 Technicolor" 65a858ca95dcfa032e812a7f1fc7ee5bdac88f5b,Using Pre-Trained Models for Fine-Grained Image Classification in Fashion Field,"Using Pre-Trained Models for Fine-Grained Image Classification in Fashion Field Anna Iliukovich-Strakovskaia Moscow Institute of Physics and Technology Moscow Institute of Physics and Alexey Dral Technology “А” Kerchenskaya st., Moscow, 17303, Russian Federation “А” Kerchenskaya st., Moscow, 17303, Russian Federation +7 495 408 45 54 +7 495 408 45 54 Emeli Dral Moscow Institute of Physics and Technology & Yandex Data Factory “А” Kerchenskaya st., Moscow, 17303, Russian Federation +7 495 408 45 54" 656e7c7739e3f334d4f275c71499485501aabc44,A Two-Step Methodology for Human Pose Estimation Increasing the Accuracy and Reducing the Amount of Learning Samples Dramatically,"A two-step methodology for human pose estimation increasing the accuracy and reducing the amount of learning samples dramatically Samir Azrour, Sébastien Piérard, Pierre Geurts, and Marc Van Droogenbroeck INTELSIG Laboratory, Department of Electrical Engineering and Computer Science, University of Liège, Belgium" 65a8c76a25c1eb95436bab22e99f78f6b390c87a,Local Multi-Grouped Binary Descriptor With Ring-Based Pooling Configuration and Optimization,"Local Multi-Grouped Binary Descriptor with Ring-based Pooling Configuration and Optimization Yongqiang Gao, Weilin Huang, and Yu Qiao them are hand-crafted descriptors, which significantly limit their generality to various tasks or different databases by using pre-defined filters and unfeasible pooling configurations. Recently, learning-based descriptors have been proposed by optimising both local filters and pooling regions using training data, with promising improvements achieved [16]–[18]. The discriminative capability and computational complexity are two crucial but conflicted issues, which need to be balanced arefully in the learning processing." 6581c5b17db7006f4cc3575d04bfc6546854a785,Contextual Person Identification in Multimedia Data,"Contextual Person Identification in Multimedia Data zur Erlangung des akademischen Grades eines Doktors der Ingenieurwissenschaften der Fakultät für Informatik des Karlsruher Instituts für Technologie (KIT) genehmigte Dissertation Dipl.-Inform. Martin Bäuml us Erlangen Tag der mündlichen Prüfung: 8. November 2014 Hauptreferent: Korreferent: Prof. Dr. Rainer Stiefelhagen Karlsruher Institut für Technologie Prof. Dr. Gerhard Rigoll Technische Universität München KIT – Universität des Landes Baden-Württemberg und nationales Forschungszentrum in der Helmholtz-Gemeinschaft www.kit.edu" 651125ca22947e95e5be6206c3056988b850266a,Swifter: improved online video scrubbing,"Swifter: Improved Online Video Scrubbing Justin Matejka, Tovi Grossman, and George Fitzmaurice Autodesk Research, Toronto, Ontario, Canada Figure 1. Scrubbing behavior of a traditional streaming video player, the Swift interface [16], and our new Swifter interface, which shows multiple frames around the active timeline location and allows for direct selection of each frame. Traditional Swift Swifter" 656aeb92e4f0e280576cbac57d4abbfe6f9439ea,USE OF IMAGE ENHANCEMENT TECHNIQUES FOR IMPROVING REAL TIME FACE RECOGNITION EFFICIENCY ON WEARABLE GADGETS,"Journal of Engineering Science and Technology Vol. 12, No. 1 (2017) 155 - 167 © School of Engineering, Taylor’s University USE OF IMAGE ENHANCEMENT TECHNIQUES FOR IMPROVING REAL TIME FACE RECOGNITION EFFICIENCY ON WEARABLE GADGETS MUHAMMAD EHSAN RANA1,*, AHMAD AFZAL ZADEH2, AHMAD MOHAMMAD MAHMOOD ALQURNEH3 , 3Asia Pacific University of Technology & Innovation, Kuala Lumpur 57000, Malaysia Staffordshire University, Beaconside Stafford ST18 0AB, United Kingdom *Corresponding Author:" 65eff143b099e53dcf39692c2fb542b0ee1fdfb6,Real-time Scale-invariant Object Recognition from Light Field Imaging, 650f4ccbe7d4aa49ae80e246df394ca6c60894ec,Pedestrian detection in urban environments based on vision and depth data Personenerkennung in städtischen,"DEPARTMENT OF INFORMATICS TECHNISCHE UNIVERSITÄT MÜNCHEN Bachelor’s Thesis in Informatics Pedestrian detection in urban environments ased on vision and depth data Andreas Kreutz" 6527cf0b9dbddbd0c6429a35a3cbded3ca336583,MCMC Supervision for People Re-identification in Nonoverlapping Cameras,"MEDEN, LERASLE, SAYD: MCMC TRACKING-BY-REIDENTICATION MCMC Supervision for People Reidentification in Nonoverlapping Cameras Boris Meden1 Frédéric Lerasle2 lerasle.laas.fr Patrick Sayd1 CEA, LIST, Laboratoire Vision et Ingénierie des Contenus, BP 94, F-91191 Gif-sur-Yvette, France CNRS ; LAAS ; Université de Toulouse ; UPS, LAAS ; F-31077 Toulouse Cedex 4, France" 656a59954de3c9fcf82ffcef926af6ade2f3fdb5,Convolutional Network Representation for Visual Recognition,"Convolutional Network Representation for Visual Recognition ALI SHARIF RAZAVIAN Doctoral Thesis Stockholm, Sweden, 2017" 65817963194702f059bae07eadbf6486f18f4a0a,WhittleSearch: Interactive Image Search with Relative Attribute Feedback,"http://dx.doi.org/10.1007/s11263-015-0814-0 WhittleSearch: Interactive Image Search with Relative Attribute Feedback Adriana Kovashka · Devi Parikh · Kristen Grauman Received: date / Accepted: date" 659fc2a483a97dafb8fb110d08369652bbb759f9,Improving the Fisher Kernel for Large-Scale Image Classification,"Improving the Fisher Kernel for Large-Scale Image Classification Florent Perronnin, Jorge S´anchez, and Thomas Mensink Xerox Research Centre Europe (XRCE)" 65d588e2ff7b4f2903efbeded978885f7da5d0e0,UMPM benchmark: A multi-person dataset with synchronized video and motion capture data for evaluation of articulated human motion and interaction,"UMPM benchmark: a multi-person dataset with synchronized video and motion apture data for evaluation of articulated human motion and interaction N.P. van der Aa1,2, X. Luo1, G.J. Giezeman1, R.T. Tan1, R.C. Veltkamp1 {x.luo, g.j.giezeman, r.t.tan, Utrecht University Noldus Information Technology" 653942873bc7ea6f1056739dc5015ec3631d9bbe,Face Detection Techniques-A Review,"International Journal of Current Engineering and Technology ISSN 2277 - 4106 © 2013 INPRESSCO. All Rights Reserved. Available at http://inpressco.com/category/ijcet Research Article Face Detection Techniques- A Review Chandrashekhar S.PatilȦ and Gopal N.DhootȦ* ȦDepartment of E&TC, University of North Maharashtra, State Maharashtra, Country India Accepted 20 November 2013, Available online 01 December 2013, Vol.3, No.5 (December 2013)" 65237b5e96c7492a0e5d01ddea5b1d381da408cd,A human-machine collaborative approach to tracking human movement in multi-camera video,"A Human-Machine Collaborative Approach to Tracking Human Movement in Multi-Camera Video Philip DeCamp MIT Media Lab 0 Ames Street, E15-441 Cambridge, Massachusetts 02139 Deb Roy MIT Media Lab 0 Ames Street, E15-488 Cambridge, Massachusetts 02139" 65edab091e437d3b9d093dcb8be7c5dc4ce0fe0f,DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation,"DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation Holger R. Roth, Le Lu, Amal Farag, Hoo-Chang Shin, Jiamin Liu, Evrim B. Turkbey, and Ronald M. Summers Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD 0892-1182, USA" 659fc18b1ec79a7437e6e7b1dce145d423e82199,Real time person detection and tracking by mobile robots using RGB-D images,"Real Time Person Detection and Tracking by Mobile Robots using RGB-D Images Duc My Vo, Lixing Jiang and Andreas Zell" 657ae9ecb59cb2a27e57784577a9efb60de81126,The Task Matters: Comparing Image Captioning and Task-Based Dialogical Image Description,"The Task Matters: Comparing Image Captioning and Task-Based Dialogical Image Description Nikolai Ilinykh, Sina Zarrieß, David Schlangen Dialogue Systems Group University of Bielefeld Germany" 658c802890c7133e2ade778b5d88b68bcd0dca9c,Learning to Segment via Cut-and-Paste,"Learning to Segment via Cut-and-Paste Tal Remez, Jonathan Huang, Matthew Brown Google" 65126e0b1161fc8212643b8ff39c1d71d262fbc1,Occlusion Coherence: Localizing Occluded Faces with a Hierarchical Deformable Part Model,"Occlusion Coherence: Localizing Occluded Faces with a Hierarchical Deformable Part Model Golnaz Ghiasi Charless C. Fowlkes Dept. of Computer Science, University of California, Irvine" 6506e45c15cf24d9cbf3d694994195ef56063a80,Dynamic and Robust Object Tracking for Activity Recognition. (Suivi dynamique et robuste d'objets pour la reconnaissance d'activités),"Dynamic and Robust Object Tracking for Activity Recognition Duc Phu Chau To cite this version: Duc Phu Chau. Dynamic and Robust Object Tracking for Activity Recognition. Computer Vision nd Pattern Recognition [cs.CV]. Institut National de Recherche en Informatique et en Automatique (INRIA), 2012. English. HAL Id: tel-00695567 https://tel.archives-ouvertes.fr/tel-00695567 Submitted on 22 Nov 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 6574eaab393aa8d674cd785fab16cae06a53151a,A study on polymorphing superscalar processor dynamically to improve power efficiency,"A Study on Polymorphing Superscalar Processor Dynamically to Improve Power Efficiency Sudarshan Srinivasan, Rance Rodrigues, Arunachalam Annamalai, Israel Koren and Sandip Kundu Department of Electrical and Computer Engineering University of Massachusetts at Amherst, MA, USA Email: {ssrinivasan, rodrigues, annamalai, koren," 6520367a3ff4f863a95e0d34eda54cd4903f557c,European Robotics Network Network of Excellence Information Society Technologies Priority DR 2 . 4 IROS ’ 06 Workshop on Benchmarks,"FP6-507728 EURON European Robotics Network Network of Excellence Information Society Technologies Priority DR 2.4 IROS’06 Workshop on Benchmarks Due date of deliverable: 31 December 2006 Actual submission date: 4 June 2007 Start date of the project: 1 May 2004 Duration: 48 months Organisation name of lead contractor for this deliverable: UJI Revision: Revised version, June 2007 Dissemination level: PU" 652d3f33fd0a99808dd646aed228b45eacdaf34f,A Framework for Binding and Retrieving Class-Specific Information to and from Image Patterns Using Correlation Filters,"A Framework for Binding and Retrieving Class-Specific Information to and from Image Patterns using Correlation Filters Vishnu Naresh Boddeti, Student Member, IEEE, and B.V.K Vijaya Kumar, Fellow, IEEE" 65341edca2f74ffad7d0aa56f20558f5305b307e,Co-design of architectures and algorithms for mobile robot localization and model-based detection of obstacles. (Co-conception d'architectures et d'algorithmes pour la localisation de robots mobiles et la détection d'obstacles basée sur des modèles),"Co-design of architectures and algorithms for mobile robot localization and model-based detection of obstacles Daniel Törtei To cite this version: Daniel Törtei. Co-design of architectures and algorithms for mobile robot localization and model-based detection of obstacles. Embedded Systems. Université Paul Sabatier - Toulouse III, 2016. English. . HAL Id: tel-01477662 https://tel.archives-ouvertes.fr/tel-01477662v2 Submitted on 16 Feb 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 659fe7f32475bec73ed763f50cea929352b1309a,Facial image prediction using exemplar-based algorithm and non-negative matrix factorization,"Facial Image Prediction Using Exemplar-based Algorithm and Non-negative Matrix Factorization Department of Electrical Engineering, National Yunlin University of Science and Technology, Douliou, Taiwan Hsuan T. Chang* and Hsiao W. Peng† * E-mail: Tel: +886-5-5342601#4263 E-mail: Tel: +886-5-5342601#4299 Therefore, we used the non-family people images sometime. Currently, many human face databases in the internet are open for public. For example, FG-NET aging database [11]. Although, GF-NET database provides numerous face images, it does not offer the facial image sequence of different ages of the persons in the same family THE PROPOSED METHOD" 656a5d4d84c450792402b3c69eecbdbca4cad4cb,2.1. Imagenet and Related Datasets,"Figure 4: Percent of clean images at different tree depth levels in ImageNet. A total of 80 synsets are randomly sampled at every tree depth of the mammal and vehicle subtrees. An independent group of subjects verified the correctness of each of the images. An average of 99.7% precision is achieved for each synset. ImageNet TinyImage LabelMe LHill LabelDisam Clean DenseHie FullRes PublicAvail Segmented Table 1: Comparison of some of the properties of ImageNet ver- sus other existing datasets. ImageNet offers disambiguated la- els (LabelDisam), clean annotations (Clean), a dense hierarchy (DenseHie), full resolution images (FullRes) and is publicly avail-" a67e7ca0c7e1e3020169b5c59dc492e9f62f0022,FACE RECOGNITION PERFORMANCE UNDER ADVERSARIAL CONDITIONS, a6ebe013b639f0f79def4c219f585b8a012be04f,Facial Expression Recognition Based on Hybrid Approach,"Facial Expression Recognition Based on Hybrid Approach Md. Abdul Mannan, Antony Lam, Yoshinori Kobayashi, and Yoshinori Kuno Graduate School of Science and Engineering, Saitama University, 55 Shimo-Okubo, Sakura-ku, Saitama-shi, Saitama 338-8570, Japan E-mail" a6eb6ad9142130406fb4ffd4d60e8348c2442c29,"Video Description: A Survey of Methods, Datasets and Evaluation Metrics","Video Description: A Survey of Methods, Datasets and Evaluation Metrics Nayyer Aafaq, Syed Zulqarnain Gilani, Wei Liu, and Ajmal Mian" a6404e91af8d1644aa7eea307ffceefa715dd7ea,Human Motion Capture Using a Drone,"Human Motion Capture Using a Drone Xiaowei Zhou, Sikang Liu, Georgios Pavlakos, Vijay Kumar, Kostas Daniilidis" a6eb8cb1c35d0f53f8d2c9a404e374c01275544b,NovaSearch on Medical ImageCLEF 2013,"NovaSearch on medical ImageCLEF 2013 Andr´e Mour˜ao, Fl´avio Martins and Jo˜ao Magalh˜aes Universidade Nova de Lisboa, Faculdade de Ciˆencias e Tecnologia, Caparica, Portugal," a6f477f3c1cb2ab230fe8d89c31ae6af0b9c2346,Relevance Subject Machine: A Novel Person Re-identification Framework,"Relevance Subject Machine: A Novel Person Re-identification Framework Igor Fedorov, Student Member, IEEE, Ritwik Giri, Student Member, IEEE, Bhaskar D. Rao, Fellow, IEEE, Truong Q. Nguyen, Fellow, IEEE" a62ca056821a3179b116662b28338433ba5b5e7d,How far can we go without convolution: Improving fully-connected networks,"Under review as a conference paper at ICLR 2016 HOW FAR CAN WE GO WITHOUT CONVOLUTION: IM- PROVING FULLY-CONNECTED NETWORKS Zhouhan Lin & Roland Memisevic Universit´e de Montr´eal Canada {zhouhan.lin, Kishore Konda Goethe University Frankfurt Germany" a694180a683f7f4361042c61648aa97d222602db,Face recognition using scattering wavelet under Illicit Drug Abuse variations,"Face Recognition using Scattering Wavelet under Illicit Drug Abuse Variations Prateekshit Pandey, Richa Singh, Mayank Vatsa fprateekshit12078, rsingh, IIIT-Delhi India" a65e953df1dbc007862f8eaa8c12ceb225d15837,Robust Head-shoulder Detection using Deformable Part-based Models,"Robust Head-shoulder Detection using Deformable Part-based Models Enes Dayangac, Christian Wiede, Julia Richter and Gangolf Hirtz Faculty of Electrical Engineering and Information Technology, Technische Universit¨at Chemnitz, Chemnitz, Germany Keywords: Person Detection, Head-shoulder Detection, Ambient Assisted Living, Latent SVM, DPM, ACF-Detector." a618cc9c513762d4eb5db2f7f7b686e7e2b758ca,Learning Semi-Riemannian Metrics for Semisupervised Feature Extraction,"Learning Semi-Riemannian Metrics for Semisupervised Feature Extraction Wei Zhang, Zhouchen Lin, Senior Member, IEEE, and Xiaoou Tang, Fellow, IEEE" a6e7513371a49cd7b8b30bb444e8fc448c5326cb,Simple online and realtime tracking,"SIMPLE ONLINE AND REALTIME TRACKING Alex Bewley†, Zongyuan Ge†, Lionel Ott(cid:5), Fabio Ramos(cid:5), Ben Upcroft† Queensland University of Technology†, University of Sydney(cid:5)" a6161e53d77d7cbd6e69d1b84e6d03d7041cb93e,Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime,"Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime Dengxin Dai1 and Luc Van Gool1,2" a63638b26d36bab8db10bd95fb287c727bab33ec,Joint Sparse and Low-Rank Representation for Emotion Recognition,"MAY 2014 Joint Sparse and Low-Rank Representation for Emotion Recognition Xiang Xiang, Fabian Prada, Hao Jiang" a60146c458adfe9207f015d7a77cb7dfb54f744f,Understanding Dynamic Social Grouping Behaviors of Pedestrians,"Understanding Dynamic Social Grouping Behaviors of Pedestrians Linan Feng, Student Member, IEEE, and Bir Bhanu, Fellow, IEEE" a649bc66524e5e61e4d34cc00159099b6b58db2f,Chapter 3 Large-Scale Image Geolocalization,"Chapter 3 Large-Scale Image Geolocalization James Hays and Alexei A. Efros" a67d54cf585c9491ab8a3e2d58d9c4b223359602,Spatial information and end-to-end learning for visual recognition. (Informations spatiales et apprentissage bout-en-bout pour la reconnaissance visuelle),"Spatial information and end-to-end learning for visual recognition Mingyuan Jiu To cite this version: Mingyuan Jiu. Spatial information and end-to-end learning for visual recognition. Computer Science [cs]. INSA de Lyon, 2014. English. . HAL Id: tel-01127462 https://tel.archives-ouvertes.fr/tel-01127462 Submitted on 7 Mar 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" a6ce2f0795839d9c2543d64a08e043695887e0eb,Driver Gaze Region Estimation Without Using Eye Movement,"Driver Gaze Region Estimation Without Using Eye Movement Lex Fridman, Philipp Langhans, Joonbum Lee, and Bryan Reimer Massachusetts Institute of Technology (MIT)" a6a7fa90d44a1afc4217e627cde83704668ec53f,Automatic Face Recognition using Radial Basis Function Networks,"Automatic Face Recognition using Radial Basis Function Networks Andrew Jonathan Howell CSRP 488 September, 1997 ISSN 1350–3162 Cognitive Science Research Papers" a6990136d9db12d50245f574941aa992f01116c4,Moving visual focus in salient object segmentation,"Moving Visual Focus in Salient Object Segmentation Manuscript ID: IPR-2014-0987 Manuscript Type: Research Paper Date Submitted by the Author: 13-Dec-2014 Complete List of Authors: Chen, Zhihua; East China University of Science and Technology, Department of Computer Science and Engineering Xiao, Xiaolong; East China University of Science and Technology, Department of Computer Science and Engineering Liu, Yi; East China University of Science and Technology, Department of Computer Science and Engineering Ying, Fangli; East China University of Science and Technology, Department of Computer Science and Engineering Zhang, Jing; East China University of Science and Technology, Department of Computer Science and Engineering Yuan, Yu-Bo; East China University of Science and Technology, Department of Computer Science and Engineering Keyword: IMAGE PROCESSING, IMAGE RECOGNITION, IMAGE RETRIEVAL IET Review Copy Only" a66373beaad40fb5a8e2e1b42c5a2213b166a55c,Childhood abuse is related to working memory impairment for positive emotion in female university students.,"Childhood abuse is related to working memory impairment for positive emotion in female university students Cromheeke S, Herpoel LA, Mueller SC. 014; 19(1):38-48 ARTICLE IDENTIFIERS DOI: 10.1177/1077559513511522 PMID: 24271026 PMCID: not available JOURNAL IDENTIFIERS LCCN: not available pISSN: 1077-5595 eISSN: 1552-6119 OCLC ID: 30832620 CONS ID: sn 94001296 US National Library of Medicine ID: 9602869 This article was identified from a query of the SafetyLit database. Powered by TCPDF (www.tcpdf.org)" a66d89357ada66d98d242c124e1e8d96ac9b37a0,Failure Detection for Facial Landmark Detectors,"Failure Detection for Facial Landmark Detectors Andreas Steger, Radu Timofte, and Luc Van Gool Computer Vision Lab, D-ITET, ETH Zurich, Switzerland {radu.timofte," a6a6cfae45e8633c01793debf43592b7d515f65d,From ImageNet to Mining: Adapting Visual Object Detection with Minimal Supervision,"From ImageNet to Mining: Adapting Visual Object Detection with Minimal Supervision Alex Bewley and Ben Upcroft" a6590c49e44aa4975b2b0152ee21ac8af3097d80,3D Interpreter Networks for Viewer-Centered Wireframe Modeling,"https://doi.org/10.1007/s11263-018-1074-6 D Interpreter Networks for Viewer-Centered Wireframe Modeling Jiajun Wu1 · Tianfan Xue2 · Joseph J. Lim3 · Yuandong Tian4 · Joshua B. Tenenbaum1 · Antonio Torralba1 · William T. Freeman1,5 Received: date / Accepted: date" dbf360fa9997b2918a8076f1d0df9a1fffa94ed7,Recommending and Planning Trip Itineraries for Individual Travellers and Groups of Tourists,"Recommending and Planning Trip Itineraries for Individual Travellers and Groups of Tourists *Department of Computing and Information Systems, The University of Melbourne, Australia Victoria Research Laboratory, National ICT Australia, Australia Kwan Hui Lim*†" dbb7f37fb9b41d1aa862aaf2d2e721a470fd2c57,Face image analysis with convolutional neural networks,"Face Image Analysis With Convolutional Neural Networks Dissertation Zur Erlangung des Doktorgrades der Fakult¨at f¨ur Angewandte Wissenschaften n der Albert-Ludwigs-Universit¨at Freiburg im Breisgau Stefan Duffner" db85195e171f7b75e4e6f99ed3029d31ee557e13,the influence of a verticality metaphor in the processing of happy and sad faces,"RIPS / IRSP, 27 (2), 51-77 © 2014, Presses universitaires de Grenoble the influence of a verticality metaphor in the processing of happy and sad faces L’influence de la métaphore de verticalité sur le traitement des émotions faciales de gaieté et de tristesse Timothée Mahieu*,** Olivier Corneille** Vincent Y. Yzerbyt** Key-words Metaphorical thinking, grounded cognition, facial emotions, gender Mots-clés Pensée métaphorique, ognition incarnée, émotions faciales, genre" db24a2c27656db88486479b26f99d8754a44f4b8,Age estimation via face images : a survey,"Angulu et al. EURASIP Journal on Image and Video Processing (2018) 2018:42 https://doi.org/10.1186/s13640-018-0278-6 EURASIP Journal on Image nd Video Processing REVIEW Open Access Age estimation via face images: a survey Raphael Angulu1*† , Jules R. Tapamo2 and Aderemi O. Adewumi1" db545026d0b42c2dcf935a1505a68edb36381194,Development of an Encrypting System for an Image Viewer based on Hill Cipher Algorithm,"Covenant Journal of Engineering Technology (CJET) Vol.1 No. 2, Dec. 2017 An Open Access Journal Available Online Development of an Encrypting System for an Image Viewer based on Hill Cipher Algorithm Okereke Chinonso, Osemwegie Omoruyi, Kennedy Okokpujie & Samuel John Department of Electrical and Information Engineering, Covenant University, Ota, Ogun state, Nigeria Corresponding Author:" db480f100004e3ef075f9404041fe4f89fcf4e0c,Human Pose Estimation for RGBD Imagery with Multi-Channel Mixture of Parts and Kinematic Constraints,"Human Pose Estimation for RGBD Imagery with Multi-Channel Mixture of Parts and Kinematic Constraints ENRIQUE MARTINEZ-BERTI Universitat Politecnica de Valencia Instituto AI2 Camino de Vera s/n, Valencia SPAIN ANTONIO J. SNCHEZ-SALMERN Universitat Politecnica de Valencia CARLOS RICOLFE-VIALA Universitat Politecnica de Valencia Instituto AI2 Camino de Vera s/n, Valencia SPAIN Instituto AI2 Camino de Vera s/n, Valencia SPAIN Center for Research in Computer Vision Center for Research in Computer Vision OLIVER NINA" db458242dd526d84579aeee563355ca1a7dea5ea,Face Detection in Nighttime Images Using Visible-Light Camera Sensors with Two-Step Faster Region-Based Convolutional Neural Network,"Article Face Detection in Nighttime Images Using Visible-Light Camera Sensors with Two-Step Faster Region-Based Convolutional Neural Network Se Woon Cho, Na Rae Baek, Min Cheol Kim, Ja Hyung Koo, Jong Hyun Kim and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pil-dong-ro 1-gil, Jung-gu, Seoul 04620, Korea; (S.W.C.); (N.R.B.); (M.C.K.); (J.H.K.); (J.H.K.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 31 July 2018; Accepted: 4 September 2018; Published: 7 September 2018" dbd5e9691cab2c515b50dda3d0832bea6eef79f2,Image-based Face Recognition: Issues and Methods 1,"Image-basedFaceRecognition:IssuesandMethods WenYiZhao RamaChellappa Sarno(cid:11)Corporation CenterforAutomationResearch WashingtonRoad UniversityofMaryland Princeton,NJ CollegePark,MD-" db68105a787d7ef60ebb5bb4cfce151d47748123,Improved RGB-D-T based face recognition,"Aalborg Universitet Improved RGB-D-T based Face Recognition Oliu Simon, Marc; Corneanu, Ciprian; Nasrollahi, Kamal; Nikisins, Olegs; Guerrero, Sergio Escalera; Sun, Yunlian; Li, Haiqing; Sun, Zhenan; Moeslund, Thomas B.; Greitans, Modris Published in: DOI (link to publication from Publisher): 0.1049/iet-bmt.2015.0057 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Oliu Simon, M., Corneanu, C., Nasrollahi, K., Nikisins, O., Guerrero, S. E., Sun, Y., ... Greitans, M. (2016). mt.2015.0057 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain ? You may freely distribute the URL identifying the publication in the public portal ?" dbaf89ca98dda2c99157c46abd136ace5bdc33b3,Nonlinear Cross-View Sample Enrichment for Action Recognition,"Nonlinear Cross-View Sample Enrichment for Action Recognition Ling Wang, Hichem Sahbi Institut Mines-T´el´ecom; T´el´ecom ParisTech; CNRS LTCI" db0d33590dc15de2d30cf0407b7a26ae79cd51b5,Deep Probabilistic Modeling of Natural Images using a Pyramid Decomposition,"Deep Probabilistic Modeling of Natural Images using a Pyramid Decomposition Alexander Kolesnikov IST Austria, Am Campus 1, Klosterneuburg, 3400 Austria Christoph H. Lampert IST Austria, Am Campus 1, Klosterneuburg, 3400 Austria" db9ddb2c730d75ab741544654c7c227831ed1243,Recent Advances in Zero-shot Recognition,"Recent Advances in Zero-shot Recognition Yanwei Fu, Tao Xiang, Yu-Gang Jiang, Xiangyang Xue, Leonid Sigal, and Shaogang Gong" dbb0a527612c828d43bcb9a9c41f1bf7110b1dc8,Machine Learning Techniques for Face Analysis,"Chapter 7 Machine Learning Techniques for Face Analysis Roberto Valenti, Nicu Sebe, Theo Gevers, and Ira Cohen" db227f72bb13a5acca549fab0dc76bce1fb3b948,Characteristic Based Image Search Using Re-Ranking Method,"International Refereed Journal of Engineering and Science (IRJES) ISSN (Online) 2319-183X, (Print) 2319-1821 Volume 4, Issue 6 (June 2015), PP.169-169-174 Characteristic Based Image Search using Re-Ranking method Chitti Babu, 2Yasmeen Jaweed, 3G.Vijay Kumar ,2,3Computer Science Engineering Dept, Sree Dattha Institute of Engineering & Science" dba3ec4420a0bcca3264f75f4c975cabdbb1af74,"""Edutainment 2017"" a visual and semantic representation of 3D face model for reshaping face in images","J Vis (2018) 21:649–660 https://doi.org/10.1007/s12650-018-0476-4 R E G UL A R P A P E R Jiang Du • Dan Song • Yanlong Tang • Ruofeng Tong • Min Tang ‘‘Edutainment 2017’’ a visual and semantic representation of 3D face model for reshaping face in images Received: 15 September 2017 / Revised: 20 December 2017 / Accepted: 22 January 2018 / Published online: 16 February 2018 Ó The Visualization Society of Japan 2018" db186bd2a276a574b2246e3e4d136f8a07c53ff2,Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment,"Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment Thomio Watanabe University of Sao Paulo Denis Wolf University of Sao Paulo" db6d00f9237cce392c08b422662b48baa2ed1b80,A New Framework for Biometric Face Recognition Using Visual,"Annals of DAAAM for 2012 & Proceedings of the 23rd International DAAAM Symposium, Volume 23, No.1, ISSN 2304-1382 ISBN 978-3-901509-91-9, CDROM version, Ed. B. Katalinic, Published by DAAAM International, Vienna, Austria, EU, 2012 Make Harmony between Technology and Nature, and Your Mind will Fly Free as a Bird Annals & Proceedings of DAAAM International 2012 A NEW FRAMEWORK FOR BIOMETRIC FACE RECOGNITION USING VISUAL CRYPTOGRAPY MIHAILESCU, M[arius] I[ulian] & PIRLOAGA, M[arian] D[orin]" db3814e155e77cefaa71016b0e5ebdc6be34a925,Enhanced Clustering Method using 3 D Laser Range Data for an Autonomous Vehicle,"Enhanced Clustering Method using 3D Laser Range Data for an Autonomous Vehicle KUK CHO, SEUNGHO BAEG, and SANGDEOK PARK Korea Institute of Industrial Technology Department of Robot Research & Business Development 271-18, Sa-1dong, Sangruk-gu, Ansan Republic of Korea googi33, shbaeg," dbb065aa2a6e6804e0ab8aee27314a6f68c4cde1,Advanced Hypothesis Testing Techniques and Their Application to Image Classification Advanced Hypothesis Testing Techniques and Their Application to Image Classification Title: Advanced Hypothesis Testing Techniques and Their Application to Image Classification Acknowledgements,"Dipartimento di Informatica e Scienze dell’Informazione •• •• Advanced Hypothesis testing techniques and their pplication to image classification Emanuele Franceschi Theses Series DISI-TH-2005-XX DISI, Universit`a di Genova v. Dodecaneso 35, 16146 Genova, Italy http://www.disi.unige.it/" dbe2f62c086b2e6617c7744f8c242de401f17cc0,Particle-based Pedestrian Path Prediction using LSTM-MDL Models,"Particle-based Pedestrian Path Prediction using LSTM-MDL Models Ronny Hug∗, Stefan Becker∗, Wolfgang H¨ubner∗ and Michael Arens∗" 318d7a4bc9c7b1e3a01056815479564ed8ad78a4,University of Oklahoma Graduate College Reinforcement Learning Scheduler for Heterogeneous Multi-core Processors Reinforcement Learning Scheduler for Heterogeneous Multi-core Processors a Thesis Approved for the School of Computer Science,"UNIVERSITY OF OKLAHOMA GRADUATE COLLEGE REINFORCEMENT LEARNING SCHEDULER FOR HETEROGENEOUS MULTI-CORE PROCESSORS A THESIS SUBMITTED TO THE GRADUATE FACULTY in partial fulfillment of the requirements for the Degree of MASTER OF SCIENCE XIAOLEI YAN Norman, Oklahoma" 3137870bf1314e25c2246d4a9d77d941aadd5398,Influence of Positive Instances on Multiple Instance Support Vector Machines,"Influence of Positive Instances on Multiple Instance Support Vector Machines Nuno Barroso Monteiro1,2, Jo˜ao Pedro Barreto2, and Jos´e Gaspar1 Institute for Systems and Robotics (ISR/IST), LARSyS, Univ. of Lisbon, Portugal Institute for Systems and Robotics, Univ. of Coimbra, Portugal" 318ee553c61888f2418280cb1d342c698d3444c9,Towards face unlock: on the difficulty of reliably detecting faces on mobile phones,"Towards Face Unlock: On the Difficulty of Reliably Detecting Faces on Mobile Phones Rainhard D. Findling Softwarepark 11 Hagenberg, Austria Rene Mayrhofer Softwarepark 11 Hagenberg, Austria Department for Mobile Computing Upper Austria University of Applied Sciences Department for Mobile Computing Upper Austria University of Applied Sciences" 3130eb9bfab5e5a095ab989ba3cc6a2ec62c156d,Generating Facial Ground Truth with Synthetic Faces,"Generating Facial Ground Truth with Synthetic Faces Rossana Queiroz, Marcelo Cohen, Juliano L. Moreira, Adriana Braun, J´ulio C. Jacques J´unior, Soraia Raupp Musse Pontif´ıcia Universidade Cat´olica do Rio Grande do Sul - PUCRS Graduate Programme in Computer Science Virtual Human Laboratory -www.inf.pucrs.br/∼vhlab Porto Alegre, Brazil Figure 1. A sample of 3D faces generated by our prototype." 31786e6d5187d7bc41678cbd2d1bf8edf1ddfed9,Capture de mouvements humains par capteurs RGB-D. (Capture human motions by RGB-D sensor ),"Capture de mouvements humains par capteurs RGB-D Jean-Thomas Masse To cite this version: Jean-Thomas Masse. Capture de mouvements humains par capteurs RGB-D. Robotique [cs.RO]. Universit´e Paul Sabatier - Toulouse III, 2015. Fran¸cais. ¡ NNT : 2015TOU30361 HAL Id: tel-01280163 https://tel.archives-ouvertes.fr/tel-01280163v2 Submitted on 26 Apr 2017 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires" 318c4c25d86511690cc5df7b041a6392e8cc4ea8,Fashion-Gen: The Generative Fashion Dataset and Challenge,"Fashion-Gen: The Generative Fashion Dataset and Challenge Negar Rostamzadeh 1 Seyedarian Hosseini 1 2 Thomas Boquet 1 Wojciech Stokowiec 1 Ying Zhang 1 Christian Jauvin 1 Chris Pal 3 1" 31c174f2190889d5792358713e078336926d7ee4,Image Categorization using Codebooks Built from Scored and Selected Local Features,"Image Categorization using Codebooks Built from Scored and Selected Local Features Department of Computer Science, Northern Illinois University DeKalb IL USA 60115 Bala S. Divakaruni and Jie Zhou follows (M&C) process" 31625522950e82ad4dffef7ed0df00fdd2401436,Motion Representation with Acceleration Images,"Motion Representation with Acceleration Images Hirokatsu Kataoka, Yun He, Soma Shirakabe, Yutaka Satoh National Institute of Advanced Industrial Science and Technology (AIST) Tsukuba, Ibaraki, Japan {hirokatsu.kataoka, yun.he, shirakabe-s," 31da1da2d4e7254dd8f2a4578d887c57e0678438,Unsupervised Person Re-identification: Clustering and Fine-tuning,"Unsupervised Person Re-identification: Clustering and Fine-tuning Hehe Fan, Liang Zheng and Yi Yang" 317f5a56519df95884cce81cfba180ee3adaf5a5,Operator-In-The-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification,"FusionCam C1Cam C2Classical re-id schemeProposed re-idschemeQueryQueryRanked List: Cam 𝐶1Ranked List: Cam 𝐶2Ranked List: Cam 𝐶1OperatorFeedbackRanked List: Cam 𝐶2Fig.1:(Top)Classicalre-idschemewherequeryimage’sfeaturerepresentationisusedtosearcheachcamerainthenetworkinde-pendently.Theretrievedlistsarereturnedtothehumanoperator.(Bottom)Ourproposedsequentialre-idschemewhereoperatorfeedbackregardingtargetsightingisutilizedtowardsbetterre-idperformanceinanonlinefashion.Inthefigure,cameraC1isqueriedfirstandrankedlistofmatchesisobtained.Thecorrectmatch(pinkbox)inretrievedrankedlistisidentifiedbyoperator.Thecorrectmatchisfusedwithqueryimageatfeaturelevel(orangeblock).ThisfusedrepresentationisusedtoquerycameraC2.NoticethatrankingofquerytargetinC2’slistimprovesinourapproachunliketheclassicalversionwhichcannotexploitoperatorinputstoimprovesubsequentqueries.arXiv:1807.07295v3 [cs.CV] 6 Nov 2018" 318eb316c0117059dd47978854cfa92baeaac1d2,Deterministic CUR for Improved Large-Scale Data Analysis: An Empirical Study,"Deterministic CUR for Improved Large-Scale Data Analysis: An Empirical Study Christian Thurau, Kristian Kersting, and Christian Bauckhage Fraunhofer IAIS, Germany" 31fc3b044ec908f7f61386422727ef23784178c0,Enhancing Face Recognition using Average per Region,"International Journal of Computer Applications (0975 – 8887) Volume 65– No.3, March 2013 Enhancing Face Recognition using Average per Region Basheer M. Nasef Teaching Assistant Dept of Computer and Systems Engineering, Zagazig University, Sharkia, Egypt Ibrahim E. Ziedan Dept of Computer and Systems Engineering, Professor Zagazig University, Sharkia, Egypt" 316e67550fbf0ba54f103b5924e6537712f06bee,Multimodal semi-supervised learning for image classification,"Multimodal semi-supervised learning for image classification Matthieu Guillaumin, Jakob Verbeek, Cordelia Schmid LEAR team, INRIA Grenoble, France" 315ac7b1c160eb593b6ce80d46b4ae2bcab49e12,SLAM++ -A highly efficient and temporally scalable incremental SLAM framework,"SLAM++1. A Highly Efficient and Temporally Scalable Incremental SLAM Framework Viorela Ila, Lukas Polok, Marek Solony and Pavel Svoboda" 3199a528e5e68f48827544abee7fd6b47678dba5,Human Face Recognition Using Weighted Vote of Gabor Magnitude Filters,"Information Technology and Applications Journal Human Face Recognition Using Weighted Vote of Gabor Magnitude Filters Iqbal Nouyed, Graduate Student member IEEE, M. Ashraful Amin, Member IEEE, Bruce Poon, Senior Member IEEE, Hong Yan, Fellow IEEE" 312b807a24b8c30876c1750530b08e4d9627e231,Increasing Trustworthiness of Face Authentication in Mobile Devices by Modeling Gesture Behavior and Location Using Neural Networks,"Article Increasing Trustworthiness of Face Authentication in Mobile Devices by Modeling Gesture Behavior and Location Using Neural Networks Blerim Rexha 1 ID , Gresa Shala 2,* and Valon Xhafa 3 Faculty of Electrical and Computer Engineering, University of Prishtina, Kodra e Diellit p.n., 0000 Prishtina, Kosovo; Department of Computer Science, Freiburg University, Georges-Köhler Alley 101, 79110 Freiburg im Breisgau, Germany Department of Informatics, Technical University of Munich, Boltzmannstraße 3, 85748 Garching bei München, Germany; * Correspondence: Received: 18 January 2018; Accepted: 2 February 2018; Published: 5 February 2018" 31de9b3dd6106ce6eec9a35991b2b9083395fd0b,FERET ( Face Recognition Technology ) Recognition Algorithm Development and Test Results,"FERET (Face Recognition Technology) Recognition Algorithm Development and Test Results y P. Jonathon Phillips, Patrick J. Rauss, and Sandor Z. Der ARL-TR-995 October 1996 Approved for public release; distribution unlimited." 318df1761d01ebafc955eca683392dc98a5056d0,On the Use of SIFT Features for Face Authentication,"On the use of SIFT features for face authentication Manuele Bicego, Andrea Lagorio, Enrico Grosso, Massimo Tistarelli University of Sassari" 3176ee88d1bb137d0b561ee63edf10876f805cf0,Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation,"Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation Sina Honari1, Jason Yosinski2, Pascal Vincent1,4, Christopher Pal3 University of Montreal, 2Cornell University, 3Ecole Polytechnique of Montreal, 4CIFAR {honaris," 31ea3186aa7072a9e25218efe229f5ee3cca3316,A ug 2 01 7 Reinforced Video Captioning with Entailment Rewards,"Reinforced Video Captioning with Entailment Rewards Ramakanth Pasunuru and Mohit Bansal UNC Chapel Hill {ram," 31ca0d6488a27a140263291c51ec924b8a49967b,"Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering","Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering Vahid Kazemi Ali Elqursh Google Research 600 Amphitheater Parkway {vahid," 3107486fe666a3004b720125bd2b05ff9382fdb8,Generalized two-dimensional linear discriminant analysis with regularization,"JOURNAL OF LATEX CLASS FILES, VOL. , NO. Generalized two-dimensional linear discriminant nalysis with regularization Chun-Na Li, Yuan-Hai Shao,Wei-Jie Chen, Zhen Wang and Nai-Yang Deng" 31c0968fb5f587918f1c49bf7fa51453b3e89cf7,Deep Transfer Learning for Person Re-Identification,"Deep Transfer Learning for Person Re-identification Mengyue Geng Yaowei Wang Tao Xiang Yonghong Tian" 3174fceef3cf09ac35e8d1eb4e1b8b73a3b2c713,Unsupervised learning from videos using temporal coherency deep networks,"Computer Vision and Image Understanding journal homepage: www.elsevier.com Unsupervised learning from videos using temporal coherency deep networks Carolina Redondo-Cabreraa,∗∗, Roberto Lopez-Sastrea GRAM, University of Alcal´a, Alcal´a de Henares, 28805, Spain" 31d30089d00d89715167ca4a130a5d262e1d79d3,Measuring the effect of nuisance variables on classifiers,"FAWZI, FROSSARD: MEASURING THE EFFECT OF NUISANCE VARIABLES Measuring the effect of nuisance variables on classifiers Alhussein Fawzi Pascal Frossard Signal Processing Laboratory (LTS4) Ecole Polytechnique Fédérale de Lausanne (EPFL) Lausanne, Switzerland" 318f7b59fc22d6326f77b24939860b0137bf8e77,Multiple Classifier Boosting and Tree-Structured Classifiers,"Multiple Classifier Boosting and Tree-Structured Classifiers Tae-Kyun Kim and Roberto Cipolla" 3137eede6bbada4442e0193dc5918788b7e88aa1,Hyper-class augmented and regularized deep learning for fine-grained image classification,"Hyper-class Augmented and Regularized Deep Learning for Fine-grained Image Classification Saining Xie1, Tianbao Yang2 Xiaoyu Wang3, Yuanqing Lin4 University of California, San Diego. 2University of Iowa. 3Snapchat Research. 4NEC Labs America, Inc. Fine-grained image classification (FGIC) is challenging because (i) fine- grained labeled data is much more expensive to acquire (usually requir- ing domain expertise); (ii) there exists large intra-class and small inter- lass variance. In this paper, we propose a systematic framework of learn- ing a deep CNN that addresses the challenges from two new perspectives: (i) identifying easily annotated hyper-classes inherent in the fine-grained data and acquiring a large number of hyper-class-labeled images from read- ily available external sources, and formulating the problem into multi-task learning, to address the data scarcity issue. We use two common types of hyper-classes to augment our data, with one being the super-type hyper- lasses that subsume a set of fine-grained classes, and another being named factor-type hyper-classes (e.g., different view-points of a car) that explain the large intra-class variance. (ii) a novel learning model by exploiting a reg- ularization between the fine-grained recognition model and the hyper-class recognition model to mitigate the issue of large intra-class variance and im- prove the generalization performance. The proposed approach also closely relates to attribute-based learning, since one can consider that factor-type" 3123e97a6b86913d994e44f8d9d5c639e0e2dc96,A Method of Initialization for Nonnegative Matrix Factorization,"A METHOD OF INITIALIZATION FOR NONNEGATIVE MATRIX FACTORIZATION Yong-Deok Kim and Seungjin Choi Department of Computer Science, POSTECH, Korea {karma13," 31afdb6fa95ded37e5871587df38976fdb8c0d67,Quantized fuzzy LBP for face recognition,"QUANTIZED FUZZY LBP FOR FACE RECOGNITION Jianfeng Xudong Jiang, Junsong BeingThere Centre Institute of Media Innovation Nanyang 50 Nanyang Technological Singapore Drive, 637553. University School of Electrical & Electronics Engineering Nanyang 50 Nanyang" 31ef5419e026ef57ff20de537d82fe3cfa9ee741,Facial Expression Analysis Based on High Dimensional Binary Features,"Facial Expression Analysis Based on High Dimensional Binary Features Samira Ebrahimi Kahou, Pierre Froumenty, and Christopher Pal ´Ecole Polytechique de Montr´eal, Universit´e de Montr´eal, Montr´eal, Canada {samira.ebrahimi-kahou, pierre.froumenty," 316bed02e22aa6742dffcd50c29a7365c5a5a437,Representation Learning for Visual-Relational Knowledge Graphs,"Representation Learning for Visual-Relational Knowledge Graphs Daniel Oñoro-Rubio, Mathias Niepert, Alberto García-Durán, Roberto González-Sánchez and Roberto J. López-Sastre* NEC Labs Europe, Alcalá de Henares* {daniel.onoro, mathias.niepert, alberto.duran, https://github.com/nle-ml/mmkb.git" 310a88a60ffa2d8a0fa7ef9fc77fa842d16eed57,View Invariant Gait Recognition,"View Invariant Gait Recognition Richard D. Seely, Michela Goffredo, John N. Carter and Mark S. Nixon" 3151b110ecdcf2105def494bfb0775f21259d7e8,Asymmetric Cuts: Joint Image Labeling and Partitioning,"Asymmetric Cuts : Joint Image Labeling and Partitioning Thorben Kroeger1, J¨org H. Kappes2, Thorsten Beier1, Ullrich Koethe1 and Fred A. Hamprecht1,2 Multidimensional Image Processing Group, Heidelberg University Heidelberg Collaboratory for Image Processing, Heidelberg University" 31ace8c9d0e4550a233b904a0e2aabefcc90b0e3,Learning Deep Face Representation,"Learning Deep Face Representation Haoqiang Fan Megvii Inc. Zhimin Cao Megvii Inc. Yuning Jiang Megvii Inc. Qi Yin Megvii Inc. Chinchilla Doudou Megvii Inc." 31470cf8fda53c4460de4373e5ac4544236c44af,Biased information processing as an endophenotype for depression,"PDF hosted at the Radboud Repository of the Radboud University Nijmegen The following full text is a publisher's version. For additional information about this publication click this link. http://repository.ubn.ru.nl/handle/2066/127113 Please be advised that this information was generated on 2017-04-19 and may be subject to hange." 31b9251dedce1e10467a0a33f56ac4eb05ed0451,Viewpoint-dependent 3D human body posing for sports legacy recovery from images and video,"VIEWPOINT-DEPENDENT 3D HUMAN BODY POSING FOR SPORTS LEGACY RECOVERY FROM IMAGES AND VIDEO Luis Unzueta, Jon Goenetxea, Mikel Rodriguez and Maria Teresa Linaza Vicomtech-IK4, Paseo Mikeletegi, 57, Parque Tecnológico, 20009, Donostia, Spain" 318985dc2b8d5a1882b709eedeaac4a2e7de1d81,Accelerating Message Passing for MAP with Benders Decomposition,"Accelerating Message Passing for MAP with Benders Decomposition Julian Yarkony Experian Data Lab. Shaofei Wang Baidu Inc. May 15, 2018" 31bec2ba11ccf217461a491e810dc1d8ef33f9a9,Multimodal Probabilistic Model-Based Planning for Human-Robot Interaction,"Multimodal Probabilistic Model-Based Planning for Human-Robot Interaction Edward Schmerling1 Karen Leung2 Wolf Vollprecht3 Marco Pavone2" c791682fa3f716401bca46c6e9a2af495b0d9d51,Interested in publishing with us ? Contact book,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." c72914e2e999c99753d1d0058c459af69af6662a,CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation,"MACKOWIAK ET AL.: CEREALS CEREALS – Cost-Effective REgion-based Active Learning for Semantic Segmentation Robert Bosch GmbH Corporate Research - Computer Vision Robert-Bosch-Straße 200 1139 Hildesheim, DE Heidelberg Collaboratory for Image Processing (HCI) Berliner Straße 43, 69120 Heidelberg, DE Radek Mackowiak1 Philip Lenz1 Omair Ghori1 Ferran Diego1 Oliver Lange1 Carsten Rother2" c7391b43bd0216daf697fb77906b76c71f5c50e2,Learning where to attend like a human driver,"Where Should You Attend While Driving? Simone Calderara Stefano Alletto Andrea Palazzi∗ Francesco Solera∗ Rita Cucchiara University of Modena and Reggio Emilia" c758b9c82b603904ba8806e6193c5fefa57e9613,Heterogeneous Face Recognition with CNNs,"Heterogeneous Face Recognition with CNNs Shreyas Saxena Jakob Verbeek INRIA Grenoble, Laboratoire Jean Kuntzmann" c71f71200fc85d9fdbd5b3d8b4b6a9daf5a2b424,Machine Learning for Image Based Motion Capture,"INSTITUTNATIONALPOLYTECHNIQUEDEGRENOBLENum´eroattribu´eparlabiblioth`equeTH`ESEpourobtenirlegradedeDOCTEURDEL’INSTITUTNATIONALPOLYTECHNIQUEDEGRENOBLESp´ecialit´e:Imagerie,VisionetRobotiqueEcoleDoctorale:Math´ematiques,SciencesetTechnologiedel’Informationpr´esent´eeetsoutenuepubliquementparAnkurAgarwalle26Avril2006MachineLearningforImageBasedMotionCaptureDirecteurdeth`ese:M.WilliamTriggsJURYM.RogerMohrPr´esidentM.AndrewZissermanRapporteurM.PascalFuaRapporteurM.WilliamTriggsDirecteurdeth`eseM.PhilipTorrExaminateurTh`esepr´epar´eedanslelaboratoireGRAVIR–IMAGauseinduprojetLEARINRIARhˆone-Alpes,655avenuedel’Europe,38334SaintIsmier,France." c7f80cd585117ae7028148c38ddce8e63b311ba5,Real-Time Face Detection and Recognition via Local Binary Pattern Plus Sample Selective Biomimetic Pattern Recognition,"IEICE TRANS. INF. & SYST., VOL.E96–D, NO.3 MARCH 2013 PAPER SpecialSectiononFacePerceptionandRecognition Real-Time Face Detection and Recognition via Local Binary Pattern Plus Sample Selective Biomimetic Pattern Recognition Yikui ZHAI†,††a), Student Member, Junying GAN†, Jinwen LI††, Junying ZENG†, nd Ying XU†,†††, Nonmembers SUMMARY Due to security demand of society development, real-time face recognition has been receiving more and more attention nowadays. In this paper, a real-time face recognition system via Local Binary Pat- tern (LBP) plus Improved Biomimetic Pattern Recognition (BPR) has been proposed. This system comprises three main steps: real-time color face de- tection process, feature extraction process and recognition process. Firstly, color face detector is proposed to detect face with eye alignment and si- multaneous performance; while in feature extraction step, LBP method is dopted to eliminate the negative effect of the light heterogeneity. Finally, n improved BPR method with Selective Sampling construction is applied to the recognition system. Experiments on our established database named WYU Database, PUT Database and AR Database show that this real-time face recognition system can work with high ef‌f‌iciency and has achieved" c76d143b3fa0d25e21580c583d39ab07fc937e71,3D Position Estimation of a Person of Interest in Multiple Video Sequences: People Detection,"Institutionen för systemteknik Department of Electrical Engineering Examensarbete D Position Estimation of a Person of Interest in Multiple Video Sequences: People Detection Examensarbete utfört i Datorseende vid Tekniska högskolan vid Linköpings universitet Johannes Markström LiTH-ISY-EX--13/4721--SE Linköping 2013 Department of Electrical Engineering Linköpings universitet SE-581 83 Linköping, Sweden Linköpings tekniska högskola Linköpings universitet 581 83 Linköping" c7ea9611446817f7b668882061ab11c7e998296c,Towards a Crowd Analytic Framework For Crowd Management in Majid-al-Haram,"Towards a Crowd Analytic Framework For Crowd Management in Majid-al-Haram Sultan Daud Khan1,*, Muhammad Tayyab1, Muhammad Khurram Amin1, Akram Nour1, Anas Basalamah1, Saleh Basalamah1, and Sohaib Ahmad Khan1,2,* Technology Innovation Center, Wadi Makkah, Makkah Al Mukarramah, Saudi Arabia Science and Technology Unit, Umm Al Qura University, Makkah Al Mukarramah, Saudi Arabia" c7e4c7be0d37013de07b6d829a3bf73e1b95ad4e,MO : A VIDEO DATABASE OF NATURAL FACIAL EXPRESSIONS OF EMOTIONS,"The International Journal of Multimedia & Its Applications (IJMA) Vol.5, No.5, October 2013 DYNEMO: A VIDEO DATABASE OF NATURAL FACIAL EXPRESSIONS OF EMOTIONS Anna Tcherkassof1, Damien Dupré1, Brigitte Meillon2, Nadine Mandran2, Michel Dubois1 and Jean-Michel Adam2 LIP, Univ. Grenoble Alpes, BP 47 - 38040 Grenoble Cedex 9, France LIG, Univ. Grenoble Alpes, BP 53 - 38041 Grenoble Cedex 9, France" c7fff0d0a6312965b269c6180b2112babd40564c,Unsupervised Person Re-identification: Clustering and Fine-tuning,"Unsupervised Person Re-identification: Clustering and Fine-tuning Hehe Fan, Liang Zheng and Yi Yang" c7eb127e9cd67d645b9a7f59c03bc73183faefeb,Human Detection in Indoor Environments Using Multiple Visual Cues and a Mobile Robot,"Human Detection in Indoor Environments Using Multiple Visual Cues and a Mobile Robot Stefan Pszcz´o(cid:2)lkowski and Alvaro Soto Pontificia Universidad Catolica de Chile Santiago 22, Chile" c7c03324833ba262eeaada0349afa1b5990c1ea7,A Wearable Face Recognition System on Google Glass for Assisting Social Interactions,"A Wearable Face Recognition System on Google Glass for Assisting Social Interactions Bappaditya Mandal∗, Chia Shue Ching, Liyuan Li, Vijay Ramaseshan Chandrasekhar, Cheston Tan Yin Chet and Lim Joo Hwee Visual Computing Department, Institute for Infocomm Research, Singapore Email address: (∗Contact author: Bappaditya Mandal); {scchia, lyli, vijay, cheston-tan," c7f752eea91bf5495a4f6e6a67f14800ec246d08,EXPLORING THE TRANSFER LEARNING ASPECT OF DEEP NEURAL NETWORKS IN FACIAL INFORMATION PROCESSING,"EXPLORING THE TRANSFER LEARNING ASPECT OF DEEP NEURAL NETWORKS IN FACIAL INFORMATION PROCESSING A DISSERTATION SUBMITTED TO THE UNIVERSITY OF MANCHESTER FOR THE DEGREE OF MASTER OF SCIENCE IN THE FACULTY OF ENGINEERING AND PHYSICAL SCIENCES Crefeda Faviola Rodrigues School of Computer Science" c751a00dd5357e2e390e5af2626b5fbb6223ea1c,Behavioral and neural indices of affective coloring for neutral social stimuli,"Social Cognitive and Affective Neuroscience, 2018, 310–320 doi: 10.1093/scan/nsy011 Advance Access Publication Date: 13 February 2018 Original article Behavioral and neural indices of affective coloring for neutral social stimuli Daniel W. Grupe, Stacey M. Schaefer, Regina C. Lapate, Andrew J. Schoen, Lauren K. Gresham, Jeanette A. Mumford, and Richard J. Davidson Center for Healthy Minds and Waisman Laboratory for Brain Imaging and Behavior, University of Wisconsin- Madison, Madison, WI 53706, USA Correspondence should be addressed to Daniel W. Grupe, Center for Healthy Minds and Waisman Laboratory for Brain Imaging and Behavior, University of Wisconsin-Madison, 625 West Washington Ave, Madison, WI 53703, USA. E-mail:" c7f63fc2ff20513c6dc233ec3419417b43b39209,Human Detection from Aerial Imagery for Automatic Counting of Shellfish Gatherers,"Human Detection from Aerial Imagery for Automatic Counting of Shellfish gatherers Mathieu Laroze, Luc Courtrai and Sébastien Lefèvre Univ. Bretagne-Sud, UMR 6074 IRISA {mathieu.laroze, luc.courtrai, F-56000, Vannes, France Keywords: Human Detection, Image Stitching, Aerial Imagery, Image Mosaicing, Patch Classification, Object Detection" c719a718073128a985c957cdfa3f298706a180e6,Comparative Evaluations of Selected Tracking-by-Detection Approaches,"Comparative Evaluations of Selected Tracking-by-Detection Approaches Alhayat Ali Mekonnen, Frédéric Lerasle To cite this version: Alhayat Ali Mekonnen, Frédéric Lerasle. Comparative Evaluations of Selected Tracking-by-Detection Approaches. IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical nd Electronics Engineers, 2018, <10.1109/TCSVT.2018.2817609>. HAL Id: hal-01815850 https://hal.laas.fr/hal-01815850 Submitted on 14 Jun 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" c726ea46544968335f1e51be633f15d0cc0f0311,Generalized feature learning and indexing for object localization and recognition,"Generalized Feature Learning and Indexing for Object Localization and Recognition Ning Zhou∗ UNC, Charlotte Anelia Angelova∗ Google Inc Jianping Fan UNC, Charlotte" c7c405b6fc95ff2ccf2cb5b59942db4343558fc4,Pseudo 2 D Hidden Markov Model Based Face Recognition System Using Singular Values Decomposition Coefficients,"Pseudo 2D Hidden Markov Model Based Face Recognition System Using Singular Values Decomposition Coefficients Mukundhan Srinivasan Department of Electronics & Communication Engineering Alpha College of Engineering Chennai, TN India Sabarigirish Vijayakumar Retail Domain Tata Consultancy Services (TCS) Chennai, TN India" c72796c511e2282e4088b0652a4cce0e2da4296c,Hierarchical Discrete Distribution Decomposition for Match Density Estimation,"Hierarchical Discrete Distribution Decomposition for Match Density Estimation Zhichao Yin Trevor Darrell UC Berkeley Fisher Yu" c7774fd600630684cc1d6be8313e2935bb198880,Adapting Hausdorff Metrics to Face Detection Systems: A Scale-Normalized Hausdorff Distance Approach,"Adapting Hausdorff metrics to face detection systems: a scale-normalized Hausdorff distance pproach Pablo Suau Departamento de Ciencia de la Computaci´on e Inteligencia Artificial Universidad de Alicante, Ap. de correos 99, 03080, Alicante (Spain)" c757f6ee46208c1c26572265803068f8d837c384,Thermal imaging systems for real-time applications in smart cities,"Aalborg Universitet Thermal Imaging Systems for Real-Time Applications in Smart Cities Gade, Rikke; Moeslund, Thomas B.; Nielsen, Søren Zebitz; Skov-Petersen, Hans; Andersen, Hans Jørgen; Basselbjerg, Kent; Dam, Hans Thorhauge; Jensen, Ole B.; Jørgensen, Anders; Lahrmann, Harry Spaabæk; Madsen, Tanja Kidholm Osmann; Skouboe, Esben Bala; Povey, Bo Ø. Published in: International Journal of Computer Applications in Technology DOI (link to publication from Publisher): Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Gade, R., Moeslund, T. B., Nielsen, S. Z., Skov-Petersen, H., Andersen, H. J., Basselbjerg, K., ... Povey, B. Ø. (2016). Thermal Imaging Systems for Real-Time Applications in Smart Cities. International Journal of Computer General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research." c7742e63579cfea8655606ec6bd9047140efe96a,D and Pseudo-2d Hidden Markov Models for Image Analysis. Theoretical Introduction 1d and Pseudo-2d Hidden Markov Models for Image Analysis. Theoretical Introduction,"D and Pseudo-D Hidden Markov Models for Image Analysis. Theoretical Introduction ephane Marchand-Maillet - Multimedia Communications Email: Phone: + . ... - Fax: + . ... Date: November ,  Technical Report RR- - Part A Condential: No ecom’s research is partially supported by its industrial members: Ascom, Cegetel, France Telecom, Hitachi, IBM France, Motorola, Swisscom, Texas Instruments, and Thomson CSF. Multimedia Communications Institut EURECOM  BP  .   Sophia Antipolis  France T.R. RR- - Part A  November , " c7d7cf88d2e9f3194aec2121eb19dbfed170dba8,Unconstrained Gaze Estimation Using Random Forest Regression Voting,"Unconstrained Gaze Estimation Using Random Forest Regression Voting Amine Kacete, Renaud Séguier, Michel Collobert, Jérôme Royan To cite this version: Amine Kacete, Renaud Séguier, Michel Collobert, Jérôme Royan. Unconstrained Gaze Estimation Using Random Forest Regression Voting. Springer. ACCV 13th Asian Conference on Computer Vision, Nov 2016, Taipei, Taiwan. . HAL Id: hal-01393591 https://hal.archives-ouvertes.fr/hal-01393591 Submitted on 7 Nov 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" c77c094faf7b1a4e293609a0909c7c50b468675a,Satyam: Democratizing Groundtruth for Machine Vision,"SATYAM: DEMOCRATIZING GROUNDTRUTH FOR MACHINE VISION Hang Qiu?, Krishna Chintalapudi†, Ramesh Govindan?" c7de0c85432ad17a284b5b97c4f36c23f506d9d1,RANSAC-Based Training Data Selection for Speaker State Recognition,"INTERSPEECH 2011 RANSAC-based Training Data Selection for Speaker State Recognition Elif Bozkurt1, Engin Erzin1, C¸ i˘gdem Ero˘glu Erdem2, A.Tanju Erdem3 Multimedia, Vision and Graphics Laboratory, Koc¸ University, Istanbul, Turkey Department of Electrical and Electronics Engineering, Bahc¸es¸ehir University, Istanbul, Turkey Department of Electrical and Computer Engineering, ¨Ozye˘gin University, Istanbul, Turkey ebozkurt," c70ad19c90491e2de8de686b6a49f9bbe44692c0,Seeing with Humans: Gaze-Assisted Neural Image Captioning,"Seeing with Humans: Gaze-Assisted Neural Image Captioning Yusuke Sugano and Andreas Bulling" c74a42afeae520ff6ab280d17bccf0d082ba8de5,The Concept of Comprehensive Data Analysis from Ultra-Wideband Subsystem for Smart City Positioning Purposes,"Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 25 October 2018 doi:10.20944/preprints201810.0609.v1 Article The Concept of Comprehensive Data Analysis from Ultra-Wideband Subsystem for Smart City Positioning Purposes Damian Grzechca *, Krzysztof Hanzel and Krzysztof Paszek Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology Gliwice, Poland; * Correspondence: Tel.: +48-32-237-2717" c7c8d150ece08b12e3abdb6224000c07a6ce7d47,DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification,"DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification National Laboratory of Pattern Recognition, CASIA Center for Research on Intelligent Perception and Computing, CASIA Shu Zhang Ran He Tieniu Tan" c737e65d7e8696f5a2878ac623c61aeff434f92d,The influences of face inversion and facial expression on sensitivity to eye contact in high-functioning adults with autism spectrum disorders.,"J Autism Dev Disord (2013) 43:2536–2548 DOI 10.1007/s10803-013-1802-2 O R I G I N A L P A P E R The Influences of Face Inversion and Facial Expression on Sensitivity to Eye Contact in High-Functioning Adults with Autism Spectrum Disorders Mark D. Vida • Daphne Maurer • Andrew J. Calder • Gillian Rhodes • Jennifer A. Walsh • Matthew V. Pachai • M. D. Rutherford Published online: 8 March 2013 Ó Springer Science+Business Media New York 2013" c7fde641178549bbd1860144138bffdc9e800540,Deep CNN Framework for Audio Event Recognition using Weakly Labeled Web Data,"Deep CNN Framework for Audio Event Recognition using Weakly Labeled Web Data Anurag Kumar, Student Member, IEEE, and Bhiksha Raj, Fellow, IEEE" c7ecb2ca791fe23c182a06e7700c4e41f5ffa79d,A Review of Sentiment Analysis in Spanish Una Revisión Sobre el Análisis de Sentimientos en Español,"DOI: http://dx.doi.org/10.18180/tecciencia.2017.22.5 A Review of Sentiment Analysis in Spanish Una Revisión Sobre el Análisis de Sentimientos en Español Carlos Henríquez Miranda1*, Jaime Guzmán2 Universidad Autónoma, Barranquilla, Colombia Universitario Nacional de Colombia, Bogotá, Colombia Received: 11 Dec 2015 Accepted: 6 Sep 2016 Available Online: 7 Dec 2016" 9452d029f5d140aece06619b6fd8e47b070cacd1,Urban classification by pixel and object-based approaches for very high resolution imagery,"FACULTY OF ENGINEERING AND SUSTAINABLE DEVELOPMENT Department of Industrial Development, IT and Land Management Urban classification by pixel and object-based pproaches for very high resolution imagery Fadi Ali Student thesis, Advanced level (Master degree, one year), 15 HE Geomatics Master Programme in Geomatics Supervisor: Dr. Julia Åhlén Examiner: Prof. Dr. Bin Jiang Assistant examiner: Ding Ma" 940ab36a8b2cdf6cb6a08093bd382ad375717942,Human violence recognition and detection in surveillance videos,"Human Violence Recognition and Detection in Surveillance Videos Piotr Bilinski nd Francois Bremond INRIA Sophia Antipolis, STARS team 004 Route des Lucioles, BP93, 06902 Sophia Antipolis, France" 949079cc466e875df1ee6bd6590052ba382a35cf,0 Large-Scale Face Image Retrieval :,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 942bb63e78d9edfe3b8d0a4bf9a3511c736a6930,"Implementing Efficient, Portable Computations for Machine Learning","Implementing Efficient, Portable Computations for Machine Learning Matthew Walter Moskewicz Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2017-37 http://www2.eecs.berkeley.edu/Pubs/TechRpts/2017/EECS-2017-37.html May 9, 2017" 948af4b04b4a9ae4bff2777ffbcb29d5bfeeb494,Face Recognition From Single Sample Per Person by Learning of Generic Discriminant Vectors,"Available online at www.sciencedirect.com Procedia Engineering 41 ( 2012 ) 465 – 472 International Symposium on Robotics and Intelligent Sensors 2012 (IRIS 2012) Face Recognition From Single Sample Per Person by Learning of Generic Discriminant Vectors Fadhlan Hafiza*, Amir A. Shafieb, Yasir Mohd Mustafahb Faculty of Electrical Engineering, University of Technology MARA, Shah Alam, 40450 Selangor, Malaysia Faculty of Engineering, International Islamic University, Jalan Gombak, 53100 Kuala Lumpur, Malaysia" 947c973846f2c5f8f42225c1108810bcdb4a7015,Grounded language understanding for manipulation instructions using GAN-based classification,"GROUNDED LANGUAGE UNDERSTANDING FOR MANIPULATION INSTRUCTIONS USING GAN-BASED CLASSIFICATION Komei Sugiura and Hisashi Kawai National Institute of Information and Communications Technology, Japan" 94a11b601af77f0ad46338afd0fa4ccbab909e82,"Title of dissertation : EFFICIENT SENSING , SUMMARIZATION AND CLASSIFICATION OF VIDEOS", 94eeae23786e128c0635f305ba7eebbb89af0023,On the Emergence of Invariance and Disentangling in Deep Representations,"Journal of Machine Learning Research 18 (2018) 1-34 Submitted 01/17; Revised 4/18; Published 6/18 Emergence of Invariance and Disentanglement in Deep Representations∗ Alessandro Achille Department of Computer Science University of California Los Angeles, CA 90095, USA Stefano Soatto Department of Computer Science University of California Los Angeles, CA 90095, USA Editor: Yoshua Bengio" 9434524669777d281a8a7358f20181c9e157942e,VSEM: An open library for visual semantics representation,"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 187–192, Sofia, Bulgaria, August 4-9 2013. c(cid:13)2013 Association for Computational Linguistics" 942dd0a7f975a3400bd6bf37e3a06bb50e70297c,A Weighted Discrete KNN Method for Mandarin Speech and Emotion Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 944592fcb4ab1d254ea55bd32960b6482556a1e6,The VidTIMIT Database,"The VidTIMIT Database Conrad Sanderson (*) IDIAP–Com 02-06 August 2002 D a l l e M o l l e I n s t i t u t e f o r P e r c e p t u a l A r t i f i c i a l Intelligence • P.O.Box 592 • Martigny • Valais • Switzerland phone +41 − 27 − 721 77 11 +41 − 27 − 721 77 12 e-mail internet http://www.idiap.ch" 943b1b92b5bdee0b5770418c645a4a17bded1ccf,MX-LSTM: Mixing Tracklets and Vislets to Jointly Forecast Trajectories and Head Poses,"MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses Irtiza Hasan1,2, Francesco Setti1, Theodore Tsesmelis1,2,3, Alessio Del Bue3, Fabio Galasso2, and Marco Cristani1 University of Verona (UNIVR) OSRAM GmbH Istituto Italiano di Tecnologia (IIT)" 946a3294007cd69769639cc0ff7a24c07eb9f29c,CAN: Composite Appearance Network and a Novel Evaluation Metric for Person Tracking,"CAN: Composite Appearance Network and a Novel Evaluation Metric for Person Tracking Neeti Narayan, Nishant Sankaran, Srirangaraj Setlur, Senior Member IEEE, and Venu Govindaraju, Life Fellow, IEEE" 948853c269cf97251ba5082db0481ce6f96cf886,Efficient Distributed Training of Vehicle Vision Systems,"Efficient Distributed Training of Vehicle Vision Systems Sung-Li Chiang Xinlei Pan Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2016-195 http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-195.html December 11, 2016" 9499b8367a84fccb3651a95e4391d6e17fd92ec5,Face Recognition Issues in a Border Control Environment,"Face Recognition Issues in a Border Control Environment Marijana Kosmerlj, Tom Fladsrud, Erik Hjelm˚as, and Einar Snekkenes Department of Computer Science and Media Technology NISlab Gjøvik University College P. O. Box 191, N-2802 Gjøvik, Norway" 94686d5df14875ed800a9f710bfa43ba4eb19b75,OCCLUSION HANDLING FOR PEDESTRIAN TRACKING USING PARTIAL OBJECT TEMPLATE-BASED COMPONENT PARTICLE FILTER,"IADIS International Journal on Computer Science and Information Systems Vol. 8, No. 2, pp. 40-50 ISSN: 1646-3692 OCCLUSION HANDLING FOR PEDESTRIAN TRACKING USING PARTIAL OBJECT TEMPLATE-BASED COMPONENT PARTICLE FILTER Daw-Tung Lin. Department of Computer Science and Information Engineering, National Taipei University, Taiwan. Yen-Hsiang Chang. Department of Computer Science and Information Engineering, National Taipei University, Taiwan." 944faf7f14f1bead911aeec30cc80c861442b610,Action Tubelet Detector for Spatio-Temporal Action Localization,"Action Tubelet Detector for Spatio-Temporal Action Localization Vicky Kalogeiton1,2 Philippe Weinzaepfel3 Vittorio Ferrari2 Cordelia Schmid1" 94780b00dc2807ec507ae91500b622ec7a8ddb12,Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector,"Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector Chen Du1,2, Chunheng Wang1, Cunzhao Shi1, Baihua Xiao1 Institute of Automation, Chinese Academy of Sciences(CASIA) University of Chinese Academy of Sciences(UCAS) {duchen2016, chunheng.wang, cunzhao.shi," 940a675de8a48b54bac6b420f551529d2bc53b99,"Advances , Challenges , and Opportunities in Automatic Facial Expression Recognition","Advances, Challenges, and Opportunities in Automatic Facial Expression Recognition Brais Martinez and Michel F. Valstar" 94ded2328a91b678447657b9344a1423ed538374,Tool for Semiautomatic Labeling of Moving Objects in Video Sequences: TSLAB,"Sensors 2015, 15, 15159-15178; doi:10.3390/s150715159 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article Tool for Semiautomatic Labeling of Moving Objects in Video Sequences: TSLAB Carlos Cuevas *, Eva María Yáñez and Narciso García Grupo de Tratamiento de Imágenes, Universidad Politécnica de Madrid (UPM), E-28040 Madrid, Spain; E-Mails: (E.M.Y.); (N.G.) * Author to whom correspondence should be addressed; E-Mail: Tel.: +34-913367353. Academic Editor: Vittorio M.N. Passaro Received: 23 March 2015 / Accepted: 18 June 2015 / Published: 29 June 2015" 9432e1157f252ee626511b2270126436b0e80b73,A set theoretic approach to object-based image restoration,"Image Processing: Algorithms and Systems IV, edited by Edward R. Dougherty, Jaakko T. Astola, Karen O. Egiazarian, Proc. of SPIE-IS&T Electronic Imaging, SPIE Vol. 5672 © 2005 SPIE and IS&T · 0277-786X/05/$15" 940865fc3f7ee5b386c4188c231eb6590db874e9,Security and Surveillance System for Drivers Based on User Profile and learning systems for Face Recognition,"Network Protocols and Algorithms ISSN 1943-3581 015, Vol. 7, No. 1 Security and Surveillance System for Drivers based on User Profile and Learning Systems for Face Recognition Loubna Cherrat Mathematic and Application Laboratory, FSTT of Tangier Tangier (Morocco) Tel: 06-64-43-39-18 E-mail: Mostafa Ezziyyani Mathematic and Application Laboratory, FSTT of Tangier Tangier (Morocco) Tel: 06-61-63-03-01 E-mail: Annas EL Mouden Mathematic and Application Laboratory, FSTT of Tangier Tangier (Morocco) Tel: 06-66-63-73-63 E-mail: Mohammed Hassar Mathematic and Application Laboratory, FSTT of Tangier" 9458642e7645bfd865911140ee8413e2f5f9fcd6,Efficient Multiple People Tracking Using Minimum Cost Arborescences,"Ef‌f‌icient Multiple People Tracking Using Minimum Cost Arborescences Roberto Henschel1, Laura Leal-Taix´e2, Bodo Rosenhahn1 Institut f¨ur Informationsverarbeitung, Leibniz Universit¨at Hannover, Institute of Geodesy and Photogrammetry, ETH Zurich," 947f2d465df60ec49f441f02733edbeb81dde2f2,Fast Object Localization Using a CNN Feature Map Based Multi-Scale Search,"Fast Object Localization Using a CNN Feature Map Based Multi-Scale Search Hyungtae Lee1, Heesung Kwon1, Archith J. Bency2, nd William D. Nothwang1 U.S. Army Research Laboratory, Adelphi, MD, USA University of California, Santa Barbara, CA, USA" 941166547968081463398c9eb041f00eb04304f7,Structure-Preserving Sparse Decomposition for Facial Expression Analysis,"Structure-Preserving Sparse Decomposition for Facial Expression Analysis Sima Taheri, Student Member, IEEE, Qiang Qiu, Student Member, IEEE, and Rama Chellappa, Fellow, IEEE" 947399fef66bd8c536c6f784a0501b34e4e094bf,Towards Recovery of Conditional Vectors from Conditional Generative Adversarial Networks,"Towards Recovery of Conditional Vectors from Conditional Generative Adversarial Networks Sihao Ding Andreas Wallin {sihao.ding," b3e2bd3f89e49833d45c30af7d5c923489b4d5fc,Fast Approximate kNN Graph Construction for High Dimensional Data via Recursive Lanczos Bisection,"Fast Approximate kNN Graph Construction for High Dimensional Data via Recursive Lanczos Bisection∗ Jie Chen† Haw-ren Fang† Yousef Saad† October 2, 2008" b34e7a2218abd5894525a60ed4f106cb9c3dc1e8,UNDERSTANDING GROUNDED LANGUAGE LEARNING AGENTS,"Under review as a conference paper at ICLR 2018 UNDERSTANDING GROUNDED LANGUAGE LEARNING AGENTS Anonymous authors Paper under double-blind review" b308706f194e273e19731711db6986863b2db798,"UAV, do you see me? Establishing mutual attention between an uninstrumented human and an outdoor UAV in flight","UAV, Do You See Me? Establishing Mutual Attention Between an Uninstrumented Human and an Outdoor UAV In Flight Mani Monajjemi, Jake Bruce, Seyed Abbas Sadat, Jens Wawerla and Richard Vaughan∗" b340f275518aa5dd2c3663eed951045a5b8b0ab1,Visual inference of human emotion and behaviour,"Visual Inference of Human Emotion and Behaviour Shaogang Gong Caifeng Shan Tao Xiang Dept of Computer Science Queen Mary College, London Dept of Computer Science Queen Mary College, London Dept of Computer Science Queen Mary College, London England, UK England, UK England, UK" b3d8705d46a1d63b40a76bbcf8822b2e90b3b9ad,Efficient Labelling of Pedestrian Supervisions,"Electronic Letters on Computer Vision and Image Analysis 15(1):77-99, 2016 Efficient Labelling of Pedestrian Supervisions Kyaw Kyaw Htike School of Information Technology, UCSI University, Kuala Lumpur, Malaysia Received 7th Mar 2016; accepted 26th Jun 2016" b3e1e5718bb2313fb888255d63e9f6ad0a2dbdd6,Laser – visual – inertial odometry and mapping with high robustness and low drift,"Received: 10 November 2017 | Revised: 23 March 2018 | Accepted: 9 July 2018 DOI: 10.1002/rob.21809 R E G U L A R A R T I C L E Laser–visual–inertial odometry and mapping with high robustness and low drift Ji Zhang | Sanjiv Singh Kaarta, Inc., Pittsburgh, Pennsylvania Correspondence Ji Zhang, Kaarta, Inc., Pittsburgh, PA 15213. Email:" b34487edb8d47c0101d514b8cb63148d80deee54,Utility of Satellite and Aerial Images for Quantification of Canopy Cover and Infilling Rates of the Invasive Woody Species Honey Mesquite (Prosopis Glandulosa) on Rangeland,"Remote Sens. 2012, 4, 1947-1962; doi:10.3390/rs4071947 OPEN ACCESS ISSN 2072-4292 www.mdpi.com/journal/remotesensing Article Utility of Satellite and Aerial Images for Quantification of Canopy Cover and Infilling Rates of the Invasive Woody Species Honey Mesquite (Prosopis Glandulosa) on Rangeland Mustafa Mirik * and R. James Ansley Texas AgriLife Research, P.O. Box 1658, 11708 Hwy 70 South, Vernon, TX 76385, USA; E-Mail: * Author to whom correspondence should be addressed; E-Mail: Tel.: +1-940-552-9941; Fax: +1-940-552-2317. Received: 9 May 2012; in revised form: 5 June 2012 / Accepted: 25 June 2012 / Published: 29 June 2012" b38e5da11281be44c82d184079d762c9d526ba2e,UNDERSTANDING GROUNDED LANGUAGE LEARNING AGENTS,"Under review as a conference paper at ICLR 2018 UNDERSTANDING GROUNDED LANGUAGE LEARNING AGENTS Anonymous authors Paper under double-blind review" b331ca23aed90394c05f06701f90afd550131fe3,Double regularized matrix factorization for image classification and clustering,"Zhou et al. EURASIP Journal on Image and Video Processing (2018) 2018:49 https://doi.org/10.1186/s13640-018-0287-5 EURASIP Journal on Image nd Video Processing R ES EAR CH Double regularized matrix factorization for image classification and clustering Wei Zhou1* , Chengdong Wu2, Jianzhong Wang3,4, Xiaosheng Yu2 and Yugen Yi5 Open Access" b32f7c045801dea27d58e47917badb5b075ab0cf,Motion and appearance based MultiTask Learning network for autonomous driving,"Motion and appearance based Multi-Task Learning network for autonomous driving Anonymous Author(s) Affiliation Address email" b336f946d34cb427452517f503ada4bbe0181d3c,Diagnosing Error in Temporal Action Detectors,"Diagnosing Error in Temporal Action Detectors Humam Alwassel, Fabian Caba Heilbron, Victor Escorcia, and Bernard Ghanem King Abdullah University of Science and Technology (KAUST), Saudi Arabia http://www.humamalwassel.com/publication/detad/ {humam.alwassel, fabian.caba, victor.escorcia," b3d936c0d82f9b2032949af685a10708c6856d2c,Deep Learning From Noisy Image Labels With Quality Embedding,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Deep Learning from Noisy Image Labels with Quality Embedding Jiangchao Yao, Jiajie Wang, Ivor Tsang, Ya Zhang, Jun Sun, Chengqi Zhang, Rui Zhang" b32631f456397462b3530757f3a73a2ccc362342,Discriminant Tensor Dictionary Learning with Neighbor Uncorrelation for Image Set Based Classification,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) b32cf547a764a4efa475e9c99a72a5db36eeced6,Mimicry of ingroup and outgroup emotional expressions,"UvA-DARE (Digital Academic Repository) Mimicry of ingroup and outgroup emotional expressions Sachisthal, M.S.M.; Sauter, D.A.; Fischer, A.H. Published in: Comprehensive Results in Social Psychology 0.1080/23743603.2017.1298355 Link to publication Citation for published version (APA): Sachisthal, M. S. M., Sauter, D. A., & Fischer, A. H. (2016). Mimicry of ingroup and outgroup emotional expressions. Comprehensive Results in Social Psychology, 1(1-3), 86-105. DOI: 0.1080/23743603.2017.1298355 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Download date: 08 Aug 2018" b31f37fd71b7b45e6fd8978960e271a7db1ee212,DICTING IMAGE ROTATIONS,"Published as a conference paper at ICLR 2018 UNSUPERVISED REPRESENTATION LEARNING BY PRE- DICTING IMAGE ROTATIONS Spyros Gidaris, Praveer Singh, Nikos Komodakis University Paris-Est, LIGM Ecole des Ponts ParisTech" b3f0a87043f7843b79744ec19dc0b93324d055d5,Improvements to Tracking Pedestrians in Video Streams Using a Pre-trained Convolutional Neural Network,"Western University Electronic Thesis and Dissertation Repository August 2016 Improvements to Tracking Pedestrians in Video Streams Using a Pre-trained Convolutional Neural Network Marjan Ramin The University of Western Ontario Supervisor Dr. Jagath Samarabandu The University of Western Ontario Graduate Program in Electrical and Computer Engineering A thesis submitted in partial fulfillment of the requirements for the degree in Master of Engineering Science © Marjan Ramin 2016 Follow this and additional works at: https://ir.lib.uwo.ca/etd Part of the Computer Engineering Commons Recommended Citation Ramin, Marjan, ""Improvements to Tracking Pedestrians in Video Streams Using a Pre-trained Convolutional Neural Network"" (2016). Electronic Thesis and Dissertation Repository. 3886. https://ir.lib.uwo.ca/etd/3886" b3655bcc6f491ae995c652c7f51e1b9b3a36d39c,User authentication based on foot motion,"Noname manuscript No. (will be inserted by the editor) User Authentication Based on Foot Motion Davrondzhon Gafurov, Patrick Bours and Einar Snekkenes Received: date / Accepted: date" b3eb61c3542e0c6bafb4c1acd05cffc0970faa85,Region-Based Image Retrieval Revisited,"Region-Based Image Retrieval Revisited Ryota Hinami (cid:140)e University of Tokyo Yusuke Matsui National Institute of Infomatics National Institute of Infomatics Shin’ichi Satoh" b3f7c772acc8bc42291e09f7a2b081024a172564,"A novel approach for performance parameter estimation of face recognition based on clustering , shape and corner detection","www.ijmer.com Vol. 3, Issue. 5, Sep - Oct. 2013 pp-3225-3230 ISSN: 2249-6645 International Journal of Modern Engineering Research (IJMER) A novel approach for performance parameter estimation of face recognition based on clustering, shape and corner detection .Smt.Minj Salen Kujur , 2.Prof. Prashant Jain, Department of Electronics & Communication Engineering college Jabalpur" b3adc7617dff08d7427142837a326b95d2e83969,A Panoramic View of Performance,"Comp. by: BVijayalakshmi Stage: Galleys ChapterID: 0000883562 Date:27/1/09 Time:17:57:10 Evaluation of Gait Recognition , ZONGYI LIU SUDEEP SARKAR Computer Science and Engineering, University of South Florida, Tampa, FL, USA Amazon.com, Seattle, WA, USA Synonyms Gait recognition; Progress in gait recognition Definition Gait recognition refers to automated vision methods that use video of human gait to recognize or to identify person. Evaluation of gait recognition refers to the enchmarking of progress in the design of gait recog- nition algorithms on standard, common, datasets. Introduction Design of biometric algorithms and evaluation of per- formance goes hand in hand. It is important to con- stantly evaluate and analyze progress being at various levels of biometrics design. This evaluation can be of" b3c60b642a1c64699ed069e3740a0edeabf1922c,Max-Margin Object Detection,"Max-Margin Object Detection Davis E. King" b33b88a5fa5d4f20c24dd0e5f3b3529b7545c9e6,Object Detection in Real Images,"SCHOOL OF COMPUTER ENGINEERING PhD Confirmation Report Object Detection in Real Images Submitted by: Dilip Kumar Prasad Research Student (PhD) School of Computer Engineering E-mail: Supervisor: Dr. Maylor K. H. Leung Associate Professor, School of Computer Engineering E-mail: August 2010" b30bdbad88c72938c476f1ea6827d8b10c300da4,Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos,"Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos Naman Kohli, Student Member, IEEE, Daksha Yadav, Student Member, IEEE, Mayank Vatsa, Senior Member, IEEE, Richa Singh, Senior Member, IEEE, and Afzel Noore, Senior Member, IEEE." b3be6c26e00671fa8b18587409e656d5bbecdcf7,Investigation of multimodal template-free biometric techniques and associated exception handling,"Kent Academic Repository Full text document (pdf) Citation for published version Aldosary, Saad (2015) Investigation of Multimodal Template-Free Biometric Techniques and Associated Exception Handling. Doctor of Philosophy (PhD) thesis, University of Kent. Link to record in KAR http://kar.kent.ac.uk/54805/ Document Version UNSPECIFIED Copyright & reuse Content in the Kent Academic Repository is made available for research purposes. Unless otherwise stated all ontent is protected by copyright and in the absence of an open licence (eg Creative Commons), permissions for further reuse of content should be sought from the publisher, author or other copyright holder. Versions of research The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record. Enquiries For any further enquiries regarding the licence status of this document, please contact: If you believe this document infringes copyright then please contact the KAR admin team with the take-down" b32f15264a50d5619526d80a908b848bbcded5be,J-MOD2: Joint Monocular Obstacle Detection and Depth Estimation,"J-MOD2: Joint Monocular Obstacle Detection and Depth Estimation Michele Mancini1, Gabriele Costante1, Paolo Valigi1 and Thomas A. Ciarfuglia1" b375db63742f8a67c2a7d663f23774aedccc84e5,Brain-Inspired Classroom Occupancy Monitoring on a Low-Power Mobile Platform,"Brain-inspired Classroom Occupancy Monitoring on a Low-Power Mobile Platform Department of Electrical, Electronic and Information Engineering, University of Bologna, Italy Francesco Conti∗, Antonio Pullini† and Luca Benini∗† Integrated Systems Laboratory, ETH Zurich, Switzerland" b348d5c7ac93d1148265284d71234e200c9c5f02,GibbsNet: Iterative Adversarial Inference for Deep Graphical Models,"GibbsNet: Iterative Adversarial Inference for Deep Graphical Models Alex Lamb MILA, Universite de Montreal Yaroslav Ganin MILA, Universite de Montreal R Devon Hjelm MILA, Universite de Montreal Joseph Paul Cohen MILA, Universite de Montreal Institute for Reproducible Research Aaron Courville MILA, Universite de Montreal CIFAR Yoshua Bengio MILA, Universite de Montreal CIFAR" b362b812ececef21100d7a702447fcf5ab6d4715,Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer,"Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer David Berthelot∗ Google Brain Colin Raffel∗ Google Brain Aurko Roy Google Brain Ian Goodfellow Google Brain" b3cbbcf67aea4ae28a01bdc5f0c75580f869d82b,RAPID DETERMINATION OF AGE CLASSIFICATION BY TIMOTHY H BALL A DISSERTATION SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"RAPID DETERMINATION OF AGE CLASSIFICATION TIMOTHY H BALL A DISSERTATION SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY COMPUTER SCIENCE UNIVERSITY OF RHODE ISLAND" b3cb91a08be4117d6efe57251061b62417867de9,Label propagation approach for predicting missing biographic labels in face-based biometric records,"T. Swearingen and A. Ross. ""A label propagation approach for predicting missing biographic labels in A Label Propagation Approach for Predicting Missing Biographic Labels in Face-Based Biometric Records Thomas Swearingen and Arun Ross" 3d8c8acb8c59e9f23f048f44a23f36ffd791cdf5,Visual tracking over multiple temporal scales,"Khan, Muhammad Haris (2015) Visual tracking over multiple temporal scales. PhD thesis, University of Nottingham. Access from the University of Nottingham repository: http://eprints.nottingham.ac.uk/33056/1/Thesis.pdf Copyright and reuse: The Nottingham ePrints service makes this work by researchers of the University of Nottingham available open access under the following conditions. This article is made available under the University of Nottingham End User licence and may e reused according to the conditions of the licence. For more details see: http://eprints.nottingham.ac.uk/end_user_agreement.pdf For more information, please contact" 3d94f81cf4c3a7307e1a976dc6cb7bf38068a381,Data-Dependent Label Distribution Learning for Age Estimation,"Data-Dependent Label Distribution Learning for Age Estimation Zhouzhou He, Xi Li, Zhongfei Zhang, Fei Wu, Xin Geng, Yaqing Zhang, Ming-Hsuan Yang, and Yueting Zhuang" 3dec830b2514e82c714162622b3077966660112f,Statistical Evaluation of Face Recognition Techniques under Variable Environmental Constraints,"International Journal of Statistics and Probability; Vol. 4, No. 4; 2015 ISSN 1927-7032 E-ISSN 1927-7040 Published by Canadian Center of Science and Education Statistical Evaluation of Face Recognition Techniques under Variable Environmental Constraints Louis Asiedu1, Atinuke O. Adebanji2, Francis Oduro3 & Felix O. Mettle4 Department of Statistics, University of Ghana, Legon-Accra, Ghana Department of Mathematics, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana Department of Mathematics, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana Department of Statistics, University of Ghana, Legon-Accra, Ghana Correspondence: Louis Asiedu, Department of Statistics, University of Ghana, Legon-Accra, Ghana. Tel: 33-543-426-707. E-mail: Received: August 1, 2015 Accepted: August 19, 2015 Online Published: October 9, 2015 doi:10.5539/ijsp.v4n4p93 URL: http://dx.doi.org/10.5539/ijsp.v4n4p93" 3daafe6389d877fe15d8823cdf5ac15fd919676f,Human Action Localization with Sparse Spatial Supervision,"Human Action Localization with Sparse Spatial Supervision Philippe Weinzaepfel, Xavier Martin, and Cordelia Schmid, Fellow, IEEE" 3d5187a957cc90f4143e6302786d65dbedf7d9bb,Stacking With Auxiliary Features for Visual Question Answering,"To Appear In Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 2018." 3d3a7225b441d669a0e6133546db4cef18884360,Video Liveness for Citizen Journalism: Attacks and Defenses,The final version of 3dcebd4a1d66313dcd043f71162d677761b07a0d,Local binary pattern domain local appearance face recognition,"Yerel Đkili Örüntü Ortamında Yerel Görünüme Dayalı Yüz Tanıma Local Binary Pattern Domain Local Appearance Face Recognition Hazım K. Ekenel1, Mika Fischer1, Erkin Tekeli2, Rainer Stiefelhagen1, Aytül Erçil2 Institut für Theorestische Informatik, Universität Karlsruhe (TH), Karlsruhe, Germany Faculty of Engineering and Natural Sciences, Sabancı University, Đstanbul, Turkey Özetçe Bu bildiride, ayrık kosinüs dönüşümü tabanlı yerel görünüme dayalı yüz tanıma algoritması ile yüz imgelerinin yerel ikili örüntüye (YĐÖ) dayalı betimlemesini birleştiren hızlı bir yüz tanıma algoritması sunulmuştur. Bu tümleştirmedeki amaç, yerel ikili örüntünün dayanıklı imge betimleme yeteneği ile yrık kosinüs dönüşümünün derli-toplu veri betimleme yeteneğinden yararlanmaktır. Önerilen yaklaşımda, yerel görünümün modellenmesinden önce girdi yüz imgesi yerel ikili örüntü ile betimlenmiştir. Elde edilen YĐÖ betimlemesi, irbirleri ile örtüşmeyen bloklara ayrılmış ve her blok üzerinde yerel özniteliklerin çıkartımı için ayrık kosinüs dönüşümü uygulanmıştır. Çıkartımı yapılan yerel öznitelikler daha sonra arka arkaya eklenerek global öznitelik vektörü oluşturulmuştur. Önerilen algoritma, CMU PIE ve FRGC" 3dba6c86541aad3ec8f54c55d57eca9aa98f4ed2,PAC-Bayesian Majority Vote for Late Classifier Fusion,"PAC-Bayesian Majority Vote for Late Classifier Fusion∗ Aix-Marseille Univ., LIF-QARMA, CNRS, UMR 7279, F-13013, Marseille, France Emilie Morvant St´ephane Ayache Amaury Habrard Univ. of St-Etienne, Lab. Hubert Curien, CNRS, UMR 5516, F-42000, St-Etienne, France May 2, 2014" 3df5e17e87144b1e84b5ab9467bc2c2f233b66c7,Convolutional Architecture Exploration for Action Recognition and Image Classification,"Convolutional Architecture Exploration for Action Recognition and Image Classification JT Turner∗1,2, David Aha1, Leslie Smith1, and Kalyan Moy Gupta2 Knexus Research Corporation; 74 Waterfront Street Suite 310; National Harbor, MD 20745 Navy Center for Applied Research in Artificial Intelligence; Naval Research Laboratory (Code 5514); Washington, DC 20375" 3ddb88f9294e962dfd9c99c5864b2b8690b56d90,Multimodal Image Alignment Through a Multiscale Chain of Neural Networks with Application to Remote Sensing,"Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing Armand Zampieri1, Guillaume Charpiat2, Nicolas Girard1, and Yuliya Tarabalka1 TITANE team, INRIA, Universit´e Cˆote d’Azur, France TAU team, INRIA, LRI, Universit´e Paris-Sud, France" 3d74d4177f5c1444b73221c12f359e858625a691,Composite-ISA Cores : Enabling Multi-ISA Heterogeneity Using a Single ISA,"ISCA 2018 Submission #283 Confidential Draft: DO NOT DISTRIBUTE Composite-ISA Cores: Enabling Multi-ISA Heterogeneity Using a Single ISA" 3df7401906ae315e6aef3b4f13126de64b894a54,Robust learning of discriminative projection for multicategory classification on the Stiefel manifold,"Robust Learning of Discriminative Projection for Multicategory Classification on the Stiefel Manifold Duc-Son Pham and Svetha Venkatesh Dept. of Computing, Curtin University of Technology GPO Box U1987, Perth, WA 6845, Australia" 3d21b7b4f48e614bc2f2b87eb110aa329b7d66d8,Recognizing Human Actions by Using Effective Codebooks and Tracking,"Recognizing Human Actions by using Effective Codebooks and Tracking Lamberto Ballan, Lorenzo Seidenari, Giuseppe Serra, Marco Bertini and Alberto Del Bimbo" 3d91ba69bfbb2ba018419342d279f2d7571530f6,Qualitative Tracking Performance Evaluation without Ground-Truth,"Qualitative Tracking Performance Evaluation without Ground-Truth∗ Dept. of Computer Science and Engineering Dept. of Computer Science and Engineering Jihun Hamm Bohyung Han POSTECH, Korea" 3d88180732d63a4babf3a4b1a82dd7fdf27a7520,"Facial expression, size, and clutter: Inferences from movie structure to emotion judgments and back.","23Attention, Perception, &Psychophysics ISSN 1943-3921Volume 78Number 3 Atten Percept Psychophys (2016)78:891-901DOI 10.3758/s13414-015-1003-5Facial expression, size, and clutter:Inferences from movie structure to emotionjudgments and backJames E. Cutting & Kacie L. Armstrong" 3d67aa108e65e636158abc0f31b703af3d31baa6,Decorrelating Semantic Visual Attributes by Resisting the Urge to Share,"Decorrelating Semantic Visual Attributes by Resisting the Urge Supplementary material for CVPR 2014 submission ID 0824 to Share In this document, we provide supplementary material for our CVPR 2014 submission “Decorrelating Semantic Visual Attributes by Resisting the Urge to Share”(Paper ID 0824). Sec 1 gives additional details for our experi- mental setup (Sec 4 of the paper). Sec 1.1 lists the groups used in all three datasets in our experiments. Sec 1.2 discusses the details of the image descriptors used for each dataset. Sec 2 discusses how attributes are localized for our experiments in Sec 4.1 in the paper. Sec 3 discusses how it is posible to set parameters that generalize well to novel test sets, using only training data. Sec 4 discusses the details of the optimization of our formulation (Eq 4 in the paper). Datasets .1 Groups (see para on Semantic groups in Sec 4 in the paper) Fig 1, 2 and 3 show the attribute groups used in our experiments on the CUB, AwA and aPY datasets respectively. The 28 CUB groups come pre-specified with the dataset [6]. The groups on AwA match exactly the groups specified in [5]. Those on aPY also match the groups outlined in [5] on the 25 attributes (see paper) used in our experiments (aPY-25). In each figure, attribute groups are enclosed in shaded boxes, and phrases in larger font labeling the boxes indicate the rationale for the grouping. .2 Features (see also Sec 3.2 and para on Features in Sec 4 in the paper)" 3da9a9091cfa8f4bf625829faf7a4c35a8fe91e0,Working memory network alterations in high-functioning adolescents with an autism spectrum disorder.,"PDF hosted at the Radboud Repository of the Radboud University Nijmegen The following full text is a publisher's version. For additional information about this publication click this link. http://hdl.handle.net/2066/183247 Please be advised that this information was generated on 2018-05-20 and may be subject to hange." 3db588f1e58c1207685771d8015fa9427d731a53,An automatic 3D expression recognition framework based on sparse representation of conformal images,"An Automatic 3D Expression Recognition Framework based on Sparse Representation of Conformal Images Wei Zeng, Huibin Li, Liming Chen, Jean-Marie Morvan, Xianfeng David Gu" 3d42aedd347f927a6bce28d0fa509c6d2132c11f,3D Hand Pose Detection in Egocentric RGB-D Images,"International Journal of Computer Vision manuscript No. (will be inserted by the editor) D Hand Pose Detection in Egocentric RGB-D Images Gr´egory Rogez · J. S. Supanˇciˇc III · Maryam Khademi · J. M. M. Montiel · Deva Ramanan Received: date / Accepted: date" 3d1382fa43c31e594ed2d84dda9984b1db047b0e,Compositional Memory for Visual Question Answering,"Compositional Memory for Visual Question Answering Aiwen Jiang1,2 Fang Wang2 Fatih Porikli2 Yi Li∗ 2,3 NICTA and ANU {fang.wang, Toyota Research Institute North America feature as the first word to initialize the sequential learning. While the use of holistic approach is straightforward and onvenient, it is, however, debatably problematic. For ex- mple, in the VQA problems many answers are directly re- lated to the contents of some image regions. Therefore, it is dubious if the holistic features are rich enough to provide the information only available at regions. Also, it may hin- der the exploration of finer-grained local features for VQA. In this paper we propose a Compositional Memory for n end-to-end training framework. Our approach takes the dvantage of the recent progresses in image captioning [3, ], natural language processing [5], and computer vision to" 3de3c479164312ab3a1795ee84f20c16632c04c4,Scalable Deep Learning Logo Detection,"Scalable Deep Learning Logo Detection Hang Su∗, Shaogang Gong†, Xiatian Zhu‡ † Queen Mary University of London ‡ Vision Semantics Ltd." 3df26d623b15b2e27a19f5cfef33e36112f07675,"Multiple Sensor Fusion for Detection, Classification and Tracking of Moving Objects in Driving Environments. (Fusion multi-capteur pour la detection, classification et suivi d'objets mobiles en environnement routier)","Multiple Sensor Fusion for Detection, Classification and Tracking of Moving Objects in Driving Environments R. Omar Chavez-Garcia To cite this version: R. Omar Chavez-Garcia. Multiple Sensor Fusion for Detection, Classification and Tracking of Moving Objects in Driving Environments. Robotics [cs.RO]. Université de Grenoble, 2014. English. HAL Id: tel-01082021 https://hal.archives-ouvertes.fr/tel-01082021 Submitted on 12 Nov 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 3dc3f0b64ef80f573e3a5f96e456e52ee980b877,MAXIMUM LIKELIHOOD TRAINING OF THE EMBEDDED HMM FOR FACE DETECTION AND RECOGNITION Ara V. Ne an and Monson H. Hayes III Center for Signal and Image Processing School of Electrical and Computer Engineering,"AXU ED TRAG F TE EBEDDED  FR FACE DETECT AD RECGT Aa V. e(cid:12)a ad  . aye  Cee f Siga ad age ceig Sch f Eecica ad C e Egieeig Gegia i e f Techgy Aaa GA 30332 faa" 3dd4d719b2185f7c7f92cc97f3b5a65990fcd5dd,Ensemble of Hankel Matrices for Face Emotion Recognition,"Ensemble of Hankel Matrices for Face Emotion Recognition Liliana Lo Presti and Marco La Cascia DICGIM, Universit´a degli Studi di Palermo, V.le delle Scienze, Ed. 6, 90128 Palermo, Italy, DRAFT To appear in ICIAP 2015" 3d97f739ae76c8db1146da4aaeb0dc1ef3d31c33,Données multimodales pour l ’ analyse d ’ image,"UNIVERSITÉDEGRENOBLENoattribuéparlabibliothèqueTHÈSEpourobtenirlegradedeDOCTEURDEL’UNIVERSITÉDEGRENOBLESpécialité:MathématiquesetInformatiquepréparéeauLaboratoireJeanKuntzmanndanslecadredel’ÉcoleDoctoraleMathématiques,SciencesetTechnologiesdel’Information,InformatiqueprésentéeetsoutenuepubliquementparMatthieuGuillauminle27septembre2010ExploitingMultimodalDataforImageUnderstandingDonnéesmultimodalespourl’analysed’imageDirecteursdethèse:CordeliaSchmidetJakobVerbeekJURYM.ÉricGaussierUniversitéJosephFourierPrésidentM.AntonioTorralbaMassachusettsInstituteofTechnologyRapporteurMmeTinneTuytelaarsKatholiekeUniversiteitLeuvenRapporteurM.MarkEveringhamUniversityofLeedsExaminateurMmeCordeliaSchmidINRIAGrenobleExaminatriceM.JakobVerbeekINRIAGrenobleExaminateur" 3d42e17266475e5d34a32103d879b13de2366561,The Global Dimensionality of Face Space,"Proc.4thIEEEInt’lConf.AutomaticFace&GestureRecognition,Grenoble,France,pp264–270 The Global Dimensionality of Face Space (cid:3) http://venezia.rockefeller.edu/ The Rockefeller University Penio S. Penev Laboratory of Computational Neuroscience Lawrence Sirovich Laboratory for Applied Mathematics Mount Sinai School of Medicine (cid:13) IEEE2000 230 York Avenue, New York, NY 10021 One Gustave L. Levy Place, New York, NY 10029" 3d7fce66c1880f4b29171e415cfad57d8b96ced2,Exploiting Ambiguities in the Analysis of Cumulative Matching Curves for Person Re-identification, 3dad8d0b5185503b3281bdeda10b9904ea19da50,Using probabilistic graphical models to detect dynamic objects for mobile robots by Daniek Brink,"Using probabilistic graphical models to detect dynamic objects for mobile robots Daniek Brink Dissertation presented for the degree of Doctor of Engineering in the Faculty of Engineering at Stellenbosch University Promoter: Co-promoter: Dr C.E. van Daalen Prof. B.M. Herbst December 2016" 3d5a1be4c1595b4805a35414dfb55716e3bf80d8,Hidden Two-Stream Convolutional Networks for Action Recognition,"Hidden Two-Stream Convolutional Networks for Action Recognition Yi Zhu, Zhenzhong Lan, Shawn Newsam, Alexander G. Hauptmann" 3d740c4f2246ce8e63d0eacc2cc1a5c31259e9ee,Discovering Attribute Shades of Meaning with the Crowd,"http://dx.doi.org/10.1007/s11263-014-0798-1 Discovering Attribute Shades of Meaning with the Crowd Adriana Kovashka · Kristen Grauman Received: date / Accepted: date" 3d5b8127ce57279f9fd77d3a24d8034b485163a4,System ( tm ) for Image and Vision Computing Manuscript Draft Manuscript Number : IMAVIS-D16-00270 R 2 Title : Extended three-dimensional rotation invariant local binary patterns,"Elsevier Editorial System(tm) for Image and Vision Computing Manuscript Draft Manuscript Number: IMAVIS-D-16-00270R2 Title: Extended three-dimensional rotation invariant local binary patterns Article Type: Full Length Article Keywords: Local binary patterns (LBP); Three-dimensions; Rotation invariance; Texture classification Corresponding Author: Mr. Leonardo Citraro, MSc. Corresponding Author's Institution: University of Southampton First Author: Leonardo Citraro, MSc. Order of Authors: Leonardo Citraro, MSc.; Sasan Mahmoodi, Professor, Phd; Angela Darekar, Phd; Brigitte Vollmer, Professor, Phd" 3dc78b41ed926b88c9cc4d40c6c5250bfafad74a,A pilot study for mood-based classification of TV programmes,"Research & Development White Paper WHP 231 September 2012 A Pilot Study for Mood-based Classification of TV Programmes Jana Eggink, Penelope Allen, Denise Bland BRITISH BROADCASTING CORPORATION" 3dffacda086689c1bcb01a8dad4557a4e92b8205,Multiple Object Tracking: A Literature Review,"Multiple Object Tracking: A Literature Review Wenhan Luo, Junliang Xing, Anton Milan, Xiaoqin Zhang, Wei Liu, Xiaowei Zhao and Tae-Kyun Kim" 3dcc51a37f2e5e91d77ff00f18178484c4e938cb,Excitation Dropout: Encouraging Plasticity,"Under review as a conference paper at ICLR 2019 EXCITATION DROPOUT: ENCOURAGING PLASTICITY IN DEEP NEURAL NETWORKS Anonymous authors Paper under double-blind review" 3d85cf942efda695347c7d95485fcd1e6796ee3a,Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy,"Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy Daniel S´aez Trigueros, Li Meng School of Engineering and Technology University of Hertfordshire Hatfield AL10 9AB, UK Margaret Hartnett GBG plc London E14 9QD, UK" 3dbb2ca6942eb49538d92823fe22c7475e866ca1,Institutionen för systemteknik Department of Electrical Engineering Examensarbete Autonomous Morphometrics using Depth Cameras for Object Classification and Identification,"Institutionen för systemteknik Department of Electrical Engineering Examensarbete Autonomous Morphometrics using Depth Cameras for Object Classification and Identification Examensarbete utfört i Datorseende vid Tekniska högskolan vid Linköpings universitet Felix Björkeson LiTH-ISY-EX--13/4680--SE Linköping 2013 Department of Electrical Engineering Linköpings universitet SE-581 83 Linköping, Sweden Linköpings tekniska högskola Linköpings universitet 581 83 Linköping" 3d9d1f8075ebdd03f86b4e40b9a5d08447ade8d3,COMPARISON OF ILLUMINATION NORMALIZATION METHODS FOR FACE RECOGNITION,"COMPARISON OF ILLUMINATION NORMALIZATION METHODS FOR FACE RECOGNITION(cid:3) Mauricio Villegas Santamar·(cid:17)a and Roberto Paredes Palacios Instituto Tecnol·ogico de Inform·atica Universidad Polit·ecnica de Valencia Camino de Vera s/n, 46022 Valencia (Spain)" ef5531711a69ed687637c48930261769465457f0,Studio2Shop: from studio photo shoots to fashion articles,"Studio2Shop: from studio photo shoots to fashion articles Julia Lasserre1, Katharina Rasch1 and Roland Vollgraf Zalando Research, Muehlenstr. 25, 10243 Berlin, Germany Keywords: omputer vision, deep learning, fashion, item recognition, street-to-shop" ef73e91b47c0043febed130896f610982fb89976,Layer-Structured 3D Scene Inference via View Synthesis,"Layer-structured 3D Scene Inference via View Synthesis Shubham Tulsiani1∗, Richard Tucker2, Noah Snavely2 University of California, Berkeley 2Google" ef75007cd6e5b990d09e7f3c4ba119be6c2546fb,Lecture 20: Object Recognition 20.1 Introduction 20.2.1 Neocognitron,"Chapter 20 Lecture 20: Object recognition 0.1 Introduction In its simplest form, the problem of recognition is posed as a binary classification task, namely distin- guishing between a single object class and background class. Such a classification task can be turned into a detector by sliding it across the image (or image pyramid), and classifying each local window. Classifier based methods have defined their own family of object models. Driven by advances in machine learning, a common practice became to through a bunch of features into the last published lgorithm. However, soon became clear that such an approach, in which the research gave up into trying to have a well defined physical model of the object, hold a lot of promise. In many cases, the use of a specific classifier has driven the choice of the object representation and not the contrary. In classifier- ased models, the preferred representations are driven by efficiency constraints and by the characteristics of the classifier (e.g., additive models, SVMs, neural networks, etc.). 0.2 Neural networks Although neural networks can be trained in other settings than a purely discriminative framework, some of the first classifier based approaches used neural networks to build the classification function. Many urrent approaches, despite of having a different inspiration, still follow an architecture motivated by neural networks. 0.2.1 Neocognitron The Neocognitron, developed by Fukushima in the 80 [8], consisted on a multilayered network with" ef52f1e2b52fd84a7e22226ed67132c6ce47b829,Online Eye Status Detection in the Wild with Convolutional Neural Networks, ef2084979a3191403c1b8b48f503d06f346afb8f,Une méthode de reconnaissance des expressions du visage basée sur la perception,"Une m´ethode de reconnaissance des expressions du visage bas´ee sur la perception Rizwan Khan, Alexandre Meyer, Hubert Konik, Saida Bouakaz To cite this version: Rizwan Khan, Alexandre Meyer, Hubert Konik, Saida Bouakaz. Une m´ethode de reconnais- sance des expressions du visage bas´ee sur la perception. RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Jan 2012, Lyon, France. pp.978-2-9539515-2-3, 2012. HAL Id: hal-00660976 https://hal.archives-ouvertes.fr/hal-00660976 Submitted on 19 Jan 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," ef247c194162f76eb8d44b1f83c25a4002ab69a6,An Effective Profile Based Video Browsing System for e-Learning.,"An Effective Profile Based Video Browsing System for e- Learning S. C. Premaratne, D. D. Karunaratna and K. P. Hewagamage University of Colombo School of Computing, Sri Lanka" ef48f1d8ec88dabbf7253cb1c8a224cb95f604af,Survey on Video Analysis of Human Walking Motion,"International Journal of Signal Processing, Image Processing and Pattern Recognition Vol.7, No.3 (2014), pp.99-122 http://dx.doi.org/10.14257/ijsip.2014.7.3.10 Survey on Video Analysis of Human Walking Motion S. Nissi Paul and Y. Jayanta Singh Dept. Computer Science Engineering and information Technology Don Boco College of Engineering and Technology, Assam Don Bosco University Guwahati, Assam - India" ef42f6584d696513605b424752bd9fed6ed98fa0,Facial Motion Analysis using Clustered Shortest Path Tree Registration,"Author manuscript, published in ""The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA’08, Marseille : France (2008)""" ef4b5bcaad4c36d7baa7bc166bd1712634c7ad71,Towards Spatio-temporal Face Alignment in Unconstrained Conditions, ef999ab2f7b37f46445a3457bf6c0f5fd7b5689d,Improving face verification in photo albums by combining facial recognition and metadata with cross-matching,"Calhoun: The NPS Institutional Archive DSpace Repository Theses and Dissertations . Thesis and Dissertation Collection, all items 017-12 Improving face verification in photo albums by ombining facial recognition and metadata with cross-matching Bouthour, Khoubeib Monterey, California: Naval Postgraduate School http://hdl.handle.net/10945/56868 Downloaded from NPS Archive: Calhoun" effd46389bc45dfdbf32f00eddeef6cf5f0f7947,Face Verification Using Kernel Principle Component Analysis,"International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181 Vol. 2 Issue 1, January- 2013 Face Verification Using Kernel Principle Component Analysis Manjupriya, U.G Student, Dept. of ECE Chithra. C .K U.G Student, Dept. of ECE Divya. M U.G Student, Dept. of ECE Karthikeyan.V Assistant Professor, Dept. of ECE" efa65394d0ec5a16ecd57075951016502c541c0d,The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers,"The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers Dongxiang Zhang, Lei Wang, Nuo Xu, Bing Tian Dai and Heng Tao Shen" efd308393b573e5410455960fe551160e1525f49,Tracking Persons-of-Interest via Unsupervised Representation Adaptation,"Tracking Persons-of-Interest via Unsupervised Representation Adaptation Shun Zhang, Jia-Bin Huang, Jongwoo Lim, Yihong Gong, Jinjun Wang, Narendra Ahuja, and Ming-Hsuan Yang" ef3ccf4c7d4b240ad0fbcc29f4e6be9334db9a18,IJERA ) ISSN : 2248-9622 Recent Trends in Mobile & Cloud Computing ( NCRMC-08,"International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 Recent Trends in Mobile & Cloud Computing (NCRMC- 08th & 09th October 2015) RESEARCH ARTICLE OPEN ACCESS Emotion recognition from geometric facial patterns Krupali Joshi, Pradeep Narwade Electronics and Telecommunication, Ksiet, Hingoli, (M S) India Email- Email–" efe208a03e2f75ddcebf8bb0f10b1c0bea4824be,A data set for evaluating the performance of multi-class multi-object video tracking,"A data set for evaluating the performance of multi-class multi-object video tracking Avishek Chakrabortya, Victor Stamatescua, Sebastien C. Wongb, Grant Wigleya, David Kearneya Computational Learning Systems Laboratory, School of Information Technology and Mathematical Sciences, University of South Australia, Mawson Lakes, SA, Australia; bDefence Science and Technology Group, Edinburgh, SA, Australia" efbe52289f71eca9a0aaa8a5362f73334fa6b23c,EAI Endorsed Transactions on Context-aware Systems and Applications,"EAI Endorsed Transactions on Context-aware Systems and Applications Research Article Face recognition based on LDA in manifold subspace Hung Phuoc Truong1, Tue-Minh Dinh Vo1 and Thai Hoang Le1, * Faculty of Information Technology, University of Science – Vietnam National University Ho Chi Minh city, 227 Nguyen Van Cu street, HCMc, Vietnam" efa08283656714911acff2d5022f26904e451113,Active Object Localization in Visual Situations,"Active Object Localization in Visual Situations Max H. Quinn, Anthony D. Rhodes, and Melanie Mitchell" efef00465e1b2f4003e838e50f9c8fa1c8ffaf3e,SceneNet: A Perceptual Ontology for Scene Understanding,"SceneNet: A Perceptual Ontology for Scene Understanding Ilan Kadar and Ohad Ben-Shahar Ben-Gurion University of the Negev" ef61e43a1cce95afdc0696879085e834b981d5de,Real time multi-object tracking using multiple cameras Semester Project,"CVLab: Computer Vision Laboratory School of Computer and Communication Sciences Ecole Polytechnique Fédérale de Lausanne http://cvlab.epfl.ch/ Real time multi-object tracking using multiple cameras Semester Project Michalis Zervos Supervisor Professor Pascal Fua Teaching Assistant Horesh Ben Shitrit Spring Semester June 2012" ef4ecb76413a05c96eac4c743d2c2a3886f2ae07,Modeling the importance of faces in natural images,"Modeling the Importance of Faces in Natural Images Jin B.a, Yildirim G.a, Lau C.a, Shaji A.a, Ortiz Segovia M.b and S¨usstrunk S.a EPFL, Lausanne, Switzerland; Oc´e, Paris, France" ef032afa4bdb18b328ffcc60e2dc5229cc1939bc,Attribute-enhanced metric learning for face retrieval,"Fang and Yuan EURASIP Journal on Image and Video Processing (2018) 2018:44 https://doi.org/10.1186/s13640-018-0282-x EURASIP Journal on Image nd Video Processing RESEARCH Open Access Attribute-enhanced metric learning for face retrieval Yuchun Fang* nd Qiulong Yuan" ef230e3df720abf2983ba6b347c9d46283e4b690,QUIS-CAMPI: an annotated multi-biometrics data feed from surveillance scenarios,"Page 1 of 20 QUIS-CAMPI: An Annotated Multi-biometrics Data Feed From Surveillance Scenarios João Neves1,*, Juan Moreno2, Hugo Proença3 IT - Instituto de Telecomunicações, University of Beira Interior Department of Computer Science, University of Beira Interior IT - Instituto de Telecomunicações, University of Beira Interior" ef66ed8d8db41f67048d077fd4b772c8ba748090,Reservoir Computing Hardware with Cellular Automata,"Reservoir Computing Hardware with Cellular Automata Alejandro Mor´an, Christiam F. Frasser and Josep L. Rossell´o Electronic Engineering Group, Physics Department, Universitat de les Illes Balears, Spain. E-mail: June 22, 2018" ef473c96dde98e2015b2d135a17a2d734319649a,Playlist Generation using Facial Expression Analysis and Task Extraction,"Pobrane z czasopisma Annales AI- Informatica http://ai.annales.umcs.pl Data: 04/05/2018 16:53:32 U M CS" 97692960a11d4316880fb229cca699293e133945,An efficient multi-resolution SVM network approach for object detection in aerial images,"015 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 17–20, 2015, BOSTON, USA AN EFFICIENT MULTI-RESOLUTION SVM NETWORK APPROACH FOR OBJECT DETECTION IN AERIAL IMAGES J. Pasquet(cid:63)† M. Chaumont∗† G. Subsol † M. Derras(cid:63) LIRMM, Universit´e de Montpellier / CNRS, France (cid:63) Berger Levrault, Lab`ege, France Universit´e de Nˆımes, France" 97b8249914e6b4f8757d22da51e8347995a40637,"Large-Scale Vehicle Detection, Indexing, and Search in Urban Surveillance Videos","Large-Scale Vehicle Detection, Indexing, nd Search in Urban Surveillance Videos Rogerio Schmidt Feris, Associate Member, IEEE, Behjat Siddiquie, James Petterson, Yun Zhai, Associate Member, IEEE, Ankur Datta, Lisa M. Brown, Senior Member, IEEE, and Sharath Pankanti, Fellow, IEEE" 978c6e9c01dd6fa64dd0e357bc750345b06ff6bb,Query-Driven Approach to Face Clustering and Tagging,"Query-Driven Approach to Face Clustering and Tagging Liyan Zhang, Xikui Wang, Dmitri V. Kalashnikov, Sharad Mehrotra, and Deva Ramanan" 979f63114a30d60c5c06d4c9c18c8249c3a63099,Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations,"Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations Jonathan Tremblay Thang To Artem Molchanov† Stephen Tyree Jan Kautz Stan Birchfield" 97d9c57576a573955c1b21b63f5b5ae44438e973,Human Action Recognition Based Sparse Representation, 97a25752c91538ae0d9d1f5db5ae97e2719b528f,Finding the traces of behavioral and cognitive processes in big data and naturally occurring datasets,"Behav Res DOI 10.3758/s13428-017-0874-x Finding the traces of behavioral and cognitive processes in big data and naturally occurring datasets Alexandra Paxton 1,2 & Thomas L. Griffiths 1,3 # The Author(s) 2017. This article is an open access publication" 97a0aba4e9a95db17c3d4367f59aad1f02e04b55,How far did we get in face spoofing detection?,"This manuscript is a preprint version. The final version of this paper is vailable in Engineering Applications of Artificial Intelligence, vol. 72, pp. 368-381, 2018. DOI: 10.1016/j.engappai.2018.04.013 How far did we get in face spoofing detection? Luiz Souza, Luciano Oliveira, Mauricio Pamplona IVISION Lab, Federal University of Bahia Joao Papa RECOGNA Lab, S˜ao Paulo State University" 97ede92a6a3579f9fc8ad7c179eaaf37b3966e5a,Bicycle tracking using ellipse extraction,"Bicycle Tracking Using Ellipse Extraction Tohid Ardeshiri, Fredrik Larsson, Fredrik Gustafsson, Thomas B. Sch¨on, Michael Felsberg Department of Electrical Engineering Link¨oping University Link¨oping, Sweden e-mail: {tohid, larsson, fredrik, schon," 9755554b13103df634f9b1ef50a147dd02eab02f,How Transferable Are CNN-Based Features for Age and Gender Classification?,"How Transferable are CNN-based Features for Age and Gender Classification? Gökhan Özbulak1, Yusuf Aytar2 and Hazım Kemal Ekenel1" 970e571305ed9dde9308e559694044e204d6e2ad,Learning Finer-class Networks for Universal Representations,"GIRARD ET AL.: FINER-CLASS NETWORKS Learning Finer-class Networks for Universal Representations Julien Girard12 Youssef Tamaazousti123 Hervé Le Borgne2 Céline Hudelot3 Both authors contributed equally. CEA LIST Vision Laboratory, Gif-sur-Yvette, France. CentraleSupélec, MICS Laboratory, Châtenay-Malabry, France." 973e3d9bc0879210c9fad145a902afca07370b86,From Emotion Recognition to Website Customizations,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 7, No. 7, 2016 From Emotion Recognition to Website Customizations O.B. Efremides School of Web Media Bahrain Polytechnic Isa Town, Kingdom of Bahrain" 97865d31b5e771cf4162bc9eae7de6991ceb8bbf,Face and Gender Classification in Crowd Video,"Face and Gender Classification in Crowd Video Priyanka Verma IIIT-D-MTech-CS-GEN-13-100 July 16, 2015 Indraprastha Institute of Information Technology New Delhi Thesis Advisors Dr. Richa Singh Dr. Mayank Vatsa Submitted in partial fulfillment of the requirements for the Degree of M.Tech. in Computer Science (cid:13) Verma, 2015 Keywords : Face Recognition, Gender Classification, Crowd database" 9728c3e32f57b54dea94fa9737c8f300de5cc468,Imbalanced Malware Images Classification: a CNN based Approach,"Imbalanced Malware Images Classification: a CNN ased Approach Songqing Yue University of Wisconsin" 9715aba0688195b2019d510ae3fd8da2e40f6e20,Evaluation of color spaces for person re-identification,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-1-6 ©2012 IAPR" 97bcf007516cb70d8cb17b7de6452aa06c4b9c76,GABAergic neurotransmission alterations in autism spectrum disorders,"Neurotransmitter 2015; 2: e1052. doi: 10.14800/nt.1052; © 2015 by Carla V Sesarini http://www.smartscitech.com/index.php/nt REVIEW GABAergic neurotransmission alterations in autism spectrum disorders Carla V Sesarini Instituto de Ciencias Básicas y Medicina Experimental (ICBME), Instituto Universitario del Hospital Italiano de Buenos Aires (HIBA), Potosi 4240 (C1199ACL), CABA, Argentina Correspondence: Carla V Sesarini E-mail: Received: October 04, 2015 Published online: November 09, 2015 Autism spectrum disorders (ASDs) are a group of complex disorders of neurodevelopment characterized by difficulties in social interaction, verbal and nonverbal communication, and repetitive behaviors. In ASD, deficits in social cognition and related cognitive functions would be the resultant of reduced synchronization between rain regions. A possible explanation for ASDs is the disturbance of the delicate balance between excitation and inhibition in the developing brain which may have profound impact in neurobehavioral phenotypes. At least some forms of autism would be caused by a disproportionately high level of excitation (or weaker inhibition) in neural circuits that mediate language and social behavior (local circuits). A more excitable cortex (more weakly inhibited) is functionally more poorly differentiated and could lead to broad ranging abnormalities in" 97e6633c9865dba296a36a5e80e3d66109b43b0c,New learning paradigms for real-world environment perception,"New learning paradigms for real-world environment perception Alexander Gepperth To cite this version: Alexander Gepperth. New learning paradigms for real-world environment perception. Machine Learn- ing [cs.LG]. Université Pierre Marie Curie, 2016. HAL Id: tel-01418147 https://hal.archives-ouvertes.fr/tel-01418147 Submitted on 16 Dec 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 97104def2b92b430c02f595d7802f9ba23b74cc7,DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery,"DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery Junming Zhang1, Katherine A. Skinner2, Ram Vasudevan3 and Matthew Johnson-Roberson4" 97e7810f21a145caddc7e5168b59f0ab8894f669,Technical Report : Learning to Rank using High-Order Information,"Technical Report: Learning to Rank using High-Order Information Puneet K. Dokania1, Aseem Behl2, C. V. Jawahar2, and M. Pawan Kumar1 Ecole Centrale de Paris1, INRIA Saclay1, IIIT Hyderabad - India2" 97cf04eaf1fc0ac4de0f5ad4a510d57ce12544f5,"Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond","manuscript No. (will be inserted by the editor) Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond Dimitrios Kollias (cid:63) · Panagiotis Tzirakis † · Mihalis A. Nicolaou ∗ · Athanasios Papaioannou(cid:107) · Guoying Zhao1 · Bj¨orn Schuller2 · Irene Kotsia3 · Stefanos Zafeiriou4" 9709d362a15414b062efa9cf4a212469af803a7a,Holistic Multi-modal Memory Network for Movie Question Answering,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Holistic Multi-modal Memory Network for Movie Question Answering Anran Wang, Anh Tuan Luu, Chuan-Sheng Foo, Hongyuan Zhu, Yi Tay, Vijay Chandrasekhar" 970e723404885e94e77780766b39ee951dd7abb3,Multimodal Learning of Geometry-Preserving Binary Codes for Semantic Image Retrieval,"IEICE TRANS. INF. & SYST., VOL.E100–D, NO.4 APRIL 2017 INVITED PAPER SpecialSectiononAward-winningPapers Multimodal Learning of Geometry-Preserving Binary Codes for Semantic Image Retrieval Go IRIE†a), Hiroyuki ARAI†, Members, and Yukinobu TANIGUCHI††, Senior Member SUMMARY This paper presents an unsupervised approach to feature inary coding for ef‌f‌icient semantic image retrieval. Although the majority of the existing methods aim to preserve neighborhood structures of the fea- ture space, semantically similar images are not always in such neighbors ut are rather distributed in non-linear low-dimensional manifolds. More- over, images are rarely alone on the Internet and are often surrounded by text data such as tags, attributes, and captions, which tend to carry rich se- mantic information about the images. On the basis of these observations, the approach presented in this paper aims at learning binary codes for se- mantic image retrieval using multimodal information sources while pre- serving the essential low-dimensional structures of the data distributions in the Hamming space. Specifically, after finding the low-dimensional struc- tures of the data by using an unsupervised sparse coding technique, our pproach learns a set of linear projections for binary coding by solving an" 9782c3827fb5563e6230e8c3bd72dc456a557da6,Colour Spaces Study for Skin Colour Detection in Face Recognition Systems,"COLOUR SPACES STUDY FOR SKIN COLOUR DETECTION IN FACE RECOGNITION SYSTEMS Jose M. Chaves-González, Miguel A. Vega-Rodríguez Juan A. Gómez-Pulido and Juan M. Sánchez-Pérez Univ. Extremadura, Dept. Technologies of Computers and Communications, Escuela Politécnica, Campus Universitario s/n, 10071, Cáceres,Spain Keywords: Face detection, colour spaces, YUV, YIQ, RGB, YCbCr, HSV, skin colour detection." 9729ff547b6882b49898c1f5abb69646edf77e71,Two Kinds of Statistics for Better Face Recognition,"Two Kinds of Statistics for Better Face Recognition Manuel Günther, Marco K. Müller and Rolf P. Würtz Institut für Neuroinformatik, Ruhr-Universität, 44780 Bochum, Germany" 97470d68743f338070f32fbb75b7c8a3cb4c045d,Combining experts for improved face verification performance *,"Combining experts for improved face verification performance* Vitomir Štruc, France Mihelič, Nikola Pavešić Fakulteta za elektrotehniko, Univerza v Ljubljani Tržaška 25, 1000 Ljubljana, Slovenija Večmodalni pristop k razpoznavanju obrazov Samodejno razpoznavanje (avtentikacija/identifikacija) obrazov predstavlja eno najaktivnejših raziskovalnih področij biometrije. Avtentikacija oz. identifikacija oseb razpoznavanjem obrazov ponuja možen način povečanja varnosti pri različnih dejavnostih, (npr. pri elektronskem poslovanju na medmrežju, pri bančnih storitvah ali pri vstopu v določene prostore, stavbe in države). Ponuja univerzalen in nevsiljiv način razpoznavanja oseb, ki pa trenutno še ni dovolj zanesljiv. Kot možna rešitev problema zanesljivosti razpoznavanja se v literaturi vse pogosteje pojavljajo večmodalni pristopi, v katerih se razpoznavanje izvede na podlagi večjega števila postopkov razpoznavanja" 9794d69194ac772c3e92ee1f322a36feb3c16239,HAUSDORFF ARTMAP FOR HUMAN FACE RECOGNITION,"HAUSDORFF ARTMAP FOR HUMAN FACE RECOGNITION ARIT THAMMANO AND CHONGKOLNEE RUNGRUANG Faculty of Information Technology King Mongkut’s Institute of Technology Ladkrabang, Bangkok, 10520 Thailand later received identification has encompasses ll of" 9727c74a09aad74abd67ff1d2dff083cc73d4a2e,Visual Focus of Attention in Non-calibrated Environments using Gaze Estimation,"Int J Comput Vis DOI 10.1007/s11263-013-0691-3 Visual Focus of Attention in Non-calibrated Environments using Gaze Estimation Stylianos Asteriadis · Kostas Karpouzis · Stefanos Kollias Received: 24 May 2012 / Accepted: 2 December 2013 © Springer Science+Business Media New York 2013" 97032b13f1371c8a813802ade7558e816d25c73f,Total Recall Final Report,"Total Recall Final Report Peter Collingbourne, Nakul Durve, Khilan Gudka, Steve Lovegrove, Jiefei Ma, Sadegh Shahrbaf Supervisor: Professor Duncan Gillies January 11, 2006" 9717bd66ad50aedabaea0f3af784c7ba9643b686,TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation,"TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation Stefano Alletto*, Davide Abati, Simone Calderara, Rita Cucchiara University of Modena and Reggio Emilia Via P. Vivarelli 10, Modena, Italy Luca Rigazio* Panasonic Silicon Valley Laboratory 0900 North Tantau Avenue, Suite 200, Cupertino, CA, USA" 5da139fc43216c86d779938d1c219b950dd82a4c,A Generalized Multiple Instance Learning Algorithm for Iterative Distillation and Cross-Granular Propagation of Video Annotations,"-4244-1437-7/07/$20.00 ©2007 IEEE II - 205 ICIP 2007" 5d7f8eb73b6a84eb1d27d1138965eb7aef7ba5cf,Robust Registration of Dynamic Facial Sequences,"Robust Registration of Dynamic Facial Sequences Evangelos Sariyanidi, Hatice Gunes, and Andrea Cavallaro" 5dcfb84ab3f5d5f1dd02f59e45154c9710de97b2,On the Latent Variable Interpretation in Sum-Product Networks,"On the Latent Variable Interpretation in Sum-Product Networks Robert Peharz, Robert Gens, Franz Pernkopf, Senior Member, IEEE, and Pedro Domingos" 5d233e6f23b1c306cf62af49ce66faac2078f967,Optimal Geometrical Set for Automated Marker Placement to Virtualized Real-Time Facial Emotions,"RESEARCH ARTICLE Optimal Geometrical Set for Automated Marker Placement to Virtualized Real-Time Facial Emotions Vasanthan Maruthapillai, Murugappan Murugappan* School of Mechatronic Engineering, Universiti Malaysia Perlis, 02600, Ulu Pauh, Arau, Perlis, West Malaysia" 5d09d5257139b563bd3149cfd5e6f9eae3c34776,Pattern recognition with composite correlation fi lters designed with multi-objective combinatorial optimization,"Optics Communications 338 (2015) 77–89 Contents lists available at ScienceDirect Optics Communications journal homepage: www.elsevier.com/locate/optcom Pattern recognition with composite correlation filters designed with multi-objective combinatorial optimization Victor H. Diaz-Ramirez a,n, Andres Cuevas a, Vitaly Kober b, Leonardo Trujillo c, Abdul Awwal d Instituto Politécnico Nacional – CITEDI, Ave. del Parque 1310, Mesade Otay, Tijuana B.C. 22510, México Department of Computer Science, CICESE, Carretera Ensenada-Tijuana 3918, Ensenada B.C. 22860, México Instituto Tecnológico de Tijuana, Blvd. Industrial y Ave. ITR TijuanaS/N, Mesa de Otay, Tijuana B.C. 22500, México d National Ignition Facility, Lawrence Livermore National Laboratory, Livermore, CA 94551, USA r t i c l e i n f o b s t r a c t Article history: Received 12 July 2014 Accepted 16 November 2014 Available online 23 October 2014 Keywords: Object recognition" 5df11c59e3b47189486445f5833675bf08359bfe,Influence of Image Classification Accuracy on Saliency Map Estimation,"IET Research Journals Brief Paper Influence of Image Classification Accuracy on Saliency Map Estimation Taiki Oyama1 Takao Yamanaka1 Department of Information & Communication Sciences, Sophia University, 7-1 Kioi-cho, Chiyoda-ku, Tokyo, 102-0094, Japan * E-mail: ISSN 1751-8644 doi: 0000000000 www.ietdl.org" 5d80149e005894ab57f47e667f3e060e247d8e43,Lip reading using CNN and LSTM,"Lip reading using CNN and LSTM Amit Garg Jonathan Noyola Sameep Bagadia" 5d165ff5b0b389e32809c17838a2afc218a91d62,Object Detectors Emerge in Deep Scene CNNs,"Published as a conference paper at ICLR 2015 OBJECT DETECTORS EMERGE IN DEEP SCENE CNNS Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Computer Science and Artificial Intelligence Laboratory, MIT" 5d25caad6e551ca7b39c66f1f79998bfe6c71ceb,5 D Facial Analysis via Bio-Inspired Active Appearance Model and Support Vector Machine for Forensic Application,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 8, No.7, 2017 .5 D Facial Analysis via Bio-Inspired Active Appearance Model and Support Vector Machine for Forensic Application Siti Norul Huda Sheikh Abdullah Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bandar Baru Bangi, Malaysia Mohammed Hasan Abdulameer Department of Computer Science, Faculty of Education for Women, University of Kufa, Nazri Ahmad Zamani Digital Forensics lab, CyberSecurity Malaysia, Seri Kembangan, Malaysia Khairul Akram Zainol Ariffin" 5d90f06bb70a0a3dced62413346235c02b1aa086,Learning Multiple Layers of Features from Tiny Images,"Learning Multiple Layers of Features from Tiny Images Alex Krizhevsky April 8, 2009" 5da740682f080a70a30dc46b0fc66616884463ec,Real-Time Head Pose Estimation Using Multi-variate RVM on Faces in the Wild,"Real-Time Head Pose Estimation Using Multi-Variate RVM on Faces in the Wild Mohamed Selim, Alain Pagani, Didier Stricker Augmented Vision Research Group, German Research Center for Artificial Intelligence (DFKI), Tripstaddterstr. 122, 67663 Kaiserslautern, Germany Technical University of Kaiserslautern http://www.av.dfki.de" 5db46dda9f0f08220d49a5db1204f149bd4f6a4a,Engaging Image Captioning Via Personality,"ENGAGING IMAGE CAPTIONING VIA PERSONALITY Kurt Shuster, Samuel Humeau, Hexiang Hu, Antoine Bordes, Jason Weston Facebook AI Research" 5d1608e03ab9c529d0b05631f9d2a3afcbf1c3e3,Sparsity and Robustness in Face Recognition,"Sparsity and Robustness in Face Recognition John Wright, Arvind Ganesh, Allen Yang, Zihan Zhou, and Yi Ma Background. This note concerns the use of techniques for sparse signal representation and sparse from the paper [WYG+09], which showed how, under certain technical conditions, one could cast the face recognition problem as one of seeking a sparse representation of a given input face image in terms of a “dictionary” of training images and images of individual pixels. To be more precise, the method of [WYG+09] assumes access to a suf‌f‌icient number of well-aligned training images of each of the k subjects. These images are stacked as the columns of matrices A1, . . . , Ak. Given a new test image y, also well aligned, but possibly subject to illumination variation or occlusion, the method of [WYG+09] seeks to represent y as a sparse linear combination of the database as whole. Writing A = [A1 | ··· | Ak], this approach solves (cid:107)x(cid:107)1 + (cid:107)e(cid:107)1 subj. to Ax + e = y. minimize the identity of the test image y the index whose sparse coef‌f‌icients minimize the residual: ˆi = arg min (cid:107)y − Aixi − e(cid:107)2. This approach demonstrated successful results in laboratory settings (fixed pose, varying illumi- nation, moderate occlusion) in [WYG+09], and was extended to more realistic settings (involving moderate pose and misalignemnt) in [WWG+11]. For the sake of clarity, we repeat the above" 5dc60d250e648f96a799db986a336ad344577405,SIFTing the Relevant from the Irrelevant: Automatically Detecting Objects in Training Images,"SIFTing the Relevant from the Irrelevant: Automatically Detecting Objects in Training Images Edmond Zhang, Michael Mayo Department of Computer Science The University of Waikato Hamilton, New Zealand {ez1," 5d7f9e1463b596eb5d77865a8b1a0e149215303b,A Hidden Markov Model-based Approach for Face Detection and Recognition a Hidden Markov Model-based Approach for Face Detection and Recognition,"AHiddenMarkovModel-BasedApproach forFaceDetectionandRecognition ATHESIS Presentedto TheAcademicFaculty AraNe(cid:12)an InPartialFul(cid:12)llment oftheRequirementsfortheDegreeof DoctorofPhilosophyinElectricalEngineering GeorgiaInstituteofTechnology August," 5d4af8c9321168f9ba7a501f33fb019fa2deaa22,Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems,"Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems Svetlana Kiritchenko and Saif M. Mohammad National Research Council Canada" 5da0224590d91defe8c75db0ab5e12d50b6ab6f3,NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems,"NMTPY: A FLEXIBLE TOOLKIT FOR ADVANCED NEURAL MACHINE TRANSLATION SYSTEMS Ozan Caglayan, Mercedes García-Martínez, Adrien Bardet, Walid Aransa, Fethi Bougares, Loïc Barrault Laboratoire d’Informatique de l’Université du Maine (LIUM) Language and Speech Technology (LST) Team Le Mans, France" 5d04bd7104f08f7fb91967613ffc519c27641e99,Bound to Lose: Physical Incapacitation Increases the Conceptualized Size of an Antagonist in Men,"Bound to Lose: Physical Incapacitation Increases the Conceptualized Size of an Antagonist in Men Daniel M. T. Fessler*, Colin Holbrook Department of Anthropology and Center for Behavior, Evolution, and Culture, University of California Los Angeles, Los Angeles, California, United States of America" 5d0e11844f1a210f16025e990de938f6732672ab,Distance to Center of Mass Encoding for Instance Segmentation,"Distance to Center of Mass Encoding for Instance Segmentation Thomio Watanabe University of Sao Paulo Denis Wolf University of Sao Paulo" 5da43ff9c246ae37d9006bba3406009cb4fb1dcf,"Lifelong Machine Learning November , 2016","Lifelong Machine Learning November, 2016 Zhiyuan Chen and Bing Liu Draft : This is an early draft of the book. Zhiyuan Chen and Bing Liu. Lifelong Machine Learning. Morgan & Claypool Publishers, Nov 2016. LifelongMachineLearningZhiyuan ChenBing Liu" 5d5cd6fa5c41eb9d3d2bab3359b3e5eb60ae194e,Face Recognition Algorithms,"Face Recognition Algorithms Proyecto Fin de Carrera June 16, 2010 Ion Marqu´es Supervisor: Manuel Gra˜na" 5d185d82832acd430981ffed3de055db34e3c653,A Fuzzy Reasoning Model for Recognition of Facial Expressions,"A Fuzzy Reasoning Model for Recognition of Facial Expressions Oleg Starostenko1, Renan Contreras1, Vicente Alarcón Aquino1, Leticia Flores Pulido1, Jorge Rodríguez Asomoza1, Oleg Sergiyenko2, and Vira Tyrsa3 Research Center CENTIA, Department of Computing, Electronics and Mechatronics, Universidad de las Américas, 72820, Puebla, Mexico {oleg.starostenko; renan.contrerasgz; vicente.alarcon; leticia.florespo; Engineering Institute, Autonomous University of Baja California, Blvd. Benito Juárez, Insurgentes Este, 21280, Mexicali, Baja California, Mexico Universidad Politécnica de Baja California, Mexicali, Baja California, Mexico" 5d14cc415a93e6f3a625ed7794e1fdcf99ea5713,Predicting Face Recognition Performance Using Image Quality,"Predicting Face Recognition Performance Using Image Quality Abhishek Dutta, Raymond Veldhuis, Senior Member, IEEE and Luuk Spreeuwers," 5db4fe0ce9e9227042144758cf6c4c2de2042435,Recognition of Facial Expression Using Haar Wavelet Transform,"INTERNATIONAL JOURNAL OF ELECTRICAL AND ELECTRONIC SYSTEMS RESEARCH, VOL.3, JUNE 2010 Recognition of Facial Expression Using Haar Wavelet Transform M. Satiyan, M.Hariharan, R.Nagarajan paper features investigates" 5da2ae30e5ee22d00f87ebba8cd44a6d55c6855e,"When facial expressions do and do not signal minds: The role of face inversion, expression dynamism, and emotion type.","This is an Open Access document downloaded from ORCA, Cardiff University's institutional repository: http://orca.cf.ac.uk/111659/ This is the author’s version of a work that was submitted to / accepted for publication. Citation for final published version: Krumhuber, Eva G, Lai, Yukun, Rosin, Paul and Hugenberg, Kurt 2018. When facial expressions Publishers page: Please note: Changes made as a result of publishing processes such as copy-editing, formatting and page numbers may not be reflected in this version. For the definitive version of this publication, please refer to the published source. You are advised to consult the publisher’s version if you wish to cite this paper. This version is being made available in accordance with publisher policies. See http://orca.cf.ac.uk/policies.html for usage policies. Copyright and moral rights for publications made available in ORCA are retained by the copyright holders." 5d7de2eb2ee99798bfb2e50ed5169e3b8a35469a,Design of a Three-Dimensional Face Recognition System,"The Open Automation and Control Systems Journal, 2015, 7, 587-590 Design of a Three-Dimensional Face Recognition System Send Orders for Reprints to Open Access Wang Xuechun* and Wang Zhaoping School of Information Engineering, Huanghe Science and Technology College, Zhengzhou, Henan, 450006, P.R. China" 5dc003a75a302761778cb1c15d796e3d90dd9322,Bayesian Fisher's Discriminant for Functional Data,"Bayesian Fisher’s Discriminant for Functional Data Yao-Hsiang Yang ∗, Lu-Hung Chen†, Chieh-Chih Wang‡, and Chu-Song Chen § December 10, 2014" 5d197c8cd34473eb6cde6b65ced1be82a3a1ed14,A Face Image Database for Evaluating Out-of-Focus Blur,"0AFaceImageDatabaseforEvaluatingOut-of-FocusBlurQiHan,QiongLiandXiamuNiuHarbinInstituteofTechnologyChina1.IntroductionFacerecognitionisoneofthemostpopularresearchfieldsofcomputervisionandmachinelearning(Tores(2004);Zhaoetal.(2003)).Alongwithinvestigationoffacerecognitionalgorithmsandsystems,manyfaceimagedatabaseshavebeencollected(Gross(2005)).Facedatabasesareimportantfortheadvancementoftheresearchfield.Becauseofthenonrigidityandcomplex3Dstructureofface,manyfactorsinfluencetheperformanceoffacedetectionandrecognitionalgorithmssuchaspose,expression,age,brightness,contrast,noise,blurandetc.Someearlyfacedatabasesgatheredunderstrictlycontrolledenvironment(Belhumeuretal.(1997);Samaria&Harter(1994);Turk&Pentland(1991))onlyallowslightexpressionvariation.Toinvestigatetherelationshipsbetweenalgorithms’performanceandtheabovefactors,morefacedatabaseswithlargerscaleandvariouscharacterswerebuiltinthepastyears(Bailly-Bailliereetal.(2003);Flynnetal.(2003);Gaoetal.(2008);Georghiadesetal.(2001);Hallinan(1995);Phillipsetal.(2000);Simetal.(2003)).Forinstance,The""CAS-PEAL"",""FERET"",""CMUPIE"",and""YaleB""databasesincludevariousposes(Gaoetal.(2008);Georghiadesetal.(2001);Phillipsetal.(2000);Simetal.(2003));The""HarvardRL"",""CMUPIE""and""YaleB""databasesinvolvemorethan40differentconditionsinillumination(Georghiadesetal.(2001);Hallinan(1995);Simetal.(2003));Andthe""BANCA"",and""NDHID""databasescontainover10timesgathering(Bailly-Bailliereetal.(2003);Flynnetal.(2003)).Thesedatabaseshelpresearcherstoevaluateandimprovetheiralgorithmsaboutfacedetection,recognition,andotherpurposes.Blurisnotthemostimportantbutstillanotablefactoraffectingtheperformanceofabiometricsystem(Fronthaleretal.(2006);Zamanietal.(2007)).Themainreasonsleadingblurconsistinout-of-focusofcameraandmotionofobject,andtheout-of-focusblurismoresignificantintheapplicationenvironmentoffacerecognition(Eskicioglu&Fisher(1995);Kimetal.(1998);Tanakaetal.(2007);Yitzhaky&Kopeika(1996)).Toinvestigatetheinfluenceofbluronafacerecognitionsystem,afaceimagedatabasewithdifferentconditionsofclarityandefficientblurevaluatingalgorithmsareneeded.Thischapterintroducesanewfacedatabasebuiltforthepurposeofblurevaluation.Theapplicationenvironmentsoffacerecognitionareanalyzedfirstly,thenaimagegatheringschemeisdesigned.Twotypicalgatheringfacilitiesareusedandthefocusstatusaredividedinto11steps.Further,theblurassessmentalgorithmsaresummarizedandthecomparisonbetweenthemisraisedonthevarious-claritydatabase.The7www.intechopen.com" 7ae0212d6bf8a067b468f2a78054c64ea6a577ce,Human Face Processing Techniques With Application To Large Scale Video Indexing,"Human Face Processing Techniques With Application To Large Scale Video Indexing LE DINH DUY DOCTOR OF PHILOSOPHY Department of Informatics, School of Multidisciplinary Sciences, The Graduate University for Advanced Studies (SOKENDAI) 006 (School Ｙear) September 2006" 7ace44190729927e5cb0dd5d363fcae966fe13f7,A bag-of-features approach based on Hue-SIFT descriptor for nude detection,"7th European Signal Processing Conference (EUSIPCO 2009) Glasgow, Scotland, August 24-28, 2009 A BAG-OF-FEATURES APPROACH BASED ON HUE-SIFT DESCRIPTOR FOR NUDE DETECTION Ana P. B. Lopes1,2, Sandra E. F. de Avila1, Anderson N. A. Peixoto1 Rodrigo S. Oliveira1 and Arnaldo de A. Ara´ujo1 Computer Science Department – Federal University of Minas Gerais Av. Antˆonio Carlos, 6627, Pampulha, CEP 31270–901, Belo Horizonte, MG, Brazil Exact and Technological Sciences Department – State University of Santa Cruz Rodovia Ilh´eus-Itabuna, km 16 – Pavilh˜ao Jorge Amado, CEP 45600-000, Ilh´eus, BA, Brazil" 7a0fb972e524cb9115cae655e24f2ae0cfe448e0,Facial Expression Classification Using RBF AND Back-Propagation Neural Networks,"Facial Expression Classification Using RBF AND Back-Propagation Neural Networks R.Q.Feitosa1,2, M.M.B.Vellasco1,2, D.T.Oliveira1, D.V.Andrade1, S.A.R.S.Maffra1 – Catholic University of Rio de Janeiro, Brazil Department of Electric Engineering – State University of Rio de Janeiro, Brazil Department of Computer Engineering e-mail: [raul, -rio.br, [diogo," 7aa062c6c90dba866273f5edd413075b90077b51,Minimizing Separability : A Comparative Analysis of Illumination Compensation Techniques in Face Recognition,"I.J. Information Technology and Computer Science, 2017, 5, 40-51 Published Online May 2017 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijitcs.2017.05.06 Minimizing Separability: A Comparative Analysis of Illumination Compensation Techniques in Face Recognition Chollette C. Olisah Department of Computer Science and IT, Baze University, Abuja, Nigeria E-mail:" 7a7a04a02e807d7c9cb90ab8442ac428904d2415,Automated Latent Fingerprint Recognition,"Automated Latent Fingerprint Recognition Kai Cao and Anil K. Jain, Fellow, IEEE" 7a0c93d7cc75187aebb1a42772c79839c8f681c5,Détection de marqueurs affectifs et attentionnels de personnes âgées en interaction avec un robot. (Audio-visual detection of emotional (laugh and smile) and attentional markers for elderly people in social interaction with a robot),"Détection de marqueurs affectifs et attentionnels de personnes âgées en interaction avec un robot Fan Yang To cite this version: Fan Yang. Détection de marqueurs affectifs et attentionnels de personnes âgées en interaction vec un robot. Intelligence artificielle [cs.AI]. Université Paris-Saclay, 2015. Français. . HAL Id: tel-01280505 https://tel.archives-ouvertes.fr/tel-01280505 Submitted on 29 Feb 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 7a1828e181e3c8bd014c7e5fc1bcc417f122c18c,Face Perception and Test Reliabilities in Congenital Prosopagnosia in Seven Tests,"i-Perception January-February 2016: 1–37 ! The Author(s) 2016 DOI: 10.1177/2041669515625797 ipe.sagepub.com Article Face Perception and Test Reliabilities in Congenital Prosopagnosia in Seven Tests Janina Esins Department of Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Tu¨bingen, Germany Johannes Schultz Department of Psychology, Durham University, Durham, UK Claudia Stemper Institute of Human Genetics, Westfa¨lische Wilhelms-Universita¨t Mu¨nster, Mu¨nster, Germany Ingo Kennerknecht Institute of Human Genetics, Westfa¨lische Wilhelms-Universita¨t Mu¨nster, Mu¨nster, Germany" 7a9ef491914d515bb5570aa9b3a261d42d430b86,"Excuse Me, Do I Know You From Somewhere? Unaware Facial Recognition Using Brain-Computer Interfaces","Proceedings of the 50th Hawaii International Conference on System Sciences | 2017 Excuse Me, Do I Know You From Somewhere? Unaware Facial Recognition Using Brain-Computer Interfaces Christopher Bellman Miguel Vargas Martin Shane MacDonald University of Ontario Institute University of Ontario Institute University of Ontario Institute of Technology of Technology of Technology Ruba Alomari Ramiro Liscano University of Ontario Institute of Technology University of Ontario Institute of Technology" 7aa4c16a8e1481629f16167dea313fe9256abb42,Multi-task learning for face identification and attribute estimation,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" 7a97de9460d679efa5a5b4c6f0b0a5ef68b56b3b,Constrained Joint Cascade Regression Framework for Simultaneous Facial Action Unit Recognition and Facial Landmark Detection,"nd Face shape relationship2)AU relationship3)Face shape patternUpdate facial landmark locationsUpdate AU activation probabilitiesAU activation probabilitiesCurrent landmark locationsFigure1.Constrainedjointcascaderegressionframeworkforsi-multaneousfacialactionunitrecognitionandlandmarkdetection.wouldenablethemachineunderstandingofhumanfacialbehavior,intent,emotionetc.Facialactionunitrecognitionandfaciallandmarkdetec-tionarerelatedtasks,buttheyareseldomlyexploitedjointlyintheliteratures.Forexample,thefaceshapedefinedbythelandmarklocationsareconsideredaseffectivefeaturesforAUrecognition.But,thelandmarklocationinforma-tionisusuallyextractedbeforehandwithfaciallandmarkdetectionalgorithms.Ontheotherhand,theActionUnitinformationisrarelyutilizedintheliteraturetohelpfaciallandmarkdetection,eventhoughthefacialmusclemove-mentsandtheactivationofspecificfacialactionunitcancausetheappearanceandshapechangesofthefacewhichsignificantlyaffectfaciallandmarkdetection.Themutualinformationandintertwinedrelationshipamongfacialac-tionunitrecognitionandfaciallandmarkdetectionshouldbeutilizedtoboosttheperformancesofbothtasks.Cascaderegressionframeworkhasbeenshowntobeaneffectivemethodforfacealignmentrecently[19][13].Itstartsfromaninitialfaceshape(e.g.meanface)anditit-erativelyupdatesthefaciallandmarklocationsbasedonthelocalappearancefeaturesuntilconvergence.Severalregres-sionmodelshavebeenappliedtolearnthemappingfromthelocalappearancefeaturestothefaceshapeupdate.Toleveragethesuccessofthecascaderegressionframe-workandtoachievethegoalofjointfacialactionunit13400" 7a776f080b270c8759b2b4fe601682276d1b2eb4,Multi-target Tracking with Sparse Group Features and Position Using Discrete-Continuous Optimization,"Multi-Target Tracking with Sparse Group Features and Position using Discrete-Continuous Optimization Billy Peralta (1) and Alvaro Soto (2) (1)Universidad Cat´olica de Temuco, (2)Pontificia Universidad Cat´olica de Chile" 7ad77b6e727795a12fdacd1f328f4f904471233f,Supervised Local Descriptor Learning for Human Action Recognition,"Supervised Local Descriptor Learning for Human Action Recognition Xiantong Zhen, Feng Zheng, Ling Shao, Senior Member, IEEE, Xianbin Cao, Senior Member, IEEE, and Dan Xu" 7a88d33b3e23a2cdf1e8a2b848c73a12a34ba88c,TUB-IRML at MediaEval 2014 Violent Scenes Detection Task: Violence Modeling through Feature Space Partitioning,"TUB-IRML at MediaEval 2014 Violent Scenes Detection Task: Violence Modeling through Feature Space Partitioning Esra Acar, Sahin Albayrak DAI Laboratory, Technische Universität Berlin Ernst-Reuter-Platz 7, TEL 14, 10587 Berlin, Germany" 7afb39dcf74b5d9ae082ae33ebf3ce04dceb0cf8,Evaluation of Face R,"Recognition Techniques for Application Evaluation of Face R Enrique G. O Brian C. Becker University of Centr Carnegie Mellon Univ versity 000 Central Flori 5000 Forbes Av Pittsburgh, PA 152 Orlando, FL 32 ker.com http://www.enriqueg http://www.briancbec" 7af6d86139aa86cb5897904563a9f67c016a176d,Performance of Correlation Filters in Facial Recognition,"Performance of Correlation Filters in Facial Recognition Everardo Santiago-Ramirez, J.A. Gonzalez-Fraga, and J.I. Ascencio-Lopez Facultad de Ciencias, Universidad Autónoma de Baja California, Km. 103, Carretera Tijuana- Ensenada, Ensenada, Baja California C. P. 22860" 7a81967598c2c0b3b3771c1af943efb1defd4482,Do We Need More Training Data?,"Do We Need More Training Data? Xiangxin Zhu · Carl Vondrick · Charless C. Fowlkes · Deva Ramanan" 7a7a53b05e22305b2963c05ac89830e099146767,Assessing fish abundance from underwater video using deep neural networks,"Assessing fish abundance from underwater video using deep neural networks Ranju Mandal∗, Rod M. Connolly†, Thomas A. Schlacher‡ and Bela Stantic∗ School of ICT, Griffith Sciences, Griffith University, QLD 4222, Australia Australian Rivers Institute - Coast & Estuaries and School of Environment and Science, Griffith University, QLD 4222, Australia School of Science and Engineering, University of the Sunshine Coast, QLD 4558, Australia {r.mandal, r.connolly," 7a9fe5781220cca6ca600833015f200a9c03d50e,Teaching Machines to Describe Images via Natural Language Feedback,"Teaching Machines to Describe Images via Natural Language Feedback Huan Ling1, Sanja Fidler1,2 University of Toronto1, Vector Institute2" 7ab9035ec3871bbeadf1095afbe1ff9d9cb25480,DLBP and SVD Fusion for 3 D Face Recognition Using Range Image,"Computer Science and Information Technology 5(2): 61-65, 2017 DOI: 10.13189/csit.2017.050203 http://www.hrpub.org DLBP and SVD Fusion for 3D Face Recognition Using Range Image El Mahdi Barrah, Rachid Ahdid, Said Safi, Abdessamad Malaoui∗ Interdisciplinary Laboratory of Research in Sciences and Technologies (LIRST), Sultan Moulay Slimane University, Bni Mellal, Morocco Copyright c(cid:13)2017 by authors, all rights reserved. Authors agree that this article remains permanently open access under the terms of the Creative Commons Attribution License 4.0 International License" 7a540e0e2049a8f0118be2eab9a2ec5f57e022c9,Deep Learning Methods for Classification with Limited Training Data Seminar Report : Spring 2017,"Deep Learning Methods for Classification with Limited Training Data Seminar Report : Spring 2017 submitted by Aviral Kumar (140070031) under the guidance of Prof. Sunita Sarawagi Department of Computer Science and Engineering Indian Institute of Technology Bombay April, 2017" 7a4f3d17672ecd89e4ad0d4f3a9257352a055d9b,A Novel Data-driven Image Annotation Method,"A Novel Data-driven Image Annotation Method Guiguang Ding, Jianmin Wang, Na Xu" 7a8ffddbceb14a5b5fb5fc52c47a4db366e47f80,The Rosario Dataset: Multisensor Data for Localization and Mapping in Agricultural Environments,"The Rosario Dataset: Multisensor Data for Localization and Mapping in Agricultural Environments Journal Title XX(X):1–8 ©The Author(s) 2016 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/ToBeAssigned www.sagepub.com/ Taih ´u Pire1, Mart´ın Mujica1, Javier Civera2 and Ernesto Kofman1" 7ab41d2fb37079d20db5e25fd6e71755673f82f0,Building Emotional Machines: Recognizing Image Emotions Through Deep Neural Networks,"Building Emotional Machines: Recognizing Image Emotions through Deep Neural Networks Hye-Rin Kim, Yeong-Seok Kim, Seon Joo Kim, In-Kwon Lee" 7ad7897740e701eae455457ea74ac10f8b307bed,Random Subspace Two-dimensional LDA for Face Recognition,"Random Subspace Two-dimensional LDA for Face Recognition* Garrett Bingham1" 7a0ae1abc9b999ce7dfdd7879f5c29b1992f254b,Fusion of Silhouette Based Gait Features for Gait Recognition,"International Journal of Engineering and Technical Research (IJETR) ISSN: 2321-0869, Volume-2, Issue-8, August 2014 Fusion of Silhouette Based Gait Features for Gait Recognition Mohan Kumar H P, Nagendraswamy H S" 7acc05ae92823c12b28d6ad73cb2a7707ccb6c7b,Single view-based 3D face reconstruction robust to self-occlusion,"Lee et al. EURASIP Journal on Advances in Signal Processing 2012, 2012:176 http://asp.eurasipjournals.com/content/2012/1/176 R ES EAR CH Open Access Single view-based 3D face reconstruction robust to self-occlusion Youn Joo Lee1, Sung Joo Lee2, Kang Ryoung Park3, Jaeik Jo1 and Jaihie Kim1*" 7a82d83f818cdc4ac714e468446bc2499ff9caa7,Object Referring in Videos with Language and Human Gaze,"Object Referring in Videos with Language and Human Gaze Arun Balajee Vasudevan1, Dengxin Dai1, Luc Van Gool1,2 ETH Zurich1 KU Leuven 2" a949b8700ca6ba96ee40f75dfee1410c5bbdb3db,Instance-Weighted Transfer Learning of Active Appearance Models,"Instance-weighted Transfer Learning of Active Appearance Models Daniel Haase, Erik Rodner, and Joachim Denzler Computer Vision Group, Friedrich Schiller University of Jena, Germany Ernst-Abbe-Platz 2-4, 07743 Jena, Germany" a94c3091be2090df6144bd121e41e7dfa96ec0e9,Enhanced visual functioning in autism: an ALE meta-analysis.,"Enhanced Visual Functioning in Autism: An ALE Meta-Analysis Fabienne Samson,1 Laurent Mottron,1 Isabelle Soulie` res,1,2 nd Thomas A. Zeffiro2 Centre d’Excellence en Troubles Envahissants du De´veloppement de l’Universite´ de Montre´al Neural Systems Group, Massachusetts General Hospital, Boston, Massachusetts (CETEDUM), Montre´al, QC, Canada" a92b5234b8b73e06709dd48ec5f0ec357c1aabed,Disjoint Multi-task Learning Between Heterogeneous Human-Centric Tasks, a93781e6db8c03668f277676d901905ef44ae49f,Recent Data Sets on Object Manipulation: A Survey.,"Recent Datasets on Object Manipulation: A Survey Yongqiang Huang, Matteo Bianchi, Minas Liarokapis and Yu Sun" a91d0ebc1255d6de1c4588767b3b5e1fc630e56f,FBI-HH-M-345 / 10 eTRIMS Scene Interpretation Datasets,"Universit¨at Hamburg Technical Report FBI-HH-M-345/10 eTRIMS Scene Interpretation Datasets Johannes Hartz Patrick Koopmann Arne Kreutzmann Kasim Terzi´c {hartz | koopmann | informatik.uni-hamburg.de November 15, 2010" a9978df0b4df4d7b04bc4e9464c67f9ff7c31d3d,FROM TRADITIONAL TO INTERACTIVE PLAYSPACES FROM TRADITIONAL TO INTERACTIVE PLAYSPACES FROM TRADITIONAL TO INTERACTIVE PLAYSPACES Automatic Analysis of Player Behavior in the Interactive Tag Playground,"FROM TRADITIONAL TO FROM TRADITIONAL TO INTERACTIVE PLAYSPACES INTERACTIVE PLAYSPACES Automatic Analysis of Player Behavior in the Interactive Tag Playground CTIT Ph.D. Thesis Series No. 16-386 ISSN: 1381-3617 Alejandro Moreno" a9d3547ab16a9cc936bf5991bf8fb475eadce931,Face Recognition using DWT with HMM,"Eng. & Tech. Journal, Vol.30, No.1, 2012 Face Recognition using DWT with HMM Dr. Eyad I. Abbas Department of Electrical Engineering, University of Technology/ Baghdad Hameed R. Farhan Department of Electrical Engineering, Engineering College, University of Kerbala/ Kerbala Received on: 19/6/2011 & Accepted on: 3/11/2011" a90226c41b79f8b06007609f39f82757073641e2,Β-vae: Learning Basic Visual Concepts with a Constrained Variational Framework,"Under review as a conference paper at ICLR 2017 β-VAE: LEARNING BASIC VISUAL CONCEPTS WITH A CONSTRAINED VARIATIONAL FRAMEWORK Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, Alexander Lerchner Google DeepMind {irinah,lmatthey,arkap,cpburgess,glorotx," a975f1aea5dbb748955da0e17eef8d2270a49f25,Object Recognition Sensory Data Acquisition Light Intensity Images,"OBJECT RECOGNITION Object recognition is a subproblem of the more general problem of perception, and can be defined as follows. Given scene consisting of one or more objects, can we identify nd localize those objects that are sufficiently visible to the sensory system? It is generally assumed that a de- scription of each object to be recognized is available to the omputer and can be used to facilitate the task of iden- tification and localization. These descriptions can either e model-based or appearance-based, or a combination of oth. Model-based object representation is based on geo- metric features, whereas appearance-based representation uses a large set of images for training but does not require ny insight into the geometric structure of the objects. Ob- ject recognition is a key component of many intelligent vi- sion systems, such as those used in hand-eye coordination for bin picking, inspection, and mobile robotics. Various types of object recognition problems can be stated based on the dimensionality of their spatial descrip- tion: (1) recognition of a 2-D object from a single 2-D im-" a9f03e4bb90addab234423994bfd8c25854484ea,OBJECT BASED IMAGE RETRIEVAL USING LBP AND FUZZY CLUSTERING METHOD,"Volume1, Issue 3, 15 May- 15 August 2015 International Journal In Applied Studies And Production Management ISSN 2394-840X OBJECT BASED IMAGE RETRIEVAL USING LBP AND FUZZY CLUSTERING METHOD Jiwanjot kaur Bhinder Department of Computer Science & Engg, RIMT(IET) Mandigobindgarh Kirti joshi Department of Computer Science & Engg, RIMT(IET) Mandigobindgarh" a9453721f35f364e176a5aaa7bdb622f72fbcaec,Learning Articulated Motion Models from Visual and Lingual Signals,"Learning Articulated Motion Models from Visual and Lingual Signals Zhengyang Wu Georgia Tech Atlanta, GA 30332 Mohit Bansal TTI-Chicago Chicago, IL 60637 Matthew R. Walter TTI-Chicago Chicago, IL 60637" a9286519e12675302b1d7d2fe0ca3cc4dc7d17f6,Learning to Succeed while Teaching to Fail: Privacy in Closed Machine Learning Systems,"Learning to Succeed while Teaching to Fail: Privacy in Closed Machine Learning Systems Jure Sokoli´c, Qiang Qiu, Miguel R. D. Rodrigues, and Guillermo Sapiro" a9eb6e436cfcbded5a9f4b82f6b914c7f390adbd,A Model for Facial Emotion Inference Based on Planar Dynamic Emotional Surfaces,"(IJARAI) International Journal of Advanced Research in Artificial Intelligence, Vol. 5, No.6, 2016 A Model for Facial Emotion Inference Based on Planar Dynamic Emotional Surfaces Ruivo, J. P. P. Escola Polit´ecnica Negreiros, T. Escola Polit´ecnica Barretto, M. R. P. Escola Polit´ecnica Tinen, B. Escola Polit´ecnica Universidade de S˜ao Paulo Universidade de S˜ao Paulo Universidade de S˜ao Paulo Universidade de S˜ao Paulo S˜ao Paulo, Brazil S˜ao Paulo, Brazil S˜ao Paulo, Brazil S˜ao Paulo, Brazil" a937c7cbb38d26dbc1d2769780cde6e0c7cc5d90,Offline Generation of High Quality Background Subtraction Data,"Offline Generation of High Quality Background Subtraction Data Etienne Grossmann, Amit Kale, Christopher Jaynes and Sen-ching Samson Cheung UK Center for Visualization and Virtual Environments      ! #"" !!$%!&'()! ! *+ -,%,.(-! ! Quality Street; Lexington KY 40507-1464, USA" a94b832facb57ea37b18927b13d2dd4c5fa3a9ea,Domain transfer convolutional attribute embedding,"April 3, 2018 Journal of Experimental & Theoretical Artificial Intelligence To appear in the Journal of Experimental & Theoretical Artificial Intelligence Vol. 00, No. 00, Month 20XX, 1–23 Domain transfer convolutional attribute embedding Fang Sua ∗ , Jing-Yan Wangb School of Economics and Management, Shaanxi University of Science & Technology, Xi’an, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates ShaanXi Province, P.R.C, 710021 (v5.0 released July 2015) In this paper, we study the problem of transfer learning with the attribute data. In the trans- fer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross different domains. This strongly motives us to learn effective domain transfer attribute representations. To this end, we proposed to embed the ttributes of the data to a common space by using the powerful convolutional neural net- work (CNN) model. The convolutional representations of the data points are mapped to the orresponding attributes so that they can be effective embedding of the attributes. We also represent the data of different domains by a domain-independent CNN, ant a domain-specific CNN, and combine their outputs with the attribute embedding to build the classification" a9f5acdcf1fbc9563aaad943cbe1c195b796aa62,Learning Fashion By Simulated Human Supervision,"Learning Fashion By Simulated Human Supervision Eli Alshan Sharon Alpert Assaf Neuberger Nathaniel Bubis Eduard Oks {alshan, alperts, neuberg, bubis, Amazon Lab126" a9f63dcae167630b0c6ba4131897539151217e2b,Testing a Method for Statistical Image Classification in Image Retrieval,"Testing a Method for Statistical Image Classification in Image Retrieval Christoph Rasche, Constantin Vertan Laboratorul de Analiza si Prelucrarea Imaginilor Universitatea Politehnica din Bucuresti Bucuresti 061071, RO" a9c120de41679fe336e2779f3e6fe4b04945cb3a,A Robust Multilinear Model Learning Framework for 3D Faces,"A Robust Multilinear Model Learning Framework for 3D Faces∗ Timo Bolkart Stefanie Wuhrer Saarland University, Germany Inria Grenoble Rhˆone-Alpes, France" a98316980b126f90514f33214dde51813693fe0d,Collaborations on YouTube: From Unsupervised Detection to the Impact on Video and Channel Popularity,"Collaborations on YouTube: From Unsupervised Detection to the Impact on Video and Channel Popularity Christian Koch, Moritz Lode, Denny Stohr, Amr Rizk, Ralf Steinmetz Multimedia Communications Lab (KOM), Technische Universität Darmstadt, Germany E-Mail: {Christian.Koch | Denny.Stohr | Amr.Rizk |" a97f3d2313affd35c889c57f2ebe21e7ba2b5bbb,Real-Time Semantic Mapping for Autonomous Off-Road Navigation,"Real-time Semantic Mapping for Autonomous Off-Road Navigation Daniel Maturana, Po-Wei Chou, Masashi Uenoyama and Sebastian Scherer" a9e1bddb0fdc862859b90d03e20b34d4cfdf4b93,Automatic Determination of Body Condition Score of Dairy Cows from 3D Images,"Automatic Determination of Body Condition Score of Dairy Cows from 3D Images Processing and pattern recognition in images from a time-of-flight camera M A R I L Y N K R U K O W S K I Master of Science Thesis Stockholm, Sweden 2009" a921dbe7659e4a75c1ac53f5bdc1fcdc6caa5933,Title Detection based low frame rate human tracking,"Title Detection based low frame rate human tracking Author(s) Wang, L; Yung, NHC Citation The 20th International Conference on Pattern Recognition (ICPR 010), Istanbul, Turkey, 23-26 August 2010. In Proceedings of 0th ICPR, 2010, p. 3529-3532 Issued Date http://hdl.handle.net/10722/137721 Rights International Conference on Pattern Recognition. Copyright © IEEE, Computer Society." a9e8c08c69b8752a8afad752ec26a2b3807ede50,"PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship","SUBMITTED TO IEEE TRANSACTIONS ON AFFECTIVE COMPUTING PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship Le Zhang, Songyou Peng, and Stefan Winkler, Fellow, IEEE" a9d6d62f4f3f12ed565e5d75f8c4b7a202a3d809,Action and intention recognition of pedestrians in urban traffic,"Action and intention recognition of pedestrians in urban traffic Dimitrios Varytimidis1, Fernando Alonso-Fernandez1, Boris Duran2 and Cristofer Englund1,2∗" a9d2c96cead937e53e614abb9fd051574a55c77a,Ensembling Visual Explanations for,"In Proceedings of the NIPS 2017 workshop on Visually-Grounded Interaction and Language (ViGIL), December 2017." a9e53a7533c9c743b57b6668c11be0c73525f188,Enhanced Feature Sets for Face Recognition with varying Lighting Conditions and Noise,"Enhanced Feature Sets for Face Recognition with varying Lighting Conditions and Noise ISSN 2278 – 3806 Enhanced Feature Sets for Face Recognition with varying Lighting Conditions and Noise Final ME (CSE), 2Head of Department of Computer Science and Engineering S.Vishnupriya1 Dr.k.Lakshmi2 Periyar Maniammai University, Thanjavur, Tamilnadu, India." a9e28863c7fb963b40a379c5a4e0da00eb031933,A Corpus of Natural Language for Visual Reasoning,"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 217–223 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 217–223 Vancouver, Canada, July 30 - August 4, 2017. c(cid:13)2017 Association for Computational Linguistics Vancouver, Canada, July 30 - August 4, 2017. c(cid:13)2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-2034 https://doi.org/10.18653/v1/P17-2034" a9791544baa14520379d47afd02e2e7353df87e5,The Need for Careful Data Collection for Pattern Recognition in Digital Pathology,"Technical Note The Need for Careful Data Collection for Pattern Recognition in Digital Pathology Raphaël Marée1 Department of Electrical Engineering and Computer Science, Montefiore Institute, University of Liège, 4000 Liège, Belgium Received: 08 December 2016 Accepted: 15 March 2017 Published: 10 April 2017" a91caf771905ddff8cb271f04e7ede1a8b6d529b,Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training,"Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training Department of Biomedical Engineering Department of Computer Science Faisal Mahmood1 Richard Chen2 Nicholas J. Durr1 Johns Hopkins University (JHU) {faisalm, rchen40," a91fd02ed2231ead51078e3e1f055d8be7828d02,The Robust Manifold Defense: Adversarial Training using Generative Models,"The Robust Manifold Defense: Adversarial Training using Generative Models Andrew Ilyas Ajil Jalal Eirini Asteri MIT EECS UT Austin UT Austin Constantinos Daskalakis Alexandros G. Dimakis MIT EECS UT Austin December 27, 2017 Problems worthy of attack, prove their worth by fighting back." a9ad8f6c6bf110485921b17f9790241b1548487c,Automatic Skin Tone Extraction for Visagism Applications, a9adb6dcccab2d45828e11a6f152530ba8066de6,Aydınlanma Alt-uzaylarına dayalı Gürbüz Yüz Tanıma Illumination Subspaces based Robust Face Recognition,"Aydınlanma Alt-uzaylarına dayalı Gürbüz Yüz Tanıma Illumination Subspaces based Robust Face Recognition D. Kern, H.K. Ekenel, R. Stiefelhagen Interactive Systems Labs, Universität Karlsruhe (TH) 76131 Karlsruhe, Almanya web: http://isl.ira.uka.de/face_recognition Özetçe yönlerine ydınlanma kaynaklanan sonra, yüz uzayı Bu çalışmada aydınlanma alt-uzaylarına dayalı bir yüz tanıma sistemi sunulmuştur. Bu sistemde, ilk olarak, baskın ydınlanma yönleri, bir topaklandırma algoritması kullanılarak öğrenilmiştir. Topaklandırma algoritması sonucu önden, sağ ve sol yanlardan olmak üzere üç baskın aydınlanma yönü gözlemlenmiştir. Baskın karar -yüzün görünümündeki" a93eef69847a623e0c3273bb3f1c7d86987abb6f,Ney Log-Linear Mixture Models for Patch-Based Object Recognition vorgelegt,"Diplomarbeit im Fach Informatik Rheinisch-Westf¨alische Technische Hochschule Aachen Lehrstuhl f¨ur Informatik 6 Prof. Dr.-Ing. H. Ney Log-Linear Mixture Models for Patch-Based Object Recognition vorgelegt von: Tobias Weyand Matrikelnummer 238060 Gutachter: Prof. Dr.-Ing. H. Ney Prof. Dr. rer. nat. T. Seidl Betreuer: Dipl.-Inform. T. Deselaers" a94aac3caccebd82413dd05707ef8bf525dc46b9,Evaluation of the UR 3 D algorithm using the FRGC v 2 data set,"Evaluation of the UR3D algorithm using the FRGC v2 data set G. Passalis, I.A. Kakadiaris, T. Theoharis, G. Toderici and N. Murtuza Visual Computing Lab, Dept. of Computer Science, Univ. of Houston, Houston, TX 77204, USA" df9768bedaada944d283af357234a0250bc46523,An Overview of Deep Learning Based Methods for Unsupervised and Semi-Supervised Anomaly Detection in Videos,"An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos B Ravi Kiran, Dilip Mathew Thomas, Ranjith Parakkal" df5fe0c195eea34ddc8d80efedb25f1b9034d07d,Robust modified Active Shape Model for automatic facial landmark annotation of frontal faces,"Robust Modified Active Shape Model for Automatic Facial Landmark Annotation of Frontal Faces Keshav Seshadri and Marios Savvides" dfa53c8a4d66ab6219d6f00219ca7ed3909832fd,Probabilistic Neural Network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework,"Probabilistic Neural Network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework Andrey V. Savchenko these drawbacks by replacing" dfecaedeaf618041a5498cd3f0942c15302e75c3,A recursive framework for expression recognition: from web images to deep models to game dataset,"Noname manuscript No. (will be inserted by the editor) A Recursive Framework for Expression Recognition: From Web Images to Deep Models to Game Dataset Wei Li · Christina Tsangouri · Farnaz Abtahi · Zhigang Zhu Received: date / Accepted: date" df310591dfba9672252d693bc87da73c246749c9,Fusion of Holistic and Part Based Features for Gender Classification in the Wild,"Fusion of Holistic and Part Based Features for Gender Classification in the Wild Modesto Castrill´on-Santana(B), Javier Lorenzo-Navarro, nd Enrique Ram´on-Balmaseda Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain http://berlioz.dis.ulpgc.es/roc-siani" dfc784c860795f4f9aa704b7655f6d1321018980,Unsupervised Co-Activity Detection from Multiple Videos Using Absorbing Markov Chain,"Unsupervised Co-activity Detection from Multiple Videos using Absorbing Markov Chain Donghun Yeo, Bohyung Han, Joon Hee Han Department of Computer Science and Engineering, POSTECH, Korea" dfcae2db863381ea8047f78f65b25146e696115a,Deep Learning Applications for Autonomous Driving,"Thesis for the degree of Licentiate of Engineering Deep Learning Applications for Autonomous Driving LUCA CALTAGIRONE Department of Mechanics and Maritime Sciences CHALMERS UNIVERSITY OF TECHNOLOGY G¨oteborg, Sweden 2018" df06d165b107318e270e59f15fdfe7792a49baaa,Seeing the Wood for the Trees: Reliable Localization in Urban and Natural Environments,"Seeing the Wood for the Trees: Reliable Localization in Urban and Natural Environments Georgi Tinchev, Simona Nobili and Maurice Fallon" dff612c198dc50a7bef5a9cd48da5da1f893fa72,A fast stereo-based multi-person tracking using an approximated likelihood map for overlapping silhouette templates,"A Fast Stereo-Based Multi-Person Tracking using an Approximated Likelihood Map for Overlapping Silhouette Templates Junji Satake Jun Miura Department of Computer Science and Engineering Toyohashi University of Technology Email: {satake, Toyohashi, Japan" df999184b1bb5691cd260b2b77df7ef00c0fe7b1,On Latent Distributions Without Finite Mean in Generative Models,"On Latent Distributions Without Finite Mean in Generative Models Damian Le´sniak∗ Igor Sieradzki∗ Jagiellonian University Igor Podolak" dfbc3a6a629433f24f4e06fdfe8389f83afa7094,Learning OpenCV,"Learning OpenCV Gary Bradski and Adrian Kaehler Beijing · Cambridge · Farnham · Köln · Sebastopol · Taipei · Tokyo" dfe7700ed053d4788ecea4a18431806581e03291,Grammatical facial expression recognition using customized deep neural network architecture,"Grammatical facial expression recognition using customized deep neural network architecture Devesh Walawalkar" df8aee8aef6f0c71f968979318dafcd53da04bdc,Bending the Curve: Improving the ROC Curve Through Error Redistribution,"Bending the Curve: Improving the ROC Curve Through Error Redistribution Oran Richman Department of Electrical Engineering Technion Haifa, Israel Shie Mannor Department of Electrical Engineering Technion Haifa, Israel September 21, 2018" dffb64ac066bbcfe6aea6b11408b5ea62a40e9fb,"A New Face Recognition Scheme for Faces with Expressions , Glasses and Rotation","International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print), INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & ISSN 0976 - 6375(Online), Volume 5, Issue 4, April (2014), pp. 11-23 © IAEME TECHNOLOGY (IJCET) ISSN 0976 – 6367(Print) ISSN 0976 – 6375(Online) Volume 5, Issue 4, April (2014), pp. 11-23 © IAEME: www.iaeme.com/ijcet.asp Journal Impact Factor (2014): 8.5328 (Calculated by GISI) www.jifactor.com IJCET © I A E M E A NEW FACE RECOGNITION SCHEME FOR FACES WITH EXPRESSIONS, GLASSES AND ROTATION Walaa M Abdel-Hafiez1, Mohamed Heshmat2, Moheb Girgis3, Seham Elaw4 , 2, 4Faculty of Science, Mathematical and Computer Science Department, Sohag University, 82524, Sohag, Egypt 3Faculty of Science, Department of Computer Science, Minia University, El-Minia, Egypt" df50e6e2ad60825167c6b3e641eb5cda0f3dc505,Theoretical vs. empirical discriminability: the application of ROC methods to eyewitness identification,"Wixted and Mickes Cognitive Research: Principles and Implications (2018) 3:9 https://doi.org/10.1186/s41235-018-0093-8 Cognitive Research: Principles nd Implications TU T O R I A L R E V I EW Theoretical vs. empirical discriminability: the application of ROC methods to eyewitness identification John T. Wixted1* and Laura Mickes2 Open Access" df4525d7d99f7237c864adbcb2dab30d8f7447e0,Kernel Cross-View Collaborative Representation based Classification for Person Re-Identification,"Kernel Cross-View Collaborative Representation based Classification for Person Re-Identification Raphael Prates and William Robson Schwartz Universidade Federal de Minas Gerais, Brazil 6627, Av. Pres. Antˆonio Carlos - Pampulha, Belo Horizonte - MG, 31270-901" df5094b2e8cf7e3bde3943ca7a56eb879b8e34ab,A Concatenated Residual Convolutional Network for Image Deblurring,"A Concatenated Residual Convolutional Network for Image Deblurring Li Si-Yao1, Dongwei Ren2, Zijian Hu1, Junfeng Li1, Qian Yin1*, Ping Guo1,3 Beijing Normal University 2 Tianjin University 3 Beijing Institute of Technology {rendongweihit, {lijunfeng," df674dc0fc813c2a6d539e892bfc74f9a761fbc8,An Image Mining System for Gender Classification & Age Prediction Based on Facial Features,"IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661, p- ISSN: 2278-8727Volume 10, Issue 6 (May. - Jun. 2013), PP 21-29 www.iosrjournals.org An Image Mining System for Gender Classification & Age Prediction Based on Facial Features 1.Ms.Dhanashri Shirkey , 2Prof.Dr.S.R.Gupta, M.E(Scholar),Department Computer Science & Engineering, PRMIT & R, Badnera Asstt.Prof. Department Computer Science & Engineering, PRMIT & R, Badnera" df28cd627afe6d20eb198b8406ff25ece340653d,The Acquisition of Sign Language by Deaf Children with Autism Spectrum Disorder,"The Acquisition of Sign Language by Deaf Children with Autism Spectrum Disorder Aaron Shield and Richard P. Meier Introduction Autism spectrum disorder (ASD) consists of a set of neurobiological developmental disorders characterized by communicative and social deficits s well as repetitive, stereotyped behaviors.1 In this chapter, we use the terms ‘ASD’ and ‘autism’ interchangeably; although ‘autism’ is not a clinical term, it is the term popularly used to refer to the range of disorders found in ASD. The language deficits of hearing children with autism are well docu- mented, and can range from the very mild in highly fluent speakers to the very severe in children with a total absence of productive spoken language. For those children who do acquire speech, the most common characteristics of autistic language include echolalia (echoing the utterances of others), pronoun reversal, idiosyncratic language use and neologisms (the creation of new words), difficulty with pragmatics (problems interpreting the use of language in context and the non-literal use of language), and abnormal" dfbf49ed66a9e48671964872c84f75d7f916c131,Supplementary Material for Sparsity Invariant CNNs,"Supplementary Material for Sparsity Invariant CNNs Jonas Uhrig(cid:63),1,2 Nick Schneider(cid:63),1,3 Lukas Schneider1,4 Uwe Franke1 Thomas Brox2 Andreas Geiger4,5 Daimler R&D Sindelfingen University of Freiburg KIT Karlsruhe ETH Z¨urich 5MPI T¨ubingen . Convergence Analysis We find that Sparse Convolutions converge much faster than standard convolutions for most input-output-combinations, especially for those on Synthia with irregularly sparse depth input, as considered in Section 5.1 of the main paper. In Figure , we show the mean average error in meters on our validation subset of Synthia over the process of training with identical solver settings (Adam with momentum terms of β1 = 0.9, β2 = 0.999 and delta 1e−8). We chose for each variant the maximal learning rate which still causes the network to converge (which turned out to be 1e−3 for all three variants). We find that Sparse Convolutions indeed train much faster and much smoother compared to both ConvNet variants, most likely aused by the explicit ignoring of invalid regions in the update step. Interestingly, the ConvNet variant with concatenated visibility mask in the input converges smoother than the variant with only sparse depth in the input, however, additionally" df90850f1c153bfab691b985bfe536a5544e438b,"Face Tracking Algorithm Robust to Pose , Illumination and Face Expression Changes : a 3 D Parametric Model Approach","FACE TRACKING ALGORITHM ROBUST TO POSE, ILLUMINATION AND FACE EXPRESSION CHANGES: A 3D PARAMETRIC MODEL APPROACH Marco Anisetti, Valerio Bellandi University of Milan - Department of Information Technology via Bramante 65 - 26013, Crema (CR), Italy Luigi Arnone, Fabrizio Beverina STMicroelectronics - Advanced System Technology Group via Olivetti 5 - 20041, Agrate Brianza, Italy Keywords: Face tracking, expression changes, FACS, illumination changes." dfe2d36ca249876e5ab5500f155e3a5094dbc170,Application of common sense computing for the development of a novel knowledge-based opinion mining engine,"Application of Common Sense Computing for the Development of a Novel Knowledge-Based Opinion Mining Engine A thesis submitted in accordance with the requirements of the University of Stirling for the degree of Doctor of Philosophy Erik Cambria Principal Supervisor: Amir Hussain (University of Stirling, UK) Additional Supervisor: Catherine Havasi (MIT Media Laboratory, USA) Industrial Supervisor: Chris Eckl (Sitekit Solutions Ltd, UK) Department of Computing Science & Mathematics University of Stirling, Scotland, UK December 2011" dfa80e52b0489bc2585339ad3351626dee1a8395,Human Action Forecasting by Learning Task Grammars,"Human Action Forecasting by Learning Task Grammars Tengda Han Jue Wang Anoop Cherian Stephen Gould" dfcb4773543ee6fbc7d5319b646e0d6168ffa116,Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks,"Unifying Variational Autoencoders and Generative Adversarial Networks Adversarial Variational Bayes: Lars Mescheder 1 Sebastian Nowozin 2 Andreas Geiger 1 3" df353e3a46cca8c1ef274994f5a6dcb580231726,Data-driven fundamental models for pedestrian movements THÈSE,"POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCESacceptée sur proposition du jury:Prof. P. Frossard, président du juryProf. M. Bierlaire, directeur de thèseProf. H. Mahmassani, rapporteurProf. S. Hoogendoorn, rapporteurProf. N. Geroliminis, rapporteurData-driven fundamental models for pedestrian movementsTHÈSE NO 7613 (2017)ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNEPRÉSENTÉE LE 5 MAI 2017À LA FACULTÉ DE L'ENVIRONNEMENT NATUREL, ARCHITECTURAL ET CONSTRUITLABORATOIRE TRANSPORT ET MOBILITÉPROGRAMME DOCTORAL EN GÉNIE ÉLECTRIQUE Suisse2017PARMarija NIKOLIĆ" df577a89830be69c1bfb196e925df3055cafc0ed,"Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions","Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions Bichen Wu, Alvin Wan∗, Xiangyu Yue∗, Peter Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, Kurt Keutzer UC Berkeley" df372ccb1b3220f877e0db8c21c603e57897bfce,Human Detection Based on a Probabilistic Assembly of Robust Part Detectors,"Some Interesting Papers at ECCV 2004 Tim Cootes∗ June 11, 2004 The European Conference on Computer Vision took place in Prague 11-15 May 2004. There were 41 presentations nd about 149 posters, selected from 550 submissions. This document summarises a few that caught my attention. There are probably quite a few very interesting or worthy papers that I’ve failed to include, due to my failing memory and lack of judgement. Simultaneous Object Recognition and Segmentation by Image Exploration V. Ferraria and T. Tuytelaars and L. Van Gool [7] • Extends part based object detection to find heavily occluded things in cluttered scenes • Looks for matches of af‌f‌ine invariant patches on model and image • Takes each putative match and attempts to extend it, the idea being that if one part of the object matches t a particular point in the image, then nearby object structure should be found at a predictable position. • The additional matches so generated are then pruned using consistancy constraints • Iterating gradually extends matches over most of visible object area, and suppresses most of false matches • Impressive results, demonstrating system works even with considerable clutter and occlusion Recognition by Probabalistic Hypothesis Construction P. Moreels and M. Maire and P. Perona [13] • Extension of Perona’s work, simplifying model. Human Detection Based on a Probabalistic Assembly of Robust Part Detectors" dfd18b71f5c53ec2a95fcbe327cf7710da3b4851,Robust Submodular Maximization: A Non-Uniform Partitioning Approach,"Robust Submodular Maximization: A Non-Uniform Partitioning Approach Ilija Bogunovic 1 Slobodan Mitrovi´c 2 Jonathan Scarlett 1 Volkan Cevher 1" df3b560a5d6c8cc5fa1477d3a89245a0d3b60715,Human tracking with multiple parallel metrics,"Human tracking with multiple parallel metrics P. M. Birch*, W. Hassan, R. C. D. Young, C.R. Chatwin Dept. of Engineering and Design, University of Sussex, Falmer, UK, BN1 9QT Keywords: HOG, Correlation, Tracking" df3178e77fa6655bbcae65c00b732ef240d99fa5,SOFT-SLAM : Computationally Efficient Stereo Visual SLAM for Autonomous UAVs,"SOFT-SLAM: Computationally Ef‌f‌icient Stereo Visual SLAM for Autonomous UAVs Igor Cviˇsi´c University of Zagreb Josip ´Cesi´c University of Zagreb Faculty of Electrical Engineering and Computing Faculty of Electrical Engineering and Computing HR-10000, Zagreb, Croatia HR-10000, Zagreb, Croatia Ivan Markovi´c University of Zagreb Ivan Petrovi´c University of Zagreb Faculty of Electrical Engineering and Computing Faculty of Electrical Engineering and Computing HR-10000, Zagreb, Croatia HR-10000, Zagreb, Croatia" ca48c87bbba1a07cf126cf3bb04a53d1758d66f5,Semantic Segmentation of Highly Structured and Weakly Structured Images. (Segmentation sémantique d'images fortement structurées et faiblement structurées),"Semantic Segmentation of Highly Structured and Weakly Structured Images Raghu Deep Gadde To cite this version: Raghu Deep Gadde. Semantic Segmentation of Highly Structured and Weakly Structured Images. Signal and Image Processing. Université Paris-Est, 2017. English. . HAL Id: tel-01743925 https://pastel.archives-ouvertes.fr/tel-01743925 Submitted on 26 Mar 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" cace0a45de20f12df44e4aa07c07ccdd0278b787,Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network,"Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network Matthieu Grard1,2, Romain Br´egier1,3, Florian Sella1, Emmanuel Dellandr´ea2, and Liming Chen2 Sil´eane, 17 rue Descartes, F-42000 St ´Etienne, France Universit´e de Lyon, CNRS, ´Ecole Centrale de Lyon LIRIS UMR5205, F-69134 Lyon, France Univ. Grenoble Alpes, Inria, CNRS Grenoble INP, LIG, F-38000 Grenoble, France" ca400e0c7a739ce5555b2e3eccccbcea65e71b11,Neural Mechanisms of Emotion Regulation in Autism Spectrum Disorder.,"J Autism Dev Disord DOI 10.1007/s10803-015-2359-z S I : E M O T I O N R E G U L A T I O N A N D P S Y C H I A T R I C C O M O R B I D I T Y I N A S D Neural Mechanisms of Emotion Regulation in Autism Spectrum Disorder J. Anthony Richey • Cara R. Damiano • Antoinette Sabatino • Alison Rittenberg • Chris Petty • Josh Bizzell • James Voyvodic • Aaron S. Heller • Marika C. Coffman • Moria Smoski • Richard J. Davidson • Gabriel S. Dichter Ó Springer Science+Business Media New York 2015 ccount of" ca37eda56b9ee53610c66951ee7ca66a35d0a846,Semantic Concept Discovery for Large-Scale Zero-Shot Event Detection,"Semantic Concept Discovery for Large-Scale Zero-Shot Event Detection Xiaojun Chang1,2, Yi Yang1, Alexander G. Hauptmann2, Eric P. Xing3 and Yao-Liang Yu3∗ Centre for Quantum Computation and Intelligent Systems, University of Technology Sydney. Language Technologies Institute, Carnegie Mellon University. Machine Learning Department, Carnegie Mellon University. {cxj273, {alex, epxing," ca581cd5bd0cecf346f2bc47f4b67bfee31b9da1,"Providing Fairness in Heterogeneous Multicores with a Predictive, Adaptive Scheduler","Providing Fairness in Heterogeneous Multicores with a Predictive, Adaptive Scheduler Saeid Barati University of Chicago Henry Hoffmann University of Chicago" cad7845e9668884caf4842b14983ec0e45bbbc75,Urban Tracker: Multiple object tracking in urban mixed traffic,"Urban Tracker: Multiple Object Tracking in Urban Mixed Traffic Jean-Philippe Jodoin, Guillaume-Alexandre Bilodeau LITIV lab., Dept. of computer & software eng. ´Ecole Polytechnique de Montr´eal Montr´eal, QC, Canada Nicolas Saunier Dept. of civil, geo. and mining eng. ´Ecole Polytechnique de Montr´eal Montr´eal, QC, Canada" cacd51221c592012bf2d9e4894178c1c1fa307ca,Face and Expression Recognition Techniques : A Review,"ISSN: 2277-3754 ISO 9001:2008 Certified International Journal of Engineering and Innovative Technology (IJEIT) Volume 4, Issue 11, May 2015 Face and Expression Recognition Techniques: A Review Advanced Communication & Signal Processing Laboratory, Department of Electronics & Communication engineering, Government College of Engineering Kannur, Kerala, India. Rishin C. K, Aswani Pookkudi, A. Ranjith Ram" cae87d5a724507e06f6d8178cfbec043db854fe3,Bayesian Nonparametric Latent Feature Models,"Bayesian Nonparametric Latent Feature Models Kurt Miller Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2011-78 http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-78.html June 28, 2011" cad24ba99c7b6834faf6f5be820dd65f1a755b29,"Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes","Understanding hand-object manipulation by modeling the ontextual relationship between actions, grasp types and object attributes Minjie Cai1, Kris M. Kitani2 and Yoichi Sato1 Journal Title XX(X):1–14 (cid:13)The Author(s) 2016 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/ToBeAssigned www.sagepub.com/" cae68d5af3c3c6167aa9b2247ca27efe75992ccd,Face recognition: handling data misalignments implicitly by fusion of sparse representations,"Received on 10th February 2014 Revised on 8th May 2014 Accepted on 10th June 2014 doi: 10.1049/iet-cvi.2014.0039 www.ietdl.org ISSN 1751-9632 Face recognition: handling data misalignments implicitly by fusion of sparse representations Hugo Proença, João Neves, Juan Briceño Department of Computer Science, Instituto de Telecomunicações, University of Beira Interior, 6200 Covilhã, Portugal E-mail:" ca0363d29e790f80f924cedaf93cb42308365b3d,Facial Expression Recognition in Image Sequences Using Geometric Deformation Features and Support Vector Machines,"Facial Expression Recognition in Image Sequences using Geometric Deformation Features and Support Vector Machines Irene Kotsiay and Ioannis Pitasy,Senior Member IEEE yAristotle University of Thessaloniki Department of Informatics Box 451 54124 Thessaloniki, Greece email:" cad52d74c1a21043f851ae14c924ac689e197d1f,From Ego to Nos-Vision: Detecting Social Relationships in First-Person Views,"From Ego to Nos-vision: Detecting Social Relationships in First-Person Views Stefano Alletto, Giuseppe Serra, Simone Calderara, Francesco Solera and Rita Cucchiara Universit`a degli Studi di Modena e Reggio Emilia Via Vignolese 905, 41125 Modena - Italy" ca7be47d26abdc6fd3f229e9827484e91dbd7752,ADAPTED FUSION SCHEMES FOR MULTIMODAL BIOMETRIC AUTHENTICATION,"UNIVERSIDAD POLIT´ECNICA DE MADRID ESCUELA T´ECNICA SUPERIOR DE INGENIEROS DE TELECOMUNICACI ´ON DEPARTAMENTO DE SE ˜NALES, SISTEMAS Y RADIOCOMUNICACIONES ADAPTED FUSION SCHEMES FOR MULTIMODAL BIOMETRIC AUTHENTICATION –TESIS DOCTORAL– ESQUEMAS ADAPTADOS DE FUSI ´ON PARA AUTENTICACI ´ON BIOM ´ETRICA MULTIMODAL Author: Juli´an Fi´errez Aguilar (Ingeniero de Telecomunicaci´on, UPM) A Thesis submitted for the degree of: Doctor of Philosophy Madrid, May 2006" ca228b42de0f0311f4826292a2996d3348ca43fe,Modeling and Inferring Human Intents and Latent Functional Objects for Trajectory Prediction,"FOR REVIEW: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Modeling and Inferring Human Intents and Latent Functional Objects for Trajectory Prediction Dan Xie, Tianmin Shu, Sinisa Todorovic and Song-Chun Zhu" ca754b826476b3e4083a0a6fbac3ac39b494fd43,Supporting data-driven I/O on GPUs using GPUfs,"Supporting data-driven I/O on GPUs using GPUfs Sagi Shahar Mark Silberstein Technion - Israel Institute of Technology Technion - Israel Institute of Technology Computations on large data sets necessarily involve file ccesses, but current GPUs cannot access a host file system directly because they lack file system access support. There- fore, an application developer needs to coordinate GPU ac- esses to secondary storage via explicit application-level management code running on a CPU. This code performs file accesses on GPU’s behalf and manages low level data transfers to/from GPU memory. Furthermore, all the data that a GPU may need must be resident in the GPU mem- ory prior to computations, and it is the responsibility of a GPU developer to ensure that this is the case. As a result, all the potential GPU accesses to data must be known before the GPU execution starts. This requirement impedes the use of GPUs to run data processing algorithms with irregular data ccess pattern on large datasets." cabe652bb3b150f35db9db1434cec69f081c4a60,Towards Scene Understanding : Deep and Layered Recognition and Heuristic Parsing of Objects,"Towards Scene Understanding: Deep and Layered Recognition nd Heuristic Parsing of Objects Dissertation Submitted to Xi’an Jiaotong University In partial fulfillment of the requirement for the degree of Doctor of Engineering Science Yang Wu (Control Science and Engineering) Supervisor: Prof. Nanning Zheng May 2010" ca6b2b75db9ff8444744df9149601a4ef2beefd4,MirBot: A Multimodal Interactive Image Retrieval System,"MirBot: A multimodal interactive image retrieval system Antonio Pertusa, Antonio-Javier Gallego, and Marisa Bernabeu DLSI, University of Alicante http://www.dlsi.ua.es" cac3bf3ceba79e6a6c8e51eb44c6862b81661f85,Learning Data-Driven Representations for Robust Monocular Computer Vision Applications,"Learning Data-Driven Representations for Robust Monocular Computer Vision Applications Dissertation der Mathematisch-Naturwissenschaftlichen Fakultät der Eberhard Karls Universität Tübingen zur Erlangung des Grades eines Doktors der Naturwissenschaften (Dr. rer.-nat.) Dipl.-math. Christian Joachim Herdtweck vorgelegt von us Stuttgart Tübingen" ca1accedbc1c698c03e9835d9f960c40e9d3ef51,Implementing a Cloud Platform for Autonomous Driving,"Implementing a Cloud Platform for Autonomous Driving Shaoshan Liu, Jie Tang, Chao Wang, Quan Wang, and Jean-Luc Gaudiot, Fellow, IEEE unified driving support utonomous infrastructure" ca494a2f20c267210a677ed9c509c4570f420fdf,Learning to Globally Edit Images with Textual Description,"Learning to Globally Edit Images with Textual Description Hai Wang † Jason D. Williams ‡ Sing Bing Kang §" ca8dc160836a87055579ea9bc4fc379a95f3156a,Face Recognition Based on Nonlinear DCT Discriminant Feature Extraction Using Improved Kernel DCV,"IEICE TRANS. INF. & SYST., VOL.E92–D, NO.12 DECEMBER 2009 LETTER Face Recognition Based on Nonlinear DCT Discriminant Feature Extraction Using Improved Kernel DCV Sheng LI†, Student Member, Yong-fang YAO†, Xiao-yuan JING†a), Heng CHANG†, Shi-qiang GAO†, David ZHANG††, and Jing-yu YANG†††, Nonmembers SUMMARY This letter proposes a nonlinear DCT discriminant feature extraction approach for face recognition. The proposed approach first se- lects appropriate DCT frequency bands according to their levels of nonlin- ear discrimination. Then, this approach extracts nonlinear discriminant fea- tures from the selected DCT bands by presenting a new kernel discriminant method, i.e. the improved kernel discriminative common vector (KDCV) method. Experiments on the public FERET database show that this new pproach is more effective than several related methods. key words: DCT frequency bands selection, the improved KDCV, nonlinear DCT feature extraction, face recognition Introduction Discrete cosine transform (DCT) is a widely used im- ge processing technique [1], and discriminant analysis is" 214db8a5872f7be48cdb8876e0233efecdcb6061,Semantic-Aware Co-Indexing for Image Retrieval,"Semantic-aware Co-indexing for Image Retrieval Shiliang Zhang2, Ming Yang1, Xiaoyu Wang1, Yuanqing Lin1, Qi Tian2 NEC Laboratories America, Inc. Dept. of CS, Univ. of Texas at San Antonio Cupertino, CA 95014 San Antonio, TX 78249" 21f2f1693fdb6478a8f3306f377f1ce7df6e036e,3D Face Recognition,"Chapter 1 D Face Recognition Berk G¨okberk, Albert Ali Salah, Ne¸se Aly¨uz, Lale Akarun .1 Introduction Face is the natural assertion of identity: We show our face as proof of who we re. Due to this widely accepted cultural convention, face is the most widely ccepted biometric modality. Face recognition has been a specialty of human vision: Something humans re so good at that even a days-old baby can track and recognize faces. Computer vision has long strived to imitate the success of human vision and in most cases, has come nowhere near its performance. However, the recent Face Recognition Vendor Test (FRVT06), has shown that automatic algorithms have caught up with the performance of humans in face recognition [73]. How has this increase in performance come about? This can partly be ttributed to the advances in 3D face recognition in the last decade. 3D face recognition has important advantages over 2D; it makes use of shape and texture channels simultaneously, where the texture channel carries 2D image information. However, it is registered with the shape channel, and intensity an now be associated with shape attributes such as the surface normal. The shape channel does not suffer from certain problems that the texture" 21b0b2f5df87318912d58d3b843da363a4fb91c3,"Distributed and Higher-Order Graphical Models: towards Segmentation, Tracking, Matching and 3D Model Inference Defended by","ECOLECENTRALEPARISPHDTHESIStoobtainthetitleofDoctorofEcoleCentraleParisSpecialty:APPLIEDMATHEMATICSDistributedandHigher-OrderGraphicalModels:towardsSegmentation,Tracking,Matchingand3DModelInferenceDefendedbyChaohuiWANGpreparedatEcoleCentraleParis,MASlaboratorydefendedonSeptember29,2011JURYChairman:Prof.HenriMAITRE-TélécomParisTechReviewers:Prof.MichaelJ.BLACK-MaxPlanckInstituteforIntelligentSystemsProf.PhilipH.S.TORR-OxfordBrookesUniversityAdvisor:Prof.NikosPARAGIOS-EcoleCentraleParisExaminers:Prof.PatrickBOUTHEMY-INRIA-RennesProf.VladimirKOLMOGOROV-InstituteofScienceandTechnologyAustriaProf.DimitrisSAMARAS-StonyBrookUniversity" 21ac5d1c34675bf6056d2670f9fa3dde530b1716,ALB at SemEval-2018 Task 10: A System for Capturing Discriminative Attributes,"Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 963–967 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics" 218595e1979007ccd6b1bc5a30a3484841c0eafa,Discovering Beautiful Attributes for Aesthetic Image Analysis,"Noname manuscript No. (will be inserted by the editor) Discovering beautiful attributes for aesthetic image analysis Luca Marchesotti · Naila Murray · Florent Perronnin Received: date / Accepted: date" 21262e01039e5994114b4c102fc80e9afa3f1bde,Pedestrian Detection and Tracking in Thermal Images from Aerial MPEG Videos, 2118b1ce0c2551e75d30fb6ba24482e50b319a90,Ensemble Projection for Semi-supervised Image Classification,"Ensemble Projection for Semi-supervised Image Classification Dengxin Dai Computer Vision Lab, ETH Zurich Luc Van Gool Computer Vision Lab, ETH Zurich" 21ef129c063bad970b309a24a6a18cbcdfb3aff5,Individual and Inter-related Action Unit Detection in Videos for Affect Recognition,"POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCESacceptée sur proposition du jury:Dr J.-M. Vesin, président du juryProf. J.-Ph. Thiran, Prof. D. Sander, directeurs de thèseProf. M. F. Valstar, rapporteurProf. H. K. Ekenel, rapporteurDr S. Marcel, rapporteurIndividual and Inter-related Action Unit Detection in Videos for Affect RecognitionTHÈSE NO 6837 (2016)ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNEPRÉSENTÉE LE 19 FÉVRIER 2016À LA FACULTÉ DES SCIENCES ET TECHNIQUES DE L'INGÉNIEURLABORATOIRE DE TRAITEMENT DES SIGNAUX 5PROGRAMME DOCTORAL EN GÉNIE ÉLECTRIQUE Suisse2016PARAnıl YÜCE" 21d7130230162af2a4cc1b9375bfe9b37dbbd499,Origami: A 803-GOp/s/W Convolutional Network Accelerator,"ARXIV PREPRINT Origami: A 803 GOp/s/W Convolutional Network Accelerator Lukas Cavigelli, Student Member, IEEE, and Luca Benini, Fellow, IEEE these algorithms is essential" 218b2c5c9d011eb4432be4728b54e39f366354c1,Enhancing Training Collections for Image Annotation: An Instance-Weighted Mixture Modeling Approach,"Enhancing Training Collections for Image Annotation: An Instance-Weighted Mixture Modeling Approach Neela Sawant, Student Member, IEEE, James Z. Wang, Senior Member, IEEE, Jia Li, Senior Member, IEEE." 21a9f713a664374bfdcca6f4c8f267b85e63ad7a,Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions,"FINDING STRUCTURE WITH RANDOMNESS: PROBABILISTIC ALGORITHMS FOR CONSTRUCTING APPROXIMATE MATRIX DECOMPOSITIONS N. HALKO , P. G. MARTINSSON , AND J. A. TROPP" 21a1654b856cf0c64e60e58258669b374cb05539,"You Only Look Once: Unified, Real-Time Object Detection","You Only Look Once: Unified, Real-Time Object Detection Joseph Redmon∗, Santosh Divvala∗†, Ross Girshick¶, Ali Farhadi∗† University of Washington∗, Allen Institute for AI†, Facebook AI Research¶ http://pjreddie.com/yolo/" 2170636d5d31eb461618b5da10f4473c67e74e73,Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function,"Person Re-Identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, Nanning Zheng Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University,Xi’an, Shaanxi, P.R. China" 2198a3d3342442d6ed6608f2e2b0687f644b67d6,Dynamic High Resolution Deformable Articulated Tracking,"Dynamic High Resolution Deformable Articulated Tracking Aaron Walsman Weilin Wan Tanner Schmidt Dieter Fox Paul G. Allen School of Computer Science and Engineering University of Washington" 21967faefa55857c6a09f9fe52a10a394757d59c,Emotion Recognition Ability Test Using JACFEE Photos: A Validity/Reliability Study of a War Veterans' Sample and Their Offspring,"RESEARCH ARTICLE Emotion Recognition Ability Test Using JACFEE Photos: A Validity/Reliability Study of War Veterans' Sample and Their Offspring Ivone Castro-Vale1,5*, Milton Severo2,3, Davide Carvalho4,5, Rui Mota-Cardoso1 Medical Psychology Unit, Department of Clinical Neurosciences and Mental Health, Faculty of Medicine, University of Porto, Porto, Portugal, 2 Department of Clinical Epidemiology, Predictive Medicine and Public Health, Faculty of Medicine, University of Porto, Porto, Portugal, 3 Department of Medical Education and Simulation, Faculty of Medicine, University of Porto, Porto, Portugal, 4 Department of Endocrinology, Diabetes and Metabolism, Centro Hospitalar Sāo Joāo, Faculty of Medicine, University of Porto, Porto, Portugal, 5 Instituto de Investigação e Inovação em Saúde, Universidade do Porto, Porto, Portugal 11111" 21241d07840e3cc30feda59642571a9b459c817b,Biometrics via Oculomotor Plant Characteristics: Impact of Parameters in Oculomotor Plant Model,"This is a pre-print. Final version of the paper will be available at ACM digital library. Biometrics via Oculomotor Plant Characteristics: Impact of Parameters in Oculomotor Plant Model OLEG KOMOGORTSEV, COREY HOLLAND, ALEX KARPOV, AND LARRY R. PRICE Texas State University This paper proposes and evaluates a novel biometric approach utilizing the internal, non-visible, anatomical structure of the human eye. The proposed method estimates the anatomical properties of the human oculomotor plant from the measurable properties of human eye movements, utilizing a two-dimensional linear homeomorphic model of the oculomotor plant. The derived properties are evaluated within a biometric framework to determine their efficacy in both verification and identification scenarios. The results suggest that the physical properties derived from the oculomotor plant model are capable of achieving 20.3% equal error rate and 65.7% rank-1 identification rate on high-resolution equipment involving 32 subjects, with biometric samples taken over four recording sessions; or 22.2% equal error rate and 12.6% rank-1 identification rate on low-resolution equipment involving 172 subjects, with biometric samples taken over two recording sessions. Categories and Subject Descriptors: I.2.10 [Artificial Intelligence]: Vision and Scene Understanding—Modeling and recovery of physical ttributes; I.5.1 [Pattern Recognition]: Models—Structural; I.6.4 [Simulation and Modeling]: Model Validation and Analysis General Terms: Biometrics Additional Key Words and Phrases: Human oculomotor system, biological system modeling, mathematical model, security and protection. ACM Reference Format: Komogortsev, O., Holland, C., Karpov, A., and Price, L. R. 2014. Oculomotor Plant Characteristics: Biometric Performance Evaluation. ACM Trans. Appl. Percept. 2, 3, Article 1 (May 2014), 13 pages. DOI:http://dx.doi.org/10.1145/0000000.0000000 INTRODUCTION" 210cc7fb206355a795b1c50ac8d17445e4546747,Nonparametric Belief Propagation and Facial Appearance Estimation,"m a s s a c h u s e t t s i n s t i t u t e o f t e c h n o l o g y — a r t i f i c i a l i n t e l l i g e n c e l a b o r a t o r y Nonparametric Belief Propagation and Facial Appearance Estimation Erik B. Sudderth, Alexander T. Ihler, William T. Freeman and Alan S. Willsky AI Memo 2002-020 December 2002 © 2 0 0 2 m a s s a c h u s e t t s i n s t i t u t e o f t e c h n o l o g y, c a m b r i d g e , m a 0 2 1 3 9 u s a — w w w. a i . m i t . e d u" 213a579af9e4f57f071b884aa872651372b661fd,Automatic and Efficient Human Pose Estimation for Sign Language Videos,"Int J Comput Vis DOI 10.1007/s11263-013-0672-6 Automatic and Efficient Human Pose Estimation for Sign Language Videos James Charles · Tomas Pfister · Mark Everingham · Andrew Zisserman Received: 4 February 2013 / Accepted: 29 October 2013 © Springer Science+Business Media New York 2013" 2129304075990cd2f3317ea67a2acf52b7d7a3e2,Face Recognition and Detection through Similarity Measurements,"International Journal of Computer Applications (0975 – 8887) Volume 174 – No.3, September 2017 Face Recognition and Detection through Similarity Measurements Irfan Bashir M.Tech( CSE) Schoral SMVDU, Kakryal Katra, Jummu" 2168ec12eff5c3d1ff09d0f3c13d6df5b5061164,Face recognition with salient local gradient orientation binary patterns,"978-1-4244-5654-3/09/$26.00 ©2009 IEEE ICIP 2009" 2114b25727a21275e88e30dad0423752f6047dae,Generic Visual Recognition on Non-Uniform Distributions Based on AdaBoost Codebooks,"Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'11 | Generic Visual Recognition on Non-Uniform Distributions Based on AdaBoost Codebooks Mohammad Mahdi Dehshibi, Member IEEE Faculty of Electrical, Computer, and IT, Islamic Azad University Qazvin Branch, Qazvin, Iran Seyed Meysam Alavi Islamic Azad University Hamedan Branch, Hamedan, Iran in several rather further improve introducing tasks are conducted to demonstrate lustering, but locality-sensitive hashing the proposed method can" 21b16df93f0fab4864816f35ccb3207778a51952,Recognition of Static Gestures Applied to Brazilian Sign Language (Libras),"Recognition of Static Gestures applied to Brazilian Sign Language (Libras) Igor L. O. Bastos Math Institute Michele F. Angelo, Angelo C. Loula Department of Technology, Department of Exact Sciences Federal University of Bahia (UFBA), State University of Feira de Santana (UEFS) Salvador, Brazil Feira de Santana, Brazil" 2186944cd69dc4fe680dcea50e45c15905eac2e6,Modular PCA and Probabilistic Similarity Measure for Robust Face Recognition,"Modular PCA and Probabilistic Similarity Measure for Robust Face Recognition Kwanyong Lee1 and Hyeyoung Park2 Korea National Open University, Seoul, Korea School of Electrical Engineering and Computer Science Kyungpook National University, Daegu, Korea" 21160be824d97e66fcd7d55ed502b36d3e691c1f,Assessment of Deep Convolutional Neural Networks for Road Surface Classification,"Assessment of Deep Convolutional Neural Networks for Road Surface Classification Marcus Nolte, Nikita Kister and Markus Maurer Institute of Control Engineering Technische Universit¨at Braunschweig Email: {nolte, Braunschweig, Germany" 21679eb7e953bd132803703c27dcd56484d497e6,"utism , oxytocin and interoception","Neuroscience and Biobehavioral Reviews 47 (2014) 410–430 Contents lists available at ScienceDirect Neuroscience Biobehavioral Reviews j o u r n a l h o m e p a g e : w w w . e l s e v i e r . c o m / l o c a t e / n e u b i o r e v Review Autism, oxytocin and interoception E. Quattrocki∗, Karl Friston 1 The Wellcome Trust Centre for Neuroimaging, UCL, 12 Queen Square, London WC1N 3BG, UK Article history: Received 5 February 2014 Received in revised form 23 July 2014 Accepted 20 September 2014 Available online 30 September 2014 Keywords: Autism Oxytocin Interoception Bayesian predictive coding" 21e666abe02b1cab090825199471db7f744aa424,A REAL-TIME FACE RECOGNITION SYSTEM USING MULTIPLE MEAN FACES AND I DUAL MODE FISHEFWACES,"A REAL-TIME FACE RECOGNITION SYSTEM USING MULTIPLE MEAN FACES AND DUAL MODE FISHEFWACES Jongmoo Choi, Sanghoon Lee, Chilgee Lee, Juneho Yi School of Electrical and Computer Engineering S ungkyunkw an University 00, ChunChundong, Jangan-guy Suwon 440-746, Korea Cjmchoi, armofgod, cslee, jhyi}" 2151b0aec991bfc609d46d10107d4622150c806f,Improving the Effectiveness of Local Feature Detection,"Improving the Effectiveness of Local Feature Detection Shoaib Ehsan A thesis submitted for the degree of Doctor of Philosophy t the School of Computer Science and Electronic Engineering University of Essex May 2012" 216c61796c6ead27b1042046e1d95a2038624d26,Vehicle Re-identification Using Quadruple Directional Deep Learning Features,"Vehicle Re-identification Using Quadruple Directional Deep Learning Features Jianqing Zhu, Huanqiang Zeng, Jingchang Huang, Shengcai Liao, Zhen Lei, Canhui Cai and LiXin Zheng" 216081f7e3ac058b2bad7609676193f50da24db9,Misleading first impressions: different for different facial images of the same person.,"http://pss.sagepub.com/ Misleading First Impressions: Different for Different Facial Images of the Same Person Alexander Todorov and Jenny M. Porter 2014 25: 1404 originally published online 27 May 2014 DOI: 10.1177/0956797614532474 The online version of this article can be found at: http://pss.sagepub.com/content/25/7/1404 Published by: http://www.sagepublications.com On behalf of: Additional services and information for can be found at: Email Alerts: http://pss.sagepub.com/cgi/alerts Subscriptions: http://pss.sagepub.com/subscriptions Reprints: http://www.sagepub.com/journalsReprints.nav Permissions: http://www.sagepub.com/journalsPermissions.nav" 2155739f578e33449546f45a0b4cf64dbd614025,FaceReader Methodology Note what is facereader ?,"FaceReader Methodology Note what is facereader? FaceReader™ is a program for facial analysis. It can detect facial expressions. FaceReader has been trained to classify expressions in one of the following categories: happy, sad, angry, surprised, scared, disgusted, and neutral. These emotional categories have been described by Ekman [1] s the basic or universal emotions. In addition to these asic emotions, contempt can be classified as expression, just like the other emotions [2]. Obviously, facial expres- sions vary in intensity and are often a mixture of emo- tions. In addition, there is quite a lot of interpersonal variation. Figure 1. Analyzing facial expressions with FaceReader. FaceReader has been trained to classify the expressions mentioned above. It is not possible to add expressions to the software yourself. Please contact Noldus Information Technology if you are interested in the classification of other expressions." 21913787b7ed62773926a287b60308d1960e6966,LR-CNN for fine-grained classification with varying resolution,"LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION M. Chevalier(1,2), N. Thome(1), M. Cord(1), J. Fournier(2), G. Henaff(2), E. Dusch(2) (1) Sorbonne Universit´es, UPMC Univ Paris 06, LIP6, 4 place Jussieu 75005 Paris, France (2) Thales Optronique S.A.S., 2 avenue Gay-Lussac, 78990 Elancourt, France" 21ff1d20dd7b3e6b1ea02036c0176d200ec5626d,Loss Max-Pooling for Semantic Image Segmentation,"Loss Max-Pooling for Semantic Image Segmentation Samuel Rota Bul`o(cid:63),† Gerhard Neuhold† Peter Kontschieder† Mapillary - Graz, Austria - (cid:63)FBK - Trento, Italy -" 21e5a220734de4d6509996223c48778559f77358,Gender Identification from Facial Image using Compound Local Binary Pattern ( CLBP,"International Journal of Computer Applications (0975 – 8887) Volume 100– No.3, August 2014 Gender Identification from Facial Image using Compound Local Binary Pattern (CLBP) Emam Hossain Ahsanullah University of Science and Technology, Dhaka, Bangladesh Shayla Azad Bhuyan BRAC University, Dhaka, Bangladesh Faisal Ahmed Islamic University of Technology, Dhaka, Bangladesh robust feature descriptor" 72c37e7507439fc6de2b8385d8842f0805b095b6,A Study of Filtering Approaches for Sliding Window Pedestrian Detection,"A Study of Filtering Approaches for Sliding Window Pedestrian Detection Artur Jord˜ao Lima Correia, Victor Hugo Cunha de Melo, William Robson Schwartz Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil Email:" 72ecaff8b57023f9fbf8b5b2588f3c7019010ca7,Facial Keypoints Detection,"Facial Keypoints Detection Shenghao Shi" 72944b4266523effe97708bff89e1d57d6aebf50,Multisensory Versus Unisensory Integration : Contrasting Modes in the Superior Colliculus,"A Multi-Sensory, Automated and Accelerated Sensory Integration Program The Research Below are several published research reports that document the efficacy of a singular program such as auditory therapy or visual therapy alone as well as the use of multi-sensory programs using one or more sensory programs together. This is only a sample of the volumes of research that has been done. Multisensory integration of cross-modal stimulus combinations yielded responses that were significantly greater than those evoked by the best component stimulus. J Neurophysiol 97: 3193–3205, 2007. doi:10.1152/jn.00018.2007. Multisensory Versus Unisensory Integration: Contrasting Modes in the Superior Colliculus, Juan Carlos Alvarado, J. William Vaughan, Terrence R. Stanford, and Barry E. Stein Department of Neurobiology and Anatomy, Wake Forest University School of Medicine, Winston-Salem, North Carolina When sound and touch were activated simultaneously, the activation of the uditory cortex was strongest. Auditory information in conjunction with tactile input assists with making tactile decisions. Tactile and auditory stimulation simultaneously and individually may positively impact neuroplastic changes in individuals with neurological deficits or impairments. Used singularly, sound" 727d03100d4a8e12620acd7b1d1972bbee54f0e6,von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification,"von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification Md. Abul Hasnat, Julien Bohn´e, Jonathan Milgram, St´ephane Gentric and Liming Chen" 72c32e48a82b2ef2da26c78b4b8c8b4ec888d062,Impact of the GSM and CDMA Mobile Phone Networks on the Strength of Speech Evidence in Forensic Voice Comparison,"rnal of F o rensic ISSN: 2157-7145 Journal of Forensic Research Nair BBT et al, J Forensic Res 2016, 7:2 DOI: 10.4172/2157-7145.1000324 Research Article Impact of the GSM and CDMA Mobile Phone Networks on the Strength of Speech Evidence in Forensic Voice Comparison Open Access Balamurali B T Nair1,2*, Esam A S Alzqhoul1,2 and Bernard J Guillemin1,2 Forensic and Biometrics Research Group (FaB), The University of Auckland, New Zealand Department of Electrical and Computer Engineering, The University of Auckland, New Zealand Corresponding author: Balamurali B T Nair, Ph D., The University of Auckland, New Zealand, E-mail: Received date: Nov 22, 2015;Accepted date: May 11, 2016; Published date: May 25, 2016 Copyright: © 2016 Nair BBT, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited." 72c248c8d3bd76e2a31963aad7286b8d06ab7f8e,Looking outside of the Box: Object Detection and Localization with Multi-scale Patterns.,"Looking outside of the Box: Object Detection and Localization with Multi-scale Patterns Eshed Ohn-Bar, Student Member, IEEE, and Mohan Manubhai Trivedi, Fellow, IEEE" 727c8c696c6acc04e57b6c3541613702c22c6f0f,Optimal discrete wavelet transform (DWT) features for face recognition,"010 Asia Pacific Conference on Circuits and Systems (APCCAS 2010) 6 - 9 December 2010, Kuala Lumpur, Malaysia Optimal Discrete Wavelet Transform (DWT) Features for Face Recognition Paul Nicholl School of Electronics, Electrical Engineering & Computer Science Queen’s Univ., Northern Ireland Email: Afandi Ahmad Abbes Amira JEC, Faculty of. Elec. and Electronic Eng. Univ. Tun Hussein Onn Malaysia NIBEC, Faculty of Comp. and Eng. Univ. of Ulster, Jordanstown Campus Johor, Malaysia Email: Northern Ireland Email:" 72ef87fb1a49f0e386f123a6b4f5566f51a3a47d,Minimizing Latency for Secure Coded Computing Using Secret Sharing via Staircase Codes,"Minimizing Latency for Secure Coded Computing Using Secret Sharing via Staircase Codes Rawad Bitar, Parimal Parag, and Salim El Rouayheb" 729a30040132909cda0eab2c6c4ba60d6d1941b5,Image-based Plant Species Identification with Deep Convolutional Neural Networks,"Image-based Plant Species Identification with Deep Convolutional Neural Networks Mario Lasseck Museum für Naturkunde Berlin, Germany" 729a9d35bc291cc7117b924219bef89a864ce62c,Recognizing Material Properties from Images.,"Recognizing Material Properties from Images Gabriel Schwartz and Ko Nishino, Senior Member, IEEE" 7214d9356398aa39923c69650bcf761d4ab6307f,Improving Spatial Saliency Using Affinity Model and Temporal Motion,"Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'15 | Improving Spatial Saliency Using Affinity Model and Temporal Motion Dept. of Computer and Communications Engineering, Kangwon National University Manbae Kim Chunchon, Gangwondo, Republic of Korea E-mail:" 72a1ecfcd5f0b022fef49cab72bb476e41dea40e,Bag-of-features representations using spatial visual vocabularies for object classification,"BAG-OF-FEATURES REPRESENTATIONS USING SPATIAL VISUAL VOCABULARIES FOR OBJECT CLASSIFICATION Rene Grzeszick, Leonard Rothacker, Gernot A. Fink TU Dortmund Email: {rene.grzeszick, leonard.rothacker, Department of Computer Science" 725597072c76dad5caa92b7baa6e1c761addc300,Deep adversarial neural decoding,"Deep adversarial neural decoding Ya˘gmur Güçlütürk*, Umut Güçlü*, Katja Seeliger, Sander Bosch, Rob van Lier, Marcel van Gerven, Radboud University, Donders Institute for Brain, Cognition and Behaviour Nijmegen, the Netherlands *Equal contribution" 728f656a4e8525112618badc15b2cf04669f3bc0,Learning structure-from-motionfrom motion,"Learning structure-from-motion from motion Cl´ement Pinard1,2, Laure Chevalley2, Antoine Manzanera1, and David Filliat1 ENSTA ParisTech Computer Science and System Engineering Department {clement.pinard, antoine.manzanera, Palaiseau, France Parrot, Paris, France" 727ecf8c839c9b5f7b6c7afffe219e8b270e7e15,AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"LEVERAGING GEO-REFERENCED DIGITAL PHOTOGRAPHS A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Mor Naaman July 2005" 7249b263d0a84d2d9d03f2f7b378778d129f9af9,Research Statement Research Focus,"RESEARCH STATEMENT Ryan Farrell In recent years, the topic of object detection/recognition has rapidly gained in popularity and is now perhaps the most actively researched topic in computer vision. Object detection algorithms are becoming prevalent in consumer devices such as digital cameras (real-time face detection) and automobiles (pedestrian detection systems for collision avoidance are already available and will be a standard feature on new cars within a few years). Object recognition technology is quickly becoming widespread in smartphone apps; examples include Google Goggles, Amazon Flow and Leafsnap. I believe we are at a ‘tipping point’ towards the impending ubiquity of computer vision, specifically object recognition, in our everyday lives. RESEARCH FOCUS My research in object recognition focuses specifically on Fine-grained Visual Categorization (sometimes bbreviated FGVC). For many years, computer vision has focused on classifying an object in several basic- level categories such as person, car, frog, or piano. At the opposing end of the categorization spectrum (see Figure ) is biometric identification - recognizing individuals within a population (e.g. face recognition or recognizing individual whales by unique fluke patterns). Between these two extremes lie what are called entry- nd subordinate-level categories. Entry-level categories include penguin, owl, etc.; people generally use these more specific labels instead of simply saying “bird” (the basic-level category). Subordinate-level categories re highly specific. Continuing with the example of birds, categorizing at the subordinate-level would require differentiating two quite similar species (such as the Red-breasted and White-breasted Nuthatches). Fine- grained recognition addresses this situation where categories are distinguised by very subtle differences." 724a493411b7c5a904445406d3037df4a22b6c89,Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation,"Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation Panagiotis Meletis and Gijs Dubbelman" 722364dc6205074a75a0caf3c1b4d2f27f5eb794,Uncertainty Constrained Robotic Exploration: An Integrated Exploration Planner,"An Extended Treatment of Uncertainty Constrained Robotic Exploration: An Integrated Exploration Planner Alexander Ivanov1 and Mark Campbell2" 72a00953f3f60a792de019a948174bf680cd6c9f,Understanding the role of facial asymmetry in human face identification,"Stat Comput (2007) 17:57–70 DOI 10.1007/s11222-006-9004-9 Understanding the role of facial asymmetry in human face identification Sinjini Mitra · Nicole A. Lazar · Yanxi Liu Received: May 2005 / Accepted: September 2006 / Published online: 30 January 2007 C(cid:1) Springer Science + Business Media, LLC 2007" 72f8df596eb9bb3a8c8206329083c42e70fcd9fd,Will People Like Your Image?, 72edc24c67c34b5f2c98086a689bf0f3591e393d,An Introduction to Image Synthesis with Generative Adversarial Nets,"An Introduction to Image Synthesis with Generative Adversarial Nets He Huang, Phillip S. Yu and Changhu Wang" 725a45ad75caf0112d649253f8a69793b1f00e80,LIFEisGAME : An approach to the utilization of serious games for therapy for children with ASD,"LIFEisGAME: An approach to the utilization of serious games for therapy for children with ASD Tiago Fernandes1,5, Samanta Alves2, José Miranda3,5, Cristina Queirós2, Verónica Instituto de Telecomunicações, Lisboa, Portugal, Faculdade de Psicologia da Universidade do Porto, Porto, Portugal, Instituto Politécnico da Guarda, Porto, Portugal, Faculdade de Ciências da Universidade do Porto, Porto, Portugal, 5 Faculdade de Engenharia da Universidade do Porto, Porto, Portugal, Orvalho1,4" 72a79f351d4ae03ff940ff920898e41ce960f58e,Author's Personal Copy Backtracking: Retrospective Multi-target Tracking,"(This is a sample cover image for this issue. The actual cover is not yet available at this time.) This article appeared in a journal published by Elsevier. The attached opy is furnished to the author for internal non-commercial research nd education use, including for instruction at the authors institution nd sharing with colleagues. Other uses, including reproduction and distribution, or selling or licensing copies, or posting to personal, institutional or third party websites are prohibited. In most cases authors are permitted to post their version of the rticle (e.g. in Word or Tex form) to their personal website or institutional repository. Authors requiring further information regarding Elsevier’s archiving and manuscript policies are encouraged to visit: http://www.elsevier.com/copyright" 721fbc63a647239158bf817311d1c084455398e9,Shape-based automatic detection of a large number of 3D facial landmarks,"Shape-based Automatic Detection of a Large Number of 3D Facial Landmarks Syed Zulqarnain Gilani, Faisal Shafait, Ajmal Mian School of Computer Science and Software Engineering,The University of Western Australia. Figure 3: Histogram of mean localization error for 18 landmarks on 4,007 scans of FRGCv2 dataset (18× 4007 Landmarks). Mean Localization Error(mm) Neutral Non−Neutral Neutral Level−1 Level−2 Level−3 Level−4 Figure 1: Our algorithm automatically detects an arbitrarily large number of facial landmarks by establishing dense correspondences between 3D faces. The figure shows 85 landmarks detected (red) on neutral and extreme anger expression of a subject from BU3DFE database [3]. The ground truth is represented by blue dots. 2202 Mean Localization Error(mm)" 7227c1d8f53279041822266c7a6d0ac128e96d05,Multi-view People Tracking via Hierarchical Trajectory Composition,"Multi-view People Tracking via Hierarchical Trajectory Composition∗ Yuanlu Xu1, Xiaobai Liu2, Yang Liu1 and Song-Chun Zhu1 Dept. Computer Science and Statistics, University of California, Los Angeles (UCLA) Dept. Computer Science, San Diego State University (SDSU)" 722221f6c696b4a7cc094748aaad8158990ec41e,3D facial expression recognition: A perspective on promises and challenges,"D Facial Expression Recognition: A Perspective on Promises and Challenges T. Fang, X. Zhao, O. Ocegueda, S.K. Shah and I.A. Kakadiaris*" 72f4c415b5f3ecf63380b6985c95c5af2ba72632,Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset,"ACTIVITY RECOGNITION ON A LARGE SCALE IN SHORT VIDEOS - MOMENTS IN TIME DATASET Ankit Parag Shah* ∗ Harini Kesavamoorthy* Poorva Rane* Pramati Kalwad* Alexander Hauptmann Florian Metze" 7276a3ffa0941524083ac0fa9f0129746bca65d7,Multi-scale Deep Learning Architectures for Person Re-identification,"Multi-scale Deep Learning Architectures for Person Re-identification Xuelin Qian1 Yanwei Fu2,5,* Yu-Gang Jiang1,3 Tao Xiang4 Xiangyang Xue1,2 Shanghai Key Lab of Intelligent Info. Processing, School of Computer Science, Fudan University; School of Data Science, Fudan University; 3Tencent AI Lab; Queen Mary University of London; 5University of Technology Sydney;" 72591a75469321074b072daff80477d8911c3af3,Group Component Analysis for Multiblock Data: Common and Individual Feature Extraction,"Group Component Analysis for Multi-block Data: Common and Individual Feature Extraction Guoxu Zhou, Andrzej Cichocki Fellow, IEEE, Yu Zhang, and Danilo Mandic Fellow, IEEE" 72a6044a0108e0f8f1e68cd70ada46c81a416324,Improved Training of Generative Adversarial Networks Using Representative Features,"Improved Training of Generative Adversarial Networks using Representative Features Duhyeon Bang 1 Hyunjung Shim 1" 721d9c387ed382988fce6fa864446fed5fb23173,Assessing Facial Expressions in Virtual Reality Environments, 72a87f509817b3369f2accd7024b2e4b30a1f588,Fault diagnosis of a railway device using semi-supervised independent factor analysis with mixing constraints,"Fault diagnosis of a railway device using semi-supervised independent factor analysis with mixing constraints Etienne Côme, Latifa Oukhellou, Thierry Denoeux, Patrice Aknin To cite this version: Etienne Côme, Latifa Oukhellou, Thierry Denoeux, Patrice Aknin. Fault diagnosis of a railway device using semi-supervised independent factor analysis with mixing constraints. Pattern Analysis and Applications, Springer Verlag, 2012, 15 (3), pp.313-326. HAL Id: hal-00750589 https://hal.archives-ouvertes.fr/hal-00750589 Submitted on 11 Nov 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 728a8c4ed6b5565a250bd1e0587293a6a97f515b,Arguing Machines: Human Supervision of Black Box AI Systems That Make Life-Critical Decisions,"Arguing Machines: Human Supervision of Black Box AI Systems That Make Life-Critical Decisions Lex Fridman* Li Ding Massachusetts Institute of Technology (MIT) Benedikt Jenik Bryan Reimer Figure 1: “Arguing machines” framework that adds a secondary system to a primary “black box” AI system that makes life- ritical decisions and uses disagreement between the two as a signal to seek human supervision. We demonstrate that this can e a powerful way to reduce overall system error." 72ef0ac03d3043bf664ca7c21abafc4191b24557,Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection,"Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection Di Feng1, Lars Rosenbaum1, Klaus Dietmayer2" 7278f4c361f960b2e54275c5efd98535f9ccaded,Image Based Recognition of Dynamic Traffic Situations by Evaluating the Exterior Surrounding and Interior Space of Vehicles,"IMAGE BASED RECOGNITION OF DYNAMIC TRAFFIC SITUATIONS BY EVALUATING THE EXTERIOR SURROUNDING AND INTERIOR SPACE OF VEHICLES Photogrammetry & Remote Sensing, Technische Universitaet Muenchen, Germany - (alexander.hanel, ludwig.hoegner, BMW Research & Technology, Muenchen, Germany - A. Hanela, H. Klödenb, L. Hoegnera, U. Stillaa KEY WORDS: vehicle camera system, crowd sourced data, image analysis, machine learning, object detection, illumination recogni- tion, traffic situation recognition" 7238e8f34c662af74b81de80fa6c01838a06b349,Combining SVMS for face class modeling,"COMBINING SVMS FOR FACE CLASS MODELING Julien Meynet, Vlad Popovici, Matteo Sorci and Jean-Philippe Thiran Ecole Polytechnique F·ed·erale de Lausanne (EPFL) Signal Processing Institute CH-1015 Lausanne, Switzerland http://itswww.ep(cid:3).ch" 72367499712525a9f82d0a1d844e2a76d749304d,Multi-layer Biometric System for the Port of Los Angeles Final Report,"Multi-Layer Biometric System for the Port of Los Angeles Final Report METRANS Project 11-19 July 2012 Principal Investigator: Xiaolong Wu Associate Professor Co-Principal Investigator: Burkhard Englert Professor California State University Long Beach Department of Computer Engineering and Computer Science 250 Bellflower Boulevard Long Beach, CA 90840 Tel: (562) 985-5291 Fax: (562) 985-7823 Email:" 72c0c8deb9ea6f59fde4f5043bff67366b86bd66,Age progression in Human Faces : A Survey,"Age progression in Human Faces : A Survey Narayanan Ramanathan, Rama Chellappa and Soma Biswas" 7252b7146697e7a7e33bddb5c49f18af2d0fc9db,Learning to See : Genetic and Environmental Influences on Visual Development,"Copyright James Albert Bednar" 72cebd7d046080899703ed3cd96e3019a9f60f13,Interpreting Visual Question Answering Models,"Towards Transparent AI Systems: Interpreting Visual Question Answering Models Yash Goyal, Akrit Mohapatra, Devi Parikh, Dhruv Batra {ygoyal, akrit, parikh, Virginia Tech" 72d067a6e1fd447ef512262248ad5f73823a3842,Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms,"Probabilistic Models for D Urban Scene Understanding from Movable Platforms Dissertation Dipl.-Inform. Andreas Geiger" 034050422f90938a43e9cfd292187aef124fef61,Race recognition from face images using Weber local descriptor,"Paper 1569528513 IWSSIP 2012, 11-13 April 2012, Vienna, Austria . INTRODUCTION" 034f7d5b3878f8b2db92a7cb7f12edcd5681eca7,FAST Pre-Filtering-Based Real Time Road Sign Detection for Low-Cost Vehicle Localization,"Article FAST Pre-Filtering-Based Real Time Road Sign Detection for Low-Cost Vehicle Localization Kyoungtaek Choi 1, Jae Kyu Suhr 2 Department of Electronic Engineering, Korea National University of Transportation, 50 Daehak-ro, nd Ho Gi Jung 1,* Chungju-si 27469, Korea; School of Intelligent Mechatronics Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul 05006, Korea; * Correspondence: Tel. +82-43-841-5366 Received: 11 September 2018; Accepted: 16 October 2018; Published: 22 October 2018" 03a9affced96b1554b6208ff148617fdfde6712c,Error Detector Facial Landmarks Checker 2 . Face Normalization Facial Proportions Extractor Facial Landmarks Extractor Noise Mask Similarity Computation System Forensic Examiner,"Repositorio Institucional de la Universidad Autónoma de Madrid https://repositorio.uam.es Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: 013 International Workshop on Biometrics and Forensics (IWBF). IEEE, 2013 DOI: http://dx.doi.org/10.1109/IWBF.2013.6547306 Copyright: © 2013 IEEE El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription" 038277dbfcd767b0a0899de42d3277b5b253cc8e,TR-IIS-14-003 Review and Implementation of High-Dimensional Local Binary Patterns and Its Application to Face Recognition,"TR-IIS-14-003 Review and Implementation of High-Dimensional Local Binary Patterns and Its Application to Face Recognition Bor-Chun Chen, Chu-Song Chen, Winston Hsu July. 24, 2014 || Technical Report No. TR-IIS-14-003 http://www.iis.sinica.edu.tw/page/library/TechReport/tr2014/tr14.html" 037e17ac0272b4db0d4761067dbf0ee56d91e6dd,A New Multi-modal Dataset for Human Affect Analysis,"A New Multi-Modal Dataset for Human Affect Analysis nonymous for review nonymous for review" 03f4c0fe190e5e451d51310bca61c704b39dcac8,CHEAVD: a Chinese natural emotional audio–visual database,"J Ambient Intell Human Comput DOI 10.1007/s12652-016-0406-z O R I G I N A L R E S E A R C H CHEAVD: a Chinese natural emotional audio–visual database Ya Li1 • Jianhua Tao1,2,3 • Linlin Chao1 • Wei Bao1,4 • Yazhu Liu1,4 Received: 30 March 2016 / Accepted: 22 August 2016 Ó Springer-Verlag Berlin Heidelberg 2016" 0328b975b11fd4153010535d1a06cf618f9b0c91,Evaluating the complexity of databases for person identification and verification,"IDIAP Martigny - Valais - Suisse EvaluatingtheComplexity ofDatabasesforPerson Identificationand Verification G.Thimm,S.Ben-Yacoub,J.Luettin IDIAP{RR - revisedinJanuary, submittedforpublication PDalleMolle Institute forPerceptualArtificial Intelligence(cid:15)P.O.Box (cid:15) Martigny(cid:15)Valais(cid:15)Switzerland phone+(cid:0)(cid:0) +(cid:0)(cid:0) internethttp://www.idiap.ch" 032825000c03b8ab4c207e1af4daeb1f225eb025,A Novel Approach for Human Face Detection in Color Images Using Skin Color and Golden Ratio,"J. Appl. Environ. Biol. Sci., 7(10)159-164, 2017 ISSN: 2090-4274 © 2017, TextRoad Publication Journal of Applied Environmental nd Biological Sciences www.textroad.com A Novel Approach for Human Face Detection in Color Images Using Skin Color and Golden Ratio Faizan Ullah*1, Dilawar Shah1, Sabir Shah1, Abdus Salam2, Shujaat Ali1 Department of Computer Science, Bacha Khan University, Charsadda, KPK, Pakistan1 Department of Computer Science, Abdul WaliKhan University, Mardan, KPK, Pakistan2 Received: May 9, 2017 Accepted: August 2, 2017" 0322e69172f54b95ae6a90eb3af91d3daa5e36ea,Face Classification using Adjusted Histogram in Grayscale,"Face Classification using Adjusted Histogram in Grayscale Weenakorn Ieosanurak, and Watcharin Klongdee" 036a8cb922a30d766b0fc0ba5954098a1d2a09f5,Learning Similarities for Rigid and Non-rigid Object Detection,"Learning Similarities for Rigid and Non-Rigid Object Detection Asako Kanezaki The Univ. of Tokyo Emanuele Rodol`a TU Munich Daniel Cremers TU Munich Tatsuya Harada The Univ. of Tokyo" 0321d183932ff1353d59e418847ff5bf8f5df5d2,Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification,"Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification Eric M¨uller-Budack1,2[0000−0002−6802−1241], Kader Pustu-Iren1[0000−0003−2891−9783], and Ralph Ewerth1,2[0000−0003−0918−6297] Leibniz Information Centre for Science and Technology (TIB), Hannover, Germany L3S Research Center, Leibniz Universit¨at Hannover, Germany" 0313f71c856b0732d7e7b46755ca77eede77f2f7,Fast computation of the performance evaluation of biometric systems: Application to multibiometrics,"Fast Computation of the Performance Evaluation of Biometric Systems: Application to Multibiometrics Romain Giot∗, Mohamad El-Abed, Christophe Rosenberger GREYC Laboratory ENSICAEN - University of Caen Basse Normandie - CNRS 6 Boulevard Mar´echal Juin, 14000 Caen Cedex - France" 034f7fcf5a393ac3307ac3609c2b971df6efaff6,Can Synthetic Data Handle Unconstrained Gaze Estimation?,"Can Synthetic Data Handle Unconstrained Gaze Estimation ? Amine Kacete, Renaud Séguier, Michel Collobert, Jérôme Royan To cite this version: Amine Kacete, Renaud Séguier, Michel Collobert, Jérôme Royan. Can Synthetic Data Handle Uncon- strained Gaze Estimation ?. Conférence Nationale sur les Applications Pratiques de l’Intelligence Ar- tificielle, Jul 2017, Caen, France. Conférence Nationale sur les Applications Pratiques de l’Intelligence Artificielle. HAL Id: hal-01561526 https://hal.archives-ouvertes.fr/hal-01561526 Submitted on 12 Jul 2017 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," 03650399cbf53d916d10a507852c9e94a02ee13f,3D faces in motion: Fully automatic registration and statistical analysis,"D Faces in Motion: Fully Automatic Registration and Statistical Analysis Timo Bolkarta,∗, Stefanie Wuhrera Saarland University, Saarbr¨ucken, Germany" 03de6b2a3c81b26eecbec2705173da3dba25ecbb,FineTag: Multi-attribute Classification at Fine-grained Level in Images,"FineTag: Multi-attribute Classification at Fine-grained Level in Images Roshanak Zakizadeh, Michele Sasdelli, Yu Qian and Eduard Vazquez Cortexica Vision Systems, London, UK" 03a65d274dc6caea94f6ab344e0b4969575327e3,CrowdHuman: A Benchmark for Detecting Human in a Crowd,"CrowdHuman: A Benchmark for Detecting Human in a Crowd Shuai Shao∗ Zijian Zhao∗ Boxun Li Tete Xiao Gang Yu Xiangyu Zhang Jian Sun {shaoshuai, zhaozijian, liboxun, xtt, yugang, zhangxiangyu, Megvii Inc. (Face++)" 035ef7b25991b0f7ea841a2270ed053198aab09e,"Retrieval of Images with Objects of Specific Size, Location, and Spatial Configuration","Retrieval of images with objects of specific size, location and spatial configuration Niloufar Pourian B.S. Manjunath Department of Electrical and Computer Engineering University of California, Santa Barbara, United States" 0332ae32aeaf8fdd8cae59a608dc8ea14c6e3136,Large Scale 3D Morphable Models,"Int J Comput Vis DOI 10.1007/s11263-017-1009-7 Large Scale 3D Morphable Models James Booth1 Stefanos Zafeiriou1 · Anastasios Roussos1,3 · Allan Ponniah2 · David Dunaway2 · Received: 15 March 2016 / Accepted: 24 March 2017 © The Author(s) 2017. This article is an open access publication" 03a2235fea70317461222fac05e38ee35ead9711,Implementation of a Computer Vision Algorithm for Onboard Detection of Unmanned Aircraft submitted by Lukáš Bauer,"Implementation of a Computer Vision Algorithm for Onboard Detection Bachelor’s Thesis Review of Unmanned Aircraft submitted by Luk´aˇs Bauer The bachelor’s thesis of Luk´aˇs Bauer is concerned with vision-based algorithms for the detection and localization of UAVs in images from an on-board UAV camera. This is n interesting problem with several applications. The first set of goals included studying different methods for the real-time detection and localization of UAVs, selecting a method for implementation from the candidates, and then integrating and optimizing the selected method as a Robot Operating System (ROS), which operates on the embedded computer of the UAV. The second set of goals included testing the method on simulated and real- word data, evaluating the precision and the computational speed of the implementation on the embedded device, and preparing the system for integration into a formation-control lgorithm. The goals of the thesis were only partially fulfilled. The thesis includes a study of the literature and describes several approaches for object detection. Luk´aˇs Bauer chose the YOLOv2 visual detector and implemented this detector as a ROS node operating on- oard of a UAV. The YOLO detector is a state-of-the-art convolutional neural network that is tuned for real-time object detection. The configuration file and the pre-trained weight file for the YOLO detector are available online. For the given problem it was" 033fde43e6ff235fd560435bc060d5ffd14fb827,Pose Estimation and Tracking of Eating Persons in Real-life Settings,"ASCI { IPA { SIKS tracks, ICT.OPEN, Veldhoven, November 14{15, 2011 Pose Estimation and Tracking of Eating Persons in Real-life Settings Lu Zhang EWI-TUDelft Laurens van der Maaten EWI-TUDelft Nicole Koenderink Wageningen UR, FBR Franck Golbach Wageningen UR, FBR Emile Hendriks EWI-TUDelft" 0365ea467c169134e858bb668a8e19bd251019e7,Orthogonal Neighborhood Preserving Projections: A Projection-Based Dimensionality Reduction Technique,"Orthogonal Neighborhood Preserving Projections: A projection-based dimensionality reduction technique ∗ E. Kokiopoulou † Y. Saad‡ March 21, 2006" 03ea398fcefc53a1bd041346c895aadcffed0261,Learning an Alphabet of Shape and Appearance for Multi-Class Object Detection,"Int J Comput Vis DOI 10.1007/s11263-008-0139-3 Learning an Alphabet of Shape and Appearance for Multi-Class Object Detection Andreas Opelt · Axel Pinz · Andrew Zisserman Received: 28 February 2007 / Accepted: 4 April 2008 © The Author(s) 2008" 033e3fe75da26d8d3dd3cb0f99640181655e6746,From generic to specific deep representations for visual recognition,"Factors of Transferability for a Generic ConvNet Representation Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson {azizpour, razavian, sullivan, atsuto, Computer Vision and Active Perception (CVAP), Royal Institute of Technology (KTH), Stockholm, SE-10044 Sweden Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units ctivation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target). Recent studies have shown this form of representation transfer to be suitable for a wide range of target visual recognition tasks. This paper introduces and investigates several factors affecting the transferability of such representations. It includes parameters for training of the source ConvNet such as its architecture, distribution of the training data, etc. and also the parameters of feature extraction such as layer of the trained ConvNet, dimensionality reduction, etc. Then, y optimizing these factors, we show that significant improvements can be achieved on various (17) visual recognition tasks. We further show that these visual recognition tasks can be categorically ordered based on their distance from the source task such that correlation between the performance of tasks and their distance from the source task w.r.t. the proposed factors is observed. Index Terms—Convolutional Neural Networks, Transfer Learning, Representation Learning, Deep Learning, Visual Recognition I. INTRODUCTION C ONVOLUTIONAL NETWORKS (ConvNets) trace back to the early works on digit and character recognition [11], [23]. Prior to 2012, though, in computer vision field, neural networks were more renowned for their propensity to" 03a8f53058127798bc2bc0245d21e78354f6c93b,Max-margin additive classifiers for detection,"Max-Margin Additive Classifiers for Detection Subhransu Maji and Alexander C. Berg Sam Hare VGG Reading Group October 30, 2009" 03f14159718cb495ca50786f278f8518c0d8c8c9,Can subspace based learning approach perform on makeup face recognition?,"015 IEEE International Conference on Control System, Computing and Engineering, Nov 27 – Nov 29, 2015 Penang, Malaysia 015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE2015) Technical Session 1A – DAY 1 – 27th Nov 2015 Time: 3.00 pm – 4.30 pm Venue: Jintan Topic: Signal and Image Processing .00 pm – 3.15pm .15 pm – 3.30pm .30 pm – 3.45pm .45 pm – 4.00pm .00 pm – 4.15pm .15 pm – 4.30pm .30 pm – 4.45pm A 01 ID3 Can Subspace Based Learning Approach Perform on Makeup Face Recognition? Khor Ean Yee, Pang Ying Han, Ooi Shih Yin and Wee Kuok Kwee A 02 ID35 Performance Evaluation of HOG and Gabor Features for Vision-based" 034addac4637121e953511301ef3a3226a9e75fd,Implied Feedback: Learning Nuances of User Behavior in Image Search,"Implied Feedback: Learning Nuances of User Behavior in Image Search Devi Parikh Virginia Tech" 032c1e19a59cdbeb3fb741a812980f52c1461ce1,"Mining textural knowledge in biological images: Applications, methods and trends","Computational and Structural Biotechnology Journal 15 (2017) 56–67 j o u r n a l h o m e p a g e : w w w . e l s e v i e r . c o m / l o c a t e / c s b j Mining textural knowledge in biological images: Applications, methods nd trends Santa Di Cataldo*, Elisa Ficarra Dept. of Computer and Control Engineering, Politecnico di Torino, Cso Duca degli Abruzzi 24, Torino 10129, Italy A R T I C L E I N F O A B S T R A C T Article history: Received 25 August 2016 Received in revised form 14 November 2016 Accepted 15 November 2016 Available online 24 November 2016 Keywords: Textural analysis Bioimaging Textural features extraction Texture classification Feature encoding" 03b98b4a2c0b7cc7dae7724b5fe623a43eaf877b,Acume: A new visualization tool for understanding facial expression and gesture data,"Acume: A Novel Visualization Tool for Understanding Facial Expression and Gesture Data" 031055c241b92d66b6984643eb9e05fd605f24e2,Multi-fold MIL Training for Weakly Supervised Object Localization,"Multi-fold MIL Training for Weakly Supervised Object Localization Ramazan Gokberk Cinbis Jakob Verbeek Cordelia Schmid Inria∗" 03c56c176ec6377dddb6a96c7b2e95408db65a7a,A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding,"A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding Anis Kacem, Mohamed Daoudi, Boulbaba Ben Amor, Stefano Berretti, and Juan Carlos Alvarez-Paiva" 0306a275e80d11d65c4261b8f3d45317a49c1bf7,Optimal Architecture for Deep Neural Networks with Heterogeneous Sensitivity,"Optimal Architecture for Deep Neural Networks with Heterogeneous Sensitivity Hyunjoong Cho, Jinhyeok Jang, Chanhyeok Lee, and Seungjoon Yang" 03701e66eda54d5ab1dc36a3a6d165389be0ce79,Improved Principal Component Regression for Face Recognition Under Illumination Variations,"Improved Principal Component Regression for Face Recognition Under Illumination Variations Shih-Ming Huang and Jar-Ferr Yang, Fellow, IEEE" 0394040749195937e535af4dda134206aa830258,Geodesic entropic graphs for dimension and entropy estimation in manifold learning,"Geodesic Entropic Graphs for Dimension and Entropy Estimation in Manifold Learning Jose A. Costa and Alfred O. Hero III December 16, 2003" 038ce930a02d38fb30d15aac654ec95640fe5cb0,Approximate structured output learning for Constrained Local Models with application to real-time facial feature detection and tracking on low-power devices,"Approximate Structured Output Learning for Constrained Local Models with Application to Real-time Facial Feature Detection and Tracking on Low-power Devices Shuai Zheng, Paul Sturgess and Philip H. S. Torr" 03ac1c694bc84a27621da6bfe73ea9f7210c6d45,Chapter 1 Introduction to information security foundations and applications,"Chapter 1 Introduction to information security foundations and applications Ali Ismail Awad1,2 .1 Background Information security has extended to include several research directions like user uthentication and authorization, network security, hardware security, software secu- rity, and data cryptography. Information security has become a crucial need for protecting almost all information transaction applications. Security is considered as n important science discipline whose many multifaceted complexities deserve the synergy of the computer science and engineering communities. Recently, due to the proliferation of Information and Communication Tech- nologies, information security has started to cover emerging topics such as cloud omputing security, smart cities’ security and privacy, healthcare and telemedicine, the Internet-of-Things (IoT) security [1], the Internet-of-Vehicles security, and sev- eral types of wireless sensor networks security [2,3]. In addition, information security has extended further to cover not only technical security problems but also social and organizational security challenges [4,5]. Traditional systems’ development approaches were focusing on the system’s usability where security was left to the last stage with less priority. However, the" 03889b0e8063532ae56d36dd9c54c3784a69e4d4,Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence,"Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence Emilio Jorge1, Mikael Kågebäck2, and Emil Gustavsson1 Fraunhofer-Chalmers Centre , Göteborg, Sweden , Computer Science & Engineering , Chalmers University of Technology , Göteborg, Sweden ," 03adcf58d947a412f3904a79f2ab51cfdf0e838a,Video-based face recognition : a survey,"World Journal of Science and Technology 2012, 2(4):136-139 ISSN: 2231 – 2587 Available Online: www.worldjournalofscience.com _________________________________________________________________ Proceedings of ""Conference on Advances in Communication and Computing (NCACC'12)” Held at R.C.Patel Institute of Technology, Shirpur, Dist. Dhule,Maharastra,India. April 21, 2012 Video-based face recognition: a survey Shailaja A Patil1 and Pramod J Deore2 Department of Electronics and Telecommunication, R.C.Patel Institute of Technology,Shirpur,Dist.Dhule.Maharashtra,India." 035c606bc6a05e2018e57859737877043673b7b9,Fine-Grained Image Classification by Exploring Bipartite-Graph Labels,"Fine-grained Image Classification by Exploring Bipartite-Graph Labels Feng Zhou NEC Labs Yuanqing Lin NEC Labs www.f-zhou.com" 03faf0afc44e0e2462dfbfd83ab2e2e7b3874d3e,Gesture control interface for immersive panoramic displays,"Multimed Tools Appl DOI 10.1007/s11042-013-1605-7 Gesture control interface for immersive panoramic displays Marcel Alcoverro· Xavier Suau· Josep R. Morros· Adolfo López-Méndez· Albert Gil· Javier Ruiz-Hidalgo· Josep R. Casas © Springer Science+Business Media New York 2013" 03e83659f0fc98dd03c354a2cc7a90d585ff9cf5,Face Recognition Using Holistic Features and Within Class Scatter-Based PCA,"GSTF JOURNAL ON COMPUTING, VOL. 3, NO. 2, JUNE 2013 (cid:2)(cid:3)(cid:4)(cid:5)(cid:1)(cid:6)(cid:7)(cid:8)(cid:9)(cid:10)(cid:7)(cid:11)(cid:8)(cid:12)(cid:13)(cid:7)(cid:11)(cid:14)(cid:1)(cid:15)(cid:13)(cid:16)(cid:10)(cid:7)(cid:11)(cid:14)(cid:1)(cid:13)(cid:7)(cid:1)(cid:17)(cid:13)(cid:18)(cid:19)(cid:16)(cid:8)(cid:12)(cid:7)(cid:20)(cid:1)(cid:21)(cid:15)(cid:13)(cid:17)(cid:22)(cid:23)(cid:1)(cid:24)(cid:13)(cid:14)(cid:25)(cid:1)(cid:26)(cid:1)(cid:27)(cid:13)(cid:25)(cid:1)(cid:28)(cid:23)(cid:1)(cid:15)(cid:16)(cid:14)(cid:29)(cid:1)(cid:28)(cid:30)(cid:31)(cid:26) DOI 10.7603/s40601-013-0002-4 Face Recognition Using Holistic Features and Within Class Scatter-Based PCA I Gede Pasek Suta Wijaya, Non-Member, IEEE, Keiichi Uchimura, Non-Member, IEEE, Gou Koutaki, Non-Member, IEEE" 0393723dff4c00262c1daf34c26d27fa6fc52ab6,Pedestrian detection in outdoor images using color and gradients,"Pedestrian Detection in Outdoor Images using Color and Gradients Marcel H¨aselich Michael Klostermann Dietrich Paulus Active Vision Group, University of Koblenz-Landau, 56070 Koblenz, Germany {mhaeselich, michaelk," 0315c68902edca77d2c15cfc1f1335d55343c715,Towards optimal distortion-based visual privacy filters,"TOWARDS OPTIMAL DISTORTION-BASED VISUAL PRIVACY FILTERS Pavel Korshunov and Touradj Ebrahimi Multimedia Signal Processing Group, EPFL, Lausanne, Switzerland" 032a1c95388fb5c6e6016dd8597149be40bc9d4d,Finding action tubes,"Finding Action Tubes Georgia Gkioxari UC Berkeley Jitendra Malik UC Berkeley" 030ff7012b92b805a60976f8dbd6a08c1cecebe6,DCAN: Dual Channel-Wise Alignment Networks for Unsupervised Scene Adaptation, 030646f4fc694ffea5d4f77203cbbc5d02aae797,Cognitive Deep Machine Can Train Itself,"Technical Report: NIPG 2016 COGNITIVE DEEP MACHINE CAN TRAIN ITSELF A. L˝orincz, M. Csákvári, Á. Fóthi, Z. Á. Milacski, A. Sárkány & Z. T˝osér Department of Software Technology and Methodology Faculty of Informatics, Eötvös Loránd University Pázmány Péter sétány 1/C, Budapest, Hungary, H-1117" 0313924b600ebb8f608705d96c06b133b3b9627a,Deciphering the Crowd: Modeling and Identification of Pedestrian Group Motion,"Sensors 2013, 13, 875-897; doi:10.3390/s130100875 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article Deciphering the Crowd: Modeling and Identification of Pedestrian Group Motion Zeynep Y¨ucel *, Francesco Zanlungo, Tetsushi Ikeda, Takahiro Miyashita and Norihiro Hagita Intelligent Robotics and Communication Laboratories, Advanced Telecommunications Research Institute International, Kyoto 619-0288, Japan; E-Mails: (F.Z.); (T.I.); (T.M.); (N.H.) * Author to whom correspondence should be addressed; E-Mail: Tel.: +81-774-95-1405. Received: 14 December 2012; in revised form: 20 December 2012 / Accepted: 4 January 2013 / Published: 14 January 2013" 038b8b2b629a8ba1e2ad6f9319e16b68e83e518a,Assessing Water Stress of Desert Tamarugo Trees Using in situ Data and Very High Spatial Resolution Remote Sensing,"Remote Sens. 2013, 5, 5064-5088; doi:10.3390/rs5105064 OPEN ACCESS ISSN 2072-4292 www.mdpi.com/journal/remotesensing Article Assessing Water Stress of Desert Tamarugo Trees Using in situ Roberto O. Chávez 1,*, Jan G. P. W. Clevers 1, Martin Herold 1, Edmundo Acevedo 2 nd Mauricio Ortiz 2,3 6700 AA Wageningen, The Netherlands; E-Mails: (J.G.P.W.C.); (M.H.) Laboratorio de Relación Suelo-Agua-Planta, Facultad de Ciencias Agronómicas, Universidad de Chile, Casilla 1004, Santiago, Chile; E-Mail: (E.A.); (M.O.) Centro de Estudios Avanzados en Fruticultura (CEAF), Conicyt-Regional R08I1001, Av. Salamanca s/n, Rengo, Chile * Author to whom correspondence should be addressed; E-Mails: or Tel.: +31-317-481-552; Fax: +31-317-419-000. Received: 24 July 2013; in revised form: 12 September 2013 / Accepted: 9 October 2013 / Published: 15 October 2013" 03ae36b2ed0215b15c5bc7d42fbe20b1491e551a,Learning scene-specific pedestrian detectors without real data,"Learning Scene-Specific Pedestrian Detectors without Real Data Hironori Hattori1, Vishnu Naresh Boddeti2, Kris Kitani2, Takeo Kanade2 Sony Corporation. 2Carnegie Mellon University. Figure 1: Overview: For every grid location, geometrically correct renderings of pedestrian are synthetically generated using known scene information such as camera calibration parameters, obstacles (red), walls (blue) and walkable areas (green). All location-specific pedestrian detectors are trained jointly to learn a smoothly varying appearance model. Multiple scene-and-location-specific detectors are run in parallel at every grid location. Consider the scenario in which a new surveillance system is installed in a novel location and an image-based pedestrian detector must be trained without access to real scene-specific pedestrian data. A similar situation may arise when a new imaging system (i.e., a custom camera with unique lens distortion) has been designed and must be able to detect pedestrians without the expensive process of collecting data with the new imaging de- vice. One can use a generic pedestrian detection algorithm trained over co- pious amounts of real data to work robustly across many scenes. However, generic models are not always best-suited for detection in specific scenes. In many surveillance scenarios, it is more important to have a customized pedestrian detection model that is optimized for a single scene. Optimiz- ing for a single scene however often requires a labor intensive process of ollecting labeled data – drawing bounding boxes of pedestrians taken with particular camera in a specific scene. The process also takes time, as" 036fac2b87cf04c3d93e8a59da618d56a483a97d,Query Adaptive Late Fusion for Image Retrieval,"MANUSCRIPT Query Adaptive Late Fusion for Image Retrieval Zhongdao Wang, Liang Zheng, Shengjin Wang" 03df507b31691baeb7343d3eb70d048943e2d4f4,Exploring the Use of Local Descriptors for Fish Recognition in LifeCLEF 2015,"Exploring the use of local descriptors for fish recognition in LifeCLEF 2015 Jorge Cabrera-G´amez, Modesto Castrill´on-Santana, Antonio Dom´ınguez-Brito, Daniel Hern´andez-Sosa, Josep Isern-Gonz´alez, and Javier Lorenzo-Navarro Universidad de Las Palmas de Gran Canaria SIANI Spain http://berlioz.dis.ulpgc.es/roc-siani" 03f6d738f9b916f80ce22c3ba605a0fa4d7830c1,Automated Reconstruction of Evolving Curvilinear Tree Structures,"POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCESacceptée sur proposition du jury:Prof. P. Dillenbourg, président du juryProf. P. Fua, directeur de thèseDr F. Moreno-Noguer, rapporteurDr R. Sznitman, rapporteurProf. S. Süsstrunk, rapporteuseAutomated Reconstruction of Evolving Curvilinear Tree StructuresTHÈSE NO 6930 (2016)ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNEPRÉSENTÉE LE 18 MARS 2016À LA FACULTÉ INFORMATIQUE ET COMMUNICATIONSLABORATOIRE DE VISION PAR ORDINATEURPROGRAMME DOCTORAL EN INFORMATIQUE ET COMMUNICATIONS Suisse2016PAR(cid:51)(cid:85)(cid:93)(cid:72)(cid:80)(cid:92)(cid:86)(cid:227)(cid:68)(cid:90)(cid:3)(cid:53)(cid:68)(cid:73)(cid:68)(cid:227)(cid:3)(cid:42)(cid:226)(cid:50)(cid:58)(cid:36)(cid:38)(cid:46)(cid:44)" 03161081b47eba967fd3e663c57ec2f99f66eebd,Face and Facial Feature Localization,"Face and facial feature localization Paola Campadelli?, Raffaella Lanzarotti??, Giuseppe Lipori, and Eleonora Salvi Dipartimento di Scienze dell’Informazione Universit(cid:30)a degli Studi di Milano Via Comelico, 39/41 - 20135 Milano, Italy fcampadelli, lanzarotti, http://homes.dsi.unimi.it/(cid:24)campadel/LAIV/" 03f3bde03f83c3ff4f346d761fde4ce031dd4c69,Deep Models Calibration with Bayesian Neural Networks,"Under review as a conference paper at ICLR 2019 DEEP MODELS CALIBRATION WITH BAYESIAN NEURAL NETWORKS Anonymous authors Paper under double-blind review" cbca355c5467f501d37b919d8b2a17dcb39d3ef9,Super-resolution of Very Low Resolution Faces from Videos,"CANSIZOGLU, JONES: SUPER-RESOLUTION OF VERY LR FACES FROM VIDEOS Super-resolution of Very Low-Resolution Faces from Videos Esra Ataer-Cansizoglu Michael Jones Mitsubishi Electric Research Labs (MERL) Cambridge, MA, USA" cba90ec61155a233fee33b529401e65d9481213a,Houdini: Fooling Deep Structured Prediction Models,"Houdini: Fooling Deep Structured Prediction Models Moustapha Cisse Facebook AI Research Natalia Neverova* Facebook AI Research" cb1214e42fa81977bc21f4b3c8e194a9b68278f5,Visually Aligned Word Embeddings for Improving Zero-shot Learning,"Qiao et al.: Visually Aligned Word Embeddings. Appearing in Proc. British Mach. Vis. Conf. 2017 Visually Aligned Word Embeddings for Improving Zero-shot Learning School of Computer Science, University of Adelaide, Australia Ruizhi Qiao Lingqiao Liu Chunhua Shen Anton van den Hengel" cbe4eac494fa7bc0bcd958d67393f097e0cb17db,A Multi-task Learning Approach for Image Captioning,Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) cb84229e005645e8623a866d3d7956c197f85e11,Disambiguating Visual Verbs,"Disambiguating Visual Verbs Spandana Gella, Frank Keller, and Mirella Lapata" cbef6ee44bb87f54d80ea2ca7d1266bc624d9d07,Deep Graphical Feature Learning for Face Sketch Synthesis,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) cb8b2db657cd6b6ccac13b56e2ca62b7d88eda68,Log Hyperbolic Cosine Loss Improves Varia-,"Under review as a conference paper at ICLR 2019 LOG HYPERBOLIC COSINE LOSS IMPROVES VARIA- TIONAL AUTO-ENCODER Anonymous authors Paper under double-blind review" cb8567f074573a0d66d50e75b5a91df283ccd503,Large Margin Learning in Set-to-Set Similarity Comparison for Person Reidentification,"Large Margin Learning in Set to Set Similarity Comparison for Person Re-identification Sanping Zhou, Jinjun Wang, Rui Shi, Qiqi Hou, Yihong Gong, Nanning Zheng" cbdca5e0f1fd3fd745430497d372a2a30b7bb0c5,Towards Distributed Coevolutionary GANs,"Towards Distributed Coevolutionary GANs Abdullah Al-Dujaili, Tom Schmiedlechner, Erik Hemberg and Una-May O’Reilly CSAIL, MIT, USA" cb7bbede1c2eae831dd73440f439955c4310837f,Cross-Cultural and Cultural-Specific Production and Perception of Facial Expressions of Emotion in the Wild,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Cross-Cultural and Cultural-Specific Production nd Perception of Facial Expressions of Emotion in the Wild Ramprakash Srinivasan, Aleix M. Martinez" cb6be69c67b0b15ebbda89a126f4dd62a4d32958,Igure Qa : a N a Nnotated F Igure D Ataset for V Isual R Easoning,"Workshop track - ICLR 2018 FIGUREQA: AN ANNOTATED FIGURE DATASET FOR VISUAL REASONING Samira Ebrahimi Kahou1∗, Vincent Michalski2∗†, Adam Atkinson1, Ákos Kádár3†, Adam Trischler1, Yoshua Bengio3 Microsoft Research Montréal Université de Montréal, MILA Tilburg University" cb96c819f20f05ad0d85bba91f86795162f63445,Noisy Ocular Recognition Based on Three Convolutional Neural Networks,"Article Noisy Ocular Recognition Based on Three Convolutional Neural Networks Min Beom Lee, Hyung Gil Hong and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (M.B.L.); (H.G.H.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 18 October 2017; Accepted: 14 December 2017; Published: 17 December 2017" cb4418b5bddaaceb92caea9e72c8cc528ce4e3cc,Generative Semantic Manipulation with Contrasting GAN,"Generative Semantic Manipulation with Contrasting Xiaodan Liang, Hao Zhang, Eric P. Xing Carnegie Mellon University and Petuum Inc. {xiaodan1, hao," cb11a150fc245958799e763069a6ae3080814d40,3d Face Recognition from Range Image, cb94ea16f12bde2de91d3cf3fac03a20b02611b1,Element-wise Bilinear Interaction for Sentence Matching,"Proceedings of the 7th Joint Conference on Lexical and Computational Semantics (*SEM), pages 107–112 New Orleans, June 5-6, 2018. c(cid:13)2018 Association for Computational Linguistics" cb4f0656ce177161667759b46e20aec5488550fa,Learning with single view . . .,"Washington University in St. Louis School of Engineering and Applied Science Department of Computer Science and Engineering Dissertation Examination Committee: Kilian Q. Weinberger, Chair John Blitzer John Cunningham Tao Ju Robert Pless Bill Smart Learning with Single View Co-training and Marginalized Dropout Minmin Chen A dissertation presented to the Graduate School of Arts and Sciences of Washington University in partial fulfillment of the requirements for the degree of Doctor of Philosophy May 2013 Saint Louis, Missouri" cb30c1370885033bc833bc7ef90a25ee0900c461,FaceOff: Anonymizing Videos in the Operating Rooms,"FaceOff: Anonymizing Videos in the Operating Rooms Evangello Flouty1, Odysseas Zisimopoulos1, and Danail Stoyanov1,2 Wellcome / ESPRC Centre for Interventional and Surgical Sciences, London, Digital Surgery, London, United Kingdom United Kingdom" cb658e9e0823dc7afe66b593307b230cc2747790,Nouveau modèle pour la datation automatique de photographies à partir de caractéristiques visuelles,"Nouveau modèle pour la datation utomatique de photographies à partir de caractéristiques visuelles1 Paul MARTIN* — Antoine DOUCET** — Frédéric JURIE* * Laboratoire GREYC [UMR 6072], Université de Caen Normandie, FRANCE 14032 {paul.martin ; ** Laboratoire L3i, Université de La Rochelle, FRANCE 17042 RÉSUMÉ. Nous présentons, dans cet article, une méthode de datation de photographies par l’usage du contenu visuel de celles-ci. Nous nous sommes inspirés de travaux récents de la vision par ordinateur. Nous avons amélioré la méthode de classification utilisée dans ces tra- vaux en dépassant une limite intrinsèque de leur approche. En effet, ils considèrent la datation d’images comme un problème de classification multi-classes, pour lequel une classe repré- sente un ensemble d’années, mais ignorant l’ordre relatif sous-jacent à l’information tempo- relle. Dans leur approche soit une prédiction est bonne (période valide) soit elle est mauvaise (période invalide) mais aucune différence n’est faite entre se tromper d’une décennie ou de plusieurs. Nos travaux, s’appuient sur des avancées récentes en classification ordinale. Nous onsidérons les dates comme des attributs à la fois ordonnés et relatifs et nous proposons un adre spécifique pour les manipuler." cb76c7002b9a813405359b2bc2a29756bf426bb4,Combination of In Vogue Algorithms for Human Detection and Tracking,"International Journal of Computer Applications (0975 – 8887) National Conference “Electronics, Signals, Communication and Optimization"" (NCESCO 2015) Combination of In Vogue Algorithms for Human Detection and Tracking Bhuvanarjun K.M. PG Scholar, Signal Processing, Siddaganga Institute of Technology, Tumakuru, Karnataka (India)." cbe859d151466315a050a6925d54a8d3dbad591f,Gaze shifts as dynamical random sampling,"GAZE SHIFTS AS DYNAMICAL RANDOM SAMPLING Giuseppe Boccignone Mario Ferraro Dipartimento di Scienze dell’Informazione Universit´a di Milano Via Comelico 39/41 0135 Milano, Italy" cbae3eaf926aede9bec7ce2e28c35c1c50b1b43f,Fast RGB-D people tracking for service robots,"Noname manuscript No. (will be inserted by the editor) Fast RGB-D People Tracking for Service Robots Matteo Munaro · Emanuele Menegatti Received: date / Accepted: date" cb1018a7eadc1b4f686c15d2abd2723d1e6eeec3,Image-based people detection,"Image-based people detection Tommi Tikkanen (78748P) Valvoja: Arto Visala AS-0.3100 Automaatio- ja systeemitekniikan seminaari Syksy 2013" cb38b4a5e517b4bcb00efbb361f4bdcbcf1dca2c,Learning towards Minimum Hyperspherical Energy,"Learning towards Minimum Hyperspherical Energy Weiyang Liu1,*, Rongmei Lin2,*, Zhen Liu1,*, Lixin Liu3,*, Zhiding Yu4, Bo Dai1,5, Le Song1,6 Georgia Institute of Technology 2Emory University South China University of Technology 4NVIDIA 5Google Brain 6Ant Financial" cbd1a47356d8dc1c46d569d55eb803945193f9b0,SurfConv: Bridging 3D and 2D Convolution for RGBD Images,"SurfConv: Bridging 3D and 2D Convolution for RGBD Images Hang Chu1,2 Wei-Chiu Ma3 Kaustav Kundu1,2 Raquel Urtasun1,2,3 Sanja Fidler1,2 University of Toronto 2Vector Institute 3Uber ATG {chuhang1122, kkundu, {weichiu," cb3d38cd18c99aca9c2a228aeb4998f394c7b1b3,Impairments in facial affect recognition associated with autism spectrum disorders: a meta-analysis.,"# Cambridge University Press 2014 doi:10.1017/S0954579414000479 Impairments in facial affect recognition associated with autism spectrum disorders: A meta-analysis LEAH M. LOZIER, JOHN W. VANMETER, AND ABIGAIL A. MARSH Georgetown University" cb34481714bc7194ac108a1568d34e120f256405,Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7,"Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7 Huda Alamri∗†, Vincent Cartillier∗, Raphael Gontijo Lopes∗, Abhishek Das∗, Jue Wang†, Irfan Essa∗, Dhruv Batra∗, Devi Parikh∗, Anoop Cherian†, Tim K. Marks†, Chiori Hori† School of Interactive Computing, Georgia Tech Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA" cb4fc4d49783f2049c48a062169f04eb744443ec,Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention,"Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention MARCELLA CORNIA, University of Modena and Reggio Emilia LORENZO BARALDI, University of Modena and Reggio Emilia GIUSEPPE SERRA, University of Udine RITA CUCCHIARA, University of Modena and Reggio Emilia Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, nd Recurrent Neural Networks to generate the corresponding captions. At the same time, a significant research effort has been dedicated to the development of saliency prediction models, which can predict human eye fixations. Even though saliency information could be useful to condition an image captioning architecture, by providing an indication of what is salient and what is not, research is still struggling to incorporate these two techniques. In this work, we propose an image captioning approach in which a generative recurrent neural network can focus on different parts of the input image during the generation of the caption, by exploiting the conditioning given by a saliency prediction model on which parts of the image are salient and which are ontextual. We show, through extensive quantitative and qualitative experiments on large scale datasets, that our model achieves superior performances with respect to captioning baselines with and without saliency, nd to different state of the art approaches combining saliency and captioning. CCS Concepts: • Computing methodologies → Scene understanding; Natural language generation; Additional Key Words and Phrases: saliency, visual saliency prediction, image captioning, deep learning." a8eeace37181dd87d5125c213add6e15fdd9d9f7,Approximate Fisher Kernels of Non-iid Image Models for Image Categorization,"Approximate Fisher Kernels of non-iid Image Models for Image Categorization Ramazan Gokberk Cinbis, Jakob Verbeek, and Cordelia Schmid, Fellow, IEEE" a8d41c63462da7dbddf4094eddaa0bb6d72d0fdc,A Semantic-based Method for Visualizing Large Image Collections.,"A Semantic-based Method for Visualizing Large Image Collections Xiao Xie, Xiwen Cai, Junpei Zhou, Nan Cao, Yingcai Wu" a8c58660bf2ee1fddc3ef05ce52c42775eb0b2b7,Multitype Activity Recognition in Robot-Centric Scenarios,"Multi-Type Activity Recognition in Robot-Centric Scenarios Ilaria Gori1, J. K. Aggarwal1, Larry Matthies2, and M. S. Ryoo3" a8ed00afc46064b18a6bcc7aa282e554891eacf2,Underwater image restoration: super-resolution and deblurring via sparse representation and denoising by means of marine snow removal,"Underwater Image Restoration: Super-resolution and Deblurring via Sparse Representation and Denoising by Means of Marine Snow Removal Dissertation Erlangung des akademischen Grades Doktor-Ingenieur (Dr.-Ing) der Fakultät für Informatik und Elektrotechnik der Universität Rostock vorgelegt von Fahimeh Farhadifard geb. am 05.11.1985 in Mashhad/Iran us Rostock Rostock, den 27. Oktober 2017" a856449c724f958dbb2f0629228d26a322153ba3,Face Mask Extraction in Video Sequence,"Face Mask Extraction in Video Sequence Yujiang Wang 1 · Bingnan Luo 1 · Jie Shen 1 · Maja Pantic 1" a870a4672dcdc53f8f85828cb64da50e51f05348,AUDIO-VISUAL PERCEPTION OF HUMANS FOR A HUMANOID ROBOT,"AUDIO-VISUAL PERCEPTION OF HUMANS FOR A HUMANOID ROBOT Kai Nickel, Hazim K. Ekenel, Michael Voit, Rainer Stiefelhagen Interactive Systems Labs Universit¨at Karlsruhe (TH)" a8788ce65d01018a0e1b4cdaf6466f495e68f7e3,A Probabilistic Retrieval Model for Word Spotting based on Direct Attribute Prediction,"A Probabilistic Retrieval Model for Word Spotting based on Direct Attribute Prediction Eugen Rusakov, Leonard Rothacker, Hyunho Mo, and Gernot A. Fink Department of Computer Science TU Dortmund University 4221 Dortmund, Germany Email:{eugen.rusakov, leonard.rothacker, hyunho.mo," a8a30a8c50d9c4bb8e6d2dd84bc5b8b7f2c84dd8,This is a repository copy of Modelling of Orthogonal Craniofacial Profiles,"This is a repository copy of Modelling of Orthogonal Craniofacial Profiles. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/131767/ Version: Published Version Article: Dai, Hang, Pears, Nicholas Edwin orcid.org/0000-0001-9513-5634 and Duncan, Christian (2017) Modelling of Orthogonal Craniofacial Profiles. Journal of Imaging. ISSN 2313-433X https://doi.org/10.3390/jimaging3040055 Reuse This article is distributed under the terms of the Creative Commons Attribution (CC BY) licence. This licence llows you to distribute, remix, tweak, and build upon the work, even commercially, as long as you credit the uthors for the original work. More information and the full terms of the licence here: https://creativecommons.org/licenses/ Takedown If you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing including the URL of the record and the reason for the withdrawal request. https://eprints.whiterose.ac.uk/" a85007fe09e96e13cc30992ba19d71cae75634c6,BlazeIt : An OptimizingQuery Engine for Video at Scale Extended Abstract,BlazeIt: An Optimizing Query Engine for Video at Scale a83fc450c124b7e640adc762e95e3bb6b423b310,Deep Face Feature for Face Alignment and Reconstruction,"Deep Face Feature for Face Alignment Boyi Jiang, Juyong Zhang, Bailin Deng, Yudong Guo and Ligang Liu" a887937b813f267507203d4faef1013043cf09d0,Automatic Process to Build a Contextualized Detector,"AUTOMATIC PROCESS TO BUILD A CONTEXTUALIZED DETECTOR Thierry Chesnais1, Nicolas Allezard1, Yoann Dhome1 and Thierry Chateau2 CEA, LIST, Vision and Content Engineering Laboratory, Point Courrier 94, F-91191 Gif-sur-Yvette, France Lasmea, UMR6602, CNRS, Blaise Pascal University, Clermont-Ferrand, France {thierry.chesnais, nicolas.allezard, video surveillance, object detection, pedestrian detection, semi-supervised learning, oracle. Keywords:" a8d5f1416760dbd8d2993358938f85c7ab04e85a,Robust Multi-person Tracking for Real-Time Intelligent Video Surveillance,"Robust Multi-person Tracking for Real-Time Intelligent Video Surveillance We propose a novel multiple-object tracking algorithm for real-time intelligent video surveillance. We adopt particle filtering as our tracking framework. Background modeling and subtraction are used to generate a region of interest. A two-step pedestrian detection is employed to reduce the computation time of the algorithm, and an iterative particle repropagation method is proposed to enhance its tracking accuracy. A matching score for greedy data association is proposed to assign the detection results of the two-step pedestrian detector to trackers. Various experimental results demonstrate that the proposed algorithm tracks multiple objects accurately and precisely in real time. Keywords: Multiple-object tracking, particle filter, ackground modeling, pedestrian detection, real-time pplications, video surveillance applications. Manuscript received May 22, 2014; revised Jan. 1, 2015; accepted Jan. 17, 2015. This work was partly supported by the ICT R&D program of the MSIP, Rep. of Korea (No." a8bf49021017e19df051a3efb7337d93ea263e37,Deep Multiple Instance Hashing for Object-based Image Retrieval,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) queryRetrieval ResultFigure1:Queryingaboutmultipleobjects.toryresults.Inparticular,theerrorsinthesegmentationstepwillbepropagatedtotheindex,anditisdifficulttofindop-timalhand-craftedfeaturesforindexcreation.Ontheotherhand,mostexistingobject-basedimageretrievalapproachesconcentrateonqueryingbyasingleobject.However,usersmayalsowanttoqueryaboutmultipleobjects,asillustratedinFig.1:intheupperexampletheuserisinterestedinpho-toscontainingbothhumanandhorses,asinthequery;inthelowercasetheusermaywanttowriteapoliticalcommentaryaboutObamaandPutinbutthereisnogroupphotoofthemathand.Duetothelackofabilitytodetectvariousobjects,previousapproacheswillincurpoorperformancewhentheyaredirectlyusedtocopewithmulti-objectqueries.Recentadvancesindeeplearninghaveprovedthatconvo-lutionalneuralnetworks(CNNs)trainedend-to-endcanlearnpowerfulfeaturerepresentations.Intermsofobjectdetec-tion,anumberoftechniquesbasedondeepCNNshavebeenproposed[Renetal.,2015;Liuetal.,2016]andachievedgoodresultsonsomehigh-qualitypublicimagedatasetslikeImageNet,PASCALVOCandMSCOCO.However,theseapproachesnecessitatelarge-scaletrainingdatawithlabelsofobjectlocationstolearnmodelstoharvest“objectness”,whereasthelabelingworkisverytediousandexpensive.Itisoftenthecasethatweonlyhaveimage-levelobjectlabelswithoutobjectlocations,i.e.weaklabelsforobjectdetection" a81d396c9210282d461f9f08b7b9794b096ecdfe,FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising,"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising Kai Zhang, Wangmeng Zuo, Senior Member, IEEE, and Lei Zhang, Fellow, IEEE" a8a45d083e5535812f991afb686b4e36ea9f0717,Face Recognition Using Gradient Derivative Local Binary Patterns,"International Journal of Applied Engineering Research ISSN 0973-4562 Volume 12, Number 7 (2017) pp. 1316-1323 © Research India Publications. http://www.ripublication.com Face Recognition Using Gradient Derivative Local Binary Patterns" a87ab836771164adb95d6744027e62e05f47fd96,Understanding human-human interactions: a survey,"Understanding human-human interactions: a survey Alexandros Stergiou Department of Information and Computing Sciences, Utrecht University,Buys Ballotgebouw, Princetonplein 5, Utrecht, 3584CC, Netherlands Department of Information and Computing Sciences, Utrecht University,Buys Ballotgebouw, Princetonplein 5, Utrecht, 3584CC, Netherlands Ronald Poppe1" a825364ada04007221577d305cbc42d413239f03,LaFiDa - A Laserscanner Multi-Fisheye Camera Dataset,"Article LaFiDa—A Laserscanner Multi-Fisheye Camera Dataset Steffen Urban * and Boris Jutzi * Institute of Photogrammetry and Remote Sensing (IPF) Karlsruhe Institute of Technology (KIT), Englerstr. 7, 76131 Karlsruhe, Germany * Correspondence: (S.U.); (B.J.) Academic Editors: Hassan Ugail, Lihua You and Gonzalo Pajares Martinsanz Received: 22 September 2016; Accepted: 4 January 2017; Published: 17 January 2017" a8e5d204549fcf93c5bea88b0f99a2e4da9648e7,Neuropeptidergic regulation of affiliative behavior and social bonding in animals,"www.elsevier.com/locate/yhbeh Neuropeptidergic regulation of affiliative behavior and social bonding in animals Miranda M. Lim 1, Larry J. Young ⁎ Center for Behavioral Neuroscience, Department of Psychiatry and Behavioral Sciences, and 954 Gatewood Road Yerkes National Primate Research Center, Emory University, Atlanta, GA 30322, USA Received 16 May 2006; revised 26 June 2006; accepted 27 June 2006 Available online 4 August 2006" a8420e7fa53b81b8069ced8d9c743c141e2fc432,Real-Time Multiple Object Tracking - A Study on the Importance of Speed,"Real-TimeMultipleObjectTrackingAStudyontheImportanceofSpeedSAMUELMURRAYMaster’sProgramme,MachineLearningDate:September28,2017Supervisor:KevinSmithExaminer:HedvigKjellströmPrincipal:HelmutPrendinger,NationalInstituteofInformatics,TokyoSwedishtitle:IdentifieringavrörligaobjektirealtidSchoolofComputerScienceandCommunication" a81769a36c9ed7b6146a408eb253eb8e0d3ad41e,Super-Fine Attributes with Crowd Prototyping.,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Super-Fine Attributes with Crowd Prototyping Daniel Martinho-Corbishley, Mark S. Nixon and John N. Carter" a88640045d13fc0207ac816b0bb532e42bcccf36,Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reduction,"ARXIV VERSION Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reduction Yanwei Pang, Senior Member, IEEE, Bo Zhou, and Feiping Nie, Senior Member, IEEE" a8948941f7a24c09cd7c26f3635d8571c7998570,Face recognition of Pose and Illumination changes using Extended ASM and Robust sparse,"IOSR Journal of Dental and Medical Sciences (IOSR-JDMS) e-ISSN: 2279-0853, p-ISSN: 2279-0861.Volume 13, Issue 3 Ver. VI. (Mar. 2014), PP 49-54 www.iosrjournals.org Face recognition of Pose and Illumination changes using Extended ASM and Robust sparse coding Arulmurugan R1, Laxmi Priya M.R2 (Information Technology, Bannari Amman Institute of Technology, India) (Information Technology, Bannari Amman Institute of Technology, India)" a8c776ad5f4e0ccf9a3e6c5073e8951bb11d187a,Spontaneous Inference of Personality Traits and Effects on Memory for Online Profiles,"Spontaneous Inference of Personality Traits and Effects on Memory for Online Profiles Kristin Stecher & Scott Counts University of Washington & Microsoft Research Department of Psychology, 351525, Seattle, WA, 98195 One Microsoft Way, Redmond, WA, 98052" a8638a07465fe388ae5da0e8a68e62a4ee322d68,How to predict the global instantaneous feeling induced by a facial picture,"How to predict the global instantaneous feeling induced y a facial picture? Arnaud Lienhard, Patricia Ladret, Alice Caplier To cite this version: Arnaud Lienhard, Patricia Ladret, Alice Caplier. How to predict the global instantaneous feeling induced by a facial picture?. Signal Processing: Image Communication, Elsevier, 2015, pp.1-30. . HAL Id: hal-01198718 https://hal.archives-ouvertes.fr/hal-01198718 Submitted on 14 Sep 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" a8d3dc5c68032c60ebbe3b547ac948d7cf8dd1d8,Multi-Label Zero-Shot Learning via Concept Embedding,"Multi-Label Zero-Shot Learning via Concept Embedding Ubai Sandouk and Ke Chen" 8c6c0783d90e4591a407a239bf6684960b72f34e,Knowledge Management in a Large Organization : a Practical Case Study,"SESSION KNOWLEDGE ENGINEERING AND MANAGEMENT + KNOWLEDGE ACQUISITION Chair(s) Int'l Conf. Information and Knowledge Engineering | IKE'13 |1" 8c6db488bebf3fb2c50d951c4a9f002a531f9b61,Modeling Multimodal Dynamic Spatiotemporal Graphs,"Modeling Multimodal Dynamic Spatiotemporal Graphs Boris Ivanovic Marco Pavone" 8c7f4c11b0c9e8edf62a0f5e6cf0dd9d2da431fa,Dataset Augmentation for Pose and Lighting Invariant Face Recognition,"Dataset Augmentation for Pose and Lighting Invariant Face Recognition Daniel Crispell∗, Octavian Biris∗, Nate Crosswhite†, Jeffrey Byrne†, Joseph L. Mundy∗ Vision Systems, Inc. Systems and Technology Research" 8c2c4e3db2de3305b1d25368695c258fea6a6076,The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems,"IEEE 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, Hawaii, USA, November 2018 The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems Robert Krajewski, Julian Bock, Laurent Kloeker and Lutz Eckstein Figure 1. Example of a recorded highway including bounding boxes and labels of detected vehicles. The color of the bounding boxes indicates the class of the detected object (car: yellow, truck: green). Every vehicle is assigned a unique id for tracking and its speed is estimated over time." 8cc07ae9510854ec6e79190cc150f9f1fe98a238,Using Deep Learning to Challenge Safety Standard for Highly Autonomous Machines in Agriculture,"Article Using Deep Learning to Challenge Safety Standard for Highly Autonomous Machines in Agriculture Kim Arild Steen *,†, Peter Christiansen †, Henrik Karstoft and Rasmus Nyholm Jørgensen Department of Engineering, Aarhus University, Finlandsgade 22 8200 Aarhus N, Denmark; (P.C.); (H.K.); (R.N.J.) * Correspondence: Tel.: +45-3116-8628 These authors contributed equally to this work. Academic Editors: Francisco Rovira-Más and Gonzalo Pajares Martinsanz Received: 18 December 2015; Accepted: 2 February 2016; Published: 15 February 2016" 8c13f2900264b5cf65591e65f11e3f4a35408b48,A GENERIC FACE REPRESENTATION APPROACH FOR LOCAL APPEARANCE BASED FACE VERIFICATION,"A GENERIC FACE REPRESENTATION APPROACH FOR LOCAL APPEARANCE BASED FACE VERIFICATION Hazim Kemal Ekenel, Rainer Stiefelhagen Interactive Systems Labs, Universität Karlsruhe (TH) 76131 Karlsruhe, Germany {ekenel, web: http://isl.ira.uka.de/face_recognition/" 8cb4349f7d4b04a2e98b727524d3699bad50de1c,SOCIAL GAME EPITOME VERSUS AUTOMATIC VISUAL ANALYSIS Paper ID ***,"SOCIAL GAME EPITOME VERSUS AUTOMATIC VISUAL ANALYSIS Paper ID ***" 8ca29760334b7bdeaa7ad7ae4ff54c3b24420dd2,Analysis of Dynamic Characteristics of Spontaneous Facial Expressions,"Analysis of Dynamic Characteristics of Spontaneous Facial Expressions Masashi Komori Yoshitaro Onishi Division of Information and Computer Sciences, Osaka Electro-Communication University, 8-8 Hatsucho, Neyagawa, Osaka, 572-8530, JAPAN" 8c955f3827a27e92b6858497284a9559d2d0623a,"Tom 53 ( 67 ) , Fascicola 1-2 , 2008 Facial Expression Recognition under Noisy Environment Using Gabor Filters","Buletinul Ştiinţific al Universităţii ""Politehnica"" din Timişoara Seria ELECTRONICĂ şi TELECOMUNICAŢII TRANSACTIONS on ELECTRONICS and COMMUNICATIONS Tom 53(67), Fascicola 1-2, 2008 Facial Expression Recognition under Noisy Environment Using Gabor Filters Ioan Buciu1, I. Nafornita2, I. Pitas3" 8c244417db2082f4d5897548e72ef304ae886e52,Tree Based Space Partition of Trajectory Pattern Mining For Frequent Item Sets,"Australian Journal of Basic and Applied Sciences, 10(2) Special 2016, Pages: 250-261 Australian Journal of Basic and Applied Sciences AUSTRALIAN JOURNAL OF BASIC AND AUSTRALIAN JOURNAL OF BASIC AND APPLIED SCIENCES ISSN:1991-8178 EISSN: 2309-8414 Journal home page: www.ajbasweb.com Tree Based Space Partition of Trajectory Pattern Mining For Frequent Tree Based Space Partition of Trajectory Pattern Mining For Frequent Tree Based Space Partition of Trajectory Pattern Mining For Frequent Item Sets nd Engineering , Alagappa University, Tamil Nadu, India. P.Geetha and 2 E. Ramaraj Ph.D scholar, Alagappa University. Department of Computer Science and Engineering Address For Correspondence: P.Geetha, Ph.D scholar, Alagappa University. Ph.D scholar, Alagappa University. A R T I C L E I N F O Article history:" 8c5fa29c9bcab3d518fdf355e9da62fb0b58905e,Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation,"Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation st Pierluigi Zama Ramirez University of Bologna nd Alessio Tonioni University of Bologna rd Luigi Di Stefano University of Bologna" 8c0f38c7c07c631d0b5414a84dda2992bdc4514f,Development of an Efficient Face Recognition System Based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 8c5852530abaefcdce805d1e339677351c6ec7fe,Lernen situationsunabhängiger Personenerkennung,"{ HAUPTBEITRAG / SITUATIONSUNABHÄNGIGE PERSONENERKENNUNG Lernen situationsunabhängiger Personenerkennung Marco K. Müller · Michael Tremer Christian Bodenstein · Rolf P. Würtz Einleitung In den vergangenen 25 Jahren hat sich automati- sche Gesichtserkennung von einem akademischen Projekt zu einer reifen Technik entwickelt. Bei der Frage, ob es sich auf zwei Fotos um die gleiche Per- son handelt, sind kommerzielle Systeme inzwischen sogar Menschen überlegen [6]. Dies ist nicht mit der Erkennung von bekannten Personen zu verwech- seln, die der Mensch in sehr vielen verschiedenen Situationen auch nach vielen Jahren wiedererkennen kann. Es ist eine zentrale Aufgabe des Computersehens, ekannte Objekte in Bildern wiederzuerkennen. Dies ist schwierig, weil dasselbe Objekt in verschiede- nen Situationen sehr verschiedene Bilder erzeugt." 8cb6daba2cb1e208e809633133adfee0183b8dd2,Know Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models,"Know Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models Ashesh Jain, Hema S Koppula, Bharad Raghavan, Shane Soh, Ashutosh Saxena Cornell University and Stanford University" 8c63bf3b7b35d4ba6309cf19a181f6aaf8b83435,Sustained striatal activity predicts eudaimonic well-being and cortisol output.,"http://pss.sagepub.com/ Aaron S. Heller, Carien M. van Reekum, Stacey M. Schaefer, Regina C. Lapate, Barry T. Radler, Carol D. Ryff and Richard Sustained Striatal Activity Predicts Eudaimonic Well-Being and Cortisol Output J. Davidson 2013 24: 2191 originally published online 20 September 2013 DOI: 10.1177/0956797613490744 The online version of this article can be found at: http://pss.sagepub.com/content/24/11/2191 Published by: http://www.sagepublications.com On behalf of: Additional services and information for can be found at: Email Alerts: http://pss.sagepub.com/cgi/alerts Subscriptions: http://pss.sagepub.com/subscriptions Reprints: http://www.sagepub.com/journalsReprints.nav Permissions:" 8c3c699f568ee825eefc4dc44b71c8b0bc592cca,Binary Multi-View Clustering.,"Binary Multi-View Clustering Zheng Zhang†, Li Liu†, Fumin Shen, Heng Tao Shen, Ling Shao*" 8c305b2d8982135da852cb005dcf602a02f04118,FAST RADIOMETRY GUIDED FUSION OF DISPARITY IMAGES,"FAST RADIOMETRY GUIDED FUSION OF DISPARITY IMAGES Stephan Schmida, Dieter Fritschb Institute for Photogrammetry, University of Stuttgart - Daimler AG - Commission III, WG III/1 KEY WORDS: Disparity fusion, multi-view stereo, real-time stereo, machine vision, photo-consistency" 8ce9b7b52d05701d5ef4a573095db66ce60a7e1c,Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework,"Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework Chun-Guang Li, Chong You, and Ren´e Vidal" 8ce4a669358dadbfac69ff0d313af042aeb94de1,Pedestrian intention recognition using Latent-dynamic Conditional Random Fields,"Pedestrian Intention Recognition using Latent-dynamic Conditional Random Fields Andreas Th. Schulz1 and Rainer Stiefelhagen2" 8cf3b70f9247be23de9cc42272464e0363acb426,Multi-label classification of a real-world image dataset,"Multi-label classification of a real-world image dataset Nikita Uvarov Applied Computer Science Submission date: June 2017 Supervisor: Co-supervisor: Rune Hjelsvold, IDI Faouzi Alaya Cheikh, IDI Norwegian University of Science and Technology Department of Computer Science" 8c30b154811453b6a1017bb27e3becefde44f689,Bibliometric profile of the global scientific research on autism spectrum disorders,"Sweileh et al. SpringerPlus (2016) 5:1480 DOI 10.1186/s40064-016-3165-6 RESEARCH Bibliometric profile of the global scientific research on autism spectrum disorders Waleed M. Sweileh1*, Samah W. Al‑Jabi2, Ansam F. Sawalha1 and Sa’ed H. Zyoud2 Open Access" 8c9b29d6df5601d0bc9f6164d99a26a1cb1e256d,Two-Dimensional Joint Bayesian Method for Face Verification,"J Inf Process Syst, Vol.12, No.3, pp.381~391, September 2016 ISSN 1976-913X (Print) ISSN 2092-805X (Electronic) Two-Dimensional Joint Bayesian Method for Face Verification Sunghyu Han*, Il-Yong Lee**, and Jung-Ho Ahn***" 8cc23e554d98522b377d227dc78e9382a0ed35e5,"Bootstrap, Review, Decode: Using Out-of-Domain Textual Data to Improve Image Captioning","Bootstrap, Review, Decode: Using Out-of-Domain Textual Data to Improve Image Captioning Wenhu Chen RWTH Aachen Aurelien Lucchi ETH Zurich Thomas Hofmann ETH Zurich" b1a40665eb4c0a4c6978e84539ece1c0f406b8f5,Human Visual System Based Framework For Gender Recognition,"Human Visual System Based Framework For Gender Recognition Cherinet G. Zewdie1,2 and Hubert Konik1,2 Universit´e de Lyon, CNRS, 37 Rue du Repos, 69007 Lyon, France Universit´e Jean Monnet, Laboratoire Hubert Curien, UMR5516, 42000 Saint-Etienne, France Keywords: Human Visual System, Gender Recognition, Salient Region, HVS Inspired Gender Recognition, Local Binary Pattern." b183914d0b16647a41f0bfd4af64bf94a83a2b14,Extensible video surveillance software with simultaneous event detection for low and high density crowd analysis,"Extensible Video Surveillance Software with Simultaneous Event Detection for Low and High Density Crowd Analysis Anuruddha L. Hettiarachchi, Heshani O. Thathsarani, Pamuditha U. Wickramasinghe, Dilranjan S. Wickramasuriya and Ranga Rodrigo Department of Electronic and Telecommunication Engineering, University of Moratuwa, Sri Lanka Email: 090184v, 090518c, 090560v, 090561b," b14b672e09b5b2d984295dfafb05604492bfaec5,Apprentissage de Modèles pour la Classification et la Recherche d ’ Images Learning Image Classification and Retrieval Models,LearningImageClassificationandRetrievalModelsThomasMensink b18f94c5296a9cebe9e779d50d193fd180f78ed9,Forecasting Interactive Dynamics of Pedestrians with Fictitious Play,"Forecasting Interactive Dynamics of Pedestrians with Fictitious Play Wei-Chiu Ma1 De-An Huang2 Namhoon Lee3 Kris M. Kitani4 Stanford Oxford" b166ce267ddb705e6ed855c6b679ec699d62e9cb,Sample group and misplaced atom dictionary learning for face recognition,"Turk J Elec Eng & Comp Sci (2017) 25: 4421 { 4430 ⃝ T (cid:127)UB_ITAK doi:10.3906/elk-1702-49 Sample group and misplaced atom dictionary learning for face recognition Meng WANG1;2, Zhengping HU1;(cid:3) , Zhe Sun1, Mei ZHU2, Mei SUN2 Department of Information Science & Engineering, Faculty of Electronics & Communication, Yanshan University, Department of Physics & Electronics Engineering, Faculty of Electronics & Communication, Taishan University, Qinhuangdao, P.R. China Tai’an, P.R. China Received: 04.02.2017 (cid:15) Accepted/Published Online: 01.06.2017 (cid:15) Final Version: 05.10.2017" b1e27fade89e973f4087ed9a243981b0e713b22c,Functional neuroanatomy and the rationale for using EEG biofeedback for clients with Asperger's syndrome.,"Appl Psychophysiol Biofeedback (2010) 35:39–61 DOI 10.1007/s10484-009-9095-0 Functional Neuroanatomy and the Rationale for Using EEG Biofeedback for Clients with Asperger’s Syndrome Lynda Thompson Æ Michael Thompson Æ Andrea Reid Published online: 1 July 2009 Ó Springer Science+Business Media, LLC 2009 nd Oberman" b1edff56936e5d306e51479142b98cc2414c1a56,Human-Centered Autonomous Vehicle Systems: Principles of Effective Shared Autonomy,"Human-Centered Autonomous Vehicle Systems: Principles of E(cid:128)ective Shared Autonomy Massachuse(cid:138)s Institute of Technology (MIT) Lex Fridman Figure 1: Principles of shared autonomy used for the design and development of the Human-Centered Autonomous Vehicle." b18efa91e9893ae5fdfcaf880bae5c569fab4d18,Visual Scanning of Dynamic Affective Stimuli in Autism Spectrum Disorders,"Georgia State University ScholarWorks Georgia State University Psychology Dissertations Department of Psychology 8-1-2012 Visual Scanning of Dynamic Affective Stimuli in Autism Spectrum Disorders Susan M. McManus Georgia State University Follow this and additional works at: http://scholarworks.gsu.edu/psych_diss Recommended Citation McManus, Susan M., ""Visual Scanning of Dynamic Affective Stimuli in Autism Spectrum Disorders."" Dissertation, Georgia State University, 2012. http://scholarworks.gsu.edu/psych_diss/105 This Dissertation is brought to you for free and open access by the Department of Psychology at ScholarWorks Georgia State University. It has been ccepted for inclusion in Psychology Dissertations by an authorized administrator of ScholarWorks Georgia State University. For more information, please contact" b19e83eda4a602abc5a8ef57467c5f47f493848d,Heat Kernel Based Local Binary Pattern for Face Representation,"JOURNAL OF LATEX CLASS FILES Heat Kernel Based Local Binary Pattern for Face Representation Xi Li†, Weiming Hu†, Zhongfei Zhang‡, Hanzi Wang§" b13499d60e7be1d593ec91fc952b9c32ce62bd57,Gambit : A Robust Chess-Playing Robotic System,"Gambit: A Robust Chess-Playing Robotic System Cynthia Matuszek, Brian Mayton, Roberto Aimi, Marc Peter Deisenroth, Liefeng Bo, Robert Chu, Mike Kung, Louis LeGrand, Joshua R. Smith, Dieter Fox" b147baa55e7b6456419d1518ccc9fd16f5ba2db2,An Study on Re-identification in RGB-D Imagery,"An study on re-identification in RGB-D imagery J. Lorenzo-Navarro and M. Castrill´on-Santana and D. Hern´andez-Sosa (cid:63) Instituto Universitario SIANI Universidad de Las Palmas de Gran Canaria Campus de Tafira, 35017 Las Palmas, SPAIN" b13254c2c9ca90f57e385d34abc7fe78d74e5222,Real-Time Multi-object Tracking with Occlusion and Stationary Objects Handling for Conveying Systems,"Real-time Multi-Object Tracking with Occlusion and Stationary Objects Handling for Conveying Systems Adel Benamara, Serge Miguet, Mihaela Scuturici To cite this version: Adel Benamara, Serge Miguet, Mihaela Scuturici. Real-time Multi-Object Tracking with Occlu- sion and Stationary Objects Handling for Conveying Systems. 12th International Symposium on Visual Computing (ISVC’16), Dec 2016, Las Vegas, NV, United States. . HAL Id: hal-01385529 https://hal.archives-ouvertes.fr/hal-01385529 Submitted on 26 Oct 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" b19f24ec92388513d1516d71292559417c776006,CAUSALGAN: LEARNING CAUSAL IMPLICIT GENER-,"Under review as a conference paper at ICLR 2018 CAUSALGAN: LEARNING CAUSAL IMPLICIT GENER- ATIVE MODELS WITH ADVERSARIAL TRAINING Anonymous authors Paper under double-blind review" b1451721864e836069fa299a64595d1655793757,Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking,"Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking James Tompkin,1∗ Kwang In Kim,2∗ Hanspeter Pfister,3 and Christian Theobalt4 Brown University 2University of Bath Harvard University 4Max Planck Institute for Informatics" b17b20c3a3804482a1af3be897758d4f3be26677,Self-calibrating 3D context for retrieving people with luggage,"Self-Calibrating 3D Context for Retrieving People with Luggage Johannes Schels∗ , Joerg Liebelt∗ EADS Innovation Works M¨unchen, Germany Rainer Lienhart University of Augsburg Augsburg, Germany" b1290dff343ae4980e3e853055ad9a5b9116238b,"Gender Classification Based on Fusion of Different Spatial Scale Features Selected by Mutual Information From Histogram of LBP, Intensity, and Shape","Gender Classification Based on Fusion of Different Spatial Scale Features Selected by Mutual Information From Histogram of LBP, Intensity, and Shape Juan E. Tapia, Graduate Student Member, IEEE, and Claudio A. Perez, Senior Member, IEEE" b1ffa7a926e129f8dccdd6f258fea034cbee9160,Minimizing hallucination in histogram of Oriented Gradients,"Minimizing hallucination in Histogram of Oriented Gradients Sławomir B ˛ak Michał Koperski INRIA Sophia Antipolis, STARS group François Brémond 004, route des Lucioles, BP93 06902 Sophia Antipolis Cedex - France Javier Ortiz" b16ff1331f961b2067c9464c491b7cbe90694758,Automatic plankton image classification combining multiple view features via multiple kernel learning,"Zheng et al. BMC Bioinformatics 2017, 18(Suppl 16):570 DOI 10.1186/s12859-017-1954-8 RESEARCH Open Access Automatic plankton image classification ombining multiple view features via multiple kernel learning Haiyong Zheng1, Ruchen Wang1, Zhibin Yu1, Nan Wang1, Zhaorui Gu1 and Bing Zheng2* From 16th International Conference on Bioinformatics (InCoB 2017) Shenzhen, China. 20-22 September 2017 including phytoplankton and zooplankton, are the main source of food for organisms in the" b1d89015f9b16515735d4140c84b0bacbbef19ac,Too Far to See? Not Really!—Pedestrian Detection With Scale-Aware Localization Policy,"Too Far to See? Not Really! — Pedestrian Detection with Scale-aware Localization Policy Xiaowei Zhang, Li Cheng, Bo Li, and Hai-Miao Hu" b196f95a4274533b7f931a509eaf5507358945f9,Transformation-Invariant Analysis of Visual Signals with Parametric Models,"POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCESacceptée sur proposition du jury:Prof. P. Vandergheynst, président du juryProf. P. Frossard, directeur de thèseProf. D. Kressner, rapporteur Dr G. Peyré, rapporteur Prof. M. B. Wakin, rapporteurTransformation-Invariant Analysis of Visual Signals with Parametric ModelsTHÈSE NO 5844 (2013)ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNEPRÉSENTÉE LE 4 OCTOBRE 2013 À LA FACULTÉ DES SCIENCES ET TECHNIQUES DE L'INGÉNIEURLABORATOIRE DE TRAITEMENT DES SIGNAUX 4PROGRAMME DOCTORAL EN GÉNIE ÉLECTRIQUESuisse2013PARElif VURAL" b11e97d5a12046ded77bc4dc0f762ac3c34e65cb,BLUR AND ILLUMINATION INVARIANT ROBUST FACE RECOGNITION USING SUPPORT VECTOR MACHINE ( SVM ),"Vetri--International Journal of Computer Science information and Engg., Technologies ISSN 2277-4408 || 01032014-011 BLUR AND ILLUMINATION INVARIANT ROBUST FACE RECOGNITION USING SUPPORT VECTOR MACHINE (SVM) A.Vetri Selvi1 , N.Priyalakshmi2, S.Reshmi3 , G.Nandhini4, 1, 2, 3 UG Scholars, Department of Information Technology, Sri Ramakrishna Engineering College, Coimbatore, India. 4 Assistant Professor, Department of Information Technology, Sri Ramakrishna Engineering College, Coimbatore, India." b1898f8fe31147779a841f56795a776db6699efd,Automatic Detection of the Optimal Acceptance Threshold in a Face Verification System,"Automatic Detection of the Optimal Acceptance Threshold in a Face Verification System Raquel Montes Diez, Cristina Conde, and Enrique Cabello Universidad Rey Juan Carlos (ESCET), http://frav.escet.urjc.es C/Tulipán s/n, 8933 Móstoles, Spain" b1ffd13e8f68401a603eea9806bc37e396a3c77d,Face Generation with Conditional Generative Adversarial Networks,"Face Generation with Conditional Generative Adversarial Networks Xuwen Cao, Subramanya Rao Dulloor, Marcella Cindy Prasetio" b1ec55cbf2e9a6785e1f1f2fc060e4171ec88b4b,Implicit Discrimination of Basic Facial Expressions of Positive/Negative Emotion in Fragile X Syndrome and Autism Spectrum Disorder.,"015, Vol. 120, No. 4, 328–345 EAAIDD DOI: 10.1352/1944-7558-120.4.328 Implicit Discrimination of Basic Facial Expressions of Positive/Negative Emotion in Fragile X Syndrome and Autism Spectrum Disorder Hayley Crawford, Joanna Moss, Giles M. Anderson, Chris Oliver, and Joseph P. McCleery" b12431e61172443c534ea523a4d7407e847b5c5b,Yüz Tanımaya Dayalı Kişi Bazlı Test Otomasyonu,"Y¨uz Tanımaya Dayalı Ki¸si Bazlı Test Otomasyonu Alphan C¸ amlı1, Damla G¨ulen1, Nihat ¨Uk1, and Anıl G¨undo˘gdu1 Siemens A.S., Istanbul 34870, Turkey" b15a06d701f0a7f508e3355a09d0016de3d92a6d,Facial contrast is a cue for perceiving health from the face.,"Running head: FACIAL CONTRAST LOOKS HEALTHY Facial contrast is a cue for perceiving health from the face Richard Russell1, Aurélie Porcheron2,3, Jennifer R. Sweda1, Alex L. Jones1, Emmanuelle Mauger2, Frederique Morizot2 Gettysburg College, Gettysburg, PA, USA CHANEL Recherche et Technologie, Chanel PB Université Grenoble Alpes Author Note Richard Russell, Jennifer R. Sweda, and Alex L. Jones, Department of Psychology, Gettysburg College. Aurélie Porcheron, Emmanuelle Mauger, and Frederique Morizot, CHANEL Recherche et Technologie, Chanel PB. Aurélie Porcheron, Laboratoire de Psychologie et NeuroCognition, Université Grenoble Alpes. Corresponding author: Richard Russell, Department of Psychology, Box 407, Gettysburg College, Gettysburg, PA 17325, USA. Email: This is a prepublication copy. This article may not exactly replicate the authoritative document published in the APA journal. It is not the copy of record. The authoritative document can be found through this DOI: http://psycnet.apa.org/doi/10.1037/xhp0000219" b172c7073b7c2e032e7489cff66188605f13f57c,A Framework towards Domain Specific Video Summarization,"A Framework towards Domain Specific Video Summarization Vishal Kaushal IIT Bombay Sandeep Subramanian IIT Bombay Suraj Kothawade IIT Bombay Rishabh Iyer Microsoft Corporation Ganesh Ramakrishnan IIT Bombay" b1fe9715f3f49980785db00066cb9062990a58ac,Study of the Changing Trends in Facial Expression Recognition,"Study of the Changing Trends in Facial Expression Recognition {tag} {/tag} International Journal of Computer Applications © 2011 by IJCA Journal Number 5 - Article 3 Year of Publication: 2011 Authors: Dr. S. Ravi Mahima S 10.5120/2509-3397" 6e50c32f7244e3556eb879f24b7de8410f3177f6,Visual Social Relationship Recognition,"manuscript No. (will be inserted by the editor) Visual Social Relationship Recognition Junnan Li · Yongkang Wong · Qi Zhao · Mohan S. Kankanhalli" 6e44ddb54edbb80d5bb8f2ca3b36e40c486b9daf,Evolutionary 3 D Mapping Using the GPU Calculating the psi similarity function for 2 D images,"Evolutionary 3D Mapping Using the GPU Calculating the psi similarity function for 2D images Diana Cristina Albu May 7, 2007 Submitted to the School of Engineering and Sciences in partial fulfillment of the requirements for the degree of Bachelor of Science in Electrical Engineering and Computer Science Jacobs University Bremen Supervisor: Andreas Birk" 6ee1f57cbf7daa37576efca7e7d24040a5c94ee2,Aalborg Universitet Multimodal Neural Network for Overhead Person Re-identification,"Aalborg Universitet Multimodal Neural Network for Overhead Person Re-identification Lejbølle, Aske Rasch; Nasrollahi, Kamal; Krogh, Benjamin; Moeslund, Thomas B. Published in: 6th International Conference of the Biometrics Special Interest Group DOI (link to publication from Publisher): 0.23919/BIOSIG.2017.8053514 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Lejbølle, A. R., Nasrollahi, K., Krogh, B., & Moeslund, T. B. (2017). Multimodal Neural Network for Overhead Person Re-identification. In 16th International Conference of the Biometrics Special Interest Group IEEE. https://doi.org/10.23919/BIOSIG.2017.8053514 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain" 6eb7ae81554ad4db92ee6b578f47be659c8b9cbd,Audio phrases for audio event recognition,"AUDIO PHRASES FOR AUDIO EVENT RECOGNITION Huy Phan(cid:63)†, Lars Hertel(cid:63), Marco Maass(cid:63), Radoslaw Mazur(cid:63), and Alfred Mertins(cid:63) Graduate School for Computing in Medicine and Life Sciences, University of L¨ubeck, Germany (cid:63)Institute for Signal Processing, University of L¨ubeck, Germany Email: {phan, hertel, maass, mazur," 6ee3fbc4768f578601d42b1596aaf2b0cfa1d40a,Human Detection and Identification by Robots Using Thermal and Visual Information in Domestic Environments,"J Intell Robot Syst (2012) 66:223–243 DOI 10.1007/s10846-011-9612-2 Human Detection and Identification by Robots Using Thermal and Visual Information in Domestic Environments Mauricio Correa · Gabriel Hermosilla · Rodrigo Verschae · Javier Ruiz-del-Solar Received: 11 December 2010 / Accepted: 30 May 2011 / Published online: 12 July 2011 © Springer Science+Business Media B.V. 2011" 6e99832e265999194aa88958d892db62afbd7ac9,Is Combinational Strategy Better For Image Memorability Prediction,"Is Combinational Strategy Better For Image Memorability Prediction Wenting Zhu" 6e35585eb37ee8a1de60a10a56a3183af480e214,"The YLI-MED Corpus: Characteristics, Procedures, and Plans", 6ed22b934e382c6f72402747d51aa50994cfd97b,Customized expression recognition for performance-driven cutout character animation,"Customized Expression Recognition for Performance-Driven Cutout Character Animation Xiang Yu† NEC Laboratories America Jianchao Yang‡ Wilmot Li§ Snapchat" 6ebc601bba067af64b57d59039319650168df4c9,CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images.,"CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images Yudong Guo, Juyong Zhang†, Jianfei Cai, Boyi Jiang and Jianmin Zheng" 6e1802874ead801a7e1072aa870681aa2f555f35,Exploring Feature Descritors for Face Recognition,"­4244­0728­1/07/$20.00 ©2007 IEEE I ­ 629 ICASSP 2007 *22+),)164,7+616DAIK??AIIB=B=?AHA?CEJE=CHEJDCHA=JOHAEAI.EIDAHB=?A -*/ 4A?AJO?=*E=HO2=JJAH*22+),)" 6ed738ff03fd9042965abdfaa3ed8322de15c116,K-MEAP: Generating Specified K Clusters with Multiple Exemplars by Efficient Affinity Propagation,"This document is downloaded from DR-NTU, Nanyang Technological University Library, Singapore. Title K-MEAP: Generating Specified K Clusters with Multiple Exemplars by Efficient Affinity Propagation Author(s) Wang, Yangtao; Chen, Lihui Citation Wang, Y & Chen, L. (2014). K-MEAP: Generating Specified K Clusters with Multiple Exemplars by Efficient Affinity Propagation. 2014 IEEE International Conference on Data Mining (ICDM), 1091-1096. http://hdl.handle.net/10220/39690 Rights © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any opyrighted component of this work in other works. The" 6e261b9e539ecd03d76063f893d59c6eafb6ed43,On the Use of External Face Features for Identity Verification,"On the Use of External Face Features for Identity Verification `Agata Lapedriza1, David Masip2 and Jordi Vitri`a1 Computer Vision Center (CVC), Computer Science Dept. Universitat Aut`onoma de Barcelona Bellaterra, Spain, 08193. {agata, Department of Applied Mathematics and Analysis (MAiA) University of Barcelona (UB) Edifici Hist`oric Gran Via de les Corts Catalanes 585, Barcelona 08007, Spain." 6e9862146e7e081429da233960ba0dfa9e400fc2,Cross-Spectral Cross-Resolution Face Recognition in Videos,"Cross-Spectral Cross-Resolution Face Recognition in Videos Student Name: Nikita Gupta Roll Number: 2013068 Student Name: Sanchit Gupta Roll Number: 2013088 BTP report submitted in partial fulfillment of the requirements for the Degree of B.Tech. in Computer Science & Engineering on 24th April 2017 BTP Track: Research BTP Advisor Dr. Richa Singh Dr. Mayank Vatsa Indraprastha Institute of Information Technology New Delhi" 6e6f516ed1ce0089d4f6d113797d711d5997802b,Face Analysis and Recognition in Mobile Devices,"Face Analysis and Recognition in Mobile Devices Valencia, November 2008 Departamento de Sistemas Informáticos y ComputaciónUniversidad Politécnica de ValenciaMauricio Villegas Santamaría" 6ee2173c06c84cae6aae2912a4439ec956ecc3bb,Zero-shot Sim-to-Real Transfer with Modular Priors,"Zero-shot Sim-to-Real Transfer with Modular Priors Robert Lee1,2, Serena Mou1,2, Vibhavari Dasagi2, Jake Bruce2, J¨urgen Leitner1,2, Niko S¨underhauf1,2" 6eabb24b358dea9c66ad28d2efc2c9c469e115c4,On the use of dynamic features in face biometrics: recent advances and challenges,"(will be inserted by the editor) On the Use of Dynamic Features in Face Biometrics: Recent Advances nd Challenges Abdenour Hadid · Jean-Luc Dugelay · Matti Pietik¨ainen Received: DD month YYYY / Revised: DD month YYYY / Accepted: DD month YYYY / Published: DD month YYYY" 6ee64c19efa89f955011531cde03822c2d1787b8,Table S1: Review of existing facial expression databases that are often used in social psycholgy,"Table S1: Review of existing facial expression databases that are often used in social psycholgy. Author database Expressions1 Format Short summary GEMEP Corpus Mind Reading: the interactive guide to emotions udio video record- Videos nger, muse- dmiration, ment," 6e5a9fe3937fddf09a5c2604a13b9692d30db176,Relative Depth Order Estimation Using Multi-scale Densely Connected Convolutional Networks,"RELATIVE DEPTH ORDER ESTIMATION Relative Depth Order Estimation Using Multi-scale Densely Connected Convolutional Networks Ruoxi Deng, Tianqi Zhao, Chunhua Shen, Shengjun Liu" 6eba25166fe461dc388805cc2452d49f5d1cdadd,"ALBANIE, VEDALDI: LEARNING GRIMACES BY WATCHING TV 1 Learning Grimaces by Watching TV","Pages 122.1-122.12 DOI: https://dx.doi.org/10.5244/C.30.122" 6edb41364802b0fdd1e3e98d644fe78b1ecbbe45,Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task,"Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task Nan Ding Google Sebastian Goodman Google Fei Sha Google Radu Soricut Google" 6e1b85aabb132ed741381fdf00909475d16cd3ba,"Motor, emotional and cognitive empathic abilities in children with autism and conduct disorder","Motor, Emotional and Cognitive Empathic Abilities in Children with Autism and Conduct Disorder Danielle M.A. Bons1,2 +31 (0)488 – 469 611 Nanda N.J. Rommelse1,2 +31 (0)24 351 2222 Floor E. Scheepers1 Jan K. Buitelaar1,2 Karakter child- and adolescent psychiatry University Centre Nijmegen, Zetten-Tiel Department of Psychiatry UMC St. Radboud P.O. Box 9101, 6500HB Nijmegen, The P.O. Box 104, 6670AC Zetten, The Netherlands the studies" 6e80caed3f2ac86db775bd5e7d64925b00f1a0ca,Social interaction contexts bias the perceived expressions of interactants.,"City Research Online City, University of London Institutional Repository Citation: Gray, K., Barber, L., Murphy, J. & Cook, R. (2017). Social interaction contexts 0.1037/emo0000257 This is the accepted version of the paper. This version of the publication may differ from the final published version. Permanent repository link: http://openaccess.city.ac.uk/16315/ Link to published version: http://dx.doi.org/10.1037/emo0000257 Copyright and reuse: City Research Online aims to make research outputs of City, University of London available to a wider audience. Copyright and Moral Rights remain with the author(s) and/or copyright holders. URLs from City Research Online may be freely distributed and linked to. City Research Online: http://openaccess.city.ac.uk/" 6e911227e893d0eecb363015754824bf4366bdb7,Wasserstein Divergence for GANs,"Wasserstein Divergence for GANs Jiqing Wu1, Zhiwu Huang1, Janine Thoma1, Dinesh Acharya1, and Luc Van Gool1,2 Computer Vision Lab, ETH Zurich, Switzerland VISICS, KU Leuven, Belgium" 6e75fcf384b31ea2108a81d868fbb886f39cd188,Sparse Coding on Symmetric Positive Definite Manifolds Using Bregman Divergences,"Sparse Coding on Symmetric Positive Definite Manifolds using Bregman Divergences Mehrtash Harandi, Richard Hartley, Brian Lovell, Conrad Sanderson" 6e74a055a70c69c287a34d86ce8b159456cf4420,Institutionen För Systemteknik Pose Recognition for Tracker Initialization Using 3d Models Pose Recognition for Tracker Initialization Using 3d Models,"Institutionen för systemteknik Department of Electrical Engineering Examensarbete Pose Recognition for Tracker Initialization Using D Models Examensarbete utfört i Bildbehandling vid Tekniska högskolan i Linköping Martin Berg LiTH-ISY-EX--07/4076--SE Linköping 2008 Department of Electrical Engineering Linköpings universitet SE-581 83 Linköping, Sweden Linköpings tekniska högskola Linköpings universitet 581 83 Linköping" 6e7cfcefe82471a6aca78b59be0285467ce37b8b,Déjà Vu: an empirical evaluation of the memorization properties of ConvNets,"D´ej`a Vu: an empirical evaluation of the memorization properties of ConvNets Alexandre Sablayrolles†,(cid:63), Matthijs Douze†, Cordelia Schmid(cid:63), nd Herv´e J´egou† Facebook AI Research (cid:63)Inria September 19, 2018" 6e7d799497b94954dc4232d840628c3a00263e42,Aalborg Universitet Deep Multimodal Pain Recognition : A Database and Comparison of Spatio-Temporal Visual,"Aalborg Universitet Deep Multimodal Pain Recognition: A Database and Comparison of Spatio-Temporal Visual Modalities Haque, Mohammad Ahsanul; Nasrollahi, Kamal; Moeslund, Thomas B.; B. Bautista, Ruben; Laursen, Christian B.; Escalera, Sergio; Irani, Ramin; Andersen, Ole Kæseler; Spaich, Erika Geraldina; Kulkarni, Kaustubh; Bellantonio, Marco; Anbarjafari, Gholamreza; Noroozi, Fatemeh Published in: Proc. of the 13th IEEE Conf. on Automatic Face and Gesture Recognition Publication date: Link to publication from Aalborg University Citation for published version (APA): Haque, M. A., Nasrollahi, K., Moeslund, T. B., B. Bautista, R., Laursen, C. B., Escalera, S., ... Noroozi, F. (2018). Deep Multimodal Pain Recognition: A Database and Comparison of Spatio-Temporal Visual Modalities. In Proc. of the 13th IEEE Conf. on Automatic Face and Gesture Recognition (pp. 1). IEEE. General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain" 6ef1996563835b4dfb7fda1d14abe01c8bd24a05,Nonparametric Part Transfer for Fine-Grained Recognition,"Nonparametric Part Transfer for Fine-grained Recognition Christoph G¨oring, Erik Rodner, Alexander Freytag, and Joachim Denzler∗ Computer Vision Group, Friedrich Schiller University Jena www.inf-cv.uni-jena.de" 6e7b2afb4daf1fe50a62faf75018ff81c24ee526,Discriminant Analysis Based Feature Extraction,"SubmittedtoCVPR' DiscriminantAnalysisbasedFeatureExtraction W.Zhao CenterforAutomationResearch UniversityofMaryland CollegePark,MD- nantAnalysishaveachievedquiteasuccessinprac-" 6e7248f33be3f6b44d6089b7039a5c2d84acaed0,Object cosegmentation using deep Siamese network,"Object cosegmentation using deep Siamese network Prerana Mukherjee∗, Brejesh Lall∗ and Snehith Lattupally∗ Dept of EE, IIT Delhi, India. Email: {eez138300, brejesh, eet152695" 6ef0b43cf897f527540c29cae0618aabb7329072,Parallel Algorithms for Nearest Neighbor Search Problems in High Dimensions,"PARALLEL ALGORITHMS FOR NEAREST NEIGHBOR SEARCH PROBLEMS IN HIGH DIMENSIONS. BO XIAO∗ AND GEORGE BIROS†" 6e82ce9897093ce4f5fa795887273992489c380d,Face recognition using Eigensurface on Kinect depth-maps,"Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'16 | Face recognition using Eigensurface on Kinect depth-maps Marcelo Romero1, Cesar Flores1, Vianney Muñoz1 and Luis Carlos Altamirano2 Universidad Autónoma del Estado de México1 and Benemérita Universidad Autónoma de Puebla2" 6e0288b874320b1b6461016fde8b215c3ba46b90,Recognising activities by jointly modelling actions and their effects,"This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e.g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use: This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author. The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author. When referring to this work, full bibliographic details including the author, title, warding institution and date of the thesis must be given." 6e198f6cc4199e1c4173944e3df6f39a302cf787,MORPH-II : Inconsistencies and Cleaning Whitepaper,"MORPH-II: Inconsistencies and Cleaning Whitepaper Participants: G. Bingham, B. Yip, M. Ferguson, and C. Nansalo Mentors: C. Chen, Y. Wang, and T. Kling NSF-REU Site at UNC Wilmington, Summer 2017" 6e0a05d87b3cc7e16b4b2870ca24cf5e806c0a94,RANDOM GRAPHS FOR STRUCTURE DISCOVERY IN HIGH-DIMENSIONAL DATA,"RANDOM GRAPHS FOR STRUCTURE DISCOVERY IN HIGH-DIMENSIONAL DATA Jos¶e Ant¶onio O. Costa A dissertation submitted in partial fulflllment of the requirements for the degree of Doctor of Philosophy (Electrical Engineering: Systems) in The University of Michigan Doctoral Committee: Professor Alfred O. Hero III, Chair Professor Jefirey A. Fessler Professor Susan A. Murphy Professor David L. Neuhofi" 6e604946a0a51911db0e887378ba1ae103dcfb9e,Detection and Classification of a Moving Object in a Video Stream,"Proc. of the Intl. Conf. on Advances in Computing and Information Technology-- ACIT 2014 Copyright © Institute of Research Engineers and Doctors. All rights reserved. ISBN: 978-981-07-8859-9 doi: 10.3850/ 978-981-07-8859-9_23 Detection and Classification of a Moving Object in a Video Stream Asim R. Aldhaheri and Eran A. Edirisinghe" 6e93fd7400585f5df57b5343699cb7cda20cfcc2,Comparing a novel model based on the transferable belief model with humans during the recognition of partially occluded facial expressions.,"http://journalofvision.org/9/2/22/ Comparing a novel model based on the transferable elief model with humans during the recognition of partially occluded facial expressions Zakia Hammal Martin Arguin Frédéric Gosselin Département de Psychologie, Université de Montréal, Canada Département de Psychologie, Université de Montréal, Canada Département de Psychologie, Université de Montréal, Canada Humans recognize basic facial expressions effortlessly. Yet, despite a considerable amount of research, this task remains elusive for computer vision systems. Here, we compared the behavior of one of the best computer models of facial expression recognition (Z. Hammal, L. Couvreur, A. Caplier, & M. Rombaut, 2007) with the behavior of human observers during the M. Smith, G. Cottrell, F. Gosselin, and P. G. Schyns (2005) facial expression recognition task performed on stimuli randomly sampled using Gaussian apertures. The modelVwhich we had to significantly modify in order to give the bility to deal with partially occluded stimuliVclassifies the six basic facial expressions (Happiness, Fear, Sadness, Surprise, Anger, and Disgust) plus Neutral from static images based on the permanent facial feature deformations and the" 6e9680fe35a752590ad2d750ba1aa2b387cba135,Low-Shot Learning with Large-Scale Diffusion,"Low-shot learning with large-scale diffusion Matthijs Douze†, Arthur Szlam†, Bharath Hariharan†∗, Herv´e J´egou† Facebook AI Research *Cornell University" 6e5363af2bfb7d1b2bd13feb41c2688bd0cf12b3,Detection of US Traffic Signs,"Aalborg Universitet Detection of U.S. Traffic Signs Møgelmose, Andreas; Liu, Dongran; Trivedi, Mohan M. Published in: I E E E Transactions on Intelligent Transportation Systems DOI (link to publication from Publisher): 0.1109/TITS.2015.2433019 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Møgelmose, A., Liu, D., & Trivedi, M. M. (2015). Detection of U.S. Traffic Signs. I E E E Transactions on Intelligent Transportation Systems, 16(6), 3116 - 3125. https://doi.org/10.1109/TITS.2015.2433019 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain ? You may freely distribute the URL identifying the publication in the public portal ?" 6ee8a94ccba10062172e5b31ee097c846821a822,How to solve classification and regression problems on high-dimensional data with a supervised extension of slow feature analysis,"Submitted 3/13; Revised 10/13; Published 12/13 How to Solve Classification and Regression Problems on High-Dimensional Data with a Supervised Extension of Slow Feature Analysis Alberto N. Escalante-B. Laurenz Wiskott Institut f¨ur Neuroinformatik Ruhr-Universit¨at Bochum Bochum D-44801, Germany Editor: David Dunson" 0199150ccad6479eac9d693a7cc0406935d877a8,Towards Real-Time Accurate Object Detection in Both Images and Videos Based on Dual Refinement.,"Towards Real-Time Accurate Object Detection in Both Images and Videos Based on Dual Refinement Xingyu Chen, Junzhi Yu, Senior Member, IEEE, Shihan Kong, Zhengxing Wu, and Li Wen Member, IEEE" 01a152e7ca6accce4fa52e29b27feb76418583fb,Tracking Multiple High-Density Homogeneous Targets,"IEEE TRANSACTION ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, VOL. X, NO. X, XXXX Tracking multiple high-density homogeneous targets Fabio Poiesi and Andrea Cavallaro" 01bef320b83ac4405b3fc5b1cff788c124109fb9,Translating Head Motion into Attention - Towards Processing of Student's Body-Language.,"de Lausanne RLC D1 740, CH-1015 Lausanne de Lausanne RLC D1 740, CH-1015 Lausanne de Lausanne RLC D1 740, CH-1015 Lausanne Translating Head Motion into Attention - Towards Processing of Student’s Body-Language Mirko Raca CHILI Laboratory Łukasz Kidzi´nski CHILI Laboratory Pierre Dillenbourg CHILI Laboratory École polytechnique fédérale École polytechnique fédérale École polytechnique fédérale" 01b5d63b60bcc35aa8bead42ea52a517f879bfc9,Solving Uncalibrated Photometric Stereo Using Total Variation,"Noname manuscript No. (will be inserted by the editor) Solving Uncalibrated Photometric Stereo using Total Variation Yvain Qu´eau · Fran¸cois Lauze · Jean-Denis Durou the date of receipt and acceptance should be inserted later" 014b4335d055679bc680a6ceb6f1a264d8ce8a4a,Are You Sure You Want To Do That? Classification with Verification,"Are You Sure You Want To Do That? Classification with Verification Harris Chan∗ Atef Chaudhury∗ Kevin Shen∗" 01c4cf9c7c08f0ad3f386d88725da564f3c54679,Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV),"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) Been Kim Martin Wattenberg Justin Gilmer Carrie Cai James Wexler Fernanda Viegas Rory Sayres" 01d785bb989850019001a418a16202fd7502ac14,Hierarchical object detection and tracking with an Implicit Shape Model,"Hierarchical object detection and tracking with an Implicit Shape Model K. Jüngling1, S. Becker1, and M. Arens1 Object Recognition, Fraunhofer IOSB, Ettlingen, Germany" 01591390da1356b871aefe11d4bb92c1df5ba082,Online Appendix to : Content-based Image Retrieval,"Content-based Image Retrieval Haoran Wang, Yuanbin Wang, This is a project report for the graduate capstone course of Search Engine Architecture at NYU. In this project, we implemented a basic image search engine based on mere image content. In other words, we use n image to search other similar images. We don’t take into consideration the text information related to images, but just the image content. As the past few years have seen amazingly successful applications of deep learning to images, we employ convolutional neural networks as our tool to extract content (features) from images. We chose this topic for our project specifically because information (image) retrieval is highly relevant to this course and also because we would love to explore the use of deep learning for content-based image retrieval. Our results show that our image search engine can correctly retrieve similar images given n query image, which further proves the use of deep learning as image feature extractor in this case. Next, we will briefly describe the details of the project in the following sections. Additional Key Words and Phrases: Image retrieval, deep learning, image content, search engine, informa- tion retrieval, search engine architecture, capstone project ACM Reference Format: Haoran Wang, Yuanbin Wang, 2017. Content-based Image Retrieval ACM Trans. Embedd. Comput. Syst. V, N, Article 1 (May 2017), 8 pages. DOI:http://dx.doi.org/10.1145/0000000.0000000 . INTRODUCTION" 016473c5b809ff55304a2923c36eaf58f02f02e4,DensePose: Dense Human Pose Estimation In The Wild,"DensePose: Dense Human Pose Estimation In The Wild Rıza Alp G¨uler∗ Natalia Neverova Iasonas Kokkinos INRIA-CentraleSup´elec Facebook AI Research Facebook AI Research Figure 1: Dense pose estimation aims at mapping all human pixels of an RGB image to the 3D surface of the human body. spondences for 50K images, and train DensePose-RCNN to densely regress UV coordinates at multiple frames per second. Right: Partitioning and UV parametrization of the body surface." 014e1186209e4f942f3b5ba29b6b039c8e99ad88,Social interactions: A first-person perspective,"Social Interactions: A First-Person Perspective Alireza Fathi, Jessica K. Hodgins, James M. Rehg CVPR 2012 Bora Çelikkale" 014e3d0fa5248e6f4634dc237e2398160294edce,What does 2D geometric information really tell us about 3D face shape?,"Int J Comput Vis manuscript No. (will be inserted by the editor) What does 2D geometric information really tell us about D face shape? Anil Bas1 · William A. P. Smith1 Received: date / Accepted: date" 01e5eb25e262afa4289d39b964c837a22a32f5a2,Cricket activity detection,"Cricket Activity Detection Ashok Kumar(11164) Javesh Garg(11334) March 1, 2014" 0155c2921f060a95c0eca8c64bf62a1eaac591e4,Spatiotemporal CNNs for Pornography Detection in Videos,"Spatiotemporal CNNs for Pornography Detection in Videos Murilo Varges da Silva1,2 and Aparecido Nilceu Marana3 UFSCar - Federal University of Sao Carlos, Sao Carlos, SP, Brazil IFSP - Federal Institute of Education of Sao Paulo, Birigui, SP, Brazil UNESP - Sao Paulo State University, Bauru, SP, Brazil" 0135747b4d3c9a2d983f7d0d9f4c39e094825149,Embedded wavelet-based face recognition under variable position,"Embedded wavelet-based face recognition under variable position Pascal Cotreta, Stéphane Chevobbea and Mehdi Darouicha CEA, LIST, Laboratoire Adéquation Algorithme Architecture, Gif-sur-Yvette, F-91191 France" 016860404c0926dda53b9bf4745f3eb9708fa1d2,Iterative hypothesis testing for multi-object tracking in presence of features with variable reliability,"Iterative hypothesis testing for multi-object tracking in presence of features with variable reliability Amit Kumar K.C.1, Damien Delannay2 and Christophe De Vleeschouwer1 ISPGroup, ELEN Department, Universit´e catholique de Louvain, Belgium {amit.kc, Keemotion, Belgium" 0171bdeb1c6e333287be655c667cfba5edb89b76,Aggregated Residual Transformations for Deep Neural Networks,"Aggregated Residual Transformations for Deep Neural Networks Saining Xie1 Ross Girshick2 Piotr Doll´ar2 Zhuowen Tu1 Kaiming He2 UC San Diego Facebook AI Research" 0145dc4505041bf39efa70ea6d95cf392cfe7f19,Human action segmentation with hierarchical supervoxel consistency,"Human Action Segmentation with Hierarchical Supervoxel Consistency Jiasen Lu1, Ran Xu1 Jason J. Corso2 Department of Computer Science and Engineering, SUNY at Buffalo. 2Department of EECS, University of Michigan. Detailed analysis of human action, such as classification, detection and lo- alization has received increasing attention from the community; datasets like J-HMDB [1] have made it plausible to conduct studies analyzing the impact that such deeper information has on the greater action understanding problem. However, detailed automatic segmentation of human action has omparatively been unexplored. In this paper, we introduce a hierarchical MRF model to automatically segment human action boundaries in videos “in-the-wild” (see Fig. 1). We first propose a human motion saliency representation which incor- porates two parts: foreground motion and human appearance information. For foreground motion estimation, we propose a new motion saliency fea- ture by using long-term trajectories to build a camera motion model, and then measure the motion saliency via the deviation from the camera model. For human appearance information, we use a DPM person detector trained on PASCAL VOC 2007 and construct a saliency map by averaging the nor- malized detection score of all the scale and all components. Then, to segment the human action, we start by applying hierarchical" 013ae78fc6bd26a13799fe2e07a6ad363aca9ba7,Inspiring Computer Vision System Solutions,"Inspiring Computer Vision System Solutions Julian Zilly 1 Amit Boyarski 2 Micael Carvalho 3 Amir Atapour Abarghouei 4 Konstantinos Amplianitis 5 Aleksandr Krasnov 6 Massimiliano Mancini 7 Hernán Gonzalez 8 Riccardo Spezialetti 9 Carlos Sampedro Pérez 10 Hao Li 11" 0181fec8e42d82bfb03dc8b82381bb329de00631,Discriminative Subspace Clustering,"Discriminative Subspace Clustering Vasileios Zografos∗1, Liam Ellis†1, and Rudolf Mester‡1 2 CVL, Dept. of Electrical Engineering, Link¨oping University, Link¨oping, Sweden VSI Lab, Computer Science Department, Goethe University, Frankfurt, Germany" 01bd864085b7ba7c9c85c593bd893a5cbb13b136,On Model-Based Analysis of Ear Biometrics,"On Model-Based Analysis of Ear Biometrics Banafshe Arbab-Zavar, Mark S. Nixon, and David J. Hurley" 0183eff3a60f44bc6e4bcade37518f6470af3437,Human Identification Using Temporal Information Preserving Gait Template,"Human Identification Using Temporal Information Preserving Gait Template Chen Wang, Junping Zhang, IEEE Member, Liang Wang, IEEE Senior Member, Jian Pu, and Xiaoru Yuan, IEEE Member" 014844a9e6ae39a101fb79f103aa047699f88246,Interpretable Counting for Visual Question Answering,"Under review as a conference paper at ICLR 2018 INTERPRETABLE COUNTING FOR VISUAL QUESTION ANSWERING Anonymous authors Paper under double-blind review" 01959ef569f74c286956024866c1d107099199f7,VQA: Visual Question Answering,"VQA: Visual Question Answering www.visualqa.org Stanislaw Antol∗1, Aishwarya Agrawal∗1, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh" 019a95631c49011330773e953194a0c73c61f3f0,Impairments in monkey and human face recognition in 2-year-old toddlers with Autism Spectrum Disorder and Developmental Delay.,"DOI: 10.1111/j.1467-7687.2006.00543.x Blackwell Publishing Ltd Face recognition in ASD PAPER Impairments in monkey and human face recognition in -year-old toddlers with Autism Spectrum Disorder and Developmental Delay Katarzyna Chawarska and Fred Volkmar Child Study Center, Yale University School of Medicine, New Haven, CT, USA" 0144b29bde2579e0a1b8ab3a38306c5621a5c30b,Top-Down Visual Saliency via Joint CRF and Dictionary Learning,"Top-Down Visual Saliency via Joint CRF and Dictionary Learning Jimei Yang and Ming-Hsuan Yang University of California at Merced" 017229c2df23c542b30c59f4a5eeb747e3d34729,Efficient Object Recognition using Convolution Neural Networks Theorem,"International Journal of Computer Applications (0975 – 8887) Volume 161 – No 2, March 2017 Efficient Object Recognition using Convolution Neural Networks Theorem Aarushi Thakral VIT University Vellore Tamil Nadu Shaurya Shekhar VIT University Vellore Tamil Nadu to overcome" 01b527641d1f23cddac932d9fe20b44ec39114a3,CS 341 Final Report : Towards Real-time Detection and Camera Triggering,"CS341 Final Report: Towards Real-time Detection and Camera Triggering Yundong Zhang Haomin Peng Pan Hu" 01574e0d3be1b866471b83e39f7404c80d608e63,Application of Blind Deblurring Algorithm for Face Biometric,"Application of Blind Deblurring Algorithm for Face International Journal of Computer Applications (0975 – 8887) Volume 105 – No. 2, November 2014 F.Alaoui Faculty of science Chouaib doukkali El- jadida Biometric A. Ghlaifan Abdo Saleh Faculty of science Chouaib doukkali El- jadida V.Dembele Faculty of science Chouaib doukkali El- jadida A.Nassim Faculty of science Chouaib doukkali El-" 011c5bb510c9a4c24e2fc07e7464fa8493237058,Accelerating Nearest Neighbor Search on Manycore Systems,"Accelerating Nearest Neighbor Search on Manycore Systems Lawrence Cayton Max Planck Institute Tübingen, Germany" 010f0f4929e6a6644fb01f0e43820f91d0fad292,YFCC100M: the new data in multimedia research,"YFCC100M: The New Data in Multimedia Research Bart Thomee Yahoo Labs San Francisco, CA, USA Benjamin Elizalde∗ Mountain View, CA, USA David A. Shamma Yahoo Labs San Francisco, CA, USA Karl Ni† In-Q-Tel Menlo Park, CA, USA Gerald Friedland Berkeley, CA, USA Douglas Poland Livermore, CA, USA Damian Borth‡ Kaiserslautern, Germany Li-Jia Li§ Snapchat" 014b8df0180f33b9fea98f34ae611c6447d761d2,Facial feature tracking and expression recognition for sign language,"Facial Feature Tracking and Expression Recognition for Sign Language ˙Ismail Arı Computer Engineering Bo˜gazic.i University ˙Istanbul, Turkey Email: Asli Uyar Computer Engineering Bo˜gazic.i University ˙Istanbul, Turkey Email: Lale Akarun Computer Engineering Bo˜gazic.i University ˙Istanbul, Turkey Email:" 01381e2faeb26489ae9c24c84c42df33901cfe61,Multi-scale Deep Learning Architectures for Person Re-identification,"Multi-scale Deep Learning Architectures for Person Re-identification Xuelin Qian1 Yanwei Fu2,5,* Yu-Gang Jiang1,3 Tao Xiang4 Xiangyang Xue1,2 Shanghai Key Lab of Intelligent Info. Processing, School of Computer Science, Fudan University; School of Data Science, Fudan University; 3Tencent AI Lab; Queen Mary University of London; 5University of Technology Sydney;" 01ababc0985143ad57320b0599fb2f581d79d3c2,Unobtrusive Low Cost Pupil Size Measurements using Web cameras,"Unobtrusive Low Cost Pupil Size Measurements using Web cameras Sergios Petridis, Theodoros Giannakopoulos and Costantine D. Spyropoulos National Center for Scientific Research ""Demokritos"" Unobtrusive every day health monitoring can be of important use for the elderly population. In particular, pupil size may be a valuable source of information, since, apart from pathological ases, it can reveal the emotional state, the fatigue and the ageing. To allow for unobtrusive monitoring to gain acceptance, one should seek for ef‌f‌icient methods of monitoring using com- mon low-cost hardware. This paper describes a method for monitoring pupil sizes using a ommon web camera in real time. Our method works by first detecting the face and the eyes rea. Subsequently, optimal iris and sclera location and radius, modelled as ellipses, are found using ef‌f‌icient filtering. Finally, the pupil center and radius is estimated by optimal filtering within the area of the iris. Experimental result show both the ef‌f‌iciency and the effectiveness of our approach. Keywords: video analysis, eye tracking, pupil size estimation, physiological measurements Motivation Unobtrusive every day health monitoring can be of im- portant use for the elderly population. In particular, pupil size may be a valuable source of information, since, apart from pathological cases, it can reveal the emotional state, the" 01915181692c821cc5a0a703047bd5b07c1f9af5,Cross-Caption Coreference Resolution for Automatic Image Understanding,"Proceedings of the Fourteenth Conference on Computational Natural Language Learning, pages 162–171, Uppsala, Sweden, 15-16 July 2010. c(cid:13)2010 Association for Computational Linguistics" 01ece1dd9a0a2a7289d791625c6c7446d38584e7,A Comparative Analysis of Classification Algorithms Applied to M 5 AIE-Extracted Human Poses,"A Comparative Analysis of Classification Algorithms Applied to M5AIE-Extracted Human Poses Andr´e Brand˜ao, Leandro A. F. Fernandes, and Esteban Clua MediaLab-UFF, Instituto de Computac¸˜ao, Universidade Federal Fluminense Email: CEP 24210-240 Niter´oi, RJ, Brazil" 01c9f0be6a300f385274b72a5463a650e51e300a,Support Vector Data Description based on PCA features for face detection,"SUPPORT VECTOR DATA DESCRIPTION BASED ON PCA FEATURES FOR FACE DETECTION Ver´onica Vilaplana and Ferran Marqu´es phone: + (34)934011066, fax: + (34)934016447, email: Jordi Girona, 1-3, 08034 Barcelona, SPAIN Image Processing Group, Universitat Polit`ecnica de Catalunya web: gps-tsc.upc.es/imatge" 01f42436042ddaa48998c87109cbe46cad6e7e52,Schedtask: a hardware-assisted task scheduler,"SchedTask: A Hardware-Assisted Task Scheduler Prathmesh Kallurkar∗ Microarchitecture Research Lab Intel Corporation Smruti R. Sarangi Department of Computer Science Indian Institute of Technology Delhi" 013e0fe2d203eaa33a4b42d057688815116cc6bb,Recognizing Car Fluents from Video,"Recognizing Car Fluents from Video Bo Li1,∗, Tianfu Wu2, Caiming Xiong3,∗ and Song-Chun Zhu2 Beijing Lab of Intelligent Information Technology, Beijing Institute of Technology Department of Statistics, University of California, Los Angeles Metamind Inc. {tfwu," 011e6146995d5d63c852bd776f782cc6f6e11b7b,Fast Training of Triplet-Based Deep Binary Embedding Networks,"Fast Training of Triplet-based Deep Binary Embedding Networks Bohan Zhuang, Guosheng Lin, Chunhua Shen∗, Ian Reid The University of Adelaide; and Australian Centre for Robotic Vision" 0136bf1d3747770a7fb4fcdeaf0b4b195815ed67,Weighted Fourier Series Representation and Its Application to Quantifying the Amount of Gray Matter,"Weighted Fourier Series Representation and Its Application to Quantifying the Amount of Gray Matter Moo K. Chung*, Kim M. Dalton, Li Shen, Alan C. Evans, and Richard J. Davidson" 0113b302a49de15a1d41ca4750191979ad756d2f,Matching Faces with Textual Cues in Soccer Videos,"­4244­0367­7/06/$20.00 ©2006 IEEE ICME 2006" 015d25f66514ce0a966300944201d45968a104ba,SIMPLE IMAGE DESCRIPTION GENERATOR VIA A LINEAR PHRASE-BASED MODEL Rémi Lebret,"SIMPLE IMAGE DESCRIPTION GENERATOR VIA A LINEAR PHRASE-BASED MODEL Rémi Lebret Pedro H. O. Pinheiro Ronan Collobert Idiap-RR-22-2015 JUNE 2015 Idiap Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" c6fdbdbbbc7642daae22df0b7812e78d0647afb3,Unsupervised feature learning with C-SVDDNet,"Unsupervised Feature Learning with C-SVDDNet Dong Wang and Xiaoyang Tan" c68ec931585847b37cde9f910f40b2091a662e83,A Comparative Evaluation of Dotted Raster-Stereography and Feature-Based Techniques for Automated Face Recognition,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 9, No. 6, 2018 A Comparative Evaluation of Dotted Raster- Stereography and Feature-Based Techniques for Automated Face Recognition Muhammad Wasim S. Talha Ahsan Department of Computer Science Department of Electrical Engineering Usman Institute of Technology Usman Institute of Technology Karachi, Pakistan Karachi, Pakistan Lubaid Ahmed, Syed Faisal Ali, Fauzan Saeed Department of Computer Science Usman Institute of Technology Karachi, Pakistan feature-based system. The" c636cd6eba286357fe807c0ca4b02c3b9b7b5619,Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization,"Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization Jonathan Tremblay∗ Aayush Prakash∗ David Acuna∗† Mark Brophy∗ Varun Jampani Cem Anil† Thang To Eric Cameracci Shaad Boochoon Stan Birchfield NVIDIA also University of Toronto {jtremblay,aayushp,dacunamarrer,markb,vjampani," c694b397a3a0950cd20699a687fe6c8a3173b107,Explaining autism spectrum disorders: central coherence vs. predictive coding theories.,"J Neurophysiol 112: 2669 –2671, 2014. First published May 28, 2014; doi:10.1152/jn.00242.2014. Neuro Forum Explaining autism spectrum disorders: central coherence vs. predictive coding theories Jason S. Chan and Marcus J. Naumer Institute of Medical Psychology, Goethe-University, Frankfurt, Germany Submitted 27 March 2014; accepted in final form 23 May 2014 Chan JS, Naumer MJ. Explaining autism spectrum disorders: central oherence vs. predictive coding theories. J Neurophysiol 112: 2669–2671, 014. First published May 28, 2014; doi:10.1152/jn.00242.2014.—In this rticle, we review a recent paper by Stevenson et al. (J Neurosci 34: 691–697, 2014). This paper illustrates the need to present different forms of stimuli in order to characterize the perceptual abilities of people with autism spectrum disorder (ASD). Furthermore, we will discuss their behavioral results and offer an opposing viewpoint to the suggested neuronal drivers of utism spectrum disorder; multisensory integration; temporal binding window THE DIFFERENCE in propagation time between an auditory and a visual stimulus can be substantial, depending on the distance" c6d6193c8f611331c8178c3857f9ef92607a4507,i i '-o A Study on Using Mid-Wave Infrared Images for Face Recognition,"Sensing Technologies for Global Health, Military Medicine, Disaster Response, and Environmental Monitoring II; and Biometric Technology for Human Identification IX, edited by Sárka O. Southern, et al., Proc. of SPIE Vol. 8371, 83711K © 2012 SPIE · CCC code: 0277-786X/12/$18 · doi: 10.1117/12.918899 Proc. of SPIE Vol. 8371 83711K-1 From: http://spiedigitallibrary.org/ on 04/30/2013 Terms of Use: http://spiedl.org/terms" c6c3cee8adacff8a63ab84dc847141315e874400,Disentangling by Factorising,"Disentangling by Factorising Hyunjik Kim 1 2 Andriy Mnih 1" c6ecb8e20250e3fa8ef2a5edd8fad4131f3e874f,EigenBody : Analysis of body shape for gender from noisy images,"EigenBody: Analysis of body shape for gender from noisy images Matthew Collins, Jianguo Zhang, Paul Miller, Hongbin Wang and Huiyu Zhou Institute of Electronics Communications and Information Technology (ECIT) Queens University Belfast" c62c07de196e95eaaf614fb150a4fa4ce49588b4,SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation,Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) c62c4e5d8243da6bc1fde64097b2ab8971e6e51f,"A Unified Approach for Conventional Zero-Shot, Generalized Zero-Shot, and Few-Shot Learning","JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2017 A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning Shafin Rahman, Salman H. Khan and Fatih Porikli" c65d7b7c111b1e6303b460ebd484c81537ecae80,Boosting Localized Features for Speaker and Speech Recognition,"Boosting Localized Features for Speaker and Speech Recognition TH`ESE No 5212 (2011) PR´ESENT´EE LE 6 OCTOBRE 2011 `A LA FACULT´E SCIENCES ET TECHNIQUES DE L’ING´ENIEUR LABORATOIRE DE L’IDIAP PROGRAMME DOCTORAL EN G´ENIE ´ELECTRIQUE ´ECOLE POLYTECHNIQUE F ´ED ´ERALE DE LAUSANNE POUR L’OBTENTION DU GRADE DE DOCTEUR `ES SCIENCES Anindya Roy ccept ´ee sur proposition du jury : Prof. Pierre Vandergheynst, pr ´esident du jury Prof. Herv ´e Bourlard, directeur de th `ese Dr. S ´ebastien Marcel, co-directeur de th `ese Prof. Jan ˘Cernock´y, rapporteur Dr. Nicholas Evans, rapporteur Prof. Jean-Philippe Thiran, rapporteur Lausanne, EPFL" c607572fd2594ca83f732c9790fd590da9e69eb1,Comparative Evaluation of Deep Architectures for Face Recognition in Unconstrained Environment ( FRUE ),"Comparative Evaluation of Deep Architectures for Face Recognition in Unconstrained Environment (FRUE) Deeksha Gupta Department of Computer Science and Applications, MCM DAV College for Women, Chandigarh, (India)" c6381f055793b406a1aa0375374348cf99502f13,Perception and Processing of Faces in the Human Brain Is Tuned to Typical Feature Locations.,"de Haas, Benjamin; Schwarzkopf, D. Samuel; Alvarez, Ivan; Lawson, Rebecca P.; Henriksson, Linda; Kriegeskorte, Nikolaus; Rees, Geraint Perception and processing of faces in the human brain is tuned to typical feature locations Published in: JOURNAL OF NEUROSCIENCE 0.1523/JNEUROSCI.4131-14.2016 Published: 07/09/2016 Document Version Publisher's PDF, also known as Version of record Please cite the original version: de Haas, B., Schwarzkopf, D. S., Alvarez, I., Lawson, R. P., Henriksson, L., Kriegeskorte, N., & Rees, G. (2016). Perception and processing of faces in the human brain is tuned to typical feature locations. JOURNAL OF NEUROSCIENCE, 36(36), 9289-9302. DOI: 10.1523/JNEUROSCI.4131-14.2016 This is an electronic reprint of the original article.This reprint may differ from the original in pagination and typographic detail.Powered by TCPDF (www.tcpdf.org)This material is protected by copyright and other intellectual property rights, andduplication or sale of all or part of any of the repository collections is not permitted, except that material maybe duplicated by you for your research use or educational purposes in electronic or print form. You mustobtain permission for any other use. Electronic or print copies may not be offered, whether for sale orotherwise to anyone who is not an authorised user." c614450c9b1d89d5fda23a54dbf6a27a4b821ac0,Face Image Retrieval of Efficient Sparse Code words and Multiple Attribute in Binning Image,"Vol.60: e17160480, January-December 2017 http://dx.doi.org/10.1590/1678-4324-2017160480 ISSN 1678-4324 Online Edition Engineering,Technology and Techniques BRAZILIAN ARCHIVES OF BIOLOGY AND TECHNOLOGY A N I N T E R N A T I O N A L J O U R N A L Face Image Retrieval of Efficient Sparse Code words and Multiple Attribute in Binning Image Suchitra S1*. Srm Easwari Engineering College, Ramapuram, Bharathi Salai, Chennai, Tamil Nadu, India." c6b7c2a485f13bb97283c367dc2811266a68ef64,Exploring the potential of combining time of flight and thermal infrared cameras for person detection,"Exploring the Potential of Combining Time of Flight and Thermal Infrared Cameras for Person Detection Wim Abbeloos and Toon Goedem´e KU Leuven, Department of Electrical Engineering, EAVISE Leuven, Belgium Keywords: Time of Flight : Range Image : 2.5D : Thermal Infrared : Thermopile Array : Calibration : Camera : Sensor : Data Fusion : Measurement Errors : Scattering : Multi-path Interference." c6dab0aba7045f078313a4186cd507ff8eb8ce32,Atypical disengagement from faces and its modulation by the control of eye fixation in children with autism spectrum disorder.,"BIROn - Birkbeck Institutional Research Online Enabling open access to Birkbeck’s published research output Atypical disengagement from faces and its modulation y the control of eye fixation in children with Autism Spectrum Disorder Journal Article http://eprints.bbk.ac.uk/4677 Version: Accepted (Refereed) Citation: © 2011 Springer Publisher version ______________________________________________________________ All articles available through Birkbeck ePrints are protected by intellectual property law, including opyright law. Any use made of the contents should comply with the relevant law. ______________________________________________________________ Kikuchi, Y.; Senju, A.; Akechi, H.; Tojo, Y.; Osanai, H.; Hasegawa, T. (2011) Atypical disengagement from faces and its modulation by the control of eye fixation in children with Autism Spectrum Disorder Deposit Guide" c69f4ec3ba6ae4a627fcb5d4f58cd07b8c42e4e4,k-fold Subsampling based Sequential Backward Feature Elimination, c6c086748474dcda06d773891848aa1472de3560,Activity Recognition Based on a Magnitude-Orientation Stream Network,"Activity Recognition based on a Magnitude-Orientation Stream Network Carlos Caetano, Victor H. C. de Melo, Jefersson A. dos Santos, William Robson Schwartz Smart Surveillance Interest Group, Department of Computer Science Universidade Federal de Minas Gerais, Belo Horizonte, Brazil" c6badb2cc1191f9dd5e5bea7df75a76349176d01,Densely tracking sequences of 3D face scans,"Densely tracking sequences of 3D face scans Huaxiong DING Ecole Centrale de LYON Liming Chen Ecole Centrale de LYON" c63f31a938944f55027808fb9afd4d6e0b8b645e,Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation,"Simultaneous Learning of Trees and Representations for Extreme Classification nd Density Estimation Yacine Jernite 1 Anna Choromanska 1 David Sontag 2" c65407a1a25b3e47cbf21b50bd02c929f9cb5ed4,Sparse interacting Gaussian processes: Efficiency and optimality theorems of autonomous crowd navigation,"Sparse Interacting Gaussian Processes: Efficiency and Optimality Theorems of Autonomous Crowd Navigation Pete Trautman Galois, Inc." c693c578d783323d130d642bd04d391aac7e8f81,Semantic Pyramids for Gender and Action Recognition,"Semantic Pyramids for Gender and Action Recognition Fahad Shahbaz Khan, Joost van de Weijer, Rao Muhammad Anwer, Michael Felsberg, Carlo Gatta" c6643a771521b19ffc0df035e806b03c2ec00782,Incorporating invariants in Mahalanobis distance based classifiers : Application to Face Recognition,"Incorporating invariants in Mahalanobis distance based classifiers: Application to Face Recognition Andrew M. Fraser Portland State University and Los Alamos National Laboratory Nicolas W. Hengartner, Kevin R. Vixie, and Brendt E. Wohlberg Los Alamos National Laboratory Los Alamos, NM 87545" c6eb026d3a0081f4cb5cde16d3170f8ecf8ce706,Face Recognition: From Traditional to Deep Learning Methods,"Face Recognition: From Traditional to Deep Learning Methods Daniel S´aez Trigueros, Li Meng School of Engineering and Technology University of Hertfordshire Hatfield AL10 9AB, UK Margaret Hartnett GBG plc London E14 9QD, UK" c6260f83e86dd4d1ece92e528422ecc6e36c13ef,Siamese networks for generating adversarial examples,"Siamese networks for generating adversarial examples Mandar Kulkarni Data Scientist Schlumberger" c610888cadcf2aa45e7367f43e42eaa7a586652e,Fast Convergence for Object Detection by Learning how to Combine Error Functions,"(cid:13) 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new ollective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Accepted version." c679fd4e29597c64e5921fad796183ae30db8396,LG ] 5 M ar 2 01 6 A Latent-Variable Grid Model,"A Latent-Variable Grid Model Rajasekaran Masatran Computer Science and Engineering, Indian Institute of Technology Madras FREESHELL · ORG" c600e985ae3af9143b41271abd040a1c1e89177e,Nonparametric Video Retrieval and Frame Classification using Tiny Videos,"Nonparametric Video Retrieval and Frame Classification using Tiny Videos {tag} {/tag} IJCA Proceedings on International Conference in Recent trends in Computational Methods, Communication and Controls (ICON3C 2012) © 2012 by IJCA Journal ICON3C - Number 3 Year of Publication: 2012 Authors: A. K. M. Shanawas Fathima R. Kanthavel {bibtex}icon3c1024.bib{/bibtex}" c6d5d47513d6a7a1b0b92b33efda3f2a866d34ad,Characterizing International Travel Behavior from Geotagged Photos: A Case Study of Flickr,"RESEARCH ARTICLE Characterizing International Travel Behavior from Geotagged Photos: A Case Study of Flickr Yihong Yuan*, Monica Medel Department of Geography, Texas State University, San Marcos, Texas, 78666, United States of America" c696c9bbe27434cb6279223a79b17535cd6e88c8,Facial Expression Recognition with Pyramid Gabor Features and Complete Kernel Fisher Linear Discriminant Analysis,"International Journal of Information Technology Vol.11 No.9 2005 Discriminant Analysis Facial Expression Recognition with Pyramid Gabor Features and Complete Kernel Fisher Linear Duan-Duan Yang1, Lian-Wen Jin1, Jun-Xun Yin1, Li-Xin Zhen2, Jian-Cheng Huang2 School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510640, P.R.China {ddyang, Motorola China Research Center, Shanghai, 210000, P.R.China {Li-Xin.Zhen," f66bc143d85d2b1d9aafec20f598a21d2b90b0c0,SEEING 3 D OBJECTS IN A SINGLE 2 D IMAGE,"Accepted for publication in the Proceedings of the 12th International Conference of Computer Vision, 2009 Seeing 3D Objects in a Single 2D Image Diego Rother Johns Hopkins University" f663ad5467721159263c1cde261231312893f45d,UvA-DARE ( Digital Academic Repository ) Gaze Embeddings for Zero-Shot Image Classification,"UvA-DARE (Digital Academic Repository) Gaze Embeddings for Zero-Shot Image Classification Karessli, N.; Akata, Z.; Schiele, B.; Bulling, A. Published in: 0th IEEE Conference on Computer Vision and Pattern Recognition 0.1109/CVPR.2017.679 Link to publication Citation for published version (APA): Karessli, N., Akata, Z., Schiele, B., & Bulling, A. (2017). Gaze Embeddings for Zero-Shot Image Classification. In 0th IEEE Conference on Computer Vision and Pattern Recognition: CVPR 2017 : 21-26 July 2016, Honolulu, Hawaii : proceedings (pp. 6412-6421). Piscataway, NJ: IEEE. DOI: 10.1109/CVPR.2017.679 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Download date: 18 Nov 2018" f672d6352a5864caab5a5a286fbc1ce042b55c16,Stabilizing GAN Training with Multiple Random Projections,"Under review as a conference paper at ICLR 2018 Stabilizing GAN Training with Multiple Random Projections Anonymous authors Paper under double-blind review" f67afec4226aba674e786698b39b85b124945ddd,Spatial Variational Auto-Encoding via Matrix-Variate Normal Distributions,"Spatial Variational Auto-Encoding via Matrix-Variate Normal Distributions Zhengyang Wang School of Electrical Engineering nd Computer Science Washington State University Pullman, WA 99163 Hao Yuan School of Electrical Engineering nd Computer Science Washington State University Pullman, WA 99163 Shuiwang Ji School of Electrical Engineering nd Computer Science Washington State University Pullman, WA 99163" f6d8b67755af67d469fc1b68c52d4c9910eae0e8,Chapter 2 Sentiment Analysis Using Social Multimedia,"Chapter 2 Sentiment Analysis Using Social Multimedia Jianbo Yuan, Quanzeng You and Jiebo Luo" f6066a3428a60904b39dccfd4cb7ec522b4a69f4,Active shape model-based user identification for an intelligent wheelchair,"Int. J. Advanced Mechatronic Systems, Vol. 1, No. 4, 2009 Active shape model-based user identification for an intelligent wheelchair P. Jia* and H. Hu School of Computer Science and Electronic Engineering, University of Essex, Colchester, CO4 3SQ, UK E-mail: *Corresponding author E-mail:" f68f20868a6c46c2150ca70f412dc4b53e6a03c2,Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition,"Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition Khadoudja Ghanem, Amer Draa, Elvis Vyumvuhore and Ars`ene Simbabawe MISC Laboratory, Constantine 2 University, Constantine, Algeria The base system in this paper uses Hidden Markov Models (HMMs) to model dynamic relationships among facial features in facial behavior interpretation and un- derstanding field. The input of HMMs is a new set of derived features from geometrical distances obtained from detected and automatically tracked facial points. Numerical data representation which is in the form of multi-time series is transformed to a symbolic repre- sentation in order to reduce dimensionality, extract the most pertinent information and give a meaningful repre- sentation to humans. The main problem of the use of HMMs is that the training is generally trapped in local minima, so we used the Differential Evolution (DE)" f6fa97fbfa07691bc9ff28caf93d0998a767a5c1,K2-means for Fast and Accurate Large Scale Clustering,"k2-means for fast and accurate large scale clustering Eirikur Agustsson Computer Vision Lab D-ITET ETH Zurich Radu Timofte Computer Vision Lab D-ITET ETH Zurich Luc Van Gool ESAT, KU Leuven D-ITET, ETH Zurich" f614f9ba33554cfd1a474be03520319b51651a35,Cardiac interoceptive learning is modulated by emotional valence perceived from facial expressions,"Social Cognitive and Affective Neuroscience, 2018, 677–686 doi: 10.1093/scan/nsy042 Advance Access Publication Date: 6 April 2018 Original article Cardiac interoceptive learning is modulated by emotional valence perceived from facial expressions Amanda C. Marshall, Antje Gentsch, Lena Schro¨ der, and Simone Schu¨ tz-Bosbach General and Experimental Psychology Unit, Department of Psychology, Ludwig-Maximilians University Munich, D-80802 Munich, Germany Correspondence should be addressed to Amanda C. Marshall, General and Experimental Psychology Unit, Department of Psychology, Ludwig- Maximilians-University Munich, Leopoldstr. 13, D-80802 Munich, Germany. E-mail:" f614b449ee2fd45974214014c109d993aab73343,A Mathematical Motivation for Complex-Valued Convolutional Networks,"A Mathematical Motivation for Complex-valued Convolutional Networks Joan Bruna, Soumith Chintala, Yann LeCun, Serkan Piantino, Arthur Szlam, Mark Tygert Facebook Artificial Intelligence Research, 1 Facebook Way, Menlo Park, California 94025 Keywords: deep learning, neural networks, harmonic analysis" f61fa90e4e60aab8366831d4a8a7bed980b76073,An Integrated Soft Computing Approach to a Multi-biometric Security Model,"AN INTEGRATED SOFT COMPUTING APPROACH TO A MULTI-BIOMETRIC SECURITY MODEL A THESIS SUBMITTED TO DAYALBAGH EDUCATIONAL INSTITUTE TOWARDS FULFILMENT OF THE REQUIREMENTS FOR THE AWARD OF DOCTOR OF PHILOSOPHY PHYSICS AND COMPUTER SCIENCE PREM SEWAK SUDHISH DEPARTMENT OF PHYSICS AND COMPUTER SCIENCE DAYALBAGH EDUCATIONAL INSTITUTE" f636c087091847bd4ccd6d196ada6c0894b52d88,Rate-Accuracy Trade-Off in Video Classification with Deep Convolutional Neural Networks,"Rate-Accuracy Trade-Off In Video Classification With Deep Convolutional Neural Networks Mohammad Jubran, Alhabib Abbas, Aaron Chadha and Yiannis Andreopoulos, Senior Member, IEEE" f6cf2108ec9d0f59124454d88045173aa328bd2e,Robust User Identification Based on Facial Action Units Unaffected by Users' Emotions,"Robust user identification based on facial action units unaffected by users’ emotions Ricardo Buettner Aalen University, Germany" f6ba16aee3c40b69dc88c947ae59811104b1bd49,Skeletal Tracking using Microsoft Kinect,"Skeletal Tracking using Microsoft Kinect Abhishek Kar Advisors: Dr. Amitabha Mukerjee & Dr. Prithwijit Guha Department of Computer Science and Engineering, IIT Kanpur" f6a050314881488d0f6653c0c6883937a722eff5,Retina Recognition Based on Fractal Dimension,"IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.10, October 2009 Retina Recognition Based on Fractal Dimension S.Sukumaran, 1 Dr. M.Punithavalli 2 S.G. Lecturer in Computer Science, Erode Arts College, Erode – 638 009. India. Director, Sri Ramakrishna College of Arts & Science for Women Coimbatore - 641 044. India. other problems the best methodology can be used is retina based biometric technology for the authentication to be more accurate and secure as it does not variant and provide a permanent and unique personal identification. The retina of a normal human though small (11 mm) and sometimes problematic to image, it has the great mathematical advantage that its pattern variability among different persons is enormous. It is an internal (yet externally visible) organ of the eye, the retina is well protected from the environment, and stable over time [6]. The paper is organized as follows. The next section describes the fundamentals of fractals, followed y the section describing the evaluation of fractal" f6cf220b8ef17e0a4bef0ff5aadc40eec9653159,Automated System for interpreting Non-verbal Communication in Video Conferencing,"Chetana Gavankar et al / International Journal on Computer Science and Engineering Vol.2(1), 2010, 22-27 Automated System for interpreting Non-verbal Communication in Video Conferencing Chetana Gavankar Senior Lecturer, Department of Information Technology Cummins College of Engineering for Women Karve Nagar, Pune - 411052 for more effective" f6684367e7925cd90fb8974640d41823191c7cff,CNN-based Pore Detection and Description for High-Resolution Fingerprint Recognition,"Automatic Dataset Annotation to Learn CNN Pore Description for Fingerprint Recognition Gabriel Dahia Maur´ıcio Pamplona Segundo Department of Computer Science, Federal University of Bahia" f64fb2e5cfa86fe68e9c239557f440c412d02274,Fast Face Detection using MLP and FFT,"Fast Face Detection using MLP and FFT S(cid:0) Ben(cid:1)Yacoub(cid:2) B(cid:0) Fasel and J(cid:0) L(cid:3)uttin IDIAP CP  (cid:2)   Martigny Switzerland email(cid:0) sby(cid:1)idiap(cid:2)ch" f6567671cc9d204c1dd1322e9c49d2053ed734c5,A REVIEW OF VISION BASED HAND GESTURES RECOGNITION,"International Journal of Information Technology and Knowledge Management July-December 2009, Volume 2, No. 2, pp. 405-410 A REVIEW OF VISION BASED HAND GESTURES RECOGNITION G. R. S. Murthy & R. S. Jadon With the ever-increasing diffusion of computers into the society, it is widely believed that present popular mode of interactions with computers (mouse and keyboard) will become a bottleneck in the effective utilization of information flow between the omputers and the human. Vision based Gesture recognition has the potential to be a natural and powerful tool supporting efficient and intuitive interaction between the human and the computer. Visual interpretation of hand gestures can help in chieving the ease and naturalness desired for Human Computer Interaction (HCI). This has motivated many researchers in omputer vision-based analysis and interpretation of hand gestures as a very active research area. We surveyed the literature on visual interpretation of hand gestures in the context of its role in HCI and various seminal works of researchers are emphasized. The purpose of this review is to introduce the field of gesture recognition as a mechanism for interaction with omputers. Keywords: Hand Gesture Recognition, Human Computer Interaction, Computer Vision. . INTRODUCTION With the development of information technology in our society, we can expect that computer systems to a larger extent will be embedded into our environment. These environments will impose needs for new types of human- omputer-interaction, with interfaces that are natural and" f6ce34d6e4e445cc2c8a9b8ba624e971dd4144ca,Cross-Label Suppression: A Discriminative and Fast Dictionary Learning With Group Regularization,"Cross-label Suppression: A Discriminative and Fast Dictionary Learning with Group Regularization Xiudong Wang and Yuantao Gu∗ April 24, 2017" f621f4cdb4158f72f12fdd55564bcdce322dce7c,Recursive Coarse-to-Fine Localization for Fast Object Detection,"International Journal of Control and Automation Vol.7, No.1 (2014), pp.235-242 http://dx.doi.org/10.14257/ijca.2014.7.1.20 Recursive Coarse-to-Fine Localization for Fast Object Detection Quy Nguyen Trung, Dung Phan,Soo Hyung Kim, In Seop Na* nd Hyung Jeong Yang School of Electronics and Computer Engineering Chonnam National University 77 Yongbong-ro, Gwangju, 500-757 South Korea" f6785ffe6fe2c30887637a61061a64f4d6725979,BAR: Bayesian Activity Recognition using variational inference,"BAR: Bayesian Activity Recognition using variational inference Ranganath Krishnan Mahesh Subedar Omesh Tickoo Intel Labs Hillsboro, OR (USA)" f6c70635241968a6d5fd5e03cde6907022091d64,Measuring Deformations and Illumination Changes in Images with Applications to Face Recognition, f6742010372210d06e531e7df7df9c01a185e241,Dimensional Affect and Expression in Natural and Mediated Interaction,"Dimensional Affect and Expression in Natural and Mediated Interaction Michael J. Lyons Ritsumeikan, University Kyoto, Japan October, 2007" f6488c7741eaddf6cbbd0b0728c48fd8ee1c00a4,Super-Resolution of Face Images Using Kernel PCA-Based Prior,"[3] C. L. Yang, L. M. Po, and W. H. Lam, “A fast H.264 intra prediction lgorithm using macroblock properties,” in Proc. IEEE ICIP’04, Oct. 004, vol. 1, pp. 461–464. [4] F. Pan, X. Lin, S. Rahardja, and K. P. Lim et al., “Fast mode decision lgorithm for intraprediction in H.264/AVC video coding,” IEEE Trans. Circuits Syst. Video Technol., vol. 15, no. 7, pp. 813–822, Jul. 2005. [5] P. Yin, H. C. Tourapis, A. M. Tourapis, and J. Boyce, “Fast mode de- ision and motion estimation for JVT/H.264,” in Proc. IEEE ICIP’03, Sept. 2003, vol. 3, pp. 853–856. [6] X. Jing and L. P. Chau, “Fast approach for H.264 inter mode decision,” Electron. Lett., vol. 40, no. 17, pp. 1051–1052, Aug. 2004. [7] D. Wu, F. Pan, K. P. Lim, and S. Wu et al., “Fast intermode decision in H.264/AVC video coding,” IEEE Trans. Circuits Syst. Video Technol., vol. 15, no. 7, pp. 953–958, Jul. 2005. [8] L. Yang, K. Yu, J. Li, and S. Li, “An effective variable block-size early termination algorithm for H.264 video coding,” IEEE Trans. Circuits Syst. Video Technol., vol. 15, no. 6, pp. 784–788, Jun. 2005. [9] H.264/AVC Reference Software JM9.5 [Online]. Available: http:// iphome.hhi.de/suehring/tml/ [10] Y. H. Moon, G. Y. Kim, and J. H. Kim, “An improved early" f6ce7e947f1cfe75abda61f018c3ca7e38fceb20,NLE@MediaEval'17: Combining Cross-Media Similarity and Embeddings for Retrieving Diverse Social Images,"NLE MediaEval’17: Combining Cross-Media Similarity and Embeddings for Retrieving Diverse Social Images Jean-Michel Renders and Gabriela Csurka Naver Labs Europe, Meylan, France" f676cdb17ccd5b65f44ce67677d8646b48d8939e,Occupancy Networks: Learning 3D Reconstruction in Function Space,"Occupancy Networks: Learning 3D Reconstruction in Function Space Lars Mescheder1 Michael Oechsle1,2 Michael Niemeyer1 Sebastian Nowozin3† Andreas Geiger1 Autonomous Vision Group, MPI for Intelligent Systems and University of T¨ubingen ETAS GmbH, Stuttgart Google AI Berlin" f60070d3a4d333aa1436e4c372b1feb5b316a7ba,Face Recognition via Centralized Coordinate Learning,"Face Recognition via Centralized Coordinate Learning Xianbiao Qi, Lei Zhang" 7dba0e39bb059103e10fb81bce2fe831f520fb38,Articulated human pose estimation in natural images,"Articulated Human Pose Estimation in Natural Images Samuel Alan Johnson Submitted in accordance with the requirements for the degree of Doctor of Philosophy. The University of Leeds School of Computing October 2012" 7d057676c9ba7b313adf0b191f64eb26ac2f9dd6,Variability in postnatal sex hormones due to the use of oral contraception and the phase of menstrual cycle influenced brain,"SEX DIFFERENCES AND THE ROLE OF SEX HORMONES IN FACE DEVELOPMENT AND FACE PROCESSING Klára Marečková, MSc. Thesis submitted to the University of Nottingham for the degree of Doctor of Philosophy JULY 2013" 7d98dcd15e28bcc57c9c59b7401fa4a5fdaa632b,FACE APPEARANCE FACTORIZATION FOR EXPRESSION ANALYSIS AND SYNTHESIS,"FACE APPEARANCE FACTORIZATION FOR EXPRESSION ANALYSIS AND SYNTHESIS Bouchra Abboud, Franck Davoine Heudiasyc Laboratory, CNRS, University of Technology of Compi`egne. BP 20529, 60205 COMPIEGNE Cedex, FRANCE. E-mail:" 7d7f60e41dd9cb84ac5754d59e5a8b418fc7a685,Generator Based On Deep Neural Networks,"Image Caption Generator Based On Deep Neural Networks Jianhui Chen CPSC 503 CS Department Wenqiang Dong CPSC 503 CS Department Minchen Li CPSC 540 CS Department" 7d3dd33950f4a1be56eb88c0791263b3e3a6deee,Object Counts! Bringing Explicit Detections Back into Image Captioning,"Object Counts! Bringing Explicit Detections Back into Image Captioning Josiah Wang, Pranava Madhyastha and Lucia Specia {j.k.wang, p.madhyastha, Department of Computer Science University of Sheffield, UK" 7db00be42ded44f87f23661c49913f9d64107983,TROPE R HCRAESE R PAID I 2 D FACE RECOGNITION : AN EXPERIMENTAL AND REPRODUCIBLE RESEARCH SURVEY,"D FACE RECOGNITION: AN EXPERIMENTAL AND REPRODUCIBLE RESEARCH SURVEY Manuel Günther Laurent El Shafey Sébastien Marcel Idiap-RR-13-2017 APRIL 2017 Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" 7dab6fbf42f82f0f5730fc902f72c3fb628ef2f0,An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks,"An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks Rushil Anirudh Center for Applied Scientific Computing Lawrence Livermore National Laboratory Jayaraman J. Thiagarajan Center for Applied Scientific Computing Lawrence Livermore National Laboratory Bhavya Kailkhura Timo Bremer Center for Applied Scientific Computing Lawrence Livermore National Laboratory Center for Applied Scientific Computing Lawrence Livermore National Laboratory" 7de028e5c878b56057559bfbd57f1ce6482ec282,An Architecture for Agile Machine Learning in Real-Time Applications,"An Architecture for Agile Machine Learning in Real-Time Applications Johann Schleier-Smith San Francisco, CA 94111 if(we) Inc. 848 Battery St." 7d96ecb24b3d8595267365cfc9878d46280f1e8c,End-to-end steering angle prediction and object detection using convolutional neural networks,"End-to-end steering angle prediction and object detection using convolutional neural networks Øyvind Kjeldstad Grimnes Master of Science in Computer Science Submission date: June 2017 Supervisor: Frank Lindseth, IDI Norwegian University of Science and Technology Department of Computer Science" 7d92d82eae23fe872e8d29116ae22cbd0b15abce,Joint Image Clustering and Labeling by Matrix Factorization,"Joint Image Clustering and Labeling y Matrix Factorization Seunghoon Hong, Jonghyun Choi, Jan Feyereisl, Bohyung Han, Larry S. Davis" 7d7024c8c97c972f81c0789a3d282470c1737652,Spatio-Temporal View Invariant Human Pose Recovery in Cluttered Scenes,"Thesis Proposal Spatio-Temporal View Invariant Human Pose Recovery in Cluttered Scenes PhD Student Xavier P´erez Sala Advisor Cecilio Angulo Bah´on Co-Advisor Sergio Escalera Guerrero Universitat Polit`ecnica de Catalunya (UPC) PhD in Artificial Intelligence June 14, 2012" 7ddd2eb46fcc7cb36974b5d105e84071c3e40572,On design and optimization of face verification systems that are smart-card based,"DOI 10.1007/s00138-009-0187-x ORIGINAL PAPER On design and optimization of face verification systems that are smart-card based Thirimachos Bourlai · Josef Kittler · Kieron Messer Received: 19 November 2007 / Revised: 26 October 2008 / Accepted: 11 January 2009 / Published online: 10 February 2009 © Springer-Verlag 2009" 7dfedb083fadb6822c07be82233588c31f37317c,FPGA-based IP cores implementation for face recognition using dynamic partial reconfiguration,"J Real-Time Image Proc (2013) 8:327–340 DOI 10.1007/s11554-011-0221-x S P E C I A L I S S U E FPGA-based IP cores implementation for face recognition using dynamic partial reconfiguration Afandi Ahmad • Abbes Amira • Paul Nicholl • Benjamin Krill Received: 8 October 2010 / Accepted: 22 August 2011 / Published online: 14 September 2011 Ó Springer-Verlag 2011" 7d3f6dd220bec883a44596ddec9b1f0ed4f6aca2,Linear Regression for Face Recognition,"Linear Regression for Face Recognition Imran Naseem, Roberto Togneri, Senior Member, IEEE, and Mohammed Bennamoun" 7d84c9322368e0df02b2ee3649c368b10e99cc80,Wavelet – Based Face Recognition Schemes 99 Wavelet – Based Face Recognition Schemes,"Wavelet–Based Face Recognition Schemes Wavelet–Based Face Recognition Schemes Sabah A. Jassim University of Buckingham, Buckingham MK18 1EG United Kingdom" 7d5a83495c4eff62c98c3fd27d0992850611b2bd,Enhanced Performance of Consensus Fault-tolerant Schemes for Decentralized 363 Unmanned Autonomous Vehicle System —,"Proceedings of the Pakistan Academy of Sciences: A. Physical and Computational Sciences 53 (4): 363–372 (2016) Copyright © Pakistan Academy of Sciences ISSN: 2518-4245 (print), 2518-4253 (online) Pakistan Academy of Sciences Research Article Enhanced Performance of Consensus Fault-tolerant Schemes for Decentralized Unmanned Autonomous Vehicle System Naeem Khan*, Aitzaz Ali, and Wasi Ullah Campus, Pakistan *Electrical Engineering Department, University of Engineering and Technology Peshawar, Bannu" 7d8b467a524bfd4d65d6e9481dd56a1fb381723a,Research on Robust Local Feature Extraction Method for Human Detection,"Waseda University Doctoral Dissertation Research on Robust Local Feature Extraction Method for Human Detection TANG, Shaopeng Graduate School of Information, Production and Systems Waseda University Feb. 2011" 7d42c27163619fb259992ba518f165dd13eca11c,Face Recognition Using Completed Local Ternary Pattern ( CLTP ) Texture Descriptor,"International Journal of Electrical and Computer Engineering (IJECE) Vol. 7, No. 3, June 2017, pp. 1594~1601 ISSN: 2088-8708, DOI: 10.11591/ijece.v7i3.pp1594-1601  1594 Face Recognition Using Completed Local Ternary Pattern (CLTP) Texture Descriptor Taha H. Rassem1, Nasrin M. Makbol2, Sam Yin Yee3 ,3 Faculty of Computer Systems and Software Engineering, Universiti Malaysia Pahang, Kuantan, Malaysia IBM Centre of Excellence, Universiti Malaysia Pahang, Kuantan, Malaysia School of Electrical and Electronic Engineering, Universiti Sains Malaysia, Penang, Malaysia Article Info Article history: Received Feb 21, 2017 Revised Apr 21, 2017 Accepted May 6, 2017 Keyword: Face recognition Completed local binary pattern (CLBP) Completed local ternary" 7da069849066a55d219b9e5b043fb4e07dee2652,Image-based Family Verification in the wild,"Máster Universitario en Ingeniería Computacional y Sistemas Inteligentes Master Thesis Image-based Family Verification in the wild Oscar Serradilla Casado Director: Fadi Dornaika Co-director: Ignacio Arganda Carreras" 7d6132a884d2b154059c461e107c7a8c41603ef7,Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection,"Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection Jiale Cao, Yanwei Pang, Senior Member, IEEE, and Xuelong Li, Fellow, IEEE" 7dffe7498c67e9451db2d04bb8408f376ae86992,LEAR-INRIA submission for the THUMOS workshop,"LEAR-INRIA submission for the THUMOS workshop Heng Wang and Cordelia Schmid LEAR, INRIA, France" 7d73adcee255469aadc5e926066f71c93f51a1a5,Face alignment by deep convolutional network with adaptive learning rate,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 7d9dbef9bacf1257e942121f82c3f411f2a78fff,Machine Learning Performance on Face Expression Recognition using Filtered Backprojection in DCT-PCA Domain,"Machine Learning Performance on Face Expression Recognition using Filtered Backprojection in DCT-PCA Domain. Ongalo Pheobe1, Huang DongJun2 and Richard Rimiru3 1 School of Information Science and Engineering, Central South University Changsha, Hunan, 410083, PR China School of Information Science and Engineering, Central South University Changsha, Hunan, 410083, PR China School of Information Science and Engineering, Central South University Changsha, Hunan, 410083, PR China" 7d7cfc8dc71967f93c2b5ec611747e63c06e1aa1,Crowd Counting and Profiling : Methodology and Evaluation,"Crowd Counting and Profiling: Methodology nd Evaluation Chen Change Loy, Ke Chen, Shaogang Gong, and Tao Xiang" 7dd654ac5e775fa1fa585e257565455ae8832caf,Deep Pictorial Gaze Estimation,"Deep Pictorial Gaze Estimation Seonwook Park, Adrian Spurr, and Otmar Hilliges AIT Lab, Department of Computer Science, ETH Zurich" 7d841607ce29ff4a75734ffbf569431425d8342f,Bimodal 2D-3D face recognition using a two-stage fusion strategy,"Bimodal 2D-3D face recognition using a two-stage fusion strategy Amel AISSAOUI1 and Jean MARTINET2 University of Science and Technologies Houari Boumediene Algiers, Algeria Email: CRIStAL Lille 1 University Villeneuve d’Ascq, France Email:" 7dcd927b3651d9230f074d19a9b65d1c96fc4604,How to Train a CAT: Learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change,"How to Train a CAT: Learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change Lee Clement1 and Jonathan Kelly1" 7dfb22b8762575420f914305c5616515bd1b4aba,Design and Implementation of Real-Time Vehicular Camera for Driver Assistance and Traffic Congestion Estimation,"Sensors 2015, 15, 20204-20231; doi:10.3390/s150820204 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article Design and Implementation of Real-Time Vehicular Camera for Driver Assistance and Traffic Congestion Estimation Sanghyun Son and Yunju Baek * School of Computer Science and Engineering, Pusan National University, Busan 609735, Korea; E-Mail: * Author to whom correspondence should be addressed; E-Mail: Tel.: +82-10-2937-2599; Fax: +82-51-583-2873. Academic Editor: Leonhard M. Reindl Received: 16 June 2015 / Accepted: 10 August 2015 / Published: 18 August 2015" 7dce05b7765541b3fb49a144fb39db331c14fdd1,Modélisation et suivi des déformations faciales : applications à la description des expressions du visage dans le contexte de la langue des signes,"Modélisation et suivi des déformations faciales : pplications à la description des expressions du visage dans le contexte de la langue des signes Hugo Mercier To cite this version: Hugo Mercier. Modélisation et suivi des déformations faciales : applications à la description des expressions du visage dans le contexte de la langue des signes. Interface homme-machine [cs.HC]. Université Paul Sabatier - Toulouse III, 2007. Français. HAL Id: tel-00185084 https://tel.archives-ouvertes.fr/tel-00185084 Submitted on 5 Nov 2007 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents" 7df103807902f45824329ab9b2a558b8baf950b2,Precise Localization in High-Definition Road Maps for Urban Regions,"Precise Localization in High-Definition Road Maps for Urban Regions Fabian Poggenhans1, Niels Ole Salscheider1 and Christoph Stiller2" 7d30939e2d6f8b980910f4eeca5338d072f5ecb6,Pylon Model for Semantic Segmentation,"A Pylon Model for Semantic Segmentation Victor Lempitsky Andrea Vedaldi Visual Geometry Group, University of Oxford∗ Andrew Zisserman" 7dbc14895390babea6f283fb9153bae94eab727f,Segmentation de scènes extérieures à partir d ’ ensembles d ’ étiquettes à granularité et sémantique variables,"Segmentation de sc`enes ext´erieures `a partir d’ensembles d’´etiquettes `a granularit´e et s´emantique variables Damien Fourure, R´emi Emonet, Elisa Fromont, Damien Muselet, Alain Tremeau, Christian Wolf To cite this version: Damien Fourure, R´emi Emonet, Elisa Fromont, Damien Muselet, Alain Tremeau, et al.. Seg- mentation de sc`enes ext´erieures `a partir d’ensembles d’´etiquettes `a granularit´e et s´emantique variables. RFIA 2016, Jun 2016, Clermont Ferrand, France. HAL Id: hal-01318461 https://hal.archives-ouvertes.fr/hal-01318461 Submitted on 20 May 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," 7d35fe4f4a932d7598d94d64b72cfa7e6a70286d,Experimental Evaluation of Multiplicative Kernel SVM Classifiers for Multi-Class Detection,"Experimental Evaluation of Multiplicative Kernel SVM Classifiers for Multi-Class Detection Valentina Zadrija Mireo d.d. Zagreb, Croatia Email: Siniˇsa ˇSegvi´c Faculty of Electrical Engineering and Computing University of Zagreb Zagreb, Croatia Email:" 7d8354627468f1cb236c9f6f42c317c9c09f0c85,A DCT-based Multimanifold face recognition method using single sample per person,"The 8th Symposium on Advances in Science and Technology (8thSASTech), Mashhad, Iran. 8thSASTech.khi.ac.ir A DCT-based Multimanifold face recognition method using single sample per person Mehrasa Nabipour1, Ali Aghagolzadeh2, Homayun Motameni1 - Department of Computer Eng., Faculty of Eng., Sari Islamic Azad University, Sari, Iran - Faculty of Electrical and Computer Eng., Babol University of Technology, Babol, Iran." 7de6e81d775e9cd7becbfd1bd685f4e2a5eebb22,Labeled Faces in the Wild : A Survey,"Labeled Faces in the Wild: A Survey Erik Learned-Miller, Gary Huang, Aruni RoyChowdhury, Haoxiang Li, Gang Hua" 7d39d69b23424446f0400ef603b2e3e22d0309d6,"YOLO9000: Better, Faster, Stronger","YOLO9000: Better, Faster, Stronger Joseph Redmon∗†, Ali Farhadi∗† University of Washington∗, Allen Institute for AI† http://pjreddie.com/yolo9000/" 2d1f710ba593833cdb0b63880f60146504cf1dc5,Linguistically-driven Framework for Computationally Efficient and Scalable Sign Recognition,"Linguistically-driven Framework for Computationally Efficient and Scalable Sign Recognition Dimitris Metaxas*, Mark Dilsizian*, Carol Neidle** *Rutgers University, **Boston University *Rutgers University, CBIM, Department of Computer Science, 617 Bowser Road, Piscataway, NJ 08854 **Boston University Linguistics, 621 Commonwealth Ave., Boston, MA 02215" 2d1b8f60f2724efd6c9344870fb60e8525157d70,Parallel Multiscale Autoregressive Density Estimation,"Parallel Multiscale Autoregressive Density Estimation Scott Reed 1 A¨aron van den Oord 1 Nal Kalchbrenner 1 Sergio G´omez Colmenarejo 1 Ziyu Wang 1 Yutian Chen 1 Dan Belov 1 Nando de Freitas 1" 2d919473cf43e2522b2366271b778ce6ce7dc75c,Appearance-Based Re-identification of Humans in Low-Resolution Videos Using Means of Covariance Descriptors,"Appearance-based Re-Identification of Humans in Low-Resolution Videos using Means of Covariance Descriptors Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB J¨urgen Metzler 76131 Karlsruhe, Germany" 2df4d05119fe3fbf1f8112b3ad901c33728b498a,A regularization scheme for structured output problems : an application to facial landmark detection,"Facial landmark detection using structured output deep neural networks Soufiane Belharbi ∗1, Cl´ement Chatelain∗1, Romain H´erault∗1, and S´ebastien Adam∗2 LITIS EA 4108, INSA de Rouen, Saint ´Etienne du Rouvray 76800, France LITIS EA 4108, UFR des Sciences, Universit´e de Rouen, France. September 24, 2015" 2d6d4899c892346a9bc8902481212d7553f1bda4,Neural Face Editing with Intrinsic Image Disentangling SUPPLEMENTARY MATERIAL,"Neural Face Editing with Intrinsic Image Disentangling SUPPLEMENTARY MATERIAL Zhixin Shu1 Ersin Yumer2 Sunil Hadap2 Kalyan Sunkavalli2 Eli Shechtman 2 Dimitris Samaras1,3 Stony Brook University 2Adobe Research 3 CentraleSup´elec, Universit´e Paris-Saclay . Implementation: more details In this section, we provide more details regarding the implementation of the rendering layers fshading and fimage-formation as described in the paper. .1. Shading Layer The shading layer is rendered with a spherical harmonics illumination representation [6, 2, 7, 1]. where = c3n2 z − c5 = 2c1nxnz = c1n2 x − c1n2 The forward process is described by equations (3),(4), nd (5) in the main paper. We now provide the backward process, i.e., the partial derivatives ∂Si" 2d950a3e8c74efb08197bfcb9c64a6b111f6bcd9,DENSE MATCHING COMPARISON BETWEEN CENSUS AND A CONVOLUTIONAL NEURAL NETWORK ALGORITHM FOR PLANT RECONSTRUCTION,"DENSE MATCHING COMPARISON BETWEEN CENSUS AND A CONVOLUTIONAL NEURAL NETWORK ALGORITHM FOR PLANT RECONSTRUCTION Y. Xia, J. Tian, P. d’Angelo, P. Reinartz German Aerospace Center (DLR), Remote Sensing Technology Institute, 82234 Wessling, Germany (Yuanxin.Xia, Jiaojiao.Tian, Pablo.Angelo, Commission II, WG II/2 KEY WORDS: Dense Matching, Plants, 3D Modelling, Semi-Global Matching, Census, Convolutional Neural Networks" 2dc4b472fe257522a106dc1246b758113be60b59,Image Co-segmentation by Incorporating Color Reward Strategy and Active Contours Model,"Image Co-segmentation by Incorporating Color Reward Strategy and Active Contours Model Fanman Meng, Hongliang Li, Senior Member, IEEE, Guanghui Liu, King Ngi Ngan, Fellow, IEEE" 2d072cd43de8d17ce3198fae4469c498f97c6277,Random Cascaded-Regression Copse for Robust Facial Landmark Detection,"Random Cascaded-Regression Copse for Robust Facial Landmark Detection Zhen-Hua Feng, Student Member, IEEE, Patrik Huber, Josef Kittler, Life Member, IEEE, William Christmas, nd Xiao-Jun Wu" 2d3d4883350a48708cdc0c260479110e5eed965a,Leveraging Visual Question Answering for Image-Caption Ranking,"Leveraging Visual Question Answering for Image-Caption Ranking Xiao Lin Devi Parikh Virginia Tech" 2d54dc50bbc1a0a63b6f1000bc255f88d57a7a63,It's All Fun and Games until Someone Annotates: Video Games with a Purpose for Linguistic Annotation,Submitted 10/2013; Revised 03/2014; Revised 08/2014; Published 10/2014. c(cid:13)2014 Association for Computational Linguistics. 2d8eff4b085b57788e2f4485c81eb80910f94da0,The impact of organizational performance on the emergence of Asian American leaders.,"Journal of Applied Psychology The Impact of Organizational Performance on the Emergence of Asian American Leaders Seval Gündemir, Andrew M. Carton, and Astrid C. Homan Online First Publication, September 24, 2018. http://dx.doi.org/10.1037/apl0000347 CITATION Gündemir, S., Carton, A. M., & Homan, A. C. (2018, September 24). The Impact of Organizational Performance on the Emergence of Asian American Leaders. Journal of Applied Psychology. Advance online publication. http://dx.doi.org/10.1037/apl0000347" 2d9e30680a17bbdf83ce27287bc1901da7198f74,"Symmetry, probability, and recognition in face space.","Symmetry, probability, and recognition in face space Lawrence Sirovich1 and Marsha Meytlis Laboratory of Applied Mathematics, Mount Sinai School of Medicine, 1 Gustave L. Levy Place, New York, NY 10029 Communicated by Mitchell J. Feigenbaum, The Rockefeller University, New York, NY, December 12, 2008 (received for review June 9, 2008) The essential midline symmetry of human faces is shown to play a key role in facial coding and recognition. This also has deep and important connections with recent explorations of the organiza- tion of primate cortex, as well as human psychophysical experi- ments. Evidence is presented that the dimension of face recogni- tion space for human faces is dramatically lower than previous estimates. One result of the present development is the construc- tion of a probability distribution in face space that produces an interesting and realistic range of (synthetic) faces. Another is a recognition algorithm that by reasonable criteria is nearly 100% ccurate. face dimension 兩 probability distributions 兩 face recognition Visual space may be conveniently regarded as a tableau of gray levels assigned to a square of O(105) pixels. Human faces belong to a subspace of this high-dimensional space, and the representation/identification of faces termed the Rogue’s" 2d690c63b00e68782666ebf86ac0756fad100a18,Multiple-view face hallucination by a novel regression analysis in tensor space,"The International Arab Journal of Information Technology, Vol. 13, No. 6, November 2016 Multiple-View Face Hallucination by a Novel Regression Analysis in Tensor Space Faculty of Engineering and Technology, Panyapiwat Institute of Management, Thailand Parinya Sanguansat" 2d84c0d96332bb4fbd8acced98e726aabbf15591,Investigating the Role of Saliency for Face Recognition,"UNIVERSITY OF CALIFORNIA RIVERSIDE Investigating the Role of Saliency for Face Recognition A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Electrical Engineering Ramya Malur Srinivasan March 2015 Dissertation Committee: Professor Amit K Roy-Chowdhury, Chairperson Professor Ertem Tuncel Professor Conrad Rudolph Professor Tamar Shinar" 2d120c8c74bc029a14fb0726ef103c873a5090eb,Real-Time Gender Classification by Face Eman,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 7, No. 3, 2016 Real-Time Gender Classification by Face Eman Fares Al Mashagba Computer Sciences Department Zarqa University Zarqa, Jordan" 2d7d8c468bdf123b50ea473fe78a178bfc50724c,Evaluating multi-modal deep learning systems with microworlds,"Research proposal: Evaluating multi-modal deep learning systems with micro-worlds Alexander Kuhnle University of Cambridge (United Kingdom) 6th November 2016" 2d88e7922d9f046ace0234f9f96f570ee848a5b5,Building Better Detection with Privileged Information,"Building Better Detection with Privileged Information Z. Berkay Celik Department of CSE The Pennsylvania State University Patrick McDaniel Department of CSE The Pennsylvania State University Rauf Izmailov Applied Communication Sciences Basking Ridge, NJ, US Nicolas Papernot Department of CSE The Pennsylvania State University Ananthram Swami Army Research Laboratory" 2dfc48168c0de9e6c7135293c95b7d794fcfbbbf,Query-Driven Locally Adaptive Fisher Faces and Expert-Model for Face Recognition,"-4244-1437-7/07/$20.00 ©2007 IEEE I - 141 ICIP 2007" 2d27e2d8188743c4e3ca30fda5c25e70775f03e8,FollowMe: Person following and gesture recognition with a quadrocopter,"FollowMe: Person Following and Gesture Recognition with a Quadrocopter Tayyab Naseer*, J¨urgen Sturm†, and Daniel Cremers† *Department of Computer Science, University of Freiburg, Germany Department of Computer Science, Technical University of Munich, Germany" 2d12efd5aef4c180ecfaf65184eb7b56e5a40329,Object Recognition Based on Image Features : A Survey,"D Object Recognition Based on Image Features: A International Journal of Computer and Information Technology (ISSN: 2279 – 0764) Volume 03 – Issue 03, May 2014 Survey Dept. of Information Systems, Faculty of Computers and Khaled Alhamzi Information, Mansoura University Mansoura, Egypt Kalhamzi {at} yahoo.com Mohammed Elmogy Dept. of Information Technology, Faculty of Computers and Information, Mansoura University Mansoura, Egypt Dept. of Information Systems, Faculty of Computers and Sherif Barakat Information, Mansoura University Mansoura, Egypt" 2d71e0464a55ef2f424017ce91a6bcc6fd83f6c3,A Survey on : Image Process using Two-Stage Crawler,"International Journal of Computer Applications (0975 – 8887) National Conference on Advancements in Computer & Information Technology (NCACIT-2016) A Survey on: Image Process using Two- Stage Crawler Nilesh Wani Assistant Professor SPPU, Pune Department of Computer Engg Department of Computer Engg Department of Computer Engg Dipak Bodade BE Student SPPU, Pune Savita Gunjal BE Student SPPU, Pune Varsha Mahadik BE Student Department of Computer Engg SPPU, Pune dditional" 2df6aa6dd2683fb35f7dcd8536d7b67fb72ede12,What drives social in-group biases in face recognition memory? ERP evidence from the own-gender bias.,"doi:10.1093/scan/nst024 SCAN (2014) 9, 580^590 What drives social in-group biases in face recognition memory? ERP evidence from the own-gender bias Nicole Wolff,1,2 Kathleen Kemter,1 Stefan R. Schweinberger,1,2 and Holger Wiese1,2 Friedrich Schiller University of Jena, Jena, Germany and 2DFG Research Unit Person Perception, Friedrich Schiller University of Jena, Jena, Germany It is well established that memory is more accurate for own-relative to other-race faces (own-race bias), which has been suggested to result from larger perceptual expertise for own-race faces. Previous studies also demonstrated better memory for own-relative to other-gender faces, which is less likely to result from differences in perceptual expertise, and rather may be related to social in-group vs out-group categorization. We examined neural correlates of the own-gender bias using event-related potentials (ERP). In a recognition memory experiment, both female and male participants remembered faces of their respective own gender more accurately compared with other-gender faces. ERPs during learning yielded significant differences between the subsequent memory effects (subsequently remembered – subsequently forgotten) for own-gender compared with other-gender faces in the occipito-temporal P2 and the central N200, whereas neither later subsequent memory effects nor ERP old/new effects at test reflected a neural orrelate of the own-gender bias. We conclude that the own-gender bias is mainly related to study phase processes, which is in line with sociocognitive ccounts. Keywords: own-gender bias; ERP; face processing; Dm effect; old/new effect INTRODUCTION Although humans can recognize a massive number of previously en-" 2d9a49666bd72e7ba06579d9411ceb2df5205466,3D Face Mesh Modeling from Range Images for 3D Face Recognition,"-4244-1437-7/07/$20.00 ©2007 IEEE IV - 509 ICIP 2007" 2dc8364433bde6041f38792cd01a6e80a55b1471,Multi-target tracking by discriminative analysis on Riemannian manifold,"MULTI-TARGET TRACKING BY DISCRIMINATIVE ANALYSIS ON RIEMANNIAN MANIFOLD Slawomir Bak, Duc Phu Chau, Julien Badie, Etienne Corvee, François Bremond, Monique Thonnat To cite this version: Slawomir Bak, Duc Phu Chau, Julien Badie, Etienne Corvee, François Bremond, et al.. MULTI- TARGET TRACKING BY DISCRIMINATIVE ANALYSIS ON RIEMANNIAN MANIFOLD. ICIP - International Conference on Image Processing - 2012, Sep 2012, Orlando, United States. Computer Society, 1, pp.1-4, 2012, People re-identification and tracking from multiple cameras. HAL Id: hal-00703633 https://hal.inria.fr/hal-00703633 Submitted on 7 Jun 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est" 2d8d089d368f2982748fde93a959cf5944873673,Visually Guided Spatial Relation Extraction from Text,"Proceedings of NAACL-HLT 2018, pages 788–794 New Orleans, Louisiana, June 1 - 6, 2018. c(cid:13)2018 Association for Computational Linguistics" 2d0dfa8779aefa1a9a89a1b400188fa9114b4c0a,Functional Map of the World,"Functional Map of the World Gordon Christie1 Neil Fendley1 The Johns Hopkins University Applied Physics Laboratory James Wilson2 Ryan Mukherjee1 DigitalGlobe" 2db0d42192618d0c7419321fac06b887d96dea53,Image Set Classification for Low Resolution Surveillance,"Image Set Classification for Low Resolution Surveillance Uzair Nadeem, Syed Afaq Ali Shah, Mohammed Bennamoun, Roberto Togneri nd Ferdous Sohel" 2d6130f043e69849fc0443bb489c5d21f933eddd,Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach,"Noname manuscript No. (will be inserted by the editor) Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach Lin Wu · Chunhua Shen · Anton van den Hengel" 2d42b5915ca18fdc5fa3542bad48981c65f0452b,Generalization and Equilibrium in Generative Adversarial Nets (GANs),"Generalization and Equilibrium in Generative Adversarial Nets (GANs) Sanjeev Arora∗ Rong Ge † Yingyu Liang‡ Tengyu Ma§ Yi Zhang¶" 2d51b52b3eeae8877d1a76ca564a35b8e5051c9d,AU recognition on 3D faces based on an extended statistical facial feature model,"AU Recognition on 3D Faces Based On An Extended Statistical Facial Feature Model Xi Zhao, Emmanuel Dellandr´ea, Liming Chen and Dimitris Samaras" 2d15a7546c16d5821ffa8f769eb7ec18e435e64d,Recognition in Terra Incognita,"Recognition in Terra Incognita Sara Beery, Grant Van Horn, and Pietro Perona Caltech" 2d22a60e69ebdb3fde056adcf4f6a08ccdb6106f,Robust Facial Expression Recognition Mr,"IJREAT International Journal of Research in Engineering & Advanced Technology, Volume 2, Issue 2, Apr-May, 2014 ISSN: 2320 – 8791 (Impact Factor: 1.479) www.ijreat.org Robust Facial Expression Recognition Mr. Mukund Kumar1, Ms. D. Udaya2 , 2Computer Science and Engineering, Dr. Pauls Engineering College,Villupuram" 2d05e768c64628c034db858b7154c6cbd580b2d5,FACIAL EXPRESSION RECOGNITION : Machine Learning using C # Author : Neda Firoz,"Neda Firoz et al, International Journal of Computer Science and Mobile Computing, Vol.4 Issue.8, August- 2015, pg. 431-446 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 8, August 2015, pg.431 – 446 RESEARCH ARTICLE ISSN 2320–088X FACIAL EXPRESSION RECOGNITION: Machine Learning using C# Author: Neda Firoz Advisor: Dr. Prashant Ankur Jain" 2df731a01db3caf45105c40ac266f76fe1871470,Affective issues in adaptive educational environments,"Neapolis University HEPHAESTUS Repository School of Information Sciences http://hephaestus.nup.ac.cy Book chapters Affective Issues in Adaptive Educational Environments Leontidis, Makis IGI Global http://hdl.handle.net/11728/6301 Downloaded from HEPHAESTUS Repository, Neapolis University institutional repository" 2d146cc0908c931d87f6e6e5d08b117c30a69b8d,Learning Assignment Order of Instances for the Constrained K-Means Clustering Algorithm,"Learning Assignment Order of Instances for Constrained K-means Clustering Algorithm Yi Hong, and Sam Kwong, Senior Member, IEEE Yi Hong is with the department of computer science, at the City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong. December 9, 2007 DRAFT" 2da845c75bf9ff02bd27b6e2ceb4732e89b05fad,Linear Support Tensor Machine With LSK Channels: Pedestrian Detection in Thermal Infrared Images,"Linear Support Tensor Machine: Pedestrian Detection in Thermal Infrared Images Sujoy Kumar Biswas, Student Member, IEEE, Peyman Milanfar, Fellow, IEEE" 2d95cf1df9701de410792997205c71208bde98d9,Visual-Inertial based autonomous navigation of an Unmanned Aerial Vehicle in GPS-Denied environments,"FACULDADE DE ENGENHARIA DA UNIVERSIDADE DO PORTO Visual-Inertial based autonomous navigation of an Unmanned Aerial Vehicle in GPS-Denied environments Francisco de Babo Martins EEC0035 - PREPARAÇÃO DA DISSERTAÇÃO Mestrado Integrado em Engenharia Electrotécnica e de Computadores Supervisor: Luís Teixeira February 18, 2015" 2d532fd0636fd49dd893c9dff7fe615f974ec826,Causal Inference in Nonverbal Dyadic Communication with Relevant Interval Selection and Granger Causality,"Causal Inference in Nonverbal Dyadic Communication with Relevant Interval Selection and Granger Causality Lea M¨uller1, Maha Shadaydeh1∗, Martin Th¨ummel1, Thomas Kessler2, Dana Schneider2 and Joachim Denzler1,3 Computer Vision Group, Friedrich Schiller University of Jena, Ernst-Abbe-Platz 2, 07743 Jena, Germany Department of Social Psychology, Friedrich Schiller University of Jena, Humboldtstrasse 26, 07743 Jena, Germany Michael Stifel Center, Ernst-Abbe-Platz 2, 07743 Jena, Germany Keywords: Nonverbal emotional communication, Granger causality, maximally coherent intervals" ecdf8e5393eead0b63c5bc4fbe426db5a70574eb,Linear Subspace Learning for Facial Expression Analysis,"Linear Subspace Learning for Facial Expression Analysis Caifeng Shan Philips Research The Netherlands . Introduction Facial expression, resulting from movements of the facial muscles, is one of the most powerful, natural, and immediate means for human beings to communicate their emotions nd intentions. Some examples of facial expressions are shown in Fig. 1. Darwin (1872) was the first to describe in detail the specific facial expressions associated with emotions in nimals and humans; he argued that all mammals show emotions reliably in their faces. Psychological studies (Mehrabian, 1968; Ambady & Rosenthal, 1992) indicate that facial expressions, with other non-verbal cues, play a major and fundamental role in face-to-face ommunication. Fig. 1. Facial expressions of George W. Bush. Machine analysis of facial expressions, enabling computers to analyze and interpret facial expressions as humans do, has many important applications including intelligent human- omputer interaction, computer animation, surveillance and security, medical diagnosis, law enforcement, and awareness system (Shan, 2007). Driven by its potential applications nd theoretical interests of cognitive and psychological scientists, automatic facial" ec4af4a6e89d61c05dcdf89f7f5d0a404bed4027,Bodily action penetrates affective perception.,"Bodily action penetrates affective perception Carlo Fantoni, Sara Rigutti and Walter Gerbino Department of Life Sciences, Psychology Unit “Gaetano Kanizsa,” University of Trieste, Trieste, Italy" ec1f3f1f1d9af3046650c3a30f95a7f2f0a78390,What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?,"IJCV VISI manuscript No. (will be inserted by the editor) What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation? Nikolaus Mayer · Eddy Ilg · Philipp Fischer · Caner Hazirbas · Daniel Cremers · Alexey Dosovitskiy · Thomas Brox Received: date / Accepted: date" ec7a545ba99542b2b74340d2e863590e4f450bb7,Sparse Subspace Clustering by Orthogonal Matching Pursuit,"Sparse Subspace Clustering by Orthogonal Matching Pursuit Center for Imaging Science, Johns Hopkins University, Baltimore, MD, 21218, USA Chong You nd Ren´e Vidal" ecf2ba5ea183a6be63b57543a19dd41e8017daaf,Cooperative Learning of Energy-Based Model and Latent Variable Model via MCMC Teaching,"Cooperative Learning of Energy-Based Model and Latent Variable Model via MCMC Teaching Jianwen Xie 1,2, Yang Lu 1,3, Ruiqi Gao 1, Ying Nian Wu 1 Department of Statistics, University of California, Los Angeles, USA Hikvision Research America Amazon RSML (Retail System Machine Learning) Group" ec6855acd0871d3e000872a5dd89db97c1554e18,Contrasting emotion processing and executive functioning in attention-deficit/hyperactivity disorder and bipolar disorder.,"016, Vol. 130, No. 5, 531–543 0735-7044/16/$12.00 © 2016 American Psychological Association http://dx.doi.org/10.1037/bne0000158 Contrasting Emotion Processing and Executive Functioning in Attention-Deficit/Hyperactivity Disorder and Bipolar Disorder Stephen Soncin, Donald C. Brien, and Brian C. Coe Queen’s University Queen’s University and Hotel Dieu Hospital, Kingston, Alina Marin Ontario, Canada Douglas P. Munoz Queen’s University Attention-deficit/hyperactivity disorder (ADHD) and bipolar disorder (BD) are highly comorbid and share executive function and emotion processing deficits, complicating diagnoses despite distinct clinical features. We compared performance on an oculomotor task that assessed these processes to capture subtle differences between ADHD and BD. The interaction between emotion processing and executive func- tioning may be informative because, although these processes overlap anatomically, certain regions that re compromised in each network are different in ADHD and BD. Adults, aged 18 – 62, with ADHD (n ⫽ 2), BD (n ⫽ 20), and healthy controls (n ⫽ 21) performed an interleaved pro- and antisaccade task" ecbb05ad1d5ffc9bad3c33a8cb800d3a6d034159,Generative Sensing: Transforming Unreliable Sensor Data for Reliable Recognition, ec196dbede1772541bb9df2efeda655d377b291e,Fast Disparity Estimation Using Dense Networks,"Fast Disparity Estimation using Dense Networks* Rowel Atienza1" ec89c5f2f5acce23b0d05736cd9f32d4ca6dc382,Body Actions Change the Appearance of Facial Expressions,"Body Actions Change the Appearance of Facial Expressions Carlo Fantoni1,2*, Walter Gerbino1 Department of Life Sciences, Psychology Unit ‘‘Gaetano Kanizsa’’, University of Trieste, Trieste, Italy, 2 Center for Neuroscience and Cognitive Istituto Italiano di Tecnologia, Rovereto, Italy" ecbaa92c289f4f5ff9a57b19a2725036a92311f5,Focused Evaluation for Image Description with Binary Forced-Choice Tasks,"Proceedings of the 5th Workshop on Vision and Language, pages 19–28, Berlin, Germany, August 12 2016. c(cid:13)2016 Association for Computational Linguistics" ec2027c2dd93e4ee8316cc0b3069e8abfdcc2ecf,Latent Variable PixelCNNs for Natural Image Modeling,"Latent Variable PixelCNNs for Natural Image Modeling Alexander Kolesnikov 1 Christoph H. Lampert 1" ec91c6d6235f31c751b03489d7b1d472dfc9da26,Face Database Retrieval Using Pseudo 2D Hidden Markov Models,"Face Database Retrieval Using Pseudo 2D Hidden Markov Models Fraunhofer Institute for Media Communication IMK Stefan Eickeler Schloss Birlinghoven 53754 Sankt Augustin, Germany" ec1e03ec72186224b93b2611ff873656ed4d2f74,D Reconstruction of “ Inthe-Wild ” Faces in Images and Videos,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 D Reconstruction of “In-the-Wild” Faces in Images and Videos James Booth, Anastasios Roussos, Evangelos Ververas, Epameinondas Anton- kos, Stylianos Ploumpis, Yannis Panagakis, and Stefanos Zafeiriou" ec90d333588421764dff55658a73bbd3ea3016d2,Protocol for Systematic Literature Review of Face Recognition in Uncontrolled Environment,"Research Article Protocol for Systematic Literature Review of Face Recognition in Uncontrolled Environment Faizan Ullah, Sabir Shah, Dilawar Shah, Abdusalam, Shujaat Ali Department of Computer Science, Bacha Khan University, Charsadda, KPK, Pakistan" ecb927634e8a734710a3b3734e1bffccac7b7061,Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization,"Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization Humam Alwassel, Fabian Caba Heilbron, and Bernard Ghanem King Abdullah University of Science and Technology (KAUST), Saudi Arabia http://www.humamalwassel.com/publication/action-search/" ecc09ab9c61dc3a3a15f55332f63bccbf443f291,Cross-Domain Deep Face Matching for Real Banking Security Systems,"Cross-Domain Deep Face Matching for Real Banking Security Systems Johnatan S. Oliveira1,∗, Gustavo B. Souza2,∗, Anderson R. Rocha3, Fl´avio E. Deus1 and Aparecido N. Marana4 Department of Electrical Engineering, University of Bras´ılia (UnB), Bras´ılia, Brazil. Department of Computing, Federal University of S˜ao Carlos (UFSCar), S˜ao Carlos, Brazil. Institute of Computing, University of Campinas (Unicamp), Campinas, Brazil. Department of Computing, S˜ao Paulo State University (Unesp), Bauru, Brazil. E-mails: {jow, Equal contributors." ece31d41b4da5457d570c04d22f19fcd026776b6,Learning Deep Disentangled Embeddings with the F-Statistic Loss,"Learning Deep Disentangled Embeddings With the F-Statistic Loss Karl Ridgeway University of Colorado Boulder, Colorado Department of Computer Science Department of Computer Science Michael C. Mozer University of Colorado Boulder, Colorado" ec5f36e9a1086401695e7b9fc1bb8a0ee4df7fe1,Safe Reinforcement Learning with Model Uncertainty Estimates,"Safe Reinforcement Learning with Model Uncertainty Estimates Bj¨orn L¨utjens, Michael Everett, Jonathan P. How" ec25f39fa6b4ef4529981a1ae051086e93642d27,Deformable Part Models are Convolutional Neural Networks Tech report,"Deformable Part Models are Convolutional Neural Networks Tech report Ross Girshick Forrest Iandola Trevor Darrell Jitendra Malik UC Berkeley" ec9e8d69b67bcb2814b538091fa288b6bdbb990f,GURLS : a Toolbox for Regularized Least Squares Learning,"Computer Science and ArtificialIntelligence LaboratoryTechnical Reportmassachusetts institute of technology, cambridge, ma 02139 usa — www.csail.mit.eduMIT-CSAIL-TR-2012-003CBCL-306January 31, 2012GURLS: a Toolbox for Regularized Least Squares LearningAndrea Tacchetti, Pavan S. Mallapragada, Matteo Santoro, and Lorenzo Rosasco" ec27b3d1548909d3f55246a388d768cf51e65802,Face Mask Extraction in Video Sequence,"Face Mask Extraction in Video Sequence Yujiang Wang 1 · Bingnan Luo 1 · Jie Shen 1 · Maja Pantic 1" ecab74350042a494110ee2f452bb96a89bc146f6,OBLIQUE AERIAL IMAGERY – A REVIEW,"Remondino, Gerke Oblique Aerial Imagery – A Review Fabio Remondino, Trento Markus Gerke, Twente" ec7d418ddf95d231b2afc70ed8c94d0764abec61,Knowledge Transfer Using Latent Variable Models,"Copyright Ayan Acharya" ec0104286c96707f57df26b4f0a4f49b774c486b,An Ensemble CNN2ELM for Age Estimation,"An Ensemble CNN2ELM for Age Estimation Mingxing Duan , Kenli Li, Senior Member, IEEE, and Keqin Li, Fellow, IEEE" ecd0a2e55f456b69243d1278fee15d8dbfc98c28,Heterogeneous Multicores : When Slower is Faster,"Heterogeneous Multicores: When Slower is Faster Tomas Hruby Herbert Bos The Network Institute, VU University Amsterdam Andrew S. Tanenbaum" ecf4690ddd3ad26f9cd1749d16ef1aa06d391f92,Does Exposure to Hostile Environments Predict Enhanced Emotion Detection?,"PDF hosted at the Radboud Repository of the Radboud University Nijmegen The following full text is a publisher's version. For additional information about this publication click this link. http://hdl.handle.net/2066/191999 Please be advised that this information was generated on 2018-06-28 and may be subject to hange." ec1223c8fc16751dd577d3418f61d44a139c7dc3,Group Influences on Engaging Self-Control: Children Delay Gratification and Value It More When Their In-Group Delays and Their Out-Group Doesn't.,"RUNNING HEAD: GROUP INFLUENCES ON SELF-CONTROL Group Influences on Engaging Self-control: Children Delay Gratification and Value It More When Their In-Group Delays and Their Out-Group Doesn’t Sabine Doebel* and Yuko Munakata Department of Psychology and Neuroscience, University of Colorado Boulder *Corresponding author" ec12f805a48004a90e0057c7b844d8119cb21b4a,Distance-Based Descriptors and Their Application in the Task of Object Detection,"Distance-Based Descriptors and Their Application in the Task of Object Detection Radovan Fusek(B) and Eduard Sojka Department of Computer Science, Technical University of Ostrava, FEECS, 7. Listopadu 15, 708 33 Ostrava-Poruba, Czech Republic" ec33350d7c4dd7a3b35bf6d7cf799af4ac1796a0,Learning towards Minimum Hyperspherical Energy,"Learning towards Minimum Hyperspherical Energy Weiyang Liu1,*, Rongmei Lin2,*, Zhen Liu1,*, Lixin Liu3,*, Zhiding Yu4, Bo Dai1,5, Le Song1,6 Georgia Institute of Technology 2Emory University South China University of Technology 4NVIDIA 5Google Brain 6Ant Financial" 376ea595a6ff5b876367654833de1e1778bacd1e,Examensarbete på avancerad nivå Independent degree project second cycle,"Bilingualism and ambiguous emotional cues 1 Examensarbete på avancerad nivå Independent degree project  second cycle Psychology Major subject Title Bilingualism and Children's Attention to Facial Expressions that Conflict with Lexical Content Amani Asad" 375993fd5f94c7b02169ff0d71a74d1b84262dfc,Parallel Application Library for Object Recognition,"Parallel Application Library for Object Recognition Bor-Yiing Su Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2012-199 http://www.eecs.berkeley.edu/Pubs/TechRpts/2012/EECS-2012-199.html September 27, 2012" 3771e8a09bc448af076a02ec7e0780d8435ed86a,Synchronous Adversarial Feature Learning for LiDAR based Loop Closure Detection, 37347e4c1b35196761fc1620e451738f880f0392,Exemplar-based human action pose correction and tagging,"Exemplar-Based Human Action Pose Correction and Tagging Wei Shen Ke Deng Xiang Bai Huazhong Univ. of Sci.&Tech. Microsoft Corporation Huazhong Univ. of Sci.&Tech. Tommer Leyvand Microsoft Corporation Baining Guo Zhuowen Tu Microsoft Research Asia Microsoft Research Asia & UCLA" 372bc106c61e7eb004835e85bbfee997409f176a,Coupled Generative Adversarial Networks,"Coupled Generative Adversarial Networks Mitsubishi Electric Research Labs (MERL), Mitsubishi Electric Research Labs (MERL), Ming-Yu Liu Oncel Tuzel" 3799e75b49d5b29d2a2a68c934d58ab4984e215c,Scale-invariant sampling for supervised image segmentation,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-0-9 ©2012 ICPR" 37a95a78bee34bb26a64c7ec30f7bd0496e072f1,The Focus-Aspect-Polarity Model for Predicting Subjective Noun Attributes in Images,"The Focus-Aspect-Polarity Model for Predicting Subjective Noun Attributes in Images Tushar Karayil1 DFKI, Germany Philipp Blandfort1 DFKI and TUK, Germany J¨orn Hees DFKI, Germany Andreas Dengel DFKI, Germany" 37c42f0a0e2e97a74113e1a1e1a79b04e0c64244,Covariance Pooling For Facial Expression Recognition,"Covariance Pooling for Facial Expression Recognition Computer Vision Lab, ETH Zurich, Switzerland VISICS, KU Leuven, Belgium Dinesh Acharya†, Zhiwu Huang†, Danda Pani Paudel†, Luc Van Gool†‡ {acharyad, zhiwu.huang, paudel," 376b73334bd9aebed1fbb69c4ed3848ec0826b6c,Online non-rigid structure-from-motion based on a keyframe representation of history,"Online Non-rigid Structure-from-motion based on a keyframe representation of history Simon Donn´e, Ljubomir Jovanov, Bart Goossens, Wilfried Philips, Aleksandra Piˇzurica Department of Telecommunications and Information Processing (TELIN) {Simon.Donne, Ljubomir.Jovanov, Bart.Goossens, Wilfried.Philips, Ghent University Ghent, Belgium" 376d9030b796cc6f0d1280aa2ff2c268eeae33b9,Tomofaces: Eigenfaces extended to videos of speakers,"-4244-1484-9/08/$25.00 ©2008 IEEE ICASSP 2008" 37a4eb74f9c9d6333864dbe1e0803d30c2e4db7c,An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification,"An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification Paul Marchwica, Michael Jamieson, Parthipan Siva Senstar Corporation Waterloo, Canada {Paul.Marchwica, Mike.Jamieson, the art" 37c014854655980870122143d16ecf585c7b8980,Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning,"Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning Crowd-Robot Interaction: Changan Chen, Yuejiang Liu, Sven Kreiss, Alexandre Alahi" 37838a832838ff3211b358bc51ba5105b9d82e89,The Complete Gabor-Fisher Classifier for Robust Face Recognition,"EURASIP JOURNAL ON ADVANCES IS SIGNAL PROCESSING The Complete Gabor-Fisher Classifier for Robust Face Recognition Vitomir ˇStruc and Nikola Paveˇsi´c" 372fb32569ced35eaf3740a29890bec2be1869fa,Mu rhythm suppression is associated with the classification of emotion in faces.,"Running head: MU RHYTHM MODULATION BY CLASSIFICATION OF EMOTION 1 Mu rhythm suppression is associated with the classification of emotion in faces Matthew R. Moore1, Elizabeth A. Franz1 Department of Psychology, University of Otago, Dunedin, New Zealand Corresponding authors: Matthew Moore & Liz Franz Phone: +64 (3) 479 5269; Fax: +64 (3) 479 8335 Department of Psychology University of Otago PO Box 56 Dunedin, New Zealand" 379ac913e976db227ff00c7e085fc97f5c8fb247,Learning Object Categories From Internet Image Searches,"I N V I T E D P A P E R Learning Object Categories From Internet Image Searches This paper shows how the results returned by an image search engine an be used to construct models from Internet images and use them for object recognition. By Rob Fergus, Li Fei-Fei, Pietro Perona, Member IEEE, and Andrew Zisserman" 377a1be5113f38297716c4bb951ebef7a93f949a,Facial emotion recognition with anisotropic inhibited Gabor energy histograms,"Dear Faculty, IGERT Fellows, IGERT Associates and Students, You are cordially invited to attend a Seminar presented by Albert Cruz. Please plan to attend. Albert Cruz IGERT Fellow Electrical Engineering Date: Friday, October 11, 2013 Location: Bourns A265 Time: 11:00am Facial emotion recognition with anisotropic inhibited gabor energy histograms" 37c1a8e302a450206580f95a2abceb5585be33e8,Title of Document : LONGITUDINAL SINGLE-UNIT RECORDING IN THE MACAQUE FACE PATCH SYSTEM : IDENTITY AND PLASTICITY IN THE ANTERIOR FUNDUS FACE PATCH,"Title of Document: Directed By:" 37381718559f767fc496cc34ceb98ff18bc7d3e1,Harnessing Synthesized Abstraction Images to Improve Facial Attribute Recognition,Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) 370b5757a5379b15e30d619e4d3fb9e8e13f3256,Labeled Faces in the Wild : A Database for Studying Face Recognition in Unconstrained Environments,"Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller" 375435fb0da220a65ac9e82275a880e1b9f0a557,From Pixels to Response Maps: Discriminative Image Filtering for Face Alignment in the Wild,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI From Pixels to Response Maps: Discriminative Image Filtering for Face Alignment in the Wild Akshay Asthana, Stefanos Zafeiriou, Georgios Tzimiropou- los, Shiyang Cheng and Maja Pantic" 378d1d5c16d816df8ffd79e9e8bf2056a0c66838,Scaling Up a Metric Learning Algorithm for Image Recognition and Representation,"Scaling Up a Metric Learning Algorithm for Image Recognition and Representation Adrian Perez-Suay and Francesc J. Ferri Dept. Inform`atica, Universitat de Val`encia. Spain" 372bf2716c53e353be6c3f027493f1a40edb6640,MINE: Mutual Information Neural Estimation,"Mutual Information Neural Estimation Mohamed Ishmael Belghazi 1 Aristide Baratin 1 2 Sai Rajeswar 1 Sherjil Ozair 1 Yoshua Bengio 1 3 4 Aaron Courville 1 3 R Devon Hjelm 1 4" 37a1c00a1f5b78eac269ed335c6610b91c4be76c,A multi-level data fusion approach for gradually upgrading theperformances of identity veri cation systems,"Amulti-leveldatafusionapproachforgraduallyupgradingthe performancesofidentityveri(cid:12)cationsystems Patrick Verlindea,b, Pascal Druytsa, G´erard Cholletb and Marc Acheroya Royal Military Academy/Signal and Image Centre, Brussels, Belgium CNRS URA-820, Ecole Nationale Sup´erieure de T´el´ecommunications/TSI Department, Paris, France" 377513421f9470f34c77bf64dc2c798eb50143d0,Pivoting strategy for fast LU decomposition of sparse block matrices,"PIVOTING STRATEGY FOR FAST LU DECOMPOSITION OF SPARSE BLOCK MATRICES Lukas Polok Brno University of Technology, Faculty of Information Technology, IT4Innovations Centre of Excellence Pavel Smrz Brno University of Technology, Faculty of Information Technology, IT4Innovations Centre of Excellence Bozetechova 1/2, Brno 61266, Czech Republic Bozetechova 1/2, Brno 61266, Czech Republic" 372a8bf0ef757c08551d41e40cb7a485527b6cd7,Unsupervised Video Hashing by Exploiting Spatio-Temporal Feature,"Unsupervised Video Hashing by Exploiting Spatio-Temporal Feature Chao Ma, Yun Gu, Wei Liu, and Jie Yang(cid:63) Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China." 37b207d2c4a82a57f80e96353f79ecd71320a854,Person Search with Natural Language Description,"Person Search with Natural Language Description Shuang Li1 Tong Xiao1 Hongsheng Li1∗ Bolei Zhou2 Dayu Yue3 Xiaogang Wang1 ∗ The Chinese University of Hong Kong 2Massachuate Institute of Technology 3SenseTime Group Limited" 37f2e03c7cbec9ffc35eac51578e7e8fdfee3d4e,Co-operative Pedestrians Group Tracking in Crowded Scenes Using an MST Approach,"WACV 2015 Submission #394. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. Co-operative Pedestrians Group Tracking in Crowded Scenes using an MST Approach Anonymous WACV submission Paper ID 394" 37278ffce3a0fe2c2bbf6232e805dd3f5267eba3,Can we still avoid automatic face detection?,"Can we still avoid automatic face detection? Michael J. Wilber1,2 Vitaly Shmatikov1,2 Serge Belongie1,2 Department of Computer Science, Cornell University 2 Cornell Tech" 3773e5d195f796b0b7df1fca6e0d1466ad84b5e7,Learning from Time Series in the Presence of Noise: Unsupervised and Semi-Supervised Approaches,"UNIVERSITY OF CALIFORNIA RIVERSIDE Learning from Time Series in the Presence of Noise: Unsupervised and Semi-Supervised Approaches A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Computer Science Dragomir Dimitrov Yankov March 2008 Dissertation Committee: Dr. Eamonn Keogh, Chairperson Dr. Stefano Lonardi Dr. Vassilis Tsotras" 3765df816dc5a061bc261e190acc8bdd9d47bec0,Presentation and validation of the Radboud Faces Database,"This article was downloaded by: [Radboud University Nijmegen] On: 24 November 2010 Access details: Access Details: [subscription number 907172236] Publisher Psychology Press Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37- 1 Mortimer Street, London W1T 3JH, UK Cognition & Emotion Publication details, including instructions for authors and subscription information: http://www.informaworld.com/smpp/title~content=t713682755 Presentation and validation of the Radboud Faces Database Oliver Langnera; Ron Dotscha; Gijsbert Bijlstraa; Daniel H. J. Wigboldusa; Skyler T. Hawkb; Ad van Knippenberga Radboud University Nijmegen, Nijmegen, The Netherlands b University of Amsterdam, Amsterdam, The Netherlands Online publication date: 22 November 2010 To cite this Article Langner, Oliver , Dotsch, Ron , Bijlstra, Gijsbert , Wigboldus, Daniel H. J. , Hawk, Skyler T. and van Knippenberg, Ad(2010) 'Presentation and validation of the Radboud Faces Database', Cognition & Emotion, 24: 8, 1377 — To link to this Article: DOI: 10.1080/02699930903485076 URL: http://dx.doi.org/10.1080/02699930903485076 PLEASE SCROLL DOWN FOR ARTICLE" 3752dc15fada54abc0af866273d03a28f4dc8975,A VARIATIONAL FRAMEWORK FOR PEDESTRIAN SEGMENTATION IN CLUTTERED SCENES USING BAG OF OPTICAL FLOWS AND SHAPE PRIORS,"A VARIATIONAL FRAMEWORK FOR PEDESTRIAN SEGMENTATION IN CLUTTERED SCENES USING BAG OF OPTICAL FLOWS AND SHAPE PRIORS Gagan Bansal A thesis submitted to The Johns Hopkins University in conformity with the requirements for the degree of Master of Science. Baltimore, Maryland January, 2009 (cid:176) Gagan Bansal 2009 All rights reserved" 3726b82007512a15a530fd1adad57af58a9abb62,Teaching Compositionality to CNNs,"Teaching Compositionality to CNNs∗ Austin Stone Yi Liu Huayan Wang D. Scott Phoenix Michael Stark Dileep George Vicarious FPC, San Francisco, CA, USA {austin, huayan, michael, yi, scott," 370ed90971eca7ad84c67d8804f97e02ff6fd5b4,"The Socio-Moral Image Database (SMID): A novel stimulus set for the study of social, moral and affective processes","RESEARCH ARTICLE The Socio-Moral Image Database (SMID): A novel stimulus set for the study of social, moral and affective processes Damien L. Crone1*, Stefan Bode1, Carsten Murawski2, Simon M. Laham1 Melbourne School of Psychological Sciences, University of Melbourne, Melbourne, Australia, Department of Finance, University of Melbourne, Melbourne, Australia" 37d6cde8be756b70d22262f1acc3442a0c6aa7ea,Kernel learning approaches for image classification,"Kernel Learning Approaches for Image Classification Dissertation zur Erlangung des akademischen Grades Doctor rerum naturalium (Dr.rer.nat) n der Naturwissenschaftlich-Technischen Fakult¨at I der Universit¨at des Saarlandes, Saarbr¨ucken vorgelegt von Dipl.-Inform. Peter Vincent Gehler 0. Juni 2009" 37c4541037b67e8f4c538b285efe80aa251a49b9,Tracking as a Whole: Multi-Target Tracking by Modeling Group Behavior With Sequential Detection,"Tracking as a Whole: Multi-Target Tracking y Modeling Group Behavior With Sequential Detection Yuan Yuan, Senior Member, IEEE, Yuwei Lu, and Qi Wang, Senior Member, IEEE" 374c7a2898180723f3f3980cbcb31c8e8eb5d7af,Facial Expression Recognition in Videos using a Novel Multi-Class Support Vector Machines Variant,"FACIAL EXPRESSION RECOGNITION IN VIDEOS USING A NOVEL MULTI-CLASS SUPPORT VECTOR MACHINES VARIANT Irene Kotsiay, Nikolaos Nikolaidisy and Ioannis Pitasy yAristotle University of Thessaloniki Department of Informatics Box 451, 54124 Thessaloniki, Greece" 370277791a0708b7c93deb21da172e025b558643,"Fusing LIDAR, camera and semantic information: A context-based approach for pedestrian detection","Fusing LIDAR, camera and semantic information: context-based approach for pedestrian detection Cristiano Premebida and Urbano Nunes The final version is available at: http://ijr.sagepub.com/content/32/3.toc This is a pre-print version." 37992120053b50b2f92eaa1949273bf828a54b50,Face Recognition Techniques-An evaluation Study,"Int. J. Advanced Networking and Applications Volume: 6 Issue: 4 Pages: 2393-2397 (2015) ISSN: 0975-0290 Face Recognition Techniques - An evaluation Department of Management Information System, Applied Science University, 166-11391, Jordan Study Dr.Asmahan M Altaher Email: Keywords" 374227c5d1858960ad1130059337b8c417a7ef15,The effect of the proportion of mismatching trials and task orientation on the confidence-accuracy relationship in unfamiliar face matching.,"Journal of Experimental Psychology: Applied The Effect of the Proportion of Mismatching Trials and Task Orientation on the Confidence–Accuracy Relationship in Unfamiliar Face Matching Rachel G. Stephens, Carolyn Semmler, and James D. Sauer Online First Publication, August 14, 2017. http://dx.doi.org/10.1037/xap0000130 CITATION Stephens, R. G., Semmler, C., & Sauer, J. D. (2017, August 14). The Effect of the Proportion of Mismatching Trials and Task Orientation on the Confidence–Accuracy Relationship in Unfamiliar Face Matching. Journal of Experimental Psychology: Applied. Advance online publication. http://dx.doi.org/10.1037/xap0000130" f9f08511f77c29ff948e146434dfb23608d3deb5,Question Answering Using Match-LSTM and Answer Pointer,"Question Answering Using Match-LSTM and Answer Pointer Annie Hu, Cindy Wang, and Brandon Yang {anniehu, ciwang, CodaLab: anniehu March 21, 2016 Introduction Machine comprehension of text is a significant problem in natural language processing today – in this project, we tackle machine reading comprehension as applied to question answering. Our goal is: given a question and a context paragraph, to extract from the paragraph the answer to the question. As an oracle, on the dataset we used, humans score over 86.8% accuracy (EM) on the test set for this task, while the best models only achieve roughly 75%. Existing approaches to this extractive Question Answering problem typically involve an encoding layer that encodes the question and paragraph into a sequence, some additional layer that accounts for interaction etween the question and paragraph, and a final decoding layer that extracts the answer from the paragraph [2][3][4][7]. In this paper, we will follow a similar structure, using LSTMs in our encoding and decoding layers, and calculating attention as our interaction layer. Dataset The dataset used is the recently released Stanford Question Answering Dataset (SQuAD)[1]. The context paragraphs are extracted from Wikipedia, while questions and answers are human-" f9028b47a4755a7349108b1dc281f13add5c6c12,Atypical gaze patterns in children and adults with autism spectrum disorders dissociated from developmental changes in gaze behaviour,"Downloaded from http://rspb.royalsocietypublishing.org/ on June 9, 2017 Proc. R. Soc. B doi:10.1098/rspb.2010.0587 Published online Atypical gaze patterns in children and dults with autism spectrum disorders dissociated from developmental changes in gaze behaviour Tamami Nakano1,2, Kyoko Tanaka3, Yuuki Endo1, Yui Yamane1, Takahiro Yamamoto4, Yoshiaki Nakano4, Haruhisa Ohta2,5, Nobumasa Kato2,5 and Shigeru Kitazawa1,2,* Department of Neurophysiology, and 3Department of Pediatrics, Juntendo University School of Medicine, Tokyo, Japan CREST, JST, Saitama, Japan Japanese Institute for Education and Treatment, Tokyo, Japan 5Department of Psychiatry, Showa University School of Medicine, Tokyo, Japan Eye tracking has been used to investigate gaze behaviours in individuals with autism spectrum disorder (ASD). However, traditional analysis has yet to find behavioural characteristics shared by both children" f935225e7811858fe9ef6b5fd3fdd59aec9abd1a,Spatiotemporal dynamics and connectivity pattern differences between centrally and peripherally presented faces,"www.elsevier.com/locate/ynimg Spatiotemporal dynamics and connectivity pattern differences etween centrally and peripherally presented faces Lichan Liu and Andreas A. Ioannides* Laboratory for Human Brain Dynamics, RIKEN Brain Science Institute (BSI), 2-1 Hirosawa, Wakoshi, Saitama, 351-0198, Japan Received 4 May 2005; revised 26 January 2006; accepted 6 February 2006 Available online 24 March 2006 Most neuroimaging studies on face processing used centrally presented images with a relatively large visual field. Images presented in this way ctivate widespread striate and extrastriate areas and make it difficult to study spatiotemporal dynamics and connectivity pattern differences from various parts of the visual field. Here we studied magneto- encephalographic responses in humans to centrally and peripherally presented faces for testing the hypothesis that processing of visual stimuli with facial expressions of emotions depends on where the stimuli are presented in the visual field. Using our tomographic and statistical parametric mapping analyses, we identified occipitotemporal reas activated by face stimuli more than by control conditions. V1/V2 ctivity was significantly stronger for lower than central and upper visual field presentation. Fusiform activity, however, was significantly" f96970f75b0f37787a47073bf7d02111f45abe83,3 D Face Recognition Performance under Adversarial Conditions, f997a71f1e54d044184240b38d9dc680b3bbbbc0,Deep Cross Modal Learning for Caricature Verification and Identification(CaVINet),"Deep Cross Modal Learning for Caricature Verification and Identification(CaVINet) https://lsaiml.github.io/CaVINet/ Jatin Garg∗ Indian Institute of Technology Ropar Himanshu Tolani∗ Indian Institute of Technology Ropar Skand Vishwanath Peri∗ Indian Institute of Technology Ropar Narayanan C Krishnan Indian Institute of Technology Ropar" f95616b1593467f5b11689582d934da34e6ad1ee,Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game,"Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game Haichao Zhang†, Haonan Yu†, and Wei Xu †§ § National Engineering Laboratory for Deep Learning Technology and Applications, Beijing China Baidu Research - Institue of Deep Learning, Sunnyvale USA" f9255703f0a89c9ca2e9256595a0526829ff4402,On the Importance of Visual Context for Data Augmentation in Scene Understanding,"On the Importance of Visual Context for Data Augmentation in Scene Understanding Nikita Dvornik, Julien Mairal, Senior Member, IEEE, and Cordelia Schmid, Fellow, IEEE" f94feceb5b725c6b303b758a0e5e90215b0174d3,Learning Non-maximum Suppression,"Learning non-maximum suppression Jan Hosang Rodrigo Benenson Bernt Schiele Max Planck Institut für Informatik Saarbrücken, Germany" f95ba7673789d1b4118d30e360a5a37fd75d3961,Face Recognition using Modified Generalized Hough Transform and Gradient Distance Descriptor,"Face Recognition using Modified Generalized Hough Transform nd Gradient Distance Descriptor Marian Moise, Xue Dong Yang and Richard Dosselmann Department of Computer Science, University of Regina, 3737 Wascana Parkway, Regina, Saskatchewan, Canada Keywords: Face Recognition, Generalized Hough Transform, Image Descriptors." f9784db8ff805439f0a6b6e15aeaf892dba47ca0,"Comparing the performance of Emotion-Recognition Implementations in OpenCV , Cognitive Services , and Google Vision APIs","Comparing the performance of Emotion-Recognition Implementations in OpenCV, Cognitive Services, and Google Vision APIs LUIS ANTONIO BELTRÁN PRIETO, ZUZANA KOMÍNKOVÁ OPLATKOVÁ Department of Informatics and Artificial Intelligence Tomas Bata University in Zlín Nad Stráněmi 4511, 76005, Zlín CZECH REPUBLIC" f9d1f12070e5267afc60828002137af949ff1544,Maximum Entropy Binary Encoding for Face Template Protection,"Maximum Entropy Binary Encoding for Face Template Protection Rohit Kumar Pandey Yingbo Zhou Bhargava Urala Kota Venu Govindaraju University at Buffalo, SUNY {rpandey, yingbozh, buralako," f98a975642972ce24e42e6957f63be556c11dd31,Dynamic Obstacle Detection of Road Scenes using Equi-Height Mosaicking Image,"Electronic Letters on Computer Vision and Image Analysis 13(2):13-14, 2014 Dynamic Obstacle Detection of Road Scenes using Equi-Height Mosaicking Image Min Woo Park and Soon Ki Jung School of Computer Science and Engineering, Kyungpook National University, 80 Daehak-ro, Bukgu, Daegu, Republic of Korea Advisor/s: Soon Ki Jung Date and location of PhD thesis defense: 3 December 2013, Kyungpook National University Received 30 January 2014; accepted 25 May 2014" f95ba9aab699394954f96c1419d3b1894b847e41,A Face Recognition Algorithm using Eigenphases and Histogram Equalization,"A Face Recognition Algorithm using Eigenphases and Histogram Equalization Kelsey Ramirez-Gutierrez, Daniel Cruz-Perez, Jesús Olivares-Mercado, Mariko Nakano-Miyatake, and Hector Perez-Meana" f9bee6e61833c0323c9175402b73442d27ab9eb8,D Human Poses Estimation from a Single 2 D Silhouette, f95f5e43f34e1bfb425b6491fc09558c44d2973d,Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation,"Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation Han Guo∗ Ramakanth Pasunuru∗ UNC Chapel Hill {hanguo, ram, Mohit Bansal" f984a9bb5c6e7b8a055b810bff468d7f8d80a7ff,Face identification by using fusing Photographic and Thermal Images,"www.jchps.com Journal of Chemical and Pharmaceutical Sciences Face identification by using fusing Photographic and Thermal Images M. Parisa Beham, 2M.R.H. Prasanna, 2SM.Mansoor Roomi and 1H. Jebina ISSN: 0974-2115 Vickram College of Engineering, Tamilnadu, India. Thiagarajar College of Engineering, Tamilnadu, India. *Corresponding Author:E-Mail" f9fdc63934841a0c4d8d29fdea80e1972ffcfe1e,Pedestrian Using Catadioptric Sensor 12,"Journal of Theoretical and Applied Information Technology 0th April 2018. Vol.96. No 8 © 2005 – ongoing JATIT & LLS ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 PEDESTRIAN USING CATADIOPTRIC SENSOR 2BOUI MAROUANE, 2HADJ-ABDELKADER HICHAM, 2ABABSA FAKHR-EDDINE, ABOUYAKHF EL HOUSSINE LIMIARF University Mohammed V-Rabat IBISC, University of Evry, France E-mail:" f96b3122f66c01cb78643d7e1b412e1bae16f2c4,Affective Robots : Evaluation of Automatic Emotion Recognition Approaches on a Humanoid Robot towards Emotionally Intelligent Machines,"World Academy of Science, Engineering and Technology International Journal of Mechanical and Mechatronics Engineering Vol:12, No:6, 2018 Affective Robots: Evaluation of Automatic Emotion Recognition Approaches on a Humanoid Robot towards Emotionally Intelligent Machines Silvia Santano Guill´en, Luigi Lo Iacono, Christian Meder" f98cbf32989387733529fa4fc943f0a7e97b5c07,To Know and To Learn - About the Integration of Knowledge Representation and Deep Learning for Fine-Grained Visual Categorization, f92ceb6875f614bbccb25e4b11ca55353773890f,Saliency Detection via Boundary Prior and Center Prior,"International Robotics & Automation Journal Saliency Detection via Boundary Prior and Center Prior" f8796b8e8246ce41efb2904c053fe0ea2868e373,A Variational U-Net for Conditional Appearance and Shape Generation,"A Variational U-Net for Conditional Appearance and Shape Generation Patrick Esser∗, Ekaterina Sutter∗, Bj¨orn Ommer Heidelberg Collaboratory for Image Processing IWR, Heidelberg University, Germany" f884a67187929e7dda66091c13867ed0a8a36d01,Weighted-Fusion-Based Representation Classifiers for Hyperspectral Imagery,"Remote Sens. 2015, 7, 14806-14826; doi:10.3390/rs71114806 OPEN ACCESS ISSN 2072-4292 www.mdpi.com/journal/remotesensing Article Weighted-Fusion-Based Representation Classifiers for Hyperspectral Imagery Bing Peng 1, Wei Li 1,*, Xiaoming Xie 1,*, Qian Du 2 and Kui Liu 3 College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China; E-Mail: Department of Electrical and Computer Engineering, Mississippi State University, Starkville, MS 39762, USA; E-Mail: Intelligent Fusion Technology, Germantown, MD 20876, USA; E-Mail: * Authors to whom correspondence should be addressed; E-Mails: (W.L.); (X.X.); Tel.: +86-010-6443-3717 (W.L.); +86-010-6441-3467 (X.X.). Academic Editors: Magaly Koch and Prasad S. Thenkabail Received: 17 June 2015 / Accepted: 30 October 2015 / Published: 6 November 2015" f8eedcca6263062b6bab11ead255f719452f1c81,Motion in action : optical flow estimation and action localization in videos. (Le mouvement en action : estimation du flot optique et localisation d'actions dans les vidéos),"Motion in action : optical flow estimation and action localization in videos Philippe Weinzaepfel To cite this version: Philippe Weinzaepfel. Motion in action : optical flow estimation and action localization in videos. Computer Vision and Pattern Recognition [cs.CV]. Université Grenoble Alpes, 2016. English. . HAL Id: tel-01407258 https://tel.archives-ouvertes.fr/tel-01407258 Submitted on 1 Dec 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" f89e5a8800b318fa03289b5cc67df54b956875b4,Do GANs actually learn the distribution? An empirical study,"Do GANs actually learn the distribution? An empirical study Sanjeev Arora Yi Zhang July 4, 2017" f881d2a04de838c8950a279e1ed8c0f9886452af,Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generation,"Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generation Lei Cai Hongyang Gao Washington State University Washington State University Pullman, WA 99164 Pullman, WA 99164 Shuiwang Ji Washington State University Pullman, WA 99164" f86d8385a6170b98e434a121fb7d12facb2c8426,Frank-Wolfe Algorithm for Exemplar Selection,"Frank-Wolfe Algorithm for Exemplar Selection Gary Cheng UC Berkeley Armin Askari UC Berkeley Laurent El Ghaoui Kannan Ramchandran UC Berkeley UC Berkeley" f8d68084931f296abfb5a1c4cd971f0b0294eaa4,UNCONDITIONAL GENERATIVE MODELS,"Published as a conference paper at ICLR 2018 LATENT CONSTRAINTS: LEARNING TO GENERATE CONDITIONALLY FROM UNCONDITIONAL GENERATIVE MODELS Jesse Engel Google Brain San Francisco, CA, USA Matthew D. Hoffman Google Inc. San Francisco, CA, USA Adam Roberts Google Brain San Francisco, CA, USA" f8ed5f2c71e1a647a82677df24e70cc46d2f12a8,Artificial Neural Network Design and Parameter Optimization for Facial Expressions Recognition,"International Journal of Scientific & Engineering Research, Volume 2, Issue 12, December-2011 1 ISSN 2229-5518 Artificial Neural Network Design and Parameter Optimization for Facial Expressions Recognition Ammar A. Alzaydi" f8e0910d50d7dffe7097b6263c6bb3952b1de336,50 Years of Test (Un)fairness: Lessons for Machine Learning,"50 Years of Test (Un)fairness: Lessons for Machine Learning Ben Hutchinson and Margaret Mitchell" f8ec92f6d009b588ddfbb47a518dd5e73855547d,Extreme Learning Machine Ensemble Using Bagging for Facial Expression Recognition,"J Inf Process Syst, Vol.10, No.3, pp.443~458, September 2014 ISSN 1976-913X (Print) ISSN 2092-805X (Electronic) Extreme Learning Machine Ensemble Using Bagging for Facial Expression Recognition Deepak Ghimire* and Joonwhoan Lee*" f8facd9691b9b41392aef606aea5e6bc2e7d489c,Recognition of Facial Expressions by Cortical Multi-scale Line and Edge Coding,"Recognition of facial expressions by cortical multi-scale line and edge coding R.J.R. de Sousa, J.M.F. Rodrigues and J.M.H. du Buf Vision Laboratory, Institute for Systems and Robotics (ISR/IST), University of the Algarve (ISE and FCT), 8005-135 Faro, Portugal" f8ec2079838520fcb9394574bdd956ac9d3d5832,Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks,"Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks Tianfan Xue*, Jiajun Wu*, Katherine L. Bouman, and William T. Freeman" f86c65bc2753ae71826a0dafbf46a75d22fb5b5b,Fearful Faces do Not Lead to Faster Attentional Deployment in Individuals with Elevated Psychopathic Traits,"J Psychopathol Behav Assess (2017) 39:596–604 DOI 10.1007/s10862-017-9614-x Fearful Faces do Not Lead to Faster Attentional Deployment in Individuals with Elevated Psychopathic Traits Sylco S. Hoppenbrouwers 1 & Jaap Munneke 2,3 & Karen A. Kooiman 4 & Bethany Little 4 & Craig S. Neumann 5 & Jan Theeuwes 4 Published online: 30 June 2017 # The Author(s) 2017. This article is an open access publication" f8ea0f76f2044168040fcd0a9e81072c88cde4a4,Nonlinear Feature Extraction using Multilayer Perceptron based Alternating Regression for Classification and Multiple-output Regression Problems, f8b26b2ec62cf76f58f95938233bc22ae1902144,UvA-DARE ( Digital Academic Repository ) Visual Tracking : An Experimental Survey Smeulders,"UvA-DARE (Digital Academic Repository) Visual Tracking: An Experimental Survey Smeulders, A.W.M.; Chu, D.M.; Cucchiara, R.; Calderara, S.; Dehghan, A.; Shah, M. Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence 0.1109/TPAMI.2013.230 Link to publication Citation for published version (APA): Smeulders, A. W. M., Chu, D. M., Cucchiara, R., Calderara, S., Dehghan, A., & Shah, M. (2014). Visual Tracking: An Experimental Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(7), 442-1468. DOI: 10.1109/TPAMI.2013.230 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Download date: 26 Apr 2018" f8f872044be2918de442ba26a30336d80d200c42,Facial Emotion Recognition Techniques : A Survey,"IJSRD - International Journal for Scientific Research & Development| Vol. 3, Issue 03, 2015 | ISSN (online): 2321-0613 Facial Emotion Recognition Techniques: A Survey Namita Rathore1 Rohit Miri2 ,2Department of Computer Science and Engineering ,2Dr C V Raman Institute of Science and Technology defense systems, surveillance" f8a5bc2bd26790d474a1f6cc246b2ba0bcde9464,"KDEF-PT: Valence, Emotional Intensity, Familiarity and Attractiveness Ratings of Angry, Neutral, and Happy Faces","ORIGINAL RESEARCH published: 19 December 2017 doi: 10.3389/fpsyg.2017.02181 KDEF-PT: Valence, Emotional Intensity, Familiarity and Attractiveness Ratings of Angry, Neutral, and Happy Faces Margarida V. Garrido* and Marília Prada Instituto Universitário de Lisboa (ISCTE-IUL), CIS – IUL, Lisboa, Portugal The Karolinska Directed Emotional Faces (KDEF) is one of the most widely used human facial expressions database. Almost a decade after the original validation study (Goeleven et al., 2008), we present subjective rating norms for a sub-set of 210 pictures which depict 70 models (half female) each displaying an angry, happy and neutral facial expressions. Our main goals were to provide an additional and updated validation to this database, using a sample from a different nationality (N = 155 Portuguese students, M = 23.73 years old, SD = 7.24) and to extend the number of subjective dimensions used to evaluate each image. Specifically, participants reported emotional labeling (forced-choice task) and evaluated the emotional intensity and valence of the expression, as well as the attractiveness and familiarity of the model (7-points rating" f81f5da2a1e4eb80b465b8dffca4c9e583a8a8a6,"Rapid Object Detection Systems , Utilising Deep Learning and Unmanned Aerial Systems ( Uas ) for Civil Engineering Applications","RAPID OBJECT DETECTION SYSTEMS, UTILISING DEEP LEARNING AND UNMANNED AERIAL SYSTEMS (UAS) FOR CIVIL ENGINEERING APPLICATIONS UCL Department of Civil, Environmental & Geomatic Engineering, Gower Street, London, WC1E 6BT – (david.griffiths.16, David Griffiths*, Jan Boehm Commission II, WG II/6 KEY WORDS: Object detection, Deep Learning, Unmanned Aerial Systems, Railway, Rapid" f865248065b8d6bcbce4a4053b73e4de2080ba23,Efficient object detection for high resolution images,"Efficient Object Detection for High Resolution Images Yongxi Lu1 and Tara Javidi1" f879556115284946637992191563849e840789d1,Geometry Guided Adversarial Facial Expression Synthesis,"Geometry Guided Adversarial Facial Expression Synthesis Lingxiao Song1,2 Zhihe Lu1,3 Ran He1,2,3 Zhenan Sun1,2 Tieniu Tan1,2,3 National Laboratory of Pattern Recognition, CASIA Center for Research on Intelligent Perception and Computing, CASIA Center for Excellence in Brain Science and Intelligence Technology, CAS" f827b596b4099b0490ab46a9dd2922db2b708963,Pathologies of Neural Models Make Interpretation Difficult,"Pathologies of Neural Models Make Interpretations Difficult Shi Feng1 Eric Wallace1 Alvin Grissom II2 Mohit Iyyer3,4 Pedro Rodriguez1 Jordan Boyd-Graber1 University of Maryland 2Ursinus College UMass Amherst 4Allen Institute for Artificial Intelligence" f8106b414d81df11ef2e9c26dd83f812711eec35,Inferring Analogous Attributes : Large-Scale Transfer of Category-Specific Attribute Classifiers,"Inferring Analogous Attributes: Large-Scale Transfer of Category-Specific Attribute Classifiers Chao-Yeh Chen and Kristen Grauman" f809f9e5a03817d238718723a7b4ac04abcd3f12,Highly Efficient 8-bit Low Precision Inference,"Under review as a conference paper at ICLR 2019 HIGHLY EFFICIENT 8-BIT LOW PRECISION INFERENCE OF CONVOLUTIONAL NEURAL NETWORKS Anonymous authors Paper under double-blind review" f8d5ab79943ca03d6ce1a24605435054ea9bd105,IR–videostream rendering based on high-level object information,"IR–videostream rendering ased on high-level object information Stefan Becker, Wolfgang H¨ubner, and Michael Arens Fraunhofer IOSB Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation Gutleuthausstr. 1, 76275 Ettlingen, Germany" e3e66ee37d08752dc19c3e3b212f869c8ff19f71,Effective Interaction-aware Trajectory Prediction using Temporal Convolutional Neural Networks,"Effective Interaction-aware Trajectory Prediction using Temporal Convolutional Neural Networks Noha Radwan Wolfram Burgard" e39f9565903a9701657ce3ade94c37d8a12f702e,Audio-Visual Scene Analysis with Self-Supervised Multisensory Features,"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features Andrew Owens Alexei A. Efros UC Berkeley" e3bbdd6efc906f6ae17e5b1d62497420991b977d,Visual Explanation by High-Level Abduction: On Answer-Set Programming Driven Reasoning About Moving Objects,"Visual Explanation by High-Level Abduction On Answer-Set Programming Driven Reasoning about Moving Objects Jakob Suchan1, Mehul Bhatt1,2, Przemysław Wał˛ega3, and Carl Schultz4 Cognitive Vision – www.cognitive-vision.org EASE CRC – http://ease-crc.org HCC Lab., University of Bremen, Germany, 2MPI Lab., Örebro University, Sweden University of Warsaw, Poland, and 4Aarhus University, Denmark" e37681d2fb9f65ed14170bb556cf64156f055167,Tracking by Prediction: A Deep Generative Model for Mutli-person Localisation and Tracking,"Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation nd Tracking Tharindu Fernando Simon Denman Sridha Sridharan Clinton Fookes Image and Video Research Laboratory, Queensland University of Technology (QUT), Australia {t.warnakulasuriya, s.denman, s.sridharan," e38709a2ec162a6f2a2fa3b4b6463e752267b154,SUPER-RESOLUTION FOR FACE RECOGNITION BASED ON CORRELATED FEATURES AND NONLINEAR MAPPINGS,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010" e3660a13fcd75cf876a6ce355c2c1a578cfb57cb,2DHMM-Based Face Recognition Method,"DHMM-BASED FACE RECOGNITION METHOD Janusz Bobulski1 Czestochowa University of Technology Institute of Computer and Information Science Dabrowskiego Street 73, 42-200 Czestochowa, Poland Summary. So far many methods of recognizing the face arose, each has the merits nd demerits. Among these methods are methods based on Hidden Markov models, nd their advantage is the high ef‌f‌iciency. However, the traditional HMM uses one- dimensional data, which is not a good solution for image processing, because the images are two-dimensional. Transforming the image in a one-dimensional feature vector, we remove some of the information that can be used for identification. The rticle presents the full ergodic 2D-HMM and applied for face identification. Introduction Face recognition has great potentials in many applications dealing with unco- operative subjects, in which the full power of face recognition being a passive iometric technique can be implemented and utilised. Face recognition has een an active area of research in image processing and computer vision due to its extensive range of prospective applications relating to biometrics, infor- mation security, video surveillance, law enforcement, identity authentication," e312e7657cb98cf03d3b2bf8b21b0ff75fbd4613,No 272 2 D Articulated Human Pose Estimation and Retrieval in ( Almost ) Unconstrained Still Images,"ETH Zurich, D-ITET, BIWI Technical Report No 272 D Articulated Human Pose Estimation and Retrieval in (Almost) Unconstrained Still Images M. Eichner, M. Marin-Jimenez, A. Zisserman, V. Ferrari" e3f63d12be07c743e7590957f4ed38b06cd98aba,A Novel Approach to Face Detection Algorithm,"A Novel Approach to Face Detection Algorithm {tag} {/tag} International Journal of Computer Applications © 2011 by IJCA Journal Number 2 - Article 4 Year of Publication: 2011 Authors: Pritam Singh A.S. Thoke Kesari Verma 10.5120/3537-4836" e378ce25579f3676ca50c8f6454e92a886b9e4d7,Robust Video Super-Resolution with Learned Temporal Dynamics,"Robust Video Super-Resolution with Learned Temporal Dynamics Ding Liu1 Zhaowen Wang2 Yuchen Fan1 Xianming Liu3 Zhangyang Wang4 Shiyu Chang5 Thomas Huang1 University of Illinois at Urbana-Champaign 2Adobe Research Facebook 4Texas A&M University 5IBM Research" e38c93bb8f7ee103eba4b78443d94f55a63bdf08,Extracting Pathlets From Weak Tracking Data ∗,"Extracting Pathlets From Weak Tracking Data∗ Kevin Streib James W. Davis Dept. of Computer Science and Engineering Ohio State University, Columbus, OH 43210" e39af9fb267c9deb81f9c73bbd71f5674b4358c0,Conceptualizing and Measuring Well-Being Using Statistical Semantics and Numerical Rating Scales,"Conceptualizing and Measuring Well-Being Using Statistical Semantics and Numerical Rating Scales Kjell, Oscar Published: 2018-03-01 Document Version Publisher's PDF, also known as Version of record Link to publication Citation for published version (APA): Kjell, O. (2018). Conceptualizing and Measuring Well-Being Using Statistical Semantics and Numerical Rating Scales Lund General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors nd/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal LUND UNIVERSITYPO Box 117221 00 Lund+46 46-222 00 00" e3144f39f473e238374dd4005c8b83e19764ae9e,Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild,"Next-Flow: Hybrid Multi-Tasking with Next-Frame Prediction to Boost Optical-Flow Estimation in the Wild Nima Sedaghat University of Freiburg Germany" e3c420b29b8590442decd330ef70494c2209f149,Learning a Part-Based Pedestrian Detector in a Virtual World,"Learning a Part-based Pedestrian Detector in Virtual World Jiaolong Xu, David V´azquez, Antonio M. L´opez Member, IEEE, Javier Mar´ın and Daniel Ponsa" e33b1833b2d0cd7b0450b22b96a567a59c9e4685,Attribute Discovery via Predictable Discriminative Binary Codes,"Attribute Discovery via Predictable Discriminative Binary Codes Mohammad Rastegari† Ali Farhadi‡ David Forsyth† University of Illinois at Urbana Champagin Carnegi Mellon University http://vision.ri.cmu.edu/projects/dbc/dbc.html" e36e8e1fb9abec16f0430bf69070bb318197d3d6,SUNIL BHARAMGOUDAR DETECTION OF FREE SPACE/OBSTACLES IN FRONT OF THE EGO CAR USING STEREO CAMERA IN URBAN SCENES,"SUNIL BHARAMGOUDAR DETECTION OF FREE SPACE/OBSTACLES IN FRONT OF THE EGO CAR USING STEREO CAMERA IN URBAN SCENES Master of Science thesis Examiner: prof. Jose L. Martinez Lastra Examiner and topic approved by the Faculty Council of the Faculty of Engineering Sciences on 3rd Sept 2014" e3e44385a71a52fd483c58eb3cdf8d03960c0b70,A Hierarchical Graphical Model for Recognizing Human Actions and Interactions in Video,"Copyright Sangho Park" e3c5c5623af4b1a1f719cac24850dcaa6a304bd5,Training Effective Node Classifiers for Cascade Classification,"ppearing in Int. J. Comput. Vis.; content may change prior to final publication. Training Effective Node Classifiers for Cascade Classification Chunhua Shen · Peng Wang · Sakrapee Paisitkriangkrai · Anton van den Hengel December 2012" e393a038d520a073b9835df7a3ff104ad610c552,Automatic temporal segment detection via bilateral long short-term memory recurrent neural networks,"Automatic temporal segment detection via bilateral long short- term memory recurrent neural networks Bo Sun Siming Cao Jun He Lejun Yu Liandong Li Bo Sun, Siming Cao, Jun He, Lejun Yu, Liandong Li, “Automatic temporal segment detection via bilateral long short-term memory recurrent neural networks,” J. Electron. Imaging 26(2), 020501 (2017), doi: 10.1117/1.JEI.26.2.020501. Downloaded From: http://electronicimaging.spiedigitallibrary.org/ on 03/03/2017 Terms of Use: http://spiedigitallibrary.org/ss/termsofuse.aspx" e3b0caa1ff9067665e349a2480b057e2afdbc41f,Interactive Effects of Obvious and Ambiguous Social Categories on Perceptions of Leadership: When Double-Minority Status May Be Beneficial.,"702373 PSPXXX10.1177/0146167217702373Personality and Social Psychology BulletinWilson et al. research-article2017 Article Interactive Effects of Obvious and Ambiguous Social Categories on Perceptions of Leadership: When Double-Minority Status May Be Beneficial Personality and Social Psychology Bulletin 017, Vol. 43(6) 888 –900 © 2017 by the Society for Personality nd Social Psychology, Inc Reprints and permissions: sagepub.com/journalsPermissions.nav DOI: 10.1177/0146167217702373 https://doi.org/10.1177/0146167217702373 journals.sagepub.com/home/pspb John Paul Wilson1, Jessica D. Remedios2, and Nicholas O. Rule3" e39d1345a5aef8a5ee32c0a774de877b903de50c,Unsupervised Learning of Semantics of Object Detections for Scene Categorization,"Unsupervised Learning of Semantics of Object Detections for Scene Categorization Grégoire Mesnil, Salah Rifai, Antoine Bordes, Xavier Glorot, Yoshua Bengio nd Pascal Vincent" e309632d479b8f59e615d0f3c4bc69938361d187,Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network,"Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network Fannya, Tjeng Wawan Cenggoroa,b Computer Science Department, School of Computer Science, Bina Nusantara University, Jakarta, Indonesia 11480 Bioinformatics and Data Science Research Center, Bina Nusantara University, Jakarta, Indonesia 11480" e33bc0cd79d92d6868989a29c3ab06b75f808590,Deep Nets: What have they ever done for Vision?,"Noname manuscript No. (will be inserted by the editor) Deep Nets: What have they ever done for Vision? Alan L. Yuille · Chenxi Liu Received: date / Accepted: date" e3f2e09894e49b2d0134cebd07d1f2fcbb22d97e,Bilingual corpus for AVASR using multiple sensors and depth information,"ISCA Archive http://www.isca-speech.org/archive Auditory-Visual Speech Processing (AVSP) 2011 Volterra, Italy September 1-2, 2011" e3917d6935586b90baae18d938295e5b089b5c62,Face localization and authentication using color and depth images,"Face Localization and Authentication Using Color and Depth Images Filareti Tsalakanidou, Sotiris Malassiotis, and Michael G. Strintzis, Fellow, IEEE" e3b92cc14f2c33bfdc07b794292a30384f8d0ad1,Local Segmentation for Pedestrian Tracking in Dense Crowds,"Local Segmentation for Pedestrian Tracking in Dense Crowds Clement Creusot Toshiba RDC, Kawasaki, Japan, http://clementcreusot.com/pedestrian" e3f2e337d4470545398cc6753a54c21debf9c37b,Potential Contrast – A New Image Quality Measure,"Potential Contrast – A New Image Quality Measure Arie Shaus, Shira Faigenbaum-Golovin, Barak Sober, Eli Turkel, Eli Piasetzky; Tel Aviv University; Tel Aviv, Israel" 32103c021e4d52f9915c3236669de5da973fb13f,Affective Image Content Analysis: A Comprehensive Survey,Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) 323cd51bc18c700fa88044dd24ae663a7eabaa68,Utilizing student activity patterns to predict performance,"Casey and Azcona International Journal of Educational Technology in Higher Education (2017) 14:4 DOI 10.1186/s41239-017-0044-3 R ES EAR CH A R T I C LE Utilizing student activity patterns to predict performance Kevin Casey1* and David Azcona2 Open Access * Correspondence: Maynooth University, Maynooth, Ireland Full list of author information is vailable at the end of the article" 327f3d65a380f70bc39fe99c7ad55d76a5f7fff4,A data-synthesis-driven method for detecting and extracting vague cognitive regions,"International Journal of Geographical Information Science ISSN: 1365-8816 (Print) 1362-3087 (Online) Journal homepage: http://www.tandfonline.com/loi/tgis20 A data-synthesis-driven method for detecting and extracting vague cognitive regions Song Gao, Krzysztof Janowicz, Daniel R. Montello, Yingjie Hu, Jiue-An Yang, Grant McKenzie, Yiting Ju, Li Gong, Benjamin Adams & Bo Yan To cite this article: Song Gao, Krzysztof Janowicz, Daniel R. Montello, Yingjie Hu, Jiue-An Yang, Grant McKenzie, Yiting Ju, Li Gong, Benjamin Adams & Bo Yan (2017): A data-synthesis- driven method for detecting and extracting vague cognitive regions, International Journal of Geographical Information Science, DOI: 10.1080/13658816.2016.1273357 To link to this article: http://dx.doi.org/10.1080/13658816.2016.1273357 Published online: 08 Jan 2017. Submit your article to this journal View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=tgis20 Download by: [UC Santa Barbara Library] Date: 09 January 2017, At: 09:44" 324cf94743359df3ada2f86ee8cd3bb6dccae695,FERA 2015-Second Facial Expression Recognition and Analysis Challenge,"FG 2015 FG 2015 Submission. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. FG 2015 FERA 2015 - Second Facial Expression Recognition and Analysis Challenge Anonymous FG 2015 submission – DO NOT DISTRIBUTE –" 32743e72cdb481b7a30a3d81a96569dcbea4e409,Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications,"Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications Baohua Sun, Lin Yang, Patrick Dong, Wenhan Zhang, Gyrfalcon Technology Inc. Jason Dong, Charles Young 900 McCarthy Blvd. Milpitas, CA 95035" 321bd4d5d80abb1bae675a48583f872af3919172,Entropy-weighted feature-fusion method for head-pose estimation,"Wang et al. EURASIP Journal on Image and Video Processing (2016) 2016:44 DOI 10.1186/s13640-016-0152-3 EURASIP Journal on Image nd Video Processing R EV I E W Entropy-weighted feature-fusion method for head-pose estimation Xiao-Meng Wang*, Kang Liu and Xu Qian Open Access" 326ac7776f000c43ff05fbbbef444a55984346e1,"Ear biometrics: a survey of detection, feature extraction and recognition methods","Ear Biometrics: A Survey of Detection, Feature Extraction and Recognition Methods Anika Pflug, Christoph Busch ∗ July 2, 2012 The possibility of identifying people by the shape of their outer ear was first discovered by the French criminologist Bertillon, and refined by the American police of‌f‌icer Iannarelli, who proposed a first ear recognition system based on only seven features. The detailed structure of the ear is not only unique, but also permanent, s the appearance of the ear does not change over the course of a human life. Additionally, the acquisition of ear images does not necessarily require person’s cooperation but is nevertheless considered to be non-intrusive by most people. Because of these qualities, the interest in ear recognition systems has grown significantly in recent years. In this survey, we categorize and summarize ap- proaches to ear detection and recognition in 2D and 3D images. Then, we provide an outlook over possible future research in the field of ear recogni- tion, in the context of smart surveillance and forensic image analysis, which we consider to be the most important application of ear recognition charac-" 320d6e79fa184dcf24c30232ab762d29f7e3d9c6,Face recognition using Hidden Markov Models,"Face recognition using Hidden Markov Models Johan Stephen Simeon Ballot Thesis presented at the University of Stellenbosch in partial fulfilment of the requirements for the degree of Master of Science in Electronic Engineering with Computer Science Department of Electrical & Electronic Engineering University of Stellenbosch Private Bag X1, 7602 Matieland, South Africa Study leaders: Prof. J.A. du Preez Prof. B.M. Herbst April 2005" 3233340bbb770187cc870f01755a658d3ae92396,A Classification approach towards Unsupervised Learning of Visual Representations,"A Classification approach towards Unsupervised Learning of Visual Representations Aditya Vora Johnson Controls Inc." 32bebe84ffbd4fd81f0e5bb30dbc90774aa3b14b,Segmentation Results Stimuli Final Saliency Map Ground Truth Constructed Graph CCA,"Noname manuscript No. (will be inserted by the editor) Hierarchical Cellular Automata for Visual Saliency Yao Qin* · Mengyang Feng* · Huchuan Lu · Garrison W. Cottrell Received: date / Accepted: date" 324d82129642f84838be71bd7401f38c80fb87d7,Adaptive Mixtures of Factor Analyzers,"Adaptive Mixtures of Factor Analyzers Heysem Kayaa,∗, Albert Ali Salaha Department of Computer Engineering Bo˘gazi¸ci University, 34342, Bebek, ˙Istanbul" 32d6ee09bd8f1a7c42708d6dd8a5fb85ac4e08bc,Non-Interfering Effects of Active Post-Encoding Tasks on Episodic Memory Consolidation in Humans,"ORIGINAL RESEARCH published: 29 March 2017 doi: 10.3389/fnbeh.2017.00054 Non-Interfering Effects of Active Post-Encoding Tasks on Episodic Memory Consolidation in Humans Samarth Varma 1*, Atsuko Takashima 1,2, Sander Krewinkel 1, Maaike van Kooten 1, Lily Fu 1, W. Pieter Medendorp 1, Roy P. C. Kessels 1 and Sander M. Daselaar 1 Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, Netherlands, 2Department of Neurobiology of Language, Max Planck Institute for Psycholinguistics, Nijmegen, Netherlands So far, studies that investigated interference effects of post-learning processes on episodic memory consolidation in humans have used tasks involving only complex and meaningful information. Such tasks require reallocation of general or encoding-specific resources away from consolidation-relevant activities. The possibility that interference an be elicited using a task that heavily taxes our limited brain resources, but has low semantic and hippocampal related long-term memory processing demands, has never been tested. We address this question by investigating whether consolidation ould persist in parallel with an active, encoding-irrelevant, minimally semantic task, regardless of its high resource demands for cognitive processing. We distinguish the impact of such a task on consolidation based on whether it engages resources that" 32bd968e6cf31e69ee5fca14d3eadeec7f4187c6,Monocular Pedestrian Detection: Survey and Experiments,"Monocular Pedestrian Detection: Survey and Experiments Markus Enzweiler, Student Member, IEEE, and Dariu M. Gavrila" 325b048ecd5b4d14dce32f92bff093cd744aa7f8,Multi-Image Graph Cut Clothing Segmentation for Recognizing People Anonymous CVPR submission Paper ID 2670,"#2670 CVPR 2008 Submission #2670. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. #2670 Multi-Image Graph Cut Clothing Segmentation for Recognizing People Anonymous CVPR submission Paper ID 2670" 32b9be86de4f82c5a43da2a1a0a892515da8910d,Robust False Positive Detection for Real-Time Multi-target Tracking,"Robust False Positive Detection for Real-Time Multi-Target Tracking Henrik Brauer, Christos Grecos, and Kai von Luck University of the West of Scotland University of Applied Sciences Hamburg" 32ef19e90e7834ec09ef19fcef7cd2aa6eff85a9,Modeling Natural Images Using Gated MRFs,"JOURNAL OF PAMI, VOL. ?, NO. ?, JANUARY 20?? Modeling Natural Images Using Gated MRFs Marc’Aurelio Ranzato, Volodymyr Mnih, Joshua M. Susskind, Geoffrey E. Hinton" 32f0c95cee39eba143452d6a0fe93283575257e6,Generative Adversarial Networks for Extreme Learned Image Compression,"GENERATIVE ADVERSARIAL NETWORKS FOR EXTREME LEARNED IMAGE COMPRESSION Eirikur Agustsson∗, Michael Tschannen∗, Fabian Mentzer∗, Radu Timofte & Luc Van Gool {aeirikur, mentzerf, radu.timofte, ETH Zurich" 322ff387087134ac776a4270cd55e7f3334edeb2,"Image Features Detection , Description and Matching","Image Features Detection, Description nd Matching M. Hassaballah, Aly Amin Abdelmgeid and Hammam A. Alshazly" 325c9f6f848407a22b86e3253cb7f29fac19e40c,Change Detection in Crowded Underwater Scenes - Via an Extended Gaussian Switch Model Combined with a Flux Tensor Pre-segmentation,"Change Detection in Crowded Underwater Scenes via an Extended Gaussian Switch Model combined with a Flux Tensor Pre-Segmentation Martin Radolko1,2, Fahimeh Farhadifard1,2 and Uwe von Lukas1,2 Institute for Computer Science, University Rostock, Rostock, Germany Fraunhofer Institute for Computer Fraphics Research IGD , Rostock, Germany {Martin.Radolko, Keywords: Change Detection, Background Subtraction, Video Segmentation, Video Segregation, Underwater Segmenta- tion, Flux Tensor" 3265c7799f9d14e29de37b1e37aec4330cd1d747,Class-Specific Binary Correlograms for Object Recognition,"Class-Specific Binary Correlograms for Object Recognition Jaume Amores1, Nicu Sebe2, Petia Radeva3 IMEDIA Research Group, INRIA, France Univ. of Amsterdam, The Netherlands Computer Vision Center, UAB, Spain" 325000c2ebe4fcfd08946aef91aee8bec22026a5,Multi-Label Learning With Fused Multimodal Bi-Relational Graph,"Multi-Label Learning With Fused Multimodal Bi-Relational Graph Jiejun Xu, Vignesh Jagadeesh, and B. S. Manjunath, Fellow, IEEE" 3274a13562029f36e2f0fad3270e3ecb9ca013bd,Real-time UAV Target Tracking System Based on Optical Flow and Particle Filter Integration,"Real-time UAV Target Tracking System Based on Optical Flow and Particle Filter Integration WESAM ASKAR Electrical Engineering Military Tech. College EGYPT OSAMA ELMOWAFY Computer Engineering New Cairo Academy ALIAA YOUSSIF Computer Engineering Helwan University GAMAL ELNASHAR Electrical Engineering Military Tech. College EGYPT EGYPT EGYPT" 32f7e1d7fa62b48bedc3fcfc9d18fccc4074d347,Hierarchical Sparse and Collaborative Low-Rank representation for emotion recognition,"HIERARCHICAL SPARSE AND COLLABORATIVE LOW-RANK REPRESENTATION FOR EMOTION RECOGNITION Xiang Xiang, Minh Dao, Gregory D. Hager, Trac D. Tran Johns Hopkins University, 3400 N. Charles Street, Baltimore, MD 21218, USA {xxiang, minh.dao, ghager1," 326df1b94624b7958cff0f7e3d16e612ea9d7e4d,Similarity rank correlation for face recognition under unenrolled pose,"Similarity Rank Correlation for Face Recognition Under Unenrolled Pose Marco K. M¨uller, Alexander Heinrichs, Andreas H.J. Tewes, Achim Sch¨afer, and Rolf P. W¨urtz Institut f¨ur Neuroinformatik, Ruhr-Universit¨at, D–44780 Bochum, Germany" 323fabb6cb4e74518fd4c7ad6ea5a1b2674e63d3,Object recognition based on radial basis function neural networks: Experiments with RGB-D camera embedded on mobile robots,"Object Recognition Based on Radial Basis Function Neural Networks: experiments with RGB-D camera embedded on mobile robots Saeed Gholami Shahbandi LISA - University of Angers Philippe Lucidarme LISA - University of Angers 62 av. Notre Dame du Lac, 49000 Angers, France 62 av. Notre Dame du Lac, 49000 Angers, France" 320ea4748b1f7e808eabedbedb75cce660122d26,"Detecting Avocados to Zucchinis: What Have We Done, and Where Are We Going?","Detecting avocados to zucchinis: what have we done, and where are we going? Olga Russakovsky1, Jia Deng1, Zhiheng Huang1, Alexander C. Berg2, Li Fei-Fei1 Stanford University1 , UNC Chapel Hill2" 32d8194269faf6ae505a8d7937a3423e4830187e,Big Five Personality Recognition from Multiple Text Genres,"Big Five Personality Recognition from Multiple Text Genres Vitor Garcia dos Santos, Ivandr´e Paraboni, and Barbara Barbosa Claudino Silva University of S˜ao Paulo, School of Arts, Sciences and Humanities, S˜ao Paulo, Brazil" 32728e1eb1da13686b69cc0bd7cce55a5c963cdd,Automatic Facial Emotion Recognition Method Based on Eye Region Changes,"Automatic Facial Emotion Recognition Method Based on Eye Region Changes Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran Mina Navraan Nasrollah Moghadam Charkari* Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran Muharram Mansoorizadeh Faculty of Electrical and Computer Engineering, Bu-Ali Sina University, Hamadan, Iran Received: 19/Apr/2015 Revised: 19/Mar/2016 Accepted: 19/Apr/2016" 32deaec54b9860bb4b81c8c9a64d11b0eea382b8,Large-Scale Image Segmentation with Convolutional Networks,"POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCESacceptée sur proposition du jury:Prof. J.-Ph. Thiran, président du juryProf. H. Bourlard, Dr R. Collobert, directeurs de thèseDr C. Schmid, rapporteuseProf. R. Fergus, rapporteurDr M. Salzmann, rapporteurLarge-Scale Image Segmentation with Convolutional NetworksTHÈSE NO 7571 (2017)ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNEPRÉSENTÉE LE 17 FÉVRIER 2017À LA FACULTÉ DES SCIENCES ET TECHNIQUES DE L'INGÉNIEURLABORATOIRE DE L'IDIAPPROGRAMME DOCTORAL EN GÉNIE ÉLECTRIQUE Suisse2017PARPedro Henrique OLIVEIRA PINHEIRO" 32cde90437ab5a70cf003ea36f66f2de0e24b3ab,The Cityscapes Dataset for Semantic Urban Scene Understanding,"The Cityscapes Dataset for Semantic Urban Scene Understanding Marius Cordts1,2 Markus Enzweiler1 Mohamed Omran3 Rodrigo Benenson3 Sebastian Ramos1,4 Timo Rehfeld1,2 Uwe Franke1 Stefan Roth2 Bernt Schiele3 Daimler AG R&D, 2TU Darmstadt, 3MPI Informatics, 4TU Dresden www.cityscapes-dataset.net train/val – fine annotation – 3475 images train – coarse annotation – 20 000 images test – fine annotation – 1525 images" 3295ec2e52cd83cec75fc7c7064a843756b4d1ee,An Efficient Pedestrian Detection Approach Using a Novel Split Function of Hough Forests,"Regular Paper Journal of Computing Science and Engineering, Vol. 8, No. 4, December 2014, pp. 207-214 An Efficient Pedestrian Detection Approach Using a Novel Split Function of Hough Forests Trung Dung Do, Thi Ly Vu, Van Huan Nguyen, Hakil Kim*, and Chongho Lee School of Information and Communication Engineering, Inha University, Incheon, Korea {dotrungdung, vuthily, {hikim," 32c3dcf95da2e54d1635f06f5714c5099cc6034e,A dataset for benchmarking vision-based localization at intersections,"A dataset for benchmarking vision-based localization at intersections supplemental material for “Vision-Based Localization at Intersections using Digital Maps” Augusto L. Ballardini, Daniele Cattaneo, and Domenico G. Sorrenti" 322c063e97cd26f75191ae908f09a41c534eba90,Improving Image Classification Using Semantic Attributes,"Noname manuscript No. (will be inserted by the editor) Improving Image Classification using Semantic Attributes Yu Su · Fr´ed´eric Jurie Received: date / Accepted: date" 323d6d93b059372bbe26a86bad1b9d94b076f50e,(A) Vision for 2050 - Context-Based Image Understanding for a Human-Robot Soccer Match,"Electronic Communications of the EASST Volume 62 (2013) Specification, Transformation, Navigation Special Issue dedicated to Bernd Krieg-Br¨uckner on the Occasion of his 60th Birthday (A) Vision for 2050 – Context-Based Image Understanding for a Human-Robot Soccer Match Udo Frese, Tim Laue, Oliver Birbach, and Thomas R¨ofer 9 pages Guest Editors: Till Mossakowski, Markus Roggenbach, Lutz Schr¨oder Managing Editors: Tiziana Margaria, Julia Padberg, Gabriele Taentzer ISSN 1863-2122" 32a6f6aa50ce2a631bf4de7432f830b29b6b05f2,Through the eyes of a child: preschoolers' identification of emotional expressions from the child affective facial expression (CAFE) set.,"Cognition and Emotion ISSN: 0269-9931 (Print) 1464-0600 (Online) Journal homepage: http://www.tandfonline.com/loi/pcem20 Through the eyes of a child: preschoolers’ identification of emotional expressions from the hild affective facial expression (CAFE) set Vanessa LoBue, Lewis Baker & Cat Thrasher To cite this article: Vanessa LoBue, Lewis Baker & Cat Thrasher (2017): Through the eyes of a hild: preschoolers’ identification of emotional expressions from the child affective facial expression (CAFE) set, Cognition and Emotion, DOI: 10.1080/02699931.2017.1365046 To link to this article: http://dx.doi.org/10.1080/02699931.2017.1365046 Published online: 10 Aug 2017. Submit your article to this journal View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pcem20 Download by: [173.56.101.121] Date: 10 August 2017, At: 05:46" 32925200665a1bbb4fc8131cd192cb34c2d7d9e3,An Active Appearance Model with a Derivative-Free Optimization,"MVA2009 IAPR Conference on Machine Vision Applications, May 20-22, 2009, Yokohama, JAPAN An Active Appearance Model with a Derivative-Free Optimization Jixia ZHANG‡, Franck DAVOINE†, Chunhong PAN‡ CNRS†, Institute of Automation of the Chinese Academy of Sciences‡ 95, Zhongguancun Dong Lu, PO Box 2728 − Beijing 100190 − PR China LIAMA Sino-French IT Lab." 321fbbe7da848b602f376219ed9aed6a7f4b7f57,Effective use of frequent itemset mining for image classification,"Effective Use of Frequent Itemset Mining for Image Classification Basura Fernando1, Elisa Fromont2, and Tinne Tuytelaars1 KU Leuven, ESAT-PSI, IBBT (Belgium) University of Saint-Etienne(France)" 32df63d395b5462a8a4a3c3574ae7916b0cd4d1d,Facial expression recognition using ensemble of classifiers,"978-1-4577-0539-7/11/$26.00 ©2011 IEEE ICASSP 2011" fbc0e33bed3bba7eff9bed2c31f33da793120929,Efficient Online Segmentation for Sparse 3 D Laser Scans,"PFG 0000 / 0, 0000 – 0001 Stuttgart, 00 0000 Article Efficient Online Segmentation for Sparse 3D Laser Scans IGOR BOGOSLAVSKYI & CYRILL STACHNISS, Bonn Keywords: Segmentation, 3D laser, online, range image, sparse data, point cloud Summary: The ability to extract individual objects in the scene is key for a large number of utonomous navigation systems such as mobile robots or autonomous cars. Such systems navigating in dynamic environments need to be aware of objects that may change or move. In most perception cues, a pre-segmentation of the current image or laser scan into individual objects is the first processing step before a further analysis is performed. In this paper, we present n effective method that first removes the ground from the scan and then segments the 3D data in range image representation into different objects. A key focus of our work is a fast execution with several hundred Hertz. Our implementation has small computational demands so that it can run online on most mobile systems. We explicitly avoid the computation of the 3D point cloud nd operate directly on a 2.5D range image, which enables a fast segmentation for each 3D scan. This approach can furthermore handle sparse 3D data well, which is important for scanners such s the new Velodyne VLP-16 scanner. We implemented our approach in C++ and ROS, thoroughly tested it using different 3D scanners, and will release the source code of our" fb3af250a2ff85145519fea9ece7187452d02a50,The WILDTRACK Multi-Camera Person Dataset,"The WILDTRACK Multi-Camera Person Dataset Tatjana Chavdarova1, Pierre Baqu´e2, St´ephane Bouquet2, Andrii Maksai2, Cijo Jose1, Louis Lettry3, Pascal Fua2, Luc Van Gool3 and Fran¸cois Fleuret1 Machine Learning group, Idiap Research Institute & ´Ecole Polytechnique F´ed´erale de Lausanne CVLab, ´Ecole Polytechnique F´ed´erale de Lausanne Computer Vision Lab, ETH Zurich" fbd781143a3f4c9d03c227cfbd1f528d658195ce,A Gender Recognition Experiment on the CASIA Gait Database Dealing with Its Imbalanced Nature.,"A GENDER RECOGNITION EXPERIMENT ON THE CASIA GAIT DATABASE DEALING WITH ITS IMBALANCED NATURE Ra´ul Mart´ın-F´elez, Ram´on A. Mollineda and J. Salvador S´anchez Institute of New Imaging Technologies (INIT) and Dept. Llenguatges i Sistemes Inform`atics Universitat Jaume I. Av. Sos Baynat s/n, 12071, Castell´o de la Plana, Spain {martinr, mollined, Keywords: Gender recognition, Gait analysis, Class imbalance problem, Human silhouette, Appearance-based method." fbbc2978758fe459f05d749a0fbd1ef3a3ba3c6c,The TUM VI Benchmark for Evaluating Visual-Inertial Odometry,"The TUM VI Benchmark for Evaluating Visual-Inertial Odometry David Schubert∗, Thore Goll∗, Nikolaus Demmel∗, Vladyslav Usenko∗, J¨org St¨uckler and Daniel Cremers" fbb304770d33f44006d134906481208ad087ce63,Visual Self-Localization with Tiny Images,"Visual Self-Localization with Tiny Images Marius Hofmeister, Sara Erhard and Andreas Zell University of T¨ubingen, Department of Computer Science, Sand 1, 72076 T¨ubingen" fb671ce90db5e3092d1f1bfa78c5bdcc06db5d21,Learning to Detect Objects with Minimal Supervision THÈSE,"Learning to Detect Objects with Minimal Supervision THÈSE NO 5310 (2012) PRÉSENTÉE LE 8 MARS 2012 À LA FACULTÉ INFORMATIQUE ET COMMUNICATIONS LABORATOIRE DE VISION PAR ORDINATEUR PROGRAMME DOCTORAL EN INFORMATIQUE, COMMUNICATIONS ET INFORMATION ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES Karim ALI cceptée sur proposition du jury: Prof. M. Pauly, président du jury Prof. P. Fua, Dr F. Fleuret, directeurs de thèse Dr D. Hasler, rapporteur Prof. M. Seeger, rapporteur Prof. A. Trouvé, rapporteur Suisse" fbd7d591e6eecb9a947e377d5b1a865a9f86a11f,Consensual and Privacy-Preserving Sharing of Multi-Subject and Interdependent Data,"Consensual and Privacy-Preserving Sharing of Multi-Subject and Interdependent Data Alexandra-Mihaela Olteanu EPFL, UNIL–HEC Lausanne K´evin Huguenin UNIL–HEC Lausanne Italo Dacosta Jean-Pierre Hubaux" fbbccf0454c84bea1fd5c5a1dcd9fd7bba301a44,Face detection using gradient vector flow,"Proceedings of the Second International Conference on Machine Learning and Cybernetics, Wan, 2-5 November 2003 FACE DETECTION USING GRADIENT VECTOR FLOW MAYANK VATSA, RICHA SINCH, P. GUPTA Department of Computer Science & Engineering Indian Institute of Technology Kanpur Kanpur INDIA, 208016 E-MAIL: (mayankv, richas, pg} cse.iitk.ac.in" fb710e9d897b7c1fd5275a0bcfa22711c5768990,A Graphical Model for Rapid Obstacle Image-Map Estimation from Unmanned Surface Vehicles,"A graphical model for rapid obstacle image-map estimation from unmanned surface vehicles Matej Kristan1,2, Janez Perˇs1, Vildana Suliˇc1, Stanislav Kovaˇciˇc1 Faculty of computer and information science University of Ljubljana, 2Faculty of electrical engineering University of Ljubljana" fb4545782d9df65d484009558e1824538030bbb1,"Learning Visual Patterns: Imposing Order on Objects, Trajectories and Networks", fbf196d83a41d57dfe577b3a54b1b7fa06666e3b,Extreme Learning Machine for Large-Scale Action Recognition,"Extreme Learning Machine for Large-Scale Action Recognition G¨ul Varol and Albert Ali Salah Department of Computer Engineering, Bo˘gazi¸ci University, Turkey" fb95fb1e0bf99347a69f76c9fd65e039024e73b7,Photograph Based Pair-matching Recognition of Human Faces,"World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:5, No:12, 2011 Photograph Base sed Pair-matching Recogn gnition of Human Faces Min Y n Yao, Kota Aoki, and Hiroshi Nagahashi (cid:1)" fb5a370a4d6364887ae334923335e8c48aed0f78,Biometrics at the Frontiers: Assessing the impact on Society,"T E C H N I C A L R E P O R T S E R I E S Biometrics at the Frontiers: Assessing the Impact on Society For the European Parliament Committee on Citizens' Freedoms and Rights, Justice and Home Affairs (LIBE) EUR 21585 EN Institute for Prospective Technological Studies" fbc93b13b8a6a5e4ed11310ce4da3be0b7541da8,Real-time Pedestrian Detection in a Truck's Blind Spot Camera,"Real-time pedestrian detection in a truck’s blind spot camera Kristof Van Beeck1,2 and Toon Goedem´e1,2 EAVISE, Campus De Nayer - KU Leuven, J. De Nayerlaan 5, 2860 Sint-Katelijne-Waver, Belgium ESAT-PSI, KU Leuven, Kasteel Arenbergpark 10, 3100 Heverlee, Belgium {kristof.vanbeeck, Keywords: Pedestrian detection, Tracking, Real-time, Computer vision, Active safety systems" fb76adeff0309ff4c8de4d0b413a8e3a637774d0,client2vec: Towards Systematic Baselines for Banking Applications,"lient2vec: Towards Systematic Baselines for Banking Applications Leonardo Baldassini BBVA Data & Analytics Jose Antonio Rodr´ıguez Serrano BBVA Data & Analytics" fb66546a16751810754430286fe4c636e4411ca4,Complementary feature sets for optimal face recognition,"Singh et al. EURASIP Journal on Image and Video Processing 2014, 2014:35 http://jivp.eurasipjournals.com/content/2014/1/35 R ES EAR CH Complementary feature sets for optimal face recognition Chandan Singh1, Neerja Mittal2* and Ekta Walia3 Open Access" fbd047862ea869973ecf8fc35ae090ca00ff06d8,Literature review of fingerprint quality assessment and its evaluation,"A Literature Review of Fingerprint Quality Assessment nd Its Evaluation Zhigang Yao, Jean-Marie Le Bars, Christophe Charrier, Christophe Rosenberger To cite this version: Zhigang Yao, Jean-Marie Le Bars, Christophe Charrier, Christophe Rosenberger. A Literature Review of Fingerprint Quality Assessment and Its Evaluation. IET journal on Biometrics, 2016. HAL Id: hal-01269240 https://hal.archives-ouvertes.fr/hal-01269240 Submitted on 5 Feb 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents" fb82681ac5d3487bd8e52dbb3d1fa220eeac855e,"Summary of Research on Informant Accuracy in Network Data, 11 and on the Reverse Small World Problem","CONNECTIONS VOLUME IV, NUMBER 2 Summer 1981 CONTENTS NETWORK NOTEBOOK MEETING CALENDAR RESEARCH REPORTS Social Networks : A Beginner's Bookshelf Linton C . Freeman (California-Irvine) Summary of Research on Informant Accuracy in Network Data, nd on the Reverse Small World Problem H . Russell Bernard (Florida), Peter D . Killworth (Cambridge) & Lee Sailer (Pittsburgh) Russell's Paradox (Part II) Linton C . Freeman (California-Irvine) Goedel's Spoof : A Reply to Freeman Peter D . Killworth (Cambridge) & H . Russell Bernard (Florida) The Norwegian Connection :" fba464cb8e3eff455fe80e8fb6d3547768efba2f,Survey Paper on Emotion Recognition,"International Journal of Engineering and Applied Sciences (IJEAS) ISSN: 2394-3661, Volume-3, Issue-2, February 2016 Survey Paper on Emotion Recognition Prachi Shukla, Sandeep Patil" fb1732a1476798c42a0123aaf127036bf8daef09,LightDenseYOLO: A Fast and Accurate Marker Tracker for Autonomous UAV Landing by Visible Light Camera Sensor on Drone,"Article LightDenseYOLO: A Fast and Accurate Marker Tracker for Autonomous UAV Landing by Visible Light Camera Sensor on Drone Phong Ha Nguyen, Muhammad Arsalan, Ja Hyung Koo, Rizwan Ali Naqvi, Noi Quang Truong nd Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 00-715, Korea; (P.H.N.); (M.A.); (J.H.K.); (R.A.N.); (N.Q.T.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 3 May 2018; Accepted: 22 May 2018; Published: 24 May 2018" fbd169c0f700fcca26a74c79bb46c5ca2d37648a,FACIAL FEATURE BASED HEAD TRACKING AND POSE ESTIMATION,"FACIAL FEATURE BASED HEAD TRACKING AND POSE ESTIMATION Jari Hannuksela" fb2379346def4846ac24bc41349e7cac7c1e7243,ClusterNet: 3D Instance Segmentation in RGB-D Images,"ClusterNet: 3D Instance Segmentation in RGB-D Images Lin Shao, Ye Tian, and Jeannette Bohg" fb748a6953e72ad6d508109f8d809c25570ff07b,"The ""Eye Avoidance"" Hypothesis of Autism Face Processing.","NIH Public Access Author Manuscript J Autism Dev Disord. Author manuscript; available in PMC 2015 April 23. The “eye avoidance” hypothesis of autism face processing James W. Tanaka1 and Andrew Sung2 Department of Psychology, University of Victoria, British Columbia Department of Special Education and Leadership Studies, University of Victoria, British Columbia" fbf20dc3367864462d7630aad81c436e50d1cd60,Iterative Bayesian Learning for Crowdsourced Regression,"Iterative Bayesian Learning for Crowdsourced Regression Jungseul Ok∗, Sewoong Oh∗, Yunhun Jang †, Jinwoo Shin†, and Yung Yi† October 9, 2018" fbd17af24e86fe487e28f99ba3e402dd6cfcd16a,Research Statement: towards Detailed Recognition of Visual Categories,"Research Statement: Towards Detailed Recognition of Visual Categories Subhransu Maji As humans, we have a remarkable ability to perceive the world around us in minute detail purely from the light that is reflected off it – we can estimate material and metric properties of objects, localize people in images, describe what they are doing, and even identify them. Automatic methods for such detailed recognition of images are essential for most human-centric applications and large scale analysis of the content of media collections for market research, advertisement, and social studies. For example, in order to shop for shoes in an on-line catalogue, a system should be able to understand the style of a shoe, the length of its heels, or the shininess of its material. In order to support visual demographics nalysis for advertisement, a system should be able to not only identify the people in a scene, but also to understand what kind (style and brand) of clothes they are wearing, whether they are wearing any ccessories, and so on. Despite several successes, such detailed recognition is beyond the current computer vision systems. This is a challenging task, and to make progress we have to make advances on several fronts. We need etter representations of visual categories that can enable fine-grained reasoning about their properties, s well as machine learning methods that can leverage ‘big-data’ to learn such representations. In order to enable benchmarks for evaluating recognition tasks and to guide learning and inference in models that solve challenging problems, we need to develop better ways of human-computer interaction. My research touches upon several such themes in the intersection of computer vision, machine learning, and human-computer interaction including:" fb17e9cab49665863f360d5f9e61e6048a7e1b28,Reconstruction-Based Pairwise Depth Dataset for Depth Image Enhancement Using CNN,"Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN Junho Jeon and Seungyong Lee POSTECH {zwitterion27," fbd287db41bff55956b9faf4a226a39efe96e6da,Radboud University Object Localization and Path Prediction Using Radar and Other Sources Towards Autonomous Shipping,"Master Thesis Computer Science Radboud University Prediction Using Radar and Other Sources Towards Autonomous Object Localization and Path Shipping Author: Koen Vijverberg, BSc Supervisor: Prof. Dr. Elena Marchiori External supervisor: Fons de Leeuw, BSc Second supervisor: Prof. Dr. Tom Heskes August 23, 2018" fb9ad920809669c1b1455cc26dbd900d8e719e61,3 D Gaze Estimation from Remote RGB-D Sensors THÈSE,"D Gaze Estimation from Remote RGB-D Sensors THÈSE NO 6680 (2015) PRÉSENTÉE LE 9 OCTOBRE 2015 À LA FACULTÉ DES SCIENCES ET TECHNIQUES DE L'INGÉNIEUR LABORATOIRE DE L'IDIAP PROGRAMME DOCTORAL EN GÉNIE ÉLECTRIQUE ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES Kenneth Alberto FUNES MORA cceptée sur proposition du jury: Prof. K. Aminian, président du jury Dr J.-M. Odobez, directeur de thèse Prof. L.-Ph. Morency, rapporteur Prof. D. Witzner Hansen, rapporteur Dr R. Boulic, rapporteur Suisse" fbb6e707c8a5f189d8ad416597e23671b884448b,Altered gaze following during live interaction in infants at risk for autism: an eye tracking study,"Thorup et al. Molecular Autism (2016) 7:12 DOI 10.1186/s13229-016-0069-9 R ES EAR CH Altered gaze following during live interaction in infants at risk for autism: n eye tracking study Emilia Thorup1*, Pär Nyström1, Gustaf Gredebäck1, Sven Bölte3,2, Terje Falck-Ytter3,1 and The EASE Team Open Access" fbaceba60619d9f76f7acf6e639669cd6150049e,Automatic Semantic Content Removal by Learning to Neglect.,"QIN, WEI, MANDUCHI: AUTOMATIC SEMANTIC CONTENT REMOVAL Automatic Semantic Content Removal y Learning to Neglect University of California, Santa Cruz Santa Cruz, CA, USA Siyang Qin Jiahui Wei Roberto Manduchi" fb4c3b2f893baa1fbf8d16da2e09aa9868c61a7a,Decoupled Weight Decay Regularization,"Under review as a conference paper at ICLR 2019 DECOUPLED WEIGHT DECAY REGULARIZATION Anonymous authors Paper under double-blind review" fb04a8cb4b573d6b565a5b0c369d775e6bfb04f1,LOOKING AT PEOPLE USING PARTIAL LEAST SQUARES by William Robson Schwartz, fbb9cdd699baf86e9d616b259ada02449c2322ca,Active Testing: An Efficient and Robust Framework for Estimating Accuracy,"Active Testing: An Efficient and Robust Framework for Estimating Accuracy. Phuc Nguyen 1 Deva Ramanan 2 Charless Fowlkes 1" fb2ac6befd22fde3e6cff180d3431f02c81bc32a,Genetic optimisation of illumination compensation methods in cascade for face recognition,"Genetic optimisation of illumination ompensation methods in cascade for face recognition C.A. Perez, L.E. Castillo, L.A. Cament, P.A. Este´vez and C.M. Held Face detection and recognition depend strongly on illumination con- ditions. In this reported work, genetic algorithms are used to optimise parameters of the modified local normalisation and self-quotient image methods in cascade for illumination compensation to improve face rec- ognition. The main novelty of the proposed method is that it applies to non-homogeneous as well as homogeneous illumination conditions. The results are compared to those of the best illumination compen- sation methods published in the literature, obtaining 100% recognition on faces with non-homogeneous illumination and significantly better results than other methods with homogeneous illumination. Introduction: Face detection and face recognition are important several applications such as security, human–machine interfaces, auto- matic driver monitoring, biometric identification, video search, etc. [1–3]. Facial images are dramatically changed by lighting variations and there- fore may cause performance degradation both in face detection and in rec-" fbb4f4959756798aabba8034cb3167756b191811,Supervised Infinite Feature Selection,"Supervised Infinite Feature Selection Sadegh Eskandari A∗1 and Emre Akbas B†2 Department of Computer Science, University of Guilan, Rasht, Department of Computer Engineering, Middle East Technical Unviersity, Ankara 06800, Turkey August 22, 2017" 9f7c1b794805be34bc2091e02c382c5461e0bcb4,On-board real-time tracking of pedestrians on a UAV,"On-board real-time tracking of pedestrians on a UAV Floris De Smedt, Dries Hulens, and Toon Goedem´e ESAT-PSI-VISICS, KU Leuven, Belgium" 9f483933bcc872771707dcf0acb1382411ffee94,Which Facial Expressions Can Reveal Your Gender? A Study With 3D Faces,"IN SUBMISSION TO IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY Which Facial Expressions Can Reveal Your Gender? A Study With 3D Faces Baiqiang XIA" 9fa1be81d31fba07a1bde0275b9d35c528f4d0b8,Identifying Persons by Pictorial and Contextual Cues,"Identifying Persons by Pictorial and Contextual Cues Nicholas Leonard Pi¨el Thesis submitted for the degree of Master of Science Supervisor: Prof. dr. Theo Gevers April 2009" 9f22e0749405dfc3e3211474b933aa7514722e4b,Theory of mind - not emotion recognition - mediates the relationship between executive functions and social functioning in patients with schizophrenia.,"© Medicinska naklada - Zagreb, Croatia Original paper THEORY OF MIND - NOT EMOTION RECOGNITION - MEDIATES THE RELATIONSHIP BETWEEN EXECUTIVE FUNCTIONS AND SOCIAL FUNCTIONING IN PATIENTS WITH SCHIZOPHRENIA Michal Hajdúk1,2, Dana Kraj(cid:254)ovi(cid:254)ová2, Miroslava Zimányiová2, Viera Ko(cid:284)ínková2, Anton Heretik1 & Ján Pe(cid:254)e(cid:278)ák2 Department of Psychology, Faculty of Arts, Comenius University, Bratislava, Slovak Republic Clinic of Psychiatry, Faculty of Medicine, Comenius University, Bratislava, Slovak Republic received: 9.8.2017; revised: 15.3.2018; ccepted: 17.7.2018 SUMMARY Background: Dysfunction of social-cognitive abilities is one of the hallmark features of schizophrenia and is associated with neurocognition and social functioning. The Green and Nuechterlein model proposed that social cognition mediates the relationship etween neurocognition and functional outcome. We tested this hypothesis in schizophrenia patients in the everyday clinical setting. Subjects and methods: Social cognition, executive function and social functioning were assessed in a group of 43 patients with schizophrenia or schizoaffective disorder using a range of measures. Results: Theory of mind was associated with executive functions and social functioning. Results of our mediation analysis" 9fede7e3fac47a4206a643c4647834e5680f2a8f,Results from a Real-time Stereo-based Pedestrian Detection System on a Moving Vehicle,"Results from a Real-time Stereo-based Pedestrian Detection System on Moving Vehicle Max Bajracharya, Baback Moghaddam, Andrew Howard, Shane Brennan, Larry H. Matthies" 9fc37eccb3d12329f208cb7d3a509024e182a100,Mel-cepstral feature extraction methods for image representation,Downloaded From: https://www.spiedigitallibrary.org/journals/Optical-Engineering on 9/28/2017 Terms of Use: https://spiedigitallibrary.spie.org/ss/TermsOfUse.aspx 9f094341bea610a10346f072bf865cb550a1f1c1,Recognition and volume estimation of food intake using a mobile device,"Recognition and Volume Estimation of Food Intake using a Mobile Device Manika Puri Zhiwei Zhu Qian Yu Ajay Divakaran Harpreet Sawhney Sarnoff Corporation 01 Washington Rd, Princeton, NJ, 08540 {mpuri, zzhu, qyu, adivakaran," 9f91fd3e9621b88769ecc330f362a591876f948f,Bicycle Detection Based On Multi-feature and Multi-frame Fusion in low-resolution traffic videos,"Bicycle Detection Based On Multi-feature and Multi-frame Fusion in low-resolution traffic videos Yicheng Zhang, Student Member, IEEE, and Qiang Ling, Senior Member, IEEE Some other methods like using MSC-HOG method for detection [12] or detecting tires of bicycles in videos [13] lso can get good results, but they are either time consuming or high quality videos required. Some new methods, such the method based on HOG features with ROI in [14], try to use more advanced hardware device like GPU to finish the great mount of computation. In summary, there are three major defects in the available icycle detection methods based on image processing. First, they require fine features for detection, which are hard to extract, particularly for traffic videos with low-resolution. Second, the processing time under these methods is usually long and may not meet the requirement of the real-time detection. Last, they make the bicycle detection decision by the information in a single frame, which may lead to misjudgment, especially in the case of strong noise or light changing." 9f545b9006970f7626b7b121c5c3c66204f1ba40,Improving Pairwise Ranking for Multi-label Image Classification,"Image courtesy of ReflectedSerendipityon Flickr.catflowervaseOutputInputPredictionPairwise Ranking(cat, 0.99)(flower, 0.82)(vase, 0.68) (window, 0.52)(ladder, 0.21)(horse, 0.02)(person, 0.01)Ranked List…DecisionPer-classThresholdEstimationFigure1:Ranking-basedmulti-labelclassificationemploysatwo-stepprocess:labelpredictionthatproducesarankedlistoflabelconfidencescores,andlabeldecisionthatdeter-mineswhichlabelstoincludeintheoutput.Weproposeanewpairwiserankinglossfunctionandaper-classthresh-oldestimationmethodinaunifiedframework,improvingexistingranking-basedapproachesinaprincipledmanner.labeldependency[1,25],labelsparsity[10,12,27],andlabelnoise[33,39].Motivatedbythesuccessofdeepcon-volutionalneuralnetworks(CNNs)[13,23],otherrecentapproachescombinerepresentationlearningandmulti-labellearningintoanend-to-endtrainablesystem[29].Recently,Westonetal.[32]proposedanideatoapplypairwiserankingtotheimageclassificationproblem.Theirmainideaisthat,whilewhatwecarethemostaboutiscorrectlyidentifyingpositivelabels,itisequallyimportantfortheclassifiertomake“sensible”mistakes.Specifically,evenwhenaclassifierfailstoidentifypositivelabels,itshouldatleastassignhigherrankstothepositivelabelsthantomostofthenegativelabels.Extendingthisidea,Gongetal.[9]appliedthepairwiserankingapproachtotrainaCNNandreportedthestate-of-the-artresultontheNUS-WIDEmulti-labelimageannotationtask[7].WhilethepairwiserankingapproachinWestonetal.[32]andGongetal.[9]providesflexibilitytotrainavarietyoflearningmachines,withgoodempiricalperformanceonreal-worldproblems,wearguethatithastwoimportantdrawbackswhenappliedtomulti-labelclassification.First,asweshowinSection3,thehingelossfunctionusedinWestonetal.[32]andGongetal.[9]isnon-smoothand1" 9f7aaa10067f8e10f87169be1a3d0c153d979157,Extended Bag-Of-Words Formalism For Image Classification,"EXTENDED BAG-OF-WORDS FORMALISM FOR IMAGE CLASSIFICATION Sandra Avila To cite this version: Sandra Avila. EXTENDED BAG-OF-WORDS FORMALISM FOR IMAGE CLASSIFICATION. Computer Vision and Pattern Recognition [cs.CV]. Université Pierre et Marie Curie - Paris VI, 2013. English. HAL Id: tel-00958547 https://tel.archives-ouvertes.fr/tel-00958547 Submitted on 12 Mar 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 9fb1bd7d98a2fa79e1b9cb21b865ec7af0c1283f,Not All Distraction Is Bad: Working Memory Vulnerability to Implicit Socioemotional Distraction Correlates with Negative Symptoms and Functional Impairment in Psychosis,"Hindawi Publishing Corporation Schizophrenia Research and Treatment Volume 2014, Article ID 320948, 6 pages http://dx.doi.org/10.1155/2014/320948 Clinical Study Not All Distraction Is Bad: Working Memory Vulnerability to Implicit Socioemotional Distraction Correlates with Negative Symptoms and Functional Impairment in Psychosis Quintino R. Mano,1,2,3 Gregory G. Brown,1,2,3 Heline Mirzakhanian,1,2,3 Khalima Bolden,1,2,3 Kristen S. Cadenhead,1,2,3 and Gregory A. Light1,2,3 San Diego Veterans Affairs Healthcare System, San Diego, CA 92161, USA VISN-22 Mental Illness, Research, Education and Clinical Center (MIRECC), VA San Diego Healthcare System, San Diego, CA 92161, USA Department of Psychiatry, University of California, San Diego, School of Medicine, San Diego, CA, USA Correspondence should be addressed to Gregory G. Brown; Received 31 July 2013; Revised 26 November 2013; Accepted 15 December 2013; Published 27 February 2014 Academic Editor: Steven J. Siegel Copyright © 2014 Quintino R. Mano et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly ited." 9f986e3f5b4a4fad6bc579e3b752809db819576e,Generalized Exponential Bidirectional Fuzzy Associative Memory with Fuzzy Cardinality-Based Similarity Measures Applied to Face Recognition,"Tendˆencias em Matem´atica Aplicada e Computacional, 19, N. 2 (2018), 221-233 © 2018 Sociedade Brasileira de Matem´atica Aplicada e Computacional www.scielo.br/tema doi: 10.5540/tema.2018.019.02.0221 Generalized Exponential Bidirectional Fuzzy Associative Memory with Fuzzy Cardinality-Based Similarity Measures Applied to Face Recognition A.C. SOUZA* and M.E. VALLE Received on April 12, 2017 / Accepted on November 27, 2017" 9f889c81bdb1d791e22c5f455baf32829b5b788b,The GRODE metrics: Exploring the performance of group detection approaches,"Exploring the Performance of Group Detection Approaches The GRODE Metrics: Francesco Setti ISTC - CNR via alla Cascata 56/C, I-38121 Trento" 9fed3f4967bcdaebd1c321fee18fed865020a641,Objektsensitive Verfolgung und Klassifikation von Fußgängern mit verteilten Multi-Sensor-Trägern,"Forschungsberichte aus der Industriellen Informationstechnik 11 Johannes Pallauf Objektsensitive Verfolgung und Klassifi kation von Fußgängern mit verteilten Multi-Sensor-Trägern" 9f96b12427e65eb00ca6cacd9839f21892ee55d9,Feature Learning for Scene Flow Estimation from LIDAR,"Feature Learning for Scene Flow Estimation from LIDAR Arash K. Ushani Computer Science and Engineering University of Michigan Ann Arbor United States Ryan M. Eustice Naval Architecture and Marine Engineering University of Michigan Ann Arbor United States" 9f1319162974cb4d6125e8c6c52878ebc48eb8a7,Loss factors for learning Boosting ensembles from imbalanced data,"Loss Factors for Learning Boosting Ensembles from Imbalanced Data Roghayeh Soleymani∗, Eric Granger∗, Giorgio Fumera† Laboratoire d’imagerie, de vision et d’intelligence artificielle, École de technologie supérieure, Université du Québec, Montreal, Canada, Dept. of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy, Email: Email:" 9fcb23adc3e0b2e0e81df0ed30abbdef0c3bb16d,Motion Guided LIDAR-camera Autocalibration and Accelerated Depth Super Resolution,"Motion Guided LIDAR-camera Autocalibration and Accelerated Depth Super Resolution Juan Castorena, Gint Puskorius and Gaurav Pandey ∗" 9fb1d7cbf1baf5f347d159410d22912fcee1fdb1,Face Detection using Ferns,"FACE DETECTION USING FERNS Venkatesh Bala Subburaman Sébastien Marcel Idiap-Com-01-2011 DECEMBER 2011 Centre du Parc, Rue Marconi 19, P.O. Box 592, CH - 1920 Martigny T +41 27 721 77 11 F +41 27 721 77 12 www.idiap.ch" 9fbe2611b1e2a49199fdee96c2083da625ba57df,Leveraging Multi-Modal Sensing for Mobile Health: A Case Review in Chronic Pain,"J-STSP-PCSPHT-00370-2015.R1 Leveraging Multi-Modal Sensing for Mobile Health: a Case Review in Chronic Pain Min S. H. Aung, Faisal Alquaddoomi, Andy Hsieh, Mashfiqui Rabbi, Longqi Yang, J.P. Pollak, Tanzeem Choudhury, and Deborah Estrin (cid:3)" 9f2328931be1cf81a9ea14b35f3373b6122f0714,Motion-Based Object Segmentation Based on Dense RGB-D Scene Flow,"Motion-based Object Segmentation based on Dense RGB-D Scene Flow Lin Shao, Parth Shah∗, Vikranth Dwaracherla∗, and Jeannette Bohg" 9ff45d69168eedc6538dc684d94460ab4522480b,Efficiently comparing face images using a modified Hausdorff distance,"Efficiently comparing face images using a modified Hausdorff distance Y. Gao" 9fb3f13fa1085dbf0c89158640979dad70047121,Comparison between Speech Parameters for Forensic Voice Comparison Using Mobile Phone Speech,"Comparison between Speech Parameters for Forensic Voice Comparison Using Esam A. S. Alzqhoul 1, 2, Balamurali B. T. Nair 1, 2, Bernard J. Guillemin 1, 2 Mobile Phone Speech Forensic and Biometrics Research Group (FaB), The University of Auckland, New Zealand Department of Electrical and Computer Engineering, The University of Auckland, New Zealand" 4f051022de100241e5a4ba8a7514db9167eabf6e,Face Parsing via a Fully-Convolutional Continuous CRF Neural Network,"Face Parsing via a Fully-Convolutional Continuous CRF Neural Network Lei Zhou, Zhi Liu, Senior Member, IEEE, Xiangjian He, Senior Member, IEEE" 4fec8a97d6d87713c5c00f369fc1373fba4377e3,Training Sources 3 D Normalized Pose Space 2 D Normalized Pose Space KD-Tree Input Image 2 D Pose Estimation 3 D Pose Reconstruction Retrieved 3 D Nearest Neighbours Motion Capture Dataset Annotated 2,"SUBMITTED TO COMPUTER VISION AND IMAGE UNDERSTANDING. A Dual-Source Approach for 3D Human Pose Estimation from a Single Image Umar Iqbal*, Andreas Doering*, Hashim Yasin, Björn Krüger, Andreas Weber, and Juergen Gall" 4fcc8e5d78c166b40e5b6ee439edc9092811c159,Recent advances in biometric person authentication,"RECENT ADVANCES IN BIOMETRIC PERSON AUTHENTICATION J.-L. Dugelay1 J.-C. Junqua2 C. Kotropoulos3(cid:39) R. Kuhn2 F. Perronnin1 I. Pitas3 Institut EURECOM, Multimedia Communications Dept., 2229, Route des Cretes-B.P. 193, F-06904 Sophia Antipolis Cedex, France Panasonic Speech Technology Lab, Suite #202, 3888 State Street, Santa Barbara, CA 93105, U.S.A. {dugelay, Dept. of Informatics, Aristotle Univ. of Thessaloniki, Box 451, GR-540 06 Thessaloniki, Greece {jcj, {costas," 4f591e243a8f38ee3152300bbf42899ac5aae0a5,Understanding Higher-Order Shape via 3D Shape Attributes,"SUBMITTED TO TPAMI Understanding Higher-Order Shape via 3D Shape Attributes David F. Fouhey, Abhinav Gupta, Andrew Zisserman" 4fc609df4e17b5854e3b7f4371e5f4192608eda5,3D Face Recognition Benchmarks on the Bosphorus Database with Focus on Facial Expressions,"D Face Recognition Benchmarks on the Bosphorus Database with Focus on Facial Expressions Nes¸e Aly¨uz1, Berk G¨okberk2, Hamdi Dibeklio˘glu1, Arman Savran3, Albert Ali Salah4, Lale Akarun1, B¨ulent Sankur3" 4f77c682f133d5010762556ebf512533524da071,Deep Learning of Appearance Models for Online Object Tracking,"Deep Learning of Appearance Models for Online Object Tracking Mengyao Zhai, Mehrsan Javan Roshtkhari, Greg Mori" 4fc044f55a3875108dc592198d8999ea51f08d77,Cloudlets: at the leading edge of mobile-cloud convergence,"014 6th International Conference on Mobile Computing, Applications nd Services (MobiCASE) Cloudlets: t the Leading Edge of Mobile-Cloud Convergence (Invited Paper) Mahadev Satyanarayanant , Zhuo Chent, Kiryong Hat, Wenlu Hut, Wolfgang Richtert, Padmanabhan Pillai+ tCamegie Mellon University nd +Intel Labs" 4f46dba09e075b2e7dfae1ba2a71e8e21b46e88d,Genetic CNN,"Genetic CNN Center for Imaging Science, The Johns Hopkins University, Baltimore, MD, USA Lingxi Xie, Alan Yuille" 4ff1ac4e66bc545275c83bc2ef1f3fb8bc207aec,An MPCA / LDA Based Dimensionality Reduction Algorithm for Face Recognition,"Charles Darwin University An MPCA/LDA Based Dimensionality Reduction Algorithm for Face Recognition Huang, Jun; Su, Kehua; El-Den, Jamal; Hu, Tao; Li, Junlong Published in: Mathematical Problems in Engineering 0.1155/2014/393265 Published: 01/01/2014 Document Version Publisher's PDF, also known as Version of record Link to publication Citation for published version (APA): Huang, J., Su, K., El-Den, J., Hu, T., & Li, J. (2014). An MPCA/LDA Based Dimensionality Reduction Algorithm for Face Recognition. Mathematical Problems in Engineering, 2014, 1-12. DOI: 10.1155/2014/393265 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal Take down policy" 4f7e4b1b74955b54c434bdf76c47fb1e96db74e0,Naive Bayes Image Classification: Beyond Nearest Neighbors,"Naive Bayes Image Classification: Beyond Nearest Neighbors Radu Timofte1, Tinne Tuytelaars1, and Luc Van Gool1,2 ESAT-VISICS /IBBT, Catholic University of Leuven, Belgium D-ITET, ETH Zurich, Switzerland" 4fb11a58d5a3ffc0bb6d4ade334a366b4a431b02,The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings, 4f4f646b65921850b7812a376fc2ac5ff806b1c8,Joint Stem Detection and Crop-Weed Classification for Plant-Specific Treatment in Precision Farming,"Joint Stem Detection and Crop-Weed Classification for Plant-specific Treatment in Precision Farming Philipp Lottes Jens Behley Nived Chebrolu Andres Milioto Cyrill Stachniss" 4f41f7a2f1f5eb5f26d47aeb168dbeb0f9ed453f,A Graph Transduction Game for Multi-target Tracking,"A Graph Transduction Game for Multi-target Tracking Tewodros Mulugeta Dagnew∗, Dalia Coppi†, Marcello Pelillo∗, Rita Cucchiara† DAIS - Ca´ Foscari University Venezia, Italy Email: DIEF - University of Modena and Reggio Emilia Email: Modena, Italy" 4fc936102e2b5247473ea2dd94c514e320375abb,Guess Where? Actor-Supervision for Spatiotemporal Action Localization,"Guess Where? Actor-Supervision for Spatiotemporal Action Localization Victor Escorcia1∗ Cuong D. Dao1 Mihir Jain3 KAUST1, University of Amsterdam2, Qualcomm Technologies, Inc.3 Bernard Ghanem1 Cees Snoek2∗" 4fdeb5d59b218ecba0f72dc3c42f38a086417c0f,InformatIon theoretIc combInatIon of classIfIers wIth applIcatIon to face DetectIon,"InformatIon theoretIc combInatIon of classIfIers wIth applIcatIon to face DetectIon THÈSE NO 3951 (2007) PRÉSENTÉE LE 23 NOvEMBRE 2007 À LA FACULTÉ DES SCIENCES ET TECHNIQUES DE L'INGÉNIEUR LABORATOIRE DE TRAITEMENT DES SIGNAUX 5 PROGRAMME DOCTORAL EN INFORMATIQUE, COMMUNICATIONS ET INFORMATION ÉCOLE POLyTECHNIQUE FÉDÉRALE DE LAUSANNE POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES Julien MEyNET DEA signal, image, parole, télécoms, Institut national polytechnique de Grenoble, France et de nationalité française cceptée sur proposition du jury: Prof. H. Bourlard, président du jury Prof. J.-Ph. Thiran, directeur de thèse Prof. A. Billard, rapporteur Prof. H. Bunke, rapporteur Prof. J. Kittler, rapporteur Suisse" 4fa6a688f350831503d158f8f618c58d1e06bc5d,A Semi-supervised Framework for Image Captioning,"Bootstrap, Review, Decode: Using Out-of-Domain Textual Data to Improve Image Captioning Wenhu Chen RWTH Aachen Aurelien Lucchi ETH Zurich Thomas Hofmann ETH Zurich" 4f5e5fea12c44a5be7107748320e6d66192b7acb,Automatic approach-avoidance tendencies as a candidate intermediate phenotype for depression: Associations with childhood trauma and the 5-HTTLPR transporter polymorphism,"RESEARCH ARTICLE Automatic approach-avoidance tendencies as candidate intermediate phenotype for depression: Associations with childhood trauma and the 5-HTTLPR transporter polymorphism Pascal Fleurkens1*, Agnes van Minnen1,2, Eni S. Becker1, Iris van Oostrom3, Anne Speckens3, Mike Rinck1, Janna N. Vrijsen3,4 Behavioural Science Institute, Radboud University Nijmegen, Nijmegen, The Netherlands, Psychotrauma Expertise Centrum (PSYTREC), Bilthoven, The Netherlands, 3 Department of Psychiatry, Radboud University Medical Centre, Nijmegen, The Netherlands, 4 Pro Persona: Institution for Integrated Mental Health Care, Nijmegen, The Netherlands" 4f77a37753c03886ca9c9349723ec3bbfe4ee967,"Localizing Facial Keypoints with Global Descriptor Search, Neighbour Alignment and Locally Linear Models","Localizing Facial Keypoints with Global Descriptor Search, Neighbour Alignment and Locally Linear Models Md. Kamrul Hasan1, Christopher Pal1 and Sharon Moalem2 ´Ecole Polytechnique de Montr´eal, Universit´e de Montr´eal University of Toronto and Recognyz Systems Technologies lso focused on emotion recognition in the wild [9]." 4f4f920eb43399d8d05b42808e45b56bdd36a929,A Novel Method for 3 D Image Segmentation with Fusion of Two Images using Color K-means Algorithm,"International Journal of Computer Applications (0975 – 8887) Volume 123 – No.4, August 2015 A Novel Method for 3D Image Segmentation with Fusion of Two Images using Color K-means Algorithm Neelam Kushwah Dept. of CSE ITM Universe Gwalior Priusha Narwariya Dept. of CSE ITM Universe Gwalior" 4f0aedbd0b5cb5939449da41579c93b98048fcdc,Robust classification using structured sparse representation,"Robust Classification using Structured Sparse Representation Center for Imaging Science, Johns Hopkins University, Baltimore MD 21218, USA Ehsan Elhamifar Ren´e Vidal" 4f10b81f822091ce2142e33f0578940da1e25ad3,"Indoor Mobile Robotics at Grima, PUC","Noname manuscript No. (will be inserted by the editor) Indoor Mobile Robotics at Grima, PUC L. Caro · J. Correa · P. Espinace · D. Maturana · R. Mitnik · S. Montabone · S. Pszcz´o(cid:32)lkowski · D. Langdon · A. Araneda · D. Mery · M. Torres · A. Soto Received: date / Accepted: date" 4f1765b1c352093718ccc59f420ead44a4bb267b,Reduced memory region based deep Convolutional Neural Network detection,"Reduced Memory Region Based Deep Convolutional Neural Network Detection Denis Tom´e, Luca Bondi, Luca Baroffio, Stefano Tubaro Dipartimento di Elettronica, Informazione e Bioingegneria Politecnico di Milano Milano, Italy Emanuele Plebani, Danilo Pau Advanced System Technology STMicroelectronics Agrate Brianza, Italy" 4f892475be26333ddf1b72c21f0c9c4ca129bd80,Mobile Cloud Computing for Biometric Applications,"Singidunum University Belgrade, Serbia Mobile Cloud Computing for Biometric Applications Milos Stojmenovic Department of Informatics and Computation" 4f4c067e684252cf5549f60036829a89b2f35fc8,Sentic Avatar: Multimodal Affective Conversational Agent with Common Sense,"Sentic Avatar: Multimodal Affective Conversational Agent with Common Sense Erik Cambria1, Isabelle Hupont2, Amir Hussain1, Eva Cerezo3, and Sandra Baldassarri3 University of Stirling, Stirling, UK Aragon Institute of Technology, Zaragoza, Spain University of Zaragoza, Zaragoza, Spain http://cs.stir.ac.uk/~eca/sentics" 4f606761ce65399ef4ff24cd503ec09cf53562e9,"A System View of the Recognition and Interpretation of Observed Human Shape, Pose and Action","Copyright © 2015 David W. Arathorn A System View of the Recognition and Interpretation of Observed Human Shape, Pose and Action David W. Arathorn Dept of Electrical and Computer Engineering (formerly of Center for Computational Biology) Montana State University-Bozeman General Intelligence Corporation Bozeman, MT" 4f5708dfbdf03b370fe6be9a6e260d6e124ca09a,Face Recognition using Symbolic KDA in the framework of Symbolic Data Analysis,"Face Recognition using Symbolic KDA in the framework of Symbolic Data Analysis" 4f863543407143a62e1bb053d435a947886ba619,Distributed deep learning on edge-devices: Feasibility via adaptive compression,"Distributed deep learning on edge-devices: feasibility via adaptive compression Corentin Hardy Technicolor, Inria Rennes, France Erwan Le Merrer Technicolor Rennes, France Bruno Sericola Inria Rennes, France" 4fe0c6c83d998a0660bc5280c8ab6e61df9df887,FACE IMAGE NORMALIZATION AND EXPRESSION / POSE VALIDATION FOR THE ANALYSIS OF MACHINE READABLE TRAVEL DOCUMENTS,"FACE IMAGE NORMALIZATION AND EXPRESSION/POSE VALIDATION FOR THE ANALYSIS OF MACHINE READABLE TRAVEL DOCUMENTS Markus Storer1, Martin Urschler1, Horst Bischof1, Josef A. Birchbauer2" 4ff7f5928f96ddc877b4b8675cc41cc08f4bd561,Recent Advance in Content-based Image Retrieval: A Literature Survey,"Recent Advance in Content-based Image Retrieval: A Literature Survey Wengang Zhou, Houqiang Li, and Qi Tian Fellow, IEEE" 4fec382efed4e08a36fafa3710b97f0b20de1ebe,BINARIZED REPRESENTATION ENTROPY (BRE) REGULARIZATION,"Published as a conference paper at ICLR 2018 IMPROVING GAN TRAINING VIA BINARIZED REPRESENTATION ENTROPY (BRE) REGULARIZATION Yanshuai Cao, Gavin Weiguang Ding, Kry Yik-Chau Lui, Ruitong Huang Borealis AI Canada" 4f00f5fe9d762009f524fb97555088769b96328c,Eye Gaze Tracking System Using . Net,"IJSART - Volume 3 Issue 5 –MAY 2017 ISSN [ONLINE]: 2395-1052 Eye Gaze Tracking System Using .Net Madhu M Nayak1, Usha Rani J2, Anandhi G3 Department of CSE , 2, 3Assistant Professor,GSSIETW, Mysuru" 4fb569af589d89f11d84d4b828459231345cc301,Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression,"Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression Dong Wang1, Lei Zhou1, Xueni Zhang1, Xiao Bai1, and Jun Zhou2 Beihang University 2Grif‌f‌ith University" 4f48c8653cd38cd18f08924c9304bc02ed7ea492,Learning from Noisy Labels with Distillation, 4f8bd3519a6e8a05db9e35b027c0c65c91d2ff62,Brain Oxytocin is a Main Regulator of Prosocial Behaviour - Link to Psychopathology,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 4f618cbf19917ce5b8703adbc14e15b0bf0d35cc,Multi-View Dynamic Facial Action Unit Detection,"Multi-View Dynamic Facial Action Unit Detection Andr´es Romero Juan Le´on Pablo Arbel´aez Universidad de los Andes" 4f15b1e750007465024181dd002dfc6d1baa48c9,Face Recognition and Computer Graphics for Modelling Expressive Faces in 3d Face Recognition and Computer Graphics for Modeling Expressive Faces in 3d,"Face Recognition and Computer Graphics for Modelling Expressive Faces in 3D Tufool Al-Nuaimi Submitted to the Department of Electrical Engineering and Computer Science in Partial Fulfillment of the Requirements for the Degree of Master of Engineering in Electrical Engineering and Computer Science t the Massachusetts Institute of Technology May 26, 2006 Copyright 2006 Tufool AI-Nuaimi. All rights reserved. The author hereby grants to M.I.T. permission to reproduce and distribute publicly paper and electronic copies of this thesis nd to grant others the right to do so. Author Certified by_ Accepted by_ _ Tufool Al-Nuaimi Department of Electrical Engineering and Computer Science -Ma 26, 2006 Judith Barry Supervisor" 9e2120e48d497b373c53563275c3786c11749883,Topological and metric robot localization through computer vision techniques,"Topological and metric robot localization through computer vision techniques A. C. Murillo, J. J. Guerrero and C. Sag¨u´es DIIS - I3A, University of Zaragoza, Spain" 9ea37d031a8f112292c0d0f8d731b837462714e9,Face Recognition: From Traditional to Deep Learning Methods,"Face Recognition: From Traditional to Deep Learning Methods Daniel S´aez Trigueros, Li Meng School of Engineering and Technology University of Hertfordshire Hatfield AL10 9AB, UK Margaret Hartnett GBG plc London E14 9QD, UK" 9ef2b2db11ed117521424c275c3ce1b5c696b9b3,Robust Face Alignment Using a Mixture of Invariant Experts,"Robust Face Alignment Using a Mixture of Invariant Experts Oncel Tuzel† Salil Tambe‡∗ Tim K. Marks† Intel Corporation Mitsubishi Electric Research Labs (MERL) {oncel," 9ee4d3c173c41ffb6f5aa3c40951aefe3da11d5b,Forming A Random Field via Stochastic Cliques: From Random Graphs to Fully Connected Random Fields,"Forming A Random Field via Stochastic Cliques: From Random Graphs to Fully Connected Random Fields M. J. Shafiee, A. Wong and P. Fieguth" 9ebe5d78163a91239f10c453d76082dfa329851d,Teacher's Perception in the Classroom,"Teachers’ Perception in the Classroom ¨Omer S¨umer1 Patricia Goldberg1 Kathleen St¨urmer1 Tina Seidel3 Peter Gerjets2 Ulrich Trautwein1 Enkelejda Kasneci1 University of T¨ubingen, Germany Leibniz-Institut f¨ur Wissensmedien, Germany Technical University of Munich, Germany" 9eeada49fc2cba846b4dad1012ba8a7ee78a8bb7,A New Facial Expression Recognition Method Based on Local Gabor Filter Bank and PCA plus LDA,"Hong-Bo Deng, Lian-Wen Jin, Li-Xin Zhen, Jian-Cheng Huang A New Facial Expression Recognition Method Based on Local Gabor Filter Bank and PCA plus LDA A New Facial Expression Recognition Method Based on Local Gabor Filter Bank and PCA plus LDA Hong-Bo Deng1, Lian-Wen Jin1, Li-Xin Zhen2, Jian-Cheng Huang2 School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510640, P.R.China Motorola China Research Center, Shanghai, 210000, P.R.China {hbdeng, {Li-Xin.Zhen," 9e92d847ba169146ceb8b3b7cfdc47925e5a53e9,The LIUM-AVS database : a corpus to test lip segmentation and speechreading systems in natural conditions,"The LIUM-AVS database : a corpus to test lip segmentation nd speechreading systems in natural conditions Philippe Daubias, Paul Del´eglise Laboratoire d’Informatique de l’Universit´e du Maine Le Mans, France" 9ed3e04586f311b1e2b5ded9c9c4bfeeecf27f0c,Understanding rapid category detection via multiply degraded images.,"http://journalofvision.org/9/6/19/ Understanding rapid category detection via multiply degraded images Chetan Nandakumar Vision Science Graduate Program, University of California, Berkeley, Berkeley, CA, USA Jitendra Malik Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, CA, USA Rapid category detection, as discovered by S. Thorpe, D. Fize, and C. Marlot (1996), demonstrated that the human visual system can detect object categories in natural images in as little as 150 ms. To gain insight into this phenomenon and to determine its relevance to naturally occurring conditions, we degrade the stimulus set along various image dimensions and investigate the effects on perception. To investigate how well modern-day computer vision algorithms cope with degradations, we conduct an analog of this same experiment with state-of-the-art object recognition algorithms. We discover that rapid category detection in humans is quite robust to naturally occurring degradations and is mediated by a non-linear interaction of visual features. In contrast, modern-day object recognition algorithms are not as robust. Keywords: rapid category detection, degraded images, object recognition, eye tracking Citation: Nandakumar, C., & Malik, J. (2009). Understanding rapid category detection via multiply degraded images. Journal of Vision, 9(6):19, 1–8, http://journalofvision.org/9/6/19/, doi:10.1167/9.6.19." 9eb111f6990d1494a3904f22be9836c202efd7d1,Exploiting workload similarities for efficient scheduling in diverse asymmetric chip multiprocessing Research,Exploiting workload similarities for efficient scheduling in diverse asymmetric chip multiprocessing Dani Shaket 9e194413f10ea3385f063de87e15287072ac357b,An a-contrario Approach for Face Matching,"An a-contrario Approach for Face Matching Luis D. Di Martino, Javier Preciozzi, Federico Lecumberry and Alicia Fern´andez Instituto de Ingener´ıa El´ectrica, Universidad de la Rep´ublica, Montevideo, Uruguay Keywords: Face Recognition, Face Matching, a-contrario, STASM, LBP, Extended LBP, Chi-Square." 9e5acdda54481104aaf19974dca6382ed5ff21ed,Automatic localization of facial landmarks from expressive images of high complexity,"Yulia Gizatdinova and Veikko Surakka Automatic localization of facial landmarks from expressive images of high complexity DEPARTMENT OF COMPUTER SCIENCES UNIVERSITY OF TAMPERE D‐2008‐9 TAMPERE 2008" 9e759860762d40505f25d6fc5c4f4c1f6500d68b,Elastic Net Hypergraph Learning for Image Clustering and Semi-Supervised Classification,"Elastic Net Hypergraph Learning for Image Clustering and Semi-supervised Classification Qingshan Liu, Seninor Member, IEEE, Yubao Sun, Cantian Wang, Tongliang Liu and Dacheng Tao, Fellow, IEEE" 9e8637a5419fec97f162153569ec4fc53579c21e,Segmentation and Normalization of Human Ears Using Cascaded Pose Regression,"Segmentation and Normalization of Human Ears using Cascaded Pose Regression Anika Pflug and Christoph Busch University of Applied Sciences Darmstadt - CASED, Haardtring 100, 64295 Darmstadt, Germany http://www.h-da.de" 9e1712ac91c7a882070a8e2740ed476d59d6d5d4,Expressive image manipulations for a variety of visual representations. (Manipulations d'image expressives pour une variété de représentations visuelles),"Expressive image manipulations for a variety of visual representations Adrien Bousseau To cite this version: Adrien Bousseau. Expressive image manipulations for a variety of visual representations. Human- Computer Interaction [cs.HC]. Université Joseph-Fourier - Grenoble I, 2009. English. HAL Id: tel-00429151 https://tel.archives-ouvertes.fr/tel-00429151 Submitted on 31 Oct 2009 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 9e071a5c3b8d85627c61bbbd303f919afc64ac3b,Evaluation of LBP and HOG Descriptors for Clothing Attribute Description,"Evaluation of LBP and HOG Descriptors for Clothing Attribute Description J. Lorenzo(cid:63), M. Castrill´on, E. Ram´on, and D. Freire Instituto Universitario SIANI Campus Universitario de Tafira 5017 Las Palmas - SPAIN Universidad de Las Palmas de Gran Canaria" 9e8dd40aea9204ad670b312a46ba807bfc0c61ce,Distribution-sensitive learning for imbalanced datasets Citation,"Distribution-sensitive learning for imbalanced datasets The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Citation As Published Publisher Version Accessed Citable Link Terms of Use Detailed Terms Song, Yale, Louis-Philippe Morency, and Randall Davis. “Distribution-Sensitive Learning for Imbalanced Datasets.” 2013 0th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG) (n.d.). http://dx.doi.org/10.1109/FG.2013.6553715 Institute of Electrical and Electronics Engineers (IEEE) Author's final manuscript Fri Jan 08 19:33:51 EST 2016 http://hdl.handle.net/1721.1/86107" 9edd7c738171b0f36b65ae771711c38ed1dc38ad,Long-Term Multi-Cue Tracking of Hands in Vehicles,"Long-Term Multi-Cue Tracking of Hands in Vehicles Akshay Rangesh, Eshed Ohn-Bar, and Mohan Manubhai Trivedi, Fellow, IEEE" 9e9052256442f4e254663ea55c87303c85310df9,On Attribute-assisted Reranking for Image Search,"International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) Volume 4 Issue 10, October 2015 Review On Attribute-assisted Reranking for Image Search Waghmare Supriya, Wavhal Archana, Patil Nital, Tapkir Yogita, Prof. Yogesh Thorat" 9e0285debd4b0ba7769b389181bd3e0fd7a02af6,From Face Images and Attributes to Attributes,"From face images and attributes to attributes Robert Torfason, Eirikur Agustsson, Rasmus Rothe, Radu Timofte Computer Vision Laboratory, ETH Zurich, Switzerland" 9e4b052844d154c3431120ec27e78813b637b4fc,Local gradient pattern-A novel feature representation for facial expression recognition,"Journal of AI and Data Mining Vol. 2, No .1, 2014, 33-38. Local gradient pattern - A novel feature representation for facial expression recognition M. Shahidul Islam Department of Computer Science, School of Applied Statistics, National Institute of Development Administration, Bangkok, Thailand. Received 23 April 2013; accepted 16 June 2013 *Corresponding author: (M.Shahidul Islam)" 9e6c15150179ce848402e89bd245831d9935f4f9,Bi-modal Face Recognition - How combining 2D and 3D Clues Can Increase the Precision,"Bi-modal face recognition How combining 2D and 3D clues can increase the precision Amel Aissaoui1, Jean Martinet2 USTHB, Algeria Lille 1 University, France issaoui Keywords: Face recognition, multimodal, 2D, 3D, LBP, RGB-depth." 9e263d429c3b87aae2653b6fb925b32b63c172cd,Enhanced image and video representation for visual recognition,"Enhanced image and video representation for visual recognition Mihir Jain To cite this version: Mihir Jain. Enhanced image and video representation for visual recognition. Computer Vision nd Pattern Recognition [cs.CV]. Universit´e Rennes 1, 2014. English. HAL Id: tel-00996793 https://tel.archives-ouvertes.fr/tel-00996793 Submitted on 27 May 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires" 9ee5218a2a74fafbc4227f6c7c587b72e141bd33,Iris Compression and Recognition using Spherical Geometry Image,"(IJARAI) International Journal of Advanced Research in Artificial Intelligence, Vol. 4, No.6, 2015 Iris Compression and Recognition using Spherical Geometry Image College of Computers and Information Technology University of Tabuk Tabuk, KSA Rabab M. Ramadan in 3D domain to test" 9ea7205ef136f207123cd6b54e15075835ae0049,Self-supervised language grounding by active sensing combined with Internet acquired images and text,"http://www.diva-portal.org Postprint This is the accepted version of a paper presented at Fourth International Workshop on Recognition and Action for Scene Understanding (REACTS2017), August 25, 2017, Ystad, Sweden. Citation for the original published paper: Abedin, M R., Bensch, S., Hellström, T. (2017) Self-supervised language grounding by active sensing combined with Internet acquired images nd text. In: Jorge Dias George Azzopardi, Rebeca Marf (ed.), Proceedings of the Fourth International Workshop on Recognition and Action for Scene Understanding (REACTS2017) (pp. 71-83). Málaga: REACTS N.B. When citing this work, cite the original published paper. Permanent link to this version: http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-138290" 9e9c600919332dcabbd32bbe81a00d1e47449193,Automatic 3D face verification from range data,"- 1330-7803-7663-3/03/$17.00 ©2003 IEEEThis paper was originally published in the Proceedings of the 2003 IEEEInternational Conference on Acoustics, Speech, & Signal Processing,April 6-10, 2003, Hong Kong (cancelled). Reprinted with permission.(cid:224)" 9e594ae4f549e0d838f497de31a5b597a6826d55,Recognition of Emotion from Facial Expressions with Direct or Averted Eye Gaze and Varying Expression Intensities in Children with Autism Disorder and Typically Developing Children,"Hindawi Publishing Corporation Autism Research and Treatment Volume 2014, Article ID 816137, 11 pages http://dx.doi.org/10.1155/2014/816137 Research Article Recognition of Emotion from Facial Expressions with Direct or Averted Eye Gaze and Varying Expression Intensities in Children with Autism Disorder and Typically Developing Children Dina Tell,1 Denise Davidson,2 and Linda A. Camras3 Department of Health Promotion, Loyola University Chicago, Marcella Niehoff School of Nursing, 2160 S. First Avenue, Maywood, IL 60153, USA Department of Psychology, Loyola University Chicago, 1032 W. Sheridan Road, Chicago, IL 60660, USA Department of Psychology, DePaul University, 2219 N. Kenmore Avenue, Chicago, IL 60614, USA Correspondence should be addressed to Denise Davidson; Received 8 November 2013; Revised 7 February 2014; Accepted 12 February 2014; Published 3 April 2014 Academic Editor: Geraldine Dawson Copyright © 2014 Dina Tell et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Eye gaze direction and expression intensity effects on emotion recognition in children with autism disorder and typically developing hildren were investigated. Children with autism disorder and typically developing children identified happy and angry expressions" 9ea73660fccc4da51c7bc6eb6eedabcce7b5cead,Talking head detection by likelihood-ratio test,"Talking Head Detection by Likelihood-Ratio Test† Carl Quillen, Kara Greenfield, and William Campbell MIT Lincoln Laboratory, Lexington MA 02420, USA" 7697295ee6fc817296bed816ac5cae97644c2d5b,Detecting and Recognizing Human-Object Interactions,"Detecting and Recognizing Human-Object Interactions Georgia Gkioxari Ross Girshick Piotr Doll´ar Kaiming He Facebook AI Research (FAIR)" 76bcd8cce40892aee1bc46de17a3b803373172d9,A 58 . 6 mW 30 fps Real-Time Programmable Multi-Object Detection Accelerator with Deformable Parts Models on Full HD 1920,"A 58.6mW 30fps Real-Time Programmable Multi-Object Detection Accelerator with Deformable Parts Models on Full HD 1920×1080 Videos The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Citation As Published Publisher Version Accessed Citable Link Terms of Use Detailed Terms Suleiman, Amr, Zhang, Zhengdong, and Sze, Vivienne. ""A 58.6 mW 30 Frames/s Real-Time Programmable Multiobject Detection Accelerator With Deformable Parts Models on Full HD 920×1080 Videos."" IEEE Journal of Solid State Circuits, 52 (March 2017): 844-855.© 2017 Institute of Electrical and Electronics Engineers (IEEE) https://doi.org/10.1109/JSSC.2017.2648820" 7608953ef5c7a882bd2e7e7053a600e543748233,Robust 3D Face Recognition by Local Shape Difference Boosting,"Robust 3D Face Recognition y Local Shape Difference Boosting Yueming Wang, Jianzhuang Liu, Senior Member, IEEE, and Xiaoou Tang, Fellow, IEEE" 76bfa74a6311db5d84bad2a7a941f30dd750d01c,Evidence That Emotion Mediates Social Attention in Rhesus Macaques,"Evidence That Emotion Mediates Social Attention in Rhesus Macaques Emily J. Bethell1*, Amanda Holmes2, Ann MacLarnon1, Stuart Semple1 Centre for Research in Evolutionary and Environmental Anthropology, University of Roehampton, London, United Kingdom, 2 Department of Psychology, University of Roehampton, London, United Kingdom" 76ec5c774bb3fd04f9e68864a411286536a544c5,Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models,"LATENT CONSTRAINTS: LEARNING TO GENERATE CONDITIONALLY FROM UNCONDITIONAL GENERATIVE MODELS Jesse Engel Google Brain San Francisco, CA, USA Matthew D. Hoffman Google Inc. San Francisco, CA, USA Adam Roberts Google Brain San Francisco, CA, USA" 76ff6a68d7a8dcc12b6ba68e914294f6720a466d,The red one!: On learning to refer to things based on discriminative properties,"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 213–218, Berlin, Germany, August 7-12, 2016. c(cid:13)2016 Association for Computational Linguistics" 76ebe6d24ee69e3f853740fb75085a2118d40d51,ILLUMINANCE FLOW ( met een samenvatting in het Nederlands ) PROEFSCHRIFT ter verkrijging van de graad van doctor,"ILLUMINANCE FLOW (met een samenvatting in het Nederlands) PROEFSCHRIFT ter verkrijging van de graad van doctor aan de Universiteit Utrecht op gezag van de rector magnificus, prof.dr. J.C. Stoof, ingevolge het besluit van het college voor promoties in het openbaar te verdedigen op vrijdag 15 januari 2010 des middags te 4.15 uur (Dan) Stefan Mikael Karlsson geboren op 3 september 1978 te Stafsinge, Zweden" 76cb2ecc96f02b1d8a7a0d1681fbb55367a4b765,Learning Object States from Videos,"Learning Object States from Videos Liang-Kang Huang Katerina Fragkiadaki" 768cb0e32de3f1b5aebe04448aaec4c25586680c,Boosting Image Captioning with Attributes,"Under review as a conference paper at ICLR 2017 BOOSTING IMAGE CAPTIONING WITH ATTRIBUTES Ting Yao, Yingwei Pan, Yehao Li, Zhaofan Qiu, Tao Mei Microsoft Research Asia {tiyao, v-yipan, v-yehl, v-zhqiu," 766794580ddbb53f4e29f4912b8d373df7ba928b,Extracting Relevant Structures,"Chapter 5 Extracting relevant structures A key problem in understanding auditory coding is to identify the acoustic features that neurons at various levels of the system code. If we can map the relevant stimulus features and trace how they change along the processing hierarchy, we can understand the processing properties of the system. A principled approach for extracting relevant features was proposed by Tishby nd co-authors [Tishby et al., 1999], with the Information Bottleneck (IB) frame- work. This powerful approach aims at identifying structures of a variable X that have functional importance, by compressing X in a way that preserves information bout another variable Y . In the context of the current problem it can be used to com- press acoustic stimuli while preserving information about the distribution of neural responses, and use it to identify the stimulus aspects to which system is sensitive. Unfortunately, the IB approach is insu(cid:14)cient for characterizing the processing that takes place in a brain region like the cortex. To understand the reason why, onsider for example a case where one measures cortical activity in response to acous- tic stimuli, and maps the acoustic features to which the cortical neurons respond. Such an analysis does not characterize cortical processing but rather the processing performed by the whole chain of processing stations that ends in the cortex. In fact, many of the features that are revealed this way do not re(cid:13)ect cortical processing, but" 761de31c575bf30162b6e0d92a1800eb406e96b5,A Flexible Convolutional Solver with Application to Photorealistic Style Transfer,"A Flexible Convolutional Solver with Application to Photorealistic Style Transfer Gilles Puy and Patrick P´erez (1) Artistic style (2) Photorealistic style (a) Input image (b) Artistic transfer (c) Photorealistic transfer Figure 1. Given an input image (a), the proposed convolutional neural network yields fast artistic stylisation results, e.g., (b) for style (1), and can be modified at runtime – hence without retraining – to yield photorealistic stylisation results, e.g., (c) for style (2)." 76c018c6dfc81f61c3912c5ed442d9a72f64e467,Graphical Processing Unit Assisted Image Processing for Accelerated Eye Tracking,"Graphical Processing Unit Assisted Image Processing for Accelerated Eye Tracking Dissertation submitted by Jean-Pierre Louis du Plessis Student Number: 2006033415 to the Department of Computer Science and Informatics Faculty of Natural and Agricultural Sciences University of the Free State, South Africa Submitted in fulfilment of the requirements of the degree Magister Scientiae February 2015 Study Leader: Prof P.J. Blignaut" 76f73c884e4437a22afcba60193bbd7f35e64aaf,Title of dissertation : RESOURCE ALLOCATION IN COMPUTER VISION, 7671234c3726fda01b2842f85327624f0dda8ead,The data deluge: Challenges and opportunities of unlimited data in statistical signal processing,"978-1-4244-2354-5/09/$25.00 ©2009 IEEE ICASSP 2009" 7689d23a22682c92bdf9a1df975fa2cdd24f1b87,MMD with Kernel Learning In practice we use finite samples from distributions to estimate,"MMD GAN: Towards Deeper Understanding of Moment Matching Network Chun-Liang Li Committee: Barnab´as P´oczos and Pradeep Ravikumar Tuesday 28th November, 2017" 7636f94ddce79f3dea375c56fbdaaa0f4d9854aa,Appl . Math . Inf . Sci . 6 No . 2 S pp . 403 S-408 S ( 2012 ) Robust Facial Expression Recognition Using a Smartphone Working against Illumination Variation,"Appl. Math. Inf. Sci. 6 No. 2S pp. 403S-408S (2012) An International Journal © 2012 NSP Applied Mathematics & Information Sciences Robust Facial Expression Recognition Using Smartphone Working against Illumination Variation 2012 NSP Natural Sciences Publishing Cor. Kyoung-Sic Cho1, In-Ho Choi1 and Yong-Guk Kim1 Department of Computer Engineering, Sejong University, 98 Kunja-Dong, Kwangjin-Gu, Seoul, Korea Corresponding author: Email: Received June 22, 2010; Revised March 21, 2011; Accepted 11 June 2011 Published online: 1 January 2012" 7606a74de57f67257c77a8bb0295ff4593566040,Content-based Image Retrieval Using Constrained Independent Component Analysis : Facial Image Retrieval Based on Compound Queries,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 76d8b370d0a8fc63ead6ba657dd438d7155d659f,Modular Sensor Fusion for Semantic Segmentation,"(cid:13)2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any urrent or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Please cite this paper as: title uthor ooktitle = ""2018 {IEEE/RSJ} International Conference on Intelligent Robots = ""Modular Sensor Fusion for Semantic Segmentation"", = ""Blum, Hermann and Gawel, Abel and Siegwart, Roland and Cadena, Cesar"", nd Systems ({IROS})"", = 2018;" 76b11c281ac47fe6d95e124673a408ee9eb568e3,Real-time Multi View Face Detection and Pose Estimation Aishwarya,"International Journal of Latest Engineering and Management Research (IJLEMR) ISSN: 2455-4847 www.ijlemr.com || Volume 02 - Issue 03 || March 2017 || PP. 59-71 REAL-TIME MULTI VIEW FACE DETECTION AND POSE ESTIMATION AISHWARYA.S1 , RATHNAPRIYA.K1, SUKANYA SARGUNAR.V2 U. G STUDENTS, DEPT OF CSE, ALPHA COLLEGE OF ENGINEERING, CHENNAI, ASST PROF.DEPARTMENT OF CSE, ALPHA COLLEGE OF ENGINEERING, CHENNAI" 76f3450e50c20fca00dd6319df38503c5d7ebad0,Sujet de la thèse : Alignement élastique d ’ images pour la reconnaissance d ’ objet — Non-rigid image alignment for object recognition,"THÈSEDEDOCTORATprésentéeparOLIVIERDUCHENNEpourobtenirlegradedeDOCTEURDEL’ÉCOLENORMALESUPÉRIEUREDomaine:MATHÉMATIQUESAPPLIQUÉESSujetdelathèse:Alignementélastiqued’imagespourlareconnaissanced’objet—Non-rigidimagealignmentforobjectrecognitionThèseprésentéeetsoutenueàl’ENSUlmle29Novembre2012devantlejurycomposéde:JeanPonceProfesseur,DirecteurduDI,ENSUlmDirecteurdethèsePedroFelzenszwalbProfesseur,BrownUniversityRapporteurMartialHebertProfesseur,CarnegieMellonUniversityRapporteurFrancisBachDirecteurderecherche,ENSUlmÉxaminateurJitendraMalikProfesseur,UniversityofBerkeleyÉxaminateurCordeliaSchmidProfesseur,INPGrenobleÉxaminateurAndrewZissermanProfesseur,UniversityofOxfordÉxaminateurThèsepréparéeauseindel’équipeWILLOWdudépartementd’informatiquedel’ÉcoleNormaleSupérieure,Ulm.(INRIA/ENS/CNRSUMR8548)." 7638cb16631fbcdf621aaf392fec5108e6fa9f47,On Nonrigid Shape Similarity and Correspondence,"Alon Shtern and Ron Kimmel November 25, 2013 trinsically symmetric halves of a human face were found by mapping the shape (left) to itself. Textures from two faces (middle) were transferred to each half (right)." 763158cef9d1e4041f24fce4cf9d6a3b7a7f08ff,Hierarchical Modeling and Applications to Recognition Tasks,"Hierarchical Modeling and Applications to Recognition Tasks Thesis submitted for the degree of ”Doctor of Philosophy” Alon Zweig Submitted to the Senate of the Hebrew University August / 2013" 76a0016ce19363ef8f7ba5c3964c4a0c29b608ca,ModaNet: A Large-scale Street Fashion Dataset with Polygon Annotations,"ModaNet: A Large-scale Street Fashion Dataset with Polygon Annotations Shuai Zheng eBay Inc. San Jose, California M. Hadi Kiapour eBay Inc. San Francisco, California Fan Yang eBay Inc. San Jose, California Robinson Piramuthu eBay Inc. San Francisco, California" 76d9f5623d3a478677d3f519c6e061813e58e833,Fast Algorithms for the Generalized Foley-Sammon Discriminant Analysis,"FAST ALGORITHMS FOR THE GENERALIZED FOLEY-SAMMON DISCRIMINANT ANALYSIS LEI-HONG ZHANG∗, LI-ZHI LIAO† , AND MICHAEL K. NG‡" 76dc11b2f141314343d1601635f721fdeef86fdb,Weighted Decoding ECOC for Facial Action Unit Classification,"Weighted Decoding ECOC for Facial Action Unit Classification Terry Windeatt" 761db68bf6031545cc865a813f398cb4ee8f61a1,Feature to Feature Matching for LBP Based Face Recognition,"Feature to Feature Matching for LBP Based Face Recognition Ladislav Lenc1,2 and Pavel Kr´al1,2 Dept. of Computer Science & Engineering Faculty of Applied Sciences University of West Bohemia Plzeˇn, Czech Republic NTIS - New Technologies for the Information Society Faculty of Applied Sciences University of West Bohemia Plzeˇn, Czech Republic" 76e2d7621019bd45a5851740bd2742afdcf62837,Real-Time Detection and Measurement of Eye Features from Color Images,"Article Real-Time Detection and Measurement of Eye Features from Color Images Diana Borza 1, Adrian Sergiu Darabant 2 and Radu Danescu 1,* Computer Science Department, Technical University of Cluj Napoca, 28 Memorandumului Street, Cluj Napoca 400114, Romania; Computer Science Department, Babes Bolyai University, 58-60 Teodor Mihali, C333, Cluj Napoca 400591, Romania; * Correspondence: Tel.: +40-740-502-223 Academic Editors: Changzhi Li, Roberto Gómez-García and José-María Muñoz-Ferreras Received: 28 April 2016; Accepted: 14 July 2016; Published: 16 July 2016" 76b2732a8684babdfd95c655b2e1a1b79c3aeb9b,Face detection from few training examples,"978-1-4244-1764-3/08/$25.00 ©2008 IEEE ICIP 2008 Authorized licensed use limited to: UNSW Library. Downloaded on June 12, 2009 at 01:20 from IEEE Xplore. Restrictions apply." 76cd5e43df44e389483f23cb578a9015d1483d70,Face Verification from Depth using Privileged Information,"BORGHI ET AL.: FACE VERIFICATION FROM DEPTH Face Verification from Depth using Privileged Information Department of Engineering ""Enzo Ferrari"" University of Modena and Reggio Emilia Modena, Italy Guido Borghi Stefano Pini Filippo Grazioli Roberto Vezzani Rita Cucchiara" 06d6015a19ef180cb11d9f32feb9e6adfa2799f5,Learning image representations equivariant to ego-motion ( Supplementary material ),"Learning image representations equivariant to ego-motion (Supplementary material) Dinesh Jayaraman UT Austin Kristen Grauman UT Austin the optimal regularizer weight (for DRLIM, TEMPORAL nd EQUIV) was selected from a logarithmic grid (steps of 100.5). For EQUIV+DRLIM, the DRLIM loss regularizer weight fixed for DRLIM was retained, and only the EQUIV loss weight was cross-validated. The contrastive loss mar- gin parameter δ in Eq (6) in DRLIM, TEMPORAL and EQUIV were set uniformly to 1.0. Since no other part of these ob- jectives (including the softmax classification loss) depends on the scale of features,1 different choices of margins δ in these methods lead to objective functions with equiva- lent optima - the features are only scaled by a factor. For EQUIV+DRLIM, we set the DRLIM and EQUIV margins re- spectively to 1.0 and 0.1 to reflect the fact that the equiv- riance maps Mg of Eq (5) applied to the representation" 06680961e99aadb366968e5f515da58864ecd784,Trends Research Enabler for Design Specifications Deliverable Trends Meta-deliverable 1 -state of the Art Security Classification : Pu Leading Partner Seram Meta Deliverable 1 -state of the Art,"Trends Research ENabler for Design Specifications FP6-IST-2005-27916 Deliverable TRENDS META-DELIVERABLE 1 - STATE OF THE ART Security Classification : PU Leading partner SERAM Issue Date 03/09/2007 Version Authors Approved by Final draft Aranzazu BERECIARTUA, Carole BOUCHARD, Marin FERECATU, Guillaume LOGEROT, Loïs RIGOUSTE, Carlotta VITALE Carole Bouchard 03/09/2007 META DELIVERABLE 1 - STATE OF THE ART This document presents a State Of the Art related to most popular products, tools and methods" 0678a8abea82793993cd89383319da75f6dc4be3,ProNet: Learning to Propose Object-Specific Boxes for Cascaded Neural Networks,"ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks Chen Sun1,2 Manohar Paluri2 Ronan Collobert2 Ram Nevatia1 Lubomir Bourdev3 UC Berkeley USC {chensun, Facebook AI Research {mano," 06262d14323f9e499b7c6e2a3dec76ad9877ba04,Real-Time Pose Estimation Piggybacked on Object Detection,"Real-Time Pose Estimation Piggybacked on Object Detection Roman Jur´anek, Adam Herout, Mark´eta Dubsk´a, Pavel Zemˇc´ık Brno University of Technology Brno, Czech Republic" 06178edf24183e6fb9e3e265ff4f290a4f0934d2,A Cautionary Tail,"A Cautionary Tail A Framework and Case Study for Testing Predictive Model Validity Peter C. Casey (cid:140)e Lab DC Government of the District of Columbia 350 Pennsylvania Avenue NW Washington, D.C. 20004 350 Pennsylvania Avenue NW 350 Pennsylvania Avenue NW David Yokum (cid:140)e Lab DC Government of the District of Columbia Washington, D.C. Kevin H. Wilson (cid:140)e Lab DC Government of the District of Columbia Washington, D.C. 20004" 06cfc431b70ec6a6783284953a668984600e77e2,A Framework for Human Pose Estimation in Videos,"A Framework for Human Pose Estimation in Videos Dong Zhang and Mubarak Shah" 066454772e51df9142e99bfed1d83eae1c755ed1,Multi-Target Tracking by Online Learning a CRF Model of Appearance and Motion Patterns,"Int J Comput Vis DOI 10.1007/s11263-013-0666-4 Multi-Target Tracking by Online Learning a CRF Model of Appearance and Motion Patterns Bo Yang · Ramakant Nevatia Received: 21 December 2012 / Accepted: 7 October 2013 © Springer Science+Business Media New York 2013" 0697bd81844d54064d992d3229162fe8afcd82cb,User-driven mobile robot storyboarding: Learning image interest and saliency from pairwise image comparisons,"User-driven mobile robot storyboarding: Learning image interest and saliency from pairwise image comparisons Michael Burke1" 069ebb57ccca31ab68983e07044e65ce1a04174f,4D facial expression recognition,"011 IEEE International Conference on Computer Vision Workshops 978-1-4673-0063-6/11/$26.00 c(cid:13)2011 IEEE" 06da0e4ae21835f0d33cfbf66c8b73b58625c57b,Facial Keypoints Detection,"Facial Keypoints Detection Shenghao Shi" 06cb0939ed5fb2b3398d54a7fcdb865fe53f414a,Bag-of-Words Image Representation: Key Ideas and Further Insight,"Chapter 2 Bag-of-Words Image Representation: Key Ideas and Further Insight Marc T. Law, Nicolas Thome and Matthieu Cord" 06262d6beeccf2784e4e36a995d5ee2ff73c8d11,Recognize Actions by Disentangling Components of Dynamics,"Recognize Actions by Disentangling Components of Dynamics Yue Zhao1, Yuanjun Xiong1,2, and Dahua Lin1 CUHK - SenseTime Joint Lab, The Chinese University of Hong Kong 2Amazon Rekognition" 0602e312a532f9af85cfd0190a2f69f07f44b4fe,The influence of self and similarity on immediate affective impressions of people Ruys,"UvA-DARE (Digital Academic Repository) The influence of self and similarity on immediate affective impressions of people Ruys, K.I. Link to publication Citation for published version (APA): Ruys, K. I. (2004). The influence of self and similarity on immediate affective impressions of people General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Download date: 18 Dec 2018 UvA-DARE is a service provided by the library of the University of Amsterdam (http://dare.uva.nl)" 060797f33c242b568189be251f9735afdc4c9f22,Robust Deep-Learning-Based Road-Prediction for Augmented Reality Navigation Systems at Night,"Robust Deep-Learning-Based Road-Prediction for Augmented Reality Navigation Systems Matthias Limmer1*, Julian Forster1*, Dennis Baudach1, Florian Schüle2, Roland Schweiger1 and Hendrik P.A. Lensch3" 06774cc8b0ab364866beaf3efda1b2d012a7bcf9,MobileNetV2: Inverted Residuals and Linear Bottlenecks,"MobileNetV2: Inverted Residuals and Linear Bottlenecks Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov Liang-Chieh Chen {sandler, howarda, menglong, azhmogin, Google Inc." 061acf48912fe058ba7084dbbdbddc407f01263b,Detection and Orientation Estimation for Cyclists by Max Pooled Features,"Detection and Orientation Estimation for Cyclists y Max Pooled Features" 068a7c7849cb6480def2e124ac5a45564e094b2a,Multi-Scale Learning for Low-Resolution Person Re-Identification,"Multi-scale learning for low-resolution person re-identification Li, X; Zheng, WS; Wang, X; Xiang, T; Gong, S © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle/123456789/19657 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 06d89147794d0889b2e031b0c6811423806f5ea0,Input Image Initialization Estimated Gaze Iterative Model Fitting 3,"A 3D Morphable Eye Region Model for Gaze Estimation Anonymous ECCV submission Paper ID 93" 069c9b3c7cf82310d3e06831208aea15f6fdfc32,Power management for mobile games on asymmetric multi-cores,"Power Management for Mobile Games on Asymmetric Multi-Cores Anuj Pathania, Santiago Pagani, Muhammad Shafique, J¨org Henkel Chair for Embedded Systems (CES), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany Corresponding Author:" 066000d44d6691d27202896691f08b27117918b9,Vision-Based Analysis of Small Groups in Pedestrian Crowds,"Vision-based Analysis of Small Groups in Pedestrian Crowds Weina Ge, Robert T. Collins, Senior Member, IEEE, and R. Barry Ruback E-mail:" 069c40a8ca5305c9a0734c1f6134eb19a678f4ab,LabelMe: A Database and Web-Based Tool for Image Annotation,"Int J Comput Vis (2008) 77: 157–173 DOI 10.1007/s11263-007-0090-8 LabelMe: A Database and Web-Based Tool for Image Annotation Bryan C. Russell · Antonio Torralba · Kevin P. Murphy · William T. Freeman Received: 6 September 2005 / Accepted: 11 September 2007 / Published online: 31 October 2007 © Springer Science+Business Media, LLC 2007" 068171535ac18a4b7b65be0748d483ce4c71a9a4,Event Specific Multimodal Pattern Mining with Image-Caption Pairs,"Event Specific Multimodal Pattern Mining with Image-Caption Pairs Hongzhi Li∗ Columbia Univeristy Joseph G. Ellis∗ Columbia Univeristy Shih-Fu Chang Columbia Univeristy" 061fb1b627554f52ff8f3ebb531e326767d845ec,Globally-optimal greedy algorithms for tracking a variable number of objects,"Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects Hamed Pirsiavash Deva Ramanan Charless C. Fowlkes Department of Computer Science, University of California, Irvine" 06fe63b34fcc8ff68b72b5835c4245d3f9b8a016,Learning semantic representations of objects and their parts,"Mach Learn DOI 10.1007/s10994-013-5336-9 Learning semantic representations of objects nd their parts Grégoire Mesnil · Antoine Bordes · Jason Weston · Gal Chechik · Yoshua Bengio Received: 24 May 2012 / Accepted: 26 February 2013 © The Author(s) 2013" 060820f110a72cbf02c14a6d1085bd6e1d994f6a,Fine-grained classification of pedestrians in video: Benchmark and state of the art,"Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art David Hall and Pietro Perona California Institute of Technology. The dataset was labelled with bounding boxes, tracks, pose and fine- grained labels. To achieve this, crowdsourcing, using workers from Ama- zon’s Mechanical Turk (MTURK) was used. A summary of the dataset’s statistics can be found in Table 1. Number of Frames Sent to MTURK Number of Frames with at least 1 Pedestrian Number of Bounding Box Labels Number of Pose Labels Number of Tracks 8,708 0,994 2,457 7,454 ,222 Table 1: Dataset Statistics A state-of-the-art algorithm for fine-grained classification was tested us- ing the dataset. The results are reported as a useful performance baseline." 0645134e885259c7ddc97bd1136b009051444061,Point Distribution Models for Pose Robust Face Recognition: Advantages of Correcting Pose Parameters Over Warping Faces to Mean Shape,"Point Distribution Models for Pose Robust Face Recognition: Advantages of Correcting Pose Parameters Over Warping Faces to Mean Shape Daniel Gonz´alez-Jim´enez and Jos´e Luis Alba-Castro⋆ Departamento de Teor´ıa de la Se˜nal y Comunicaciones Universidad de Vigo (Spain)" 063a3be18cc27ba825bdfb821772f9f59038c207,The development of spontaneous facial responses to others’ emotions in infancy: An EMG study,"This is a repository copy of The development of spontaneous facial responses to others’ emotions in infancy. An EMG study. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/125231/ Version: Published Version Article: Kaiser, Jakob, Crespo-Llado, Maria Magdalena, Turati, Chiara et al. (1 more author) (2017) The development of spontaneous facial responses to others’ emotions in infancy. An EMG study. Scientific Reports. ISSN 2045-2322 https://doi.org/10.1038/s41598-017-17556-y Reuse This article is distributed under the terms of the Creative Commons Attribution (CC BY) licence. This licence llows you to distribute, remix, tweak, and build upon the work, even commercially, as long as you credit the uthors for the original work. More information and the full terms of the licence here: https://creativecommons.org/licenses/ Takedown If you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing including the URL of the record and the reason for the withdrawal request. https://eprints.whiterose.ac.uk/" 06992ca951456bb88523f702f904dfd23eb27c53,Using Mobile Platform to Detect and Alerts Driver Fatigue,"International Journal of Computer Applications (0975 – 8887) Volume 123 – No.8, August 2015 Using Mobile Platform to Detect and Alerts Maysoon F. Abulkhair Department of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University B.P. 42808 Zip Code 21551- Girl Section, Jeddah, Saudi Arabia Driver Fatigue Hesham A. Salman Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Lamiaa F. Ibrahim" 06e15d0d6f92a11bb5b46b5a3e0250cccc452c92,Diagnostic Features of Emotional Expressions Are Processed Preferentially,"Diagnostic Features of Emotional Expressions Are Processed Preferentially Elisa Scheller1, Christian Bu¨ chel2, Matthias Gamer2* Department of Psychiatry and Psychotherapy, University Medical Center Freiburg, Freiburg, Germany, 2 Department of Systems Neuroscience, University Medical Center Hamburg-Eppendorf, Hamburg, Germany" 06ad99f19cf9cb4a40741a789e4acbf4433c19ae,SenTion: A framework for Sensing Facial Expressions,"SenTion: A framework for Sensing Facial Expressions Rahul Islam∗, Karan Ahuja∗, Sandip Karmakar∗, Ferdous Barbhuiya∗ ∗IIIT Guwahati {rahul.islam, karan.ahuja, sandip," 06599d41a3256245aa0cb2e9e56b29459c2e2c69,VisualWord2Vec (Vis-W2V): Learning Visually Grounded Word Embeddings Using Abstract Scenes,Visual Word2Vec (vis-w2v): Learning Visually Grounded 065f05c9cb2a6080191851dd82cd9b439a77499a,Comparing Boosted Cascades to Deep Learning Architectures for Fast and Robust Coconut Tree Detection in Aerial Images, 06e7e99c1fdb1da60bc3ec0e2a5563d05b63fe32,WhittleSearch: Image search with relative attribute feedback,"WhittleSearch: Image Search with Relative Attribute Feedback Adriana Kovashka, Devi Parikh and Kristen Grauman (Supplementary Material) Comparative Qualitative Search Results We present three qualitative search results for human-generated feedback, in addition to those shown in the paper. Each example shows one search iteration, where the 20 reference images are randomly selected (rather than ones that match a keyword search, as the image examples in the main paper illustrate). For each result, the first figure shows our method and the second figure shows the binary feedback result for the corresponding target image. Note that for our method, “more/less X” (where X is an attribute) means that the target image is more/less X than the reference image which is shown. Figures 1 and 2 show results for human-generated relative attribute and binary feedback, re- spectively, when both methods are used to target the same “mental image” of a shoe shown in the top left bubble. The top right grid of 20 images are the reference images displayed to the user, and those outlined and annotated with constraints are the ones chosen by the user to give feedback. The bottom row of images in either figure shows the top-ranked images after integrating the user’s feedback into the scoring function, revealing the two methods’ respective performance. We see that while both methods retrieve high-heeled shoes, only our method retrieves images that are as “open” s the target image. This is because using the proposed approach, the user was able to comment explicitly on the desired openness property." 06687e82ecc94f716d86d3e9f6bfbd30655c6631,CANDECOMP/PARAFAC Decomposition of High-Order Tensors Through Tensor Reshaping,"CANDECOMP/PARAFAC Decomposition of High-order Tensors Through Tensor Reshaping Anh Huy Phan∗, Petr Tichavsk´y and Andrzej Cichocki" 063f0e6afe13df9913617dbc2230ad4263a595bc,Loneliness and Hypervigilance to Social Cues in Females: An Eye-Tracking Study,"RESEARCH ARTICLE Loneliness and Hypervigilance to Social Cues in Females: An Eye-Tracking Study Gerine M. A. Lodder1*, Ron H. J. Scholte1¤a, Ivar A. H. Clemens2, Rutger C. M. E. Engels1¤b, Luc Goossens3, Maaike Verhagen1 Behavioural Science Institute, Radboud University, Nijmegen, The Netherlands, 2 Donders Institute for Brain, Cognition, and Behaviour, Radboud University, Nijmegen, The Netherlands, 3 Research Group School Psychology and Child and Adolescent Development, KU Leuven, Leuven, Belgium ¤a Current address: Praktikon, Nijmegen, The Netherlands ¤b Current address: The Trimbos Institute, Netherlands Institute of Mental Health and Addiction, Utrecht, The Netherlands" 0601416ade6707c689b44a5bb67dab58d5c27814,Feature Selection in Face Recognition: A Sparse Representation Perspective,"Feature Selection in Face Recognition: A Sparse Representation Perspective Allan Y. Yang John Wright Yi Ma S. Shankar Sastry Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2007-99 http://www.eecs.berkeley.edu/Pubs/TechRpts/2007/EECS-2007-99.html August 14, 2007" 06e768d74f076b251d53b0c86fc9910d7243bdc6,Effective and efficient visual description based on local binary patterns and gradient distribution for object recognition,"Effective and ef‌f‌icient visual description based on local inary patterns and gradient distribution for object recognition Chao Zhu To cite this version: Chao Zhu. Effective and ef‌f‌icient visual description based on local binary patterns and gradient distribution for object recognition. Other. Ecole Centrale de Lyon, 2012. English. . HAL Id: tel-00755644 https://tel.archives-ouvertes.fr/tel-00755644 Submitted on 21 Nov 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," 06dee5ff4b41eadf5db5c6841d3441d388f08117,3D cascade of classifiers for open and closed eye detection in driver distraction monitoring,"D Cascade of Classifiers for Open and Closed Eye Detection in Driver Distraction Monitoring Mahdi Rezaei and Reinhard Klette The .enpeda.. Project, The University of Auckland Tamaki Innovation Campus, Auckland, New Zealand" 06e959c88dcce05847a395dc404725dd0488003d,3D Pictorial Structures on RGB-D Data for Articulated Human Detection in Operating Rooms,"D Pictorial Structures on RGB-D Data for Articulated Human Detection in Operating Rooms Abdolrahim Kadkhodamohammadi, Afshin Gangi, Michel de Mathelin and Nicolas Padoy" 06de3eab314437cc3ed08c3db5171a79c1f684c6,Improving patch-based scene text script identification with ensembles of conjoined networks,"Boosting patch-based scene text script identification with ensembles of conjoined networks Lluis Gomez, Anguelos Nicolaou, Dimosthenis Karatzas Computer Vision Center, Universitat Autonoma de Barcelona. Edifici O, Campus UAB, 08193 Bellaterra (Cerdanyola) Barcelona, Spain. E-mail:" 06f251cceff93dac123e8568773295f2d0d702da,Player Tracking and Analysis of Basketball Plays,"Player Tracking and Analysis of Basketball Plays Evan Cheshire, Cibele Halasz, and Jose Krause Perin" 06928aef986877d04e9ce642a3ac71b6f061c638,Monocular Simultaneous Localisation and Mapping for Road Vehicles,"Monocular Simultaneous Localisation nd Mapping for Road Vehicles Master’s thesis in Systems, Control and Mechatronics MATHIAS ERNST, SAMUEL SCHEIDEGGER Department of Signals and Systems CHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2015" 0690ba31424310a90028533218d0afd25a829c8d,Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs,"Published as a conference paper at ICLR 2015 SEMANTIC IMAGE SEGMENTATION WITH DEEP CON- VOLUTIONAL NETS AND FULLY CONNECTED CRFS Liang-Chieh Chen Univ. of California, Los Angeles George Papandreou ∗ Google Inc. Iasonas Kokkinos CentraleSup´elec and INRIA Kevin Murphy Google Inc. Alan L. Yuille Univ. of California, Los Angeles" 06a2a3c6d44ab5572df55ce34d9b1216bc685385,GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks,"GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks Yasin Almalioglu1, Muhamad Risqi U. Saputra1, Pedro P. B. de Gusmo1, Andrew Markham1, and Niki Trigoni1" 06d10f906ac9023b5566c70a2600384b8c1b24c3,Beautiful and Damned. Combined Effect of Content Quality and Social Ties on User Engagement,"Beautiful and damned. Combined effect of content quality and social ties on user engagement Luca M. Aiello Nokia Bell Labs Rossano Schifanella University of Turin Miriam Redi Nokia Bell Labs Stacey Svetlichnaya Flickr Frank Liu Flickr Simon Osindero Flickr Published in IEEE Transactions on Knowledge and Data Engi- neering (Volume: PP, Issue: 99). Available at https://doi.org/10.1109/ TKDE.2017.2747552." 0628ffefb911d1446914098d7c38a094c92c8a70,An opportunistic prediction-based thread scheduling to maximize throughput/watt in AMPs,"An Opportunistic Prediction-based Thread Scheduling to Maximize Throughput/Watt in AMPs Arunachalam Annamalai, Rance Rodrigues, Israel Koren and Sandip Kundu Department of Electrical and Computer Engineering, University of Massachusetts at Amherst Email: {annamalai, rodrigues, koren," 0683be899f3e04b8b55a501e8ffafc0484b44056,Using Deep Learning and Low-Cost RGB and Thermal Cameras to Detect Pedestrians in Aerial Images Captured by Multirotor UAV,"Article Using Deep Learning and Low-Cost RGB and Thermal Cameras to Detect Pedestrians in Aerial Images Captured by Multirotor UAV Diulhio Candido de Oliveira * ID and Marco Aurelio Wehrmeister ID Computing Systems Engineering Laboratory (LESC), Federal University of Technology—Parana (UTFPR), Curitiba 80230-901, Brazil; * Correspondence: Tel.: +55-41-3310-4646 Received: 27 April 2018; Accepted: 3 July 2018; Published: 12 July 2018" 062c41dad67bb68fefd9ff0c5c4d296e796004dc,Temporal Generative Adversarial Nets with Singular Value Clipping,"Temporal Generative Adversarial Nets with Singular Value Clipping Masaki Saito∗ Eiichi Matsumoto∗ Preferred Networks inc., Japan {msaito, matsumoto, Shunta Saito" 0612745dbd292fc0a548a16d39cd73e127faedde,Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models,"Noname manuscript No. (will be inserted by the editor) Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models Bryan A. Plummer · Liwei Wang · Chris M. Cervantes · Juan C. Caicedo · Julia Hockenmaier · Svetlana Lazebnik Received: date / Accepted: date" 06f7e0aee7fc5807ab862432a4e5ade2cda73c4b,Flowing ConvNets for Human Pose Estimation in Videos,"Flowing ConvNets for Human Pose Estimation in Videos Tomas Pfister1, James Charles2 and Andrew Zisserman1 Objective & Contributions Estimate 2D upper body joint positions (wrist, elbow, shoulder, head) with high accuracy in real-time - A better ConvNet for general image (x,y) position regression - Spatial fusion layers that learn an implicit spatial model between predicted positions - Optical flow for propagating position predictions from neighbouring frames . Regress a heatmap for each position Heatmap ConvNet (fully convolutional) 56 x 256 x 3 64 x 64 x N . Represent positions by Gaussians k joints Idea 1: Implicit ConvNet spatial model . Add fusion layers to learn dependencies between predicted positions onv1 5x5x128 pool 2x2" 060732e29971e4598b2b086620f66671d520a349,Contactless Interaction for Automotive Applications,"Contactless Interaction for Automotive Applications Thomas Kopinski, Stefan Geisler, Uwe Handmann Computer Science Institute, Hochschule Ruhr West, University of Applied Sciences" 06f969d3858b6d14425fcbe7ff12b72e213ee240,: CARDIAC ACQUISITION PLANE RECOGNITION 1 Recognizing cardiac magnetic resonance acquisition planes,"Recognizing cardiac magnetic resonance acquisition planes Jan Margeta, Antonio Criminisi, Daniel C. Lee, Nicholas Ayache To cite this version: Jan Margeta, Antonio Criminisi, Daniel C. Lee, Nicholas Ayache. Recognizing cardiac magnetic resonance acquisition planes. MIUA - Medical Image Understanding and Analysis Conference - 2014, Jul 2014, London, United Kingdom. 2014. HAL Id: hal-01009952 https://hal.inria.fr/hal-01009952 Submitted on 19 Jun 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 06ef2ba33ec911aa0102fb938b53bd3cc36a475f,Introducing FoxFaces: A 3-in-1 Head Dataset, 066d71fcd997033dce4ca58df924397dfe0b5fd1,Iranian Face Database and Evaluation with a New Detection Algorithm,"(cid:1)(cid:2)(cid:3)(cid:4)(cid:5)(cid:3)(cid:4)(cid:6)(cid:7)(cid:3)(cid:8)(cid:9)(cid:6)(cid:10)(cid:3)(cid:11)(cid:3)(cid:12)(cid:3)(cid:13)(cid:9) (cid:3)(cid:4)(cid:14)(cid:6)(cid:15)(cid:16)(cid:3)(cid:17)(cid:18)(cid:3)(cid:11)(cid:5)(cid:19)(cid:4) (cid:20)(cid:5)(cid:11)(cid:21)(cid:6)(cid:3)(cid:6)(cid:22)(cid:9)(cid:20)(cid:6)(cid:10)(cid:9)(cid:11)(cid:9)(cid:8)(cid:11)(cid:5)(cid:19)(cid:4)(cid:6)(cid:23)(cid:17)(cid:24)(cid:19)(cid:2)(cid:5)(cid:11)(cid:21)(cid:25) (cid:26)(cid:11)(cid:5)(cid:8)(cid:17)(cid:6)(cid:27)(cid:1)(cid:9)(cid:22)(cid:8)(cid:18)(cid:1)(cid:28)(cid:12)(cid:6)(cid:29)(cid:4)(cid:20)(cid:11)(cid:6)(cid:24)(cid:30)(cid:1)(cid:15)(cid:25)(cid:1)(cid:31)(cid:8)(cid:20)(cid:8) (cid:14)(cid:1)!(cid:8) (cid:8)(cid:6)(cid:4)(cid:1)""(cid:16)(cid:8)(cid:16)(cid:20)(cid:14)(cid:1)(cid:3)(cid:15)(cid:8)(cid:22)(cid:4)(cid:12)(cid:1)(cid:23)(cid:5)(cid:29)(cid:18)(cid:14)(cid:1)(cid:31)(cid:8)(cid:20)(cid:8) (cid:14)(cid:1)(cid:26)!(cid:9)(cid:13)(cid:14)(cid:1)#(cid:17)(cid:8)(cid:6)(cid:5)$(cid:1)(cid:17)(cid:4)(cid:5)%(cid:8)(cid:10)(cid:8)(cid:11)(cid:6)(cid:8)(cid:12)&(cid:30)(cid:8)(cid:16)(cid:15)(cid:15)(cid:21)(cid:27)(cid:15)(cid:17) (cid:3)(cid:4)(cid:5)(cid:6)(cid:7)(cid:8)(cid:1)(cid:9)(cid:10)(cid:10)(cid:8)(cid:11)(cid:6)(cid:8)(cid:12)(cid:1)(cid:13)(cid:6)(cid:7)(cid:14) (cid:3)(cid:15)(cid:16)(cid:8)(cid:17)(cid:17)(cid:8)(cid:18)(cid:1)(cid:3)(cid:8)(cid:16)(cid:18)(cid:6)(cid:1)(cid:19)(cid:4)(cid:16)(cid:11)(cid:16)(cid:6)(cid:10)(cid:6)(cid:14)(cid:1)(cid:19)(cid:20)(cid:21)(cid:1)(cid:9)(cid:22)(cid:8)(cid:17)(cid:1)(cid:23)(cid:8)(cid:11)(cid:24)(cid:8)(cid:12)(cid:25)(cid:8)(cid:20)(cid:18) (cid:23)(cid:12)(cid:13)(cid:11)(cid:2)(cid:3)(cid:8)(cid:11)$(cid:1)’(cid:16)(cid:6)(cid:11) ((cid:8)((cid:4)(cid:20)(cid:1)(cid:6)(cid:12)(cid:24)(cid:20)(cid:15)(cid:18))(cid:27)(cid:4)(cid:11)(cid:1)(cid:8)(cid:1)(cid:18)(cid:8)(cid:24)(cid:8)(cid:10)(cid:8)(cid:11)(cid:4)(cid:1)(cid:15)(cid:25)(cid:1)(cid:15)(cid:29)(cid:4)(cid:20)(cid:1)*(cid:14)+,,(cid:1)(cid:27)(cid:15)(cid:5)(cid:15)(cid:20)(cid:1)(cid:6)(cid:17)(cid:8)-(cid:4)(cid:11)(cid:1).(cid:4)(cid:1)(cid:27)(cid:15)(cid:5)(cid:5)(cid:4)(cid:27)(cid:24)(cid:4)(cid:18)(cid:1)(cid:25)(cid:20)(cid:15)(cid:17)(cid:1)+(cid:2)+(cid:1)(cid:18)(cid:6)(cid:25)(cid:25)(cid:4)(cid:20)(cid:4)(cid:12)(cid:24)(cid:1)(cid:16))(cid:17)(cid:8)(cid:12)(cid:1)(cid:25)(cid:8)(cid:27)(cid:4)(cid:11) (cid:6)(cid:12)(cid:1)(cid:8)-(cid:4)(cid:11)(cid:1)(cid:10)(cid:4)(cid:24).(cid:4)(cid:4)(cid:12)(cid:1)/ (cid:8)(cid:12)(cid:18) 01(cid:21)(cid:1)2(cid:4)(cid:1)(cid:12)(cid:8)(cid:17)(cid:4)(cid:18)(cid:1)(cid:24)(cid:16)(cid:6)(cid:11)(cid:1)(cid:18)(cid:8)(cid:24)(cid:8)(cid:10)(cid:8)(cid:11)(cid:4)(cid:1)(cid:24)(cid:16)(cid:4)(cid:1)(cid:26)(cid:20)(cid:8)(cid:12)(cid:6)(cid:8)(cid:12)(cid:1)3(cid:8)(cid:27)(cid:4)(cid:1)(cid:19)(cid:8)(cid:24)(cid:8)(cid:10)(cid:8)(cid:11)(cid:4)(cid:1)4(cid:26)3(cid:19)(cid:23)5(cid:21)(cid:1)’(cid:15)(cid:1)(cid:4)(cid:29)(cid:8)(cid:5))(cid:8)(cid:24)(cid:4)(cid:1)(cid:24)(cid:16)(cid:4)(cid:1)(cid:18)(cid:8)(cid:24)(cid:8)(cid:10)(cid:8)(cid:11)(cid:4)(cid:1)(cid:24)(cid:16)(cid:4)(cid:1)(cid:4)6((cid:4)(cid:20)(cid:6)(cid:17)(cid:4)(cid:12)(cid:24)(cid:8)(cid:5)(cid:1)(cid:20)(cid:4)(cid:11))(cid:5)(cid:24)(cid:1)(cid:15)(cid:25)(cid:1)(cid:8)(cid:1)(cid:12)(cid:4).(cid:1)(cid:25)(cid:8)(cid:27)(cid:6)(cid:8)(cid:5)(cid:1) (cid:25)(cid:4)(cid:8)(cid:24))(cid:20)(cid:4)(cid:1)(cid:18)(cid:4)(cid:24)(cid:4)(cid:27)(cid:24)(cid:6)(cid:15)(cid:12)(cid:1)(cid:8)(cid:5)-(cid:15)(cid:20)(cid:6)(cid:24)(cid:16)(cid:17)(cid:1)(cid:6)(cid:11)(cid:1)(cid:20)(cid:4)((cid:15)(cid:20)(cid:24)(cid:4)(cid:18)(cid:21) (cid:26)(cid:9)(cid:27) (cid:28)(cid:19)(cid:2)(cid:14)(cid:13)$(cid:1)3(cid:8)(cid:27)(cid:4)(cid:1)(cid:26)(cid:17)(cid:8)-(cid:4)(cid:1)(cid:19)(cid:8)(cid:24)(cid:8)(cid:10)(cid:8)(cid:11)(cid:4)(cid:14)(cid:1)3(cid:8)(cid:27)(cid:6)(cid:8)(cid:5)(cid:1)3(cid:4)(cid:8)(cid:24))(cid:20)(cid:4)(cid:1)(cid:19)(cid:4)(cid:24)(cid:4)(cid:27)(cid:24)(cid:6)(cid:15)(cid:12)(cid:1)(cid:9)(cid:5)-(cid:15)(cid:20)(cid:6)(cid:24)(cid:16)(cid:17)(cid:11)(cid:14)(cid:1)(cid:9)-(cid:4)(cid:1)7(cid:5)(cid:8)(cid:11)(cid:11)(cid:6)(cid:25)(cid:6)(cid:27)(cid:8)(cid:24)(cid:6)(cid:15)(cid:12)(cid:21) (cid:29) (cid:1)(cid:4)(cid:11)(cid:2)(cid:19)(cid:14)(cid:18)(cid:8)(cid:11)(cid:5)(cid:19)(cid:4) 8)(cid:17)(cid:8)(cid:12)(cid:1) (cid:25)(cid:8)(cid:27)(cid:4)(cid:1) (cid:6)(cid:11)(cid:1) (cid:24)(cid:16)(cid:4)(cid:1) (cid:17)(cid:15)(cid:11)(cid:24)(cid:1) (cid:27)(cid:15)(cid:17)(cid:17)(cid:15)(cid:12)(cid:1) (cid:8)(cid:12)(cid:18)(cid:1) )(cid:11)(cid:4)(cid:25))(cid:5)(cid:1) (cid:7)(cid:4)(cid:30)(cid:1) (cid:24)(cid:15)(cid:1) (cid:8)(cid:1) ((cid:4)(cid:20)(cid:11)(cid:15)(cid:12)9(cid:11)(cid:1) (cid:6)(cid:18)(cid:4)(cid:12)(cid:24)(cid:6)(cid:24)(cid:30)(cid:21)(cid:1) (cid:9)(cid:11)(cid:1) (cid:16))(cid:17)(cid:8)(cid:12)(cid:11)(cid:14)(cid:1) .(cid:4)(cid:1) (cid:8)(cid:20)(cid:4)(cid:1) (cid:8)(cid:10)(cid:5)(cid:4)(cid:1) (cid:24)(cid:15)(cid:1) (cid:27)(cid:8)(cid:24)(cid:4)-(cid:15)(cid:20)(cid:6)(cid:22)(cid:4)(cid:1) (cid:8)(cid:1) ((cid:4)(cid:20)(cid:11)(cid:15)(cid:12):(cid:11)(cid:1)(cid:8)-(cid:4)(cid:1)-(cid:20)(cid:15))((cid:1)(cid:25)(cid:20)(cid:15)(cid:17)(cid:1)(cid:8)(cid:1)((cid:4)(cid:20)(cid:11)(cid:15)(cid:12):(cid:11)(cid:1)(cid:25)(cid:8)(cid:27)(cid:4)(cid:1)(cid:6)(cid:17)(cid:8)-(cid:4)(cid:1)(cid:8)(cid:12)(cid:18)(cid:1)(cid:8)(cid:20)(cid:4)(cid:1)(cid:15)(cid:25)(cid:24)(cid:4)(cid:12)(cid:1) (cid:8)(cid:10)(cid:5)(cid:4)(cid:1)(cid:24)(cid:15)(cid:1)(cid:10)(cid:4)(cid:1);)(cid:6)(cid:24)(cid:4)(cid:1)((cid:20)(cid:4)(cid:27)(cid:6)(cid:11)(cid:4)(cid:1)(cid:6)(cid:12)(cid:1)(cid:24)(cid:16)(cid:6)(cid:11)(cid:1)(cid:4)(cid:11)(cid:24)(cid:6)(cid:17)(cid:8)(cid:24)(cid:6)(cid:15)(cid:12)(cid:1)<(cid:2)=(cid:21)(cid:1)(cid:26)(cid:12)(cid:1)(cid:20)(cid:4)(cid:27)(cid:4)(cid:12)(cid:24)(cid:1)(cid:30)(cid:4)(cid:8)(cid:20)(cid:11)(cid:14)(cid:1) (cid:25)(cid:8)(cid:27)(cid:4)(cid:1) (cid:20)(cid:4)(cid:27)(cid:15)-(cid:12)(cid:6)(cid:24)(cid:6)(cid:15)(cid:12)(cid:1) (cid:8)(cid:12)(cid:18)(cid:1) (cid:20)(cid:4)(cid:5)(cid:8)(cid:24)(cid:4)(cid:18)(cid:1) .(cid:15)(cid:20)(cid:7)(cid:11)(cid:1) (cid:16)(cid:8)(cid:29)(cid:4)(cid:1) (cid:20)(cid:4)(cid:27)(cid:4)(cid:6)(cid:29)(cid:4)(cid:18)(cid:1) (cid:11))(cid:10)(cid:11)(cid:24)(cid:8)(cid:12)(cid:24)(cid:6)(cid:8)(cid:5)(cid:1) (cid:8)(cid:24)(cid:24)(cid:4)(cid:12)(cid:24)(cid:6)(cid:15)(cid:12)(cid:1) (cid:25)(cid:20)(cid:15)(cid:17)(cid:1) (cid:20)(cid:4)(cid:11)(cid:4)(cid:8)(cid:20)(cid:27)(cid:16)(cid:4)(cid:20)(cid:11)(cid:1) (cid:6)(cid:12)(cid:1) (cid:10)(cid:6)(cid:15)(cid:17)(cid:4)(cid:24)(cid:20)(cid:6)(cid:27)(cid:11)(cid:14)(cid:1) ((cid:8)(cid:24)(cid:24)(cid:4)(cid:20)(cid:12)(cid:1) (cid:20)(cid:4)(cid:27)(cid:15)-(cid:12)(cid:6)(cid:24)(cid:6)(cid:15)(cid:12)(cid:14)(cid:1) (cid:8)(cid:12)(cid:18)(cid:1) (cid:27)(cid:15)(cid:17)()(cid:24)(cid:4)(cid:20) (cid:29)(cid:6)(cid:11)(cid:6)(cid:15)(cid:12)(cid:1) (cid:27)(cid:15)(cid:17)(cid:17))(cid:12)(cid:6)(cid:24)(cid:6)(cid:4)(cid:11)(cid:1) (cid:8)(cid:12)(cid:18) 1=(cid:21)(cid:1) ’(cid:16)(cid:4)(cid:11)(cid:4)(cid:1) (cid:27)(cid:15)(cid:17)(cid:17)(cid:15)(cid:12)(cid:1)(cid:6)(cid:12)(cid:24)(cid:4)(cid:20)(cid:4)(cid:11)(cid:24)(cid:11)(cid:1)(cid:8)(cid:17)(cid:15)(cid:12)-(cid:1)(cid:20)(cid:4)(cid:11)(cid:4)(cid:8)(cid:20)(cid:27)(cid:16)(cid:4)(cid:20)(cid:11)(cid:1)(cid:17)(cid:15)(cid:24)(cid:6)(cid:29)(cid:8)(cid:24)(cid:4)(cid:18)(cid:1))(cid:11)(cid:1)(cid:24)(cid:15)(cid:1)(cid:27)(cid:15)(cid:5)(cid:5)(cid:4)(cid:27)(cid:24)(cid:1)(cid:8)(cid:1) (cid:18)(cid:8)(cid:24)(cid:8)(cid:10)(cid:8)(cid:11)(cid:4)(cid:1) (cid:15)(cid:25)(cid:1) (cid:25)(cid:8)(cid:27)(cid:6)(cid:8)(cid:5)(cid:1) (cid:6)(cid:17)(cid:8)-(cid:4)(cid:11)(cid:1) (cid:25)(cid:20)(cid:15)(cid:17)(cid:1) ((cid:4)(cid:15)((cid:5)(cid:4)(cid:1) (cid:6)(cid:12)(cid:1) (cid:18)(cid:6)(cid:25)(cid:25)(cid:4)(cid:20)(cid:4)(cid:12)(cid:24)(cid:1) (cid:8)-(cid:4)(cid:11)(cid:21) ’(cid:16)(cid:4)(cid:1) (cid:18)(cid:8)(cid:24)(cid:8)(cid:10)(cid:8)(cid:11)(cid:4)(cid:1)(cid:6)(cid:11)(cid:1)(cid:6)(cid:12)(cid:24)(cid:4)(cid:12)(cid:18)(cid:4)(cid:18)(cid:1)(cid:25)(cid:15)(cid:20)(cid:1)(cid:18)(cid:6)(cid:11)(cid:24)(cid:20)(cid:6)(cid:10))(cid:24)(cid:6)(cid:15)(cid:12)(cid:1)(cid:24)(cid:15)(cid:1)(cid:20)(cid:4)(cid:11)(cid:4)(cid:8)(cid:20)(cid:27)(cid:16)(cid:4)(cid:20)(cid:11)(cid:21) ’(cid:16)(cid:4)(cid:20)(cid:4)(cid:1) (cid:8)(cid:20)(cid:4)(cid:1) (cid:17)(cid:8)(cid:12)(cid:30)(cid:1) ()(cid:10)(cid:5)(cid:6)(cid:27)(cid:8)(cid:5)(cid:5)(cid:30)(cid:1) (cid:8)(cid:29)(cid:8)(cid:6)(cid:5)(cid:8)(cid:10)(cid:5)(cid:4)(cid:1) (cid:18)(cid:8)(cid:24)(cid:8)(cid:10)(cid:8)(cid:11)(cid:4)(cid:11)(cid:1) (cid:25)(cid:15)(cid:20)(cid:1) (cid:25)(cid:8)(cid:27)(cid:4)(cid:1)" 069f2092c5d22e6d4c1e27c30e18dc63848fa3c3,A comparison of low-level features for visual attribute recognition,"Görsel Nitelik Ö˘grenmede Alt-Düzey Özniteliklerin Kar¸sıla¸stırılması A Comparison of Low-level Features for Visual Attribute Recognition Emine Gül DANACI Bilgisayar Mühendisli˘gi Bölümü Hacettepe Üniversitesi Ankara, Türkiye Nazlı ˙IK˙IZLER C˙INB˙I¸S Bilgisayar Mühendisli˘gi Bölümü Hacettepe Üniversitesi Ankara, Türkiye Özetçe —Görsel nitelik ö˘grenme ve kullanımı, son yıllarda ilgisayarlı görü alanında sıklıkla ara¸stırılmaya ba¸slanmı¸s bir konudur. Bu çalı¸smamızda, görsel nitelik ö˘grenmeye, hangi alt düzey özniteliklerin daha anlamlı ve verimli sonuçlar verdi˘gini ra¸stırmayı amaçlamaktayız. Bu kapsamda, renk ve ¸sekil bil- gisini farklı detaylarda ele alan alt düzey özniteliklerin, nitelik sınıflandırmaya katkısı ara¸stırılmı¸s, ve deneysel olarak de˘ger- lendirilmi¸stir. Elde edilen sonuçlar, özellikle renk ve yerel ¸sekil" 06f146dfcde10915d6284981b6b84b85da75acd4,Scalable Face Image Retrieval Using Attribute-Enhanced Sparse Codewords,"Scalable Face Image Retrieval using Attribute-Enhanced Sparse Codewords Bor-Chun Chen, Yan-Ying Chen, Yin-Hsi Kuo, Winston H. Hsu" 06bd34951305d9f36eb29cf4532b25272da0e677,"A Fast and Accurate System for Face Detection, Identification, and Verification","JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 A Fast and Accurate System for Face Detection, Identification, and Verification Rajeev Ranjan, Ankan Bansal, Jingxiao Zheng, Hongyu Xu, Joshua Gleason, Boyu Lu, Anirudh Nanduri, Jun-Cheng Chen, Carlos D. Castillo, Rama Chellappa" 069cadd9d8e52ad2715a3551012a06e506191626,Person re-identification using semantic color names and RankBoost,"Person Re-identification using Semantic Color Names and RankBoost Cheng-Hao Kuo1, Sameh Khamis2∗, and Vinay Shet1 Imaging and Computer Vision, Siemens Corporation, Corporate Technology1, Princeton, NJ University of Maryland2, College Park, MD" 064b797aa1da2000640e437cacb97256444dee82,Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression,"Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression Zhiao Huang Megvii Inc. Erjin Zhou Megvii Inc. Zhimin Cao Megvii Inc." 4b9b39bbdac95e24773789f1bb543149116cdc37,Region-Of-Interest Retrieval in Brain MR Images,"Technical Note PR-TN 2008/00905 Issued: 12/2008 Region-Of-Interest Retrieval in Brain MR Images D. Unay; A. Ekin Philips Research Europe Unclassified  Koninklijke Philips Electronics N.V. 2008" 4b4106614c1d553365bad75d7866bff0de6056ed,Unconstrained Facial Images: Database for Face Recognition Under Real-World Conditions,"Unconstrained Facial Images: Database for Face Recognition under Real-world Conditions⋆ Ladislav Lenc1,2 and Pavel Kr´al1,2 Dept. of Computer Science & Engineering University of West Bohemia Plzeˇn, Czech Republic NTIS - New Technologies for the Information Society University of West Bohemia Plzeˇn, Czech Republic" 4be03fd3a76b07125cd39777a6875ee59d9889bd,Content-based analysis for accessing audiovisual archives: Alternatives for concept-based indexing and search,"CONTENT-BASED ANALYSIS FOR ACCESSING AUDIOVISUAL ARCHIVES: ALTERNATIVES FOR CONCEPT-BASED INDEXING AND SEARCH Tinne Tuytelaars ESAT/PSI - IBBT KU Leuven, Belgium" 4b60e45b6803e2e155f25a2270a28be9f8bec130,Attribute based object identification,"Attribute Based Object Identification Yuyin Sun, Liefeng Bo and Dieter Fox" 4bb83b00e7b8eb27ad04d4bb80499e91fc471a07,Emotion related structures in large image databases,"Emotion Related Structures in Large Image Databases Martin Solli ITN, Linköping University SE-60174 Norrköping, Sweden Reiner Lenz ITN, Linköping University SE-60174 Norrköping, Sweden" 4b6ea82fa73d2137c884ad43f7865d88b24ff01d,How deep should be the depth of convolutional neural networks: a backyard dog case study,"How deep should be the depth of convolutional neural networks: a backyard dog case study Alexander N. Gorban, Evgeny M. Mirkes, Ivan Y. Tukin University of Leicester, Leicester LE1 7RH, UK" 4b6eb9117c1b7833c8c6b95ecad427f8f994f023,Robust Depth-Based Person Re-Identification,"Robust Depth-based Person Re-identification Ancong Wu, Wei-Shi Zheng, Jian-Huang Lai Code is available at the project page: http://isee.sysu.edu.cn/∼wuancong/ProjectDepthReID.htm For reference of this work, please cite: Ancong Wu, Wei-Shi Zheng, Person Re-identification. (DOI:10.1109/TIP.2017.2675201) Jian-Huang Lai. Robust Depth-based title={Robust Depth-based Person Re-identification}, uthor={Wu, Ancong and Zheng, Wei-Shi and Lai, Jianhuang}, (DOI:10.1109/TIP.2017.2675201)}, year={2017}" 4baf3b165489122a1f8b574240c2a7fa9b6a7a14,Composite Statistical Inference for Semantic Segmentation,"Composite Statistical Inference for Semantic Segmentation Fuxin Li(1), Joao Carreira(2), Guy Lebanon(1), Cristian Sminchisescu(3) (1) Georgia Institute of Technology. (2) ISR - University of Coimbra. (3) Lund University" 4b9374da18cbb300d943ddd7b43bbdc189b96778,IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments,"IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments Girish Varma1 Anbumani Subramanian2 Anoop Namboodiri1 IIIT Hyderabad" 4b7dc1e99b0b34022aec2bde1a13481f28f62030,Person Re-Identification Based on Weighted Indexing Structures,"Person Re-Identification based on Weighted Indexing Structures Cristianne R. S. Dutra, Matheus Castro Rocha, and William Robson Schwartz Department of Computer Science, Universidade Federal de Minas Gerais Belo Horizonte, Minas Gerais, Brazil, 31270-901 rocha" 4b04247c7f22410681b6aab053d9655cf7f3f888,Robust Face Recognition by Constrained Part-based Alignment,"Robust Face Recognition by Constrained Part-based Alignment Yuting Zhang, Kui Jia, Yueming Wang, Gang Pan, Tsung-Han Chan, Yi Ma" 4b57456642e1d21f2bda05aea586b7f419d309ce,Disposable Ties and the Urban Poor Author ( s ) :,"Disposable Ties and the Urban Poor Author(s): Matthew Desmond Reviewed work(s): Source: American Journal of Sociology, Vol. 117, No. 5 (March 2012), pp. 1295-1335 Published by: The University of Chicago Press Stable URL: http://www.jstor.org/stable/10.1086/663574 . Accessed: 17/08/2012 17:34 Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at . http://www.jstor.org/page/info/about/policies/terms.jsp JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of ontent in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact The University of Chicago Press is collaborating with JSTOR to digitize, preserve and extend access to American Journal of Sociology. http://www.jstor.org" 4b89cf7197922ee9418ae93896586c990e0d2867,Unsupervised Discovery of Action Classes,"LATEX Author Guidelines for CVPR Proceedings First Author Institution1 Institution1 address" 4ba8be7f84b5eb9cf2078e5503b9ca55f5902add,Kinship Verification Using Facial Images by Robust Similarity Learning,"Publishing CorporationMathematical Problems in EngineeringVolume 2016, Article ID 4072323, 8 pageshttp://dx.doi.org/10.1155/2016/4072323" 4b7d5b17c0daa35f682417c32e80022c6645dc7f,Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery,"Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery Gencer Sumbul, Ramazan Gokberk Cinbis, and Selim Aksoy, Senior Member, IEEE learning (ZSL)" 4b4a174f46ce03caf1ffa4addd074aaa70539f35,BlazeIt: Fast Exploratory Video Queries using Neural Networks.,"Fast Exploratory Video Queries using Neural Networks BlazeIt: Daniel Kang, Peter Bailis, Matei Zaharia Stanford InfoLab" 4bc67489bbe634271f8fde73a851d7a59946ed36,Wide area motion capture using an array of consumer grade structured light depthsensors,"Mälardalen University School of Innovation, Design and Engineering Bachelor thesis in Computer science Wide area motion capture using an array of onsumer grade structured light depth sensors Author: Karl Arvidsson Supervisor: Afshin Ameri Examiner: Baran Çürüklü October 20, 2015" 4b69bbb6dc2959ea3d2e911ed45c6298dc531490,Deep Mixture of Experts via Shallow Embedding,"TAFE-Net: Task-Aware Feature Embeddings for Efficient Learning and Inference Xin Wang Fisher Yu Ruth Wang Trevor Darrell EECS Department, UC Berkeley Joseph E. Gonzalez" 4b8ecd100d6640fd7659be2715c86b7a9103240b,Quis-Campi: Extending in the Wild Biometric Recognition to Surveillance Environments,"Quis-Campi : Extending in the Wild Biometric Recognition to Surveillance Environments Jo˜ao C. Neves1, Gil Santos1(B), S´ılvio Filipe1, Emanuel Grancho1, Silvio Barra2, Fabio Narducci3, and Hugo Proen¸ca1 Department of Computer Science, IT - Instituto de Telecomunica¸c˜oes, University of Beira Interior, Covilh˜a, Portugal DMI - Dipartimento di Matematica e Informatica, University of Cagliari, Cagliary, Italy DISTRA-MIT, University of Salerno, Fisciano, Salerno, Italy" 4b8ce1bfedb285d8d609d1059dd0183420d63671,Transductive Multi-View Zero-Shot Learning,"Transductive Multi-view Zero-Shot Learning Yanwei Fu, Timothy M. Hospedales, Tao Xiang and Shaogang Gong" 4b90f2e4f421dd9198d4c52cd3371643acddf1f9,Detecting planar surface using a light-field camera with application to distinguishing real scenes from printed photos,"014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) 978-1-4799-2893-4/14/$31.00 ©2014 IEEE ´Ecole Polytechnique F´ed´erale de Lausanne School of Computer and Communication Sciences AudioVisual Communications Laboratory . INTRODUCTION Alireza Ghasemi Martin Vetterli" 4b5dd0a1b866f928734bc36afd597adca20a7ec1,Detector ensembles for face recognition in video surveillance,"Detector Ensembles for Face Recognition in Video Surveillance Christophe Pagano, Eric Granger, Robert Sabourin and Dmitry O. Gorodnichy" 4b726a43e201f320b906e1f155aa27c32d43bbc6,Simultaneous Object Classification and Viewpoint Estimation using Deep Multi-task Convolutional Neural Network, 4b3c5b49fa099a77c98bad4b5299c6b4eb0a8f2e,Learning Deep Features for Discriminative Localization,"Learning Deep Features for Discriminative Localization Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Computer Science and Artificial Intelligence Laboratory, MIT" 4bde15a51413fafa04193e72c15e132e7716d8a6,Performance Study of Fusion in Multimodal Biometric Verification using Ear and Iris Features,"International Conference on Research Trends in Computer Technologies (ICRTCT - 2013) Proceedings published in International Journal of Computer Applications® (IJCA) (0975 – 8887) Performance Study of Fusion in Multimodal Biometric Verification using Ear and Iris Features Poornima.S Department of IT, SSN College of Engineering Chennai, India." 4b29795faf4bbd5a623bb74d39ac1561ace9828d,Combining Classifiers for Improved Multilabel Image Classification,"Combining Classifiers for Improved Multilabel Image Classification Martin Antenreiter, Ronald Ortner, and Peter Auer University of Leoben, A-8700 Leoben, Austria" 4b0893bf71e4e13529cefb286c78b166a9491552,Estimating orientation in tracking individuals of flying swarms,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 4b1cdb96a39cf23139a21915ba9e3e0692de8563,Bridging the Gap Between Computational Photography and Visual Recognition,"Bridging the Gap Between Computational Photography and Visual Recognition Rosaura G. VidalMata*, Sreya Banerjee*, Brandon RichardWebster, Michael Albright, Pedro Davalos, Scott McCloskey, Ben Miller, Asong Tambo, Sushobhan Ghosh, Sudarshan Nagesh, Ye Yuan, Yueyu Hu, Junru Wu, Wenhan Yang, Xiaoshuai Zhang, Jiaying Liu, Zhangyang Wang, Hwann-Tzong Chen, Tzu-Wei Huang, Wen-Chi Chin, Yi-Chun Li, Mahmoud Lababidi, Charles Otto, and Walter J. Scheirer" 4be63e7891180e28085d03bb992abbc5104ac446,Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers,"Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers Jiaolong Xu1, David V´azquez1, Sebastian Ramos1, Antonio M. L´opez1,2 and Daniel Ponsa1,2 Computer Vision Center Dept. of Computer Science Autonomous University of Barcelona 08193 Bellaterra, Barcelona, Spain {jiaolong, dvazquez, sramosp, antonio," 4b2ce7064eeb014a480255c29bf147a441b3fa3f,Finding people in home environments with a mobile robot,"Finding People in Home Environments with a Mobile Robot Michael Volkhardt and Horst-Michael Gross1" 4b4763303a15a4c6313bfb386756437f394a0129,Explicit Inductive Bias for Transfer Learning with Convolutional Networks,"Explicit Inductive Bias for Transfer Learning with Convolutional Networks Xuhong LI 1 Yves GRANDVALET 1 Franck DAVOINE 1" 4b37efd3987c1e625b063a6998bd6b282c844915,End-to-end Convolutional Network for Saliency Prediction,"End-to-end Convolutional Network for Saliency Prediction Junting Pan and Xavier Gir´o-i-Nieto Universitat Politecnica de Catalunya (UPC) Barcelona, Catalonia/Spain" 4ba503d8f173880d8e8402808f54b78b653e5d20,Accelerating Stochastic Gradient Descent via Online Learning to Sample,"Accelerating Stochastic Gradient Descent via Online Learning to Sample Guillaume Bouchard Xerox Research Center Europe Th´eo Trouillon Xerox Research Center Europe University of Grenoble - LIG Julien Perez Xerox Research Center Europe Adrien Gaidon Xerox Research Center Europe" 4b5eeea5dd8bd69331bd4bd4c66098b125888dea,Human Activity Recognition Using Conditional Random Fields and Privileged Information,"Human Activity Recognition Using Conditional Random Fields and Privileged Information DOCTORAL THESIS submitted to the designated by the General Assembly Composition of the Department of Computer Science & Engineering Inquiry Committee Michalis Vrigkas in partial fulfillment of the Requirements for the Degree of DOCTOR OF PHILOSOPHY February 2016" 4bfdbe2ffc6311c8a297355422d914cb666b358a,"On Boosting, Tug of War, and Lexicographic Programming","On Boosting, Tug of War, and Lexicographic Programming Shounak Datta, Sayak Nag, and Swagatam Das, Senior Member, IEEE" 4be10db13a9210e078d78a4a072c569d9bbd9939,"Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation","Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation Alexander Kolesnikov and Christoph H. Lampert IST Austria" 4ba1cf65eb86aba729192d2f0fe2cd064ac346cf,One-shot person re-identification with a consumer depth camera,"One-Shot Person Re-Identification with a Consumer Depth Camera Matteo Munaro, Andrea Fossati, Alberto Basso, Emanuele Menegatti and Luc Van" 4b042eb64ddb8991c0e63fff02b1c51c378a8f58,Leveraging Massive User Contributions for Knowledge Extraction,"Chapter 16 Leveraging Massive User Contributions for Knowledge Extraction Spiros Nikolopoulos, Elisavet Chatzilari, Eirini Giannakidou, Symeon Papadopoulos, Ioannis Kompatsiaris, and Athena Vakali" 81d5c4b49fe17aaa3af837745cafdedb066a067d,Automatic Adaptive Center of Pupil Detection Using Face Detection and CDF Analysis,"Automatic Adaptive Center of Pupil Detection Using Face Detection and CDF Analysis Mansour Asadifard, Jamshid Shanbezadeh" 819ff65fc6bdc9c4aea53b14e1431796c1b1d3d1,A voting method for stereo egomotion estimation,"Research Article A voting method for stereo egomotion estimation International Journal of Advanced Robotic Systems May-June 2017: 1–16 ª The Author(s) 2017 DOI: 10.1177/1729881417710795 journals.sagepub.com/home/arx Hugo Silva1, Alexandre Bernardino2 and Eduardo Silva1 image blur, pixel noise," 811dff89b6d4657e5a0b8534e208baefd2204cee,Pseudo-Feature Generation for Imbalanced Data Analysis in Deep Learning,"Pseudo-Feature Generation for Imbalanced Data Analysis in Deep Learning Tomohiko Konno∗ and Michiaki Iwazume AI Science Research and Development Promotion Center National Institute of Information and Communications Technology, Tokyo Japan Figure 1: The sketch of proposed method. Left: train deep neural networks. Center: extract features from a layer, and then obtain multivariate probability distributions of the features, and then generate pseudo-features of minority classes from the probability distributions, and then re-train the layers elow the layer. Right: Put the retrained layers back to the original one. (It is the last classifier that is re-trained and put back in the experiment.)" 8149c30a86e1a7db4b11965fe209fe0b75446a8c,Semi-supervised multiple instance learning based domain adaptation for object detection,"Semi-Supervised Multiple Instance Learning based Domain Adaptation for Object Detection Siemens Corporate Research Siemens Corporate Research Siemens Corporate Research Amit Kale Bangalore Chhaya Methani Bangalore {chhaya.methani, Rahul Thota Bangalore rahul.thota," 81eb9fca9093f58eabb8850512f8f46fe2bb07a2,Sem-GAN: Semantically-Consistent Image-to-Image Translation,"Sem-GAN: Semantically-Consistent Image-to-Image Translation Anoop Cherian Alan Sullivan Mitsubishi Electric Research Labs (MERL), Cambridge, MA {cherian," 81a51cd6ecd467abb1ef38c8e35bdf1885f96fe3,Deep Spatio-Temporal Random Fields for Efficient Video Segmentation,"Deep Spatio-Temporal Random Fields for Efficient Video Segmentation Siddhartha Chandra1 Camille Couprie2 INRIA GALEN, Ecole CentraleSup´elec Paris Iasonas Kokkinos2 Facebook AI Research, Paris" 81ff6d7f934f7134d93b2039d788b72f8593693c,Accelerating Convolutional Neural Network Systems,"Accelerating Convolutional Neural Network Systems Henry G.R. Gouk This report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Computing and Mathematical Sciences with Honours (BCMS(Hons)) t The University of Waikato. COMP520-14C (HAM) © 2014 Henry G.R. Gouk" 81c3d1be0c69e9d3e13054969e4b67ee69a4e6f0,Dynamical Models for Neonatal Intensive Care Monitoring,"This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e.g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use: This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author. The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author. When referring to this work, full bibliographic details including the author, title, warding institution and date of the thesis must be given." 810eafc9e854ea9b1d7a9e9f755f8102310d5db6,Dynamic Multimodal Instance Segmentation Guided by Natural Language Queries,"Dynamic Multimodal Instance Segmentation Guided by Natural Language Queries Edgar Margffoy-Tuay, Juan C. P´erez, Emilio Botero, and Pablo Arbel´aez {ea.margffoy10, jc.perez13, e.botero10, Universidad de los Andes, Colombia" 816c8c8d0f02200f988625d4989a1b4b34d779c6,An Efficient Hybrid Face Recognition Algorithm Using PCA and GABOR Wavelets Regular Paper, 81695fbbbea2972d7ab1bfb1f3a6a0dbd3475c0f,Comparison of Face Recognition Neural Networks,"UNIVERSITY OF TARTU FACULTY OF SCIENCE AND TECHNOLOGY Institute of Computer Science Computer Science Zepp Uibo Comparison of Face Recognition Neural Networks Bachelor's thesis (6 ECST) Supervisor: Tambet Matiisen Tartu 2016" 81a142c751bf0b23315fb6717bc467aa4fdfbc92,Pairwise Trajectory Representation for Action Recognition,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" 81b337f2006cd6c8d5fd148a56cab3e5a662d40d,Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings,"Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings Stefano Pellegrini 1, Andreas Ess 1, and Luc Van Gool 1,2 Computer Vision Laboratory ESAT-PSI / IBBT ETH Zurich KU Leuven" 816c1925de9e8557fa70ec67d0ff71a5059eb931,Person Re-identification by Articulated Appearance Matching,"Person Re-identification by Articulated Appearance Matching Dong Seon Cheng and Marco Cristani" 815b9ac1cc300187f649b2b65f6e34eb7a35d2e4,Visual Object Recognition with 3D-Aware Features in KITTI Urban Scenes,"Sensors 2015, 15, 9228-9250; doi:10.3390/s150409228 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article Visual Object Recognition with 3D-Aware Features in KITTI Urban Scenes J. Javier Yebes *, Luis M. Bergasa and Miguel Ángel García-Garrido Department of Electronics, University of Alcalá, Alcalá de Henares 28871, Spain; E-Mails: (L.M.B.), (M.Á.G.-G) * Author to whom correspondence should be addressed; E-Mail: Tel.: +34-918-856-807; Fax: +34-918-856-591. Academic Editor: Felipe Jimenez Received: 9 March 2015 / Accepted: 14 April 2015 / Published: 20 April 2015" 81bfe562e42f2eab3ae117c46c2e07b3d142dade,A Hajj And Umrah Location Classification System For Video Crowded Scenes,"A Hajj And Umrah Location Classification System For Video Crowded Scenes Hossam M. Zawbaa† Salah A. Aly†‡ Adnan A. Gutub† Center of Research Excellence in Hajj and Umrah, Umm Al-Qura University, Makkah, KSA College of Computers and Information Systems, Umm Al-Qura University, Makkah, KSA" 81d327ec41c67728b15438bca86d10b72de1d88f,Visual Affordance and Function Understanding: A Survey,"JOURNAL OF LATEX CLASS FILES, VOL. 6, NO. 1, JULY 2018 Visual Affordance and Function Understanding: A Survey Mohammed Hassanin, Salman Khan, Murat Tahtali" 81cb69e401b3b51e49ec378dba4bc0c8e33448e1,Applying Domain Randomization to Synthetic Data for Object Category Detection,"Applying Domain Randomization to Synthetic Data for Object Category Detection Jo˜ao Borrego(cid:63), Atabak Dehban(cid:63), Rui Figueiredo, Plinio Moreno, Alexandre Bernardino, and Jos´e Santos-Victor {jborrego,adehban,ruifigueiredo,plinio,alex,jasv} Instituto Superior T´ecnico" 814d091c973ff6033a83d4e44ab3b6a88cc1cb66,The EU-Emotion Stimulus Set: A validation study.,"Behav Res (2016) 48:567–576 DOI 10.3758/s13428-015-0601-4 The EU-Emotion Stimulus Set: A validation study Helen O’Reilly 1,2 & Delia Pigat 1 & Shimrit Fridenson 5 & Steve Berggren 3,4 & Shahar Tal 5 & Ofer Golan 5 & Sven Bölte 3,4 & Simon Baron-Cohen 1,6 & Daniel Lundqvist 3 Published online: 30 September 2015 # Psychonomic Society, Inc. 2015" 81ed28ea6cfe71bfc4cfc35c6695fa07dd7cc42e,"Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution","Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution Jonas Rothfuss∗†, Fabio Ferreira∗†, Eren Erdal Aksoy ‡, You Zhou† and Tamim Asfour†" 812725dc3968aaff6429ec7c3f44ba1ca2116013,Acoplamiento de micro multitudes para el desarrollo de videojuegos controlados por movimiento,"Acoplamiento de micro multitudes para el desarrollo de videojuegos ontrolados por movimiento Iv´an Rivalcoba1, Krely Rodr´ıguez2, Oriam Degives1, Isaac Rudom´ın3 Tecnol´ogico de Monterrey, Campus Estado de M´exico, M´exico Tecnol´ogico de Minatitl´an, Minatitl´an, Veracruz, M´exico Barcelona Supercomputing Center Barcelona, Espa˜na Resumen. La simulaci´on de multitudes en tiempo real y los juegos controlados por movimiento se han vuelto muy populares en los ´ultimos a˜nos. En conjunto estas dos tecnolog´ıas proporcionan una mejor experiencia de juego en entornos virtuales logrando escenas m´as realistas y vibrantes. Sin embargo, hasta ahora no se ha explotado la interacci´on de m´ultiples jugadores con una gran multitud bajo un entorno virtual. En este trabajo presentamos un sistema no intrusivo capaz de simular multitudes virtuales acopladas en tiempo real con varios usuarios, sentando con ello las bases para la creaci´on de juegos donde interact´uen muchos jugadores con muchas personajes, para ello se realiza una detecci´on de personas en una secuencia de v´ıdeo, nuestra contribuci´on consiste en utilizar patrones" 81e628a23e434762b1208045919af48dceb6c4d2,Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery,"Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery Pau Rodr´ıguez†, Josep M. Gonfaus‡, Guillem Cucurull†, F. Xavier Roca†, Jordi Gonz`alez† Computer Vision Center and Universitat Aut`onoma de Barcelona (UAB), Campus UAB, 08193 Bellaterra, Catalonia Spain Visual Tagging Services, Parc de Recerca, Campus UAB" 810d60ff5c0106de53a48fa2731eacf5ca2377b6,MultiQ: single sensor-based multi-quality multi-modal large-scale biometric score database and its performance evaluation,"Uddin et al. IPSJ Transactions on Computer Vision and Applications (2017) 9:18 DOI 10.1186/s41074-017-0029-0 IPSJ Transactions on Computer Vision and Applications TECHNICAL NOTE Open Access MultiQ: single sensor-based multi-quality multi-modal large-scale biometric score database and its performance evaluation Md. Zasim Uddin*, Daigo Muramatsu, Takuhiro Kimura, Yasushi Makihara and Yasushi Yagi" 812d3f6975f4cb87e9905ef18696c5c779227634,A novel comparative deep learning framework for facial age estimation,"Abousaleh et al. EURASIP Journal on Image and Video Processing (2016) 2016:47 DOI 10.1186/s13640-016-0151-4 EURASIP Journal on Image nd Video Processing RESEARCH Open Access A novel comparative deep learning framework for facial age estimation Fatma S. Abousaleh1,2,3†, Tekoing Lim2†, Wen-Huang Cheng2, Neng-Hao Yu3*, M. Anwar Hossain4 nd Mohammed F. Alhamid4" 81f30bc57b84a6e5b71983b50bdea32f32bee285,"The more fine-grained, the better for transfer learning","The more fine-grained, the better for transfer learning Anonymous Author(s) Affiliation Address email" 81fc46dd71121cfafbb11455745ae62f6eca0b25,Joint Camera Pose Estimation and 3D Human Pose Estimation in a Multi-camera Setup,"Joint Camera Pose Estimation and 3D Human Pose Estimation in a Multi-Camera Setup Jens Puwein1, Luca Ballan1, Remo Ziegler2 and Marc Pollefeys1 Department of Computer Science, ETH Zurich, Switzerland Vizrt" 81782b19656cd70fccc7cccab57db3967db8ad67,"OBJECT CLASSIFICATION VIA GEOMETRICAL , ZERNIKE AND LEGENDRE MOMENTS","Journal of Theoretical and Applied Information Technology © 2005 - 2009 JATIT. All rights reserved. www.jatit.org OBJECT CLASSIFICATION VIA GEOMETRICAL, ZERNIKE AND LEGENDRE MOMENTS THAWAR ARIF, ZYAD SHAABAN, LALA KREKOR, SAMI BABA Faculty of Information Technology, Applied Science University, Amman 11931, Jordan E-mail:" 81eb804756f27d08f2d193d1074e58e1c5d263ca,Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision,"Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision Dushyant Mehta*, Helge Rhodin*, Dan Casass, Oleksandr Sotnychenko*, Weipeng Xu*, and Christian Theobalt* *Max Planck Institute For Informatics, Saarland Informatics Campus, Germany sUniversidad Rey Juan Carlos, Spain" 815069f591122aa7b388615f944c17c7fa1eff14,Constrained Overcomplete Analysis Operator Learning for Cosparse Signal Modelling,"Constrained Overcomplete Analysis Operator Learning for Cosparse Signal Modelling Mehrdad Yaghoobi, Sangnam Nam, R´emi Gribonval and Mike E. Davies" 816eff5e92a6326a8ab50c4c50450a6d02047b5e,Fast Low-Rank Representation Using Frobenius,"fLRR: Fast Low-Rank Representation Using Frobenius Norm Haixian Zhang, Zhang Yi, and Xi Peng Low Rank Representation (LRR) intends to find the representation with lowest-rank of a given data set, which can be formulated as a rank minimization problem. Since the rank operator is non-convex and discontinuous, most of the recent works use the nuclear norm as a convex relaxation. This letter theoretically shows that under some conditions, Frobenius-norm-based optimization problem has an unique solution that is also a solution of the original LRR optimization problem. In other words, it is feasible to apply Frobenius-norm as a surrogate of the nonconvex matrix rank function. This replacement will largely reduce the time-costs for obtaining the lowest-rank solution. Experimental results show that our method (i.e., fast Low Rank Representation, fLRR), performs well in terms of accuracy and computation speed in image lustering and motion segmentation compared with nuclear-norm-based LRR algorithm. Introduction: Given a data set X ∈ Rm×n(m < n) composed of column vectors, let A be a data set composed of vectors with the same dimension s those in X. Both X and A can be considered as matrices. A linear" 81b6de17391f44c07b2efe75a529aa200604ee48,Machine à Vecteurs Supports Multi-Noyau pour la détection de points caractéristiques du visage,"Machine à Vecteurs Supports Multi-Noyau pour la détection de points aractéristiques du visage Vincent Rapp1, Thibaud Senechal1, Kevin Bailly1, Lionel Prevost2 ISIR - CNRS UMR 7222 Université Pierre et Marie Curie, Paris LAMIA - EA 4540 Université des Antilles et de la Guyanne {rapp, senechal, Résumé Dans cet article, nous présentons une méthode robuste et précise pour détecter 17 points caractéristiques du vi- sage sur des images expressives. Une nouvelle architecture multi-résolution basée sur les récents algorithmes multi- noyau est introduite. Les patches de faibles résolutions odent les informations globales du visage donnant lieu à une détection grossière mais robuste du point désiré. Les patches de grandes résolutions quant à eux utilisent les dé- tails locaux afin d’affiner cette localisation. En combinant une détection indépendante de points et des informations priori sur les distributions de points, nous proposons" 819d1dcea397e6e671acf74adccdef5750550873,Representations for Visually Guided Actions,"Representations for Visually Guided Actions Saurabh Gupta Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2018-104 http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-104.html August 8, 2018" 81c03eda1d175fbe351980ac4cffe42c5dec47b0,User observation & dataset collection for robot training,"User Observation & Dataset Collection for Robot Training Caroline Pantofaru Willow Garage, Inc. Menlo Park, CA 94025 Categories and Subject Descriptors: I.5.2 [Comput- ing Methodologies]: Pattern Recognition - Design Method- ology, H.1.2 [Information Systems]: Models and Principles - User/Machine Systems General Terms: Measurement INTRODUCTION Personal robots operate in human environments such as homes and of‌f‌ices, co-habiting with people. To effectively train robot algorithms for such scenarios, a large amount of training data containing both people and the environment is required. Collecting such data involves taking a robot into new environments, observing and interacting with people. So far, best practices for robot data collection have been undefined. Fortunately, the human-robot interaction com- munity has conducted field studies whose methodology can" 812a6ced985317b3b9429ef0455645a9744af6d1,No need for a social cue! A masked magician can also trick the audience in the vanishing ball illusion.,"Atten Percept Psychophys DOI 10.3758/s13414-015-1036-9 No need for a social cue! A masked magician can also trick the audience in the vanishing ball illusion Cyril Thomas 1 & André Didierjean 1 # The Psychonomic Society, Inc. 2015" 8199803f476c12c7f6c0124d55d156b5d91314b6,The iNaturalist Species Classification and Detection Dataset,"The iNaturalist Species Classification and Detection Dataset Grant Van Horn1 Oisin Mac Aodha1 Yang Song2 Yin Cui3 Chen Sun2 Alex Shepard4 Hartwig Adam2 Pietro Perona1 Serge Belongie3 Caltech Google Cornell Tech iNaturalist" 816617fa6801fb2abd3d4475c459bf6e3221954d,3D human detection and tracking on a mobile platform for situation awareness,"D Human Detection and Tracking on a Mobile Platform for Situation Awareness Niklas Beuter" 81ea29bde0216e41420c4591bebb800142fa3269,Learning Active Learning from Data,"Learning Active Learning from Data Ksenia Konyushkova Raphael Sznitman University of Bern Pascal Fua" 81b2a541d6c42679e946a5281b4b9dc603bc171c,Semi-supervised learning with committees: exploiting unlabeled data using ensemble learning algorithms,"Universit¨at Ulm | 89069 Ulm | Deutschland Fakult¨at f¨ur Ingenieurwissenschaften und Informatik Institut f¨ur Neuroinformatik Direktor: Prof. Dr. G¨unther Palm Semi-Supervised Learning with Committees: Exploiting Unlabeled Data Using Ensemble Learning Algorithms Dissertation zur Erlangung des Doktorgrades Doktor der Naturwissenschaften (Dr. rer. nat.) der Fakult¨at f¨ur Ingenieurwissenschaften und Informatik der Universit¨at Ulm vorgelegt von Mohamed Farouk Abdel Hady us Kairo, ¨Agypten Ulm, Deutschland" 81006fe4c4947d225b9fa17e6b98b8acb36a7692,A Dataset for Grasping and Manipulation using ROS,"A Dataset for Grasping and Manipulation using ROS Matei Ciocarlie†, Gary Bradski†, Kaijen Hsiao† and Peter Brook†∗" 8134b052a9aedd573dd16649a611f68b48e30cb2,InverseFaceNet: Deep Monocular Inverse Face Rendering,"InverseFaceNet: Deep Single-Shot Inverse Face Rendering From A Single Image Hyeongwoo Kim1 Justus Thies2 Max-Planck-Institute for Informatics Michael Zollhöfer1 Christian Richardt3 University of Erlangen-Nuremberg 3 University of Bath Christian Theobalt1 Ayush Tewari1 Figure 1. Our single-shot deep inverse face renderer InverseFaceNet obtains a high-quality geometry, reflectance and illumination estimate from just a single input image. We jointly recover the face pose, shape, expression, reflectance and incident scene illumination. From left to right: input photo, our estimated face model, its geometry, and the pointwise Euclidean error compared to Garrido et al. [14]." 8121824f4598d600e4cdb745cd2715e4655c9e88,A Taxonomy of Emerging Multilinear Discriminant Analysis Solutions for Biometric Signal Recognition 1,"Contents A Taxonomy of Emerging Multilinear Discriminant Analysis Solutions for Biometric Signal Recognition Haiping Lu, K. N. Plataniotis and A. N. Venetsanopoulos Introduction .2 Multilinear basics .3 Multilinear discriminant analysis .5 Conclusions Empirical Comparison of MLDA variants on Face Recognition Appendix: Multilinear decompositions References" c03c16668426d8b069e75cb440686e12a9adbcd7,Deep Unsupervised Similarity Learning Using Partially Ordered Sets,"Deep Unsupervised Similarity Learning using Partially Ordered Sets Miguel A. Bautista∗ , Artsiom Sanakoyeu∗ , Bj¨orn Ommer Heidelberg Collaboratory for Image Processing IWR, Heidelberg University, Germany" c099a6dc8b9f731bbc9a29a920233257c13d9b00,Audio-visual Speech Recognition Workshop 2000 Final Report,"AUDIO-VISUAL SPEECH RECOGNITION Chalapathy Neti IBM T. J. Watson Research Center, Yorktown Heights, Gerasimos Potamianos IBM T. J. Watson Research Center, Yorktown Heights, Juergen Luettin Institut Dalle Molle d’Intelligence Articielle Perceptive, Martigny, Iain Matthews Carnegie Mellon University, Pittsburgh, Herve Glotin Institut de la Communication Parl ee, Grenoble; and Institut Dalle Molle d’Intelligence Articielle Perceptive, Martigny, Dimitra Vergyri Center for Language and Speech Processing, Baltimore, June Sison University of California, Santa Cruz, Azad Mashari University of Toronto, Toronto, nd Jie Zhou The Johns Hopkins University, Baltimore Workshop  Final Report October , " c0014e048a5d15ddfeffa075a1b819bcb93dd351,Simple and Efficient Visual Gaze Estimation,"Simple and Efficient Visual Gaze Estimation Roberto Valenti Nicu Sebe Intelligent Systems Lab Amsterdam Kruislaan 403, 1018SJ Amsterdam, The Netherlands Theo Gevers" c0c8d720658374cc1ffd6116554a615e846c74b5,Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification Yu-Gang Jiang, Zuxuan Wu, Jinhui Tang, Zechao Li, Xiangyang Xue, Shih-Fu Chang" c03ef6e94808185c1080ac9b155ac3b159b4f1ec,Learning to Avoid Errors in GANs by Manipulating Input Spaces,"Learning to Avoid Errors in GANs by Manipulating Input Spaces Alexander B. Jung TU Dortmund" c0b3159ca4bc847913e82c9a4c1f96f14e0e52db,"An effective biometric discretization approach to extract highly discriminative, informative, and privacy-protective binary representation","Lim and Teoh EURASIP Journal on Advances in Signal Processing 2011, 2011:107 http://asp.eurasipjournals.com/content/2011/1/107 RESEARCH Open Access An effective biometric discretization approach to extract highly discriminative, informative, and privacy-protective binary representation Meng-Hui Lim and Andrew Beng Jin Teoh*" c0e9d06383442d89426808d723ca04586db91747,Cascaded SR-GAN for Scale-Adaptive Low Resolution Person Re-identification,Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) c05a7c72e679745deab9c9d7d481f7b5b9b36bdd,"Naval Postgraduate School Monterey, California Approved for Public Release; Distribution Is Unlimited Biometric Challenges for Future Deployments: a Study of the Impact of Geography, Climate, Culture, and Social Conditions on the Effective Collection of Biometrics","NPS-CS-11-005 NAVAL POSTGRADUATE SCHOOL MONTEREY, CALIFORNIA BIOMETRIC CHALLENGES FOR FUTURE DEPLOYMENTS: A STUDY OF THE IMPACT OF GEOGRAPHY, CLIMATE, CULTURE, AND SOCIAL CONDITIONS ON THE EFFECTIVE COLLECTION OF BIOMETRICS Paul C. Clark, Heather S. Gregg, with preface by Cynthia E. Irvine April 2011 Approved for public release; distribution is unlimited" c06447df3e50ec451240205cefa0708caee8ab8c,Picture it in your mind: generating high level visual representations from textual descriptions,"Picture It In Your Mind: Generating High Level Visual Representations From Textual Descriptions Fabio Carrara ISTI-CNR via G. Moruzzi, 1 56124 Pisa, Italy Andrea Esuli ISTI-CNR via G. Moruzzi, 1 56124 Pisa, Italy Tiziano Fagni ISTI-CNR via G. Moruzzi, 1 56124 Pisa, Italy Fabrizio Falchi ISTI-CNR via G. Moruzzi, 1 56124 Pisa, Italy Alejandro Moreo Fernández" c043f8924717a3023a869777d4c9bee33e607fb5,Emotion Separation Is Completed Early and It Depends on Visual Field Presentation,"Emotion Separation Is Completed Early and It Depends on Visual Field Presentation Lichan Liu1,2*, Andreas A. Ioannides1,2 Lab for Human Brain Dynamics, RIKEN Brain Science Institute, Wakoshi, Saitama, Japan, 2 Lab for Human Brain Dynamics, AAI Scientific Cultural Services Ltd., Nicosia, Cyprus" c08420b1bfa093e89e35e3b8d3a9e3e881f4f563,A Classification Framework for Large-Scale Face Recognition Systems,"Kent Academic Repository Full text document (pdf) Citation for published version Zhou, Ziheng and Deravi, Farzin (2009) A Classification Framework for Large-Scale Face Recognition Systems. In: 3rd IAPR/IEEE International Conference on Biometrics, 2-5 June, University of Sassari, Italy. https://doi.org/10.1007/978-3-642-01793-3_35 Link to record in KAR http://kar.kent.ac.uk/23302/ Document Version Author's Accepted Manuscript Copyright & reuse Content in the Kent Academic Repository is made available for research purposes. Unless otherwise stated all ontent is protected by copyright and in the absence of an open licence (eg Creative Commons), permissions for further reuse of content should be sought from the publisher, author or other copyright holder. Versions of research The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record. Enquiries" c02dbf756b9e9e2bed37cb7d295529397cad616a,Semantic Segmentation of RGBD Videos with Recurrent Fully Convolutional Neural Networks,"Semantic Segmentation of RGBD Videos with Recurrent Fully Convolutional Neural Networks Ekrem Emre Yurdakul, Y¨ucel Yemez Computer Engineering Department, Koc¸ University Istanbul, Turkey" c0be23ae7f327f9415e583aee1936b9932c9b58b,Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data,"NetworkCNNimageslabelsFakeDatasetimages24132labelsTarget NetworkCNNimageslabelsOriginalDatasetFakeDatasetFig.1:Ontheleft,thetargetnetworkistrainedwithanoriginal(confidential)datasetandisservedpubliclyasanAPI,receivingimagesasinputandprovidingclasslabelsasoutput.Ontheright,itispresentedtheprocesstogetstolenlabelsandtocreateafakedataset:randomnaturalimagesaresenttotheAPIandthelabelsareobtained.Afterthat,thecopycatnetworkistrainedusingthisfakedataset.cloud-basedservicestocustomersallowingthemtooffertheirownmodelsasanAPI.Becauseoftheresourcesandmoneyinvestedincreatingthesemodels,itisinthebestinterestofthesecompaniestoprotectthem,i.e.,toavoidthatsomeoneelsecopythem.Someworkshavealreadyinvestigatedthepossibilityofcopyingmodelsbyqueryingthemasablack-box.In[1],forexample,theauthorsshowedhowtoperformmodelextractionattackstocopyanequivalentornear-equivalentmachinelearningmodel(decisiontree,logisticregression,SVM,andmultilayerperceptron),i.e.,onethatachievescloseto100%agreementonaninputspaceofinterest.In[2],theauthorsevaluatedtheprocessofcopyingaNaiveBayesandSVMclassifierinthecontextoftextclassification.Bothworksfocusedongeneralclassifiersandnotondeepneuralnetworksthatrequirelargeamountsofdatatobetrainedleavingthequestionofwhetherdeepmodelscanbeeasilycopied.Althoughthesecondusesdeeplearningtostealtheclassifiers,itdoesnottrytouseDNNstostealfromdeepmodels.Additionally,theseworksfocusoncopyingbyqueryingwithproblemdomaindata.Inrecentyears,researchershavebeenexploringsomeintriguingpropertiesofdeepneuralnetworks[3],[4].More©2018IEEE.Personaluseofthismaterialispermitted.PermissionfromIEEEmustbeobtainedforallotheruses,inanycurrentorfuturemedia,includingreprinting/republishingthismaterialforadvertisingorpromotionalpurposes,creatingnewcollectiveworks,forresaleorredistributiontoserversorlists,orreuseofanycopyrightedcomponentofthisworkinotherworks." c08ef9ebf46e5a88c4ee1aa64dac104ddc07bee2,Classification of vehicles for urban traffic scenes,"Classification of Vehicles for Urban Traffic Scenes Norbert Erich Buch Submitted in partial fulfilment of the requirements of Kingston University for the degree of Doctor of Philosophy June, 2010 Collaborating partner: Traffic Directorate at Transport for London" c0afa514524a4cf4b1772c1738ceb6989bff1b71,Impact of Tone-mapping Algorithms on Subjective and Objective Face Recognition in HDR Images,"Impact of Tone-mapping Algorithms on Subjective and Objective Face Recognition in HDR Images Pavel Korshunov MMSPG, EPFL Marco V. Bernardo Optics Center, UBI Touradj Ebrahimi MMSPG, EPFL António M. G. Pinheiro Optics Center, UBI" c0a9f8c2b1ad60c9d42252c80ff8cea4a3a25c2c,Face Class Modeling Using Mixture of SVMs,"Face Class Modeling Using Mixture of SVMs Julien Meynet1, Vlad Popovici, and Jean-Philippe Thiran Signal Processing Institute, Swiss Federal Institute of Technology Lausanne, CH-1015 Lausanne, Switzerland http://itswww.epfl.ch" c0d79e6077c47d6289ab89054f2b51653d887958,Action Search: Learning to Search for Human Activities in Untrimmed Videos,"Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization Humam Alwassel, Fabian Caba Heilbron, and Bernard Ghanem King Abdullah University of Science and Technology (KAUST), Saudi Arabia http://www.humamalwassel.com/publication/action-search/" c08a826913a25792d0221cc419daf8f47ebbdf9a,FACE DETECTION AND RECOGNITION USING BACK PROPAGATION NEURAL NETWORK AND FOURIER,"Signal & Image Processing : An International Journal (SIPIJ) Vol.2, No.3, September 2011 FACE DETECTION AND RECOGNITION USING BACK PROPAGATION NEURAL NETWORK AND FOURIER GABOR FILTERS Anissa Bouzalmat1, Naouar Belghini2, Arsalane Zarghili3 and Jamal Kharroubi4 Department of Computer Sciences, Sidi Mohamed Ben Abdellah University, Fez, Department of Computer Sciences, Sidi Mohamed Ben Abdellah University, Fez, Morocco Department of Computer Sciences, Sidi Mohamed Ben Abdellah University, Fez, Morocco Department of Computer Sciences, Sidi Mohamed Ben Abdellah University, Fez, Morocco Morocco" c04fec95a448f9b01dd4399b3a5a365f67448bdf,From Image Sequence to Frontal Image : Reconstruction of the Unknown Face A Forensic Case,"From Image Sequence to Frontal Image: A Forensic Case Christiaan van Dam" c03fdf0f43f393e04743f9858d0950c28256560e,Feature extraction without learning in an analog Spatial Pooler memristive-CMOS circuit design of Hierarchical Temporal Memory,"Noname manuscript No. (will be inserted by the editor) Feature extraction without learning in an analog Spatial Pooler memristive-CMOS circuit design of Hierarchical Temporal Memory Olga Krestinskaya · Alex Pappachen James Received: date / Accepted: date" c0992975eafd94746a4c18a0a2ca252044fcdc64,Unsupervised Adaptation for Deep,"Unsupervised Adaptation for Deep Stereo Alessio Tonioni, Matteo Poggi, Stefano Mattoccia, Luigi Di Stefano University of Bologna, Department of Computer Science and Engineering (DISI) Viale del Risorgimento 2, Bologna {alessio.tonioni, matteo.poggi8, stefano.mattoccia," c0f17f99c44807762f2a386ac6579c364330e082,A Review on Deep Learning Techniques Applied to Semantic Segmentation,"A Review on Deep Learning Techniques Applied to Semantic Segmentation A. Garcia-Garcia, S. Orts-Escolano, S.O. Oprea, V. Villena-Martinez, and J. Garcia-Rodriguez" c038beaa228aeec174e5bd52460f0de75e9cccbe,Temporal Segment Networks for Action Recognition in Videos,"Temporal Segment Networks for Action Recognition in Videos Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, and Luc Van Gool" c0a0adb7f02d5509969e6107c914f7cc6e9ec881,Semantic Instance Segmentation via Deep Metric Learning,"Semantic Instance Segmentation via Deep Metric Learning Alireza Fathi∗ Zbigniew Wojna∗ Vivek Rathod∗ Peng Wang† Sergio Guadarrama∗ Kevin P. Murphy∗ Hyun Oh Song∗" c038186138b76a625500ff84c9dadb18aae29f1c,Learning Implicit Transfer for Person Re-identification,"Learning Implicit Transfer for Person Re-identi(cid:12)cation Tamar Avraham, Ilya Gurvich, Michael Lindenbaum, and Shaul Markovitch Computer science department, Technion - I.I.T., Haifa 32000, Israel." c02847a04a99a5a6e784ab580907278ee3c12653,Fine Grained Video Classification for Endangered Bird Species Protection Non-Thesis MS Final Report,"Fine Grained Video Classification for Endangered Bird Species Protection Non-Thesis MS Final Report Chenyu Wang . Introduction .1 Background This project is about detecting eagles in videos. Eagles are endangered species at the brim of extinction since 1980s. With the bans of harmful pesticides, the number of eagles keep increasing. However, recent studies on golden eagles’ activities in the vicinity of wind turbines have shown significant number of turbine blade collisions with eagles as the major cause of eagles’ mortality. [1] This project is a part of a larger research project to build an eagle detection and deterrent system on wind turbine toward reducing eagles’ mortality. [2] The critical component of this study is a omputer vision system for eagle detection in videos. The key requirement are that the system should work in real time and detect eagles at a far distance from the camera (i.e. in low resolution). There are three different bird species in my dataset - falcon, eagle and seagull. The reason for involving only these three species is based on the real world situation. Wind turbines are always installed near coast and mountain hill where falcons and seagulls will be the majority. So my model will classify the minority eagles out of other bird species during the immigration season and protecting them by using the deterrent system. .2 Brief Approach" c0d21722d83c126af4175add38ffc893a33ee01e,Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor,"Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor Wongun Choi NEC Laboratories America 0080 N. Wolfe Rd, Cupertino, CA, USA" acee1e7700e9f084ff64805a2c67d16fe69e63a8,250 years Lambert surface: does it really exist?,"50 years Lambert surface: does it really exist? Institut f¨ur Lasertechnologien in der Medizin und Meßtechnik, Helmholtzstr.12, D-89081 Ulm, Alwin Kienle∗ and Florian Foschum Germany" acd26d5b85e979d73101ac790bfdedf17bfe8ed1,Learning from PhotoShop Operation Videos : the PSOV Dataset,"Learning from PhotoShop Operation Videos: the PSOV Dataset Jingchun Cheng2(cid:63) Han-Kai Hsu1∗ Fang Chen3 Hailin Jin3 Shengjin Wang2‡ Ming-Hsuan Yang1 University of California, Merced 2Tsinghua University 3Adobe Research" ac7f898ff5789914d423526c392ee61b979fdd8e,"Target Tracking with Kalman Filtering , KNN and LSTMs Dan Iter","Target Tracking with Kalman Filtering, KNN and LSTMs Dan Iter Jonathan Kuck Philip Zhuang December 17, 2016" ac9feef881ed00a5a5e53bddb88f135a9cffe048,A general method for appearance-based people search based on textual queries,"A general method for appearance-based people search based on textual queries Riccardo Satta, Giorgio Fumera, and Fabio Roli Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d’Armi, 09123 Cagliari, Italy" ac8441e30833a8e2a96a57c5e6fede5df81794af,Hierarchical Representation Learning for Kinship Verification,"IEEE TRANSACTIONS ON IMAGE PROCESSING Hierarchical Representation Learning for Kinship Verification Naman Kohli, Student Member, IEEE, Mayank Vatsa, Senior Member, IEEE, Richa Singh, Senior Member, IEEE, Afzel Noore, Senior Member, IEEE, and Angshul Majumdar, Senior Member, IEEE" ac7c643794b9f55309f0d2041b12ae7bf845a52d,Graphical models for visual object recognition and tracking,"Graphical Models for Visual Object Recognition and Tracking Erik B. Sudderth B.S., Electrical Engineering, University of California at San Diego, 1999 S.M., Electrical Engineering and Computer Science, M.I.T., 2002 Submitted to the Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Electrical Engineering and Computer Science t the Massachusetts Institute of Technology May, 2006 ° 2006 Massachusetts Institute of Technology All Rights Reserved. Signature of Author: Department of Electrical Engineering and Computer Science May 26, 2006 Certified by: Certified by: Accepted by: William T. Freeman Professor of Electrical Engineering and Computer Science" ac83b9ad20ecf63c7818ff1e43a99b4c626fac12,Accuracy and Security Evaluation of Multi-Factor Biometric Authentication,"Accuracy and Security Evaluation of Multi-Factor Biometric Authentication Hisham Al-Assam, Harin Sellahewa, Sabah Jassim Department of Applied Computing University of Buckingham Buckingham, MK18 1EG, United Kingdom {hisham.al-assam, harin.sellahewa," aca232de87c4c61537c730ee59a8f7ebf5ecb14f,Ebgm Vs Subspace Projection for Face Recognition,"EBGM VS SUBSPACE PROJECTION FOR FACE RECOGNITION Andreas Stergiou, Aristodemos Pnevmatikakis, Lazaros Polymenakos 9.5 Km Markopoulou Avenue, P.O. Box 68, Peania, Athens, Greece Athens Information Technology Keywords: Human-Machine Interfaces, Computer Vision, Face Recognition." ac71673da236ac440f647226dddd94aef3bd72b2,Pedestrian detection in thermal images using adaptive fuzzy C-means clustering and convolutional neural networks,"MVA2015 IAPR International Conference on Machine Vision Applications, May 18-22, 2015, Tokyo, JAPAN Pedestrian Detection in Thermal Images Using Adaptive Fuzzy C-Means Clustering and Convolutional Neural Networks Vijay John Zheng Liu Toyota Technological Institute, Japan Toyota Technological Institute, Japan Seiichi Mita Bin Qi Toyota Technological Institute, Japan Toyota Technological Institute, Japan" acaa89fb6263aef7ad58a37d9cac79c8fcaa29ca,Person Re-identification in Identity Regression Space,"Noname manuscript No. (will be inserted by the editor) Person Re-Identification in Identity Regression Space Hanxiao Wang · Xiatian Zhu · Shaogang Gong · Tao Xiang Received: date / Accepted: date" ac479607e6b44c69022a56b5847a055535ae63ed,Cross-domain fashion image retrieval,"Cross-domain fashion image retrieval Bojana Gaji´c, Ramon Baldrich Computer Vision Center Universitat Autnoma de Barcelona Edifici O. UAB. Bellaterra, Spain. {bgajic," ac559873b288f3ac28ee8a38c0f3710ea3f986d9,Team DEEP-HRI Moments in Time Challenge 2018 Technical Report,"Team DEEP-HRI Moments in Time Challenge 2018 Technical Report Chao Li, Zhi Hou, Jiaxu Chen, Yingjia Bu, Jiqiang Zhou, Qiaoyong Zhong, Di Xie and Shiliang Pu Hikvision Research Institute" ac8e09128e1e48a2eae5fa90f252ada689f6eae7,Leolani: A Reference Machine with a Theory of Mind for Social Communication,"Leolani: a reference machine with a theory of mind for social communication Piek Vossen, Selene Baez, Lenka Baj˘ceti´c, and Bram Kraaijeveld VU University Amsterdam, Computational Lexicology and Terminology Lab, De Boelelaan 1105, 1081HV Amsterdam, The Netherlands www.cltl.nl" acc37d228f6cb2205497df81532c582ed71dd9fe,Deep Ordinal Ranking for Multi-Category Diagnosis of Alzheimer's Disease using Hippocampal MRI data,"Deep Ordinal Ranking for Multi-Category Diagnosis of Alzheimer’s Disease using Hippocampal MRI data Hongming Li, Mohamad Habes, Yong Fan nd for the Alzheimer's Disease Neuroimaging Initiative* Section for Biomedical Image Analysis (SBIA), Center for Biomedical Image Computing and Analytics (CBICA), Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA *Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found t: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf" ac0d88ca5f75a4a80da90365c28fa26f1a26d4c4,MOT16: A Benchmark for Multi-Object Tracking,"MOT16: A Benchmark for Multi-Object Tracking Anton Milan∗, Laura Leal-Taix´e∗, Ian Reid, Stefan Roth, and Konrad Schindler" ac43a881c0ab8af00ccfca7cb7558c7f816ded1a,Multi-Step Prediction of Occupancy Grid Maps with Recurrent Neural Networks,"Multi-Step Prediction of Occupancy Grid Maps with Recurrent Neural Networks Nima Mohajerin and Mohsen Rohani∗ Huawei Noah’s Ark, Markham, ON, Canada {nima.mohajerin," ac26166857e55fd5c64ae7194a169ff4e473eb8b,Personalized Age Progression with Bi-Level Aging Dictionary Learning,"Personalized Age Progression with Bi-level Aging Dictionary Learning Xiangbo Shu, Jinhui Tang, Senior Member, IEEE, Zechao Li, Hanjiang Lai, Liyan Zhang nd Shuicheng Yan, Fellow, IEEE" ac5d0705a9ddba29151fd539c668ba2c0d16deb6,RED-Net: A Recurrent Encoder–Decoder Network for Video-Based Face Alignment,"IJCV special issue (Best papers of ECCV 2016) manuscript No. (will be inserted by the editor) RED-Net: A Recurrent Encoder-Decoder Network for Video-based Face Alignment Xi Peng · Rogerio S. Feris · Xiaoyu Wang · Dimitris N. Metaxas Submitted: April 19 2017 / Revised: December 12 2017" ac5c93b789bdd557b90ce77221f1c01ead63041f,Robust People Detection using Computer Vision Spring Term 2013,"Autonomous Systems Lab Prof. Roland Siegwart Master-Thesis Robust People Detection using Computer Vision Spring Term 2013 Supervised by: Jerome Maye Paul Beardsley Author: Endri Dibra" acb83d68345fe9a6eb9840c6e1ff0e41fa373229,"Kernel methods in computer vision: object localization, clustering, and taxonomy discovery","Kernel Methods in Computer Vision: Object Localization, Clustering, nd Taxonomy Discovery vorgelegt von Matthew Brian Blaschko, M.S. us La Jolla Von der Fakult¨at IV - Elektrotechnik und Informatik der Technischen Universit¨at Berlin zur Erlangung des akademischen Grades Doktor der Naturwissenschaften Dr. rer. nat. genehmigte Dissertation Promotionsausschuß: Vorsitzender: Prof. Dr. O. Hellwich Berichter: Prof. Dr. T. Hofmann Berichter: Prof. Dr. K.-R. M¨uller Berichter: Prof. Dr. B. Sch¨olkopf Tag der wissenschaftlichen Aussprache: 23.03.2009 Berlin 2009" ac20730c27b023ac8f75c3a62d001f8a3eb918dd,Sharing big display : développement des technologies et métaphores d'interactions nouvelles pour le partage collaboratif d'affichage en groupe ouvert. (Sharing big display : technology development and new interaction metaphors for collaborative sharing display in open group),"Sharing big display : développement des technologies et métaphores d’interactions nouvelles pour le partage ollaboratif d’affichage en groupe ouvert Damien Marion To cite this version: Damien Marion. Sharing big display : développement des technologies et métaphores d’interactions nouvelles pour le partage collaboratif d’affichage en groupe ouvert. Interface homme-machine [cs.HC]. Université de Bordeaux, 2017. Français. . HAL Id: tel-01738673 https://tel.archives-ouvertes.fr/tel-01738673 Submitted on 20 Mar 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," ac2a2c655ad1b3eea3f222b213a774aa25a403c0,Self-Learning of Feature Regions for Image Recognition,"Journal of Computer Sciences and Applications, 2015, Vol. 3, No. 1, 1-10 Available online at http://pubs.sciepub.com/jcsa/3/1/1 © Science and Education Publishing DOI:10.12691/jcsa-3-1-1 Self-Learning of Feature Regions for Image Recognition Satoru Yokota1,*, Jiang Li1, Yuichi Ogishima1, Hiromasa Kubo1, Hakaru Tamukoh2,*, Masatoshi Sekine1 Graduate School of Engineering, Tokyo University of Agriculture and Technology, Tokyo, Japan Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu, Japan *Corresponding author: Received January 09, 2015; Revised January 19, 2015; Accepted January 22, 2015" ac2e3a889fc46ca72f9a2cdedbdd6f3d4e9e2627,Age detection from a single image using multitask neural networks : An overview and design proposal,"Research School of Engineering ANU College of Engineering and Computer Science ASSIGNMENT COVER SHEET THIS COVER SHEET SHOULD BE ATTACHED TO THE FRONT OF YOUR ASSIGNMENT WHEN IT IS SUBMITTED STUDENT NAME: Kiarie Ndegwa STUDENT ID NUMBER: u4742829 COURSE NAME: Special Topics in Computer Science. COURSE CODE: COMP6470 DUE DATE: 5pm 27th May 2016 Submission of this assignment constitutes a declaration that: • No part of this work has been copied from any other person’s work except where due acknowledgement is made in the text; and • No part of this work has been written by any other person except where such ollaboration has been authorised by the course lecturer concerned, and • No part of this work has been submitted for assessment in another course in this or nother part of the University except where authorised by the lecturer(s) concerned. Student Name: Kiarie Ndegwa Date: 27th May 2016" ac6a9f80d850b544a2cbfdde7002ad5e25c05ac6,Privacy-Protected Facial Biometric Verification Using Fuzzy Forest Learning,"Privacy-Protected Facial Biometric Verification Using Fuzzy Forest Learning Richard Jiang, Ahmed Bouridane, Senior Member, IEEE, Danny Crookes, Senior Member, IEEE, M. Emre Celebi, Senior Member, IEEE, and Hua-Liang Wei" ac12ba5bf81de83991210b4cd95b4ad048317681,Combining Deep Facial and Ambient Features for First Impression Estimation,"Combining Deep Facial and Ambient Features for First Impression Estimation Furkan G¨urpınar1, Heysem Kaya2, Albert Ali Salah3 Program of Computational Science and Engineering, Bo˘gazi¸ci University, Bebek, Istanbul, Turkey Department of Computer Engineering, Namık Kemal University, C¸ orlu, Tekirda˘g, Turkey Department of Computer Engineering, Bo˘gazi¸ci University, Bebek, Istanbul, Turkey" acf13c52c86a3b38642ba0c6cbcd1b771778965c,NAACL HLT 2018 Generalization in the Age of Deep Learning Proceedings of the Workshop,"NAACLHLT2018GeneralizationintheAgeofDeepLearningProceedingsoftheWorkshopJune5,2018NewOrleans,Louisiana" aca8c4a62ed6e590889f1e859d7bc79311fa6f4d,Beyond Universal Saliency: Personalized Saliency Prediction with Multi-task CNN,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) Semantic labels Observer A Observer B Observer C Figure1:AnillustrationofPSMdataset.Ourdatasetprovidesbotheyefixationsofdifferentsubjectsandsemanticlabels.Duetothelargeamountofobjectsinourdataset,foreachimage,wedidn’tful-lysegmentitandonlylabelledobjectsthatcoveratleastthreegazepointsfromeachindividual.AnotabledifferencebetweenPSManditspredecessorsisthateachsubjectslooks4timesonPSMdatatoderivesolidfixationgroundtruthmaps.Bothcommonalityanddis-tinctivenessexistforPSMsviewedbydifferentparticipant.ThismotivatesustomodelPSMbasedonUSM.recognizingheterogeneityacrossindividuals.ExamplesinFig.1illustratethatwhilemultipleobjectsaredeemedhigh-lysalientwithinthesameimage(eg,humanface(firstrow),text(lasttowrows)andobjectof(highcolorcontrast),differ-entindividualshaveverydifferentfixationpreferenceswhenviewingtheimage.Fortherestofthepaper,weusetermuniversalsaliencytodescribesalientregionsthatincurhighfixationsacrossallsubjectsandtermpersonalizedsaliencytodescribetheheterogeneousones.Motivation.Infact,heterogeneityinsaliencypreferencehasbeenwidelyrecognizedinpsychology:”Interestingnessishighlysubjectiveandthereareindividualswhodidnotconsideranyimageinterestinginsomesequences”[Gyglietal.,2013].Therefore,onceweknowaperson’spersonal-izedinterestingnessovereachimage(personalizedsaliency),weshalldesigntailoredalgorithmstocatertohim/herneed-s.Forexample,intheapplicationofimageretargeting,thetextsonthetableinthefourthrowinFig.1shouldbepre-" ac57b04359818c17d416ee53ae05a5f126eca4db,Detection and classification of the behavior of people in an intelligent building by camera,"Detection and classification of the behavior of people in an intelligent building by camera Henni Sid Ahmed1, Belbachir Mohamed Faouzi2, Jean Caelen3 Universite of sciences and technology USTO in Oran Algeria, laboratory LSSD, Faculty genie electrique, department electronique, BP 1505 el menouar Oran 31000 Algeria Universite of sciences and technology USTO in Oran Algeria, laboratory LSSD, Faculty genie electrique, department electronique, BP 1505 el menouar Oran 31000 Algeria Universite Joseph Fourier, Grenoble, F , LIG Grenoble computer laboratory ,domaine universitaire BP 53, 220 rue de la chimie 38041 Grenoble cedex 9 France Emails: 1 Submitted: Apr. 10, 2013 Accepted: July 30, 2013 Published: Sep. 3, 2013" 6acc92f30c7a141384b9b1bbec8dffe16b08a438,Improving Bag-of-Visual-Words Towards Effective Facial Expressive Image Classification,"Improving Bag-of-Visual-Words Towards Effective Facial Expressive Image Classification Dawood Al Chanti1 and Alice Caplier1 Univ. Grenoble Alpes, CNRS, Grenoble INP∗ , GIPSA-lab, 38000 Grenoble, France Keywords: BoVW, k-means++, Relative Conjunction Matrix, SIFT, Spatial Pyramids, TF.IDF." 6ae13c7dcd1d10d2dfe58546a49da09b0b471d68,Person-independent facial expression recognition based on compound local binary pattern (CLBP),"The International Arab Journal of Information Technology, Vol. 11, No. 2, March 2014 195 Person-Independent Facial Expression Recognition Based on Compound Local Binary Pattern (CLBP) Department of Computer Science and Engineering, Islamic University of Technology, Bangladesh Faisal Ahmed1, Hossain Bari2, and Emam Hossain3 2Samsung Bangladesh R & D Center Ltd, Bangladesh 3Department of Computer Science and Engineering, Ahsanullah University of Science and Technology, Bangladesh" 6a553f7ef42000001f407e95f4955e7ddde46a83,A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation,"IJCARS manuscript No. (will be inserted by the editor) A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation Max-Heinrich Laves · Jens Bicker · Lüder A. Kahrs · Tobias Ortmaier Received: date / Accepted: date" 6aa21d78af359853ee07288cfc8d047e914ce458,Facial Expression Recognition using Log-Euclidean Statistical Shape Models,"FACIAL EXPRESSION RECOGNITION USING LOG-EUCLIDEAN STATISTICAL SHAPE MODELS Bartlomiej W. Papiez, Bogdan J. Matuszewski, Lik-Kwan Shark and Wei Quan Applied Digital Signal and Image Processing Research Centre, University of Central Lancashire, PR1 2HE Preston, U.K. Keywords: Facial expression representation, Facial expression recognition, Vectorial log-Euclidean statistics, Statistical shape modelling." 6a69b790a7ec5a396607eb717da2b271a750faaa,Stacked Latent Attention for Multimodal Reasoning,"Stacked Latent Attention for Multimodal Reasoning Haoqi Fan Jiatong Zhou Facebook Research Facebook Research Hacker Way Hacker Way" 6a7ec333ccabd41b9d20f05c145b3377f6045f43,"C 2010 Zihan Zhou Face Recognition under Varying Illumination, Pose and Contiguous Occlusion",(cid:13) 2010 Zihan Zhou 6a41ba9db0affa701ea125e09a2fe7eb583e3ac9,Frontal imgelerden otomatik yüz tan ı ma Automatic face recognition from frontal images,"Frontal imgelerden otomatik yüz tanıma Automatic face recognition from frontal images Hasan Serhan Yavuz, Hakan Çevikalp, Rıfat Edizkan Elektrik ve Elektronik Mühendisliği Bölümü Eskişehir Osmangazi Üniversitesi Eskişehir, Türkiye fotoğraflanan laboratuarımızda Özetçe—Yüz tanıma basitçe kişilere ait olan yüz imgelerinden kimlik tespit edilmesi olarak tanımlanabilir. Bu çalışmada, sayısal kamera frontal imgeler kullanılarak yüz tanıma yapılmıştır. Otomatik yüz tanıma süreci sırasıyla yüz sezme, göz sezme, sezilen gözlerin orta noktalarını kullanarak belirlenen standart bir yüz şablonuna uyacak biçimde haritalama yapma ve sonrasında hizalanan yüz imgelerini sınıflandırma basamaklarından oluşur. Literatürde yüz imgesi hazırlama süreci genellikle elle yapılmaktadır. Yüz imgelerinin tamamı birebir aynı biçimde kesildiği için çok yüksek tanıma oranları elde edilir ancak bir otomatik yüz tanıma" 6a536aa4ecd6359d54a34aca7eff828e4df02730,Multimodal Observation and Interpretation of Subjects Engaged in Problem Solving,"Multimodal Observation and Interpretation of Subjects Engaged in Problem Solving Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP*, LIG, Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP*, LIG, (cid:140)omas Guntz F-38000 Grenoble, France Dominique Vaufreydaz F-38000 Grenoble, France Ra(cid:130)aella Balzarini F-38000 Grenoble, France James Crowley F-38000 Grenoble, France Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP*, LIG, Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP*, LIG," 6a4bb2a376068d8186272306c500ea332db0eae7,Gender Classification from Neutral and Expressive Faces,"Sixth International Conference on Machine Vision (ICMV 2013), edited by Antanas Verikas, Branislav Vuksanovic, Jianhong Zhou, Proc. of SPIE Vol. 9067, 906723 · © 2013 SPIE · CCC code: 0277-786X/13/$18 · doi: 10.1117/12.2051041 Proc. of SPIE Vol. 9067 906723-1" 6a16b91b2db0a3164f62bfd956530a4206b23fea,A Method for Real-Time Eye Blink Detection and Its Application,"A Method for Real-Time Eye Blink Detection and Its Application Chinnawat Devahasdin Na Ayudhya Mahidol Wittayanusorn School Puttamonton, Nakornpatom 73170, Thailand" 6a3a07deadcaaab42a0689fbe5879b5dfc3ede52,Learning to Estimate Pose by Watching Videos,"Learning to Estimate Pose by Watching Videos Prabuddha Chakraborty and Vinay P. Namboodiri Department of Computer Science and Engineering IIT Kanpur {prabudc, vinaypn}" 6a9c460952a96a04e12caa7bae07ae2f7df1238e,Exploiting scene context for on-line object tracking in unconstrained environments. (Exploitation du contexte de scène pour le suivi d'objet en ligne dans des environnements non contraints),"Exploiting scene context for on-line object tracking in unconstrained environments Salma Moujtahid To cite this version: Salma Moujtahid. Exploiting scene context for on-line object tracking in unconstrained environments. Modeling and Simulation. Université de Lyon, 2016. English. . HAL Id: tel-01783935 https://tel.archives-ouvertes.fr/tel-01783935 Submitted on 2 May 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 6a75ef6b36489cb59c61f21f3cd09c50ad5b2995,MVTec D2S: Densely Segmented Supermarket Dataset,"MVTec D2S: Densely Segmented Supermarket Dataset Patrick Follmann1,2[0000−0001−5400−2384], Tobias B¨ottger1,2[0000−0002−5404−8662], Philipp H¨artinger1[0000−0002−7093−6280], Rebecca K¨onig1[0000−0002−4169−6759], nd Markus Ulrich1[0000−0001−8457−5554] MVTec Software GmbH, 80634 Munich, Germany https://www.mvtec.com/research Technical University of Munich, 80333 Munich, Germany" 6a14652508138fcf0aa8c518109165f65c88fd3f,Programming a humanoid robot in natural language : an experiment with description logics,"Programming a humanoid robot in natural language: n experiment with description logics Nicola Vitucci , Alessio Mauro Franchi, Giuseppina Gini DEIB, Politecnico di Milano Milano, Italy" 6a4dbd2db0e09a4f3aab3d2602db3176f825d8f9,Multi-Rate Gated Recurrent Convolutional Networks for Video-Based Pedestrian Re-Identification,"The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) Multi-Rate Gated Recurrent Convolutional Networks for Video-Based Pedestrian Re-Identification Zhihui Li,1 Lina Yao,2 Feiping Nie,3∗ Dingwen Zhang,4 Min Xu5 School of Computer Science and Engineering, University of New South Wales. Beijing Etrol Technologies Co., Ltd. Centre for OPTical Imagery Analysis and Learning, Northwestern Polytechnical University. School of Automation, Northwestern Polytechnical University. 5School of Electrical and Data Engineering, University of Technology Sydney." 6af98f9843ba629ae1b0347e8b8d81a263f8d7f2,Does this recession make me look black? The effect of resource scarcity on the categorization of biracial faces.,"Short Report Does This Recession Make Me Look Black? The Effect of Resource Scarcity on the Categorization of Biracial Faces 3(12) 1476 –1478 © The Author(s) 2012 Reprints and permission: sagepub.com/journalsPermissions.nav DOI: 10.1177/0956797612450892 http://pss.sagepub.com Christopher D. Rodeheffer, Sarah E. Hill, and Charles G. Lord Texas Christian University Received 2/27/12; Revision accepted 5/10/12 Prosperity makes friends; adversity tries them. —Publilius Syrus (Lyman, 1856, p. 73) In-group biases are a ubiquitous feature of human social life (e.g., Brewer, 1979; Halevy, Bornstein, & Sagiv, 2008; Mullen, Dovidio, Johnson, & Copper, 1992; Tajfel, 1982). One explana- tion offered for these biases is that they arise from resource ompetition between groups (e.g., Kurzban & Neuberg, 2005;" 6a951df76a56fc89e5df3fbba2e5699ccad4f199,Relative Pairwise Relationship Constrained Non-negative Matrix Factorisation,"IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING Relative Pairwise Relationship Constrained Non-negative Matrix Factorisation Shuai Jiang, Kan Li, and Richard Yida Xu" 6a3cbe2bb27b2a7d32c358e0be4ed268f7d4455c,"Modeling Shape, Appearance and Self-Occlusions for Articulated Object Tracking","Modeling Shape, Appearance and Self-Occlusions for Articulated Object Tracking Yanchao Yang and Ganesh Sundaramoorthi" 6ae47c7793e2f0f684ae07357335c7cf338d66ef,Optimistic and pessimistic neural networks for object recognition,"published in: International Conference on Image Processing (ICIP) 2017 OPTIMISTIC AND PESSIMISTIC NEURAL NETWORKS FOR OBJECT RECOGNITION Rene Grzeszick Sebastian Sudholt Gernot A. Fink email: TU Dortmund University, Germany" 6a55d6db1b31f44c9bb37b070fbf7c8f64a31f13,Aging and Emotion Recognition : An Examination of Stimulus and Attentional Mechanisms,"Cleveland State University ETD Archive Aging and Emotion Recognition: An Examination of Stimulus and Attentional Mechanisms Stephanie Nicole Sedall Follow this and additional works at: http://engagedscholarship.csuohio.edu/etdarchive Part of the Experimental Analysis of Behavior Commons How does access to this work benefit you? Let us know! Recommended Citation Sedall, Stephanie Nicole, ""Aging and Emotion Recognition: An Examination of Stimulus and Attentional Mechanisms"" (2016). ETD Archive. 903. http://engagedscholarship.csuohio.edu/etdarchive/903 This Thesis is brought to you for free and open access by It has been accepted for inclusion in ETD Archive by an uthorized administrator of For more information, please contact" 6a38c575733b0f7118970238e8f9b480522a2dbc,Random Forests Can Hash,"Accepted as a workshop contribution at ICLR 2015 RANDOM FORESTS CAN HASH Qiang Qiu, Guillermo Sapiro, and Alex Bronstein Duke University and Tel Aviv University {qiang.qiu," 6a1e5f4dbabf451122bf35228c8b25c79c7d235f,Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation,"Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation Patrick Follmann, Rebecca K¨onig, Philipp H¨artinger, Michael Klostermann MVTec Software GmbH, www.mvtec.com," 6af35225cfd744b79577c126e553f549e5b5cdcc,Title Discriminative Hessian Eigenmaps for face recognition,"Title Discriminative Hessian Eigenmaps for face recognition Author(s) Si, S; Tao, D; Chan, KP Citation The 2010 IEEE International Conference on Acoustics, Speech nd Signal Processing (ICASSP), Dallas, TX., 14-19 March 2010. In IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, 2010, p. 5586-5589 Issued Date http://hdl.handle.net/10722/125723 Rights IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings. Copyright © IEEE.; ©2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted omponent of this work in other works must be obtained from the IEEE.; This work is licensed under a Creative Commons" 6a8a3b27a78c78bc80984fca29554de3269d34d3,Speeding-Up Object Detection Training for Robotics with FALKON,"Speeding-up Object Detection Training for Robotics with FALKON Elisa Maiettini1,2,3, Giulia Pasquale1,2, Lorenzo Rosasco2,3 and Lorenzo Natale1" 6a27ffd788a0db64fef74e673786763c82902a26,Discriminative deep transfer metric learning for cross-scenario person re-identification,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 9/13/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use Discriminativedeeptransfermetriclearningforcross-scenariopersonre-identificationTongguangNiXiaoqingGuHongyuanWangZhongbaoZhangShoubingChenCuiJinTongguangNi,XiaoqingGu,HongyuanWang,ZhongbaoZhang,ShoubingChen,CuiJin,“Discriminativedeeptransfermetriclearningforcross-scenariopersonre-identification,”J.Electron.Imaging27(4),043026(2018),doi:10.1117/1.JEI.27.4.043026." 6ada03f390f92704f3df1556846697c54c00f7da,of Problem Solving Human-Machine Cooperation in Large-Scale Multimedia Retrieval : A Survey,"Human-Machine Cooperation in Large-Scale Multimedia Retrieval: A Survey Kimiaki Shirahama,1 Marcin Grzegorzek,1 and Bipin Indurkhya2 University of Siegen, 2AGH University of Science and Technology Correspondence: Correspondence concerning this rticle should be addressed to Kimiaki Shirahama, Pattern Recognition Group, University of Siegen, Hoelderlinstrasse 3, 57076 Siegen, Germany, or via email to Keywords: large-scale multimedia retrieval, human- machine cooperation, machine-based methods, human-based methods Large-Scale Multimedia Retrieval (LSMR) is the task to fast analyze a large amount of multi- media data like images or videos and accurately find the ones relevant to a certain semantic meaning. Although LSMR has been investigated for more than two decades in the fields of multimedia processing and computer vision, a more interdisciplinary approach is neces- sary to develop an LSMR system that is really meaningful for humans. To this end, this paper ims to stimulate attention to the LSMR problem from diverse research fields. By explaining" 6a0b70abb9a81a96d4baa9b396deb9da4cc20f8f,Clustering through ranking on manifolds,"Clustering Through Ranking On Manifolds Markus Breitenbach Dept. of Computer Science; University of Colorado, Boulder, USA Gregory Z. Grudic Dept. of Computer Science; University of Colorado, Boulder, USA" 6a8a3c604591e7dd4346611c14dbef0c8ce9ba54,An Affect-Responsive Interactive Photo Frame,"ENTERFACE’10, JULY 12TH - AUGUST 6TH, AMSTERDAM, THE NETHERLANDS. An Affect-Responsive Interactive Photo Frame Hamdi Dibeklio˘glu, Ilkka Kosunen, Marcos Ortega Hortas, Albert Ali Salah, Petr Zuz´anek" 6a951a47aa545e08508b0b2c6a2bef45e154a3a9,DeepCoder: Semi-Parametric Variational Autoencoders for Automatic Facial Action Coding,"DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding Dieu Linh Tran∗, Robert Walecki, Ognjen (Oggi) Rudovic*, Stefanos Eleftheriadis, Bj¨orn Schuller and Maja Pantic {linh.tran, r.walecki14, bjoern.schuller," 6ac7fe3a292dc5e0f7d27e11b85ed8277905e9ba,Detecting Traffic Lights by Single Shot Detection,"Detecting Traffic Lights by Single Shot Detection Julian M¨uller1 and Klaus Dietmayer1" 6ad32b70ee21b6fc16ff4caf7b4ada2aaf13cabc,Efficient Subwindow Search: A Branch and Bound Framework for Object Localization,"Efficient Subwindow Search: A Branch and Bound Framework for Object Localization Christoph H. Lampert, Matthew B. Blaschko, and Thomas Hofmann n image of as low resolution as 320×240 contains more than one billion rectangular subimages. In general, the number of subimages grows quadratically with the number of image pix- els, which makes it computationally too expensive to evaluate the quality function exhaustively for all of these. Instead, one typically uses heuristics to speed up the search that introduce the risk of mispredicting the location of an object or even missing it." 6aefe7460e1540438ffa63f7757c4750c844764d,Non-rigid Segmentation Using Sparse Low Dimensional Manifolds and Deep Belief Networks,"Non-rigid Segmentation using Sparse Low Dimensional Manifolds and Deep Belief Networks ∗ Jacinto C. Nascimento Instituto de Sistemas e Rob´otica Instituto Superior T´ecnico, Portugal" 6afed8dc29bc568b58778f066dc44146cad5366c,Kernel Hebbian Algorithm for Single-Frame Super-Resolution,"Kernel Hebbian Algorithm for Single-Frame Super-Resolution Kwang In Kim1, Matthias O. Franz1, and Bernhard Sch¨olkopf1 Max Planck Institute f¨ur biologische Kybernetik Spemannstr. 38, D-72076 T¨ubingen, Germany {kimki, mof, http://www.kyb.tuebingen.mpg.de/" 6a6280189ead63b2eec733b8e8ac507e830928fd,Face localization in color images with complex background,"Face localization in color images with complex ackground Paola Campadelli, Raffaella Lanzarotti, Giuseppe Lipori Dipartimento di Scienze dell’Informazione Universit(cid:30)a degli Studi di Milano Via Comelico, 39/41 20135 Milano, Italy fcampadelli, lanzarotti," 6a52e6fce541126ff429f3c6d573bc774f5b8d89,Role of Facial Emotion in Social Correlation,"Role of Facial Emotion in Social Correlation Pankaj Mishra, Rafik Hadfi, and Takayuki Ito Department of Computer Science and Engineering Nagoya Institute of Technology, Gokiso, Showa-ku, Nagoya, 466-8555 Japan {pankaj.mishra," 6a806978ca5cd593d0ccd8b3711b6ef2a163d810,Facial feature tracking for emotional dynamic analysis,"Facial feature tracking for Emotional Dynamic Analysis Thibaud Senechal1, Vincent Rapp1, and Lionel Prevost2 ISIR, CNRS UMR 7222 Univ. Pierre et Marie Curie, Paris {rapp, LAMIA, EA 4540 Univ. of Fr. West Indies & Guyana" 6a9c3011b5092daa1d0cacda23f20ca4ae74b902,Fast and Accurate Person Re-Identification with RMNet.,"Fast and Accurate Person Re-Identification with RMNet Evgeny Izutov IOTG Computer Vision (ICV), Intel" 63e9deb375f260bdc0c4308410caca0755d307c5,A New 3D Object Pose Detection Method Using LIDAR Shape Set,"Article A New 3D Object Pose Detection Method Using LIDAR Shape Set Jung-Un Kim and Hang-Bong Kang * Department of Media Engineering, Catholic University of Korea, 43-1, Yeoggok 2-dong, Wonmmi-gu, Bucheon-si, Gyeonggi-do 14662, Korea; * Correspondence: Tel.: +82-2-2164-4599 Received: 7 February 2018; Accepted: 14 March 2018; Published: 16 March 2018" 634f698c05d640ab355e94a9a0cf9191891b3dcb,Video Face Recognition From A Single Still Image Using an Adaptive Appearance Model Tracker,"Video Face Recognition From A Single Still Image Using an Adaptive Appearance Model Tracker M. Ali Akber Dewan E. Granger, R. Sabourin G.-L. Marcialis, F. Roli School of Computing and Information Systems, Athabasca University Department of Automated Production Engineering, École de technologie supé- Department of Electrical and Electronic Engineering, University of Cagliari Edmonton, Canada rieure, Montreal, Canada Cagliari, Italy" 63344dee49a1ab7e27ac34eefc30fb948a0bf9bb,Geometry and Illumination Modelling for Scene Understanding,"Geometry and Illumination Modelling for Scene Understanding Principal Investigators: Jana Koˇseck´a and Dimitris Samaras Project Summary The goal this proposal is to develop unified framework for reasoning about objects, scenes and lighting from single and multiple views of indoors and outdoors environments. We propose computational models for semantic parsing of scenes which incorporate information bout the lighting and illumination to resolve the ambiguities of purely appearance based methods nd develop class of models where partial geometry and semantic information aid the process of recovery of illumination. The proposed work can be partitioned into three main research topics: . Supervised approach for semantic parsing of object and non-object categories using photo- metric, geometric and shadow cues. . Closing the loop on estimation of Illumination using coarse object models and geometric ontext. . Object recognition, change detection, scene matching and 3D reconstruction with dramatic hanges in illumination. We propose to study the interactions between appearance, geometry and lighting in the context of the problems outlined above and develop computational models which jointly consider these spects. In some cases different models will serve as preprocessing stage for the follow up prob- lems and in others they will interact jointly or in a feedback loop manner. For joint interactions final inference for estimation of semantic categories and illumination will be formulated in Markov Random field or Conditional Markov Random field using both photometric, geometric and illumi-" 631d21e51ca9100f1eca3c80dcf42db81cfc7e2b,Interactive Person Following and Gesture Recognition with a Flying Robot,"Interactive Person Following and Gesture Recognition with a Flying Robot Tayyab Naseer*, J¨urgen Sturm†, Wolfram Burgard*, and Daniel Cremers† *Department of Computer Science, University of Freiburg, Germany Department of Computer Science, Technical University of Munich, Germany" 63c7c0511e82172b6b60af21e56df68e2c6ab228,Target-based evaluation of face recognition technology for video surveillance applications,"Target-based evaluation of face recognition technology for video surveillance applications Dmitry Gorodnichy and Eric Granger" 63cbfc7bfabd1e234c779f8445ea775b74d8fbe8,Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks,"Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks Yi Han School of Computing and Information Systems University of Melbourne Ben Rubinstein School of Computing and Information Systems University of Melbourne" 63f2c3e312d07c6452bdad0a8adef1b879950500,Multi-stage sampling with boosting cascades for pedestrian detection in images and videos,"Multi-stage Sampling with Boosting Cascades for Pedestrian Detection in Images and Videos Giovanni Gualdi, Andrea Prati, and Rita Cucchiara University of Modena and Reggio Emilia(cid:2), Italy" 6321b0a9f210203a869cf38ca71d9b099943fb62,Kernels on Attributed Pointsets with Applications,"Kernels on Attributed Pointsets with Applications Mehul Parsana Sourangshu Bhattacharya Chiranjib Bhattacharyya K. R. Ramakrishnan" 63ed42249d7cbb21a4b0d42419d42b014ff114eb,Comprehensive Parameter Sweep for Learning-Based Detector on Traffic Lights,"Aalborg Universitet Comprehensive Parameter Sweep for Learning-based Detector on Traffic Lights Jensen, Morten Bornø; Philipsen, Mark Philip; Trivedi, Mohan M.; Moeslund, Thomas B. Published in: Advances in Visual Computing. ISVC 2016 DOI (link to publication from Publisher): 0.1007/978-3-319-50832-0_10 Publication date: Document Version Accepted author manuscript, peer reviewed version Link to publication from Aalborg University Citation for published version (APA): Jensen, M. B., Philipsen, M. P., Trivedi, M. M., & Moeslund, T. B. (2016). Comprehensive Parameter Sweep for Learning-based Detector on Traffic Lights. In Advances in Visual Computing. ISVC 2016: Lecture Notes in Computer Science (LNCS) (Vol. 10073, pp. 92-100). Springer. DOI: 10.1007/978-3-319-50832-0_10 General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners nd it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. ? Users may download and print one copy of any publication from the public portal for the purpose of private study or research. ? You may not further distribute the material or use it for any profit-making activity or commercial gain" 63ebe80e020d902bc1fdc865c23a9ad7d1eac17a,Exploring the feasibility of subliminal priming on smartphones,"Exploring the Feasibility of Subliminal Priming on Anonymised for blind review Smartphones Affiliation City, Country e-mail address" 637648198f9e91654ce27eaaa40512f2dc870fc1,Survey of Visual Question Answering: Datasets and Techniques,"Survey of Visual Question Answering: Datasets and Techniques Akshay Kumar Gupta Indian Institute of Technology Delhi" 63c022198cf9f084fe4a94aa6b240687f21d8b41,Consensus Message Passing for Layered Graphical Models, 635bea02dae6d4402b53eb3b31930b53ef00adc0,Unsupervised Feature Learning for Dense Correspondences Across Scenes,"Unsupervised Feature Learning for Dense Correspondences cross Scenes Chao Zhang, Chunhua Shen, Tingzhi Shen v1 July 2014; v2 December 2014; v3 April 2015" 63a1efb1dc6d269b9f77aea5adad914c30e62686,Predicting Human Trajectories in Multi-Class Settings,"Predicting Human Trajectories in Multi-Class Settings Karthik Raju (kraju444), Max Chang (mchang4) December 17, 2016 Introduction Related Work In recent years, autonomous navigation has be- ome of increasing prominence with companies like Uber, Google, and Tesla building their state-of-the- rt self-driving cars. There are other opportuni- ties, however, for self-navigating vehicles in non-road settings, including social robots that can navigate rowded spaces. Examples include driving through malls, walking dogs through populated parks, or help- ing blind pedestrians navigate around others. In navigating crowded areas, autonomous agents must adopt a set of common sense rules and social onventions in interacting with other objects in the same proximity. For example, when humans are de- iding how to walk on a crowded sidewalk, they plan" 63db76fc3ab23beb921be682d70eb021cb6c4f16,How Polarized Have We Become? A Multimodal Classification of Trump Followers and Clinton Followers, 63c65e8584d2c3fb8833af772eb713f438cbdfe0,Exposing seam carving forgery under recompression attacks by hybrid large feature mining,"Cancún Center, Cancún, México, December 4-8, 2016 978-1-5090-4846-5/16/$31.00 ©2016 IEEE" 631483c15641c3652377f66c8380ff684f3e365c,Sync-DRAW: Automatic GIF Generation using Deep Recurrent Attentive Architectures,"Sync-DRAW: Automatic Video Generation using Deep Recurrent A(cid:130)entive Architectures Gaurav Mi(cid:138)al∗ Tanya Marwah∗ IIT Hyderabad Vineeth N Balasubramanian IIT Hyderabad" 632fa986bed53862d83918c2b71ab953fd70d6cc,What Face and Body Shapes Can Tell About Height,"GÜNEL ET AL.: WHAT FACE AND BODY SHAPES CAN TELL ABOUT HEIGHT What Face and Body Shapes Can Tell About Height Semih Günel Helge Rhodin Pascal Fua CVLab EPFL, Lausanne, Switzerland" 6388fb33b274d74a158aa3ed658a2d5d9e6553d2,Modeling scenes with local descriptors and latent aspects,"Modeling Scenes with Local Descriptors and Latent Aspects P. Quelhasy, F. Monayy, J.-M. Odobezy, D. Gatica-Perezy, T. Tuytelaarsz, and L. Van Goolz yIDIAP Research Institute, Martigny, Switzerland zKatholieke Universiteit, Leuven, Belgium fquelhas, monay, odobez, ftinne.tuytelaars," 63c109946ffd401ee1195ed28f2fb87c2159e63d,Robust Facial Feature Localization Using Improved Active Shape Model and Gabor Filter,"MVA2011 IAPR Conference on Machine Vision Applications, June 13-15, 2011, Nara, JAPAN Robust Facial Feature Localization using Improved Active Shape Model and Gabor Filter Hui-Yu Huang Engineering, National Formosa University, Taiwan E-mail:" 63cf5fc2ee05eb9c6613043f585dba48c5561192,Prototype Selection for Classification in Standard and Generalized Dissimilarity Spaces,"Prototype Selection for Classification in Standard nd Generalized Dissimilarity Spaces" 632931c2da6d558cca3c9e57cd27bca2dd36fdca,Secured access to terminals and teleservices using biometrics verification,"Secured access to terminals and teleservices using biometrics verification G. Richard1, Y. Menguy, I. Guis, P. Lockwood Matra Nortel Communications Rue JP Timbaud, 78392 Bois d’Arcy, France." 63dbacac269c29b46b2b0bddbef828db025689dd,Deep Structure Inference Network for Facial Action Unit Recognition,"Deep Structure Inference Network for Facial Action Unit Recognition Ciprian A. Corneanu1, Meysam Madadi2,3, Sergio Escalera1,2 Dept. Mathematics and Informatics, Universitat de Barcelona, Catalonia, Spain Computer Vision Center, Edifici O, Campus UAB, 08193 Bellaterra (Barcelona), Catalonia, Spain Dept. of Computer Science, Univ. Aut`onoma de Barcelona (UAB), 08193 Bellaterra, Catalonia, Spain" 634541661d976c4b82d590ef6d1f3457d2857b19,Advanced Techniques for Face Recognition under Challenging Environments,"AAllmmaa MMaatteerr SSttuuddiioorruumm –– UUnniivveerrssiittàà ddii BBoollooggnnaa in cotutela con Università di Sassari DOTTORATO DI RICERCA IN INGEGNERIA ELETTRONICA, INFORMATICA E DELLE TELECOMUNICAZIONI Ciclo XXVI Settore Concorsuale di afferenza: 09/H1 Settore Scientifico disciplinare: ING-INF/05 ADVANCED TECHNIQUES FOR FACE RECOGNITION UNDER CHALLENGING ENVIRONMENTS TITOLO TESI YUNLIAN SUN Presentata da: Coordinatore Dottorato ALESSANDRO VANELLI-CORALLI Relatore DAVIDE MALTONI Relatore MASSIMO TISTARELLI Esame finale anno 2014" 6358b95b1c97df4f10f57a90913f672e44d2094b,Opponent colors for human detection,"Opponent Colors for Human Detection Rao Muhammad Anwer, David V´azquez, and Antonio M. L´opez Computer Vision Center and Computer Science Dpt., Universitat Aut`onoma de Barcelona -- www.cvc.uab.es/adas Edifici O, 08193 Bellaterra, Barcelona, Spain" 6374e5307c699da00875a858134653c16d5fd035,Audio-Visual Speech Modeling for Continuous Speech Recognition,"IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 2, NO. 3, SEPTEMBER 2000 Audio-Visual Speech Modeling for Continuous Speech Recognition Stéphane Dupont and Juergen Luettin" 6306ee4a2bab01890eacd74e55aedb207fed0353,Structure-Measure: A New Way to Evaluate Foreground Maps,"Structure-measure: A New Way to Evaluate Foreground Maps Deng-Ping Fan1 Ming-Ming Cheng1 ∗ CCCE, Nankai University Yun Liu1 Tao Li1 CRCV, UCF Ali Borji2 http://dpfan.net/smeasure/" 6372262685162f3f11ef7ac1882c327e98564875,A Survey of Approaches for Curve Based Facial Surface Representations For Three-Dimensional Face Recognition,"A Survey of Approaches for Curve Based Facial Surface Representations For Three-Dimensional Face Recognition Aouragh Salima1,3, Sbaa Salim2, Taleb-Ahmed Abdelmalik3 Department of Electrical engineering, Kasdi Merbah University, Ouargla, Algeria. Department of Electrical engineering, Mohamed Kheider University, Biskra, Algeria. LAMIH UMR CNRS 8201 UVHC, University of Valenciennes and Hainaut Cambrésis, France." 63488398f397b55552f484409b86d812dacde99a,Learning Universal Multiview Age Estimator by Video Contexts,"Learning Universal Multi-view Age Estimator by Video Contexts Zheng Song1, Bingbing Ni3, Dong Guo4, Terence Sim2, Shuicheng Yan1 Department of Electrical and Computer Engineering, 2 School of Computing, National University of Singapore; {zheng.s, Advanced Digital Sciences Center, Singapore; 4 Facebook" 6388c3f3559b61632942856bbede67b724542c9e,Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 8, No. 11, 2017 Multi-Target Tracking Using Hierarchical Convolutional Features and Motion Cues Heba Mahgoub, Khaled Mostafa, Khaled T. Wassif, Ibrahim Farag Faculty of Computers and Information Cairo University Cairo, Egypt" 6332a99e1680db72ae1145d65fa0cccb37256828,Pose and Face Recovery via Spatio-temporal GrabCut Human Segmentation,"MASTER IN COMPUTER VISION AND ARTIFICIAL INTELLIGENCE REPORT OF THE RESEARCH PROJECT OPTION: COMPUTER VISION Pose and Face Recovery via Spatio-temporal GrabCut Human Segmentation Author: Antonio Hernández Vela Date: 13/07/2010 Advisor: Sergio Escalera Guerrero" 636027f52ab111b2b22332ab2ec5346d03aac305,Unsupervised learning of foreground object detection,"Unsupervised learning of foreground object detection Ioana Croitoru · Simion-Vlad Bogolin · Marius Leordeanu" 630ae5a734dc9dc9d46b05278f0bcb5a252f6998,FACIAL EXPRESSION RECOGNITION USING AAM ALGORITHM,"Generated by Foxit PDF Creator © Foxit Software http://www.foxitsoftware.com For evaluation only. FACIAL EXPRESSION RECOGNITION USING AAM ALGORITHM Thanh Nguyen Duc, Tan Nguyen Huu, Luy Nguyen Tan* Division of Automatic Control, Ho Chi Minh University of Technology, Vietnam *National key lab for Digital Control & System Engineering, Vietnam" 63f38f60022ab78aa5e47bd84070547409ab3cc8,The Use of Semantic Human Description as a Soft Biometric,"The Use of Semantic Human Description as a Soft Biometric Sina Samangooei Baofeng Guo Mark S. Nixon" 63b89e654124eb2b8edeeb82c6373bdcf228744e,Single-Image 3D Scene Parsing Using Geometric Commonsense,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) image I3D reconstructed sceneFigure1:Single-view3DscenereconstructionusingGeometriccommonsense.Top:theworldisfullofcommonsenseovergeo-metricdimensions,e.g.,thatasedanisabout4.5meterslong.Bot-tom:exemplarresultoftheproposedmethod,includingsynthesizedimage(left),planarsegmentation(middle),anddepthmap(right).geometriccommonsensefor3Dsceneparsing.Suchapars-ingtaskaimstosegmentbothlow-levelsceneentities(e.g.,straightedges,semanticregions)andobject-levelsceneenti-ties(e.g.,human,vehicles)in2Dimages,andestimatetheirgeometricdimensionsinthe3Dworld[Hoiemetal.,2005;DelPeroetal.,2013;Liuetal.,2014;Wangetal.,2015a;Mottaghietal.,2016].Mostexisting3Dparsingalgo-rithms[Hoiemetal.,2008]aredesignedforaparticu-lartypeofscenecategories,e.g.,urban[Liuetal.,2014;Guptaetal.,2010],indoor[Wangetal.,2015b].Howev-er,apracticalAIsystem,e.g.,autonomousdriving,usuallyneedstodealwithawidevarietyofscenecategories.Oursolutiontotheabovechallengesismotivatedbythefactthatwehumanbeings,unconsciouslysometimes,uti-lizerichpriorknowledgeofthegeometricdimensionsofsceneentitiestounderstandthescenestructuresinimagesorvideos[Davisetal.,1993].Thisknowledgecanberoughlydividedintotwotypes:i)priordistributionsoverasingledi-mensionofobjects,e.g.,theheightofafemaleadultisabout1.75meters,orthatthelengthofasedanisabout4.5meters;ii)pair-wisecomparisonsbetweenthedimensionsofdifferentsceneentitiesatbothobject-level,e.g.,human,windows,ve-hicles,etc.,andpart-level,e.g.,straightedges,planarregions,etc.AsillustratedinFigure1,forexample,thewindowedgesonthesamefacadeareparalleltoeachotherandareorthog-onaltotheedgesontheground,abuildingishigherthanahuman,orthelengthofallsedansareroughlyequal.Theseu-naryandpair-wiseknowledge,onceacquired,arevalidacross" 630120d6cb9744f00d572d55701f90aff1951710,Analysing object detectors from the perspective of co-occurring object categories,"Analysing object detectors from the perspective of o-occurring object categories Csaba Nemes Nokia Bell Labs Budapest, Hungary Sandor Jordan Nokia Bell Labs Budapest, Hungary Email: Email:" 63f2d3588994f19886e3131d8615f7375d41ef9c,Can low level image differences account for the ability of human observers to discriminate facial identity?,"http://journalofvision.org/8/15/5/ Can low level image differences account for the ability of human observers to discriminate facial identity? Danelle A. Wilbraham Ohio State University, USA James C. Christensen Aleix M. Martinez James T. Todd Ohio State University, USA Ohio State University, USA Ohio State University, USA A fundamental difficulty for image- or appearance-based models of face recognition is to distinguish variations in image structure between two different individuals from those that can occur for a given individual due to changes in lighting, facial expression, or pose. The research described in the present article was designed to examine how human observers are able to cope with this problem. In two experiments, observers performed either a match-to-sample task (Experiment 1) or same–different identity judgments (Experiment 2) for photographs of unfamiliar individuals. A key aspect of these studies is that the matching or same stimulus pairs were never identical; that is to say, they always differed in terms of facial expression or the pattern of illumination. In order to provide a quantitative assessment of appearance-based models, we lso measured the optical differences for each pair of same or different images using a variety of possible distance metrics ased on the pattern of pixel intensities or wavelet decompositions. These difference measures were then correlated with" 62dd66f9f4995cfdaafb479de50363ce0255b1bd,2 Feature Extraction Based on Wavelet Moments and Moment Invariants in Machine Vision Systems,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 6211ba456908d605e85d102d63b106f1acb52186,Visual Interpretability forDeepLearning,"Zhang et al. / Front Inform Technol Electron Eng in press Frontiers of Information Technology & Electronic Engineering www.jzus.zju.edu.cn; engineering.cae.cn; www.springerlink.com ISSN 2095-9184 (print); ISSN 2095-9230 (online) E-mail: Visual Interpretability for Deep Learning∗ Quanshi Zhang and Song-Chun Zhu (University of California, Los Angeles) E-mail:" 6215c5713adeacbb33b9d1c4c739f2b0b50dd17f,PART-BASED 3 D FACE RECOGNITION UNDER POSE AND EXPRESSION VARIATIONS,"PART-BASED 3D FACE RECOGNITION UNDER POSE AND EXPRESSION VARIATIONS Hamdi Dibeklio˘glu B.S, in Computer Engineering, Yeditepe University, 2006 Submitted to the Institute for Graduate Studies in Science and Engineering in partial fulfillment of the requirements for the degree of Master of Science Graduate Program in Computer Engineering Bo˘gazi¸ci University" 62b90583723174220b26c92bd67f6c422ad75570,DNA-GAN: LEARNING DISENTANGLED REPRESEN-,"Under review as a conference paper at ICLR 2018 DNA-GAN: LEARNING DISENTANGLED REPRESEN- TATIONS FROM MULTI-ATTRIBUTE IMAGES Anonymous authors Paper under double-blind review" 620c3f6605e528503a99a8832200d5afdf156c20,F2ID: a personal identification system using faces and fingerprints,"ndFingerprints AnilJain,LinHong,andYatinKulkarni DepartmentofComputerScience MichiganStateUniversity EastLansing,MI FID:APersonalIdenti(cid:12)cationSystemUsingFaces Keywords:Biometrics,Personalidenti(cid:12)cation,Minutiae,Fingerprintmatching,Face recognition,Eigenface,Decisionfusion." 62a44dbadf36099ea4b76c0656adc2ad4c8ad734,Using Skin Melanin Layer for Facial Pore Identification in RGB Digital Images,"International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 4, Issue 8, August 2014) Using Skin Melanin Layer for Facial Pore Identification in RGB Digital Images Carlos Villegas1, Joan Climent2, C. Rodrigo Villegas3 Engineering Department, Universidad Iberoamericana, Mexico City ESSAI Department, Universitat Politecnica de Catalunya, Barcelona, Spain Xin Cognicion Consulting, Mexico City" 627107c02c2df1366965f11678dd3c4fb14ac9b3,CONNECTING IMAGES AND NATURAL LANGUAGE A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"CONNECTING IMAGES AND NATURAL LANGUAGE A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Andrej Karpathy August 2016" 6221e550baf4d6266434f897f45e5438b85d8207,Efficiency of Recognition Methods for Single Sample per Person Based Face Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 624077c8c8c9306c12671870cacc0fb13ff20324,"Smart, Sparse Contours to Represent and Edit Images","Sparse, Smart Contours to Represent and Edit Images Tali Dekel 1 Chuang Gan 2 Dilip Krishnan 1 Ce Liu 1 William T. Freeman 1,3 Google Research 2 MIT-Watson AI Lab 3 MIT-CSAIL Figure 1. Our method produces high quality reconstructions of images from information along a small number of contours: a source (512×512) image in (a) is reconstructed in (c) from gradient information stored at the set of colored contours in (b)2, which are less than 5% of the pixels. The model synthesizes hair texture, facial lines and shading even in regions where no input information is provided. Our model allows for semantically intuitive editing in the contour domain. Top-right: a caricature-like result (e) is created by moving and scaling some contours in (d). Bottom-right: hairs are synthesized by pasting a set of hair contours copied from a reference image. Edited ontours are marked in green while the original contours in red." 6225e9c2a9ee47b4d3d58313a839f6e170b48525,Shape-Aware Matching of Implicit Surfaces Based on Thin Shell Energies,"SHAPE AWARE MATCHING OF IMPLICIT SURFACES BASED ON THIN SHELL ENERGIES JOS ´E A. IGLESIAS, MARTIN RUMPF, AND OTMAR SCHERZER" 6289d2c4c47d7101861153bfe78c92d16cf4581b,A Cross-Core Performance Model for Heterogeneous Many-Core Architectures,"A Cross-Core Performance Model for Heterogeneous Many-Core Architectures Rui Pinheiro, Nuno Roma, and Pedro Tom´as (cid:63) INESC-ID, Instituto Superior T´ecnico, Universidade de Lisboa" 62d1b32d67e4a4b58a66cba91629aae5f7968962,Recurrent Neural Networks for Semantic Instance Segmentation,"Recurrent Neural Networks for Semantic Instance Segmentation Amaia Salvador1, M´ıriam Bellver2, V´ıctor Campos2, Manel Baradad1 Ferran Marques1 Jordi Torres2 and Xavier Giro-i-Nieto1 Universitat Polit`ecnica de Catalunya 2Barcelona Supercomputing Center" 6275aa21331a2712222b7ab2116e9589e21ae82c,Prediction of Manipulation Actions,"Noname manuscript No. (will be inserted by the editor) Prediction of Manipulation Actions Cornelia Ferm¨uller · Fang Wang · Yezhou Yang · Konstantinos Zampogiannis · Yi Zhang · Francisco Barranco · Michael Pfeiffer the date of receipt and acceptance should be inserted later" 62e8010e2ac1523d3a3e7e1c13cb34e63e85ce04,Transfer Learning for Action Unit Recognition,"Transfer Learning for Action Unit Recognition Yen Khye Lim1, Zukang Liao1, Stavros Petridis1 and Maja Pantic1,2" 627412bf4cf2706f6dc9530313ecf06bbc532cca,Human Pose Estimation from Video and Inertial Sensors,"Human Pose Estimation from Video and Inertial Sensors Von der Fakultät für Elektrotechnik und Informatik der Gottfried Wilhelm Leibniz Universität Hannover zur Erlangung des akademischen Grades Doktor-Ingenieur (abgekürzt: Dr.-Ing.) genehmigte Dissertation Gerard Pons Moll geboren am 25. Oktober 1984 in Barcelona." 621ea1f1e364262348135c803557e7b3454a804e,Generative spatiotemporal modeling of neutrophil behavior,"Accepted to 2018 IEEE International Symposium on Biomedical Imaging Copyright ©2018 IEEE Generative Spatiotemporal Modeling Of Neutrophil Behavior Narita Pandhe(cid:63) Balazs Rada† Shannon Quinn(cid:63) (cid:63) Department of Computer Science Department of Infectious Diseases University of Georgia" 6236962ce0d627fc23774f0680e77069b9667803,Fitting a Morphable Model to Pose and Shape of a Point Cloud,"Fitting a Morphable Model to Pose and Shape of a Point Cloud David C. Schneider, Peter Eisert Fraunhofer Heinrich Hertz Institute, Einsteinufer 37, 10587 Berlin, Germany" 626c12d6ccb1405c97beca496a3456edbf351643,Conditional Variance Penalties and Domain Shift Robustness,"Conditional Variance Penalties and Domain Shift Robustness Christina Heinze-Deml & Nicolai Meinshausen Seminar for Statistics ETH Zurich Zurich, Switzerland" 62cf8c07ca6c4c7817f6a5682eb2d7cde76198ae,Boosted Metric Learning for Efficient Identity-Based Face Retrieval,"NEGREL ET AL.: BOOSTED METRIC LEARNING FOR FACE RETRIEVAL Boosted Metric Learning for Efficient Identity-Based Face Retrieval Romain Negrel Alexis Lechervy Frederic Jurie GREYC, CNRS UMR 6072, ENSICAEN Université de Caen Basse-Normandie France" 622949b1aacd316c60a7034c44121c698a3fb6a4,Highway Driving Dataset for Semantic Video Segmentation,"KIM, YIM, AND KIM: HIGHWAY DRIVING DATASET Highway Driving Dataset for Semantic Video Segmentation Byungju Kim Junho Yim Junmo Kim* School of Electrical Engineering Korea Advanced Institute of Science nd Technology (KAIST), South Korea" 623da0faea1f98f238936e34f361518829edfdf4,Digital geometry image analysis for medical diagnosis,"Digital Geometry Image Analysis for Medical Diagnosis Jiandong Fang Shiaofen Fang Jeffrey Huang Mihran Tuceryan Department of Computer and Information Science Indiana University Purdue University Indianapolis 723 W. Michigan St., SL 280 Indianapolis, IN 46202, USA -317-274-9731" 62374b9e0e814e672db75c2c00f0023f58ef442c,Frontal Face Authentication Using Discriminating Grids with Morphological Feature Vectors,"Frontalfaceauthenticationusingdiscriminatinggridswith morphologicalfeaturevectors A.Tefas C.Kotropoulos I.Pitas DepartmentofInformatics,AristotleUniversityofThessaloniki Box,Thessaloniki,GREECE EDICSnumbers:-KNOWContentRecognitionandUnderstanding -MODAMultimodalandMultimediaEnvironments Anovelelasticgraphmatchingprocedurebasedonmultiscalemorphologicaloperations,thesocalled morphologicaldynamiclinkarchitecture,isdevelopedforfrontalfaceauthentication.Fastalgorithms forimplementingmathematicalmorphologyoperationsarepresented.Featureselectionbyemploying linearprojectionalgorithmsisproposed.Discriminatorypowercoe(cid:14)cientsthatweighthematching errorateachgridnodearederived.Theperformanceofmorphologicaldynamiclinkarchitecturein frontalfaceauthenticationisevaluatedintermsofthereceiveroperatingcharacteristicontheMVTS faceimagedatabase.Preliminaryresultsforfacerecognitionusingtheproposedtechniquearealso presented. Correspondingauthor:I.Pitas DRAFT September," 62c435bc714f13a373926e3b1914786592ed1fef,Classification Signboard Detection Face Detection Animal Detection Texture Detection GPS + IMU Depth Localization Module Central Control Speech,"MAVI: An Embedded Device to Assist Mobility of Visually Impaired Rajesh Kedia∗, Yoosuf K K∗, Pappireddy Dedeepya∗, Munib Fazal∗, Chetan Arora†, and M. Balakrishnan∗ Indian Institute of Technology Delhi Indraprastha Institute of Information Technology Delhi Contact Email:" 62070fbd22b2a4bba830668c2e9720ec4bff4171,Fast human detection using template matching for gradient images and aSC descriptors based on subtraction stereo,"978-1-4799-2341-0/13/$31.00 ©2013 IEEE ICIP 2013" 62857147a6809063671614d62f43605130757b1c,Unsupervised Discriminant Projection Analysis for Feature Extraction,"Unsupervised Discriminant Projection Analysis for Feature Extraction Jian Yang David Zhang Biometrics Centre, Department of Computing, Hong Kong Polytechnic University, Kowloon, Hong Kong Zhong Jin Jing-yu Yang Department of Computer Science, Nanjing University of Science and Technology, Nanjing 210094, P. R. China" 62e0edcf5a2bab8163851ca1d6ce50d42c367660,Generalized two-dimensional linear discriminant analysis with regularization,"JOURNAL OF LATEX CLASS FILES, VOL. , NO. Generalized two-dimensional linear discriminant nalysis with regularization Chun-Na Li, Yuan-Hai Shao,Wei-Jie Chen, Zhen Wang and Nai-Yang Deng" 62e0380a86e92709fe2c64e6a71ed94d152c6643,Facial emotion recognition with expression energy,"Facial Emotion Recognition With Expression Energy Albert Cruz Center for Research in Intelligent Systems 16 Winston Chung Hall Bir Bhanu Center for Research in Intelligent Systems 16 Winston Chung Hall Ninad Thakoor Center for Research in Intelligent Systems 16 Winston Chung Hall Riverside, CA, 92521-0425, Riverside, CA, 92521-0425, Riverside, CA, 92521-0425," 62d1a31b8acd2141d3a994f2d2ec7a3baf0e6dc4,Noise-resistant network: a deep-learning method for face recognition under noise,"Ding et al. EURASIP Journal on Image and Video Processing (2017) 2017:43 DOI 10.1186/s13640-017-0188-z EURASIP Journal on Image nd Video Processing R ES EAR CH Noise-resistant network: a deep-learning method for face recognition under noise Yuanyuan Ding1,2, Yongbo Cheng1,2, Xiaoliu Cheng1, Baoqing Li1*, Xing You1 and Xiaobing Yuan1 Open Access" 62aeecbe5db3e4ed6b783f4b580157f4f1c8ba45,"Haar like and LBP based features for face , head and people detection in video sequences","Author manuscript, published in ""International Workshop on Behaviour Analysis and Video Understanding (ICVS 2011) (2011)" 6273b3491e94ea4dd1ce42b791d77bdc96ee73a8,"Evaluating Appearance Models for Recognition, Reacquisition, and Tracking","Evaluating Appearance Models for Recognition, Reacquisition, and Tracking Doug Gray Shane Brennan Hai Tao University of California, Santa Cruz 156 High St., Santa Cruz, CA 95064 {dgray, shanerb," 626859fe8cafd25da13b19d44d8d9eb6f0918647,Activity Recognition Based on a Magnitude-Orientation Stream Network,"Activity Recognition based on a Magnitude-Orientation Stream Network Carlos Caetano, Victor H. C. de Melo, Jefersson A. dos Santos, William Robson Schwartz Smart Surveillance Interest Group, Department of Computer Science Universidade Federal de Minas Gerais, Belo Horizonte, Brazil" 62007c30f148334fb4d8975f80afe76e5aef8c7f,Eye In-Painting with Exemplar Generative Adversarial Networks,"Eye In-Painting with Exemplar Generative Adversarial Networks Brian Dolhansky, Cristian Canton Ferrer Facebook Inc. Hacker Way, Menlo Park (CA), USA {bdol," 62f0d8446adee6a5e8102053a63a61af07ac4098,Facial point detection using convolutional neural network transferred from a heterogeneous task,"FACIAL POINT DETECTION USING CONVOLUTIONAL NEURAL NETWORK TRANSFERRED FROM A HETEROGENEOUS TASK Takayoshi Yamashita* Taro Watasue** Yuji Yamauchi* Hironobu Fujiyoshi* **Tome R&D *Chubu University, 200, Matsumoto-cho, Kasugai, AICHI" 62dccab9ab715f33761a5315746ed02e48eed2a0,A Short Note about Kinetics-600,"A Short Note about Kinetics-600 Jo˜ao Carreira Eric Noland Andras Banki-Horvath Chloe Hillier Andrew Zisserman" 62694828c716af44c300f9ec0c3236e98770d7cf,Identification of Action Units Related to Affective States in a Tutoring System for Mathematics,"Padrón-Rivera, G., Rebolledo-Mendez, G., Parra, P. P., & Huerta-Pacheco, N. S. (2016). Identification of Action Units Related to Identification of Action Units Related to Affective States in a Tutoring System Gustavo Padrón-Rivera1, Genaro Rebolledo-Mendez1*, Pilar Pozos Parra2 and N. Sofia Facultad de Estadística e Informática, Universidad Veracruzana, Mexico // 2Universidad Juárez Autónoma de Tabasco, Mexico // // // // for Mathematics Huerta-Pacheco1 *Corresponding author" 62306db738cfddd39e1f12e22bce0f7615ce58b8,Face detection with colour segmentation and fuzzy template matching,"Proceedings of the 17th World Congress The International Federation of Automatic Control Seoul, Korea, July 6-11, 2008 978-1-1234-7890-2/08/$20.00 © 2008 IFAC 3773 0.3182/20080706-5-KR-1001.2215" 140eaf273eabe233f67257d1ae7ee44a8f21e502,Computational Maps in the Visual Cortex,"Risto Miikkulainen, James A. Bednar, Yoonsuck Choe, and Joseph Sirosh Computational Maps in the Visual Cortex February 6, 2005 Springer Berlin Heidelberg NewYork Hong Kong London Milan Paris Tokyo" 147c33df99dd52502d65fe390ee45c585349b3b3,Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving,"Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving Yuhu Shan, Wen Feng Lu, Chee Meng Chew" 14fee990a372bcc4cb6dc024ab7fc4ecf09dba2b,Modeling Spatio-Temporal Human Track Structure for Action Localization,"Modeling Spatio-Temporal Human Track Structure for Action Localization Guilhem Ch´eron · Anton Osokin · Ivan Laptev · Cordelia Schmid" 14761b89152aa1fc280a33ea4d77b723df4e3864,Zero-Shot Learning via Visual Abstraction, 14a5feadd4209d21fa308e7a942967ea7c13b7b6,Content-based vehicle retrieval using 3D model and part information,"978-1-4673-0046-9/12/$26.00 ©2012 IEEE ICASSP 2012" 1414d4880e368414cbbbbd215e8b0471f185aa03,Face Detection in Low-Resolution Color Images,"Face Detection in Low-resolution Color Images Jun Zheng, Geovany A. Ramirez, and Olac Fuentes, Computer Science Department, University of Texas at El Paso, El Paso, Texas, 79968, U.S.A. No Institute Given" 14c988aa9086207b337dcc5611aad08422129b42,Human Relative Position Detection Based on Mutual Occlusion,"Human Relative Position Detection Based on Mutual Occlusion V´ıctor Borjas, Michal Drozdzal, Petia Radeva, and Jordi Vitri`a Facultat de Matem`atiques & Centre de Visi`o per Computador, Universitat de Barcelona, Campus UAB" 14fed18d838bf6b89d98837837ff314e61ab7c60,Deep Learning with Differential Privacy,"A preliminary version of this paper appears in the proceedings of the 23rd ACM Conference on Computer and Communications Security (CCS 2016). This is a full version. Deep Learning with Differential Privacy Martín Abadi∗ H. Brendan McMahan∗ October 25, 2016 Andy Chu∗ Ilya Mironov∗ Li Zhang∗ Ian Goodfellow† Kunal Talwar∗" 149f3cc167b046dc790b1f4f1c48eeb31e898403,A study of vehicle detector generalization on U.S. highway,"Windsor Oceanico Hotel, Rio de Janeiro, Brazil, November 1-4, 2016 978-1-5090-1889-5/16/$31.00 ©2016 IEEE" 149e5e5eeea5a9015ab5ae755f62c45ef70fa79b,Hierarchical Convolutional Features for Visual Tracking,"Hierarchical Convolutional Features for Visual Tracking Chao Ma Jia-Bin Huang Xiaokang Yang Ming-Hsuan Yang UC Merced" 14e428f2ff3dc5cf96e5742eedb156c1ea12ece1,Facial Expression Recognition Using Neural Network Trained with Zernike Moments,"Facial Expression Recognition Using Neural Network Trained with Zernike Moments Mohammed Saaidia Dept. Génie-Electrique Université M.C.M Souk-Ahras Souk-Ahras, Algeria" 1436d72a51feefda3278068a164d263f6d845236,INTERACTIVE LEARNING A PERSON DETECTOR : FEWER CLICKS – LESS FRUSTRATION 1,"INTERACTIVE LEARNING A PERSON DETECTOR: FEWER CLICKS – LESS FRUSTRATION1 Peter M. Roth2, Helmut Grabner2, Christian Leistner2, Martin Winter2, and Horst Bischof2" 14bf85bacf15241c500db72c145b0490a14addaa,Generalization in Holistic versus Analytic Processing of Faces,"Generalization in Holistic versus Analytic Processing of Faces M. Bicego∗ A.A. Salah DEIR - University of Sassari, Centrum voor Wiskunde en Informatica, via Torre Tonda, 34 07100, Sassari (Italy) PNA4 - Signals and Images, 94079, Amsterdam (The Netherlands) E. Grosso M. Tistarelli L. Akarun DEIR - University of Sassari, DAP - University of Sassari, Perceptual Intelligence Lab. via Torre Tonda, 34 07100, Sassari (Italy) piazza Duomo, 6 07041, Alghero (Italy) Bo˘gazic¸i University," 14a01628169a3a060b6af5d5dcdeeb584b648abf,Semi-Supervised Multiresolution Classification Using Adaptive Graph Filtering With Application to Indirect Bridge Structural Health Monitoring,"Semi-Supervised Multiresolution Classification Using Adaptive Graph Filtering with Application to Indirect Bridge Structural Health Monitoring Siheng Chen, Student Member, IEEE, Fernando Cerda, Piervincenzo Rizzo, Jacobo Bielak, James H. Garrett and Jelena Kovaˇcevi´c, Fellow, IEEE" 1442319de86d171ce9595b20866ec865003e66fc,Vision-Based Fall Detection with Convolutional Neural Networks,"Vision-Based Fall Detection with Convolutional Neural Networks Adri´an Nu˜nez-Marcos1, Gorka Azkune1, Ignacio Arganda-Carreras234 DeustoTech - University of Deusto Avenida de las Universidades, 24 - 48007, Bilbao, Spain Dept. of Computer Science and Artificial Intelligence, Basque Country University, San Sebastian, Spain P. Manuel Lardizabal, 1 - 20018, San Sebastian, Spain Ikerbasque, Basque Foundation for Science, Bilbao, Spain Maria Diaz de Haro, 3 - 48013 Bilbao, Spain Donostia International Physics Center (DIPC), San Sebastian, Spain P. Manuel Lardizabal, 4 - 20018, San Sebastian, Spain" 148721b162dd355812fae94c8aaf365e5e2c3a79,"Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation","Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation Ruining He UC San Diego Chen Fang Adobe Research Zhaowen Wang Adobe Research Julian McAuley UC San Diego" 140dbcb0be3ce7961ed551f129698e9ad4c9aa8c,Interactive Learning and its Role in Pervasive Robotics,"Interactive Learning and its Role in Pervasive Robotics Cynthia Matuszek Dieter Fox Nicholas FitzGerald Evan Herbst" 143e3ec5a5a11547da2d77a17d0ca7b1940280b5,"People detection, tracking and re-identification through a video camera network. (Détection, suivi et ré-identification de personnes à travers un réseau de caméra vidéo)","People detection, tracking and re-identification through video camera network Malik Souded To cite this version: Malik Souded. People detection, tracking and re-identification through a video camera network. Other [cs.OH]. Université Nice Sophia Antipolis, 2013. English. . HAL Id: tel-00913072 https://tel.archives-ouvertes.fr/tel-00913072v2 Submitted on 29 Jan 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 14b311b848b51b7b5345573a289b1cedcbb4d581,Instance Similarity Deep Hashing for Multi-Label Image Retrieval,"Instance Similarity Deep Hashing for Multi-Label Image Retrieval Zheng Zhang, Qin Zou, Qian Wang, Yuewei Lin, and Qingquan Li" 1419956b08f9ab398cd2100ddec74271ef5fa72c,Joint detection and online multi-object tracking,"Joint detection and online multi-object tracking Hilke Kieritz, Wolfgang H¨ubner, and Michael Arens Fraunhofer IOSB, Germany" 140c95e53c619eac594d70f6369f518adfea12ef,Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A,"Pushing the Frontiers of Unconstrained Face Detection and Recognition: IARPA Janus Benchmark A Brendan F. Klare, Emma Taborsky , Austin Blanton , Jordan Cheney , Kristen Allen , Patrick Grother , Alan Mah , Anil K. Jain The development of accurate and scalable unconstrained face recogni- tion algorithms is a long term goal of the biometrics and computer vision ommunities. The term “unconstrained” implies a system can perform suc- essful identifications regardless of face image capture presentation (illumi- nation, sensor, compression) or subject conditions (facial pose, expression, occlusion). While automatic, as well as human, face identification in certain scenarios may forever be elusive, such as when a face is heavily occluded or aptured at very low resolutions, there still remains a large gap between au- tomated systems and human performance on familiar faces. In order to close this gap, large annotated sets of imagery are needed that are representative of the end goals of unconstrained face recognition. This will help continue to push the frontiers of unconstrained face detection and recognition, which re the primary goals of the IARPA Janus program. The current state of the art in unconstrained face recognition is high ccuracy (roughly 99% true accept rate at a false accept rate of 1.0%) on faces that can be detected with a commodity face detectors, but unknown ccuracy on other faces. Despite the fact that face detection and recognition research generally has advanced somewhat independently, the frontal face" 147b7998526ebbdf64b1662503b378d9f6456ccd,GENERATIVE ADVERSARIAL NETWORKS FOR IMAGE STEGANOGRAPHY,"Under review as a conference paper at ICLR 2017 GENERATIVE ADVERSARIAL NETWORKS FOR IMAGE STEGANOGRAPHY Denis Volkhonskiy2,3, Boris Borisenko3 and Evgeny Burnaev1,2,3 Skolkovo Institute of Science and Technology The Institute for Information Transmission Problems RAS (Kharkevich Institute) National Research University Higher School of Economics (HSE)" 14bf36c03e6fd5171794a2d56d18748b1ab3fd17,Challenges and design space of gaze-enabled public displays,"Challenges and Design Space of Gaze-enabled Public Displays Mohamed Khamis LMU Munich Munich, Germany Florian Alt LMU Munich Munich, Germany Andreas Bulling Max Planck Institute for Informatics Saarbrücken, Germany Permission to make digital or hard copies of part or all of this work for personal or lassroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author. Copyright is held by the owner/author(s). Ubicomp/ISWC’16 Adjunct, September 12–16, 2016, Heidelberg, Germany. ACM 978-1-4503-4462-3/16/09. http://dx.doi.org/10.1145/2968219.2968342" 14f457bcb5c3e294919512b132bb171bdcaf5ec2,UNDERSTANDING HUMAN ACTIONS IN STILL IMAGES A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY,"UNDERSTANDING HUMAN ACTIONS IN STILL IMAGES A DISSERTATION SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE AND THE COMMITTEE ON GRADUATE STUDIES OF STANFORD UNIVERSITY IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Bangpeng Yao August 2013" 146879bd04a1ab25dce3484bc587e5f2ff1b1d91,Securing Certificate Revocation through Speaker Verification : the CertiVeR Project,"Securing Certificate Revocation through Speaker Verification: the CertiVeR Project Javier R. Saeta1, Javier Hernando2, Oscar Manso3, Manel Medina3 Biometric Technologies, S.L. Barcelona, Spain TALP Research Center. Universitat Politècnica de Catalunya, Spain SeMarket, S.A. Barcelona, Spain" 1450296fb936d666f2f11454cc8f0108e2306741,Learning to Discover Cross-Domain Relations with Generative Adversarial Networks,"Learning to Discover Cross-Domain Relations with Generative Adversarial Networks Taeksoo Kim 1 Moonsu Cha 1 Hyunsoo Kim 1 Jung Kwon Lee 1 Jiwon Kim 1" 142dcfc3c62b1f30a13f1f49c608be3e62033042,Adaptive region pooling for object detection,"Adaptive Region Pooling for Object Detection Yi-Hsuan Tsai UC Merced Onur C. Hamsici Qualcomm Research, San Diego Ming-Hsuan Yang UC Merced" 14aad0d391a9491eb122d5b6af6c325a0e090dc7,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" 146e6504d473b92e56108b7276d96aebaa58ccfc,Model and Part Fusion for Vehicle Retrieval,"International Journal of Research in Advent Technology, Vol.2, No.5, May 2014 E-ISSN: 2321-9637 D Model and Part Fusion for Vehicle Retrieval M.Nagarasan1, T.N.Chitradevi2, S.Senthilnathan3 Department of computer science and engineering1,2, 3 Aditya institute of technology, Coimbatore.1, 3,Sri Ramakrishna Engineering College, Coimbatore2" 14fdec563788af3202ce71c021dd8b300ae33051,Social Influence Analysis based on Facial Emotions,"Social Influence Analysis based on Facial Emotions Pankaj Mishra, Rafik Hadfi, and Takayuki Ito Department of Computer Science and Engineering Nagoya Institute of Technology, Gokiso, Showa-ku, Nagoya, 466-8555 Japan {pankaj.mishra," 143ac3b7338e240b106863d35177c4567ef9c1aa,Euclidean & Geodesic Distance between a Facial Feature Points in Two-Dimensional Face Recognition System,"Euclidean & Geodesic Distance between a Facial Feature Points in Two-Dimensional Face Recognition System Rachid AHDID1, Khaddouj TAIFI1, Said SAFI1 and Bouzid MANAUT2" 143b54525bdda1f83965002616a4e7b5b9f523a3,A probabilistic patch based image representation using Conditional Random Field model for image classification,"A probabilistic patch based image representation using Conditional Random Field model for image classification Fariborz Taherkhani Department of Electrical Engineering and Computer Science, University of Wisconsin-Milwaukee, USA" 144ba4e9e64d4f9a5bb436c80c3c02b40e4092e0,Learning Video Features for Multi-label Classification,"Learning Video Features for Multi-Label Classification Shivam Garg[0000−0002−7213−3967]" 14860877a790d99296a990281b22e6b6a430b64f,Deep Over-sampling Framework for Classifying Imbalanced Data,"Deep Over-sampling Framework for Classifying Imbalanced Data Shin Ando1 and Chun Yuan Huang2 School of Management, Tokyo University of Science, -11-2 Fujimi, Chiyoda-ku, Tokyo, Japan School of Management, Tokyo University of Science, -11-2 Fujimi, Chiyoda-ku, Tokyo, Japan" 1434c9140ba724c9a92f478781e890434e7a0215,The role of global and feature based information in gender classification of faces: a comparison of human performance and computational models,"April 11, 2005 16:8 00007 st Reading (cid:13) World Scienti(cid:12)c Publishing Company THE ROLE OF GLOBAL AND FEATURE BASED INFORMATION IN GENDER CLASSIFICATION OF FACES: A COMPARISON OF HUMAN PERFORMANCE AND COMPUTATIONAL MODELS SAMARASENA BUCHALA(cid:3), NEIL DAVEYy, RAY J. FRANKz and MARTIN LOOMESx School of Computer Science, University of Hertfordshire, College Lane Hat(cid:12)eld, Herts. AL10 9AB, UK TIM M.GALE Department of Psychiatry, QEII Hospital, Welwyn Garden City, Herts., AL7 4HQ, UK Most computational models for gender classi(cid:12)cation use global information (the full face image) giv- ing equal weight to the whole face area irrespective of the importance of the internal features. Here, we use a global and feature based representation of face images that includes both global nd featural information. We use dimensionality reduction techniques and a support vector machine lassi(cid:12)er and show that this method performs better than either global or feature based repre- sentations alone. We also present results of human subjects performance on gender classi(cid:12)cation task and evaluate how the di(cid:11)erent dimensionality reduction techniques compare with human sub-" 147fe6bfc76f30ccacc3620662511e452bc395f6,A Survey of Face Recognition Techniques,"Invited Paper Journal of Information Processing Systems, Vol.5, No.2, June 2009 41 A Survey of Face Recognition Techniques Rabia Jafri* and Hamid R. Arabnia*" 1467c4ab821c3b340abe05a1b13a19318ebbce98,Multitask and transfer learning for multi-aspect data,"Multitask and Transfer Learning for Multi-Aspect Data Bernardino Romera Paredes A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy of University College London." 1451e7b11e66c86104f9391b80d9fb422fb11c01,Image privacy protection with secure JPEG transmorphing,"Research Article Image privacy protection with secure JPEG transmorphing ISSN 1751-9675 Received on 30th December 2016 Revised 13th July 2017 Accepted on 11th August 2017 doi: 10.1049/iet-spr.2016.0756 www.ietdl.org Lin Yuan1 , Touradj Ebrahimi1 Multimedia Signal Processing Group, Electrical Engineering Department, EPFL, Station 11, Lausanne, Switzerland E-mail:" 146f6f6ed688c905fb6e346ad02332efd5464616,"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","Show, Attend and Tell: Neural Image Caption Generation with Visual Attention Kelvin Xu Jimmy Lei Ba Ryan Kiros Kyunghyun Cho Aaron Courville Ruslan Salakhutdinov Richard S. Zemel Yoshua Bengio" 14e9eaa6ac23996e9a62060c8da90bdb7116ee37,Localization Recall Precision (LRP): A New Performance Metric for Object Detection,[cs.CV] 5 Jul 2018 14373c9fd08dee8f7195a88430121c69bbebbe1b,Head Pose Estimation Using Covariance of Oriented Gradients,"978-1-4244-4296-6/10/$25.00 ©2010 IEEE ICASSP 2010" 1456f147381bf7c385225d854c2fb48c19eca285,LCAV-31: a dataset for light field object recognition,"Computational Imaging XII, edited by Charles A. Bouman, Ken D. Sauer, Proc. of SPIE-IS&T Electronic Imaging, SPIE Vol. 9020, 902014 · © 2014 SPIE-IS&T · CCC code: 0277-786X/14/$18 · doi: 10.1117/12.2041097 Proc. of SPIE-IS&T/ Vol. 9020 902014-1" 1459d4d16088379c3748322ab0835f50300d9a38,Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning,"Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning Liang Lin, Guangrun Wang, Wangmeng Zuo, Xiangchu Feng, and Lei Zhang" c5844de3fdf5e0069d08e235514863c8ef900eb7,A Study on Similarity Computations in Template Matching Technique for Identity Verification,"Lam S K et al. / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 08, 2010, 2659-2665 A Study on Similarity Computations in Template Matching Technique for Identity Verification Lam, S. K., Yeong, C. Y., Yew, C. T., Chai, W. S., Suandi, S. A. Intelligent Biometric Group, School of Electrical and Electronic Engineering Engineering Campus, Universiti Sains Malaysia 4300 Nibong Tebal, Pulau Pinang, MALAYSIA Email:" c5e4467b5830d7dad4e940f0766ae728f22e38fc,Object recognition and localization,"Object recognition and localization Badri Narayana Patro Dept. of Electrical Engineering Ganesh Boddupally Dept. of Electrical Engineering" c5d9ac2f52c9fc229890798b9d6e4d899b72c525,Image Enhancement Technique using Adaptive Multiscale Retinex for Face Recognition Systems,"Image Enhancement Technique using Adaptive Multiscale Retinex for Face Recognition Systems Khairul Anuar Ishak1, Salina Abdul Samad1 M. A. Hannan1 and Maizura Mohd Sani2 Dept. of Electrical, Electronics and Systems Engineering Faculty of Engineering and Built Environment, University Kebangsaan Malaysia 3600, UKM Bangi, Selangor, Malaysia Institute of Microengineering and Nanoelectronics, University Kebangsaan Malaysia 3600, UKM Bangi, Selangor, Malaysia" c5ea084531212284ce3f1ca86a6209f0001de9d1,Audio-visual speech processing for multimedia localisation,"Audio-Visual Speech Processing for Multimedia Localisation Matthew Aaron Benatan Submitted in accordance with the requirements for the degree of Doctor of Philosophy The University of Leeds School of Computing September 2016" c50e498ede6f5216cffd0645e747ce67fae2096a,Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation,"Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation Shiming Ge, Senior Member, IEEE, Shengwei Zhao, Chenyu Li and Jia Li, Senior Member, IEEE" c50630e485d3c7785ea9e1f3bff35ea00e926a56,Deep Image Retrieval: Learning global representations for image search,"Deep Image Retrieval: Learning global representations for image search Albert Gordo, Jon Almaz´an, Jerome Revaud, and Diane Larlus Computer Vision Group, Xerox Research Center Europe" c5b9a96fcb07f538be3181922e5f1a24a7936783,"Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming","Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming Rogerio Bonatti, Yanfu Zhang, Sanjiban Choudhury, Wenshan Wang, and Sebastian Scherer" c55a6c98887b3079647d0edb4778d81bab6708f6,Self-Similarity Representation of Faces for Kin Relationships,"HCTL Open International Journal of Technology Innovations and Research (IJTIR) http://ijtir.hctl.org Volume 16, July 2015 e-ISSN: 2321-1814, ISBN (Print): 978-1-943730-43-8 Self-Similarity Representation of Faces for Kin Relationships Pratibha Chaskar1, Dr. Manjusha Deshmukh2" c52bd60b737d17d749e6a3117d8faa3b3012865c,Face Detection Benchmark Database Data Set Location Description,"Face Detection Summary Resources for Face Detection This web page contains information of face detection works. As a first step to encourage researchers to embark on this topic, we also provide some sample code, scripts, and plots to develop face detection systems. Consequently, this page does not contain all the detailed information that you may need. Nevertheless, we think it contains ""substantial"" information that you will find useful in developing face detection methods. Reference l Ming-Hsuan Yang, David Kriegman, and Narendra Ahuja, ""Detecting Faces in Images: A Survey"", IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 24, no. 1, pp. 34-58, 2002." c55f3b1ab8f4de230a55a4702aeefeb6bc0bb68c,Maximally Stable Local Description for Scale Selection,"Maximally Stable Local Description for Scale Selection Gyuri Dork(cid:19)o and Cordelia Schmid INRIA Rh^one-Alpes, 655 Avenue de l’Europe, 38334 Montbonnot, France" c593c6080c75133191a27381a58cd07c97aa935b,Gender Classification Using a Min-Max Modular Support Vector Machine with Incorporating Prior Knowledge,"SUBMITTED TO IEEE TRANSACTIONS ON NEURAL NETWORKS Gender Classification Using a Min-Max Modular Support Vector Machine with Incorporating Prior Knowledge Hui-Cheng Lian and ∗Bao-Liang Lu, Senior Member, IEEE" c5af99522e324b72c8a563a5d6b7c9a0101efb65,Exploring Human Vision Driven Features for Pedestrian Detection,"(cid:13) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any urrent or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new ollective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works." c562e95b7906066be4210d00c4f6187475e6e13a,Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database,"Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-scale Lesion Database Imaging Biomarkers and Computer-Aided Diagnosis Laboratory National Institutes of Health Clinical Center, 10 Center Drive, Bethesda, MD 20892 {ke.yan, xiaosong.wang, ling.zhang3, mohammad.bagheri, Ke Yan, Xiaosong Wang, Le Lu, Ling Zhang, Adam P. Harrison Mohammadhadi Bagheri, Ronald M. Summers {lel," c542fa8c4cfaff6a8d8efa9678e42e1b9ead8aa9,griffith . edu . au Face Recognition using Ensemble String Matching,"Griffith Research Online https://research-repository.griffith.edu.au Face Recognition using Ensemble String Matching Author Chen, Weiping, Gao, Yongsheng Published Journal Title IEEE Transactions on Image Processing https://doi.org/10.1109/TIP.2013.2277920 Copyright Statement Copyright 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Downloaded from http://hdl.handle.net/10072/54416" c5318c79bc1b880e8356211b837b684f1ee6e5c4,Acquiring Common Sense Spatial Knowledge Through Implicit Spatial Templates,"Acquiring Common Sense Spatial Knowledge through Implicit Spatial Templates Department of Computer Science Computer Vision Laboratory Guillem Collell KU Leuven Luc Van Gool ETH Zurich Marie-Francine Moens Department of Computer Science KU Leuven" c52aa6b9c7b89782f2316ce8ef2156fa06a3696d,Learning Semantic Part-Based Models from Google Images,"Learning Semantic Part-Based Models from Google Images Davide Modolo and Vittorio Ferrari" c591cb28d12b7ee53af4e5c2050b74071527c248,The face of fear and anger: Facial width-to-height ratio biases recognition of angry and fearful expressions.,"The Face of Fear and Anger: Facial Width-to-Height Ratio Biases Recognition of Angry and Fearful Expressions Jason C. Deska, E. Paige Lloyd, and Kurt Hugenberg Online First Publication, May 11, 2017. http://dx.doi.org/10.1037/emo0000328 CITATION Deska, J. C., Lloyd, E. P., & Hugenberg, K. (2017, May 11). The Face of Fear and Anger: Facial online publication. http://dx.doi.org/10.1037/emo0000328" c588c89a72f89eed29d42f34bfa5d4cffa530732,Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning,"Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning Berkan Demirel1,3, Ramazan Gokberk Cinbis2, Nazli Ikizler-Cinbis3 HAVELSAN Inc., 2Bilkent University, 3Hacettepe University" c50c034d264083757eadeee5d0b94d933fe78544,Query by string word spotting based on character bi-gram indexing,"Query by String word spotting based on character i-gram indexing Computer Vision Center, Dept. Ci`encies de la Computaci´o Universitat Aut`onoma de Barcelona, 08193 Bellaterra (Barcelona), Spain Suman K. Ghosh and Ernest Valveny Email:" c528e6285ed170c9a838446c062c8dfbe31c546e,Real Time 3 D Head Pose Estimation : Recent Achievements and Future Challenges,"REAL TIME 3D HEAD POSE ESTIMATION: RECENT ACHIEVEMENTS AND FUTURE CHALLENGES Gabriele Fanelli, Juergen Gall, Luc Van Gool Computer Vision Laboratory - ETH Zurich" c5484a227f52e73481fdc453d74bd76675b8c943,REDUCED-GATE CONVOLUTIONAL LSTM DESIGN USING PREDICTIVE CODING FOR NEXT-FRAME VIDEO PREDICTION,"Under review as a conference paper at ICLR 2019 REDUCED-GATE CONVOLUTIONAL LSTM DESIGN USING PREDICTIVE CODING FOR NEXT-FRAME VIDEO PREDICTION Anonymous authors Paper under double-blind review" c52f2a00fdbfb7fb10252796dbede6403e780da6,Input Convex Neural Networks,"Input Convex Neural Networks Brandon Amos 1 Lei Xu 2 * J. Zico Kolter 1" c5b05718963f4edff80456c441796e4199ad8d41,Sampling and Ontologically Pooling Web Images for Visual Concept Learning,"Sampling and Ontologically Pooling Web Images for Visual Concept Learning Shiai Zhu, Chong-Wah Ngo, and Yu-Gang Jiang" c590c6c171392e9f66aab1bce337470c43b48f39,Emotion Recognition by Machine Learning Algorithms using Psychophysiological Signals,"Emotion Recognition by Machine Learning Algorithms using Psychophysiological Signals Eun-Hye Jang, 2Byoung-Jun Park, 3Sang-Hyeob Kim, 4Jin-Hun Sohn , 2, 3 BT Convergence Technology Research Department, Electronics and Telecommunications Research Institute, 138 Gajeongno, Yuseong-gu, Daejeon, 305-700, Republic of Korea, *4Department of Psychology/Brain Research Institute, Chungnam National University 220, Gung-dong, Yuseong-gu, Daejeon, 305-765, Republic of Korea," c5420ef59d7508d82e53671b0d623027eb58e6ed,Learning to Reweight Examples for Robust Deep Learning,"Learning to Reweight Examples for Robust Deep Learning Mengye Ren 1 2 Wenyuan Zeng 1 2 Bin Yang 1 2 Raquel Urtasun 1 2" c54e8c7a4f9c2ebd8787aecafa4cfdb35bfd49e0,Effective Use of Bidirectional Language Modeling for Medical Named Entity Recognition,"Effective Use of Bidirectional Language Modeling for Medical Named Entity Recognition Devendra Singh Sachan1,*, Pengtao Xie1, and Eric P Xing1 Petuum Inc, Pittsburgh, 15222, USA" 1fd54172f7388cd83ed78ff9165519296de5cf20,Changing the Image Memorability: From Basic Photo Editing to GANs,"Changing the Image Memorability: From Basic Photo Editing to GANs Oleksii Sidorov The Norwegian Colour and Visual Computing Laboratory, NTNU Gjovik, Norway Figure 1: Modification of memorability using the proposed algorithm. All the results were generated without any human intervention. “What” and “how” to change were learned by the model from experimental data." 1f5b0caec136778decf7689cb090cb1911c2263f,Semantic Mapping for Orchard Environments by Merging Two-Sides Reconstructions of Tree Rows,"Semantic Mapping for Orchard Environments by Merging Two-Sides Reconstructions of Tree Rows Wenbo Dong Pravakar Roy Volkan Isler∗" 1ff057f2fb8258bd5359cded950a3627bd8ee1f4,Low-rank embedding for semisupervised face classification,"Low-Rank Embedding for Semisupervised Face Classification Gaurav Srivastava, Ming Shao and Yun Fu∗" 1f7cd3343f4b6b0f936c94e3a45c477c014e2b5c,3D Human Pose Estimation on a Configurable Bed from a Pressure Image,"D Human Pose Estimation on a Configurable Bed from a Pressure Image Henry M. Clever*, Ariel Kapusta, Daehyung Park, Zackory Erickson, Yash Chitalia, Charles C. Kemp" 1f8d539885f78e1a9d1314e952f3099e71676a5b,Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion,"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion Israel D. Gebru, Sil`eye Ba, Xiaofei Li and Radu Horaud" 1f65cbc7894323a85f2964d05ae937070e70e43b,Eliminating Background-bias for Robust Person Re-identification,"Eliminating Background-bias for Robust Person Re-identification Maoqing Tian1, Shuai Yi1, Hongsheng Li2, Shihua Li3, Xuesen Zhang1, Jianping Shi1, Junjie Yan1, Xiaogang Wang2 SenseTime Research, 2 Chinese University of Hong Kong, 3 Shenzhen Municipal Public Security Bureau" 1fb2082d3f772933b586cca65af2099512b9c68b,Comparison of Spectral-Only and Spectral/Spatial Face Recognition for Personal Identity Verification,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2009, Article ID 943602, 6 pages doi:10.1155/2009/943602 Research Article Comparison of Spectral-Only and Spectral/Spatial Face Recognition for Personal Identity Verification Zhihong Pan,1 Glenn Healey,2 and Bruce Tromberg3 Galileo Group Inc., 100 Rialto Place Suite 737, Melbourne, FL 32901, USA Department of Electrical Engineering and Computer Science, University of California, Irvine, CA 92697, USA Beckman Laser Institute, 1002 East Health Sciences Road, Irvine, CA 92612, USA Correspondence should be addressed to Zhihong Pan, Received 29 September 2008; Revised 22 February 2009; Accepted 8 April 2009 Recommended by Kevin Bowyer Face recognition based on spatial features has been widely used for personal identity verification for security-related applications. Recently, near-infrared spectral reflectance properties of local facial regions have been shown to be suf‌f‌icient discriminants for ccurate face recognition. In this paper, we compare the performance of the spectral method with face recognition using the eigenface method on single-band images extracted from the same hyperspectral image set. We also consider methods that use multiple original and PCA-transformed bands. Lastly, an innovative spectral eigenface method which uses both spatial and spectral features is proposed to improve the quality of the spectral features and to reduce the expense of the computation. The algorithms" 1fbf9dddf0bd4c115e2256cbf5d3a3bcc5ad2060,Human Motion Prediction using Adaptable Neural Networks,"Human Motion Prediction using Adaptable Neural Networks Yujiao Cheng*, Weiye Zhao*, Changliu Liu, and Masayoshi Tomizuka" 1fd2655fd69a44bd9ca0d855521247d5620d3f82,Multi-modal Geolocation Estimation Using Deep Neural Networks,"MULTI-MODAL GEOLOCATION ESTIMATION USING DEEP NEURAL NETWORKS Jesse M. Johns, Jeremiah Rounds & Michael J. Henry Pacific Northwest National Laboratory Richland, WA 99352, USA" 1f06651fc5ce2c10cb1f4ad53dd9c931ceb66448,Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360 ^\circ ∘ Panoramic Imagery,"Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 60◦ Panoramic Imagery Gr´egoire Payen de La Garanderie, Amir Atapour Abarghouei, nd Toby P. Breckon Department of Computer Science Durham University" 1f8f0abfe4689aa93f2f6cc7ec4fd4c6adc2c2d6,Semantic Instance Segmentation with a Discriminative Loss Function,"Semantic Instance Segmentation with a Discriminative Loss Function Bert De Brabandere∗ Davy Neven∗ ESAT-PSI, KU Leuven Luc Van Gool" 1f8eefd6dd2f20fd78a67dfdfe33022c6f9981d6,Unsupervised Features for Facial Expression Intensity Estimation over Time, 1fee632cad6a3853cc43621ba50161f5dd6263e5,Gated classifiers: Boosting under high intra-class variation,"Gated Classifiers: Boosting under High Intra-Class Variation Oscar Danielsson, Babak Rasolzadeh and Stefan Carlsson School of Computer Science and Communication, Royal Inst. of Technology, Stockholm, Sweden . Motivation . Learning . Experiments and Results Combinations of weak classifiers that never occur together on any example of the target class may generate false positives. Using Gated Classifiers with AdaBoost requires only very small changes to existing boosting code. Synthetic data: Increasingly difficult datasets generated by adding more omponents to Gaussian Mixture generating positive examples. A pool of weak classifiers split the x- and y-axes into a set of intervals. By adding first tautology and falsum classifiers and then NAND and XOR classifiers we can better represent complex distributions. Solution: Add new classifier h = ¬ h1 ∧ h2 Problem: The outputs of h1 and h2 are negatively correlated on the target class, but positively" 1fed6a571d9f688e18960e560d9441f5c5e3e2bd,Scalable Active Learning for Multiclass Image Classification,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Scalable Active Learning for Multi-Class Image Classification Joshi, A.J.; Porikli, F.; Papanikolopoulos, N. TR2012-026 January 2012" 1fcd7978c6956fd9a0d752ecc9f5ac1a1b2896e9,Impact of Face Registration Errors on Recognition,"Impact of Face Registration Errors on Recognition E. Rentzeperis, A. Stergiou, A. Pnevmatikakis and L. Polymenakos Athens Information Technology, Autonomic and Grid Computing, Markopoulou Ave., 19002 Peania, Greece {eren, aste, apne, http://www.ait.edu.gr/research/RG1/overview.asp" 1f2551b2acfb6895e91e39ae36a51335893a849f,3D Face Recognition Using Face Feature Points Based on Parallel Stereo Vision,"D Face Recognition Using Face Feature Points Based on Parallel Stereo Vision Li Wei, and Eung-Joo Lee D Face Recognition Using Face Feature Points Based on Parallel *1 Information Communication Engineering Department, Tongmyong University, Busan, Korean *2, Corresponding author Information Communication Engineering Department, Tongmyong University, Stereo Vision Li Wei, and *Eung-Joo Lee Busan, Korean" 1fbccb842cf34697c98532d69b044463985f90ee,Constructing PCA Baseline Algorithms to Reevaluate ICA-Based Face-Recognition Performance,"IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, VOL. 37, NO. 4, AUGUST 2007 Constructing PCA Baseline Algorithms to Reevaluate ICA-Based Face-Recognition Performance Jian Yang, David Zhang, and Jing-Yu Yang" 1f4aa1d14bb99e152dd1c7ac3cfd5afa8f6a012f,Learning Discriminative Part Detectors for Image Classification and Cosegmentation,"Learning Discriminative Part Detectors for Image Classification and Cosegmentation Jian Sun Jean Ponce Xi’an Jiaotong University, INRIA, ∗ ´Ecole Normale Sup´erieure, * This is a preliminary version accepted for publication to ICCV 2013" 1f6dd0ff2e8493b81e3699b520193198d4eed4e6,Shaogang Gong Part I Features and Representations 1 Discriminative Image Descriptors for Person Re-identification . . . . . 25 7 One-shot Person Re-identification with a Consumer Depth Camera . 163 List of Contributors the Re-identification Challenge,"Shaogang Gong Marco Cristani Shuicheng Yan Chen Change Loy (Eds.) PERSON RE-IDENTIFICATION October 10, 2013 Springer" 1fff309330f85146134e49e0022ac61ac60506a9,Data-Driven Sparse Sensor Placement for Reconstruction,"Data-Driven Sparse Sensor Placement for Reconstruction Krithika Manohar∗, Bingni W. Brunton, J. Nathan Kutz, and Steven L. Brunton Corresponding author:" 1f5e47ad5490a63c7bea79000999b711055fbf2a,Aggregated Channels Network for Real-Time Pedestrian Detection,"Aggregated Channels Network for Real-Time Pedestrian Detection Farzin Ghorban1,2, Javier Marín3, Yu Su2, Alessandro Colombo2, Anton Kummert1 Universität Wuppertal, 2Delphi Deutschland, 3Massachusetts Institute of Technology" 1f98daf89f9a3dba655f0a4eb4164118ea6226ef,"Parallel k-Means Image Segmentation Using Sort, Scan and Connected Components on a GPU","The original publication is available at: www.springerlink.com Parallel k-Means Image Segmentation Using Sort, Scan & Connected Components on a GPU Michael Backer, Jan T¨unnermann, and B¨arbel Mertsching GET Lab, University of Paderborn, Pohlweg 47-49, 33098 Paderborn, Germany {backer, tuennermann, http://getwww.upb.de" 1f82eebadc3ffa41820ad1a0f53770247fc96dcd,Using Trajectories derived by Dense Optical Flows as a Spatial Component in Background Subtraction,"Using Trajectories derived by Dense Optical Flows as a Spatial Component in Background Subtraction Martin Radolko University of Rostock nd Fraunhofer IGD Joachim-Jungius 11 Rostock 18059 r.fraunhofer.de Fahimeh Farhadifard University of Rostock nd Fraunhofer IGD Joachim-Jungius 11 Rostock 18059 r.fraunhofer.de" 1f2f712253a68cd9f8172de19297e35cec7919dd,Vision System of Facial Robot SHFR- III for Human-robot Interaction, 1f436aa4e68274037fff44e6cfbcd0a1ee3f60df,Tell and Predict: Kernel Classifier Prediction for Unseen Visual Classes from Unstructured Text Descriptions,"Tell and Predict: Kernel Classifier Prediction for Unseen Visual Classes from Unstructured Text Descriptions Mohamed Elhoseiny, Ahmed Elgammal, Babak Saleh" 1fefc1d288a87fe218ba25024c4b2b6ef345738e,Self-ensembling for domain adaptation,"Self-ensembling for domain adaptation French, G. Mackiewicz, M. Fisher, M. November 6, 2017" 1fc249ec69b3e23856b42a4e591c59ac60d77118,Evaluation of a 3D-aided pose invariant 2D face recognition system,"Evaluation of a 3D-aided Pose Invariant 2D Face Recognition System Xiang Xu, Ha A. Le, Pengfei Dou, Yuhang Wu, Ioannis A. Kakadiaris {xxu18, hale4, pdou, ywu35, Computational Biomedicine Lab 800 Calhoun Rd. Houston, TX, USA" 1fa9c5af78b3ca04476f4ee6910684dc19008f5e,Supplementary Material : Cross-Dataset Adaptation for Visual Question Answering,"Supplementary Material: Cross-Dataset Adaptation for Visual Question Answering Wei-Lun Chao∗ U. of Southern California Los Angeles, CA Hexiang Hu∗ Los Angeles, CA U. of Southern California U. of Southern California Fei Sha Los Angeles, CA We provide contents omitted in the main text. • Section 1: details on Name that dataset! (Sect. 3.2 of the main text). • Section 2: details on the proposed domain adaptation lgorithm (Sect. 4.2 and 4.3 of the main text). • Section 3: details on the experimental setup (Sect. 5.2 of the main text). • Section 4: additional experimental results (Sect. 5.3 nd 5.4 of the main text)." 1f7cf2df2fa7719c9db3fe57a0f01d65f08a9a8f,How social exclusion modulates social information processing: A behavioural dissociation between facial expressions and gaze direction,"RESEARCH ARTICLE How social exclusion modulates social information processing: A behavioural dissociation between facial expressions and gaze direction Francesco Bossi1,2*, Marcello Gallucci1,2, Paola Ricciardelli1,2 Department of Psychology, University of Milan – Bicocca, Milan, Italy, 2 NeuroMI: Milan Center for Neuroscience, Milan, Italy" 1fd808c6fda9c530d00d7a588693244ce9f324a8,Face Recognition using Feed Forward Neural Network,"IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 17, Issue 5, Ver. II (Sep. – Oct. 2015), PP 61-65 www.iosrjournals.org Face Recognition using Feed Forward Neural Network Pooja Rani (Department of computer science/ Punjabi university, India)" 1f0c7b93636f879bd5ef3dd915a02dcd813a053d,Interpreting Deep Visual Representations via Network Dissection,"Interpreting Deep Visual Representations via Network Dissection Bolei Zhou∗, David Bau∗, Aude Oliva, and Antonio Torralba" 1fdb84cd0ce04df3c4997059a5571e043dc32c8a,Identifying whether the mystery man or elimination lineup method is most effective for children,"Western University Undergraduate Honors Theses Winter 4-30-2014 Identifying whether the mystery man or elimination lineup method is most effective for hildren Logan Ewanation King's University College, Psychology Follow this and additional works at: https://ir.lib.uwo.ca/psychK_uht Part of the Psychology Commons Recommended Citation Ewanation, Logan, ""Identifying whether the mystery man or elimination lineup method is most effective for children"" (2014). Undergraduate Honors Theses. 8. https://ir.lib.uwo.ca/psychK_uht/8 This Dissertation/Thesis is brought to you for free and open access by the Psychology at It has been accepted for inclusion in Undergraduate Honors Theses by an authorized administrator of For more information, please contact" 1f5c409e9b6aec60003b5d4534373f9b07ff8443,Saliency Weighted Features for Person Re-identification,"Saliency Weighted Features for Person Re-Identification Niki Martinel, Christian Micheloni and Gian Luca Foresti Department of Mathematics and Computer Science University of Udine - 33100, Udine, Italy" 1f9ae272bb4151817866511bd970bffb22981a49,An Iterative Regression Approach for Face Pose Estimation from RGB Images,"An Iterative Regression Approach for Face Pose Estima- tion from RGB Images Wenye He This paper presents a iterative optimization method, explicit shape regression, for face pose detection and localization. The regression function is learnt to find out the entire facial shape nd minimize the alignment errors. A cascaded learning framework is employed to enhance shape constraint during detection. A combination of a two-level boosted regression, shape performance. In this paper, we have explain the advantage of ESR for deformable object like face pose estimation and reveal its generic applications of the method. In the experiment, we compare the results with different work and demonstrate the accuracy and robustness in different scenarios. Introduction Pose estimation is an important problem in computer vision, and has enabled many practical ap- plication from face expression 1 to activity tracking 2. Researchers design a new algorithm called explicit shape regression (ESR) to find out face alignment from a picture 3. Figure 1 shows how the system uses ESR to learn a shape of a human face image. A simple way to identify a face is to find out facial landmarks like eyes, nose, mouth and chin. The researchers define a face shape S nd S is composed of Nf p facial landmarks. Therefore, they get S = [x1, y1, ..., xNf p, yNf p]T . The objective of the researchers is to estimate a shape S of a face image. The way to know the accuracy" 1f18708439ba1dadd81568e102216731d44340d5,Sparse Quantization for Patch Description,"Sparse Quantization for Patch Description Xavier Boix Michael Gygli Gemma Roig Luc Van Gool Computer Vision Lab, ETH Zurich, Switzerland" 1f47a13548317602ec76eafbea44d7b39926c4cd,Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classification,"Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classification Cheng-Yaw Low, Jaewoo Park, and, Andrew Beng-Jin Teoh, Senior Member, IEEE" 1fbb66a9407470e1da332c4ef69cdc34e169a3d7,A Baseline for General Music Object Detection with Deep Learning,"Article A Baseline for General Music Object Detection with Deep Learning Alexander Pacha 1,* , Jan Hajiˇc, Jr. 2 and Jorge Calvo-Zaragoza 3 Institute for Visual Computing and Human-Centered Technology, TU Wien, 1040 Wien, Austria Institute of Formal and Applied Linguistics, Charles University, 116 36 Staré Mˇesto, Czech Republic; PRHLT Research Center, Universitat Politècnica de València, 46022 València, Spain; * Correspondence: Received: 31 July 2018; Accepted: 26 August 2018; Published: 29 August 2018" 1f94734847c15fa1da68d4222973950d6b683c9e,Embedding Label Structures for Fine-Grained Feature Representation,"Embedding Label Structures for Fine-Grained Feature Representation Xiaofan Zhang UNC Charlotte Charlotte, NC 28223 Feng Zhou NEC Lab America Cupertino, CA 95014 Yuanqing Lin NEC Lab America Cupertino, CA 95014 Shaoting Zhang UNC Charlotte Charlotte, NC 28223" 1f8304f4b51033d2671147b33bb4e51b9a1e16fe,Beyond Trees : MAP Inference in MRFs via OuterPlanar Decomposition,"Noname manuscript No. (will be inserted by the editor) Beyond Trees: MAP Inference in MRFs via Outer-Planar Decomposition Dhruv Batra · Andrew C. Gallagher · Devi Parikh · Tsuhan Chen Received: date / Accepted: date" 1f4fff64adef5ec6ae21e8647d5a042bf71d64d9,Human detection in surveillance videos and its applications - a review,"Paul et al. EURASIP Journal on Advances in Signal Processing 2013, 2013:176 http://asp.eurasipjournals.com/content/2013/1/176 R EV I E W Human detection in surveillance videos and its pplications - a review Manoranjan Paul*, Shah M E Haque and Subrata Chakraborty Open Access" 1f09ee546815c7bcd6d8b70a74d2c3fab482c72a,Performance Comparison of Principal Component Analysis-Based Face Recognition in Color Space,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 1f1d553be51339208c572f927354033e86a5be36,Machine Learning for Image Based Motion Capture,"INSTITUT NATIONAL POLYTECHNIQUE DE GRENOBLE Num´ero attribu´e par la biblioth`eque TH`ESE pour obtenir le grade de DOCTEUR DE L’INSTITUT NATIONAL POLYTECHNIQUE DE GRENOBLE Sp´ecialit´e : Imagerie, Vision et Robotique Ecole Doctorale : Math´ematiques, Sciences et Technologie de l’Information pr´esent´ee et soutenue publiquement Ankur Agarwal le 26 Avril 2006 Machine Learning for Image Based Motion Capture Directeur de th`ese : M. William Triggs Pr´esident M. Roger Mohr M. Andrew Zisserman Rapporteur Rapporteur M. Pascal Fua Directeur de th`ese M. William Triggs M. Philip Torr" 1f2c99bf032868ce520b9c5586a0c20051367b60,A Study of The Illumination Cones Method for Face Recognition Under Variable Illumination T.J. Chin and D. Suter A Study of The Illumination Cones Method for Face Recognition Under Variable Illumination,"Department of Electrical Computer Systems Engineering Technical Report MECSE-7-2004 A Study of The Illumination Cones Method for Face Recognition Under Variable Illumination T.J. Chin and D. Suter" 1f8e44593eb335c2253d0f22f7f9dc1025af8c0d,Fine-Tuning Regression Forests Votes for Object Alignment in the Wild,"Fine-tuning regression forests votes for object alignment in the wild. Yang, H; Patras, I © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle/123456789/22607 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 1f6e627efb1ac2b31f2b18dce8359ffdc352b3f2,A Boosting Approach to Multiple Instance Learning,"A Boosting Approach to Multiple Instance Learning Peter Auer and Ronald Ortner University of Leoben, Franz-Josef-Strasse 18, 8700 Leoben, Austria" 1ff89bd94d8a21b7ca4bf844e2d366f854822918,Robust Online Multi-object Tracking by Maximum a Posteriori Estimation with Sequential Trajectory Prior,"Robust Online Multi-object Tracking y Maximum a Posteriori Estimation with Sequential Trajectory Prior Min Yang(B), Mingtao Pei, Jiajun Shen, and Yunde Jia Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing 100081, People’s Republic of China" 1fd8c71a8859da611a8fde1cbb2bba1c7cf00b4c,EYEDIAP: a database for the development and evaluation of gaze estimation algorithms from RGB and RGB-D cameras,"This paper was presented at the 2014 Symposium on Eye Tracking Research & Applications 2014 EYEDIAP: A Database for the Development and Evaluation of Gaze Estimation Algorithms from RGB and RGB-D Cameras Kenneth Alberto Funes Mora1,2, Florent Monay1 and Jean-Marc Odobez1,2 Idiap Research Institute 2 ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL), Switzerland {kfunes, monay," 1ff616ae8b61f8167f2d626b7c1a36e018b23e94,Learning with Parsimony for Large Scale Object Detection and Discovery,"Learning with Parsimony for Large Scale Object Detection and Discovery Hyun Oh Song Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2014-148 http://www.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-148.html August 12, 2014" 4d20fbd6dcdb4408dd6268951d86b92e8d96f332,Robust Face Recognition of Variations in Blur and Illumination by Using LDA Ms,"International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 International Conference on Humming Bird ( 01st March 2014) RESEARCH ARTICLE OPEN ACCESS Robust Face Recognition of Variations in Blur and Illumination y Using LDA Ms. K. Hema PG Student Department of AE University College of Engineering Nagercoil-629004. Mr. J. Arun Prem Santh M. E., Teaching Fellow Department of ECE University College of Engineering Nagercoil-629004 ." 4d87784afdb704d9eca14010212afd5cd74c60ec,Cosine Similarity Search with Multi Index Hashing,"Cosine Similarity Search with Multi-Index Hashing Sepehr Eghbali and Ladan Tahvildari" 4d0ef449de476631a8d107c8ec225628a67c87f9,Face system evaluation toolkit: Recognition is harder than it seems,"© 2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, reating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Pre-print of article that appeared at BTAS 2010. The published article can be accessed from: http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5634517" 4de83b6025526ef7a340ffca30626dac53d7f8cb,SIFT / LBP 3 D face recognition,"SIFT/LBP 3D face recognition Narimen SAAD1 NourEddine DJEDI Department of Computer Science LESIA Laboratory University of Biskra, Algeria" 4ddd55a9f103001da8dc24d123d9223dbb67f884,Combining Face and Facial Feature Detectors for Face Detection Performance Improvement,"Combining face and facial feature detectors for face detection performance improvement M. Castrill´on-Santana, D. Hern´andez-Sosa, and J. Lorenzo-Navarro(cid:63) SIANI Universidad de Las Palmas de Gran Canaria, Spain" 4da735d2ed0deeb0cae4a9d4394449275e316df2,"The rhythms of head, eyes and hands at intersections","Gothenburg, Sweden, June 19-22, 2016 978-1-5090-1820-8/16/$31.00 ©2016 IEEE" 4d530a4629671939d9ded1f294b0183b56a513ef,Facial Expression Classification Method Based on Pseudo Zernike Moment and Radial Basis Function Network,"International Journal of Machine Learning and Computing, Vol. 2, No. 4, August 2012 Facial Expression Classification Method Based on Pseudo Zernike Moment and Radial Basis Function Network Tran Binh Long, Le Hoang Thai, and Tran Hanh" 4dff517b1578dec9155936f29aa9e8ca174e0804,Integrated Object Segmentation and Tracking for 3D LIDAR Data, 4d5a12fe88e35bb5c4a556a6b2598f7dd5284f46,Sentence transition matrix: An efficient approach that preserves sentence semantics,"Sentence transition matrix: An efficient approach that preserves sentence semantics Myeongjun Jang 1 Pilsung Kang 1" 4d5c34fb36cf8c74880a62814750760bce0aef16,Boosting descriptors condensed from video sequences for place recognition,"Boosting Descriptors Condensed from Video Sequences for Place Recognition Tat-Jun Chin, Hanlin Goh and Joo-Hwee Lim Institute for Infocomm Research 1 Heng Mui Keng Terrace, Singapore 119613. {tjchin, hlgoh," 4db64fbc3dd2486a74dba3350d44c51e561f515f,An Ecological Visual Exploration Tool to Support the Analysis of Visual Processing Pathways in Children with Autism Spectrum Disorders,"Article An Ecological Visual Exploration Tool to Support the Analysis of Visual Processing Pathways in Children with Autism Spectrum Disorders Dario Cazzato 1, Marco Leo 2,*, Cosimo Distante 2, Giulia Crifaci 3, Giuseppe Massimo Bernava 4, Liliana Ruta 4, Giovanni Pioggia 4 and Silvia M. Castro 5 Interdisciplinary Centre for Security Reliability and Trust (SnT), University of Luxembourg, 29, Avenue JF Kennedy, L-1855 Luxembourg, Luxembourg; Institute of Applied Sciences and Intelligence Systems—CNR, 73100 Lecce, Italy; Department of Clinical Physiology, CNR Pisa, 56124 Pisa, Italy; Institute of Applied Sciences and Intelligence Systems—CNR, 98164 Messina, Italy; (G.M.B.); (L.R.); (G.P.) 5 Universidad Nacional del Sur, 8000 Bahía Blanca, Argentina; * Correspondence: Received: 6 November 2017; Accepted: 19 December 2017; Published: 29 December 2017" 4d442ea40635a10fd3e642a7161dfc8f2b15a71e,An Image reranking model based on attributes and visual features eliminating duplication,"© 2016 IJEDR | Volume 4, Issue 2 | ISSN: 2321-9939 An Image reranking model based on attributes and visual features eliminating duplication Ms.Madhuri Mhaske,2Prof.Sachin Patil PG Scholar at G. H. Raisoni College of Engineering and Management, Chas, Ahmednagar , 2Professor at G. H. Raisoni College of Engineering and Management, Vagholi, Pune ________________________________________________________________________________________________________" 4d6043a25bf48c6fd6aff6a46597fe1902a9c6a7,Long-term tracking of multiple interacting pedestrians using a single camera by Advice,"Long-term tracking of multiple interacting pedestrians using a single camera Mogomotsi Keaikitse∗, Willie Brink† and Natasha Govender∗ Modelling and Digital Sciences Council for Scientific and Industrial Research Pretoria, South Africa Department of Mathematical Sciences Stellenbosch University Stellenbosch, South Africa" 4dd6d511a8bbc4d9965d22d79ae6714ba48c8e41,Automatic Pixel Boosting for Face Enhancement in Dim Light,"The 23rd International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC 2008) Automatic Pixel Boosting for Face Enhancement in Dim Light Hataikan Poncharoensil1 and Seri Pansang2 School of Science, Maefahluang University 33 Moo1 Thasud, Muang Chiangrai 57100, Thailand Department of Computer Engineering, Rajabhat Chiangmai University 02 ChangPuek, Muang Chiangmai 50300, Thailand E-mail:" 4d2975445007405f8cdcd74b7fd1dd547066f9b8,Image and Video Processing for Affective Applications,"Image and Video Processing for Affective Applications Maja Pantic and George Caridakis" 4d7e1eb5d1afecb4e238ba05d4f7f487dff96c11,Largest center-specific margin for dimension reduction,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" 4dd2744a37bd1e666346a41dcd2a271945c74e2f,Human-Robot Teaming : Approaches from Joint Action and Dynamical Systems,"Human Robot Teaming: Approaches from Joint Action and Dynamical Systems Tariq Iqbal and Laurel D. Riek" 4d2022e3db712237b95fe381a75dbeb827551924,Running Head : GENDER CATEGORIZATION IN INFANTS AND CHILDREN 1 Gender Categorization in Infants and Children,"Running Head: GENDER CATEGORIZATION IN INFANTS AND CHILDREN Gender Categorization in Infants and Children Hong N. T. Bui Senior Thesis in Psychology Advisor: Karen Wynn April 27, 2018" 4dade6faf6d5d6db53d5bcb2e107311da1ad48ac,Facial Expression Biometrics Using Statistical Shape Models,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2009, Article ID 261542, 17 pages doi:10.1155/2009/261542 Research Article Facial Expression Biometrics Using Statistical Shape Models Wei Quan, Bogdan J. Matuszewski (EURASIP Member), Lik-Kwan Shark, nd Djamel Ait-Boudaoud Applied Digital Signal and Image Processing Research Centre, University of Central Lancashire, Preston PR1 2HE, UK Correspondence should be addressed to Bogdan J. Matuszewski, Received 30 September 2008; Revised 2 April 2009; Accepted 18 August 2009 Recommended by Jonathon Phillips This paper describes a novel method for representing different facial expressions based on the shape space vector (SSV) of the statistical shape model (SSM) built from 3D facial data. The method relies only on the 3D shape, with texture information not eing used in any part of the algorithm, that makes it inherently invariant to changes in the background, illumination, and to some extent viewing angle variations. To evaluate the proposed method, two comprehensive 3D facial data sets have been used for the testing. The experimental results show that the SSV not only controls the shape variations but also captures the expressive haracteristic of the faces and can be used as a significant feature for facial expression recognition. Finally the paper suggests improvements of the SSV discriminatory characteristics by using 3D facial sequences rather than 3D stills. Copyright © 2009 Wei Quan et al. This is an open access article distributed under the Creative Commons Attribution License," 4dea287ad9271d4ac73c58c03b8e6e714dd2db6c,Pyramid Center-symmetric Local 1 Binary / Trinary Patterns for Pedestrian 2 Detection,"Pyramid Center-symmetric Local Binary/Trinary Patterns for Pedestrian Detection Yongbin Zheng, Chunhua Shen, Richard Hartley and Xinsheng Huang Australian National University and NICTA, Canberra" 4d50de8ec7335ab320f9743d199336699307b523,The Bochum / USC Face Recognition Systemand How it Fared in the FERET Phase,"TheBochum/USCFaceRecognitionSystem ndHowitFaredintheFERETPhaseIII KazunoriOkada,JohannesSte(cid:11)ens;;,ThomasMaurer,HaiHong,Egor Elagin;,HartmutNeven;,andChristophvonderMalsburg; ComputerScienceDepartmentandCenterforNeuralEngineering UniversityofSouthernCalifornia LosAngeles,CA  -,USA Institutf(cid:127)urNeuroinformatik Ruhr-Universit(cid:127)atBochum D{Bochum,Germany NowalsoatEyematicInterfaces,Inc thStreet,SantaMonica,CA ,USA Summary.ThispapersummarizestheBochum/USCfacerecognitionsystem,our preparationsfortheFERETPhaseIIItest,andtestresultsasfarastheyhavebeen madeknowntous.OurtechnologyisbasedonGaborwaveletsandelasticbunch graphmatching.Webrie(cid:13)ydiscussourtechnologyinrelationtobiologicaland PCAbasedsystemsandindicatecurrentactivitiesinthelabandpotentialfuture pplications. .Introduction Visionisthemostimportantofoursensesbywhichweestablishcontinuitybetween" 4d3a6c2cee0cf06ff6471fad3d65a5835d0552f8,3-D Face Recognition Using Geodesic-Map Representation and Statistical Shape Modelling,"Article ­D Face Recognition Using Geodesic­Map Representation and Statistical Shape Modelling Quan, Wei, Matuszewski, Bogdan and Shark, Lik Available at http://clok.uclan.ac.uk/13240/ Quan, Wei, Matuszewski, Bogdan and Shark, Lik (2016) 3­D Face Recognition Using Geodesic­ Map Representation and Statistical Shape Modelling. Lecture Notes in Computer Science, 9493 . pp. 199­212. ISSN 0302­9743 It is advisable to refer to the publisher’s version if you intend to cite from the work. http://dx.doi.org/10.1007/978-3-319-27677-9_13 For more information about UCLan’s research in this area go to http://www.uclan.ac.uk/researchgroups/ and search for . For information about Research generally at UCLan please go to http://www.uclan.ac.uk/research/ All outputs in CLoK are protected by Intellectual Property Rights law, including Copyright law. Copyright, IPR and Moral Rights for the works on this site are retained y the individual authors and/or other copyright owners. Terms and conditions for use of this material are defined in the http://clok.uclan.ac.uk/policies/ Central Lancashire online Knowledge www.clok.uclan.ac.uk" 4d1e28368e1121872bcd4ce75bc7ba5e43bd42d0,Attend to You: Personalized Image Captioning with Context Sequence Memory Networks,"Post generationTask1. Hashtag predictionQuery ImageImage featureUser contextWord outputCNNytytUser’s Active VocabularyCSMN modelContextMemorySoftmaxFigure1.ProblemstatementofpersonalizedimagecaptioningwithanInstagramexample.Asmainapplications,weaddresshashtagpredictionandpostgenerationtasks.Givenaqueryim-age,theformerpredictsalistofhashtags,whilethelattergener-atesadescriptivetexttocompleteapost.Weproposeaversatilecontextsequencememorynetwork(CSMN)model.captioning,whichhavenotbeendiscussedinpreviousre-search.Weaimtogenerateadescriptivesentenceforanimage,accountingforpriorknowledgesuchastheuser’sactivevocabulariesorwritingstylesinpreviousdocuments.Potentially,personalizedimagecaptioningisapplicabletoawiderangeofautomationservicesinphoto-sharingsocialnetworks.Forexample,inInstagramorFacebook,usersin-stantlytakeandsharepicturesaspostsusingmobilephones.Onebottlenecktocompleteanimagepostistocrafthash-tagsorassociatedtextdescriptionusingtheirownwords.Indeed,craftingtextismorecumbersomethantakingapic-tureforgeneralusers;photo-takingcanbedonewithonlyasingletabonthescreenofasmartphone,whereastextwrit-ingrequiresmoretimeandmentalenergyforselectingsuit-ablekeywordsandcompletingasentencetodescribetheme,sentiment,andcontextoftheimage.Inthispaper,asexamplesofpersonalizedimagecap-tioning,wefocusontwopostautomationtasks:hashtag" 4d4bb462c9f1d4e4ab1e4aa6a75cc0bc71b38461,A 3 D Dynamic Database for Unconstrained Face Recognition,"A 3D Dynamic Database for Unconstrained Face Recognition Taleb Alashkar, Boulbaba Ben Amor, Mohamed Daoudi, Stefano Berretti To cite this version: Taleb Alashkar, Boulbaba Ben Amor, Mohamed Daoudi, Stefano Berretti. A 3D Dynamic Database for Unconstrained Face Recognition. 5th International Conference and Exhibition on 3D Body Scan- ning Technologies, Oct 2014, Lugano, Switzerland. 2014. HAL Id: hal-01074992 https://hal.archives-ouvertes.fr/hal-01074992 Submitted on 17 Oct 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 4d6ad0c7b3cf74adb0507dc886993e603c863e8c,Human Activity Recognition Based on Wearable Sensor Data : A Standardization of the State-ofthe-Art,"Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art Artur Jord˜ao, Antonio C. Nazare Jr., Jessica Sena and William Robson Schwartz Smart Surveillance Interest Group, Computer Science Department Universidade Federal de Minas Gerais, Brazil Email: {arturjordao, antonio.nazare, jessicasena," 4d6e7d73f5226142ffc42b4e8380882d5071e187,Discretion Within Constraint: Homophily and Structure in a Formal Organization,"This article was downloaded by: [128.32.74.70] On: 03 July 2014, At: 15:15 Publisher: Institute for Operations Research and the Management Sciences (INFORMS) INFORMS is located in Maryland, USA Publication details, including instructions for authors and subscription information: http://pubsonline.informs.org Discretion Within Constraint: Homophily and Structure in Formal Organization Adam M. Kleinbaum, Toby E. Stuart, Michael L. Tushman To cite this article: Adam M. Kleinbaum, Toby E. Stuart, Michael L. Tushman (2013) Discretion Within Constraint: Homophily and Structure in a Full terms and conditions of use: http://pubsonline.informs.org/page/terms-and-conditions This article may be used only for the purposes of research, teaching, and/or private study. Commercial use or systematic downloading (by robots or other automatic processes) is prohibited without explicit Publisher pproval, unless otherwise noted. For more information, contact The Publisher does not warrant or guarantee the article’s accuracy, completeness, merchantability, fitness for a particular purpose, or non-infringement. Descriptions of, or references to, products or publications, or inclusion of an advertisement in this article, neither constitutes nor implies a guarantee, endorsement, or support of claims made of that product, publication, or service. Copyright © 2013, INFORMS Please scroll down for article—it is on subsequent pages" 4da80ad59adbe530838b5685935b488edab07c7d,Effective Proximity Retrieval by Ordering Permutations,"Effective Proximity Retrieval y Ordering Permutations EDGAR CHAVEZ, Universidad Michoacana, Mexico KARINA FIGUEROA, Universidad Michoacana, Mexico, nd Universidad de Chile, Chile GONZALO NAVARRO, Universidad de Chile, Chile Supported by CONACyT (first and second author) and Millennium Nucleus Center for Web Research, Grant P04-067-F, Mideplan, Chile (second and third author). A preliminary partial version of this paper appeared in Proc. 4th Mexican International Conference on Artificial Intelligence (MICAI 2005), pp. 405–414, LNAI Series vol. 3789. September 3, 2007 DRAFT" 4d334cfafd11a93394917adcffef6c1d27aa178b,Refined Clustering technique based on boosting and outlier detection,"International Journal of Scientific & Engineering Research, Volume 6, Issue 11, November-2015 472 ISSN 2229-5518 Refined Clustering technique based on boosting nd outlier detection Ms. Reshma Y. Nagpure, Prof. P. P. Rokade" 4d1fc3245b05731a313e61165c1109f42f5b4a0c,Facial expression recognition using local binary patterns and discriminant kernel locally linear embedding,"Zhao and Zhang EURASIP Journal on Advances in Signal Processing 2012, 2012:20 http://asp.eurasipjournals.com/content/2012/1/20 RESEARCH Facial expression recognition using local binary patterns and discriminant kernel locally linear embedding Xiaoming Zhao1 and Shiqing Zhang2* Open Access" 4d7bbaa2c7e89d5ba6940ee5804cf10a6b24d6ec,Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories,"Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories Huanhuan Yu, Menglei Hu and Songcan Chen" 4d47261b2f52c361c09f7ab96fcb3f5c22cafb9f,Deep multi-frame face super-resolution,"Deep multi-frame face super-resolution Evgeniya Ustinova, Victor Lempitsky October 17, 2017" 4df3143922bcdf7db78eb91e6b5359d6ada004d2,The Chicago face database: A free stimulus set of faces and norming data.,"Behav Res (2015) 47:1122–1135 DOI 10.3758/s13428-014-0532-5 The Chicago face database: A free stimulus set of faces nd norming data Debbie S. Ma & Joshua Correll & Bernd Wittenbrink Published online: 13 January 2015 # Psychonomic Society, Inc. 2015" 4df54d4758b1a883902c036b2a10ef6d0f2d4af9,An Automatic Face Recognition System Based On Adaptive Wavelet Transforms,"International Journal of Scientific Research and Engineering Studies (IJSRES) Volume 2 Issue 4, April 2015 ISSN: 2349-8862 An Automatic Face Recognition System Based On Adaptive Wavelet Transforms Prof. Khaladkar Nilam Chavan Apurva Kadam" 4dc8b1c193c421f8f570c0a7eac2fc73da06cb51,MODS: Fast and Robust Method for Two-View Matching,"MODS: Fast and Robust Method for Two-View Matching Dmytro Mishkin, Jiri Matas, Michal Perdoch Center for Machine Perception, Faculty of Electrical Engineering, Czech Technical University in Prague. Karlovo namesti, 13. Prague 2, 12135" 4dba7e19e2958d8ab75261219747aebc675c6f8a,Finding the Topic of a Set of Images,"Finding the Topic of a Set of Images Gonzalo Vaca-Castano Univeristy of Central Florida" 4d231311cdfe3aba13766bd0b358d4db0a9af3d3,Processing and Recognising Faces in 3D Images,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 4dc6659b5022ecc2c4e1459e9dff16ddece4147e,Transfer Learning for Illustration Classification,"CEIG - Spanish Computer Graphics Conference (2017) F. J. Melero and N. Pelechano (Editors) Transfer Learning for Illustration Classification Manuel Lagunas1 Elena Garces2 Universidad de Zaragoza, I3A Technicolor Figure 1: Comparison of the probabilities of the images that belong to the class pelican using our method and the network VGG19 [SZ14]. image (a) is a photograph and image (b) is an illustration which has similar colours, gradients and edges than the natural image. On the" 4d848b2055e1bba4ce80d5d050879c26686eda50,Face recognition with enhanced privacy protection,"978-1-4244-2354-5/09/$25.00 ©2009 IEEE ICASSP 2009" 4d45612c41d3e27a30a5ec64e0d8e2362dcb6b73,Brand > Logo: Visual Analysis of Fashion Brands,"Brand > Logo: Visual Analysis of Fashion Brands M. Hadi Kiapour and Robinson Piramuthu eBay, San Francisco CA 94105, USA" 4d8347a69e77cc02c1e1aba3a8b6646eac1a0b3d,Re-ID done right: towards good practices for person re-identification.,"Re-ID done right: towards good practices for person re-identification Jon Almaz´an1 Bojana Gaji´c2∗ Naila Murray1 Diane Larlus1 Computer Vision Group NAVER LABS Europe Computer Vision Center Dept. de Ci`encies de la Computaci´o, UAB" 12919f98aecdd74c1e0db56cba13d107553e421b,Temporal Model Adaptation for Person Re-Identification : Supplementary Material,"Temporal Model Adaptation for Person Re-Identification: Supplementary Material Niki Martinel1,3, Abir Das2, Christian Micheloni1, and Amit K. Roy-Chowdhury3 University of Udine, 33100 Udine, Italy University of Massatchussets Lowell, 01852 Lowell, MA, USA University of California Riverside, 92507 Riverside, CA, USA" 1222705b626a33974e85985ddabfcea135e9ddce,k-fold Subsampling based Sequential Backward Feature Elimination, 1267eae42798940c105355a9590363fb6560595b,From Coarse to Fine: Robust Hierarchical Localization at Large Scale,"From Coarse to Fine: Robust Hierarchical Localization at Large Scale Paul-Edouard Sarlin1 Cesar Cadena1 Roland Siegwart1 Marcin Dymczyk1,2 Autonomous Systems Lab, ETH Z¨urich Sevensense Robotics AG" 127759fc41d62b516298fff2706dfcc754ff1ee8,Fabrik: An Online Collaborative Neural Network Editor,"FABRIK: AN ONLINE COLLABORATIVE NEURAL NETWORK EDITOR Utsav Garg 1 Viraj Prabhu 2 Deshraj Yadav 2 Ram Ramrakhya 3 Harsh Agrawal 2 Dhruv Batra 2 4 fabrik.cloudcv.org" 12cd96a419b1bd14cc40942b94d9c4dffe5094d2,Leveraging Captions in the Wild to Improve Object Detection,"Proceedings of the 5th Workshop on Vision and Language, pages 29–38, Berlin, Germany, August 12 2016. c(cid:13)2016 Association for Computational Linguistics" 12b58a712396bc2fd74cd19a4d758d7b9c104c3f,Cross-Domain Recommendation in the Hotel Sector,"Cross-Domain Recommendation in the Hotel Sector Marie Al-Ghossein LTCI, T´el´ecom ParisTech Paris, France Talel Abdessalem LTCI, T´el´ecom ParisTech Paris, France UMI CNRS IPAL NUS Anthony Barr´e AccorHotels Paris, France" 12417ed7ae81fb4e6c07f501ace9ea463349481b,Pairwise Augmented GANs with Adversarial Reconstruction Loss,"PAIRWISE AUGMENTED GANS WITH ADVERSARIAL RECONSTRUCTION LOSS Aibek Alanov1,2,3∗, Max Kochurov1,2∗, Daniil Yashkov5, Dmitry Vetrov1,3,4 Samsung AI Center in Moscow Skolkovo Institute of Science and Technology National Research University Higher School of Economics Joint Samsung-HSE lab 5Federal Research Center ""Informatics and Management"" of the Russian Academy of Sciences" 12e80b3a89bc021a6352840fb4552df842a6fe7d,Fast sparse representation with prototypes,"Fast Sparse Representation with Prototypes Jia-Bin Huang and Ming-Hsuan Yang University of California at Merced" 12ebb51d50f704b5d0a8d821e90dd336175ec8aa,TUHOI: Trento Universal Human Object Interaction Dataset,"Proceedings of the 25th International Conference on Computational Linguistics, pages 17–24, Dublin, Ireland, August 23-29 2014." 1295cbaf3b03de2eb8c79530289f5939d7819e5c,DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations,"DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations Srinivas S S Kruthiventi, Kumar Ayush, and R. Venkatesh Babu, Senior Member, IEEE" 1277b1b8b609a18b94e4907d76a117c9783a5373,VirtualIdentity: Privacy preserving user profiling,"VirtualIdentity: Privacy-Preserving User Profiling Sisi Wang, Wing-Sea Poon, Golnoosh Farnadi, Caleb Horst, Kebra Thompson, Michael Nickels, Rafael Dowsley, Anderson C. A. Nascimento and Martine De Cock" 127c229a3306bfc8170b84b12316f4a8024cc7ab,"A derived transformation of emotional functions using self-reports, implicit association tests, and frontal alpha asymmetries.","Learn Behav DOI 10.3758/s13420-015-0198-6 A derived transformation of emotional functions using self-reports, implicit association tests, and frontal lpha asymmetries Micah Amd 1 & Bryan Roche 1 # Psychonomic Society, Inc. 2015" 120785f9b4952734818245cc305148676563a99b,Diagnostic automatique de l'état dépressif(Classification of depressive moods),"Diagnostic automatique de l’état dépressif S. Cholet H. Paugam-Moisy Laboratoire de Mathématiques Informatique et Applications (LAMIA - EA 4540) Université des Antilles, Campus de Fouillole - Guadeloupe Résumé Les troubles psychosociaux sont un problème de santé pu- lique majeur, pouvant avoir des conséquences graves sur le court ou le long terme, tant sur le plan professionnel que personnel ou familial. Le diagnostic de ces troubles doit être établi par un professionnel. Toutefois, l’IA (l’Intelli- gence Artificielle) peut apporter une contribution en four- nissant au praticien une aide au diagnostic, et au patient un suivi permanent rapide et peu coûteux. Nous proposons une approche vers une méthode de diagnostic automatique de l’état dépressif à partir d’observations du visage en temps réel, au moyen d’une simple webcam. A partir de vidéos du challenge AVEC’2014, nous avons entraîné un lassifieur neuronal à extraire des prototypes de visages selon différentes valeurs du score de dépression de Beck" 12ff1c48f5776fda9d156c7b324af3f2674420a9,Are Large Scale Training Images or Discriminative Features Important for Codebook Construction?, 129ac698f62ca7f9024423671f4128d83a0c3c66,Image Matching Scheme by using Bhattacharyya Coefficient Algorithm,"ISSN(Online): 2320-9801 ISSN (Print): 2320-9798 International Journal of Innovative Research in Computer nd Communication Engineering (An ISO 3297: 2007 Certified Organization) Vol. 3, Issue 7, July 2015 Image Matching Scheme by using Bhattacharyya Coefficient Algorithm Nwe Nwe Soe Lecturer, Dept. of Software Technology, Computer University (Thaton), Myanmar" 12150d8b51a2158e574e006d4fbdd3f3d01edc93,Deep End2End Voxel2Voxel Prediction,"Deep End2End Voxel2Voxel Prediction Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri Presented by: Ahmed Osman Ahmed Osman" 12948518bb457d0d302bbf00160f4165ce089b9b,Adversarial Spatio-Temporal Learning for Video Deblurring,"Adversarial Spatio-Temporal Learning for Video Deblurring Kaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma, Wei Liu, and Hongdong Li" 120437e10236d175fa5c0a752a88b98617763eef,SWIR images evaluation for pedestrian detection in clear visibility conditions,"Proceedings of the 16th International IEEE Annual Conference on Intelligent Transportation Systems (ITSC 2013), The Hague, The Netherlands, October 6-9, 2013 MoC3.5 978-1-4799-2914-613/$31.00 ©2013 IEEE" 123a9768700433c405bd7266f4c57ca8222e7fe1,Expanded Parts Model for Human Attribute and Action Recognition in Still Images,"Expanded Parts Model for Human Attribute and Action Recognition in Still Images Gaurav Sharma1,2, Fr´ed´eric Jurie1, Cordelia Schmid2 GREYC, CNRS UMR 6072, University of Caen Basse-Normandie LEAR, INRIA Grenoble Rhˆone-Alpes inria}.fr" 122ee00cc25c0137cab2c510494cee98bd504e9f,The Application of Active Appearance Models to Comprehensive Face Analysis Technical Report,"The Application of Active Appearance Models to Comprehensive Face Analysis Technical Report Simon Kriegel TU M¨unchen April 5, 2007" 12149fc431d2b3ec4d1f194e92e74c765e51ee67,Concentration in unbounded metric spaces and algorithmic stability,"Concentration in unbounded metric spaces and algorithmic stability Aryeh Kontorovich Department of Computer Science, Ben-Gurion University, Beer Sheva 84105, ISRAEL" 12ebeb2176a5043ad57bc5f3218e48a96254e3e9,Traffic Road Sign Detection and Recognition for Automotive Vehicles,"International Journal of Computer Applications (0975 – 8887) Volume 120 – No.24, June 2015 Traffic Road Sign Detection and Recognition for Automotive Vehicles Md. Safaet Hossain Zakir Hyder Department of Electrical Engineering and Department of Electrical Engineering and Computer Science North South University, Dhaka Computer Science North South University, Dhaka Bangladesh Bangladesh" 1297e68cbfd314697817fd1eb2901fa391594b5c,The Research of the Real-time Detection and Recognition of Targets in Streetscape Videos,"The Research of the Real-time Detection and Recognition of Targets in Streetscape Videos Liu Jian-min" 1234323164b4512c5ffca6b6c53fdc8c2e7fa8bf,Design and Recording of Czech Audio-Visual Database with Impaired Conditions for Continuous Speech Recognition,"Design and recording of czech audio-visual database with impaired conditions for continuous speech recognition Jana Trojanov´a, Marek Hr´uz, Pavel Campr, Miloˇs ˇZelezn´y Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia Univerzitni 22, 306 14, Plzen, Czech Republic {trojana, mhruz, campr, zelezny" 12dfc8d4062b83a0b824b1676533482f14e4978c,Cutting Edge: Soft Correspondences in Multimodal Scene Parsing,"Cutting Edge: Soft Correspondences in Multimodal Scene Parsing Sarah Taghavi Namin1,2 Mohammad Najafi1,2 Mathieu Salzmann2,3 Australian National University (ANU) Lars Petersson1,2 CVLab, EPFL, Switzerland NICTA∗ {sarah.namin, mohammad.najafi," 12c5cd899d5ed85741197baed191f3b8b7fac495,Altered intrinsic functional connectivity of anterior and posterior insula regions in high-functioning participants with autism spectrum disorder.,"Altered Intrinsic Functional Connectivity of Anterior and Posterior Insula Regions in High-Functioning Participants With Autism Spectrum Disorder Sjoerd J.H. Ebisch,1,2* Vittorio Gallese,3,4 Roel M. Willems,5 Dante Mantini,1,2,6 Wouter B. Groen,7 Gian Luca Romani,1,2 Jan K. Buitelaar,7 and Harold Bekkering8 Department of Clinical Sciences and Bioimaging, G. d’Annunzio University Chieti-Pescara, Institute for Advanced Biomedical Technologies (ITAB), G. d’Annunzio Foundation, Chieti, Italy Department of Neuroscience, Section of Physiology, Parma University, Parma, Italy Chieti, Italy Italian Institute of Technology (IIT), Section of Parma, Italy 5Donders Institute for Brain, Cognition and Behavior, Centre for Cognitive Neuroimaging, 6Laboratory for Neuro-Psychophysiology, K.U. Leuven Medical School, Leuven, Belgium 7Department of Psychiatry, Radboud University Medical Centre and Karakter University Centre for Radboud University, Nijmegen, The Netherlands Child and Adolescent Psychiatry, Nijmegen, The Netherlands 8Donders Institute for Brain, Cognition and Behavior, Centre for Cognition, Radboud University, Nijmegen, The Netherlands" 12d62f1360587fdecee728e6c509acc378f38dc9,Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification Guodong Ding, Shanshan Zhang, Salman Khan, Zhenmin Tang, Jian Zhang, Senior Member, IEEE and Fatih Porikli, Fellow, IEEE" 12fd613bc68101176d8fdf1b28d4d6fb3e3fec6f,Training a Scene-Specific Pedestrian Detector Using Tracklets,"Training a Scene-Specific Pedestrian Detector Using Tracklets Yunxiang Mao Zhaozheng Yin Department of Computer Science Missouri University of Science and Technology, USA" 1246534c3104da030fdb9e041819257e0d57dcbf,Virtual view networks for object reconstruction,"Virtual View Networks for Object Reconstruction Jo˜ao Carreira, Abhishek Kar, Shubham Tulsiani and Jitendra Malik University of California, Berkeley - Berkeley, CA 94720" 124fddbb5cbe4e5e6ea69be1467437aad01eb5d9,A Unified Algorithmic Framework for Multi-Dimensional Scaling,"A Unified Algorithmic Framework for Multi-Dimensional Scaling Arvind Agarwal Jeff M. Phillips† Suresh Venkatasubramanian‡" 126be977c03d732fbef2381565a41b957d41a2cc,Discourse-Level Language Understanding with Deep Learning, 12c262912f4c09e6f34d40de77f68b465d80ac8d,Adaptive Graph Guided Embedding for Multi-label Annotation,"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) FurOutdoorMentalHumanmadeBrownFur(cid:1850)(cid:3039)(cid:1850)(cid:3048)WaterOutdoorWaterTreesFigure1:Frameworkofourmodel,whereanadaptiveaffinitygraphSconnectspair-wiserelationsacrosslabeledandunlabeledsamples.Apre-definedgraphfullyprovideslocalstructureinformationandacceleratesoptimizationprocess.AprojectionPprojectsdataintoacommonanddistinctivespacewhichalsoeliminatesinterruptionsfromnoiseandoutliers.P,S,andlabelmatrixFaresimultaneouslyupdatedtoachieveaccurateandrobustperformance.performance.Consequently,semi-supervisedlearning[Zhuetal.,2003]especiallygraph-basedapproach[Zhaetal.,2009]hasattractedgreatattention.However,theystillhavelimitationsthatthesemethodshighlydependonthepre-constructedgraphbutrarelyoptimizeitonline.Inaddi-tion,mostmethodsconstructgraphdirectlyonfeaturespace,whichissensitivetonoiseandoutliers.Severalworkuti-lizeadaptivegraphstohandletheproblem[Nieetal.,2012;2016].However,thesemethodsmainlyfocusonsingle-labelclassificationinsteadofmulti-labelscenario.Tothisend,weproposeanovelAdaptiveGraphGuidedEmbedding(AG2E)formulti-labellearninginsemi-supervisedfashion.Figure1showstheframeworkofAG2E,whosecoreideaislearningasemi-supervisedlabelpropaga-tionandaneffectiveembeddingsimultaneouslytoseekala-tentspace,andthusunlabeledimagescanbewellrecovered.Ourmaincontributionsaresummarizedasfollows:(cid:15)Weseekanadaptivegraphtoautomaticallycapturethelatentstructureofthedata.Moreover,apre-defined" 126b98473cc25e604abd58eb6bcf720354ac7e7a,An experimental illustration of 3D facial shape analysis under facial expressions,"Author manuscript, published in ""Annals of Telecommunications 64, 5-6 (2009) 369-379""" 127316fbe268c78c519ceb23d41100e86639418a,CNN Features Off-the-Shelf: An Astounding Baseline for Recognition,"CNN Features off-the-shelf: an Astounding Baseline for Recognition Ali Sharif Razavian Hossein Azizpour Josephine Sullivan Stefan Carlsson CVAP, KTH (Royal Institute of Technology) Stockholm, Sweden" 12b29fd079e047f564e115e6106f750713eabe61,Attribute-Guided Network for Cross-Modal Zero-Shot Hashing.,"Attribute-Guided Network for Cross-Modal Zero-Shot Hashing Zhong Ji, Yuxin Sun, Yunlong Yu, Yanwei Pang, Jungong Han" 12d8730da5aab242795bdff17b30b6e0bac82998,Persistent Evidence of Local Image Properties in Generic ConvNets,"Persistent Evidence of Local Image Properties in Generic ConvNets Ali Sharif Razavian, Hossein Azizpour, Atsuto Maki, Josephine Sullivan, Carl Henrik Ek, and Stefan Carlsson CVAP, KTH (Royal Institute of Technology), Stockholm, SE-10044" 12ba7c6f559a69fbfaacf61bfb2f8431505b09a0,DocFace+: ID Document to Selfie Matching,"DocFace+: ID Document to Selfie* Matching Yichun Shi, Student Member, IEEE, and Anil K. Jain, Life Fellow, IEEE" 122c674f264c53d762af841669209e131b49b3f2,Non-Rigid Structure from Motion for Building 3 D Face Model,"Faculty of Informatics Institute for Anthropomatics Chair Prof. Dr.-Ing. R. Stiefelhagen Facial Image Processing and Analysis Group Non-Rigid Structure from Motion for Building 3D Face Model DIPLOMA THESIS OF Chengchao Qu ADVISORS Dipl.-Inform. Hua Gao Dr.-Ing. Hazım Kemal Ekenel MARCH 2011 KIT – University of the State of Baden-Württemberg and National Laboratory of the Helmholtz Association www.kit.edu" 1232b992530bff6a8b209d7d71793c343ede0664,Fusion of Multiple Facial Regions for Expression-Invariant Face Recognition,"(cid:176)2007 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for dvertising or promotional purposes or for creating new col- lective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE." 1252b27c42bf095f1eccba2aee3765dab49647e3,Optical Flow with Semantic Segmentation and Localized Layers,"Optical Flow with Semantic Segmentation and Localized Layers Laura Sevilla-Lara1 Deqing Sun2,3 Varun Jampani1 Michael J. Black1 {laura.sevilla, varun.jampani, MPI for Intelligent Systems NVIDIA, 3Harvard University (a) Initial segmentation [9] (b) Our segmentation (c) DiscreteFlow [38] (d) Semantic Optical Flow Figure 1: (a) Semantic segmentation breaks the image into regions such as road, bike, person, sky, etc. (c) Existing optical flow algorithms do not have access to either the segmentations or the semantics of the classes. (d) Our semantic optical flow lgorithm computes motion differently in different regions, depending on the semantic class label, resulting in more precise flow, particularly at object boundaries. (b) The flow also helps refine the segmentation of the foreground objects." 1272d526614e40ce859e73de7e39a54baffd28cc,A unified approach to learning task-specific bit vector representations for fast nearest neighbor search,"A Unified Approach to Learning Task-Specific Bit Vector Representations for Fast Nearest Neighbor Search Vinod Nair Yahoo! Labs Bangalore Dhruv Mahajan Yahoo! Labs Bangalore S. Sundararajan Yahoo! Labs Bangalore" 12c7ecbfd714c160d2a6bb9cf03fa8b88e8da62b,Impaired Recognition of Basic Emotions from Facial Expressions in Young People with Autism Spectrum Disorder: Assessing the Importance of Expression Intensity.,"Griffiths, S. L., Jarrold, C., Penton-Voak, I., Woods, A., Skinner, A., & Munafo, M. (2017). Impaired Recognition of Basic Emotions from Facial Expressions in Young People with Autism Spectrum Disorder: Assessing the Importance of Expression Intensity. Journal of Autism and Developmental Disorders. DOI: 10.1007/s10803-017-3091-7 Publisher's PDF, also known as Version of record License (if available): CC BY Link to published version (if available): 0.1007/s10803-017-3091-7 Link to publication record in Explore Bristol Research PDF-document This is the final published version of the article (version of record). It first appeared online via Springer at http://link.springer.com/article/10.1007%2Fs10803-017-3091-7. Please refer to any applicable terms of use of the publisher. University of Bristol - Explore Bristol Research General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: http://www.bristol.ac.uk/pure/about/ebr-terms.html" 1287bfe73e381cc8042ac0cc27868ae086e1ce3b,Computational Mid-Level Vision: From Border Ownership to Categorical Object Recognition, 12831caca9674e0ab3fe2fc02a447ddb5a372994,Deep Aesthetic Quality Assessment With Semantic Information,"Deep Aesthetic Quality Assessment with Semantic Information Yueying Kao, Ran He, Kaiqi Huang" 28209a6ef1de7c10ec13717eba8bad7c2f4feba7,Deep Representation of Facial Geometric and Photometric Attributes for Automatic 3D Facial Expression Recognition,"Deep Representation of Facial Geometric and Photometric Attributes for Automatic 3D Facial Expression Recognition Huibin Li, Jian Sun∗, Dong Wang, Zongben Xu, and Liming Chen" 28cd46a078e8fad370b1aba34762a874374513a5,"cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey","CVPAPER.CHALLENGE IN 2016, JULY 2017 vpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey Hirokatsu Kataoka, Soma Shirak- be, Yun He, Shunya Ueta, Teppei Suzuki, Kaori Abe, Asako Kanezaki, Shin’ichiro Morita, Toshiyuki Yabe, Yoshihiro Kanehara, Hiroya Yatsuyanagi, Shinya Maruyama, Ryosuke Taka- sawa, Masataka Fuchida, Yudai Miyashita, Kazushige Okayasu, Yuta Matsuzaki" 28eceb438da0b841bbd3d02684dbfa263838ed60,Photographic Image Synthesis with Cascaded Refinement Networks,"Photographic Image Synthesis with Cascaded Refinement Networks Qifeng Chen† ‡ Vladlen Koltun† (a) Input semantic layouts (b) Synthesized images Figure 1. Given a pixelwise semantic layout, the presented model synthesizes an image that conforms to this layout. (a) Semantic layouts from the Cityscapes dataset of urban scenes; semantic classes are coded by color. (b) Images synthesized by our model for these layouts. The layouts shown here and throughout the paper are from the validation set and depict scenes from new cities that were never seen during training. Best viewed on the screen." 28aa89b2c827e5dd65969a5930a0520fdd4a3dc7,CHARACTERIZATION AND CLASSIFICATION OF FACES ACROSS AGE PROGRESSION by Narayanan Ramanathan, 2866cbeb25551257683cf28f33d829932be651fe,A Two-Step Learning Method For Detecting Landmarks on Faces From Different Domains,"In Proceedings of the 2018 IEEE International Conference on Image Processing (ICIP) The final publication is available at: http://dx.doi.org/10.1109/ICIP.2018.8451026 A TWO-STEP LEARNING METHOD FOR DETECTING LANDMARKS ON FACES FROM DIFFERENT DOMAINS Bruna Vieira Frade Erickson R. Nascimento Universidade Federal de Minas Gerais (UFMG), Brazil {brunafrade," 28103f6c09fd64c90a738076b0681400d4d31c9f,Color Invariants for Person Reidentification,"Color Invariants for Person Re-Identification Igor Kviatkovsky Technion - Computer Science Department - M.Sc. Thesis MSC-2012-03 - 2012" 289f58b43794394cd312944147b80986ed5d7bef,Face Verification using SVM : Influence of illumination,"Face Verification using SVM: Influence of illumination. Cristina Conde*, Antonio Ruiz**, Francisco Martín*, Susana Mata**, Luis Pastor* Javier Moguerza* and Enrique Cabello* * Universidad Rey Juan Carlos (ESCET) C/ Tulipan s/n 8933 Mostoles Madrid (Spain) e-mail: {cristina.conde, l.pastor, j.moguerza, ** Universidad Politécnica de Madrid (Facultad de Informatica) Departamento de Tecnologia Fotonica Campus de Monteganedos/n 8660 Boadilla del Monte (Spain) e-mail: {aruiz," 28d65e4d72638983fbc723b102d78b10587c06aa,Low Resolution Sparse Binary Face Patterns, 286c1e0b34ee6d40706ca6a02604420a192204e7,An overview of NuDetective Forensic Tool and its usage to combat child pornography in Brazil,"An overview of NuDetective Forensic Tool and its usage to combat child pornography in Brazil Pedro Monteiro da Silva Eleuterio and Mateus de Castro Polastro Brazilian Federal Police" 284af686292a6119129b410413831f8d2363fcc6,"Learning Representation for Scene Understanding: Epitomes, CRFs, and CNNs","UCLA Electronic Theses and Dissertations Title Learning Representation for Scene Understanding: Epitomes, CRFs, and CNNs Permalink https://escholarship.org/uc/item/5zd9x7v8 Author Chen, Liang-Chieh Publication Date Peer reviewed|Thesis/dissertation eScholarship.org Powered by the California Digital Library University of California" 28446fa9d9ac0468cc715594a6dcc0ac5d9288a5,Semantic Instance Segmentation for Autonomous Driving Bert,"Semantic Instance Segmentation for Autonomous Driving Bert De Brabandere Davy Neven Luc Van Gool ESAT-PSI, KU Leuven" 2814d558b4d7425b5dae6b3dbbf5f4a08650fcb1,A joint estimation of head and body orientation cues in surveillance video,"A Joint Estimation of Head and Body Orientation Cues in Surveillance Video Cheng Chen Alexandre Heili Jean-Marc Odobez Idiap Research Institute – CH-1920, Martigny, Switzerland∗" 2803a7e8e6057d4e9462b37b258e670df61a742d,The Conference on Empirical Methods in Natural Language Processing Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing,"EMNLP2017TheConferenceonEmpiricalMethodsinNaturalLanguageProcessingProceedingsofthe2ndWorkshoponStructuredPredictionforNaturalLanguageProcessingSeptember9-11,2017Copenhagen,Denmark" 28126d165f73c2a18600a9b0440f5e80191d52d9,Clock-Modeled Ternary Spatial Relations for Visual Scene Analysis,"Clock-Modeled Ternary Spatial Relations for Visual Scene Analysis Joanna Isabelle Olszewska School of Computing and Engineering, University of Huddersfield Queensgate, Huddersfield, HD1 3DH, United Kingdom" 287c5be2610e1c61798851feb32b88c424acfbf9,Hierarchical Co-Attention for Visual Question Answering,"Hierarchical Co-Attention for Visual Question Answering Jiasen Lu, Jianwei Yang, Dhruv Batra, Devi Parikh Virginia Tech {jiasenlu, jw2yang, dbatra," 28e77337bcb88e37d36f5660709a53e71377a2a8,5 Discriminative Cluster Analysis,",250+OPEN ACCESS BOOKS106,000+INTERNATIONALAUTHORS AND EDITORS112+ MILLIONDOWNLOADSBOOKSDELIVERED TO151 COUNTRIESAUTHORS AMONGTOP 1%MOST CITED SCIENTIST12.2%AUTHORS AND EDITORSFROM TOP 500 UNIVERSITIESSelection of our books indexed in theBook Citation Index in Web of Science™Core Collection (BKCI)Chapter from the book Theory and Novel Applications of Machine LearningDownloaded from:http://www.intechopen.com/books/theory_and_novel_applications_of_machine_learningPUBLISHED BYWorld's largest Science,Technology & Medicine Open Access book publisherInterested in publishing with InTechOpen?Contact us at" 286ea63b1b5df1b8b67718f25b47357ec3168e97,Human parsing using stochastic and-or grammars and rich appearances,"Human Parsing using Stochastic And-Or Grammars and Rich Appearances Brandon Rothrock and Song-Chun Zhu UCLA Dept. of Computer Science Thursday, November 17, 11" 28f5f8dc2f2f9f2a4e49024fe6aa7e9a63b23ab0,Vision-based bicycle detection and tracking using a deformable part model and an EKF algorithm,"Vision-based Bicycle Detection and Tracking using a Deformable Part Model and an EKF Algorithm Hyunggi Cho, Paul E. Rybski and Wende Zhang" 28bd795c580ca24f40dc82cd01d9d277749d2661,Site-adaptation methods for face recognition,"Site-adaptation methods for face recognition Jilin Tu and Xiaoming Liu and Peter Tu" 283b3160f02db64759259b4eb39dd54c4969d6f8,ActivityNet: A large-scale video benchmark for human activity understanding,"ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding Fabian Caba Heilbron1,2, Victor Escorcia1,2, Bernard Ghanem2 and Juan Carlos Niebles1 King Abdullah University of Science and Technology (KAUST), Saudi Arabia Universidad del Norte, Colombia" 2842cebee2793c9b4f503895a32b328b7781b60e,BWIBots: A platform for bridging the gap between AI and human-robot interaction research,"Article BWIBots: A platform for bridging the gap between AI and human–robot interaction research The International Journal of Robotics Research © The Author(s) 2017 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/0278364916688949 journals.sagepub.com/home/ijr Piyush Khandelwal1, Shiqi Zhang1,2, Jivko Sinapov1, Matteo Leonetti1,3, Jesse Thomason1, Fangkai Yang4, Ilaria Gori5, Maxwell Svetlik1, Priyanka Khante1, Vladimir Lifschitz1, J. K. Aggarwal5, Raymond Mooney1 and Peter Stone1" 28525f9bb0797fdf7c0a8a9d1666015c60610077,Development of Mobile Face Verification Based on Locally Normalized Gabor Wavelets,"Development of Mobile Face Verification Based on Locally Normalized Gabor Wavelets Fadhlan Hafizhelmi Kamaru Zaman*, Ahmad Asari Sulaiman#, Ihsan Mohd Yassin#, Nooritawati Md Tahir#, Zairi Ismael Rizman& *Department of Computer Engineering, Faculty of Electrical Engineering, Universiti Teknologi MARA, Shah Alam, Selangor, Malaysia E-mail: #Department of Communications Engineering, Faculty of Electrical Engineering, Universiti Teknologi MARA, Shah Alam, Selangor, Malaysia E-mail: &Faculty of Electrical Engineering, Universiti Teknologi MARA, Dungun, Terengganu, Malaysia E-mail:" 28daa489dace2d2f040dcdbbd2d4ab919b046254,2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning,"D/3D Pose Estimation and Action Recognition using Multitask Deep Learning ETIS UMR 8051, Paris Seine University, ENSEA, CNRS, F-95000, Cergy, France Sorbonne Universit´e, CNRS, Laboratoire d’Informatique de Paris 6, LIP6, F-75005 Paris, France Diogo C. Luvizon1, David Picard1,2, Hedi Tabia1 {diogo.luvizon, picard," 28f1f6cbe07b117387e2b07c11e7ac9c4ef8cf95,A Machine Learning Approach to Pedestrian Detection for Autonomous Vehicles Using High-Definition 3D Range Data,"Article A Machine Learning Approach to Pedestrian Detection for Autonomous Vehicles Using High-Definition 3D Range Data Pedro J. Navarro *,†, Carlos Fernández †, Raúl Borraz † and Diego Alonso † División de Sistemas en Ingeniería Electrónica (DSIE), Universidad Politécnica de Cartagena, Campus Muralla del Mar, s/n, Cartagena 30202, Spain; (C.F.); (R.B.); (D.A.) * Correspondence: Tel.: +34-968-32-6546 These authors contributed equally to this work. Academic Editor: Felipe Jimenez Received: 31 October 2016; Accepted: 15 December 2016; Published: 23 December 2016" 286eb053f55e45ad5d0490c1c18f6d80381dfb4b,Block-Sparse Recovery via Convex Optimization,"Block-Sparse Recovery via Convex Optimization Ehsan Elhamifar, Student Member, IEEE, and Ren´e Vidal, Senior Member, IEEE" 2891ceceaf586e4ae013d932978074ff0a06801f,Joint statistical analysis of images and keywords with applications in semantic image enhancement,"Joint Statistical Analysis of Images and Keywords with Applications in Semantic Image Enhancement Albrecht Lindner School of Computer and Communication Sciences EPFL, Switzerland Nicolas Bonnier Océ Print Logic Technologies Créteil, France Appu Shaji School of Computer and Communication Sciences EPFL, Switzerland Sabine Süsstrunk School of Computer and Communication Sciences EPFL, Switzerland" 283550fce0fdc0876db5df533625dffdfcd8d099,Fairness-aware scheduling on single-ISA heterogeneous multi-cores,"Fairness-Aware Scheduling on Single-ISA Heterogeneous Multi-Cores Kenzo Van Craeynest†◦ Ghent University, Belgium Shoaib Akram† Wim Heirman†◦ ◦ExaScience Lab, Belgium Aamer Jaleel‡ Lieven Eeckhout† VSSAD, Intel Corporation (e.g.," 2868622003cbfd5cfc817cb57896298c0858b166,BIFOCAL STEREO FOR MULTIPATH PERSON RE-IDENTIFICATION,"BIFOCAL STEREO FOR MULTIPATH PERSON RE-IDENTIFICATION G. Blotta,b∗, C. Heipkeb Robert Bosch, Computer Vision Lab, Hildesheim, Germany, Institute of Photogrammetry and GeoInformation, Leibniz Universit¨at Hannover, Germany Commission II KEY WORDS: Person Re-Identification, PRID, Bifocal Stereo, Multipath Person Re-Identification" 2805daf3795e4e153d79dbecfe88b830ddc068d3,Articulated human motion tracking with foreground learning,"ARTICULATED HUMAN MOTION TRACKING WITH FOREGROUND LEARNING Aichun Zhu1, Hichem Snoussi1, Abel Cherouat2 ICD - LM2S - Universit´e de Technologie de Troyes (UTT) - UMR STMR CNRS ICD - GAMMA3 - Universit´e de Technologie de Troyes (UTT) - UMR STMR CNRS 2 rue Marie Curie - CS 42060 - 10004 Troyes cedex - France E-mail :{aichun.zhu, hichem.snoussi," 281be1be2f0ecce173e3678a7e87419f0815e016,Studies of Plain-to-Rolled Fingerprint Matching Using the NIST Algorithmic Test Bed ( ATB ) NISTIR 7112,"Studies of Plain-to-Rolled Fingerprint Matching Using the NIST Algorithmic Test Bed (ATB) NISTIR 7112 Stephen S. Wood Charles L. Wilson April 2004" 280d59fa99ead5929ebcde85407bba34b1fcfb59,Online nonnegative matrix factorization with outliers,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 2830fb5282de23d7784b4b4bc37065d27839a412,Poselets: Body part detectors trained using 3D human pose annotations,"Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations ∗ Lubomir Bourdev1,2 and Jitendra Malik1 EECS, U.C. Berkeley, Berkeley, CA 94720 Adobe Systems, Inc., 345 Park Ave, San Jose, CA 95110" 28b6adbc5ef790413431cdb2f512432862778b3b,Security and Surveillance,"Security and Surveillance Shaogang Gong and Chen Change Loy and Tao Xiang" 28c9198d30447ffe9c96176805c1cd81615d98c8,No evidence that a range of artificial monitoring cues influence online donations to charity in an MTurk sample,"rsos.royalsocietypublishing.org Research Cite this article: Saunders TJ, Taylor AH, Atkinson QD. 2016 No evidence that a range of rtificial monitoring cues influence online donations to charity in an MTurk sample. R. Soc. open sci. 3: 150710. http://dx.doi.org/10.1098/rsos.150710 Received: 22 December 2015 Accepted: 13 September 2016 Subject Category: Psychology and cognitive neuroscience Subject Areas: ehaviour/psychology/evolution Keywords: prosociality, eye images, charity donation, reputation, online behaviour Author for correspondence: Quentin D. Atkinson e-mail:" 283181a2173b485726664edc6fe73f0465387629,Random Temporal Skipping for Multirate Video Analysis,"Random Temporal Skipping for Multirate Video Analysis Yi Zhu1 and Shawn Newsam1 University of California at Merced, Merced CA 95343, USA" 284b5dafe6d8d7552794ccd2efb4eabb12dc3512,Efficient and accurate inversion of multiple scattering with deep learning,"Efficient and accurate inversion of multiple scattering with deep learning Yu Sun1, Zhihao Xia1, and Ulugbek S. Kamilov1,2,∗ Department of Computer Science and Engineering, Washington University in St. Louis, MO 63130, USA. Department of Electrical and Systems Engineering, Washington University in St. Louis, MO 63130, USA. email:" 287afb29b5aef6255a5882418b87e6b41cc9b29d,Nude Detection in Video Using Bag-of-Visual-Features,"Nude Detection in Video using Bag-of-Visual-Features Ana Paula B. Lopes∗†, Sandra E. F. de Avila∗, Anderson N. A. Peixoto∗, Rodrigo S. Oliveira∗, Marcelo de M. Coelho∗‡ and Arnaldo de A. Ara´ujo∗ Computer Science Department, Federal University of Minas Gerais – UFMG Exact and Technological Sciences Department, State University of Santa Cruz – UESC 1270–010, Belo Horizonte, MG, Brazil 5662–000, Ilh´eus, BA, Brazil Preparatory School of Air Cadets – EPCAR 6205–900, Barbacena, MG, Brazil {paula, sandra, andenap, rsilva, mcoelho," 28bc378a6b76142df8762cd3f80f737ca2b79208,Understanding Objects in Detail with Fine-Grained Attributes,"Understanding Objects in Detail with Fine-grained Attributes Andrea Vedaldi1 Siddharth Mahendran2 Stavros Tsogkas3 Subhransu Maji4 Ross Girshick5 Juho Kannala6 Esa Rahtu6 Matthew B. Blaschko3 David Weiss7 Ben Taskar8 Naomi Saphra2 Sammy Mohamed9 Iasonas Kokkinos3 Karen Simonyan1" 28795f32b324eb3601e9a8c1ce93335691e120f3,CliqueCNN: Deep Unsupervised Exemplar Learning,"CliqueCNN: Deep Unsupervised Exemplar Learning Miguel A. Bautista∗, Artsiom Sanakoyeu∗, Ekaterina Sutter, Björn Ommer Heidelberg Collaboratory for Image Processing IWR, Heidelberg University, Germany" 2864c8df356b1b915e16bb285bda64bfd7396f74,3D Face Reconstruction from Stereo: A Model Based Approach,"-4244-1437-7/07/$20.00 ©2007 IEEE III - 65 ICIP 2007" 282578039c767f3d393529565cae6be56fda6242,Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes,"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes Hassan Abu Alhaija1 Siva Karthik Mustikovela1 Lars Mescheder2 Andreas Geiger2,3 Carsten Rother1 Computer Vision Lab, TU Dresden Autonomous Vision Group, MPI for Intelligent Systems T¨ubingen Computer Vision and Geometry Group, ETH Z¨urich" 28e1c113b1b57e0731c189d28e404cea3bddf260,Template based Mole Detection for Face Recognition,"is used recognition" 28f9cf85ebbff86207e1f6067880bb23daff0878,Prime Object Proposals with Randomized Prim's Algorithm,"Prime Object Proposals with Randomized Prim’s Algorithm Santiago Manen1 Matthieu Guillaumin1 Luc Van Gool1,2 Computer Vision Laboratory ESAT - PSI / IBBT {smanenfr, guillaumin, ETH Zurich K.U. Leuven" 28589357a7631581e55ec6db3cde2e24e4789482,Involuntary processing of social dominance cues from bimodal face-voice displays.,"Cognition and Emotion ISSN: 0269-9931 (Print) 1464-0600 (Online) Journal homepage: http://www.tandfonline.com/loi/pcem20 Involuntary processing of social dominance cues from bimodal face-voice displays Virginie Peschard, Pierre Philippot & Eva Gilboa-Schechtman To cite this article: Virginie Peschard, Pierre Philippot & Eva Gilboa-Schechtman (2016): Involuntary processing of social dominance cues from bimodal face-voice displays, Cognition and Emotion, DOI: 10.1080/02699931.2016.1266304 To link to this article: http://dx.doi.org/10.1080/02699931.2016.1266304 Published online: 21 Dec 2016. Submit your article to this journal Article views: 33 View related articles View Crossmark data Full Terms & Conditions of access and use can be found at http://www.tandfonline.com/action/journalInformation?journalCode=pcem20 Download by: [UCL Service Central des Bibliothèques] Date: 25 April 2017, At: 23:38" 284be8be0c6bedc36dfe43229bc84345ab0aedc2,Faster Training of Mask R-CNN by Focusing on Instance Boundaries,"Faster Training of Mask R-CNN by Focusing on Instance Boundaries$ Roland S. Zimmermanna,b,1, Julien N. Siemsa,c,2 BMW Car IT GmbH, Lise-Meitner-Straße 14, 89081 Ulm, Germany Georg-August University of G¨ottingen, Friedrich-Hund-Platz 1, 37077 G¨ottingen, Germany Albert Ludwig University of Freiburg, Fahnenbergplatz, 79085 Freiburg im Breisgau, Germany" 2848cde23fe32c30980183f33b6a2c2ce7526726,Three-Dimensional Model-Based Human Detection in Crowded Scenes,"Title Three-dimensional model-based human detection in crowded scenes Author(s) Wang, L; Yung, NHC Citation v. 13 n. 2, p. 691-703 Issued Date http://hdl.handle.net/10722/155766 Rights Copyright © IEEE.; ©20xx IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new ollective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.; This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives .0 International License." 28c24f16e20c83c747f2aca8232f2cb6614905f5,The Role of Face Parts in Gender Recognition,"The Role of Face Parts in Gender Recognition Yasmina Andreu and Ram´on A. Mollineda Dept. Llenguatges i Sistemes Inform`atics Universitat Jaume I. Castell´o de la Plana, Spain" 28e9ae07540e3709e7a3a6242f636f893ba557e6,Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework,"Learning to Select Pre-trained Deep Representations with Bayesian Evidence Framework Yong-Deok Kim∗1 Taewoong Jang∗2 Bohyung Han3 Seungjin Choi3 Software R&D Center, Device Solutions, Samsung Electronics, Korea Department of Computer Science and Engineering, POSTECH, Korea Stradvision Inc., Korea" 28af8e1a3cb3a158f8a642c8493fcfb207743d0a,Better Image Segmentation by Exploiting Dense Semantic Predictions,"Better Image Segmentation by Exploiting Dense Semantic Predictions Qiyang Zhao, Lewis D Griffin Beihang University & UCL" 288c03d30821d5b12754c8f21bcd76a76dd4a6fb,Feature-based Face Detection Against Skin-color Like Backgrounds with Varying Illumination,"Journal of Information Hiding and Multimedia Signal Processing Ubiquitous International ⃝2011 ISSN 2073-4212 Volume 2, Number 2, April 2011 Feature-based Face Detection Against Skin-color Like Backgrounds with Varying Illumination Wu-Chih Hu1, Ching-Yu Yang1, Deng-Yuan Huang2, and Chun-Hsiang Huang1 Department of Computer Science and Information Engineering, National Penghu University of Science and Technology, Taiwan 00, Liu-Ho Rd., Makung, Penghu 880, Taiwan Department of Electrical Engineering, Dayeh University, Taiwan 68, University Rd., Dacun, Changhua 515, Taiwan Received January 2010; revised August 2010" 28b061b5c7f88f48ca5839bc8f1c1bdb1e6adc68,Predicting User Annoyance Using Visual Attributes,"Predicting User Annoyance Using Visual Attributes Gordon Christie Virginia Tech Amar Parkash Goibibo Ujwal Krothapalli Virginia Tech Devi Parikh Virginia Tech" 28f53ec7732299fa946ed3fc27bf691a6ab5c60c,Spatial as Deep: Spatial CNN for Traffic Scene Understanding,"Spatial As Deep: Spatial CNN for Traffic Scene Understanding Xingang Pan1, Jianping Shi2, Ping Luo1, Xiaogang Wang1, and Xiaoou Tang1 {px117, pluo, The Chinese University of Hong Kong 2SenseTime Group Limited" 165d966940dcccf9c9976ebffcabe72d66996b05,Semi-Supervised Nonlinear Hashing Using Bootstrap Sequential Projection Learning,"This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Semi-supervised Nonlinear Hashing Using Bootstrap Sequential Projection Learning Chenxia Wu, Jianke Zhu, Deng Cai, Chun Chen, and Jiajun Bu" 1654fadee3e70d744a4eb231932b87c41c1e3ae5,Survey on Emotional Body Gesture Recognition,"JOURNAL OF IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, VOL. XX, NO. X, XXX 201X Survey on Emotional Body Gesture Recognition Fatemeh Noroozi, Ciprian Adrian Corneanu, Dorota Kami´nska, Tomasz Sapi´nski, Sergio Escalera, nd Gholamreza Anbarjafari," 16395b40e19cbc6d5b82543039ffff2a06363845,Action Recognition in Video Using Sparse Coding and Relative Features,"Action Recognition in Video Using Sparse Coding and Relative Features Anal´ı Alfaro Domingo Mery Alvaro Soto P. Universidad Catolica de Chile P. Universidad Catolica de Chile P. Universidad Catolica de Chile Santiago, Chile Santiago, Chile Santiago, Chile" 16da7c95c218e9e97eea7734d6c243e8b825196d,A stable and accurate multi-reference representation for surfaces of R3: Application to 3D faces description,"A stable and accurate multi-reference representation for surfaces of R3: Application to 3D faces description Wieme Gadacha1, Faouzi Ghorbel1 CRISTAL laboratory, GRIFT research group National School of Computer Sciences (NSCS), La Manouba 2010, Tunisia" 166186e551b75c9b5adcc9218f0727b73f5de899,Automatic Age and Gender Recognition in Human Face Image Dataset using Convolutional Neural Network System,"Volume 4, Issue 2, February 2016 International Journal of Advance Research in Computer Science and Management Studies Research Article / Survey Paper / Case Study Available online at: www.ijarcsms.com ISSN: 2321-7782 (Online) Automatic Age and Gender Recognition in Human Face Image Dataset using Convolutional Neural Network System Subhani Shaik1 Assoc. Prof & Head of the Department Department of CSE, Anto A. Micheal2 Associate Professor Department of CSE, St.Mary’s Group of Institutions Guntur St.Mary’s Group of Institutions Guntur Chebrolu(V&M),Guntur(Dt), Andhra Pradesh - India Chebrolu(V&M),Guntur(Dt), Andhra Pradesh - India" 161c9ef7114bda7c5a60a29ee4a3161b0a76e676,Low Rank Approximation and Decomposition of Large Matrices Using Error Correcting Codes,"Low rank approximation and decomposition of large matrices using error correcting codes Shashanka Ubaru, Arya Mazumdar Senior Member, IEEE, and Yousef Saad" 166b5bdea1f4f850af5b045a953d6de74bc18d1e,Best of both worlds: Human-machine collaboration for object annotation,"Best of both worlds: human-machine collaboration for object annotation Olga Russakovsky1, Li-Jia Li2, Li Fei-Fei1 Stanford University. 2Snapchat (this work was done while at Yahoo! Labs). The long-standing goal of localizing every object in an image remains elusive. Manually annotating objects is quite expensive despite crowd en- gineering innovations. Current automatic object detectors can accurately detect at most a few objects per image. This paper brings together the latest dvancements in object detection and in crowd engineering into a principled framework for accurately and efficiently localizing objects in images. The input to the system is an image to annotate and a set of annotation onstraints: (1) desired utility of labeling, which is a generalization of the number of labeled objects, (2) desired precision of the labeling and/or (3) the budget, which is the human cost of the labeling. Our system automati- ally solicits feedback from human workers (“users”) to annotate the image subject to these constraints, as illustrated in Figure 1. The output is a set of object annotations, informed by humans and computer vision. One important decision is which questions to pose to the human label- ers. In computer vision with human-in-the-loop approaches, human inter- vention has ranged from binary question-and-answer [1] to attribute-based feedback [4] to free-form object annotation [6]. Binary questions are not" 16647dc1bc87ba1e7b8bcd7e1ea8ccebcfe20fa5,Psychometric properties of reaction time based experimental paradigms measuring anxiety-related information-processing biases in children,"PDF hosted at the Radboud Repository of the Radboud University Nijmegen The following full text is a publisher's version. For additional information about this publication click this link. http://repository.ubn.ru.nl/handle/2066/126858 Please be advised that this information was generated on 2018-10-16 and may be subject to hange." 1670729d1edc9bc6103ee823f1137d302be41397,Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures,"Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures Andre Hegerath, Thomas Deselaers, and Hermann Ney Human Language Technology and Pattern Recognition Group, RWTH Aachen University – D-52056 Aachen, Germany {hegerath, deselaers," 16597862a1df1a983c439e82e0462424f538bb48,Personalized Saliency and its Prediction, 16d9b983796ffcd151bdb8e75fc7eb2e31230809,GazeDirector : Fully Articulated Eye Gaze Redirection in Video,"EUROGRAPHICS 2018 / D. Gutierrez and A. Sheffer (Guest Editors) Volume 37 (2018), Number 2 GazeDirector: Fully Articulated Eye Gaze Redirection in Video ID: paper1004" 16bfd904f5a76bb52d5cd8a25721277047a02e89,Blindfold Baselines for Embodied QA,"Blindfold Baselines for Embodied QA Ankesh Anand1 Eugene Belilovsky1 Kyle Kastner1 Hugo Larochelle2,1 Aaron Courville1,3 Mila Google Brain 3CIFAR Fellow" 16e8d439fbcf8311efea7b0baeb1a5340272b396,Stereo and LIDAR Fusion based Detection of Humans and Other Obstacles in Farming Scenarios, 16c884be18016cc07aec0ef7e914622a1a9fb59d,Exploiting Multimodal Data for Image Understanding. (Données multimodales pour l'analyse d'image),"UNIVERSITÉ DE GRENOBLE No attribué par la bibliothèque THÈSE pour obtenir le grade de DOCTEUR DE L’UNIVERSITÉ DE GRENOBLE Spécialité : Mathématiques et Informatique préparée au Laboratoire Jean Kuntzmann dans le cadre de l’École Doctorale Mathématiques, Sciences et Technologies de l’Information, Informatique présentée et soutenue publiquement Matthieu Guillaumin le 27 septembre 2010 Exploiting Multimodal Data for Image Understanding Données multimodales pour l’analyse d’image Directeurs de thèse : Cordelia Schmid et Jakob Verbeek M. Éric Gaussier M. Antonio Torralba Mme Tinne Tuytelaars Katholieke Universiteit Leuven M. Mark Everingham University of Leeds Mme Cordelia Schmid" 163738c0f74ec82ab670a868a051edb732543b6e,Image alignment with rotation manifolds built on sparse geometric expansions,"Image alignment with rotation manifolds built on sparse geometric expansions Effrosyni Kokiopoulou and Pascal Frossard Ecole Polytechnique F´ed´erale de Lausanne (EPFL) Signal Processing Institute - ITS CH- 1015 Lausanne, Switzerland" 1642358cd9410abe9ee512d34ba68296b308770e,Robustness Analysis of Pedestrian Detectors for Surveillance,"Robustness Analysis of Pedestrian Detectors for Surveillance Yuming Fang, Senior Memmber, IEEE, Guanqun Ding, Yuan Yuan, Weisi Lin, Fellow, IEEE, nd Haiwen Liu, Senior Memmber, IEEE" 1685ac0f9fedd83a178a2f64f25155fb37998d8f,Human tracking using wearable sensors in the pocket,"Human Tracking using Wearable Sensors in the Pocket Wenchao Jiang Department of Computer Science Zhaozheng Yin Department of Computer Science Missouri University of Science and Technology Missouri University of Science and Technology" 1602475fdbcb700f10d17c3c3e80ea92c9ba2c44,Learning the Nonlinear Geometry of High-Dimensional Data: Models and Algorithms,"Learning the nonlinear geometry of high-dimensional data: Models and algorithms Tong Wu, Student Member, IEEE, and Waheed U. Bajwa, Senior Member, IEEE" 167895bdf0f1ef88acc962e7a6f255ab92769485,Object Detection and Classification by Decision-Level Fusion for Intelligent Vehicle Systems,"Article Object Detection and Classification by Decision-Level Fusion for Intelligent Vehicle Systems Sang-Il Oh and Hang-Bong Kang * Department of Media Engineering, Catholic University of Korea, 43-1, Yeoggok 2-dong, Wonmmi-gu, Bucheon-si, Gyeonggi-do 14662, Korea; * Correspondence: Tel.: +82-2-2164-4598 Academic Editor: Simon X. Yang Received: 13 October 2016; Accepted: 16 January 2017; Published: 22 January 2017" 1630e839bc23811e340bdadad3c55b6723db361d,Exploiting relationship between attributes for improved face verification,"SONG, TAN, CHEN: EXPLOITING RELATIONSHIP BETWEEN ATTRIBUTES Exploiting Relationship between Attributes for Improved Face Verification Fengyi Song Xiaoyang Tan Songcan Chen Department of Computer Science and Technology, Nanjing University of Aero- nautics and Astronautics, Nanjing 210016, P.R. China" 161eb9ecc119952c137959e87a796da0f3c62cd1,Eye tracking in early autism research,"Falck-Ytter et al. Journal of Neurodevelopmental Disorders 2013, 5:28 http://www.jneurodevdisorders.com/content/5/1/28 R EV I E W Eye tracking in early autism research Terje Falck-Ytter1,2*, Sven Bölte1,3 and Gustaf Gredebäck2 Open Access" 1611ec5db77d20637f2881121a0457234aacde33,Learning Morphological Operators for Depth Completion,"Learning Morphological Operators for Depth Completion Martin Dimitrievski1, Peter Veelaert1, Wilfried Philips1 IMEC-IPI-Ghent University, Ghent, Belgium" 160259f98a6ec4ec3e3557de5e6ac5fa7f2e7f2b,Discriminant multi-label manifold embedding for facial Action Unit detection,"Discriminant Multi-Label Manifold Embedding for Facial Action Unit Detection Signal Procesing Laboratory (LTS5), ´Ecole Polytechnique F´ed´erale de Lausanne, Switzerland Anıl Y¨uce, Hua Gao and Jean-Philippe Thiran" 16286fb0f14f6a7a1acc10fcd28b3ac43f12f3eb,"All Smiles are Not Created Equal: Morphology and Timing of Smiles Perceived as Amused, Polite, and Embarrassed/Nervous.","J Nonverbal Behav DOI 10.1007/s10919-008-0059-5 O R I G I N A L P A P E R All Smiles are Not Created Equal: Morphology nd Timing of Smiles Perceived as Amused, Polite, nd Embarrassed/Nervous Zara Ambadar Æ Jeffrey F. Cohn Æ Lawrence Ian Reed Ó Springer Science+Business Media, LLC 2008" 16f48e8b7f1f6c03c888e3f4664ce3fa1261296b,Steganographic Generative Adversarial Networks,"Steganographic Generative Adversarial Networks Denis Volkhonskiy1,2,3, Ivan Nazarov1,2, Boris Borisenko3 and Evgeny Burnaev1,2,3 Skolkovo Institute of Science and Technology The Institute for Information Transmission Problems RAS (Kharkevich Institute) National Research University Higher School of Economics (HSE)" 16022f7f0cf6492fdc3cf768c9f474791ae3d0ca,Detecting Traffic Lights by Single Shot Detection,"Detecting Traffic Lights by Single Shot Detection Julian M¨uller1 and Klaus Dietmayer1" 16aec3ee9a97162b85b1d51c3c5ce73a472e74b8,Application of Selective Search to Pose estimation,"Application of Selective Search to Pose estimation Ujwal Krothapalli Department of Electrical and Computer Engineering Virginia Tech Blacksburg, Virginia 24061" 16d6d9a71e82b3a53f7a577063f5a4e7cfc298b1,Combining ICA Representations for Recognizing Faces,"ICIT 2015 The 7th International Conference on Information Technology doi:10.15849/icit.2015.0018 © ICIT 2015 (http://icit.zuj.edu.jo/ICIT15) Combining ICA Representations for Recognizing Faces Ashraf Y. A. Maghari Faculty of Information Technology Islamic University of Gaza Gaza, Palestine" 165abb6fdbadae997135feec447fc825edb31c6c,IMENSIONALITY REDUCTION WITH SIMULTANEOUS SPARSE APPROXIMATIONS,"SCHOOL OF ENGINEERING - STI SIGNAL PROCESSING INSTITUTE EffrosyniKokiopoulouandPascalFrossard CH-1015 LAUSANNE Telephone: +41216932601 Telefax: +41216937600 e-mail: ÉCOLE POLYTECHNIQUE(cid:13) FÉDÉRALE DE LAUSANNE DIMENSIONALITY REDUCTION WITH SIMULTANEOUS SPARSE APPROXIMATIONS Effrosyni Kokiopoulou and Pascal Frossard Swiss Federal Institute of Technology Lausanne (EPFL) Signal Processing Institute Technical Report TR-ITS-2006.010 October 21st, 2006 Part of this work has been submitted to IEEE TMM. This work has been supported by the Swiss NSF, under grants PP-002-68737, and NCCR IM2." 167c058b008c358ce5a3cd298c5859ffea441e51,The role of context in image annotation and recommendation,"McParlane, Philip James (2016) The role of context in image annotation nd recommendation. PhD thesis. http://theses.gla.ac.uk/7676/ Copyright and moral rights for this thesis are retained by the author A copy can be downloaded for personal non-commercial research or study, without prior permission or charge This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the Author The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the Author When referring to this work, full bibliographic details including the uthor, title, awarding institution and date of the thesis must be given Glasgow Theses Service http://theses.gla.ac.uk/" 16e2e9e4741795c004d15e95532b07943d3a3242,CPS: 3D Compositional Part Segmentation through Grasping,"CPS: 3D Compositional Part Segmentation through Grasping Safoura Rezapour Lakani University of Innsbruck Innsbruck, Austria Mirela Popa University of Innsbruck Innsbruck, Austria Antonio J. Rodr´ıguez-S´anchez University of Innsbruck Innsbruck, Austria Justus Piater University of Innsbruck Innsbruck, Austria" 1696f6861c208b6a7cac95fbeba524867ad3e8d6,Using deep learning to quantify the beauty of outdoor places,"Downloaded from http://rsos.royalsocietypublishing.org/ on September 4, 2017 rsos.royalsocietypublishing.org Research Cite this article: Seresinhe CI, Preis T, Moat HS. 2017 Using deep learning to quantify the eauty of outdoor places. R. Soc. open sci. : 170170. http://dx.doi.org/10.1098/rsos.170170 Received: 23 February 2017 Accepted: 19 June 2017 Subject Category: Computer science Subject Areas: environmental science/computer modelling nd simulation Keywords: environmental aesthetics, well-being, onvolutional neural networks, deep learning," 1697a4188b9f75ff5324eb9957b8317f459bbf59,Dual-tree fast exact max-kernel search,"Dual-Tree Fast Exact Max-Kernel Search Ryan R. Curtin and Parikshit Ram December 11, 2013" 16c855aea9789e2b7a77f35dc4181efc93dec69c,Exploiting Sum of Submodular Structure for Inference in Very High Order MRF-MAP Problems,"SUBMITTED TO IEEE TPAMI Exploiting Sum of Submodular Structure for Inference in Very High Order MRF-MAP Problems Ishant Shanu Surbhi Goel Chetan Arora Parag Singla" 16e577820999e584c787ec611f55746cf9147518,Cross-Domain Person Reidentification Using Domain Adaptation Ranking SVMs,"Cross-Domain Person Re-Identification Using Domain Adaptation Ranking SVMs Andy J Ma, Jiawei Li, Pong C Yuen, Senior Member, IEEE, and Ping Li label" 16e8b0a1e8451d5f697b94c0c2b32a00abee1d52,UMB-DB: A database of partially occluded 3D faces,"UMB-DB A Database of Partially Occluded 3D Faces Alessandro Colombo Claudio Cusano Raimondo Schettini Universit`a degli Studi di Milano-Bicocca 3 November 2011" 161eb88031f382e6a1d630cd9a1b9c4bc6b47652,Automatic facial expression recognition using features of salient facial patches,"Automatic Facial Expression Recognition Using Features of Salient Facial Patches S L Happy and Aurobinda Routray" f74dbf3481fc3228ea821da232128b98ad5f7a60,Using low-level motion for high-level vision,"Using Low-Level Motion for High-Level Vision Ben Daubney A dissertation submitted to the University of Bristol in accordance with the requirements for the degree of Doctor of Philosophy in the Faculty of Engineering, Department of Computer Science. July 2009" f79267b0f4c0110051c93f9faabe436215e4fc28,Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector,"Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector Chen Du1,2, Chunheng Wang1, Cunzhao Shi1, Baihua Xiao1 Institute of Automation, Chinese Academy of Sciences(CASIA) University of Chinese Academy of Sciences(UCAS) {duchen2016, chunheng.wang, cunzhao.shi," f7dcadc5288653ec6764600c7c1e2b49c305dfaa,Interactive Image Search with Attributes by,"Copyright Adriana Ivanova Kovashka" f724cbf5035e2df0dbe9a4992a0100465f5c6db5,Scalable Multicore k-NN Search via Subspace Clustering for Filtering,"Parallel Graph Partitioning for Complex Networks Henning Meyerhenke, Peter Sanders, and Christian Schulz" f77563386ac293620ce2b90b5d7250ab5d8f9f50,Regression-based Hypergraph Learning for Image Clustering and Classification,"IEEE TRANSACTIONS ON Regression-based Hypergraph Learning for Image Clustering and Classification Sheng Huang Student Member, IEEE, Dan Yang, Bo Liu, Xiaohong Zhang" f7580def2dd84a6a083188aadd9c66c99925860b,Effective Use of Synthetic Data for Urban Scene Semantic Segmentation,"Effective Use of Synthetic Data for Urban Scene Semantic Segmentation(cid:63) Fatemeh Sadat Saleh1,2[0000−0002−3695−9876], Mohammad Sadegh Aliakbarian1,2,3[0000−0003−3948−6418], Mathieu Salzmann4[0000−0002−8347−8637], Lars Petersson2[0000−0002−0103−1904], and Jose M. Alvarez5[0000−0002−7535−6322] ANU, 2 Data61-CSIRO, 3 ACRV, 4 CVLab, EPFL, 5 NVIDIA" f7ecc9df67e9d33543c68fb150270e9f7af8814a,Joint Epipolar Tracking (JET): Simultaneous Optimization of Epipolar Geometry and Feature Correspondences,"Simultaneous optimization of epipolar geometry and feature correspondences Joint Epipolar Tracking (JET): Henry Bradler1, Matthias Ochs1, Nolang Fanani1 Visual Sensorics & Information Processing Lab Goethe University, Frankfurt, Germany Rudolf Mester1,2 Computer Vision Laboratory, ISY Link¨oping University, Sweden" f7186eb3d717694d4ab1730a8d0f662e90c44d6f,A Computational Study on Word Meanings and Their Distributed Representations via Polymodal Embedding,"Proceedings of the The 8th International Joint Conference on Natural Language Processing, pages 214–223, Taipei, Taiwan, November 27 – December 1, 2017 c(cid:13)2017 AFNLP" f795b4ff67d3ecce0b988ecfc0589cc7e54f5dfa,Grounded Human-Object Interaction Hotspots from Video,"Grounded Human-Object Interaction Hotspots from Video Tushar Nagarajan∗ UT Austin Christoph Feichtenhofer Facebook AI Research Kristen Grauman Facebook AI Research" f77c9bf5beec7c975584e8087aae8d679664a1eb,Local Deep Neural Networks for Age and Gender Classification,"Local Deep Neural Networks for Age and Gender Classification Zukang Liao, Stavros Petridis, Maja Pantic March 27, 2017" f774f80fa4b5a8760084921f093730da519c6681,Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms,"Development of an Efficient Face Recognition System based on Linear and Nonlinear Algorithms {tag} {/tag} International Journal of Computer Applications Foundation of Computer Science (FCS), NY, USA Volume 134 Number 7 Year of Publication: 2016 Authors: Filani Araoluwa S., Adetunmbi Adebayo O. 10.5120/ijca2016907932 {bibtex}2016907932.bib{/bibtex}" f7de943aa75406fe5568fdbb08133ce0f9a765d4,Year 5 Deliverable Technical Report : Research Challenges in Biometrics and Indexed biography of relevant biometric research literature,"Project 1.5: Human Identification at a Distance - Hornak, Adjeroh, Cukic, Gautum, & Ross Project 1.5 Biometric Identification and Surveillance1 Don Adjeroh, Bojan Cukic, Arun Ross – West Virginia University Year 5 Deliverable Technical Report: Research Challenges in Biometrics Indexed biography of relevant biometric research literature Donald Adjeroh, Bojan Cukic, Arun Ross April, 2014 ""This research was supported by the United States Department of Homeland Security through the National Center for Border Security nd Immigration (BORDERS) under grant number 2008-ST-061-BS0002. However, any opinions, findings, and conclusions or recommendations in this document are those of the authors and do not necessarily reflect views of the United States Department of Homeland Security.""" f7514435495cd76552a4de01652a08ff8c2863c7,Recognition of Emotions From Facial Expression and Situational Cues in Children with Autism,"Dissertations Loyola University Chicago Loyola eCommons Theses and Dissertations Recognition of Emotions From Facial Expression nd Situational Cues in Children with Autism Dina Tell Loyola University Chicago Recommended Citation Tell, Dina, ""Recognition of Emotions From Facial Expression and Situational Cues in Children with Autism"" (2009). Dissertations. Paper 234. http://ecommons.luc.edu/luc_diss/234 This Dissertation is brought to you for free and open access by the Theses and Dissertations at Loyola eCommons. It has been accepted for inclusion in Dissertations by an authorized administrator of Loyola eCommons. For more information, please contact This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License. Copyright © 2009 Dina Tell" f7a37cf724aef23d0e714a35d54352243e5b52ee,Entire Reflective Object Surface Structure Understanding,"Q.LU ET AL.: ENTIRE REFLECTIVE OBJECT SURFACE STRUCTURE UNDERSTANDING 1 Entire Reflective Object Surface Structure Understanding Qinglin Lu1 Olivier Laligant1 Eric Fauvet1 Anastasia Zakharova2 University of Burgundy Le2i UMR 6306 CNRS 2,Rue de la Fonderie,71200,France INSA Rouen LMI EA3226 Avenue de l’Université,76800,France" f7db1a670a99fd68dc3c6478eb9aeadc2838a897,Feature Based Pose Invariant Face Recognition,"FEATURE BASED POSE INVARIANT FACE RECOGNITION Berk G¨okberk BS. in Computer Engineering, Bo˘gazi¸ci University, 1999 Submitted to the Institute for Graduate Studies in Science and Engineering in partial fulfillment of the requirements for the degree of Master of Science Computer Engineering Bo˘gazi¸ci University" f736b7cf8388f20bfe9619d63d9c4ce070091863,Automated Crowd Detection in Stadium Arenas,"AUTOMATED CROWD DETECTION IN STADIUM ARENAS Loris Nanni, 1 Sheryl Brahnam, 2 Stefano Ghidoni, 1 Emanuele Menegatti1 DIE, University of Padua, Via Gradenigo, 6 - 35131- Padova – Italy e-mail: {loris.nanni, ghidoni, CIS, Missouri State University, 901 S. National, Springfield, MO 65804, USA e-mail:" f727b12c905ac585de60811048c9f9dd4188b498,R 4-A . 2 : Rapid Forensic Search & Retrieval in Video,"R4-A.2: Rapid Forensic Search & Retrieval in Video Archives" f740bac1484f2f2c70777db6d2a11cf4280081d6,Soft Locality Preserving Map (SLPM) for Facial Expression Recognition,"Soft Locality Preserving Map (SLPM) for Facial Expression Recognition Cigdem Turana,*, Kin-Man Lama, Xiangjian Heb Centre for Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong Computer Science, School of Electrical and Data Engineering, University of Technology, Sydney, Australia E-mail addresses: (C. Turan), (K.-M. Lam), (X. He)" f7ba77d23a0eea5a3034a1833b2d2552cb42fb7a,LOTS about attacking deep features,"This is a pre-print of the original paper accepted at the International Joint Conference on Biometrics (IJCB) 2017. LOTS about Attacking Deep Features Andras Rozsa, Manuel G¨unther, and Terrance E. Boult Vision and Security Technology (VAST) Lab University of Colorado, Colorado Springs, USA" f77b3e6b6eb4bc6d6bfeed290a1bc533bb97968a,Real Time Violence Detection in Video with ViF and Horn-Schunck,"Real Time Violence Detection in Video with ViF and Horn-Schunck Vicente Machaca Arceda Universidad Nacional de San Agustín Arequipa, Perú Karla Fernández Fabián Universidad Nacional de San Agustín Arequipa, Perú Juan Carlos Gutíerrez Universidad Nacional de San Agustín Arequipa, Perú" f79c4bf83371627ba139b61eb427463b93cd687b,Learning from Few Examples for Visual Recognition Problems,"Learning from Few Examples for Visual Recognition Problems Erik Rodner Dissertation zur Erlangung des akademischen Grades doctor rerum naturalium (Dr. rer. nat.) vorgelegt dem Rat der Fakultät für Mathematik und Informatik der Friedrich-Schiller-Universität Jena" f7094d4888e9ef039d283267d310b0673ff0e423,FACE RECOGNITION: A NEW FEATURE SELECTION AND CLASSIFICATION TECHNIQUE,"Complex 2004 Proceedings of the 7th Asia-Pacific Conference on Complex Systems Cairns Converntion Centre, Cairns, Australia 6-10th December 2004 Face recognition: a new feature selection and lassification technique Xiaolong Fan and Brijesh Verma Faculty of Informatics and Communication Central Queensland University Bruce Hwy North Rockhampton QLD 4701 Australia" 64b78b6f13c321da77e3770a748772fa837aa8c8,Parallel Architecture for Face Recognition using MPI,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 8, No. 1, 2017 Parallel Architecture for Face Recognition using MPI Dalia Shouman Ibrahim Computer Systems Department Computer and Information Sciences Ain Shams University Egypt Salma Hamdy Computer Science Department Computer and Information Sciences Ain shams University Egypt" 64f6f1cd23bbac1983ad4115475e4ef26ab86ba4,Person re-identification by unsupervised video matching,"Person Re-Identification by Unsupervised Video Matching Xiaolong Ma1,4, Xiatian Zhu2, Shaogang Gong2, Xudong Xie1, Jianming Hu1, Kin-Man Lam3, Yisheng Zhong1" 643abe6001946ebb7e262465edcf78d600c38f4f,The COST292 experimental framework for TRECVID 2007,"The COST292 experimental framework for TRECVID 2007 Q. Zhang1, K. Chandramouli1, U. Damnjanovic1, T. Piatrik1, E. Izquierdo1, M. Corvaglia2, N. Adami2, R. Leonardi2, G. Yakın3, S. Aksoy3, U. Naci4, A. Hanjalic4, S. Vrochidis5, A. Moumtzidou5, S. Nikolopoulos5, V. Mezaris5, L. Makris5, I. Kompatsiaris5, E. Esen6, A. Alatan6, E. Spyrou7, P. Kapsalas7, G. Tolias7, P. Mylonas7, Y. Avrithis7, B. Reljin8, G. Zajic8, R. Jarina9, M. Kuba9, N. Aginamo10, J. Goya10, B. Mansencal11, J. Benois-Pineau11, A. M. G. Pinheiro12, L. A. Alexandre12, P. Almeida12 October 22, 2007" 64d9c5ab4cab193046ac839b74d182a472fe45ba,"NosePose : a competitive , landmark-free methodology for head pose estimation in the wild","NosePose: a competitive, landmark-free methodology for head pose estimation in the wild Fl´avio H. B. Zavan, Antonio C. P. Nascimento, Olga R. P. Bellon and Luciano Silva IMAGO Research Group - Universidade Federal do Paran´a" 64195b78fd4f5b9aeb5cceeb060bc9821e63136c,Object Recognition,"Object Recognition Ming-Hsuan Yang University of California at Merced http://faculty.ucmerced.edu/mhyang SYNONYMS Object Identification, Object Labeling. DEFINITION Object recognition is concerned with determining the identity of an object being observed in the image from a set of known labels. Oftentimes, it is assumed that the object being observed has been detected or there is a single object in the image. HISTORICAL BACKGROUND As the holy grail of computer vision research is to tell a story from a single image or a sequence of images, object recognition has been studied for more than four decades [9] [22]. Significant efforts have been paid to develop representation schemes and algorithms aiming at recognizing generic objects in images taken under different imaging conditions (e.g., viewpoint, illumination, and occlusion). Within a limited scope of distinct objects, such s handwritten digits, fingerprints, faces, and road signs, substantial success has been achieved. Object recognition is also related to content-based image retrieval and multimedia indexing as a number of generic objects can be recognized. In addition, significant progress towards object categorization from images has been made in the recent years [17]. Note that object recognition has also been studied extensively in psychology, computational" 6434b95401aea9ece22b2b29950118afc163c2db,Localized anomaly detection via hierarchical integrated activity discovery,"THIS PAPER APPEARED IN IEEE INT. CONF. ON ADVANCED VIDEO AND SIGNAL-BASED PROCESSING (AVSS), KRAKOW, 2013 Localized Anomaly Detection via Hierarchical Integrated Activity Discovery Thiyagarajan Chockalingam1 R´emi Emonet2 http://home.heeere.com Jean-Marc Odobez2,3 : Colorado State University – Fort Collins, CO 80523, United States : Idiap Research Institute – CH-1920, Martigny, Switzerland : ´Ecole Polytechnique F´ed´eral de Lausanne – CH-1015, Lausanne, Switzerland" 6446089a2a383ad9e4315aea0199084dc61490f9,Computational analysis of human-robot interactions through first-person vision: Personality and interaction experience,"Proceedings of the 24th IEEE International Symposium on Robot and Human Interactive Communication Kobe, Japan, Aug 31 - Sept 4, 2015 978-1-4673-6704-2/15/$31.00 ©2015 IEEE" 6402703b62325865d00da1f58dbbcaf9a2bc417d,Twin Networks: Matching the Future for Sequence Generation,"Published as a conference paper at ICLR 2018 TWIN NETWORKS: MATCHING THE FUTURE FOR SEQUENCE GENERATION Dmitriy Serdyuk,* ♦ Nan Rosemary Ke,* ♦ ‡ Alessandro Sordoni♥ Adam Trischler,♥ Chris Pal♣♦ & Yoshua Bengio¶ ♦ ♦ Montreal Institute for Learning Algorithms (MILA), Canada ♥ Microsoft Research, Canada ♣ Ecole Polytechnique, Canada ¶ CIFAR Senior Fellow Work done at Microsoft Research * Authors contributed equally" 64e205799096448a50ddee218bcd3b81ff342cba,PCA-Initialized Deep Neural Networks Applied to Document Image Analysis,"PCA-Initialized Deep Neural Networks Applied To Document Image Analysis Mathias Seuret∗, Michele Alberti∗, Rolf Ingold∗, and Marcus Liwicki∗‡, University of Fribourg, Department of Informatics Bd. de P´erolles 90, 1700 Fribourg, Switzerland Email: University of Kaiserslautern, Germany" 645de797f936cb19c1b8dba3b862543645510544,Deep Temporal Linear Encoding Networks,"Deep Temporal Linear Encoding Networks Ali Diba1,(cid:63), Vivek Sharma1,(cid:63), and Luc Van Gool1,2 ESAT-PSI, KU Leuven, 2CVL, ETH Z¨urich" 64b88125bf93a26f9e15bf57208f1cfe6e31fa1c,Retrieval-Induced Forgetting and Its Effects on Episodic Memory,"INSTITUTIONEN FÖR PSYKOLOGI Retrieval-Induced Forgetting and Its Effects on Episodic Memory Anatole Nöstl Master Thesis VT 2010 Supervisor: Mikael Johansson" 647c6ac5e0bfee0241d583650f18c6314f28aaee,Segmentation Driven Object Detection with Fisher Vectors,"Segmentation Driven Object Detection with Fisher Vectors Ramazan Gokberk Cinbis Jakob Verbeek Cordelia Schmid LEAR, INRIA Grenoble - Rhˆone-Alpes, France Laboratoire Jean Kuntzmann" 6475c1e95da0a3bd36786a32d00a893d85460e9e,Combined image- and world-space tracking in traffic scenes,"Combined Image- and World-Space Tracking in Traffic Scenes Aljoˇsa Oˇsep, Wolfgang Mehner, Markus Mathias, and Bastian Leibe" 64d1fcc26c2af47c8ed7436fe91546ba5bfc7a1f,Disentangling Multiple Conditional Inputs in GANs,"Disentangling Multiple Conditional Inputs in GANs Gökhan Yildirim Urs Bergmann Zalando Research Zalando Research Berlin, Germany Berlin, Germany Calvin Seward∗ Zalando Research Berlin, Germany process. Researchers have achieved control of image generation by using GANs that are conditioned on a categorical input [12, 13]. In this paper, we employ conditional GANs to control the visual ttributes, such as color, texture, and shape, of a generated apparel. One of the main challenges of the conditional image generation GANs is to isolate the effects of input attributes on the final image. For example, we want the color of an article to stay constant, when we tune its texture and/or shape. One possibility would be to employ Adversarial Autoencoders [11] or DNA-GAN [17] to disentangle the inputs. However, this requires an exhaustive dataset, in other" 6472df86bed51909f7b8aa0631f910db5a627c84,Minimax and Adaptive Estimation of Covariance Operator for Random Variables Observed on a Lattice Graph,"Minimax and Adaptive Estimation of Covariance Operator for Random Variables Observed on a Lattice Graph T. Tony Cai∗ and Ming Yuan† University of Pennsylvania and Georgia Institute of Technology November 3, 2012" 641fd2edcf93fa29181952356e93a83a26012aa2,Following are some examples from CIFAR dataset : Goal : To alter the training criteria to obtain ‘ objectness ’ in the synthesis of images,"Published as a conference paper at ICLR 2017 IMPROVING GENERATIVE ADVERSARIAL NETWORKS WITH DENOISING FEATURE MATCHING David Warde-Farley & Yoshua Bengio(cid:63) Montreal Institute for Learning Algorithms, (cid:63) CIFAR Senior Fellow Universit´e de Montr´eal Montreal, Quebec, Canada" 64be271fd50fce1cf8434020145a1b6e16f75c1a,Intrinsic Divergence for Face Recognition,"Centre for Theoretical Neuroscience Technical Report UW-CTN-TR-20090204-001 February 4, 2009 Intrinsic Divergence for Face Recognition Yichuan Tang and Xuan Choo Centre for Theoretical Neuroscience, Waterloo, ON. http://compneuro.uwaterloo.ca/cnrglab" 646fa86edc22ccc452a44ac7a5953ba62fc0929b,Recognizing jumbled images: The role of local and global information in image classification,"The Role of Local and Global Information in Image Classification Recognizing Jumbled Images: Toyota Technological Institute, Chicago (TTIC) Devi Parikh" 641f0989b87bf7db67a64900dcc9568767b7b50f,Reconstructing faces from their signatures using RBF regression,"Reconstructing Faces from their Signatures using RBF Regression Alexis Mignon, Fr´ed´eric Jurie To cite this version: Alexis Mignon, Fr´ed´eric Jurie. Reconstructing Faces from their Signatures using RBF Regres- sion. British Machine Vision Conference 2013, Sep 2013, Bristol, United Kingdom. pp.103.1– 03.12, 2013, <10.5244/C.27.103>. HAL Id: hal-00943426 https://hal.archives-ouvertes.fr/hal-00943426 Submitted on 13 Feb 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 6483ebbb9c28024431c8ada03354217453ca1b3b,Statement in Lieu of an Oath,"Universit¨at des Saarlandes Max-Planck-Institut f¨ur Informatik Learning to Track Humans in Videos Master’s Thesis in Computer Science Mihai Fieraru supervised by Prof. Dr. Bernt Schiele dvised by MSc Anna Khoreva MSc Eldar Insafutdinov reviewers Prof. Dr. Bernt Schiele Dr. Mario Fritz Saarbr¨ucken, December 2017" 64153df77fe137b7c6f820a58f0bdb4b3b1a879b,Shape Invariant Recognition of Segmented Human Faces using Eigenfaces,"Shape Invariant Recognition of Segmented Human Faces using Eigenfaces Zahid Riaz, Michael Beetz, Bernd Radig Department of Informatics Technical University of Munich, Germany" 64fb6c31033e38eaaa10c0f7c2b7995f8fa84de3,VISUALIZING VIDEO SOUNDS THROUGH SOUND WORD ANIMATION,"VISUALIZING VIDEO SOUNDS THROUGH SOUND WORD ANIMATION 擬音語アニメーションによる動画音響の可視化手法 Fangzhou Wang A Master Thesis Submitted to the Graduate School of the University of Tokyo on February 20, 2014 in Partial Ful(cid:12)llment of the Requirements for the Degree of Master of Information Science and Technology in Computer Science Thesis Supervisor: Takeo Igarashi 五十嵐健夫 Professor of Computer Science" 64c78c8bf779a27e819fd9d5dba91247ab5a902b,Tracking with multi-level features.,"Tracking with multi-level features Roberto Henschel, Laura Leal-Taix´e, Bodo Rosenhahn, Konrad Schindler" 648d326990ed78d2160139c1ab307a7b3e44b1bb,Random Sampling for Fast Face Sketch Synthesis,"Random Sampling for Fast Face Sketch Synthesis Nannan Wang, and Xinbo Gao, and Jie Li" 64407fe6fc65d3370427770544be0c7f2447e0f6,Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks,"Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks Long Chen1 Hanwang Zhang2 Jun Xiao1∗ Wei Liu3 Shih-Fu Chang4 Zhejiang University 2Nanyang Technological University 3Tencent AI Lab 4Columbia University {longc, {wliu, Figure 1: (a) Attribute variance heat maps of the 312 attributes in CUB birds [60] and the 102 attributes in SUN scenes [47] (lighter color indicates lower variance, i.e., lower discriminability) and the t-SNE [35] visualizations of the test images represented by all attributes (left) and only the high-variance ones (right). Some of the low-variance attributes (the lighter part to the left of the cut-off line) discarded at training are still needed in discriminating unseen test classes. (b) Comparison of reconstructed images using SAE [25] and our proposed SP-AEN method, which is shown to retain sufficient semantics for photo-realistic reconstruction." 64a6c30ca95e85427c56acb4c1c20f62c6ec0709,PersonNet: Person Re-identification with Deep Convolutional Neural Networks,"PersonNet: Person Re-identification with Deep Convolutional Neural Networks Lin Wu, Chunhua Shen, Anton van den Hengel" 64e0bd1210f180e0610b2a1faa188051a1de29bf,Combining Detectors for Robust Head Detection,"Combining Detectors for Robust Head Detection Henrik Brauer, Christos Grecos and Kai von Luck Living Place - HAW Hamburg Berliner Tor 11 0099 Hamburg, Germany" 649eb674fc963ce25e4e8ce53ac7ee20500fb0e3,Toward correlating and solving abstract tasks using convolutional neural networks, 64bd5878170bfab423bc3fc38d693202ef4ba6b6,Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision,"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision Dushyant Mehta1, Helge Rhodin2, Dan Casas3, Pascal Fua2, Oleksandr Sotnychenko1, Weipeng Xu1, and Christian Theobalt1 MPI for Informatics, Germany EPFL, Switzerland Universidad Rey Juan Carlos, Spain" 6497eb53fd7d3ff09190566be8099016fb49f801,Biometric Sensor Interoperability: A Case Study in 3D Face Recognition, 64a336f952ec67f85fe00092847d50dd29e4cddc,Fast Screening Algorithm for Template Matching FAST SCREENING ALGORITHM FOR TEMPLATE MATCHING,Fast Screening Algorithm for Template Matching 64cac22210861d4e9afb00b781da90cf99f9d19c,Facial Landmark Detection for Manga Images,"Noname manuscript No. (will be inserted by the editor) Facial Landmark Detection for Manga Images Marco Stricker · Olivier Augereau · Koichi Kise · Motoi Iwata Received: date / Accepted: date" 64c9cc92ea496b9053fa5326567487b5f08bb13f,3D Human Face Recognition Using Summation Invariants,"(cid:176)2006 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for ad- vertising or promotional purposes or for creating new collec- tive works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE." 0f1392c1180582a45b42e621e1526f03cc6e9ca6,Learning with Hierarchical-Deep Models,"Learning with Hierarchical-Deep Models Ruslan Salakhutdinov, Joshua B. Tenenbaum, and Antonio Torralba" 0fa42d4478b514b0f961e26bccbaf2b75d42e912,Extending UML for Conceptual Modeling of Annotation of Medical Images,"Extending UML for Conceptual Modeling of Annotation International Journal of Computer Applications (0975 – 8887) Volume 72– No.10, June 2013 of Medical Images Mouhamed Gaith Ayadi Riadh Bouslimi Jalel Akaichi Department of computer sciences ISG university of Tunis Tunisia Department of computer sciences ISG university of Tunis Tunisia Department of computer sciences ISG university of Tunis Tunisia" 0f556558853268d86cd05bf8ea42da6d7862a024,Shade Face: Multiple image-based 3D face recognition,"UWA Research Publication Mian, A. (2009). Shade Face: Multiple Image-based 3D Face Recognition. In R. Cipolla, M. Hebert, X. Tang, & N. Yokoya (Eds.), Proceedings of the 2009 IEEE International Workshop on 3-D Digital Imaging and Modeling (3DIM2009). (pp. 1833-1839). USA: IEEE Computer Society. 10.1109/ICCVW.2009.5457505 © 2009 IEEE This is pre-copy-editing, author-produced version of an article accepted for publication, following peer review. The definitive published version is located at http://dx.doi.org/10.1109/ICCVW.2009.5457505 This version was made available in the UWA Research Repository on 4 March 2015, in ompliance with the publisher’s policies on archiving in institutional repositories. Use of the article is subject to copyright law." 0f5bf2a208d262aa0469bd3185f6e2e56acada81,Pose Estimation and Segmentation of People in 3D Movies,"Pose Estimation and Segmentation of People in 3D Movies Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev To cite this version: Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev. Pose Estimation and Segmentation of People in 3D Movies. ICCV - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.2112-2119, 2013, <10.1109/ICCV.2013.263>. HAL Id: hal-00874884 https://hal.inria.fr/hal-00874884 Submitted on 18 Oct 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 0f25aa473e808de72c6975fdb1e3e65180a38c05,Bag of Soft Biometrics for Person Identification New trends and challenges,"Noname manuscript No. (will be inserted by the editor) Bag of Soft Biometrics for Person Identi(cid:12)cation New trends and challenges. Antitza Dantcheva (cid:1) Carmelo Velardo (cid:1) Angela D’Angelo (cid:1) Jean{Luc Dugelay Received: 01.08.2010 / Accepted: 11.10.2010" 0f04a95ec885cf98e7cee43eacff13de0c888d3b,The FERET September 1996 Database and Evaluation Procedure,"ToappearintheproceedingsoftheFirstInternationalConferenceonAudioand Video-basedBiometricPersonAuthentication,Crans-Montana,Switzerland,- March . TheFERETSeptember Databaseand EvaluationProcedure P.JonathonPhillips,?HyeonjoonMoon,yPatrickRauss,and SyedA.Rizviy U.S.ArmyResearchLaboratory,AMSRL-SE-SE, PowderMillRd.,Adelphi,MD-  DepartmentofElectricalandComputerEngineering StateUniversityofNewYorkatBu(cid:11)alo,Amherst,NY DepartmentofAppliedSciences CollegeofStatenIslandofCityUniversityofNewYork,StatenIsland,NY" 0fe5d8acc77f54d60edc56c012f35517d9c861da,Interactive Stereoscopic Video Conversion,"Interactive Stereoscopic Video Conversion Zhebin Zhang, Chen Zhou, Yizhou Wang, and Wen Gao, Fellow, IEEE erial perspective," 0f29710e54f714eeea5233628afc68c680d881bb,Tracking Indistinguishable Translucent Objects over Time Using Weakly Supervised Structured Learning,"Tracking indistinguishable translucent objects over time using weakly supervised structured learning Luca Fiaschi1, Ferran Diego1, Konstantin Gregor1, Martin Schiegg1, Ullrich Koethe1, Marta Zlatic2 and Fred A. Hamprecht1 HCI University of Heidelberg, Germany, http://hci.iwr.uni-heidelberg.de HHMI Janelia Farm, USA, http://janelia.org/" 0f08d62e882026ac83ebf26c0bd288c553873814,Multispecies Fruit Flower Detection Using a Refined Semantic Segmentation Network,"Multispecies fruit flower detection using a refined semantic segmentation network Philipe A. Dias1, Amy Tabb2, and Henry Medeiros1" 0f5e10cfca126682e1bad1a07848919489df6a65,Facial emotion processing in patients with social anxiety disorder and Williams-Beuren syndrome: an fMRI study.,"Research Paper Facial emotion processing in patients with social nxiety disorder and Williams–Beuren syndrome: n fMRI study Cynthia Binelli, PhD; Armando Muñiz, MD; Susana Subira, MD, PhD; Ricard Navines, MD, PhD; Laura Blanco-Hinojo, MSc; Debora Perez-Garcia, BSc; Jose Crippa, MD, PhD; Magi Farré, MD, PhD; Luis Pérez-Jurado, MD, PhD; Jesus Pujol, MD, PhD; Rocio Martin-Santos, MD, PhD Background: Social anxiety disorder (SAD) and Williams–Beuren syndrome (WBS) are 2 conditions with major differences in terms of genetics, development and cognitive profiles. Both conditions are associated with compromised abilities in overlapping areas, including so- ial approach, processing of social emotional cues and gaze behaviour, and to some extent they are associated with opposite behaviours in these domains. We examined common and distinct patterns of brain activation during a facial emotion processing paradigm in patients with SAD and WBS. Methods: We examined patients with SAD and WBS and healthy controls matched by age and laterality using functional MRI during the processing of happy, fearful and angry faces. Results: We included 20 patients with SAD and 20 with WBS as well as 0 matched controls in our study. Patients with SAD and WBS did not differ in the pattern of limbic activation. We observed differences in early visual areas of the face processing network in patients with WBS and differences in the cortical prefrontal regions involved in the top– down regulation of anxiety and in the fusiform gyrus for patients with SAD. Compared with those in the SAD and control groups, participants in the WBS group did not activate the right lateral inferior occipital cortex. In addition, compared with controls, patients with WBS hypoacti- vated the posterior primary visual cortex and showed significantly less deactivation in the right temporal operculum. Participants in the SAD group showed decreased prefrontal activation compared with those in the WBS and control groups. In addition, compared with controls," 0f0fb26d8999fecc362c0bf65a62c809061c5508,Building Location Models for Visual Place Recognition,"Building Location Models for Visual Place Recognition Elena Stumm, Christopher Mei, Simon Lacroix To cite this version: Elena Stumm, Christopher Mei, Simon Lacroix. Building Location Models for Visual Place Recog- nition. International Journal of Robotics Research, SAGE Publications, 2016, 35 (4), pp.334-356. <10.1177/0278364915570140>. HAL Id: hal-01064007 https://hal.archives-ouvertes.fr/hal-01064007v2 Submitted on 26 Jan 2015 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 0fac212f96e4a291482342853b38d5293195d1e1,Mobile robot with vision based navigation and pedestrian detection,"Artículo Científico / Scientific Paper Mobile robot with vision based navigation and pedestrian detection Robot móvil con navegación basada en https://doi.org/10.17163/ings.n17.2017.09 pISSN: 1390-650X / eISSN: 1390-860X visión y detección de peatones Marco A. Luna1, Julio F. Moya1, Wilbert G. Aguilar2,3,4,∗, Vanessa Abad5" 0f0cab9235bbf185acdd4f9713fd111ca50effca,Covariance Pooling for Facial Expression Recognition,"Covariance Pooling for Facial Expression Recognition Computer Vision Lab, ETH Zurich, Switzerland VISICS, KU Leuven, Belgium Dinesh Acharya†, Zhiwu Huang†, Danda Pani Paudel†, Luc Van Gool†‡ {acharyad, zhiwu.huang, paudel," 0f085f389a52e13586fe50f2dae49e105225303f,Distribution-sensitive learning for imbalanced datasets,"Distribution-Sensitive Learning for Imbalanced Datasets Yale Songl, Louis-Philippe Morency2, and Randall Davisl MIT Computer Science and Artificial Intelligence Laboratory USC Institute for Creative Technology" 0fbf59328d32e1a9950dfa08c3ec87eb94398651,Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks,"Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks Nicolas Audeberta,b,, Bertrand Le Sauxa, Sébastien Lefèvreb ONERA, The French Aerospace Lab, F-91761 Palaiseau, France Univ. Bretagne-Sud, UMR 6074, IRISA, F-56000 Vannes, France" 0f366de3ea595932dad06389f6e61fe0dd8cbe74,DeepAnomaly: Combining Background Subtraction and Deep Learning for Detecting Obstacles and Anomalies in an Agricultural Field,"Article DeepAnomaly: Combining Background Subtraction nd Deep Learning for Detecting Obstacles and Anomalies in an Agricultural Field Peter Christiansen 1,*, Lars N. Nielsen 2, Kim A. Steen 3, Rasmus N. Jørgensen 1 and Henrik Karstoft 1 Department of Engineering, Aarhus University, Aarhus 8200, Denmark; (R.N.J.); (H.K.) Danske Commodities, Aarhus 8000, Denmark; AgroIntelli, Aarhus 8200, Denmark; * Correspondence: Tel.: +45-2759-2953 Academic Editors: Gabriel Oliver-Codina, Nuno Gracias and Antonio M. López Received: 15 September 2016; Accepted: 7 November 2016; Published: 11 November 2016" 0fa28b3dfb841cf542edf8d9d5933c7205a88d41,LandmarkBoost: Efficient visualContext Classifiers for Robust Localization,"LandmarkBoost: Efficient Visual Context Classifiers for Robust Localization Marcin Dymczyk∗, Igor Gilitschenski‡, Juan Nieto∗, Simon Lynen∗†, Bernhard Zeisl†, and Roland Siegwart∗ Autonomous Systems Lab, ETH Z¨urich, †Google Inc., Z¨urich, ‡CSAIL, MIT" 0fa077478abea097a1b74915ccaaeb4952eaaec7,Object Classification With Joint Projection and Low-Rank Dictionary Learning,"Object Classification with Joint Projection and Low-rank Dictionary Learning Homa Foroughi, Nilanjan Ray and Hong Zhang" 0fad544edfc2cd2a127436a2126bab7ad31ec333,Decorrelating Semantic Visual Attributes by Resisting the Urge to Share,"Decorrelating Semantic Visual Attributes by Resisting the Urge to Share Dinesh Jayaraman UT Austin Fei Sha Kristen Grauman UT Austin" 0fdcfb4197136ced766d538b9f505729a15f0daf,Multiple pattern classification by sparse subspace decomposition,"Multiple Pattern Classification by Sparse Subspace Decomposition Institute of Media and Information Technology, Chiba University Tomoya Sakai -33 Yayoi, Inage, Chiba, Japan" 0f4b902a2e12378e0ac0cb6fff7dd4c5f81e2c0a,Capturing facial videos with Kinect 2.0: A multithreaded open source tool and database,"Capturing Facial Videos with Kinect 2.0: A Multithreaded Open Source Tool and Database Daniel Merget Tobias Eckl Institute for Human-Machine Communication, TUM, Germany Philipp Tiefenbacher Martin Schwoerer Gerhard Rigoll" 0f82a869a80b6114bd16437dbf703bcae84da7b9,Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks,"Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks Marcel Simon and Erik Rodner Computer Vision Group, University of Jena, Germany∗ http://www.inf-cv.uni-jena.de/constellation_model_revisited" 0f282d9aacd194842f8747c4ed37fa6200f601a2,Crowdsourcing Photos in Edge-Clouds with Panoptic Tadeu,"Crowdsourcing Photos Edge-Clouds with Panoptic Tadeu Augusto Leite Freitas Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos Departamento de Ciência de Computadores Orientador Rolando Martins, Professor Auxiliar Convidado, Faculdade de Ciências da Universidade do Porto Co-Orientador Miguel Coimbra, Professor Auxiliar, Faculdade de Ciências da Universidade do Porto" 0fb680b5136d80c13e8d15078ef18ca4aac269f6,Optimizing Deep Neural Network Architecture: A Tabu Search Based Approach,"Optimizing Deep Neural Network Architecture: A Tabu Search Based Approach Tarun Kumar Gupta and Khalid Raza* Department of Computer Science, Jamia Millia Islamia, New Delhi-110025" 0ffee18b495830d373dbc65f67a452d94938900b,Registration-based moving object detection from a moving camera,"IROS 2008 2nd Workshop on Planning, Perception and Navigation for Intelligent Vehicles Registration-based moving object detection from a moving camera Angel D. Sappa, Fadi Dornaika, David Ger´onimo and Antonio L´opez" 0f5275b472344dbfc4a26a9ba73dff23844b7e84,Head movements and postures as pain behavior,"RESEARCH ARTICLE Head movements and postures as pain ehavior Philipp Werner1*, Ayoub Al-Hamadi1, Kerstin Limbrecht-Ecklundt2, Steffen Walter3, Harald C. Traue3 Neuro-Information Technology group, Institute for Information Technology and Communications, Otto-von- Guericke University Magdeburg, Magdeburg, Germany, 2 Department of Anesthesiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany, 3 Medical Psychology, University Clinic for Psychosomatic Medicine and Psychotherapy, Ulm, Germany 1111111111 1111111111 1111111111 1111111111 1111111111" 0fd2956ef990443f584112fa093f85a90a43c4af,Performance Evaluation of Multi-camera Visual Tracking,"PEOPLE COUNT ESTIMATION IN SMALL CROWDS Pietro Morerio, Lucio Marcenaro, Carlo S. Regazzoni Department of Biophysical and Electronic Engineering University of Genoa, Genoa, Italy" 0f41f1a4bd5141184ee3ed3cf8874eeb396d7862,Deep Forest: Towards An Alternative to Deep Neural Networks,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 0f92e9121e9c0addc35eedbbd25d0a1faf3ab529,MORPH-II : A Proposed Subsetting Scheme,"MORPH-II: A Proposed Subsetting Scheme Participants: K. Kempfert, J. Fabish, K. Park, and R. Towner Mentors: Y. Wang, C. Chen, and T. Kling NSF-REU Site at UNC Wilmington, Summer 2017" 0fd1bffb171699a968c700f206665b2f8837d953,Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning,"Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning Ramazan Gokberk Cinbis, Jakob Verbeek, and Cordelia Schmid, Fellow, IEEE" 0ff23392e1cb62a600d10bb462d7a1f171f579d0,Toward Sparse Coding on Cosine Distance,"Toward Sparse Coding on Cosine Distance Jonghyun Choi, Hyunjong Cho, Jungsuk Kwak#, Larry S. Davis UMIACS | University of Maryland, College Park #Stanford University" 0f65c91d0ed218eaa7137a0f6ad2f2d731cf8dab,Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition,"Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition Changxing Ding, Jonghyun Choi, Dacheng Tao, Senior Member, IEEE, and Larry S. Davis, Fellow, IEEE" 0f2a910f98e9955d2fbd4841d31b4943b91ab382,Creating and Annotating Affect Databases from Face and Body Display: A Contemporary Survey,"Creating and Annotating Affect Databases from Face and Body Display: A Contemporary Survey Hatice Gunes and Massimo Piccardi" 0f0499989f3331396af94f92c29f2eda9b58d4dc,Object detection methods for robot grasping: Experimental assessment and tuning,"Object detection methods for robot grasping: Experimental assessment and tuning Ferran RIGUAL a,1, Arnau RAMISA a, Guillem ALENYA a and Carme TORRAS a Institut de Rob`otica i Inform`atica Industrial, CSIC-UPC, Barcelona" 0f4cfcaca8d61b1f895aa8c508d34ad89456948e,Local appearance based face recognition using discrete cosine transform,"LOCAL APPEARANCE BASED FACE RECOGNITION USING DISCRETE COSINE TRANSFORM (WedPmPO4) Author(s) :" 0f7ca11acc495f1a45fb2add4cee94d445d8d96f,Fully Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Safe and Efficient Navigation in Complex Scenarios,"Fully Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Safe and Efficient Navigation in Complex Scenarios Tingxiang Fan1*, Pinxin Long2*, Wenxi Liu3 and Jia Pan1 Journal Title XX(X):1–30 (cid:13)The Author(s) 2018 Reprints and permission: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/ToBeAssigned www.sagepub.com/" 0f9bd0d528603654de2687d3ae2472a522607ee3,Semantics-aware visual localization under challenging perceptual conditions,"Semantics-aware Visual Localization under Challenging Perceptual Conditions Tayyab Naseer Gabriel L. Oliveira Thomas Brox Wolfram Burgard" 0ff14ec76e5fe7f17dce102e781ffce2738c8d4b,Real-time pedestrian detection in urban scenarios,"Real-time Pedestrian Detection in Urban Scenarios VARGA Robert, VESA Andreea Valeria, JEONG Pangyu, NEDEVSCHI Sergiu {robert.varga, pangyu.jeong, Technical University of Cluj Napoca Telephone: (800) 555–1212" 0f3eb3719b6f6f544b766e0bfeb8f962c9bd59f4,Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking,"Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking Andrii Maksai Pascal Fua Computer Vision Laboratory, ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL) {andrii.maksai," 0fd1715da386d454b3d6571cf6d06477479f54fc,A Survey of Autonomous Human Affect Detection Methods for Social Robots Engaged in Natural HRI,"J Intell Robot Syst (2016) 82:101–133 DOI 10.1007/s10846-015-0259-2 A Survey of Autonomous Human Affect Detection Methods for Social Robots Engaged in Natural HRI Derek McColl · Alexander Hong · Naoaki Hatakeyama · Goldie Nejat · Beno Benhabib Received: 10 December 2014 / Accepted: 11 August 2015 / Published online: 23 August 2015 © Springer Science+Business Media Dordrecht 2015" 0f708ace6f4829e466a8a549bd23f6fcf719ab9d,Multi-shot person re-identification via relational Stein divergence,"This is the author’s version of a work that was submitted/accepted for pub- lication in the following source: Alavi, Azadeh, Yang, Yan, Harandi, Mehrtash, & Sanderson, Conrad (2013) Multi-shot person re-identification via relational stein divergence. In ICIP 2013 Proceedings : 2013 IEEE International Conference on Image Processing, Institute of Electrical and Electronics Engineers, Inc., Mel- ourne Convention and Exhibition Centre, Melbourne, pp. 3542-3546. This file was downloaded from: https://eprints.qut.edu.au/71704/ (cid:13) c(cid:13) 2013 by the Institute of Electrical and Electronics Engineers, Inc. Notice: Changes introduced as a result of publishing processes such as opy-editing and formatting may not be reflected in this document. For a definitive version of this work, please refer to the published source: https://doi.org/10.1109/ICIP.2013.6738731" 0f2ffd582674bd856247bc5482d85e6db3b49b8f,A neural signature of the creation of social evaluation.,"doi:10.1093/scan/nst051 SCAN (2014) 9, 731^736 A neural signature of the creation of social evaluation Roman Osinsky,1 Patrick Mussel,1 Linda O¨ hrlein,1 and Johannes Hewig1,2 Department of Psychology I, Julius-Maximilians-University Wu¨rzburg, 97070 Wu¨rzburg, Germany and 2Department of Psychology, Friedrich-Schiller-University Jena, 07743 Jena, Germany Previous research has shown that receiving an unfair monetary offer in economic bargaining elicits also-called feedback negativity (FN). This scalp- recorded brain potential probably reflects a bad-vs-good evaluation in the medial frontal cortex and has been linked to fundamental processes of reinforcement learning. In the present study, we investigated whether the evaluative mechanism indexed by the FN is also involved in learning who is an unfair vs fair bargaining partner. An electroencephalogram was recorded while participants completed a computerized version of the Ultimatum Game, repeatedly receiving fair or unfair monetary offers from alleged other participants. Some of these proposers were either always fair or always unfair in their offers. In each trial, participants first saw a portrait picture of the respective proposer before the monetary offer was presented. Therefore, the faces ould be used as predictive cues for the fairness of the pending offers. We found that not only unfair offers themselves induced a FN, but also (over the task) faces of unfair proposers. Thus, when interaction partners repeatedly behave in an unfair way, their faces acquire a negative valence, which manifests in a basal neural mechanism of bad-vs-good evaluation. Keywords: social evaluation; feedback negativity; ultimatum game; evaluative conditioning INTRODUCTION trading example, family, work," 0f257ae1829b3250723a87781373d339308ea996,A Fully Automated System for Sizing Nasal PAP Masks Using Facial Photographs,"A Fully Automated System for Sizing Nasal PAP Masks Using Facial Photographs Benjamin Johnston Student Member, IEEE and Philip de Chazal Senior Member, IEEE" 0f146e17dc24a304f9e9b27cd787ff51edbc33cf,Non Uniform Blur and Illumination Variance Face Recognition Using Local Binary Pattern,"International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 03 Issue: 09 | Sep -2016 www.irjet.net p-ISSN: 2395-0072 Non Uniform Blur and Illumination Variance Face Recognition Using Local Binary Pattern Sravya konakala1, Dr.Suman maloji2 Department of Electronics and communication Engineering, LBRCE, Andhra Pradesh, Department of Electronics and communication Engineering, LBRCE, Andhra Pradesh, ---------------------------------------------------------------------***-------------------------------------------------------------------- still lacking. for real-world face recognition" 0fcca61391e7ee7718f5d2c05adc658f2978a2e8,Spectral Face Recognition Using Orthogonal Subspace Bases, 0f94f4934d0a26dfd243852036468ecc9bf8d22c,Low Resolution Lidar-Based Multi-Object Tracking for Driving Applications,"Low resolution lidar-based multi-object tracking for driving applications Iv´an del Pino(cid:63), V´ıctor Vaquero(cid:63), Beatrice Masini, Joan Sol`a, Francesc Moreno-Noguer, Alberto Sanfeliu, and Juan Andrade-Cetto Institut de Rob`otica i Inform`atica Industrial, CSIC-UPC Llorens Artigas 4-6, 08028 Barcelona, Spain. http://www.iri.upc.edu" 0fb75f5cb12d1e1a909b9f698b7617bb9603002f,Design of Weight-Learning Efficient Convolutional Modules in Deep Convolutional Neural Networks and its Application to Large-Scale Visual Recognition Tasks,"Data Analysis Project Design of Weight-Learning Ef‌f‌icient Convolutional Modules in Deep Convolutional Neural Networks and its Application to Large-Scale Visual Recognition Tasks Felix Juefei-Xu May 3, 2017" 246597d62f5d4af187a01623d7c353e13693da12,3D active appearance model for aligning faces in 2D images,"D Active Appearance Model for Aligning Faces in 2D Images Chun-Wei Chen and Chieh-Chih Wang" 24d3e695af619e88613aba7dc0e7492c12fa4d0e,Sparsest Matrix based Random Projection for Classification,"Sparse Matrix-based Random Projection for Classification Weizhi Lu, Weiyu Li, Kidiyo Kpalma and Joseph Ronsin" 24727e1b401752c5914fba5c935268e284c9f55f,Calibrating Uncertainties in Object Localization Task,"Calibrating Uncertainties in Object Localization Task Buu Phan∗ Rick Salay∗ Krzysztof Czarnecki∗ Vahdat Abdelzad∗ Taylor Denouden† Sachin Vernekar†" 24ff832171cb774087a614152c21f54589bf7523,Beat-Event Detection in Action Movie Franchises,"Beat-Event Detection in Action Movie Franchises Danila Potapov Matthijs Douze Jerome Revaud Zaid Harchaoui Cordelia Schmid" 243778aefb3c23d6774309c70217cb83f7204915,"The Mutex Watershed: Efficient, Parameter-Free Image Partitioning","The Mutex Watershed: Ef‌f‌icient, Parameter-Free Image Partitioning Steffen Wolf1⋆, Constantin Pape1,2⋆, Alberto Bailoni1, Nasim Rahaman1, Anna Kreshuk1,2, Ullrich K¨othe1, and Fred A. Hamprecht1 HCI/IWR, University of Heidelberg, Germany EMBL Heidelberg, Germany" 245f8ec4373e0a6c1cae36cd6fed5a2babed1386,Lucas Kanade Optical Flow Computation from Superpixel based Intensity Region for Facial Expression Feature Extraction,"J. Appl. Environ. Biol. Sci., 7(3S)1-10, 2017 © 2017, TextRoad Publication ISSN: 2090-4274 Journal of Applied Environmental nd Biological Sciences www.textroad.com Lucas Kanade Optical Flow Computation from Superpixel based Intensity Region for Facial Expression Feature Extraction Halina Hassan1,2, Abduljalil Radman1, Shahrel Azmin Suandi1, Sazali Yaacob2 Intelligent Biometric Group, School of Electrical and Electronics Engineering, Universiti Sains Malaysia, Electrical, Electronics and Automation Section, Universiti Kuala Lumpur Malaysian Spanish Institute, 09000 Engineering Campus, 14300 Nibong Tebal, Pulau Pinang, Malaysia Kulim Hi-Tech Park, Kedah, Malaysia Received: February 21, 2017 Accepted: May 14, 2017" 24301df85a669c86ae58962b5645b04a66c63cb1,A Jointly Learned Context-Aware Place of Interest Embedding for Trip Recommendations,"A Jointly Learned Context(cid:173)Aware Place of Interest Embedding for Trip Recommendations Jiayuan He, Jianzhong Qi, Kotagiri Ramamohanarao School of Computing and Information Systems, The University of Melbourne, Australia" 24115d209e0733e319e39badc5411bbfd82c5133,Long-Term Recurrent Convolutional Networks for Visual Recognition and Description,"Long-term Recurrent Convolutional Networks for Visual Recognition and Description Jeff Donahue, Lisa Anne Hendricks, Marcus Rohrbach, Subhashini Venugopalan, Sergio Guadarrama, Kate Saenko, Trevor Darrell" 24c7554823bb8c1c0729c4ece5f3e50965aea74e,Robust Computation of Linear Models by Convex Relaxation,"ROBUST COMPUTATION OF LINEAR MODELS, OR HOW TO FIND A NEEDLE IN A HAYSTACK GILAD LERMAN∗, MICHAEL MCCOY†, JOEL A. TROPP†, AND TENG ZHANG◦" 246ec873db261257833231d657ec8995d686cc3e,Extraversion and Social Motives View project Grip Strength and Perceptions View project,"See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/315831650 Facing the implications: Dangerous world eliefs differentially predict men and Women's version to facially communicated... Article in Personality and Individual Differences · October 2017 READS DOI: 10.1016/j.paid.2017.04.018 CITATIONS authors, including: Mitch Brown University of Southern Mississippi 9 PUBLICATIONS 14 CITATIONS SEE PROFILE Some of the authors of this publication are also working on these related projects: Facially Communicated Extraversion and Social Motives View project Grip Strength and Perceptions View project All content following this page was uploaded by Mitch Brown on 09 April 2017. The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the original document nd are linked to publications on ResearchGate, letting you access and read them immediately." 24ec4cd704d07865ce31fe539d00cd2597b5dfc9,Face Localization in the Neural Abstraction Pyramid,Face Localization 24585f90bdf30583733841f70430d36948f16ae2,An efficient method for human face recognition using nonsubsampled contourlet transform and support vector machine,"Optica Applicata, Vol. XXXIX, No. 3, 2009 An efficient method for human face recognition using nonsubsampled contourlet transform nd support vector machine XUEBIN XU, DEYUN ZHANG, XINMAN ZHANG* School of Electronics and Information Engineering, Xi’an Jiaotong University, 8 Xianning West Road, Xi’an 710049, P.R. China *Corresponding author: To improve the recognition rate in different conditions, a multiscale face recognition method ased on nonsubsampled contourlet transform and support vector machine is proposed in this paper. Firstly, all face images are decomposed by using nonsubsampled contourlet transform. The contourlet coefficients of low frequency and high frequency in different scales and various ngles will be obtained. Most significant information of faces is contained in coefficients, which is important for face recognition. Then, the combinations of coefficients are applied as study samples to the support vector machine classifiers. Finally, the decomposed coefficients of testing face image are used to test classifiers, then face recognition results are obtained. The experiments re performed on the YaleB database and the Cambridge University ORL database. The results indicate that the method proposed has performs better than the wavelet-based method. Compared with the wavelet-based method, the proposed method can make the best recognition rates increase y 2.85% for YaleB database and 1.87% for ORL database, respectively. Our method is also" 24b6d839662e5d56f17fc26eab4d2901f6835ddf,Real Time Lip Motion Analysis for a Person Authentication System using Near Infrared Illumination,"REAL TIME LIP MOTION ANALYSIS FOR A PERSON AUTHENTICATION SYSTEM USING NEAR INFRARED ILLUMINATION Faisal Shafait, Ralph Kricke, Islam Shdaifat, Rolf-Rainer Grigat TUHH Vision Systems (4-08/1) Harburger Schloßstr. 20, 21079 Hamburg, Germany Tel: +49 40 42878-3125, Fax: +49 40 42878-2911 http://www.ti1.tu-harburg.de in: 2006 IEEE International Conference on Image Processing. See also BIBTEX entry below. BIBTEX: uthor = {Faisal Shafait and Ralph Kricke and Islam Shdaifat and Rolf-Rainer Grigat}, title = {REAL TIME LIP MOTION ANALYSIS FOR A PERSON AUTHENTICATION SYSTEM USING NEAR INFRARED ILLUMINATION}, ooktitle = {2006 IEEE International Conference on Image Processing}, year = {2006}, pages = {1957-1960}, month = {oct}, url = {http://www.ti1.tu-harburg.de/Publikationen} scheduled for October 8-11, 2006 in Atlanta, Georgia, USA. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for cre-" 24baf0d64384ad67feed9920ab04303bea610c13,Face Authentication System Based on FDA and ANN,"International Journal of Electrical & Computer Sciences IJECS-IJENS Vol: 10 No: 06 60 Face Authentication System Based on FDA and M. A. Teh Noranis, and N. Shahrin Azuan" 247df1d4fca00bc68e64af338b84baaecc34690b,Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces,"Review Procedure 009/6/12 Paper  “Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces”  Erno Makinen & Roope Raisamo  2008 Decision resizing lignment face detection resizing lassification resizing lignment lignment resizing face detection" 245130ac792531ca9981f9c5907190eac19ebb50,Detecting Objects using Unsupervised Parts-based Attributes,"Detecting Objects using Unsupervised Parts-based Attributes∗ Santosh K. Divvala1, Larry Zitnick2, Ashish Kapoor2 , Simon Baker2 Carnegie Mellon University. Microsoft Research. {larryz, ashishk," 246fa412f26d5bf5b151a7c3f5287141bd08ae0b,Deep Metric Learning for the Target Cost in Unit-Selection Speech Synthesizer,"Interspeech 2018 -6 September 2018, Hyderabad 0.21437/Interspeech.2018-1305" 247a6b0e97b9447850780fe8dbc4f94252251133,Facial action unit detection: 3D versus 2D modality,"Facial Action Unit Detection: 3D versus 2D Modality Arman Savran Electrical and Electronics Engineering Bo˘gazic¸i University, Istanbul, Turkey B¨ulent Sankur Electrical and Electronics Engineering Bo˘gazic¸i University, Istanbul, Turkey M. Taha Bilge Department of Psychology Bo˘gazic¸i University, Istanbul, Turkey" 2472d6e4459dd65cd77b5fce99220d3b30854408,Towards 3D object recognition via classification of arbitrary object tracks,"Towards 3D Object Recognition via Classification of Arbitrary Object Tracks Alex Teichman, Jesse Levinson, Sebastian Thrun Stanford Artificial Intelligence Laboratory {teichman, jessel," 2450c618cca4cbd9b8cdbdb05bb57d67e63069b1,A connexionist approach for robust and precise facial feature detection in complex scenes,"A Connexionist Approach for Robust and Precise Facial Feature Detection in Complex Scenes Stefan Duffner and Christophe Garcia France Telecom Research & Development , rue du Clos Courtel 5512 Cesson-S´evign´e, France fstefan.duffner," 24da9c1eb30ed5ef0052f760d5d847bf5cd1d2ba,A Machine-Learning Approach to Keypoint Detection and Landmarking on 3D Meshes,"Int J Comput Vis DOI 10.1007/s11263-012-0605-9 A Machine-Learning Approach to Keypoint Detection nd Landmarking on 3D Meshes Clement Creusot · Nick Pears · Jim Austin Received: 14 October 2011 / Accepted: 17 December 2012 © Springer Science+Business Media New York 2013" 2491203e3b268235ea0269f41dbebd113d2a1b0a,"Optimal multiplexed sensing: bounds, conditions and a graph theory link.","Optimal multiplexed sensing: bounds, onditions and a graph theory link Netanel Ratner,1 Yoav Y. Schechner,1,∗ nd Felix Goldberg2 Dept. Electrical Engineering, Technion - Israel Inst. Technology Haifa 32000, Israel Dept. Mathematics, Technion - Israel Inst. Technology Haifa 32000, Israel Corresponding author:" 24d0092a3fc2a414b73fd453c5cdd229fc0cb174,Hierarchical Visual Feature Analysis for City Street View Datasets,"To appear in an IEEE VGTC sponsored conference proceedings Hierarchical Visual Feature Analysis for City Street View Datasets Lezhi Li, James Tompkin, Panagiotis Michalatos, and Hanspeter Pfister Fig. 1. Exploring ‘perceptual neighborhood’ with our hierarchical clustering of visual features for geographically-embedded images. From top to bottom: tree representation of the hierarchy as an interactive dendrogram; geo-location of the images as cloropleth map; ircle containment representation of the hierarchy; street-level imagery for geographic regions of the selected hierarchy levels." 2409557812a3d26258949ba73a05031591f42bdc,Exact Discovery of Time Series Motifs,"Abdullah Mueen Exact Discovery of Time Series Motifs Eamonn Keogh Qiang Zhu Sydney Cash1,2 Brandon Westover1,3 Massachusetts General Hospital, 2Harvard Medical School, 3Brigham and Women's Hospital University of California – Riverside {mueen, eamonn," 24ff2797234e26bb2ffd4558eb4412df0625687e,Mind Your Language: Abuse and Offense Detection for Code-Switched Languages,"Mind Your Language: Abuse and Offense Detection for Code-Switched Languages Raghav Kapoor MIDAS Lab, NSIT-Delhi Yaman Kumar Adobe Systems Kshitij Rajput MIDAS Lab, NSIT-Delhi Rajiv Ratn Shah IIIT, Delhi Ponnurangam Kumaraguru IIIT, Delhi Roger Zimmermann NUS, Singapore" 2475ad865b2102cef83a87adfe0d2e71d4791e53,A Supervised Clustering Algorithm for the Initialization of RBF Neural Network Classifiers,"A Supervised Clustering Algorithm for the Initialization of RBF Neural Network Classifiers Hakan Cevikalp, Diane Larlus, Frédéric Jurie To cite this version: Hakan Cevikalp, Diane Larlus, Frédéric Jurie. A Supervised Clustering Algorithm for the Ini- SIU ’07 - 15th Signal Processing and Com- tialization of RBF Neural Network Classifiers. munications Applications, Jun 2007, Eskisehir, Turkey. IEEE Computer society, pp.1-4, 2007, <10.1109/SIU.2007.4298803>. HAL Id: hal-00203762 https://hal.archives-ouvertes.fr/hal-00203762 Submitted on 14 Jan 2008 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est" 247b8e6b0e1014e707117c08fc880bb341b2c248,Advantages of dynamic analysis in HOG-PCA feature space for video moving object classification,"ADVANTAGES OF DYNAMIC ANALYSIS IN HOG-PCA FEATURE SPACE FOR VIDEO MOVING OBJECT CLASSIFICATION Miriam M. L´opez Lucio Marcenaro Carlo S. Regazzoni DITEN, University of Genova Via Opera Pia 11A, 16145 Genoa - Italy {miriam.lopez, mlucio," 24e79933d8d71dd9e72e289d9d89a061ccbb01c3,Analysis of Principal Component Analysis ( PCA ) Face Recognition : Effects of Similarity Measure,"Analysis of Principal Component Analysis (PCA) Face Recognition: Effects of Similarity Measure Arjun V Mane#1, Ramesh R Manza#2, Karbhari V Kale#3 #Department of Computer Science & Information Technology, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad (MS) India" 24e98b70dc6982af2dd3a5bb4e501cc1b61f7d2b,LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images,"SUBMITTED TO IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018 LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images Gr´egory Rogez, Philippe Weinzaepfel, and Cordelia Schmid, Fellow, IEEE" 24d68f3e7ee737463f81e9bf03500afa7b88f913,Comparing apples to apples in the evaluation of binary coding methods,"Comparing apples to apples in the evaluation of inary coding methods Mohammad Rastegari, Shobeir Fakhraei, Jonghyun Choi, David Jacobs, Larry S. Davis mrastega,shobeir jhchoi,djacobs,lsd" 242ae7b1b1c3e1aafcbe9cef3cb23918c6f94f2c,Performance Evaluation of Biometric Template Update,"Performance Evaluation of Biometric Template Update Romain Giot and Christophe Rosenberger Université de Caen, UMR 6072 GREYC ENSICAEN, UMR 6072 GREYC CNRS, UMR 6072 GREYC Email: Email: Bernadette Dorizzi Institut Télécom; Télécom SudParis UMR 5157 SAMOVAR Email:" 2431eeb2df8877d78901fa37a091a23dc207c2b2,Rotation-Invariant HOG Descriptors Using Fourier Analysis in Polar and Spherical Coordinates,"Int J Comput Vis DOI 10.1007/s11263-013-0634-z Rotation-Invariant HOG Descriptors Using Fourier Analysis in Polar and Spherical Coordinates Kun Liu · Henrik Skibbe · Thorsten Schmidt · Thomas Blein · Klaus Palme · Thomas Brox · Olaf Ronneberger Received: 30 September 2012 / Accepted: 21 May 2013 © Springer Science+Business Media New York 2013" 247232ab9eabb4f2480dd70557a1ee89afed4f20,Dominant men are faster in decision-making situations and exhibit a distinct neural signal for promptness,"Cerebral Cortex, October 2018;28: 3740–3751 doi: 10.1093/cercor/bhy195 Advance Access Publication Date: 15 August 2018 Original Article O R I G I N A L A R T I C L E Dominant men are faster in decision-making situations nd exhibit a distinct neural signal for promptness Janir da Cruz1,2, João Rodrigues3, John C. Thoresen3, Vitaly Chicherov1, Patrícia Figueiredo2, Michael H. Herzog1 and Carmen Sandi Laboratory of Psychophysics, Brain Mind Institute, School of Life Sciences, Swiss Federal Institute of Technology Lausanne (EPFL), CH-1015 Lausanne, Switzerland, 2Institute for Systems and Robotics – Lisboa, Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal nd 3Laboratory of Behavioral Genetics, Brain Mind Institute, School of Life Sciences, Swiss Federal Institute of Technology Lausanne (EPFL), CH-1015 Lausanne, Switzerland Address correspondence to Carmen Sandi, Laboratory of Behavioral Genetics, Brain Mind Institute, School of Life Sciences, Swiss Federal Institute of Technology Lausanne (EPFL), CH-1015 Lausanne, Switzerland. Email: orcid.org/0000-0001-7713-8321 Janir da Cruz, João Rodrigues, and John C. Thoresen contributed equally to this work Michael H. Herzog and Carmen Sandi contributed equally to this work" 2452dfb2c5a4578ac9497cc4dc3c6d5d03997210,On designing an unconstrained tri-band pupil detection system for human identification,"DOI 10.1007/s00138-015-0700-3 ORIGINAL PAPER On designing an unconstrained tri-band pupil detection system for human identification Cameron Whitelam1 · Thirimachos Bourlai1 Received: 30 September 2014 / Revised: 11 February 2015 / Accepted: 15 June 2015 © Springer-Verlag Berlin Heidelberg 2015 facial" 244b57cc4a00076efd5f913cc2833138087e1258,Warped Convolutions: Efficient Invariance to Spatial Transformations,"Warped Convolutions: Efficient Invariance to Spatial Transformations Jo˜ao F. Henriques 1 Andrea Vedaldi 1" 247b14570940601f5c7a2da1db532ecf1c302288,Dual Attention Networks for Multimodal Reasoning and Matching,"Dual Attention Networks for Multimodal Reasoning and Matching Hyeonseob Nam Naver Search Solutions Jung-Woo Ha Naver Labs Jeonghee Kim Naver Labs" 245922e5251c103c2021577cc0f99791d748ac64,Fusion of Intraoperative 3 D B-mode and Contrast-Enhanced Ultrasound Data for Automatic Identification of Residual Brain Tumors,"Article Fusion of Intraoperative 3D B-mode and Contrast-Enhanced Ultrasound Data for Automatic Identification of Residual Brain Tumors Elisee Ilunga-Mbuyamba 1,3, Dirk Lindner 2, Juan Gabriel Avina-Cervantes 1,∗, Felix Arlt 2, Horacio Rostro-Gonzalez 1, Ivan Cruz-Aceves 4 and Claire Chalopin 3 Telematics (CA), Engineering Division (DICIS), University of Guanajuato, Campus Irapuato-Salamanca, Carr. Salamanca-Valle km 3.5 + 1.8, Comunidad de Palo Blanco, Salamanca, Gto. 36885, Mexico; (E.I.-M.); (H.R.-G.) Department of Neurosurgery, University Hospital Leipzig, Leipzig 04103, Germany; (D.L.); (F.A.) Innovation Center Computer Assisted Surgery (ICCAS), University of Leipzig, Leipzig 04103, Germany; Centro de Investigacion en Matematicas (CIMAT), A.C., Jalisco S/N, Col. Valenciana, Guanajuato, Gto. 36000, Mexico; * Correspondence: Tel.: +52-46-4647-9940 (ext. 2400) Academic Editor: Hideyuki Hasegawa Received: 15 February 2017; Accepted: 17 April 2017; Published: 19 April 2017" 24c442ac3f6802296d71b1a1914b5d44e48b4f29,Pose and Expression-Coherent Face Recovery in the Wild,"Pose and expression-coherent face recovery in the wild Xavier P. Burgos-Artizzu Joaquin Zepeda Technicolor, Cesson-S´evign´e, France Franc¸ois Le Clerc Patrick P´erez" 246218fd60d47975990908c48274341b47255292,Marker-less motion capture in general scenes with sparse multi-camera setups,"Marker-less Motion Capture in General Scenes with Sparse Multi-camera Setups Ahmed Elhayek Saarbr¨ucken, Germany Dissertation zur Erlangung des Grades des Doktors der Ingenieurswissenschaften (Dr.-Ing.) der Naturwissenschaftlich-Technischen Fakult¨aten der Universit¨at des Saarlandes March 2015" 24e099e77ae7bae3df2bebdc0ee4e00acca71250,Robust Face Alignment Under Occlusion via Regional Predictive Power Estimation,"Robust face alignment under occlusion via regional predictive power estimation. Heng Yang; Xuming He; Xuhui Jia; Patras, I © 2015 IEEE For additional information about this publication click this link. http://qmro.qmul.ac.uk/xmlui/handle/123456789/22467 Information about this research object was correct at the time of download; we occasionally make corrections to records, please therefore check the published record when citing. For more information contact" 5ecf564bc9eab26c96c17304744ff1029215a109,Single-Sample Face Recognition Based on Intra-Class Differences in a Variation Model,"Sensors 2015, 15, 1071-1087; doi:10.3390/s150101071 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article Single-Sample Face Recognition Based on Intra-Class Differences in a Variation Model Jun Cai, Jing Chen * and Xing Liang School of Optoelectronics, Beijing Institute of Technology, Beijing 100081, China; E-Mails: (J.C.); (X.L.) * Author to whom correspondence should be addressed; E-Mail: Tel.: +86-136-8151-5195. External Editor: Valentina Gatteschi Received: 17 September 2014 / Accepted: 10 December 2014 / Published: 8 January 2015" 5e0832848fab012b7e59580264257e0a3d05c596,The University of Southampton Multi-Biometric Tunnel and introducing a novel 3 D gait dataset Richard,"The University of Southampton Multi-Biometric Tunnel and introducing a novel 3D gait dataset Richard D. Seely, Sina Samangooei, Lee Middleton, John N. Carter and Mark S. Nixon" 5ee220b6fb70a3d4d99be9d81d2c0e5de06ab3b9,LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics,"Pre-print of article that will appear in Proceedings of Robotics: Science and Systems XIV, 2018.Please cite this paper as:Sourav Garg, Niko Sunderhauf, and Michael Milford. LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics. Proceedings of Robotics: Science and Systems XIV, title={LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics}, author={Garg, Sourav and Suenderhauf, Niko and Milford, Michael}, journal={Proceedings of Robotics: Science and Systems XIV}, year={2018}}" 5e9a6357fd7de7271dac77756c3992dce260eb49,ON THE CONVERGENCE OF AFFECTIVE AND PERSUASIVE TECHNOLOGIES IN COMPUTER-MEDIATED HEALTH-CARE SYSTEMS,"Rebeca I. García-Betances Life Supporting Technologies (LifeSTech) Superior Technical School of Telecommunications Engineers Polytechnic University of Madrid Superior Technical School of Telecommunications Engineers Polytechnic University of Madrid Spain Dario Salvi Spain Giuseppe Fico Life Supporting Technologies (LifeSTech) Superior Technical School of Telecommunications Engineers Polytechnic University of Madrid Spain Manuel Ottaviano Superior Technical School of Telecommunications Engineers" 5e286a45a4780a142e1420728ab99cb92993ab50,Data-driven image captioning with meta-class based retrieval,"META-SINIF TABANLI GETİRME İLE VERİYE DAYALI İMGE ALTYAZILAMA DATA-DRIVEN IMAGE CAPTIONING WITH META-CLASS BASED RETRIEVAL Mert Kılıçkaya1, Erkut Erdem1, Aykut Erdem1, Nazlı İkizler Cinbiş1, Ruket Çakıcı2 Bilgisayar Mühendisliği Bölümü Hacettepe Üniversitesi ÖZETÇE Otomatik imge altyazılama, bir imgenin açıklamasını yaratma işlemi, bilgisayarlı görü ve doğal dil işleme topluluklarının ilgisini daha yeni çeken çok zorlu bir problemdir. Bu çalışmada, verilen bir imge için; imge-altyazı ikilileri içeren geniş bir veri kümesinden ona görsel olarak en benzer imgeyi ulan ve onun altyazısını girdi imgesinin açıklaması olarak ktaran veriye dayalı özgün bir imge altyazılama stratejisi önerilmiştir. Özgünlüğümüz, getirme için girdi görüntüsünün anlamsal içeriğini daha iyi yakalamak için meta-sınıg gösterimi olarak adlandırılan yeni önerilmiş yüksek düzey bir global imge gösterimi kullanılmasında yatmaktadır. Deneylerimiz meta-sınıf güdümlü yaklaşımımızın dayanak Im2Text modeline kıyasla daha doğru açıklamalar ürettiğini" 5e8a7a2eef68f568c023f37e41576fa811e5c628,Deep Reinforcement Learning For Sequence to Sequence Models,"Deep Reinforcement Learning for Sequence-to-Sequence Models Yaser Keneshloo, Tian Shi, Naren Ramakrishnan, Chandan K. Reddy, Senior Member, IEEE" 5e0eb34aeb2b58000726540336771053ecd335fc,Low-Quality Video Face Recognition with Deep Networks and Polygonal Chain Distance,"Low-Quality Video Face Recognition with Deep Networks and Polygonal Chain Distance Christian Herrmann∗†, Dieter Willersinn†, J¨urgen Beyerer†∗ Vision and Fusion Lab, Karlsruhe Institute of Technology KIT, Karlsruhe, Germany Fraunhofer IOSB, Karlsruhe, Germany" 5ea9063b44b56d9c1942b8484572790dff82731e,Multiclass Support Vector Machines and Metric Multidimensional Scaling for Facial Expression Recognition,"MULTICLASS SUPPORT VECTOR MACHINES AND METRIC MULTIDIMENSIONAL SCALING FOR FACIAL EXPRESSION RECOGNITION Irene Kotsiay, Stefanos Zafeiriouy, Nikolaos Nikolaidisy and Ioannis Pitasy yAristotle University of Thessaloniki, Department of Informatics Thessaloniki, Greece email: fekotsia, dralbert, nikolaid," 5e39deb4bff7b887c8f3a44dfe1352fbcde8a0bd,Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!,"Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss! Maneet Singh, Student Member, IEEE, Shruti Nagpal, Student Member, IEEE, Mayank Vatsa, Senior Member, IEEE, Richa Singh, Senior Member, IEEE, and Afzel Noore, Senior Member, IEEE" 5e2266d4ca1377bdf38ad2c07d0d9e0200813522,Recognizing and Mask Removal in 3 D Faces Even In Presence of Occlusions,"ISSN(Online): 2320-9801 ISSN (Print): 2320-9798 International Journal of Innovative Research in Computer and Communication Engineering (An ISO 3297: 2007 Certified Organization) Vol.2, Special Issue 1, March 2014 Proceedings of International Conference On Global Innovations In Computing Technology (ICGICT’14) Organized by Department of CSE, JayShriram Group of Institutions, Tirupur, Tamilnadu, India on 6th & 7th March 2014 Recognizing and Mask Removal in 3D Faces Even In Presence of Occlusions M.Dhivya1, P.Purushothaman2 Dept. of Computer Science and Engineering, Muthayammal Engineering College, Rasipuram, Tamilnadu, India1. 2" 5e4ad1f19e88b6dc87000f64b984d8f09abe7baf,Invariant Spectral Hashing of Image Saliency Graph,"Invariant Spectral Hashing of Image Saliency Graph Maxime Taquet, Laurent Jacques, Christophe De Vleeschouwer and Benoˆıt Macq Information and Communication Technologies, Electronics and Applied Mathematics Universit´e catholique de Louvain, Belgium. September 17, 2010" 5ef49174ca2b54c1bb54df828acc52075cf1634b,DAPs: Deep Action Proposals for Action Understanding,"DAPs: Deep Action Proposals for Action Understanding Victor Escorcia1, Fabian Caba Heilbron1, Juan Carlos Niebles2,3, Bernard Ghanem1 King Abdullah University of Science and Technology (KAUST), Saudi Arabia. Stanford University. 3 Universidad del Norte, Colombia. {victor.escorcia, fabian.caba," 5eee9c417157916ee66689718af65965c423b2b7,"In Press: Carol Armstrong, Ed., Handbook of Medical Neuropsychology. New York: Springer Science. Autism and Asperger’s Syndrome: A Cognitive Neuroscience Perspective","In Press: Carol Armstrong, Ed., Handbook of Medical Neuropsychology. New York: Springer Science. Autism and Asperger’s Syndrome: A Cognitive Neuroscience Perspective Jeanne Townsend, Ph.D., Marissa Westerfield, Ph.D. Department of Neurosciences, University of California, San Diego Table of Contents History and Background Biological Underpinnings Postmortem Studies MRI Studies White Matter Connectivity Neuroanatomy EEG Abnormalities Seizures Diagnosis Neurocognitive Mechanisms Screening Guidelines Clinical & Research Criteria Increased Prevalence of Autism It’s not the vaccine" 5eac16cf7551d2968bc2d73200883dca0b5f7f13,Combining complementary kernels in complex visual categorization,"Combining complementary kernels in complex visual categorization Nicolas Thome1, David Picard2 and Matthieu Cord1 LIP6 UPMC Paris 6 place Jussieu, 75005 Paris, France ETIS, CNRS ENSEA UCP, 95000 Cergy-Pontoise Introduction Bag Of Words model [1] and Fisher Vectors [2] coupled with incorporated spatial information, such as the Spatial Pyramid Matching (SPM) [3] or the spatial Fisher vectors [4], proved to reach state of the art performances in many Image categorization tasks, e.g. the PASCAL VOC challenge [5]. However, image categorization remains a very challenging task because most descriptors present strong intra-class variabilities and inter-class correlations. Therefore, a natural way to improve categorization performances consists in designing ef‌f‌icient feature combination strategies. It is an important issue for both computer vision and machine learning communities, that has been extensively studied in the last decade. Multiple Kernel Learning (MKL) is appealing for that purpose, since it offers the possibility to jointly learn the weighting of the different channels (features and similarity kernels) and the classification function [6]. The goal is to find the optimal classification function f defined as follows: f (x) = Pi αiyi Pm βmkm(x, xi) − b where the variable to be optimized are both the α and the w. Ef‌f‌icient algorithms exist for solving the related optimization convex problem [7]. Recent works attempting at using MKL on image datasets for combining different channels [8, 9] use MKL optimization algorithms based on ℓ1 norm to regularize the kernel weights, like SimpleMKL [7]. Since this leads" 5e6f546a50ed97658be9310d5e0a67891fe8a102,Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?,"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet? Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh National Institute of Advanced Industrial Science and Technology (AIST) Tsukuba, Ibaraki, Japan {kensho.hara, hirokatsu.kataoka," 5e4a451faf2e47486a5dbeca8a5109b53e22d95a,Research Statement Arun Kumar,"Research Statement Arun Kumar Large-scale data analytics using machine learning (ML), popularly known as advanced analytics or “Big Data” analytics, is transforming almost every data-powered application in the enterprise, Web, science, government, and other domains. However, there are still many barriers to broad and successful adoption of advanced analytics. Designing new ML algorithms and faster ML implementations are important issues that have been studied by researchers for a long time, but for most data-powered applications, the real showstopper is a different issue that is often glossed over in research: the end-to-end process of building ML models given raw data is often too painful even for professional analysts, while developers skilled in oth general-purpose programming and the latest ML are rare. The goal of my research is to improve the productivity of the users and developers of advanced analytics systems to enable data-powered applications to realize the full potential of advanced analytics. To this end, my work focuses on fundamental research questions at the intersection of data management and ML that address usability, developability, perfor- mance, and scalability issues. My approach to solving a problem involves the whole spectrum of algorithm design, theoretical analysis, empirical analysis, building prototype systems, and deploying them in practice. Research Summary. My dissertation opens up a new problem that I call “learning over joins”, which illustrates my goal of improving the productivity of analysts. My observation is simple: most ML toolkits ssume the input data is a single table, but many real-world datasets are multi-table. Thus, analysts join ll tables to create a single table that might be much larger, which means that managing and maintaining it is a usability headache. Creating a single table also causes storage and performance issues. To mitigate" 5e832ea5328cdcc9b4346458672ad8288a56c0a7,Illumination-robust face recognition with Block-based Local Contrast Patterns,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" 5eae1a3e0dfd0834be6a003b979bf5b3dc923453,"Far-Field , Multi-Camera , Video-to-Video Face Recognition","Far-Field, Multi-Camera, Video-to-Video Face Recognition Aristodemos Pnevmatikakis and Lazaros Polymenakos Athens Information Technology Greece . Introduction Face recognition on still images has been extensively studied. Given sufficient training data (many gallery stills of each person) and/or high resolution images, the 90% recognition arrier can be exceeded, even for hundreds of different people to be recognized (Phillips et l., 2006). Face recognition on video streams has only recently begun to receive attention (Weng et al., 2000; Li et al., 2001; Gorodnichy, 2003; Lee et al., 2003; Liu and Chen, 2003; Raytchev and Murase, 2003; Aggarval et al., 2004; Xie et al., 2004; Stergiou et al., 2006). Video-to-video face recognition refers to the problem of training and testing face recognition systems using video streams. Usually these video streams are near-field, where the person to be recognized occupies most of the frame. They are also constrained in the sense that the person looks mainly at the camera. Typical such video streams originate from video-calls nd news narration, where a person’s head and upper torso is visible. A much more interesting application domain is that of the far-field unconstrained video streams. In such streams the people are far from the camera, which is typically mounted on a room corner near the ceiling. VGA-resolution cameras in such a setup can easily lead to quite" 5ece99e52efbd43ac7fed8a7d0d604218cba0337,Towards Deep Representation Learning with Genetic Programming,"Towards Deep Representation Learning with Genetic Programming(cid:63) Lino Rodriguez-Coayahuitl, Alicia Morales-Reyes, and Hugo Jair Escalante Instituto Nacional de Astrofisica, Optica y Electronica, Luis Enrique Erro No.1, Tonantzintla, 72840, Puebla, Mexico," 5eefe98aafffe665b19de515e3ba90c9c0b7219c,Trimmed Event Recognition Submission to ActivityNet Challenge 2018,"Trimmed Event Recognition​ Submission to ActivityNet Challenge 2018 Jiaqing Lin, Akikazu Takeuchi STAIR Lab, Chiba Institute of Technology, Japan {lin, . Overview This paper describes STAIR Lab submission to ActivityNet 2018 Challenge for guest task C: Trimmed Event Recognition (Moments in Time) [1]. Our approach is to utilize three networks, Audio Net, Spatial-temporal Net, and DenseNet to make individual predictions, then use MLP to fuses the results to make an overall prediction. The flow chart of our approach is shown in figure 1. . Implementation .1 Audio network Our audio dataset training is different from other methods. Usually, auditory raw waveforms are used s input and are fed into a model like SoundNet [2]. In our case, firstly, we converted auditory raw" 5e9e3afeea446a2ae19e3a8e0678f08b73b0b36b,Commonsense knowledge acquisition and applications,"Commonsense Knowledge Acquisition and Applications Niket Tandon Max-Planck-Institut f¨ur Informatik Dissertation zur Erlangung des Grades des Doktors der Ingenieurwissenschaften (Dr.-Ing.) der Naturwissenschaftlich-Technischen Fakult¨aten der Universit¨at des Saarlandes Saarbr¨ucken August, 2016" 5e053cd164b02433c4efc0fc675f6273a8a1c46a,Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling,"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 321–331 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 321–331 Vancouver, Canada, July 30 - August 4, 2017. c(cid:13)2017 Association for Computational Linguistics Vancouver, Canada, July 30 - August 4, 2017. c(cid:13)2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1030 https://doi.org/10.18653/v1/P17-1030" 5e16cc5dc7ef8b4fc1320abbfeb838b4fe041905,A Proposal for Common Dataset in Neural-Symbolic Reasoning Studies,"A Proposal for Common Dataset in Neural-Symbolic Reasoning Studies Ozgur Yilmaz, Artur d’Avila Garcez, and Daniel Silver Turgut Ozal University, Computer Science Department, Ankara Turkey City University London, Department of Computer Science, London UK Acadia University, Jodrey School of Computer Science, Nova Scotia Canada," 5efbb135fd3a49de6ca1b69ef583d1bcfe761043,APPLICATION OF SUPPORT VECTOR MACHINES IN AUTOMATIC HUMAN FACE RECOGNITION,"JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 9/2005, ISSN 1642-6037 Michał KAWULOK* utomatic face recognition, support vector machines, face detection, feature extraction, multi-method fusion APPLICATION OF SUPPORT VECTOR MACHINES IN AUTOMATIC HUMAN FACE RECOGNITION This paper presents the possibilities of applying the Support Vector Machines (SVM) in the process of utomatic human face recognition. It is described how the existing methods of face recognition can be improved y the SVM. Moreover, a new approach to the multi-method fusion utilising the SVM is proposed. Usefulness of all the methods described in the paper improving the face recognition effectiveness by the SVM is confirmed y the experimental results. . INTRODUCTION At first an idea of automatic face recognition should be described. It can be imagined that there is a system which acquires an image or a set of images as an input data, processes them, detects faces in these images and generates feature vectors describing each detected face. Furthermore, such a system is able to compare two feature vectors and calculate similarity between them in a form of the normalised similarity value. This makes it possible to assess similarity etween any two given images containing faces in an automatic way (i.e. without human attendance or interaction). As a result, such a system discriminates between different faces and fulfils four elongs to one of the defined classes or to none of them), verification, full identification." 5e2be6b7d8e483f8bd49711b93b37e7886c77be0,Cell-Based Deformation Monitoring via 3D Point Clouds,"Cell-Based Deformation Monitoring via 3D Point Clouds THÈSE NO 5399 (2012) PRÉSENTÉE LE 6 SEPTEMBRE 2012 À LA FACULTÉ DE L'ENVIRONNEMENT NATUREL, ARCHITECTURAL ET CONSTRUIT PROGRAMME DOCTORAL EN INFORMATIQUE, COMMUNICATIONS ET INFORMATION LABORATOIRE DE TOPOMÉTRIE ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE POUR L'OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES Jing WU Prof. B. Merminod, directeur de thèse cceptée sur proposition du jury: Prof. P. Fua, président du jury Prof. M. Jaboyedoff, rapporteur Prof. K. Schindler, rapporteur Prof. R. Urbanke, rapporteur Suisse" 5e1b42d07eb84cddc1ebae607f3041aa2ef8fce8,RAM: Role Representation and Identification from combined Appearance and Activity Maps,"RAM: Role Representation and Identification from combined Appearance and Activity Maps Carlos Torres† Archith J. Bency† Je(cid:130)rey C. Fried‡ B. S. Manjunath† University of California Santa Barbara ‡Santa Barbara Co(cid:138)age Hospital {carlostorres, archith," 5ec94adc9e0f282597f943ea9f4502a2a34ecfc2,Leveraging the Power of Gabor Phase for Face Identification: A Block Matching Approach,"Leveraging the Power of Gabor Phase for Face Identification: A Block Matching Approach Yang Zhong, Haibo Li KTH, Royal Institute of Technology" 5e8966e332a8cfc587fc116f71b97d6412a4472d,SoundNet: Learning Sound Representations from Unlabeled Video,"SoundNet: Learning Sound Representations from Unlabeled Video Yusuf Aytar∗ Carl Vondrick∗ Antonio Torralba" 5ef2be1aadd2f666756b2ab66bc05d146ba0681b,Normalization in Training Deep Convolutional Neural Networks for 2D Bio-medical Semantic Segmentation,"Normalization in Training Deep Convolutional Neural Networks for 2D Bio-medical Semantic Segmentation Xiao-Yun Zhou1 and Guang-Zhong Yang1" 5e0cdf7d0edee84ab0efb9cbcb9487dac154f747,Public Document State of the Art in Multimodal Biometric Systems Document Evolution Executive Summary,"Project N° IST-2002-507634 - BioSecure D8.1.1 – Revision: b3 4 June 2005 Contract Number : Project Acronym : Project Title : Instrument : Start Date of Project : Duration : Deliverable Number : Title of Deliverable : Contractual Due Date : Actual Date of Completion : IST-2002-507634 BioSecure Biometrics for Secure Authentication Network of Excellence 01 June, 2004 6 months D8.1.1" 5e4e55ad902d0749d463187dbd453fd235a1379c,Empirical research on human behavior changes and digital intervention by one-way car-sharing,Yutaka Arakawa ∗ 5e8e3d2a79537a6cd0c138545bce63ddafaa853c,Intent-aware long-term prediction of pedestrian motion,"Intent-Aware Long-Term Prediction of Pedestrian Motion Vasiliy Karasev Alper Ayvaci Bernd Heisele Stefano Soatto" 5e6ba16cddd1797853d8898de52c1f1f44a73279,Face Identification with Second-Order Pooling,"Face Identification with Second-Order Pooling Fumin Shen, Chunhua Shen and Heng Tao Shen" 5e9f01b44ffda34356dc15451098d6311335d7ae,Efficient Large-Scale Multi-Modal Classification,"Efficient Large-Scale Multi-Modal Classification Douwe Kiela, Edouard Grave, Armand Joulin and Tomas Mikolov Facebook AI Research" 5e6944abfed38fd30d8be45ee0c24dc1c0525ba1,An Algorithm for Face Recognition based on Isolated Image Points with Neural Network,"International Journal of Computer Applications (0975 – 8887) Volume 150 – No.2, September 2016 An Algorithm for Face Recognition based on Isolated Image Points with Neural Network Hassan Jaleel Hassan, PhD Computer Engineering Department, University of Technology techniques Pixel-based" 6cd96f2b63c6b6f33f15c0ea366e6003f512a951,A New Approach in Solving Illumination and Facial Expression Problems for Face Recognition,"A New Approach in Solving Illumination and Facial Expression Problems for Face Recognition Yee Wan Wong, Kah Phooi Seng, Li-Minn Ang The University of Nottingham Malaysia Campus Tel : 03-89248358, Fax : 03-89248017 E-mail : Jalan Broga 3500 Semenyih, Selangor" 6cb7648465ba7757ecc9c222ac1ab6402933d983,Visual Forecasting by Imitating Dynamics in Natural Sequences,"Visual Forecasting by Imitating Dynamics in Natural Sequences Kuo-Hao Zeng†‡ William B. Shen† De-An Huang† Min Sun‡ Juan Carlos Niebles† {khzeng, bshen88, dahuang, Stanford University ‡National Tsing Hua University" 6c67f082c4141907d60ef914a151568ef59f58d7,Biometric Solutions for Personal Identification,"Biometric Solutions for Personal Identification Tormod Emsell Larsen Master of Science in Communication Technology Submission date: Supervisor: Co-supervisor: May 2008 Svein Johan Knapskog, ITEM Danilo Gligoroski, ITEM Norwegian University of Science and Technology Department of Telematics" 6c38ab65df4a1bf546f1426e8a7f2f5cb5f765d3,Pathological Tremor Detection From Video,"Pathological Tremor Detection From Video Xilin Li" 6ceacd889559cfcf0009e914d47f915167231846,The impact of visual attributes on online image diffusion,"The Impact of Visual Attributes on Online Image Diffusion Luam Totti Federal University of Minas Gerais (UFMG) Belo Horizonte, MG, Brazil Felipe Costa Federal University of Minas Gerais (UFMG) Belo Horizonte, MG, Brazil Sandra Avila RECOD Lab., DCA / FEEC / UNICAMP Campinas, SP, Brazil Eduardo Valle RECOD Lab., DCA / FEEC / UNICAMP Campinas, SP, Brazil Wagner Meira Jr. Federal University of Minas Gerais (UFMG)" 6cd7a47bbba11a994cd8e68ee5eae2fcb0033054,Driving in the Matrix: Can virtual worlds replace human-generated annotations for real world tasks?,"Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks? Matthew Johnson-Roberson1, Charles Barto2, Rounak Mehta3, Sharath Nittur Sridhar2, and Ram Vasudevan4" 6ce6da7a6b2d55fac604d986595ba6979580393b,Cross Domain Knowledge Transfer for Person Re-identification,"Cross Domain Knowledge Transfer for Person Re-identification Qiqi Xiao Kelei Cao Haonan Chen Fangyue Peng Chi Zhang" 6cf222f7c9ac4b48d95db4a62742c8329fcbd8b6,A System for Automatic Lip Reading,"ISCA Archive http://www.iscaĆspeech.org/archive AVSP 2003 - International Conference on AudioĆVisual Speech Processing St. Jorioz, France September 4-7, 2003 A System for Automatic Lip Reading I. Shdaifat and R. Grigat D. Langmann TU Hamburg Harburg, Vision Systems D-21071 Hamburg, Germany" 6c514a85b840c461cf6959927e6a34414e1e0f5e,Texture descriptors to distinguish radiation necrosis from recurrent brain tumors on multi-parametric MRI,"Medical Imaging 2014: Computer-Aided Diagnosis, edited by Stephen Aylward, Lubomir M. Hadjiiski, Proc. of SPIE Vol. 9035, 90352B · © 2014 SPIE · CCC code: 1605-7422/14/$18 · doi: 10.1117/12.2043969 Proc. of SPIE Vol. 9035 90352B-1 From: http://proceedings.spiedigitallibrary.org/ on 10/02/2014 Terms of Use: http://spiedl.org/terms" 6c2b392b32b2fd0fe364b20c496fcf869eac0a98,Fully automatic face recognition framework based on local and global features,"DOI 10.1007/s00138-012-0423-7 ORIGINAL PAPER Fully automatic face recognition framework based on local and global features Cong Geng · Xudong Jiang Received: 30 May 2011 / Revised: 21 February 2012 / Accepted: 29 February 2012 / Published online: 22 March 2012 © Springer-Verlag 2012" 6c06f959397e990e5d68dbcc85cec8b96b4c5c2d,Real-time Accurate Pedestrian Detection and Tracking in Challenging Surveillance Videos,"Real-time Accurate Pedestrian Detection and Tracking in Challenging Surveillance Videos Kristof Van Beeck1 and Toon Goedem´e1,2 EAVISE, Campus De Nayer - KU Leuven, J. De Nayerlaan 5, 2860 Sint-Katelijne-Waver, Belgium ESAT-PSI, KU Leuven, Kasteel Arenbergpark 10, 3100 Heverlee, Belgium Keywords: Pedestrian Detection, Tracking, Surveillance, Computer Vision, Real-time." 6c5ce8bf382948bb27a9cc33b700a2402877bb64,Hyperspectral image classification via contextual deep learning,"Ma et al. EURASIP Journal on Image and Video Processing (2015) 2015:20 DOI 10.1186/s13640-015-0071-8 RESEARCH Open Access Hyperspectral image classification via ontextual deep learning Xiaorui Ma, Jie Geng and Hongyu Wang*" 6c54261f601c8a569149b77d32efe6c58f2e4a2e,Preliminary evidence that the limbal ring influences facial attractiveness.,"Evolutionary Psychology www.epjournal.net – 2011. 9(2): 137-146 ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ Original Article Preliminary Evidence that the Limbal Ring Influences Facial Attractiveness Darren Peshek, Department of Cognitive Sciences, University of California Irvine, Irvine, CA, USA. Email: (Corresponding author). Negar Semmaknejad, Department of Cognitive Sciences, University of California Irvine, Irvine, CA, USA. Donald Hoffman, Department of Cognitive Sciences, University of California Irvine, Irvine, CA, USA. Pete Foley, Innovation Science, Procter & Gamble, Cincinnati, OH, USA." 6cd557019b7775d8647ca31260734c786fdb69ec,Visual Classifier Prediction by Distributional Semantic Embedding of Text Descriptions,"Proceedings of the 2015 Workshop on Vision and Language (VL’15), pages 48–50, Lisbon, Portugal, 18 September 2015. c(cid:13)2015 Association for Computational Linguistics." 6c9f45c76b4f96fe66d8e1d7b31f89b7cc6caa44,DeNet: Scalable Real-Time Object Detection with Directed Sparse Sampling,"DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling Lachlan Tychsen-Smith, Lars Petersson CSIRO (Data61) 7 London Circuit, Canberra, ACT, 2601" 6c24fed42d9a1ec283d2aa39a2dd768256a1a066,Swift: reducing the effects of latency in online video scrubbing,"Swift: Reducing the Effects of Latency in Online Video Scrubbing Justin Matejka, Tovi Grossman, George Fitzmaurice Autodesk Research, Toronto, Ontario, Canada Traditional Video Scrubbing Swift Video Scrubbing Figure 1. An illustration of the scrubbing behavior of a traditional streaming video player and the Swift player. With the Swift system a quick-to-download low resolution version of the video is displayed while scrubbing. tasks which the effects of" 6c518aabdbba2c073eab6a3bb4120023851e524c,Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras,"Article Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras Dat Tien Nguyen, Hyung Gil Hong, Ki Wan Kim and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (D.T.N.); (H.G.H.); (K.W.K.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Academic Editor: Vittorio M. N. Passaro Received: 5 January 2017; Accepted: 14 March 2017; Published: 16 March 2017" 6c091c3bd625b3c838831d797c66eae6c8f280cc,Apperance-Based Tracking and Face Identification in Video Sequences,"Apperance-based tracking and face identification in video sequences Jos´e Miguel Buenaposada1, Juan Bekios2, and Luis Baumela3 Dept. de Ciencias de la Computaci´on, Universidad Rey Juan Carlos Calle Tulip´an s/n, 28933, M´ostoles, Spain Dept. de Ingenier´ıa de Sistemas y Computaci´on, Universidad Cat´olica del Norte Av. Angamos 0610, Antofagasta, Chile Dept. de Inteligencia Artificial, Universidad Polit´ecnica de Madrid Campus Montegancedo s/n, 28660 Boadilla del Monte, Spain" 6cfc337069868568148f65732c52cbcef963f79d,Audio-Visual Speaker Localization via Weighted Clustering Israel -,"Audio-Visual Speaker Localization via Weighted Clustering Israel-Dejene Gebru, Xavier Alameda-Pineda, Radu Horaud, Florence Forbes To cite this version: Israel-Dejene Gebru, Xavier Alameda-Pineda, Radu Horaud, Florence Forbes. Audio-Visual Speaker Localization via Weighted Clustering. IEEE Workshop on Machine Learning for Signal Processing, Sep 2014, Reims, France. pp.1-6, 2014, <10.1109/MLSP.2014.6958874>. HAL Id: hal-01053732 https://hal.archives-ouvertes.fr/hal-01053732 Submitted on 11 Aug 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" 6cbb3c47010e406de656d13fe289522bb3071bc0,Improved vehicle detection system based on customized HOG,"Improved vehicle detection system based on ustomized HOG Haythem AMEUR1, Abdelhamid HELALI1, Hassen MAAREF1, Anis YOUSSEF2 Laboratory of Micro-Optoelectronic and Nanostructure, University of Monastir Tunisia, Monastir 2 TELNET Innovation Labs Tunisia, Tunis" 6c984bb3243f3b8d0afd8d90cd4ce85eb8f1dd3c,Ear Recognition System Using Neural Network Based Self Organizing Maps,"International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 International Conference on Humming Bird ( 01st March 2014) RESEARCH ARTICLE OPEN ACCESS D Ear Recognition System Using Neural Network Based Self Organizing Maps M.Sathish Babu1, Assistant Professor Email: Department of Computer Science and Engineering, Cape Institute of Technology." 6c8c7065d1041146a3604cbe15c6207f486021ba,Attention Modeling for Face Recognition via Deep Learning,"Attention Modeling for Face Recognition via Deep Learning Sheng-hua Zhong Department of Computing, Hung Hom, Kowloon Hong Kong, 999077 CHINA Yan Liu Department of Computing, Hung Hom, Kowloon Hong Kong, 99907 CHINA Yao Zhang Department of Computing, Hung Hom, Kowloon Hong Kong, 99907 CHINA Fu-lai Chung Department of Computing, Hung Hom, Kowloon Hong Kong, 99907 CHINA" 6cddc7e24c0581c50adef92d01bb3c73d8b80b41,Face Verification Using the LARK Representation,"Face Verification Using the LARK Representation Hae Jong Seo, Student Member, IEEE, Peyman Milanfar, Fellow, IEEE," 6c289ce7cd1c8514f71bf7dc25b1b203b98f8129,Semantic-Aware Image Smoothing,"Vision, Modeling, and Visualization (2017) M. Hullin, R. Klein, T. Schultz, A. Yao (Eds.) Semantic-Aware Image Smoothing Weihao Li1,2, Omid Hosseini Jafari1,2, and Carsten Rother1,2 Computer Vision Lab, TU Dresden, Germany Visual Learning Lab, Heidelberg University, Germany" 6cad008ad80081dc42752e813ee6924e3c174dc7,Does Facial Resemblance Enhance Cooperation?,"Does Facial Resemblance Enhance Cooperation? Trang Giang*, Raoul Bell*, Axel Buchner Department of Experimental Psychology, Heinrich Heine University Du¨ sseldorf, Du¨ sseldorf, Germany" 6c9e12c7ac10b6202762b9cd7ffae3822c90c063,Deployment of Customized Deep Learning based Video Analytics On Surveillance Cameras.,"Deployment of Customized Deep Learning based Video Analytics On Surveillance Cameras Pratik Dubal(cid:63), Rohan Mahadev(cid:63), Suraj Kothawade(cid:63), Kunal Dargan, and Rishabh Iyer AitoeLabs (www.aitoelabs.com)" 6c22b549d854845c5d2f17d75417e4469e6d3f83,A robust face recognition algorithm for real-world applications,"A Robust Face Recognition Algorithm for Real-World Applications zur Erlangung des akademischen Grades eines Doktors der Ingenieurwissenschaften der Fakult¨at f¨ur Informatik der Universit¨at Fridericiana zu Karlsruhe (TH) genehmigte Dissertation Hazım Kemal Ekenel us Samsun, T¨urkei Tag der m¨undlichen Pr¨ufung: 02.02.2009 Erster Gutachter: Prof. Dr. A. Waibel Zweiter Gutachter: Prof. Dr. J. Kittler" 6cd762e7cb1301abd0ddbb265dd9c7661ffc0458,On optimal low rank Tucker approximation for tensors: the case for an adjustable core size,"On Optimal Low Rank Tucker Approximation for Tensors: The Case for an Adjustable Core Size Bilian CHEN ∗ Zhening LI † Shuzhong ZHANG ‡ August 7, 2014" 6c4d5ac0eed17513e3ceacd396526b8ad6c8fc09,Learning to Learn by Exploiting Prior Knowledge,"Learning to Learn by Exploiting Prior Knowledge Thèse n. 5587 à présenter le 07 November 2012 à la Faculté des Sciences et Techniques de L'ingénieur laboratoire de L'Idiap programme doctoral en Génie Électrique École Polytechnique Fédérale de Lausanne pour l'obtention du grade de Docteur ès Sciences Tatiana Tommasi cceptée sur proposition du jury : Prof Dario Floreano, président du jury Prof Hervé Bourlard, directeur de thèse Dr Barbara Caputo, co-directeur de thèse Prof Jean-Philippe Thiran, rapporteur Prof Jim Little, rapporteur Dr Vittorio Ferrari, rapporteur Lausanne, EPFL, 2012" 6c0f9acd62ca9f156ca632dad6d666209eae461e,Discriminative vision-based recovery and recognition of human motion,"Discriminative Vision-Based Recovery and Recognition of Human Motion 9-789036-528108 CTIT Dissertation Series No. 09-136 Center for Telematics and Information Technology (CTIT) P.O. Box 217, 7500 AE Enschede, The Netherlands Ronald Poppe" 6c0c368fca391b4456e64d2943d0bcbe6d8e1ecc,A Pipeline for Creative Visual Storytelling,"A Pipeline for Creative Visual Storytelling Stephanie M. Lukin, Reginald Hobbs, Clare R. Voss U.S. Army Research Laboratory Adelphi, MD, USA" 6c3c845fe484bdb2b3549054644c7a06bd9b87b8,ENCARA: real-time detection of frontal faces,"ENCARA: REAL-TIME DETECTION OF FRONTAL FACES M. Castrillón Santana, M. Hernández Tejera, J. Cabrera Gámez Instituto Universitario Sistemas Inteligentes y Aplicaciones Numéricas en Ingeniería Universidad de Las Palmas de Gran Canaria 5017 Gran Canaria - Spain" 6cb68c1f7558e01966ad1e1fa81feeeae3dee666,Photo Filter Recommendation by Category-Aware Aesthetic Learning,"IEEE TRANSACTION ON MULTIMEDIA Photo Filter Recommendation y Category-Aware Aesthetic Learning Wei-Tse Sun, Ting-Hsuan Chao, Yin-Hsi Kuo, Winston H. Hsu" 6cefb70f4668ee6c0bf0c18ea36fd49dd60e8365,Privacy-Preserving Deep Inference for Rich User Data on The Cloud,"Privacy-Preserving Deep Inference for Rich User Data on The Cloud Seyed Ali Osia ♯, Ali Shahin Shamsabadi ♯, Ali Taheri ♯, Kleomenis Katevas ⋆, Hamid R. Rabiee ♯, Nicholas D. Lane †, Hamed Haddadi ⋆ ♯ Sharif University of Technology ⋆ Queen Mary University of London Nokia Bell Labs & University of Oxford" 6c964e59bdac6b8044993ca96b47a9a0addedfb8,First Impressions: A Survey on Computer Vision-Based Apparent Personality Trait Analysis,"First Impressions: A Survey on Vision-based Apparent Personality Trait Analysis Julio C. S. Jacques Junior, Ya˘gmur G¨uc¸l¨ut¨urk, Marc P´erez, Umut G¨uc¸l¨u, Carlos Andujar, Xavier Bar´o, Hugo Jair Escalante, Isabelle Guyon, Marcel A. J. van Gerven, Rob van Lier and Sergio Escalera" 6c304f3b9c3a711a0cca5c62ce221fb098dccff0,Attentive Semantic Video Generation Using Captions,"Attentive Semantic Video Generation using Captions Tanya Marwah∗ IIT Hyderabad Gaurav Mittal∗ Vineeth N. Balasubramanian IIT Hyderabad" 6c0c7b90e0c7badaa95924530cb50d86444010ff,Semantic Attributes for Transfer Learning in Visual Recognition,"Semantic Attributes for Transfer Learning in Visual Recognition zur Erlangung des akademischen Grades eines Doktors der Ingenieurwissenschaften der KIT-Fakultät für Informatik des Karlsruher Instituts für Technologie (KIT) genehmigte Dissertation Ziad Al Halah Tag der mündlichen Prüfung: 5. Februar 2018 Hauptreferent: Korreferent: Prof. Dr. Rainer Stiefelhagen Karlsruher Institut für Technologie Prof. Dr. Christoph Lampert Institute of Science and Technology Austria KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft www.kit.edu" 6cadbc0122376be3c249ecfec7de8247ffbc4fb3,Bidirectional Label Propagation over Graphs,"Int J Software Informatics, Volume 7, Issue 3 (2013), pp.419–433 International Journal of Software and Informatics, ISSN 1673-7288 (cid:176)2013 by ISCAS. All rights reserved. Tel: +86-10-62661040 http://www.ijsi.org Email: Bidirectional Label Propagation over Graphs Wei Liu1 and Tongtao Zhang2 (IBM T. J. Watson Research Center, Yorktown Heights, NY, USA) (Columbia University, New York, NY, USA)" 6c27eccf8c4b22510395baf9f0d0acc3ee547862,Using CMU PIE Human Face Database to a Convolutional Neural Network - Neocognitron.,"Using CMU PIE Human Face Database to a Convolutional Neural Network - Neocognitron José Hiroki Saito1, Tiago Vieira de Carvalho1, Marcelo Hirakuri1, André Saunite1, Alessandro Noriaki Ide2 and Sandra Abib1 - Federal University of São Carlos - Computer Science Department - GAPIS Rodovia Washington Luis, Km 235, São Carlos – SP - Brazil - University of Genoa - Department of Informatics, Systems and Telematics - Neurolab Via Opera Pia, 13 – I-16145 – Genoa - Italy" 6c653fcc80c83c87f710588bec039da3c7bfd219,Designing a smart-card-based face verification system: empirical investigation,"DOI 10.1007/s00138-007-0119-6 ORIGINAL PAPER Designing a smart-card-based face verification system: empirical investigation Thirimachos Bourlai · Josef Kittler · Kieron Messer Received: 17 July 2006 / Accepted: 29 October 2007 / Published online: 2 July 2008 © Springer-Verlag 2008" 6c52c12644321d4256306feaf784ccae6ebc4fea,Enhanced vote count circuit based on nor flash memory for fast similarity search,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 050e7e32fdc48150f66cb5edf166790c69652b8b,Land Cover Segmentation of Airborne LiDAR Data Using Stochastic Atrous Network,"Article Land Cover Segmentation of Airborne LiDAR Data Using Stochastic Atrous Network Hasan Asy’ari Arief 1,* ID , Geir-Harald Strand 1,2 ID , Håvard Tveite 1 ID and Ulf Geir Indahl 1 Faculty of Science and Technology, Norwegian University of Life Sciences, 1432 Ås, Norway; (G.H.S.); (H.T.); (U.G.I.) Division of Survey and Statistics, Norwegian Institute of Bioeconomy Research, 1431 Ås, Norway * Correspondence: Tel.: +47-453-91-706 Received: 30 April 2018; Accepted: 17 June 2018; Published: 19 June 2018" 05db46c7745c360fa5938ee204c81efdcc84c1da,An Empirical Evaluation of Current Convolutional Architectures’ Ability to Manage Nuisance Location and Scale Variability,"An Empirical Evaluation of Current Convolutional Architectures’ Ability to Manage Nuisance Location and Scale Variability Nikolaos Karianakis Jingming Dong Stefano Soatto UCLA Vision Lab, University of California, Los Angeles, CA 90095" 054738ce39920975b8dcc97e01b3b6cc0d0bdf32,Towards the design of an end-to-end automated system for image and video-based recognition,"Towards the Design of an End-to-End Automated System for Image and Video-based Recognition Rama Chellappa1, Jun-Cheng Chen3, Rajeev Ranjan1, Swami Sankaranarayanan1, Amit Kumar1, Vishal M. Patel2 and Carlos D. Castillo4" 05e3167206bc440d5aacf2256fd2e2e421b0808c,PEOPLE DETECTION AND RE-IDENTIFICATION FOR MULTI SURVEILLANCE CAMERAS,"People detection and re-identification for multi surveillance cameras Etienne Corvee, Slawomir Bak and Francois Bremond INRIA, Sophia Antipolis, Pulsar Team {etienne.corvee, slawomir.bak, Keywords: people detection, people tracking, people re-identification, local binary pattern, mean Riemannian covariance" 054953d915f65b66485b653cd2ffbf61568b2849,Face Description with Local Invariant Features: Application to Face Recognition,"Face Description with Local Invariant Features: Application to Face Recognition {tag} {/tag} International Journal of Computer Applications © 2010 by IJCA Journal Number 24 - Article 12 Year of Publication: 2010 Authors: Sanjay A. Pardeshi Dr. S.N. Talbar 10.5120/555-726" 0580edbd7865414c62a36da9504d1169dea78d6f,Baseline CNN structure analysis for facial expression recognition,"Baseline CNN structure analysis for facial expression recognition Minchul Shin1, Munsang Kim2 and Dong-Soo Kwon1" 05ce0e4e9ae2c7b2320decb3bb29e066f1dd96d3,Patch-wise low-dimensional probabilistic linear discriminant analysis for Face Recognition,"PATCH-WISE LOW-DIMENSIONAL PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS FOR FACE RECOGNITION Vitomir ˇStruc, Nikola Paveˇsi´c Jerneja ˇZganec-Gros, Boˇstjan Vesnicer Faculty of Electrical Engineering UL Trˇzaˇska cesta 25, 1000 Ljubljana, Slovenia Alpineon Ltd., Ulica Iga Grudna 15 000 Ljubljana, Slovenia" 051d8bbf12877c46ae9a598a386c5b72d1b103ac,Object Detection using Geometrical Context Feedback,"Int J Comput Vis (2012) 100:154–169 DOI 10.1007/s11263-012-0547-2 Object Detection using Geometrical Context Feedback Min Sun · Sid Yingze Bao · Silvio Savarese Received: 17 December 2010 / Accepted: 16 July 2012 / Published online: 2 August 2012 © Springer Science+Business Media, LLC 2012" 056ba488898a1a1b32daec7a45e0d550e0c51ae4,Cascaded Continuous Regression for Real-Time Incremental Face Tracking,"Cascaded Continuous Regression for Real-time Incremental Face Tracking Enrique S´anchez-Lozano, Brais Martinez, Georgios Tzimiropoulos, and Michel Valstar Computer Vision Laboratory. University of Nottingham" 05bba1f1626f02ef4ca497090b4a04d47f36ebb6,Social projection increases for positive targets: ascertaining the effect and exploring its antecedents.,"545039 PSPXXX10.1177/0146167214545039Personality and Social Psychology BulletinMachunsky et al. research-article2014 Article Social Projection Increases for Positive Targets: Ascertaining the Effect and Exploring Its Antecedents Maya Machunsky1, Claudia Toma2, Vincent Yzerbyt3, nd Olivier Corneille3 Personality and Social Psychology Bulletin 014, Vol. 40(10) 1373 –1388 © 2014 by the Society for Personality nd Social Psychology, Inc Reprints and permissions: sagepub.com/journalsPermissions.nav DOI: 10.1177/0146167214545039 pspb.sagepub.com" 05b8673d810fadf888c62b7e6c7185355ffa4121,A Comprehensive Survey to Face Hallucination,"(will be inserted by the editor) A Comprehensive Survey to Face Hallucination Nannan Wang · Dacheng Tao · Xinbo Gao · Xuelong Li · Jie Li Received: date / Accepted: date" 05c1fde513e23e2ec95bb9366665e716a2fcea7d,People detection in surveillance: classification and evaluation,"Repositorio Institucional de la Universidad Autónoma de Madrid https://repositorio.uam.es Esta es la versión de autor del artículo publicado en: This is an author produced version of a paper published in: DOI: http://dx.doi.org/10.1049/iet-cvi.2014.0148 Copyright: © 2015 Institution of Engineering and Technology El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription" 052b35b3b3e8f1a8689a2e3e5c67ab08de094cfe,Clustering-weighted SIFT-based classification method via sparse representation,"Downloaded From: https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging on 11/26/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use Clustering-weightedSIFT-basedclassificationmethodviasparserepresentationBoSunFengXuJunHe" 05487784c1c94e17c26862e342c1b81acfe11258,Spontaneous facial expression analysis based on temperature changes and head motions,"Spontaneous Facial Expression Analysis Based on Temperature Changes and Head Motions Peng Liu and Lijun Yin State University of New York-at Binghamton" 05fd17673f1500d46196b0e38857eb3eaf09296e,Fourier Descriptors Based on the Structure of the Human Primary Visual Cortex with Applications to Object Recognition,"(will be inserted by the editor) Fourier descriptors based on the structure of the human primary visual cortex with applications to object recognition Amine Bohi · Dario Prandi · Vincente Guis · Fr´ed´eric Bouchara · Jean-Paul Gauthier Received: date / Accepted: date" 05384ac77be3211fb7d221802bc79eb3c9fa2873,A Novel Image Classification System Based on Evidence Probabilistic Transformation,"International Journal of Research in Computer and Communication Technology, Vol 4,Issue 2 ,February -2015 ISSN (Online) 2278- 5841 ISSN (Print) 2320- 5156 A Novel Image Classification System Based on Evidence Probabilistic Transformation Department of Computer Science, Mansoura University, Mansoura 35516, Egypt A.E. Amin information different identity paper evidence" 051a84f0e39126c1ebeeb379a405816d5d06604d,Biometric Recognition Performing in a Bioinspired System,"Cogn Comput (2009) 1:257–267 DOI 10.1007/s12559-009-9018-7 Biometric Recognition Performing in a Bioinspired System Joan Fa`bregas Æ Marcos Faundez-Zanuy Published online: 20 May 2009 Ó Springer Science+Business Media, LLC 2009" 058f053f0c0d8359b236e8fb17d541226d74a70d,Probabilistic Semi-Supervised Multi-Modal Hashing,"STUDENT, PROF, COLLABORATOR: BMVC AUTHOR GUIDELINES Probabilistic Semi-Supervised Multi-Modal Hashing Behnam Gholami Abolfazl Hajisami Computer Science Department Rutgers, The state university of New Jersey, New Brunswick, NJ, USA Department of Electrical and Computer Engineering Rutgers, The state university of New Jersey, New Brunswick, NJ, USA" 05bd3ebba35a683e5035a3920352bc7aec85bd78,License Plate Detection on Autonomous Surveillance Systems,"Journal of Computational Information Systems 6:14 (2010) 4941-4949 Available at http://www.Jofcis.com License Plate Detection on Autonomous Surveillance Systems YaoHong TSAI†, KungChun KAO Department of Information Management, Hsuan Chung University, Hsinchu City, Taiwan" 05a7be10fa9af8fb33ae2b5b72d108415519a698,Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification,"Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Xiaodong Yang Pavlo Molchanov Jan Kautz {xiaodongy, pmolchanov, NVIDIA" 056be8a896f71be4a1dee67b01f4d59e3e982304,Generative Models of Visually Grounded Imagination,"Published as a conference paper at ICLR 2018 GENERATIVE MODELS OF VISUALLY GROUNDED IMAGINATION Ramakrishna Vedantam∗ Georgia Tech Ian Fischer Google Inc. Jonathan Huang Google Inc. Kevin Murphy Google Inc." 05ce73c39368aca1d10ab48dbe0dee80ee084bdb,M ULTI-LABEL L EARNING WITH THE RNN S FOR F ASHION S EARCH,"Under review as a conference paper at ICLR 2017 MULTI-LABEL LEARNING WITH THE RNNS FOR FASHION SEARCH Se-Yeoung Kim, Sang-Il Na, Ha-Yoon Kim, Moon-Ki Kim, Byoung-Ki Jeon Machine Intelligence Lab., SK Planet Seongnam City, South Korea Taewan Kim ∗ Naver Labs, Naver Corp. Seongnam City, South Korea" 05a2547d976420f7d1de19907e16280d15199008,Semantic Road Layout Understanding by Generative Adversarial Inpainting,"Road layout understanding by generative dversarial inpainting Lorenzo Berlincioni, Federico Becattini, Leonardo Galteri, Lorenzo Seidenari, Alberto Del Bimbo" 056e2c82db905b93f7762a2ee7778d3aacc5a1f0,Bag of Attributes for Video Event Retrieval,"Bag of Attributes for Video Event Retrieval Leonardo A. Duarte1, Ot´avio A. B. Penatti2, and Jurandy Almeida1 Institute of Science and Technology Federal University of S˜ao Paulo – UNIFESP 2247-014, S˜ao Jos´e dos Campos, SP – Brazil Email: {leonardo.assuane, Advanced Technologies SAMSUNG Research Institute 3097-160, Campinas, SP – Brazil Email:" 05e03c48f32bd89c8a15ba82891f40f1cfdc7562,Scalable Robust Principal Component Analysis Using Grassmann Averages,"Scalable Robust Principal Component Analysis using Grassmann Averages Søren Hauberg, Aasa Feragen, Raffi Enficiaud, and Michael J. Black" 05ad478ca69b935c1bba755ac1a2a90be6679129,Attribute Dominance: What Pops Out?,"Attribute Dominance: What Pops Out? Naman Turakhia Georgia Tech" 050a149051a5d268fcc5539e8b654c2240070c82,Magisterské a doktorské studijnı́ programy,MAGISTERSKÉ A DOKTORSKÉSTUDIJNÍ PROGRAMY31. 5. 2018SBORNÍKSTUDENTSKÁ VĚDECKÁ KONFERENCE 052880031be0a760a5b606b2ad3d22f237e8af70,Datasets on object manipulation and interaction: a survey,"Datasets on object manipulation and interaction: a survey Yongqiang Huang and Yu Sun" 05a22ebec697cfa5e8e2883d68e6f4762bbdebd7,Few-Example Object Detection with Model Communication.,"Few-Example Object Detection with Model Communication Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng" 056892b7e573608e64c3c9130e8ce33353a94de2,Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform,"Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs nd a Discriminatively Trained Domain Transform Liang-Chieh Chen∗ Jonathan T. Barron, George Papandreou, Kevin Murphy {barron, gpapan, Alan L. Yuille" 051830b0ea58d1568f19ec3297e301d9789c9a76,Bringing Semantics into Focus Using Visual Abstraction, 05a35959c6822155bee927305e799613ce99cc2f,New valve and bonding designs for microfluidic biochips containing proteins.,"Research - Articles Digest Research Volume 5 Issue 9 - September 26, 2008 [ http://research.ncku.edu.tw/re/articles/e/20080926/1.html ] New Valve and Bonding Designs for Microfluidic Biochips Containing Proteins Yi-Je Juang Assistant Professor of Department of Chemical Engineering, College of Engineering, National Cheng Kung University Polymer-based microfluidic biochips have great potential to serve as low- ost and easy-to-fabricate analytical tools in clinical applications. One of the ritical components on microfluidic biochips is valving for fluid manipulation. There are both active and passive valve designs. The examples of the active valves include thermally actuated gels, magnetically actuated ferrofluid or monoliths, pneumatically controlled membranes, and controlled surface wetting. Most of the active valves require a mobile part or external stimuli, which limits their applications in microfluidics when the devices become smaller and need to be low cost. The passive valves provide a more affordable lternative to control the liquid flow because no moving parts are required. They include capillary valves, polymer check valves, elastomer valves, and hydrophobic valves. Among them, the apillary valve is the most popular due to its simplicity and easy implementation into the microfluidic design and" 0559fb9f5e8627fecc026c8ee6f7ad30e54ee929,4 Facial Expression Recognition,"Facial Expression Recognition Bogdan J. Matuszewski, Wei Quan and Lik-Kwan Shark ADSIP Research Centre, University of Central Lancashire . Introduction Facial expressions are visible signs of a person’s affective state, cognitive activity and personality. Humans can perform expression recognition with a remarkable robustness without conscious effort even under a variety of adverse conditions such as partially occluded faces, different appearances and poor illumination. Over the last two decades, the dvances in imaging technology and ever increasing computing power have opened up a possibility of automatic facial expression recognition and this has led to significant research efforts from the computer vision and pattern recognition communities. One reason for this growing interest is due to a wide spectrum of possible applications in diverse areas, such as more engaging human-computer interaction (HCI) systems, video conferencing, augmented reality. Additionally from the biometric perspective, automatic recognition of facial expressions has been investigated in the context of monitoring patients in the intensive care nd neonatal units for signs of pain and anxiety, behavioural research, identifying level of oncentration, and improving face recognition. Automatic facial expression recognition is a difficult task due to its inherent subjective nature, which is additionally hampered by usual difficulties encountered in pattern recognition and computer vision research. The vast majority of the current state-of-the-art" 0534304bc09e92b2cfa0a8da59cfcf0be84d70a4,Towards reliable real-time person detection,"Towards Reliable Real-Time Person Detection Silviu-Tudor SERBAN1, Srinidhi MUKANAHALLIPATNA SIMHA1, Vasanth BATHRINARAYANAN1, Etienne CORVEE1 and Francois BREMOND1 INRIA Sophia Antipolis - Mediterranee, 2004 route des Lucioles, Sophia Antipolis, France {silviu-tudor.serban,srinidhi.mukanahallipatna Keywords: Random sampling, Adaboost, Soft cascade, LBP channel features" 05ef5efd9e42f49dbb9e50ec3fe367f275a94931,Biologically Inspired Processing for Lighting Robust Face Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 051aa14e0b7dd4231636db39398c0c15b2687682,Robust Subspace Clustering via Thresholding,"Robust Subspace Clustering via Thresholding Reinhard Heckel and Helmut B¨olcskei Dept. of IT & EE, ETH Zurich, Switzerland July 2013; last revised August 2015" 050fdbd2e1aa8b1a09ed42b2e5cc24d4fe8c7371,Spatio-Temporal Scale Selection in Video Data,"Contents Scale Space and PDE Methods Spatio-Temporal Scale Selection in Video Data . . . . . . . . . . . . . . . . . . . . . Tony Lindeberg Dynamic Texture Recognition Using Time-Causal Spatio-Temporal Scale-Space Filters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Ylva Jansson and Tony Lindeberg Corner Detection Using the Affine Morphological Scale Space . . . . . . . . . . . Luis Alvarez Nonlinear Spectral Image Fusion. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Martin Benning, Michael Möller, Raz Z. Nossek, Martin Burger, Daniel Cremers, Guy Gilboa, and Carola-Bibiane Schönlieb Tubular Structure Segmentation Based on Heat Diffusion. . . . . . . . . . . . . . . Fang Yang and Laurent D. Cohen Analytic Existence and Uniqueness Results for PDE-Based Image Reconstruction with the Laplacian . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Laurent Hoeltgen, Isaac Harris, Michael Breuß, and Andreas Kleefeld Combining Contrast Invariant L1 Data Fidelities with Nonlinear Spectral Image Decomposition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Leonie Zeune, Stephan A. van Gils, Leon W.M.M. Terstappen," 05e658fed4a1ce877199a4ce1a8f8cf6f449a890,Domain Transfer Learning for Object and Action Recognition, 05ea7930ae26165e7e51ff11b91c7aa8d7722002,Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation,"Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation Tianfu Wu∗, Bo Li∗ and Song-Chun Zhu" 05a2e6a5240b77246e26ba9875213c3157cb2fca,Zero-Shot Event Detection Using Multi-modal Fusion of Weakly Supervised Concepts,"Zero-shot Event Detection using Multi-modal Fusion of Weakly Supervised Concepts Shuang Wu†, Sravanthi Bondugula‡, Florian Luisier†, Xiaodan Zhuang† and Pradeep Natarajan†∗ Speech, Language and Multimedia Raytheon BBN Technologies, Cambridge, MA" 05fcbe4009543ec8943bdc418ee81e9594b899a4,Social perception in autism spectrum disorders: impaired category selectivity for dynamic but not static images in ventral temporal cortex.,"doi:10.1093/cercor/bhs276 Social Perception in Autism Spectrum Disorders: Impaired Category Selectivity for Dynamic but not Static Images in Ventral Temporal Cortex Jill Weisberg1, Shawn C. Milleville1, Lauren Kenworthy1,2, Gregory L. Wallace1, Stephen J. Gotts1, Michael S. Beauchamp3 and Alex Martin1 NIMH, Laboratory of Brain and Cognition, Bethesda, MD 20850, 2Children’s National Medical Center, Center for Autism Spectrum Disorders, Rockville, MD 20850 and 3Department of Neurobiology and Anatomy, University of Texas Medical School t Houston, Houston, TX 77030, USA Address correspondence to Jill Weisberg, San Diego State University Research Foundation, Laboratory for Language and Cognitive Neuroscience, 6495 Alvarado Rd, Suite 200, San Diego, CA 92120, USA. Email: Studies of autism spectrum disorders (ASDs) reveal dysfunction in the neural systems mediating object processing (particularly faces) nd social cognition, but few investigations have systematically as- sessed the specificity of the dysfunction. We compared cortical responses in typically developing adolescents and those with ASD to stimuli from distinct conceptual domains known to elicit cat- egory-related activity in separate neural systems. In Experiment 1, subjects made category decisions to photographs, videos, and point-light displays of people and tools. In Experiment 2, subjects interpreted displays of simple, geometric shapes in motion depicting" 0582d338a5e5b325c282e2ff13bfd62cf4d08108,Affordance Research in Developmental Robotics: A Survey,"Affordance Research in Developmental Robotics: A Survey Huaqing Min, Chang’an Yi, Ronghua Luo, Jinhui Zhu, and Sheng Bi apture" edceeaa885f3eb29761580095059f8a34be8408b,Training data ... ... 0 1 1 0 1 0 0 1 Convolution and pooling layers fc layers Hashing layer Regularized center loss Bike Car Bird Dicycle Semantic embedding loss,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) ModelSimilar?Figure1:Zero-shothashing.Thehashingmodeltrainedwithseenconceptsshouldgeneralizewellontheunseenconcepts.supervisedhashinglikeSupervisedDiscreteHashing[Shenetal.,2015a].Withthesupervisedinformationlikesemanticsimilaritymatrixorclasslabels,thesupervisedapproachesachievesuperiorretrievalperformancebecausetheintrinsicsemanticpropertyinthedataisbetterexplored.Recentlythedeepconvolutionalneuralnetwork(CN-N)hasachievedgreatsuccessinmanycomputervisiontasks,likeimageclassification[Heetal.,2016]andfacerecognition[Wenetal.,2016].InspiredbyCNN’spower-fulfeatureextractionability,someworkshaveattemptedtobuildhashingmodelsbasedonCNN[Laietal.,2015;Liuetal.,2016;Xiaetal.,2014]haveappeared.Theyre-quirethehashcodesproducedbythelastfullyconnectedlay-ertopreservethesimilaritygivenbythesupervisedinfor-mation.ItisdemonstratedthattheimageretrievalaccuracyissignificantlyimprovedbyCNN-basedhashingapproachescomparedwiththenon-CNNones[Liuetal.,2016].Itshouldbenoticedthattheexistinghashingapproachesmainlyfocusontheclose-setretrieval,i.e.,theconceptsofpossibletestingsamples(bothdatabasesamplesandquerysamples)arewithinthetrainingset.However,theexplosivegrowthofWebimagesviolatesthissettingbecausethenewconceptsabouttheimagesmayemergerapidly.Itisexpen-sivetoannotatesufficienttrainingdataforthenewconcept-stimely,andalso,impracticaltoretrainthehashingmodelwhereastheretrievalsystemmeetsanewconcept.Asillus-tratedinFigure1,theexistingapproachesperformwellontheseenconceptsbecausetheyaregivencorrectguidance,buttheymayeasilyfailontheunseenconceptsthattheynev-ermeetbeforesuchasthe“dicycle”whichisakindofvehicle" ed2420d0fc7087d61633bd9a5b2907d1c2de1810,3 D Facial symmetry evaluation from high – density scanned data, ed28e8367fcb7df7e51963add9e2d85b46e2d5d6,A NOVEL APPROACH OF FACE RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS WITH AUTO ENCODER,"International J. of Engg. Research & Indu. Appls. (IJERIA). ISSN 0974-1518, Vol.9, No. III (December 2016), pp.23-42 A NOVEL APPROACH OF FACE RECOGNITION USING CONVOLUTIONAL NEURAL NETWORKS WITH AUTO ENCODER T. SYED AKHEEL1 AND DR. S. A. K JILANI2 Research Scholar, Dept. of Electronics & Communication Engineering, Rayalaseema University Kurnool, Andhra Pradesh. 2 Research Supervisor, Professor, Dept. of Electronics & Communication Engineering, Madanapalle Institute of Technology & Science, Madanapalle, Andhra Pradesh." edbfbcebb14234b438d90d6dcd9b667e9071952d,Learning Fashion Compatibility with Bidirectional LSTMs,"A.B.C.D.?Task 1: Fill in the blankTask 2: Outfit generation given texts or imagesWhat to dress for a biz meeting?(a)(b)Task 3: Compatibility predictionScore: 0.7Figure1:Wefocusonthreetasksoffashionrecommenda-tion.Task1:recommendingafashionitemthatmatchesthestyleofanexistingset.Task2:generatinganoutfitbasedonusers’text/imageinputs.Task3:predictingthecompatibil-ityofanoutfit.conductedonautomaticfashionanalysisinthemultimediacom-munity.However,mostofthemfocusonclothingparsing[9,26],clothingrecognition[12],orclothingretrieval[10].Although,thereareafewworksthatinvestigatedfashionrecommendation[6,8,10],theyeitherfailtoconsiderthecompositionofitemstoformanout-fit[10]oronlysupportoneofthetworecommendationcategoriesdiscussedabove[6,8].Inaddition,itisdesirablethatrecommenda-tionscantakemultimodalinputsfromusers.Forexample,ausercanprovidekeywordslike“business”,oranimageofabusinessshirt,oracombinationofimagesandtext,togenerateacollec-tionoffashionitemsforabusinessoccasion.However,nopriorapproachsupportsmultimodalinputsforrecommendation.Keytofashionrecommendationismodelingthecompatibilityoffashionitems.Wecontendthatacompatibleoutfit(asshowninFigure3)shouldhavetwokeyproperties:(1)itemsintheout-fitshouldbevisuallycompatibleandsharesimilarstyle;(2)these" ed6801362ab442097e7f753f163b9e9c0584b257,2 D TO 3 DCONVERSION BASED ON GLOBAL METHOD OF DEPTH LEARNING WITH INPUT IMAGE DENOISING,"International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 – 0882 Volume 4, Issue 5, May 2015 Learning Based 2D to 3D Conversion with Input Image Denoising Divya K.P.1, Sneha K.2, Nafla C.N.3 (Department of CSE, RCET, Akkikkvu, Thrissur) (Asst. Professor, Department of CSE, RCET, Akkikkvu, Thrissur) (Department of CSE, RCET, Akkikkvu, Thrissur)" ed07fa6df6a8fc27015d25717c9f730dc9eede84,of the 19 th Workshop on the Semantics and Pragmatics of Dialogue,"SEMDIAL 2015 goDIAL Proceedings of the 19th Workshop on the Semantics and Pragmatics of Dialogue Christine Howes and Staffan Larsson (eds.) Gothenburg, 24–26 August 2015" ed5519a03f52e47047079da2e0c480eb8c4a9805,An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark,"An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark. Stefan Becker ∗, Ronny Hug ∗, Wolfgang H¨ubner and Michael Arens Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation IOSB Gutleuthausstr. 1, 76275 Ettlingen, Germany" ed90a9d379f6412a1580e7eda5cb91640000dc42,Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe,"Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe Jiong Gong, Haihao Shen, Guoming Zhang, Xiaoli Liu, Shane Li, Ge Jin, Niharika Maheshwari, Evarist Fomenko, Eden Segal {jiong.gong, haihao.shen, guoming.zhang, xiaoli.liu, li.shane, ge.jin, niharika.maheshwari, evarist.m.fomenko, Intel Corporation" ed9967868fcca2ec38402d2bb3e6946b8e554472,Efficient Eye Location for Biomedical Imaging using Two-level Classifier Scheme,"International Journal of Control, Automation, and Systems, vol. 6, no. 6, pp. 828-835, December 2008 Efficient Eye Location for Biomedical Imaging using Two-level Classifier Scheme Mi Young Nam, Xi Wang, and Phill Kyu Rhee*" edcf668846a3aaf55120aef0c806854936208b3d,Human Recognition in RGBD Combining Object Detectors and Conditional Random Fields, ed732b3a1f8fe733686a35688b090f426d018f9b,Dual-Process Theories in Social Cognitive Neuroscience,"This article was originally published in Brain Mapping: An Encyclopedic Reference, published by Elsevier, and the attached copy is provided by Elsevier for the author's benefit and for the benefit of the author's institution, for non-commercial research and educational use including without limitation use in instruction at your institution, sending it to specific colleagues who you know, and providing a copy to your institution’s administrator. All other uses, reproduction and distribution, including without limitation ommercial reprints, selling or licensing copies or access, or posting on open internet sites, your personal or institution’s website or repository, are prohibited. For exceptions, permission may be sought for such use through Elsevier's permissions site at: http://www.elsevier.com/locate/permissionusematerial Spunt R.P. (2015) Dual-Process Theories in Social Cognitive Neuroscience. In: Arthur W. Toga, editor. Brain Mapping: An Encyclopedic Reference, vol. 3, pp. 11-215. Academic Press: Elsevier." edf074a5eb3a1f71cc710ccc42849dceb27e3531,Towards real-time unsupervised monocular depth estimation on CPU,"Towards real-time unsupervised monocular depth estimation on CPU Matteo Poggi1, Filippo Aleotti2, Fabio Tosi1, Stefano Mattoccia1" edc5c359ed0fc24a3e85628f57fde59cd9b26dd4,SEARCH SPACE OPTIMIZATION AND FALSE ALARM REJECTION FACE DETECTION FRAMEWORK,"Journal of Theoretical and Applied Information Technology 30th September 2015. Vol.79. No.3 © 2005 - 2015 JATIT & LLS. All rights reserved. ISSN: 1992-8645 www.jatit.org E-ISSN: 1817-3195 SEARCH SPACE OPTIMIZATION AND FALSE ALARM REJECTION FACE DETECTION FRAMEWORK ALI SHARIFARA, 2MOHD SHAFRY MOHD RAHIM, 3 HAMED SAYYADI, FARHAD NAVABIFAR ,2, Department of Computer Graphics and Multimedia, Faculty of Computing University Technology Malaysia (UTM).81310 Skudai Johor, Malaysia. Department of Computer Systems and Communications, Faculty of Computing University Technology Malaysia (UTM), 81310 Skudai Johor, Malaysia. Department of Computer Engineering Mobarakeh Branch-Islamic Azad University, Mobarakeh, Esfahan, E-mail: Iran." ed6a47f0e2e621d8420082ba1d0078189d76352f,3 D FACIAL EXPRESSION INTENSITY MEASUREMENT ANALYSIS,"Proceedings of the 6th International Conference on Computing and Informatics, ICOCI 2017 5-27April, 2017 Kuala Lumpur. Universiti Utara Malaysia (http://www.uum.edu.my ) Paper No. How to cite this paper: Alicia Cheong Chiek Ying, Hamimah Ujir, & Irwandi Hipiny. (2017). 3D facial expression intensity measurement nalysis in Zulikha, J. & N. H. Zakaria (Eds.), Proceedings of the 6th International Conference of Computing & Informatics (pp 43-48). Sintok: School of Computing. D FACIAL EXPRESSION INTENSITY MEASUREMENT ANALYSIS Alicia Cheong Chiek Ying1, Hamimah Ujir2and Irwandi Hipiny3 Sarawak Information Systems Sdn. Bhd. (SAINS), Universiti Malaysia Sarawak, Universiti Malaysia Sarawak," ed6003db58b67f1dfac654868b437efcef6e2ccb,Restricted Isometry Property of Gaussian Random Projection for Finite Set of Subspaces,"Restricted Isometry Property of Gaussian Random Projection for Finite Set of Subspaces Gen Li and Yuantao Gu∗ submitted April 7, 2017, revised August 11, 2017, accepted November 8, 2017" ed62a56b81511d7fcf6d247014987163d9668982,"""What happens if..."" Learning to Predict the Effect of Forces in Images","“What happens if...” Learning to Predict the Effect of Forces in Images Roozbeh Mottaghi1, Mohammad Rastegari1, Abhinav Gupta1,2, Ali Farhadi1,3 Allen Institute for AI, 2Carnegie Mellon University, 3University of Washington" ed04e161c953d345bcf5b910991d7566f7c486f7,Mirror my emotions ! Combining facial expression analysis and synthesis on a robot,"Combining facial expression analysis and synthesis on a Mirror my emotions! robot Stefan Sosnowski1 and Christoph Mayer2 and Kolja K¨uhnlenz3 and Bernd Radig4" ed3c4d2d28faaccbaef876a7daaecc3cccadb48f,3D Human Pose Estimation from a Single Image via Distance Matrix Regression,"D Human Pose Estimation from a Single Image via Distance Matrix Regression Institut de Rob`otica i Inform`atica Industrial (CSIC-UPC), 08028, Barcelona, Spain Francesc Moreno-Noguer" edef98d2b021464576d8d28690d29f5431fd5828,Pixel-Level Alignment of Facial Images for High Accuracy Recognition Using Ensemble of Patches,"Pixel-Level Alignment of Facial Images for High Accuracy Recognition Using Ensemble of Patches Hoda Mohammadzade, Amirhossein Sayyafan, Benyamin Ghojogh" ed38d22cd5558d1abb40b477027d52ff7b6d09db,SIMULTANEOUS MULTIVIEW FACE TRACKING AND RECOGNITION IN VIDEO USING PARTICLE FILTERING by Naotoshi Seo, ed510cce08500d8b3df23325ce122c76f3ddc11e,Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms,"Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms Zhihui Zhu MINDS Johns Hopkins University Yifan Wang ShanghaiTech University Daniel Robinson Johns Hopkins University Daniel Naiman Johns Hopkins University Rene Vidal MINDS Johns Hopkins University ShanghaiTech University Manolis C. Tsakiris" ed02b45d05e58803596891d660837c21be70a0af,Entity type modeling for multi-document summarization : generating descriptive summaries of geo-located entities,"Entity Type Modeling for Multi-Document Summarization: Generating Descriptive Summaries of Geo-Located Entities Ahmet Aker A thesis submitted in fulfilment of requirements for the degree of Doctor of Philosophy Department of Computer Science University of Sheffield November 2013" eda20a2f33d0f6db44a2e7d060efad3caa6621e0,"Classification with Global, Local and Shared Features","Classification with Global, Local and Shared Features Hakan Bilen1, Vinay P. Namboodiri2, Luc J. Van Gool1,3 ESAT-PSI/IBBT,VISICS/KU Leuven, Belgium Alcatel-Lucent Bell Labs, Antwerp, Belgium Computer Vision Laboratory, BIWI/ETH Z¨urich, Switzerland" eddb1a126eafecad2cead01c6c3bb4b88120d78a,Applications of a Graph Theoretic Based Clustering Framework in Computer Vision and Pattern Recognition,"DEPARTMENT DESIGN AND PLANNING IN COMPLEX ENVIRONMENTS DOTTORATO DI RICERCA IN NUOVE TECNOLOGIE, INFORMAZIONE TERRITORIO E UNIVERSIT‘A IUAV DI VENEZIA AMBIENTE, XXX CICLO APPLICATIONS OF A GRAPH THEORETIC BASED CLUSTERING FRAMEWORK IN COMPUTER VISION AND PATTERN RECOGNITION Doctoral Dissertation of: Yonatan Tariku Tesfaye Supervisor: Prof. Andrea Prati The Chair of the Doctoral Program: Prof. Fabio Peron" de0eb358b890d92e8f67592c6e23f0e3b2ba3f66,Inference-Based Similarity Search in Randomized Montgomery Domains for Privacy-Preserving Biometric Identification,"ACCEPTED BY IEEE TRANS. PATTERN ANAL. AND MACH. INTELL. Inference-Based Similarity Search in Randomized Montgomery Domains for Privacy-Preserving Biometric Identification Yi Wang, Jianwu Wan, Jun Guo, Yiu-Ming Cheung, and Pong C Yuen" de7daa206f1dc3d5f83c5342fc08e3e92ddfa126,Index Codes for Multibiometric Pattern Retrieval,"Index Codes for Multibiometric Pattern Retrieval Aglika Gyaourova, Student Member, IEEE, and Arun Ross, Senior Member, IEEE" de7a148970881cbd4e6a12b6a014e3dfeee98cc9,D4h: Final Report on Wp4,"D4h: Final report on WP4 Workpackage 4 Deliverable Date: 30th January 2008" de309a1d10f819d69a4ef2c26d968d3b287c3dd5,Preprocessing and Feature Sets for Robust Face Recognition,"Preprocessing and Feature Sets for Robust Face Recognition Xiaoyang Tan and Bill Triggs LJK-INRIA, 655 avenue de l’Europe, Montbonnot 38330, France" de595159fa9f8acbf99e4c39b935cf11cd64fde1,Object Detection with Bootstrapped Learning ∗,"Object Detection with Bootstrapped Learning ∗ Peter M. Roth* , Horst Bischof*, Danijel Skoˇcaj** and Aleˇs Leonardis** * Graz University of Technology, Institute for Computer Graphics and Vision Inffeldgasse 16/II, 8010 Graz, Austria ** University of Ljubljana, Faculty of Computer and Information Science Trˇzaˇska 25, SI-1001 Slovenia e-mail: {pmroth, {danijel.skocaj," de287480b9ab8dfab1c49e24e5517b0a3c55203b,A Tempt to Unify Heterogeneous Driving Databases using Traffic Primitives,"A Tempt to Unify Heterogeneous Driving Databases using Traffic Primitives Jiacheng Zhu1,Wenshuo Wang1, Ding Zhao1,∗" defa8774d3c6ad46d4db4959d8510b44751361d8,FEBEI-Face Expression Based Emoticon Identification CSB 657 Computer Vision,"FEBEI - Face Expression Based Emoticon Identification CS - B657 Computer Vision Nethra Chandrasekaran Sashikar - necsashi Prashanth Kumar Murali - prmurali Robert J Henderson - rojahend" de55bfc96b027b3e2bd44baed656a3f563ff6e71,"Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping","Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping Xianxu Hou, Jiang Duan, and Guoping Qiu" def3b2254caea169c5cbc4b771c44f1773c004fd,Matching Adversarial Networks,"Matching Adversarial Networks Gell´ert M´attyus and Raquel Urtasun Uber Advanced Technologies Group and University of Toronto" defcfed9c43bdf8a4388daade4899ef9d3345458,Sistema de reconocimiento multimodal de emociones relacionadas al aprendizaje en dispositivos móviles,"Sistema de reconocimiento multimodal de emociones relacionadas al aprendizaje en dispositivos móviles María Lucía Barrón-Estrada, Ramón Zatarain-Cabada, Claudia Guadalupe Aispuro-Gallegos Instituto Tecnológico de Culiacán, Culiacán, Sinaloa, México {lbarron, rzatarain, Resumen. Gran variedad de sistemas reconocedores de emociones han sido implementados, pero pocos han logrado aplicarse en el mundo real debido al elevado costo de la tecnología necesaria y al bajo porcentaje de efectividad del reconocimiento, cuando no se trabaja con emociones espontáneas. Este artículo presenta la implementación de un sistema de reconocimiento multimodal de emociones usando dispositivos móviles y la creación de una base de datos fectiva por medio de una aplicación móvil. El reconocedor puede ser integrado fácilmente a una aplicación educativa móvil para identificar las emociones de un usuario mientras éste interactúa con el dispositivo. Las emociones que el sistema reconoce son compromiso y aburrimiento. La base de datos afectiva fue creada on emociones espontáneas de estudiantes que interactuaron con una aplicación móvil educativa llamada Duolingo y una aplicación móvil recolectora de información llamada EmoData. El sistema desarrollado tiene un porcentaje de" de1505819e145b5c22a6e09002510413019f7228,DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment,"DeepFood: Deep Learning-based Food Image Recognition for Computer-aided Dietary Assessment Chang Liu1, Yu Cao1, Yan Luo1, Guanling Chen1, Vinod Vokkarane1, Yunsheng The University of Massachusetts Lowell, One University Ave, Lowell, MA, 01854, USA The University of Massachusetts Medical School, 419 Belmont Street, Worcester, MA, 01605, USA" de0aaf8c6b5dea97327e8ef8060d9a708bf564af,A Benchmark for Iris Location and a Deep Learning Detector Evaluation,"A Benchmark for Iris Location and a Deep Learning Detector Evaluation Evair Severo∗, Rayson Laroca∗, Cides S. Bezerra∗, Luiz A. Zanlorensi∗, Daniel Weingaertner∗, Gladston Moreira† and David Menotti∗ Postgraduate Program in Informatics, Federal University of Paran´a (UFPR), Curitiba, Paran´a, Brazil Computing Department, Federal University of Ouro Preto (UFOP), Ouro Preto, Minas Gerais, Brazil Email: {ebsevero, rblsantos, csbezerra, lazjunior, daniel," dee406a7aaa0f4c9d64b7550e633d81bc66ff451,Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning,"Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning Dongyu Zhang, Liang Lin, Tianshui Chen, Xian Wu, Wenwei Tan, and Ebroul Izquierdo" de2aaabc3fcc21042a64dc266f560dad91028b79,Energy-Aware real-time face recognition system on mobile CPU-GPU platform,"Energy-Aware Real-time Face Recognition System on Mobile CPU-GPU Platform Yi-Chu Wang, Bryan Donyanavard, Kwang-Ting (Tim) Cheng Dept. of Electrical and Computer Engineering University of California, Santa Barbara, CA 93106, USA" debbf2f0f9ae128e40e962bef5096adacd1cb264,Who Are You?,"Who Are You? Modesto Castrill´on-Santana IUSIANI Univ. de Las Palmas de G.C. 5017 Spain Enrico Grosso DEIR - Univ. of Sassari, Via Sardegna, 58 07100 Sassari, Italy Oscar D´eniz-Su´arez IUSIANI Univ. de Las Palmas de G. C. 5017 Spain" de7bbb79384f81d0b3d28aa6531273ce240553c3,Using 3 D Graphics to Train Object Detection Systems,"Using 3D Graphics to Train Object Detection Systems Stian Jensen Andreas Løve Selvik Master of Science in Computer Science Submission date: July 2016 Supervisor: Donn Morrison, IDI Norwegian University of Science and Technology Department of Computer and Information Science" ded968b97bd59465d5ccda4f1e441f24bac7ede5,Large scale 3 D Morphable Models,"Noname manuscript No. (will be inserted by the editor) Large scale 3D Morphable Models James Booth · Anastasios Roussos · Allan Ponniah · David Dunaway · Stefanos Zafeiriou Received: date / Accepted: date" de87a5d5fbae0733806ba965b2d70fd04596f6e9,Optimization-Based Motion Planning and Model Predictive Control for Autonomous Driving,"Predictive control for autonomous driving with experimental evaluation on a heavy-duty construction truck PEDRO F. LIMA Licenciate Thesis Stockholm, Sweden 2016" dea749f087a8c9a9baa9167b4eaff50bd3eb9d16,Physically Grounded Spatio-temporal Object Affordances,"Physically Grounded Spatio-Temporal Object Affordances Hema S. Koppula and Ashutosh Saxena Department of Computer Science, Cornell University." de99971e61613f174c9e5aa41a2c600399f59953,Pixel-wise Attentional Gating for Scene Parsing,"Pixel-wise Attentional Gating for Scene Parsing Department of Computer Science, University of California, Irvine, CA 92697, USA Shu Kong, Charless Fowlkes {skong2," de6ab8cd9d402c976082b707b1207c3ad49ae204,End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space,"MADHYASTHA ET AL.: IMAGE CAPTIONING EXPLOITS DISTRIBUTIONAL SIMILARITY 1 End-to-end Image Captioning Exploits Multimodal Distributional Similarity Pranava Madhyastha Josiah Wang Lucia Specia Department of Computer Science The University of Sheffield Sheffield, UK" dedbbb6e588e77969ab87571917d4f84a3b1722d,Multimodal Human-Human-Robot Interactions ( MHHRI ) Dataset for Studying Personality and Engagement,"JOURNAL OF IEEE TRANS. ON AFFECTIVE COMPUTING Multimodal Human-Human-Robot Interactions (MHHRI) Dataset for Studying Personality and Engagement Oya Celiktutan, Efstratios Skordos and Hatice Gunes" de724211683bb92931a5d80193e5dee31ca2e045,Sampling Design For Face Recognition,"Sampling Design For Face Recognition Yanjun Yan and Lisa A. Osadciw EECS, Syracuse University, Syracuse, NY, USA {yayan," de2faaee4f1b2ecf23149995d0146347a13b9257,Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment,"Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment Werner Zellingera,∗, Bernhard A. Moserb, Thomas Grubingerb, Edwin Lughofera, Thomas Natschl¨agerb, Susanne Saminger-Platza Johannes Kepler University, Linz, Austria Software Competence Center Hagenberg GmbH, Hagenberg, Austria" de86a9f484addcfee57a6f5a9224aa77bd23345b,Face Recognition Using Elastic Bunch Graph Matching,"International Journal For Technological Research In Engineering Volume 2, Issue 11, July-2015 ISSN (Online): 2347 - 4718 FACE RECOGNITION USING ELASTIC BUNCH GRAPH MATCHING Sandeep R1, D Jayakumar2 Dept. of ECE, Kuppam Engineering College, Chittoor, Andhra Pradesh." de26c1560db47f63ef2dc8171d7c2c52369ffede,Mathematically inspired approaches to face recognition in uncontrolled conditions : super resolution and compressive sensing,"MATHEMATICALLY INSPIRED APPROACHES TO FACE RECOGNITION IN UNCONTROLLED CONDITIONS - SUPER RESOLUTION AND COMPRESSIVE SENSING NADIA AL-HASSAN Applied Computing Department The University of Buckingham / United Kingdom A Thesis Submitted for the Degree of Doctor of Philosophy in Mathematical Science to the school of Science and Medicine in the University of Buckingham September 2014" dedabf9afe2ae4a1ace1279150e5f1d495e565da,Robust Face Recognition With Structurally Incoherent Low-Rank Matrix Decomposition,"Robust Face Recognition With Structurally Incoherent Low-Rank Matrix Decomposition Chia-Po Wei, Chih-Fan Chen, and Yu-Chiang Frank Wang" de741378150a3a841756973d262541018d0acbcd,Learning to Detect Objects with Minimal Supervision,"Learning to Detect Objects with Minimal Supervision Karim Ali Computer Vision Laboratory ´Ecole Polytechnique F´ed´erale de Lausanne A thesis submitted for the degree of Ph.D. December 2011" 6601a0906e503a6221d2e0f2ca8c3f544a4adab7,Detection of Ancient Settlement Mounds : Archaeological Survey Based on the SRTM Terrain Model,"SRTM-2 2/9/06 3:27 PM Page 321 Detection of Ancient Settlement Mounds: Archaeological Survey Based on the SRTM Terrain Model B.H. Menze, J.A. Ur, and A.G. Sherratt" 66f8115136a11684e3b95c5aaa1476a871d58a66,Face Recognition Using Multiple Image View Line Segments Title Face Recognition Using Multiple Image View Line Segments Primary Author(s) Date,"JAMESCOOKUNIVERSITY FaceRecognitionusingMultiple ImageViewLineSegments StefanAeberhardandOlivierdeVel TR / DEPARTMENTOFCOMPUTERSCIENCETOWNSVILLE QUEENSLAND AUSTRALIA" 669727b3258bb3edc38709147f348dc67e3fcac4,A Lightweight approach for biometric template protection,"A Lightweight approach for biometric template protection* Hisham Al-Assam, Harin Sellahewa, & Sabah Jassim University of Buckingham, Buckingham MK18 1EG, U.K. {hisham.al-assam , harin.sellahewa," 66d512342355fb77a4450decc89977efe7e55fa2,LEARNING NON-LINEAR TRANSFORM WITH DISCRIM- INATIVE AND MINIMUM INFORMATION LOSS PRIORS,"Under review as a conference paper at ICLR 2018 LEARNING NON-LINEAR TRANSFORM WITH DISCRIM- INATIVE AND MINIMUM INFORMATION LOSS PRIORS Anonymous authors Paper under double-blind review" 66d087f3dd2e19ffe340c26ef17efe0062a59290,Dog Breed Identification,"Dog Breed Identification Whitney LaRow Brian Mittl Vijay Singh" 66533107f9abdc7d1cb8f8795025fc7e78eb1122,Visual Servoing for a User's Mouth with Effective Intention Reading in a Wheelchair-based Robotic Arm,"Vi a Sevig f a Ue  h wih E(cid:11)ecive ei Readig i a Wheechai baed Rbic A W y g Sgy Dae i iy g S g iz ad Ze ga Biey y EECS AST 373 1  g Dg Y g G  Taej 305 701 REA z VR Cee ETR 161 ajg Dg Y g G  Taej 305 350 REA Abac Thee exi he c eaive aciviy bewee a h a beig ad ehabiiai b beca e he h a eae ehabiiai b i he ae evi e ad ha he bee(cid:12) f ehabiiai b  ch a ai ay  bie f ci. ei eadig i e f he eeia f ci f h a fiedy ehabiiai b i de  ie he f ad afey f a wh eed he. Fi f  he vea  c e f a ew wheechai baed bic a ye ARES  ad i h a b ieaci echgie ae eeed. Ag he echgie we cceae  vi a evig ha w hi bic a  eae a  y via vi a feedback. E(cid:11)ecive iei eadig  ch a" 66c792b7e9946f8cb92fac185267d03371437451,Adaptive Affinity Fields for Semantic Segmentation,"Adaptive Affinity Fields for Semantic Segmentation Tsung-Wei Ke*, Jyh-Jing Hwang*, Ziwei Liu, and Stella X. Yu UC Berkeley / ICSI" 66a9935e958a779a3a2267c85ecb69fbbb75b8dc,Fast and Robust Fixed-Rank Matrix Recovery,"FAST AND ROBUST FIXED-RANK MATRIX RECOVERY Fast and Robust Fixed-Rank Matrix Recovery German Ros*, Julio Guerrero, Angel Sappa, Daniel Ponsa and Antonio Lopez" 66884ce29c44dc1dcf1c4a40180cd3baacceaabe,Face Recognition Algorithm Based on Doubly Truncated Gaussian Mixture Model Using Hierarchical Clustering Algorithm,"Face Recognition Algorithm Based on Doubly Truncated Gaussian Mixture Model Using Hierarchical Clustering Algorithm D. Haritha1, K. Srinivasa Rao2 and Ch.Satyanaraya3 1 Department of Computer Science and Engineering, University College of Engineering, JNTU, Kakinada, Andhra Pradesh, India. Department of Statistics, Andhra University, Visakhapatnam, Andhra Pradesh, India. Department of Computer Science and Engineering, University College of Engineering, JNTU, Kakinada, Andhra Pradesh, India." 6668ca5ab57d68070f90671a4f92a6bc25f80470,Measuring cues for stand-off deception detection based on full-body non-verbal features in body-worn cameras,"Measuring cues for stand-off deception detection based on full-body non-verbal features in body-worn cameras Henri Bouma 1, Gertjan Burghouts, Richard den Hollander, Sophie Van Der Zee, Jan Baan, Johan-Martijn ten Hove, Sjaak van Diepen, Paul van den Haak, Jeroen van Rest TNO, Oude Waalsdorperweg 63, 2597 AK The Hague, The Netherlands" 66a2c229ac82e38f1b7c77a786d8cf0d7e369598,A Probabilistic Adaptive Search System for Exploring the Face Space,"Proceedings of the 2016 Industrial and Systems Engineering Research Conference H. Yang, Z. Kong, and MD Sarder, eds. A Probabilistic Adaptive Search System for Exploring the Face Space Andres G. Abad and Luis I. Reyes Castro Escuela Superior Politecnica del Litoral (ESPOL) Guayaquil-Ecuador" 66c0fcf637bede76a6ea61b58655c5fc7e890630,IMPROVING THE GENERALIZATION OF NEURAL NETWORKS BY CHANGING THE STRUCTURE OF ARTIFICIAL NEURON,"Improving the Generalization of Neural Networks by Changing the Structure of Artificial Neuron. pp 195-204 IMPROVING THE GENERALIZATION OF NEURAL NETWORKS BY CHANGING THE STRUCTURE OF ARTIFICIAL NEURON Mohammad Reza Daliri1, Mehdi Fatan2 Biomedical Engineering Department and Iran Neural Technology Center, Faculty of Electrical Engineering, Iran University of Science and Technology (IUST), Narmak, 16846-13114 Tehran, Iran (Email: Mechatronics Group, Faculty of Electrical Engineering, Qazvin Islamic Azad University, Qazvin, Iran (Email: Corresponding author: M.R. Daliri, Email:" 6618cff7f2ed440a0d2fa9e74ad5469df5cdbe4c,Ordinal Regression with Multiple Output CNN for Age Estimation,"Ordinal Regression with Multiple Output CNN for Age Estimation Zhenxing Niu1 Gang Hua3 Xidian University 2Xi’an Jiaotong University 3Microsoft Research Asia Xinbo Gao1 Mo Zhou1 Le Wang2" 66f9e488496fafe853f49f834b8041740ac82926,Moving towards in object recognition with deep learning for autonomous driving applications,"Moving Towards in Object Recognition with Deep Learning for Autonomous Driving Applications Ay(cid:250)egül Uçar, Yakup Demir Department of Mechatronic Engineering, Elaz(cid:213)(cid:247), Turkey Department of Electrical Electronics Engineering, Elaz(cid:213)(cid:247), Turkey" 66af2afd4c598c2841dbfd1053bf0c386579234e,Context-assisted face clustering framework with human-in-the-loop,"Noname manuscript No. (will be inserted by the editor) Context Assisted Face Clustering Framework with Human-in-the-Loop Liyan Zhang · Dmitri V. Kalashnikov · Sharad Mehrotra Received: date / Accepted: date" 66c92c9145c2b6a304eb1b3a58e2a717884fe064,Emotions in Pervasive Computing Environments,"IJCSI International Journal of Computer Science Issues, Vol. 6, No. 1, 2009 ISSN (Online): 1694-0784 ISSN (Print): 1694-0814 Emotions in Pervasive Computing Environments Nevin VUNKA JUNGUM1 and Éric LAURENT2 1 Computer Science and Engineering Department, University of Mauritius Réduit, Mauritius Laboratoire de Psychologie, ENACT-MCA, University of Franche-Comté Besançon, France" 668e93e89835ec662d21cf695b7347339ce74c78,LIKELIHOOD RATIO FUSION WITHIN SCORES OF INDEPENDENT COMPONENT ANALYSIS FEATURES BASED FACE BIOMETRICS VERIFICATION SYSTEMS,"June. 2015. Vol. 6, No.3 ISSN 2305-1493 International Journal of Scientific Knowledge Computing and Information Technology © 2012 - 2015 IJSK & K.A.J. All rights reserved www.ijsk.org/ijsk LIKELIHOOD RATIO FUSION WITHIN SCORES OF INDEPENDENT COMPONENT ANALYSIS FEATURES BASED FACE BIOMETRICS VERIFICATION SYSTEMS SOLTANE MOHAMED Electrical Engineering & Computing Department, Faculty of Sciences & Technology, DOCTOR YAHIA FARES UNIVERSITY OF MEDEA, 26000 MEDEA, ALGERIA Laboratoire des Systèmes Électroniques Avancées (LSEA)" 661be86559295d3b2cbabcd31cc90848f601f55c,Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks,"Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks The Chinese University of Hong Kong 2SenseTime Group Limited 3Nanyang Technological University Yuenan Hou1, Zheng Ma2, Chunxiao Liu2, and Chen Change Loy3 {mazheng," 666e08b6921a28fed75f35dd70d322f0edc06e41,Rain Removal in Traffic Surveillance: Does it Matter?,"IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS Rain Removal in Traffic Surveillance: Does it Matter? Chris H. Bahnsen nd Thomas B. Moeslund" 66e21b99ae3aeae79589d260e3daca3b04981a9c,MULTI-AGENT APPROACH TOWARDS FACE RECOGNITION,"http://www.ijccr.com VOLUME 1 ISSUE 3 MANUSCRIPT 10 NOVEMBER 2011 MULTI-AGENT APPROACH TOWARDS FACE RECOGNITION" 66ee33bf0064eee159f3563e32b15c5bbd4140a0,Face Recognition Under Varying Viewing Conditions with Subspace Distance,"Face Recognition Under Varying Viewing Conditions with Subspace Distance Jen-Mei Chang Department of Mathematics and Statistics California State University, Long Beach 250 Bellflower Blvd. Long Beach, California 90840-1001" 66e2c3d23af8ed76b116121827b9bc5e99cf4acc,Video Prediction with Appearance and Motion Conditions,"Video Prediction with Appearance and Motion Conditions Yunseok Jang 1 2 Gunhee Kim 2 Yale Song 3" 6624e30564908c233bfa45c3503ec8aff741515e,Nearest-Neighbors Based Weighted Method for the BOVW Applied to Image Classification,"J Electr Eng Technol.2015; 10(?): 709-718 http://dx.doi.org/10.5370/JEET.2015.10.?.709 ISSN(Print) 1975-0102 ISSN(Online) 2093-7423 Nearest-Neighbors Based Weighted Method for the BOVW Applied to Image Classification Mengxi Xu*,**, Quansen Sun†, Yingshu Lu*** and Chenming Shen**" 660c8a9fa166c1d81e65192e011eacfec208ec00,Discrimination of visual pedestrians data by combining projection and prediction learning,"Discrimination of visual pedestrians data by combining projection and prediction learning Mathieu Lefort, Alexander Gepperth To cite this version: Mathieu Lefort, Alexander Gepperth. Discrimination of visual pedestrians data by combining projection and prediction learning. ESANN - European Symposium on Artificial Neural Net- works, Computational Intelligence and Machine Learning, Apr 2014, Bruges, Belgium. 2014. HAL Id: hal-01061654 https://hal.inria.fr/hal-01061654 Submitted on 8 Sep 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," 6603e7de5b155c86407edc43099b46b974b7f0bb,Local Feature Based Face Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 6643a7feebd0479916d94fb9186e403a4e5f7cbf,Chapter 8 3 D Face Recognition,"Chapter 8 D Face Recognition Ajmal Mian and Nick Pears" 66886f5af67b22d14177119520bd9c9f39cdd2e6,Learning Additive Kernel For Feature Transformation and Its Application to CNN Features,"T. KOBAYASHI: LEARNING ADDITIVE KERNEL Learning Additive Kernel For Feature Transformation and Its Application to CNN Features Takumi Kobayashi National Institute of Advanced Industrial Science and Technology Tsukuba, Japan" 66b37797286952e7735901e152b4cdea171e8567,Recovering 3D Planes from a Single Image via Convolutional Neural Networks,"Recovering 3D Planes from a Single Image via Convolutional Neural Networks Fengting Yang and Zihan Zhou The Pennsylvania State University {fuy34," 66f55dc04aaf4eefdecef202211ad7563f7a703b,Synthesizing Programs for Images using Reinforced Adversarial Learning,"Synthesizing Programs for Images using Reinforced Adversarial Learning Yaroslav Ganin 1 Tejas Kulkarni 2 Igor Babuschkin 2 S. M. Ali Eslami 2 Oriol Vinyals 2" 66660f5e8b2a4a695abe0f9e1df32d230126f773,Applying Deep Learning to Improve Maritime Situational Awareness,"Applying Deep Learning to Improve Maritime Situational Awareness Kathy Tang Stottler Henke Associates, Inc. 650 S. Amphlett Blvd. Ste. 300 San Mateo, CA 94402 Intelligence" 66b955311ab6841c4644414d8ce2faf6ca721602,RoboCupRescue 2009-Robot League Team Darmstadt Rescue Robot Team ( Germany ),"RoboCupRescue 2009 - Robot League Team Darmstadt Rescue Robot Team (Germany) Micha Andriluka1, Martin Friedmann1, Stefan Kohlbrecher1, Johannes Meyer2, Karen Petersen1, Christian Reinl1, Peter Schauß1, Paul Schnitzspan1, Armin Strobel2, Dirk Thomas1, Anguelina Vatcheva1, Oskar von Stryk1(cid:63) Department of Computer Science (1) and Department of Mechanical Engineering (2), Technische Universit¨at Darmstadt, Karolinenplatz 5, D-64289 Darmstadt, Germany E-Mail: Web: www.gkmm.tu-darmstadt.de/rescue" 665e6aa652b99350a08090faaf9d4bcc7800186e,Detection-Free Multiobject Tracking by Reconfigurable Inference With Bundle Representations,"Detection-Free Multiobject Tracking by Reconfigurable Inference With Bundle Representations Liang Lin, Yongyi Lu, Chenglong Li, Hui Cheng, and Wangmeng Zuo, Senior Member, IEEE" 664ccdcc614a8ecfbfedadc7b42b9537fe43d3f1,Probabilistic integration of sparse audio-visual cues for identity tracking,"Probabilistic Integration of Sparse Audio-Visual Cues for Identity Tracking Keni Bernardin Universität Karlsruhe, ITI Am Fasanengarten 5 76131, Karlsruhe, Germany Rainer Stiefelhagen Universität Karlsruhe, ITI Am Fasanengarten 5 76131, Karlsruhe, Germany Alex Waibel Universität Karlsruhe, ITI Am Fasanengarten 5 76131, Karlsruhe, Germany" 66837b29270f3e03df64941a081d70c687c7955c,ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition,"ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition Federico Angelini, Student Member, IEEE, Zeyu Fu, Student Member, IEEE, Yang Long, Senior Member, IEEE, Ling Shao, Senior Member, IEEE, and Syed Mohsen Naqvi, Senior Member, IEEE" 66e6f08873325d37e0ec20a4769ce881e04e964e,The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding,"Int J Comput Vis (2014) 108:59–81 DOI 10.1007/s11263-013-0695-z The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding Genevieve Patterson · Chen Xu · Hang Su · James Hays Received: 27 February 2013 / Accepted: 28 December 2013 / Published online: 18 January 2014 © Springer Science+Business Media New York 2014" 660c6a47ea29de2b4f40ac942ba682954118722f,SUPER-RESOLUTION : LIMITS AND BEYOND,"Chapter 1 SUPER-RESOLUTION: LIMITS AND BEYOND Simon Baker nd Takeo Kanade" 66860100a3355f26ffcb9dcbf27e27e4757d641d,Feature Selection in Supervised Saliency Prediction,"Feature Selection in Supervised Saliency Prediction Ming Liang, Student Member, IEEE, and Xiaolin Hu, Senior Member, IEEE" 669ae4a3a21b5800829ac9ee7e780fa42f9bc5ad,LATENT ASPECT DISCOVERY WITH DEEP REPRESENTATIONS,"978-1-4799-9988-0/16/$31.00 ©2016 IEEE ICASSP 2016" 66b9e9d488ef2bad9bf0d2fb98f73f38fec2bff8,Context-aware Cascade Attention-based RNN for Video Emotion Recognition,"Context-aware Cascade Attention-based RNN for Video Emotion Recognition Man-Chin Sun Emotibot Inc. Taipei, Taiwan Shih-Huan Hsu Emotibot Inc. Taipei, Taiwan Min-Chun Yang Emotibot Inc. Taipei, Taiwan Jen-Hsien Chien Emotibot Inc. Taipei, Taiwan" 1ab7d8da096c418c0bf93de14d128eb008a92db4,Towards three-dimensional face recognition in the real Huibin,"Towards three-dimensional face recognition in the real Huibin Li To cite this version: Huibin Li. Towards three-dimensional face recognition in the real. Other. Ecole Centrale de Lyon, 2013. English. . HAL Id: tel-00998798 https://tel.archives-ouvertes.fr/tel-00998798 Submitted on 2 Jun 2014 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de recherche fran¸cais ou ´etrangers, des laboratoires publics ou priv´es." 1aff495a36ceecbe2d49a95fe5779c2062fc5127,A NEW BAG OF PIXELS APPROACH BASED ON EDGE DETECTION TO FACE IMAGE RETRIEVAL,"International Journal of Applied Science and Technology Vol. 2 No. 1; January 2012 A NEW BAG OF PIXELS APPROACH BASED ON EDGE DETECTION TO FACE IMAGE RETRIEVAL Mir Hossein Dezfoulian Image Processing Lab, Computer Engineering Department Bu-Ali Sina University Hamedan, Iran Mostafa Parchami Image Processing Lab, Computer Engineering Department Bu-Ali Sina University Hamedan, Iran Saman Bashbaghi Image Processing Lab, Computer Engineering Department Bu-Ali Sina University Hamedan, Iran" 1a0b09e7e9182a68fc457bb888536b9023f6c9fd,Multi-affinity spectral clustering,"MULTI-AFFINITY SPECTRAL CLUSTERING Hsin-Chien Huang(cid:63)† Yung-Yu Chuang(cid:63) Chu-Song Chen† (cid:63)National Taiwan University Academia Sinica" 1a1654456decd116f4ca84c98006dfda0a8a3134,INTEGRATED VISUAL INFORMATION FOR MARITIME SURVEILLANCE,"INTEGRATED VISUAL INFORMATION FOR MARITIME SURVEILLANCE Domenico D. Bloisia, Luca Iocchia, Daniele Nardia and Michele Fiorinib Department of Computer, Control, and Management Engineering, Sapienza University of Rome, via Ariosto 25, 00185 Rome, Italy. SELEX-ES S.p.A. - A Finmeccanica Company, Rome, Italy." 1ae3a26a985fe525b23f080a9e1041ecff0509ad,A Comparative Study of Statistical Conversion of Face to Voice Based on Their Subjective Impressions,"Interspeech 2018 -6 September 2018, Hyderabad 0.21437/Interspeech.2018-2005" 1a2431e3b35a4a4794dc38ef16e9eec2996114a1,Automated Face Recognition: Challenges and Solutions,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 1a8ccc23ed73db64748e31c61c69fe23c48a2bb1,Extensive Facial Landmark Localization with Coarse-to-Fine Convolutional Network Cascade,"Extensive Facial Landmark Localization with Coarse-to-fine Convolutional Network Cascade Erjin Zhou Haoqiang Fan Zhimin Cao Yuning Jiang Qi Yin Megvii Inc." 1a6300ce4fb5eb593419a92d75ee4a4120d1c58f,Person-specific face representation for recognition,"     INSTITUTO DE COMPUTAÇÃO UNIVERSIDADE ESTADUAL DE CAMPINAS Person-Specic Face Representation for Recognition Giovani Chiachia Alexandre X. Falcão Anderson Rocha Technical Report IC-11-16 - Relatório Técnico - 2011 Julho The contents of this report are the sole responsibility of the authors. O conteúdo do presente relatório é de única responsabilidade dos autores." 1a7243913d9b8c6855b1eb3bb6566f2f1041d50a,Articulated clinician detection using 3D pictorial structures on RGB-D data,"Articulated Clinician Detection Using 3D Pictorial Structures on RGB-D Data Abdolrahim Kadkhodamohammadi, Afshin Gangi, Michel de Mathelin and Nicolas Padoy" 1a0912bb76777469295bb2c059faee907e7f3258,Mask R-CNN,"Mask R-CNN Kaiming He Georgia Gkioxari Piotr Doll´ar Ross Girshick Facebook AI Research (FAIR)" 1a9e0bf9f7a9495bcdf1aeb214ccc9df9f2a9030,Challenges and Opportunities The Main Memory System : Challenges and Opportunities,"특집원고Ⅰ The Main Memory System: Challenges and Opportunities Carnegie Mellon University Onur Mutlu･Justin Meza･Lavanya Subramanian The memory system is a fundamental performance and energy bottleneck in almost all computing systems. Recent system design, application, and technology trends that require more capacity, bandwidth, efficiency, and predictability out of the memory system make it an even more important system bottleneck. At the same time, DRAM technology is experiencing difficult technology scaling challenges that make the maintenance and enhancement of its capacity, energy-efficiency, and reliability significantly more costly with conventional techniques. In this article, after describing the demands and challenges faced by the memory system, we examine some promising research and design directions to overcome challenges posed y memory scaling. Specifically, we describe three major new research challenges and solution directions: 1) enabling new DRAM architectures, functions, interfaces, and better integration of the DRAM and the rest of the system (an" 1a6b2972506d7d85100552bee99ce2b267e30d41,Learning Optimal Embedded Cascades,"Learning Optimal Embedded Cascades Mohammad Javad Saberian and Nuno Vasconcelos, Senior Member, IEEE" 1a9997d8421d577a728f6ac119d4b14a3f46402c,Using Tectogrammatical Annotation for Studying Actors and Actions in Sallust ’ s Bellum Catilinae,"The Prague Bulletin of Mathematical Linguistics NUMBER 111 OCTOBER 2018 5–28 Using Tectogrammatical Annotation for Studying Actors and Actions in Sallust’s Bellum Catilinae Berta González Saavedra,a Marco Passarottib Dep. de Filología Clásica, Universidad Autónoma de Madrid, Spain CIRCSE Research Centre. Università Cattolica del Sacro Cuore, Milan, Italy" 1a878e4667fe55170252e3f41d38ddf85c87fcaf,Discriminative Machine Learning with Structure,"Discriminative Machine Learning with Structure Simon Lacoste-Julien Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2010-4 http://www.eecs.berkeley.edu/Pubs/TechRpts/2010/EECS-2010-4.html January 12, 2010" 1a382d4e436e3e4f3d735f6e34ba2bc61e30838e,Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection, 1ad88221f308bf9f36775650f880f32d91ce929a,Learning a Recurrent Residual Fusion Network for Multimodal Matching,"Learning a Recurrent Residual Fusion Network for Multimodal Matching Yu Liu Yanming Guo Erwin M. Bakker Michael S. Lew LIACS Media Lab, Leiden University, Leiden, The Netherlands {y.liu, y.guo, e.m.bakker," 1a9839698e29c9f80db0a2ea8c4568be4e1e84d8,An Information Theoretic Approach to the Study of Auditory Coding,"An Information Theoretic Approach to the Study of Auditory Coding Thesis submitted for the degree “Doctor of Philosophy” Gal Chechik Submitted to the Senate of the Hebrew University July 2003" 1a86620ea59816564db30fe0ae94cc422c5266e3,Can 3D Pose be Learned from 2D Projections Alone?,"Can 3D Pose be Learned from D Projections Alone? Dylan Drover, Rohith MV, Ching-Hang Chen, Amit Agrawal, Ambrish Tyagi, and Cong Phuoc Huynh Amazon Lab126 Inc., Sunnyvale, CA, USA {droverd, kurohith, chinghc, aaagrawa, mbrisht," 1a8a2539cffba25ed9a7f2b869ebb737276ccee1,Pros and Cons of GAN Evaluation Measures,"Pros and Cons of GAN Evaluation Measures Ali Borji" 1a9a192b700c080c7887e5862c1ec578012f9ed1,Discriminant Subspace Analysis for Face Recognition with Small Number of Training Samples,"IEEE TRANSACTIONS ON SYSTEM, MAN AND CYBERNETICS, PART B Discriminant Subspace Analysis for Face Recognition with Small Number of Training Samples Hui Kong, Xuchun Li, Matthew Turk, and Chandra Kambhamettu" 1a765cccff5e14c8f72d3cce13683e506b35c5c6,Real-time multi-platform pedestrian detection in a heavy duty driver assistance system,"CVT 2016 – March 8–10, 2016, Kaiserslautern, Germany Real-time multi-platform pedestrian detection in a heavy duty driver assistance system Songlin Piao1, Lisa Kiekbusch1, Daniel Schmidt1, Karsten Berns1, Daniel Hering2, Stefan Wirtz2, Nils Hering2 and J¨urgen Weiland2 Technische Universit¨at Kaiserslautern, Gottlieb-Daimler-Straße, 67663 Kaiserslautern Motec Entwicklungszentrum f¨ur Nutzfahrzeugassistenzsysteme, Universit¨atsstr. 3, 56070 Koblenz" 1a849b694f2d68c3536ed849ed78c82e979d64d5,This is a repository copy of Symmetric Shape Morphing for 3 D Face and Head Modelling,"This is a repository copy of Symmetric Shape Morphing for 3D Face and Head Modelling. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/131760/ Version: Accepted Version Proceedings Paper: Dai, Hang, Pears, Nicholas Edwin orcid.org/0000-0001-9513-5634, Smith, William Alfred Peter orcid.org/0000-0002-6047-0413 et al. (1 more author) (2018) Symmetric Shape Morphing for 3D Face and Head Modelling. In: The 13th IEEE Conference on Automatic Face and Gesture Recognition. IEEE . Reuse Items deposited in White Rose Research Online are protected by copyright, with all rights reserved unless indicated otherwise. They may be downloaded and/or printed for private study, or other acts as permitted by national copyright laws. The publisher or other rights holders may allow further reproduction and re-use of the full text version. This is indicated by the licence information on the White Rose Research Online record for the item. Takedown If you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing including the URL of the record and the reason for the withdrawal request. https://eprints.whiterose.ac.uk/" 1a618ff6fd0f0f94ab070555a4746e120eb9fbab,Why Is My Classifier Discriminatory?,"Why Is My Classifier Discriminatory? Irene Y. Chen Fredrik D. Johansson David Sontag" 1a3f7b9fc451b54110aaebae56c65413c620f6e2,Multilevel Linear Dimensionality Reduction for Data Analysis using Nearest-Neighbor Graphs ∗,"Multilevel Linear Dimensionality Reduction for Data Analysis using Nearest-Neighbor Graphs∗ Sophia Sakellaridi Department of Computer Science and Engineering University of Minnesota; Minneapolis, MN 55455 Haw-ren Fang Department of Computer Science and Engineering University of Minnesota; Minneapolis, MN 55455 Yousef Saad Department of Computer Science and Engineering University of Minnesota; Minneapolis, MN 55455" 1a5151b4205ab27b1c76f98964debbfc11b124d5,Self Paced Deep Learning for Weakly Supervised Object Detection,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Self Paced Deep Learning for Weakly Supervised Object Detection Enver Sangineto†, Moin Nabi†, Dubravko Culibrk and Nicu Sebe," 1a1ed320882c00c94d9f738b7b14eadd941376ed,Extracting Human Face Similarity Judgments: Pairs or Triplets?,"Extracting Human Face Similarity Judgments: Pairs or Triplets? Linjie Li1, Vicente Malave2, Amanda Song2, and Angela J. Yu2 Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA Department of Cognitive Science, University of California, San Diego, La Jolla, CA, USA" 1abdf07ce2fca11a26222dedd581b68b141af3f2,Face Recognition Aiding Historical Photographs Indexing Using a Two-Stage Training Scheme and an Enhanced Distance Measure,"Face Recognition Aiding Historical Photographs Indexing Using a Two-stage Training Scheme and an Enhanced Distance Measure Ana Paula Brand˜ao Lopes1,2, Camillo Jorge Santos Oliveira1,3, Arnaldo de Albuquerque Ara´ujo1 Computer Science Department – Federal University of Minas Gerais Av. Antˆonio Carlos, 6627, Pampulha, CEP 31270–901, Belo Horizonte, MG, Brazil Exact and Technological Sciences Department – State University of Santa Cruz Rodovia Ilh´eus-Itabuna, km 16 – Pavilh˜ao Jorge Amado, CEP 45600-000, Ilh´eus, BA, Brazil Informatics Department – Pontifical Catholic University of Minas Gerais Rua Rio Comprido, 4.580 - CEP 32.010-025, Contagem, MG, Brazil, {paula, camillo," 1a1955920ee36d58265fe17100ca451d899e8372,A Local Feature based on Lagrangian Measures for Violent Video Classification,"Best Paper Award, IET 6th International Conference on Imaging for Crime Prevention and Detection, 2015 A Local Feature based on Lagrangian Measures for Violent Video Classification Tobias Senst, Volker Eiselein, Thomas Sikora Communication Systems Group, Technische Universität Berlin, Germany Keywords: violent video detection, recognition, lagrangian measures, lagrangian framework local feature, action" 1a5b39a4b29afc5d2a3cd49087ae23c6838eca2b,Competitive Game Designs for Improving the Cost Effectiveness of Crowdsourcing,"Competitive Game Designs for Improving the Cost Effectiveness of Crowdsourcing Markus Rokicki, Sergiu Chelaru, Sergej Zerr, Stefan Siersdorfer L3S Research Center, Hannover, Germany" 1ad823bf77c691f1d2b572799f8a8c572d941118,Towards The Deep Model: Understanding Visual Recognition Through Computational Models,"implement the system. Précis of “Towards ​The Deep Model : Understanding Visual Recognition Through Computational Models” Panqu Wang Introduction Vision, due to its significance in surviving and socializing, is one of the most important and extensively studied sensory functions in the human brain. In order to fully understand visual information processing, or more specifically, visual recognition, David Marr proposed the Tri-level Hypothesis [29], in that three levels of the system should be studied: the computational goal of the system, the internal representation or the algorithm the system uses to achieve the goal, and the neural substrates that is well-known that visual recognition in the human brain is implemented by the ventral visual pathway [32], which receives visual information from the retina and goes through a layered structure including V1 (also known as the primary visual cortex), V2, V4, before reaching the inferior temporal cortex (IT). The topographic mapping between the retina and the human visual cortex follows a log-polar transformation, in which the Cartesian coordinates of the retina are transformed to polar coordinates (polar angle and eccentricity) in the human visual cortex. From V1 to V4, each" 1aa52a25c2967b8bc228268c9ab5a96a32d2189b,Visual Fashion-Product Search at SK Planet,"Visual Fashion-Product Search at SK Planet Taewan Kim, Seyeoung Kim, Sangil Na, Hayoon Kim, Moonki Kim, Byoung-Ki Jeon Machine Intelligence Lab. SK Planet, SeongNam City, South Korea" 1afe9919ddb2b245e21b610fa96037724bcdf648,2 SceneNet : An Online Database for Scene Understanding,"SceneNet: A Perceptual Ontology for Scene Understanding Ilan Kadar and Ohad Ben-Shahar Ben-Gurion University of the Negev" 1abf6491d1b0f6e8af137869a01843931996a562,ParseNet: Looking Wider to See Better.,"ParseNet: Looking Wider to See Better Wei Liu UNC Chapel Hill Andrew Rabinovich MagicLeap Inc. Alexander C. Berg UNC Chapel Hill" 1a54a8b0c7b3fc5a21c6d33656690585c46ca08b,Fast Feature Pyramids for Object Detection,"Fast Feature Pyramids for Object Detection Piotr Doll´ar, Ron Appel, Serge Belongie, and Pietro Perona" 1afbca9f7011ec659db9cb3692cbab5b5e38499b,"A mixed bag of emotions: Model, predict, and transfer emotion distributions","Motivation From our observation: . Different people have different emotional reactions to the same image. . The same person may have multiple emotional reactions to one image. Contributions . Propose an image database, Emotion6, that models emotion distributions. . Outperform the state-of-the-art affective image classification with our method using convolutional neural networks (CNN). . Introduce a method for emotion transfer between images. Emotion6 Image Database Emotion6 properties Image source Image size Total # of images # of categories # of images per category Ground truth provided Description Flickr. ∼VGA (keep aspect ratio)." 1a51bc5f9f12f6794297a426739350ae57c87731,Image classification with CNN-based Fisher vector coding,"Kent Academic Repository Full text document (pdf) Citation for published version Song, Yan and Hong, Xinhai and McLoughlin, Ian Vince and Dai, Li-Rong (2017) Image Classification with CNN-based Fisher Vector Coding. In: IEEE International Conference on Visual Communications nd Image Processing 2016, 27-30 Nov 2016, Chengdu, Sichuan, China. https://doi.org/10.1109/VCIP.2016.7805494 Link to record in KAR http://kar.kent.ac.uk/57115/ Document Version Author's Accepted Manuscript Copyright & reuse Content in the Kent Academic Repository is made available for research purposes. Unless otherwise stated all ontent is protected by copyright and in the absence of an open licence (eg Creative Commons), permissions for further reuse of content should be sought from the publisher, author or other copyright holder. Versions of research The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record. Enquiries" 1a219e7bcd8f30f886a1f24a8c05bc26bef83ff9,Crowd Counting with Density Adaption Networks,"Crowd Counting with Density Adaption Networks Li Wang, Weiyuan Shao, Yao Lu, Hao Ye, Jian Pu, Yingbin Zheng" 1ad97cce5fa8e9c2e001f53f6f3202bddcefba22,Grassmann Averages for Scalable Robust PCA,"Grassmann Averages for Scalable Robust PCA Aasa Feragen DIKU and MPIs T¨ubingen∗ Denmark and Germany Søren Hauberg DTU Compute∗ Lyngby, Denmark" 1afd481036d57320bf52d784a22dcb07b1ca95e2,Automated Content Metadata Extraction Services Based on MPEG Standards,"The Computer Journal Advance Access published December 6, 2012 © The Author 2012. Published by Oxford University Press on behalf of The British Computer Society. All rights reserved. For Permissions, please email: doi:10.1093/comjnl/bxs146 Automated Content Metadata Extraction Services Based on MPEG Standards D.C. Gibbon∗, Z. Liu, A. Basso and B. Shahraray AT&T Labs Research, Middletown, NJ, USA Corresponding author: This paper is concerned with the generation, acquisition, standardized representation and transport of video metadata. The use of MPEG standards in the design and development of interoperable media architectures and web services is discussed. A high-level discussion of several algorithms for metadata extraction is presented. Some architectural and algorithmic issues encountered when designing services for real-time processing of video streams, as opposed to traditional offline media processing, are addressed. A prototype real-time video analysis system for generating MPEG-7 Audiovisual Description Profile from MPEG-2 transport stream encapsulated video is presented. Such a capability can enable a range of new services such as content-based personalization of live roadcasts given that the MPEG-7 based data models fit in well with specifications for advanced television services such as TV-Anytime andAlliance for Telecommunications Industry Solutions IPTV Interoperability Forum." 1afe5d933b58b4dd982a559cc6ec1d17959239de,Enhanced canonical correlation analysis with local density for cross-domain visual classification,"978-1-5090-4117-6/17/$31.00 ©2017 IEEE ICASSP 2017" 1a7e385d2aa041ca8931784fb7664e9905194565,Chapter 2 Sentiment Analysis Using Social Multimedia,"Chapter 2 Sentiment Analysis Using Social Multimedia Jianbo Yuan, Quanzeng You and Jiebo Luo" 1a7a2221fed183b6431e29a014539e45d95f0804,Person Identification Using Text and Image Data,"Person Identification Using Text and Image Data David S. Bolme, J. Ross Beveridge and Adele E. Howe Computer Science Department Colorado State Univeristy Fort Collins, Colorado 80523" 1acf1000d47fd8273ac0bca6f9345b55709f6357,Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning,"Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Hengel" 1af5f188abbfc38ac2f5985f636e0f53a4cdea10,On-line visual vocabularies for robot navigation and mapping,"The 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems October 11-15, 2009 St. Louis, USA 978-1-4244-3804-4/09/$25.00 ©2009 IEEE" 1af68c5b5ff61d95de7c585275e119796eb81b1f,Leader tracking for a walking logistics robot,"Congress Center Hamburg Sept 28 - Oct 2, 2015. Hamburg, Germany 978-1-4799-9993-4/15/$31.00 ©2015 IEEE" 1a20ddce2349bc995dceea66cd2378f8888c8027,SAN: Learning Relationship Between Convolutional Features for Multi-scale Object Detection,"SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection Yonghyun Kim1[0000−0003−0038−7850], Bong-Nam Kang2[0000−0002−6818−7532], nd Daijin Kim1[0000−0002−8046−8521] Department of Computer Science and Engineering, POSTECH, Korea Department of Creative IT Engineering, POSTECH, Korea" 1a41831a3d7b0e0df688fb6d4f861176cef97136,A Biological Model of Object Recognition with Feature Learning,"massachusetts institute of technology — artificial intelligence laboratory A Biological Model of Object Recognition with Feature Learning Jennifer Louie AI Technical Report 2003-009 CBCL Memo 227 June 2003 © 2 0 0 3 m a s s a c h u s e t t s i n s t i t u t e o f t e c h n o l o g y, c a m b r i d g e , m a 0 2 1 3 9 u s a — w w w. a i . m i t . e d u" 1a03716411e72722f853b904a83d9c15a0d737a3,Using color texture sparsity for facial expression recognition,"Using Color Texture Sparsity for Facial Expression Recognition Seung Ho Lee, Hyungil Kim, Korea Advanced Department Institute of Electrical of Science of Korea Republic Daejeon, nd Y ong Man Ro Engineering nd Technology Department Engineering Konstantinos of Electrical University N. Plataniotis" 1a515f0b852c2e93272677dbf6ecb05c7be0ea2e,Reduced serotonin receptor subtypes in a limbic and a neocortical region in autism.,"RESEARCH ARTICLE Reduced Serotonin Receptor Subtypes in a Limbic and a Neocortical Region in Autism Adrian Oblak, Terrell T. Gibbs, and Gene J. Blatt Autism is a behaviorally defined, neurological disorder with symptom onset before the age of 3. Abnormalities in social-emotional behaviors are a core deficit in autism, and are characterized by impaired reciprocal–social interaction, lack of facial expressions, and the inability to recognize familiar faces. The posterior cingulate cortex (PCC) and fusiform gyrus (FG) are two regions within an extensive limbic-cortical network that contribute to social-emotional behaviors. Evidence indicates that changes in brains of individuals with autism begin prenatally. Serotonin (5-HT) is one of the earliest expressed neurotransmitters, and plays an important role in synaptogenesis, neurite outgrowth, and neuronal migration. Abnormalities in 5-HT systems have been implicated in several psychiatric disorders, including autism, as evidenced by immunology, imaging, genetics, pharmacotherapy, and neuropathology. Although information is known regarding peripheral 5-HT in autism, there is emerging evidence that 5-HT systems in the central nervous system, including various 5-HT receptor subtypes and transporters, are affected in autism. The present study demonstrated significant reductions in 5-HT1A receptor-binding density in superficial and deep layers of the PCC and FG, and in the density of 5-HT2A receptors in superficial layers of the PCC and FG. A significant reduction in the density of serotonin transporters (5-HTT) was also found in the deep layers of the FG, but normal levels were demonstrated in both layers of the PCC and superficial layers of the FG. This study provides potential substrates for decreased 5-HT modulation/ innervation in the autism brain, and implicate two 5-HT receptor subtypes as potential neuromarkers for novel or existing pharmacotherapies. Autism Res 2013, 6: 571–583. © 2013 International Society for Autism Research, Wiley" 1a66f37f37e4fbf9a8e657853933539256bbda88,Spectral Clustering by Joint Spectral Embedding and Spectral Rotation.,"This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. Spectral Clustering by Joint Spectral Embedding nd Spectral Rotation Yanwei Pang , Senior Member, IEEE, Jin Xie, Feiping Nie , and Xuelong Li , Fellow, IEEE" 00dfd58bbaff871603e4a8aa81e67915b0675aeb,Human Sensing Using Computer Vision for Personalized Smart Spaces,"013 IEEE 10th International Conference on Ubiquitous Intelligence & Computing and 2013 IEEE 10th International Conference on Autonomic & Trusted Computing Human Sensing using Computer Vision for Personalized Smart Spaces Dipak Surie, Saeed Partonia, Helena Lindgren User Interaction and Knowledge Modeling Group Dept. of Computing Science Umeå University, Sweden {dipak, mcs10spa, spaces everyday" 0066dc9131c25e93111fc092098f6c9db6255f1a,RoI-based Robotic Grasp Detection in Object Overlapping Scenes Using Convolutional Neural Network,"RoI-based Robotic Grasp Detection for Object Overlapping Scenes Using Convolutional Neural Network Hanbo Zhang, Xuguang Lan, Xinwen Zhou, Zhiqiang Tian and Nanning Zheng" 0063b44da282eec78045ab59d2debbf61959a4a4,Improving person re-identification by viewpoint cues,"Improving Person Re-identification by Viewpoint Cues Sławomir B ˛ak Sofia Zaidenberg Bernard Boulay Francois Brémond INRIA Sophia Antipolis, STARS/Neosensys 004, route des Lucioles, BP93 06902 Sophia Antipolis Cedex - France" 004e3292885463f97a70e1f511dc476289451ed5,Quadruplet-Wise Image Similarity Learning,"Quadruplet-wise Image Similarity Learning Marc T. Law Nicolas Thome Matthieu Cord LIP6, UPMC - Sorbonne University, Paris, France {Marc.Law, Nicolas.Thome," 0033e0ce8720f913761f9edb9a6c378eed8366a8,Interactive Object Retrieval using Interpretable Visual Models,"UNIVERSIT´EPARIS-SUD11Facult´edessciencesd’OrsayN◦Ordre:2011PA112054PHDTHESISInteractiveObjectRetrievalusingInterpretableVisualModelsSubmittedforthedegreeof“docteurensciences”oftheUniversityParis-Sud11Speciality:ComputerScienceByAhmedRebaiMay2011INRIAParis-Rocquencourt,ImediaTeamThesiscommittee:Reviewers:FredStentiford-Prof.atUniversityCollegeLondon(UK)SylviePhilipp-Foliguet-Prof.atUniversit´eCergy/Pontoise(FR)Director:NozhaBoujemaa-DirectoroftheINRIA-SaclayCenter(FR)Advisor:AlexisJoly-ResearcheratINRIA-Rocquencourt(FR)Examinator:MichelCrucianu-Prof.atCNAM(FR)President:Fran¸coisYvon-Prof.atUniversit´eParis-Sud11(FR)Copyrightc(cid:13)2011AhmedRebaiAllrightsreserved." 00d8f67ac0ea0bb2c9827b60e1f47c300346cd7a,Face recognition using color local binary pattern from mutually independent color channels,"Anbarjafari EURASIP Journal on Image and Video Processing 2013, 2013:6 http://jivp.eurasipjournals.com/content/2013/1/6 R ES EAR CH Open Access Face recognition using color local binary pattern from mutually independent color channels Gholamreza Anbarjafari" 0041afaf2b17f1a33bd514db27b17ce34670fdb8,Deep Reinforcement Learning-Based Image Captioning with Embedding Reward,"Deep Reinforcement Learning-based Image Captioning with Embedding Reward Zhou Ren1 Xiaoyu Wang1 Ning Zhang1 Xutao Lv1 Li-Jia Li2∗ {zhou.ren, xiaoyu.wang, ning.zhang, Snap Inc. Google Inc." 00d9d88bb1bdca35663946a76d807fff3dc1c15f,Subjects and Their Objects: Localizing Interactees for a Person-Centric View of Importance,"Subjects and Their Objects: Localizing Interactees for a Person-Centric View of Importance Chao-Yeh Chen · Kristen Grauman" 0079d56c8e183ef36f876b84327b97ee9454825b,Scene Parsing by Weakly Supervised Learning with Image Descriptions,"Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions Ruimao Zhang, Liang Lin, Guangrun Wang, Meng Wang, and Wangmeng Zuo" 0083a395fded81d562317d83e194dfbc47b5c04a,AT&T Research at TRECVID 2010,"AT&T Research at TRECVID 2010 Zhu Liu, Eric Zavesky, Neela Sawant∗, Behzad Shahraray AT&T Labs Research, 200 Laurel Avenue, Middeltown, NJ 07748 College of Information Sciences and Technology, Penn State University, University Park, PA 16802" 004a1bb1a2c93b4f379468cca6b6cfc6d8746cc4,Balanced k-Means and Min-Cut Clustering,"Balanced k-Means and Min-Cut Clustering Xiaojun Chang, Feiping Nie, Zhigang Ma, and Yi Yang" 0077cd8f97cafd2b389783858a6e4ab7887b0b6b,Face Image Reconstruction from Deep Templates,"MAI et al.: ON THE RECONSTRUCTION OF DEEP FACE TEMPLATES On the Reconstruction of Deep Face Templates Guangcan Mai, Kai Cao, Pong C. Yuen, Senior Member, IEEE, and Anil K. Jain, Life Fellow, IEEE" 0089a590154694e0de340f357a022f6a38d60946,Speeding-up Object Detection Training for Robotics with FALKON,"Speeding-up Object Detection Training for Robotics with FALKON Elisa Maiettini1,2,3, Giulia Pasquale1,2, Lorenzo Rosasco2,3 and Lorenzo Natale1" 0052de4885916cf6949a6904d02336e59d98544c,Generalized low rank approximations of matrices,"Machine Learning, 61, 167–191, 2005 005 Springer Science + Business Media, Inc. Manufactured in The Netherlands. DOI: 10.1007/s10994-005-3561-6 Generalized Low Rank Approximations of Matrices JIEPING YE Department of Computer Science & Engineering,University of Minnesota-Twin Cities, Minneapolis, MN 55455, USA Editor: Peter Flach Published online: 12 August 2005" 00b03ee4a7e31a999715d7a0c31d283d646106fa,Multi-level Semantic Feature Augmentation for One-shot Learning,"Multi-level Semantic Feature Augmentation for One-shot Learning Zitian Chen, Yanwei Fu*, Yinda Zhang, Leonid Sigal" 00a3cfe3ce35a7ffb8214f6db15366f4e79761e3,Using Kinect for real-time emotion recognition via facial expressions,"Qi-rong Mao, Xin-yu Pan, Yong-zhao Zhan, Xiang-jun Shen, 2015. Using Kinect for real-time emotion recognition via facial expressions. Frontiers of Information Technology & Electronic Engineering, 16(4):272-282. [doi:10.1631/FITEE.1400209] Using Kinect for real-time emotion recognition via facial expressions Key words: Kinect, Emotion recognition, Facial expression, Real-time lassification, Fusion algorithm, Support vector machine (SVM) Contact: Qi-rong Mao E-mail: ORCID: http://orcid.org/0000-0002-5021-9057 Front Inform Technol & Electron Eng" 00433d2ad90b40bc5ad22a591aac0da68037003e,K-means Based Automatic Pests Detection and Classification for Pesticides Spraying,"(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 8 No. 11, 2017 K-means Based Automatic Pests Detection and Classification for Pesticides Spraying Muhammad Hafeez Javed Foundation University Islamabad M Humair Noor Babar Yaqoob Khan Foundation University Islamabad Foundation University Islamabad Nazish Noor Foundation University Islamabad Tayyaba Arshad Foundation University Islamabad" 001719ac5585722d14bf4f2d807383a368504a4a,Pedestrian detection in low resolution videos,"Pedestrian Detection in Low Resolution Videos Hisham Sager Colorado School of Mines Golden, CO 80401 William Hoff Colorado School of Mines Golden, CO 80401" 00fb2836068042c19b5197d0999e8e93b920eb9c,Genetic Algorithm for Weight Optimization in Descriptor based Face Recognition Methods, 00d931eccab929be33caea207547989ae7c1ef39,The natural input memory model,"The Natural Input Memory Model Joyca P.W. Lacroix Department of Computer Science, IKAT, Universiteit Maastricht, St. Jacobsstraat 6, 6211 LB Maastricht, The Netherlands Department of Psychology, Universiteit van Amsterdam, Roeterstraat 15, 1018 WB Amsterdam, The Netherlands Jaap M.J. Murre Department of Computer Science, IKAT, Universiteit Maastricht, St. Jacobsstraat 6, 6211 LB Maastricht, The Netherlands Eric O. Postma H. Jaap van den Herik" 005503ccf270890ea2582370feed4506f3785004,Characterizing the temporal dynamics of object recognition by deep neural networks : role of depth,"ioRxiv preprint first posted online Sep. 10, 2017; peer-reviewed) is the author/funder. All rights reserved. No reuse allowed without permission. http://dx.doi.org/10.1101/178541 The copyright holder for this preprint (which was not Characterizing the temporal dynamics of object recognition by deep neural networks : role of depth Kandan Ramakrishnan1, Iris I.A. Groen2, Arnold W.M. Smeulders1, H. Steven Scholte*3, Sennay Ghebreab*1 Institute of Informatics, University of Amsterdam. Laboratory of Brain and Cognition, National Institute of Health. Department of Psychology, University of Amsterdam. Keywords: deep neural network, ERP, architecture, number of layers" 001dc49f7f3348841b4086f966bfe4e9dfadf03e,Automatic image captioning using multitask learning,"Automatic image captioning using multi-task learning Anna Fariha" 00f0ed04defec19b4843b5b16557d8d0ccc5bb42,Modeling Spatial and Temporal Cues for Multi-label Facial Action Unit Detection, 004dc8de3a6832c8d4764144570dc122b5265ec5,Hyper-dimensional computing for a visual question-answering system that is trainable end-to-end,"Hyper-dimensional computing for a visual question-answering system that is trainable end-to-end Guglielmo Montone J.Kevin O’Regan Laboratoire Psychologie de la Perception Laboratoire Psychologie de la Perception Université Paris Descartes 75006 Paris, France Université Paris Descartes 75006 Paris, France Alexander V. Terekhov Laboratoire Psychologie de la Perception Université Paris Descartes 75006 Paris, France" 00319cd17cebae5e1095a248260bd7be15781362,A Dataset for Improved RGBD-Based Object Detection and Pose Estimation for Warehouse Pick-and-Place,"A Dataset for Improved RGBD-based Object Detection and Pose Estimation for Warehouse Pick-and-Place Colin Rennie1, Rahul Shome1, Kostas E. Bekris1, and Alberto F. De Souza2" 008dafebbb27eb64a1af8ded8bfe2e7a04c1d703,CANDLE/Supervisor: A Workflow Framework for Machine Learning Applied to Cancer Research,"CANDLE/Supervisor: A Workflow Framework for Machine Learning Applied to Cancer Research Justin M. Wozniak, Rajeev Jain, Prasanna Balaprakash Mathematics & Computer Science Argonne National Laboratory Argonne, IL, USA Jamaludin Mohd-Yusof, Cristina Garcia Cardona Computer, Computational & Statistical Sciences Los Alamos National Laboratory Los Alamos, NM, USA Jonathan Ozik, Nicholson Collier Global Security Sciences Argonne National Laboratory Argonne, IL, USA Brian Van Essen Lawrence Livermore National" 00b370765678c44acd5313f3946b2431890721a9,Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis,"Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis Christian Th´eriault, Nicolas Thome, Matthieu Cord UPMC-Sorbonne Universities, Paris, France" 0098f42c6f24d5e6d2471c1d7d1e864ff8e83226,Review on Face Recognition across Age Progression,"Review on Face Recognition across Age Progression Rashmi P1, Shifana Begaum2, B R Kishore3 ,2,3Srinivas School of Engineering, Mukka, Mangalore" 000a83a533f9c945addce83e466e308df1ae79c5,Efficient max-margin multi-label classification with applications to zero-shot learning,"Mach Learn manuscript No. (will be inserted by the editor) Efficient Max-Margin Multi-Label Classification with Applications to Zero-Shot Learning Bharath Hariharan · S. V. N. Vishwanathan · Manik Varma Received: 30 September 2010 / Accepted: date" 006a9f68bcf6edca62d8750af55168971cf0890c,Dynamic Programming Bipartite Belief Propagation For Hyper Graph Matching,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) 00d63b30e7e8383ea3dd2993499df70a51295d13,Exploiting structure in man-made environments,"Exploiting structure in man-made environments ALPER AYDEMIR Doctoral Thesis Stockholm, Sweden, 2012" 006350ae14784bb929b6a749d4e5c265a10168b7,Abstract Eye Detection Using Discriminatory Features and an Efficient Support Vector Machine Eye Detection Using Discriminatory Features and an Efficient Support Vector Machine Eye Detection Using Discriminatory Features and an Efficient Support Vector Machine,"Copyright Warning & Restrictions The copyright law of the United States (Title 17, United States Code) governs the making of photocopies or other reproductions of copyrighted material. Under certain conditions specified in the law, libraries and rchives are authorized to furnish a photocopy or other reproduction. One of these specified conditions is that the photocopy or reproduction is not to be “used for any purpose other than private study, scholarship, or research.” If a, user makes a request for, or later uses, a photocopy or reproduction for purposes in excess of “fair use” that user may be liable for copyright infringement, This institution reserves the right to refuse to accept a opying order if, in its judgment, fulfillment of the order would involve violation of copyright law. Please Note: The author retains the copyright while the New Jersey Institute of Technology reserves the right to distribute this thesis or dissertation Printing note: If you do not wish to print this page, then select “Pages from: first page # to: last page #” on the print dialog screen" 00b605f19ae4502362831e33be0f9c03228fc640,Securing Mass Biometric Templates Using Blockwise Multi-Resolution Clustering,"Securing Mass Biometric Templates Using Blockwise Multi-Resolution Clustering Watermarking Bassem S. Rabil, Robert Sabourin, and Eric Granger Laboratoire d’ Imagerie, de Vision, et d’Intelligence Artificielle ´Ecole de Technologie Superi´eure (´ETS), University of Quebec 100, rue Notre-Dame Ouest, Montreal, QC H3C 1K3, Canada. http://www.etsmtl.ca" 006f283a50d325840433f4cf6d15876d475bba77,Preserving Structure in Model-Free Tracking,"Preserving Structure in Model-Free Tracking Lu Zhang and Laurens van der Maaten" 003b141fb02078a4b5d02f4f803001ce22d73ba7,Real-time 3D Multiple Human Tracking with Robustness Enhancement through Machine Learning,"REAL-TIME 3D MULTIPLE HUMAN TRACKING WITH ROBUSTNESS ENHANCEMENT THROUGH MACHINE LEARNING Keywords: Visual Tracking" 00e39fad9846084eb435b6cddd675ee11f2dfb90,Person Re-identification Using Haar-based and DCD-based Signature,"Person Re-identification Using Haar-based and DCD-based Signature Slawomir Bak, Etienne Corvee, François Bremond, Monique Thonnat To cite this version: Slawomir Bak, Etienne Corvee, François Bremond, Monique Thonnat. Person Re-identification Us- ing Haar-based and DCD-based Signature. 2nd Workshop on Activity Monitoring by Multi-Camera Surveillance Systems, AMMCSS 2010, in conjunction with 7th IEEE International Conference on Ad- vanced Video and Signal-Based Surveillance, AVSS - 2010, Aug 2010, Boston, United States. 2010. HAL Id: inria-00496051 https://hal.inria.fr/inria-00496051 Submitted on 29 Jun 2010 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents" 00edd45d8f4fd75fc329d6a6fcc7d87108baa3a9,Distance Measures for Gabor Jets-Based Face Authentication: A Comparative Evaluation,"Distance Measures for Gabor Jets-based Face Authentication: A Comparative Evaluation Daniel Gonz´alez-Jim´enez1, Manuele Bicego2, J.W.H. Tangelder3, B.A.M Schouten3, Onkar Ambekar3, Jos´e Luis Alba-Castro1, Enrico Grosso2, Massimo Tistarelli4 TSC Department, University of Vigo, Vigo (Spain) DEIR - University of Sassari, Sassari (Italy) CWI, Amsterdam (The Netherlands) DAP - University of Sassari, Alghero (Italy)" 003846e4559fa32699f08ecd09de13ed5a4e92d2,Analysis of Brain Waves in Violent Images - Are Differences in Gender?, 0014a057ebdeca672b1cdee8104cca4dc928ef3e,Training Deformable Part Models with Decorrelated Features,"Training deformable part models with decorrelated features Ross Girshick and Jitendra Malik UC Berkeley {rbg," 00d14af37bc75b6477b4846f6ab561cdc89c96a2,"UvA-DARE ( Digital Academic Repository ) Infants ’ Temperament and Mothers ’ , and Fathers ’ Depression Predict Infants ’ Attention to Objects Paired with Emotional","UvA-DARE (Digital Academic Repository) Infants’ Temperament and Mothers’, and Fathers’ Depression Predict Infants’ Attention to Objects Paired with Emotional Faces Aktar, E.; Mandell, D.J.; de Vente, W.; Majdandzic, M.; Raijmakers, M.E.J.; Bögels, S.M. Published in: Journal of Abnormal Child Psychology 0.1007/s10802-015-0085-9 Link to publication Citation for published version (APA): Aktar, E., Mandell, D. J., de Vente, W., Majdandži, M., Raijmakers, M. E. J., & Bögels, S. M. (2016). Infants’ Temperament and Mothers’, and Fathers’ Depression Predict Infants’ Attention to Objects Paired with Emotional Faces. Journal of Abnormal Child Psychology, 44(5), 975-990. DOI: 10.1007/s10802-015-0085-9 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible." 0029418d56d8fe71d1d45bdaad88e5cc75dc58e7,Pushing the “Speed Limit”: High-Accuracy US Traffic Sign Recognition With Convolutional Neural Networks,"Pushing the “Speed Limit”: High-Accuracy U.S. Traffic Sign Recognition with Convolutional Neural Networks Yuan Li, Andreas Møgelmose, and Mohan M. Trivedi" 002d1619748a99aa683b5c30b7eafebdfe6adfc4,Nearest feature line embedding for face hallucination,"Nearest feature line embedding for face hallucination Junjun Jiang, Ruimin Hu, Zhen Han and Tao Lu A new manifold learning method, called nearest feature line (NFL) embedding, for face hallucination is proposed. While many manifold learning based face hallucination algorithms have been proposed in recent years, most of them apply the conventional nearest neighbour metric to derive the subspace and may not effectively characterise the geometrical information of the samples, especially when the number of training samples is limited. This reported work proposes using the NFL metric to define the neighbourhood relations between face samples to improve the expressing power of the given training samples for reconstruction. The algorithm preserves the linear relation- ship in a smaller local space than traditional manifold learning based methods, which better reflects the nature of manifold learning theory. Experimental results demonstrate that the method is effective at preserving detailed visual information. Introduction: Face super-resolution (SR), or face hallucination, refers to" 0037bff7be6d463785d4e5b2671da664cd7ef746,Multiple Instance Metric Learning from Automatically Labeled Bags of Faces,"Author manuscript, published in ""European Conference on Computer Vision (ECCV '10) 6311 (2010) 634--647"" DOI : 10.1007/978-3-642-15549-9_46" 00796052277d41e2bb3a1284d445c1747aed295f,Performance and Energy Consumption Characterization and Modeling of Video Decoding on Multi-core Heterogenous SoC and their Applications,"Performance and Energy Consumption Characterization nd Modeling of Video Decoding on Multi-core Heterogenous SoC and their Applications Yahia Benmoussa To cite this version: Yahia Benmoussa. Performance and Energy Consumption Characterization and Modeling of Video Decoding on Multi-core Heterogenous SoC and their Applications. Multimedia [cs.MM]. Universit´e de Bretagne Occidentale, 2015. English. HAL Id: tel-01313326 https://hal.archives-ouvertes.fr/tel-01313326 Submitted on 9 May 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non," 00cb08dcef72bfaa1aab0664d34168615ac6a5cc,Amygdala Surface Modeling with Weighted Spherical Harmonics,"Amygdala Surface Modeling with Weighted Spherical Harmonics Moo K. Chung1,2, Brendon M. Nacewicz2, Shubing Wang1, Kim M. Dalton2, Seth Pollak3, and Richard J. Davidson2,3 Department of Statistics, Biostatistics and Medical Informatics Waisman Laboratory for Brain Imaging and Behavior Department of Psychology and Psychiatry University of Wisconsin, Madison, WI 53706, USA" 00f17fca3cf3ab4262edde3626e6230a89ff1a1f,Human Pose Estimation with Iterative Error Feedback,"Human Pose Estimation with Iterative Error Feedback Jo˜ao Carreira UC Berkeley Pulkit Agrawal UC Berkeley Katerina Fragkiadaki UC Berkeley Jitendra Malik UC Berkeley" aff672a7e2c5dca5921ddfa3cf3223e2f94d5838,Towards Secure and Usable User Authentication on Mobile Devices,"Towards Secure and Usable User Authentication on Mobile Devices Dissertation zur Erlangung des Grades eines Doktor-Ingenieurs der Fakult¨at f¨ur Elektrotechnik und Informationstechnik n der Ruhr-Universit¨at Bochum vorgelegt von Sebastian Uellenbeck us Herdecke Bochum, 07. April 2014 Fakultät fürElektrotechnik undInformationstechnik" afa004a8daaa7fc093a798bf97babdb00273e1a0,EXPERIMENTAL STUDY ON FAST 2 D HOMOGRAPHY ESTIMATION FROM A FEW POINT CORRESPONDENCES,"Tutkimusraportti 111 Research Report 111 EXPERIMENTAL STUDY ON FAST 2D HOMOGRAPHY ESTIMATION FROM A FEW POINT CORRESPONDENCES Joni-Kristian Kämäräinen and Pekka Paalanen Lappeenranta University of Technology Faculty of Technology Management Department of Information Technology Box 20 FIN-53851 Lappeenranta ISBN 978-952-214-772-1 (paperback) ISBN 978-952-214-773-8 (PDF) ISSN 0783-8069 Lappeenranta 2009" af64854f653f2c1724d04c9657adfcdabe0f8440,Structure propagation for zero-shot learning,"Structure propagation for zero-shot learning Guangfeng Lina,∗, Yajun Chena, Fan Zhaoa Information science department, Xian University of Technology, 5 South Jinhua Road, Xi’an, Shaanxi Province 710048, PR China" afd3a6dde8fa3b330cb146678731b150213ddd95,Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning,"Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning Supasorn Suwajanakorn(cid:46)∗ Noah Snavely(cid:47) Jonathan Tompson(cid:47) Mohammad Norouzi(cid:47) {snavely, tompson, (cid:46)Vidyasirimedhi Institute of Science and Technology (cid:47)Google AI" af4e6fa65a692c29b9d475de360f7994808a8ff8,Boosted Linear Projections for Discriminant Analysis,"Boosted Linear Projections for Discriminant Analysis David Masip nd Jordi Vitri`a Centre de Visi´o per Computador - Dept. Inform`atica, UAB Edifici O - Campus UAB, 08193 Bellaterra, Barcelona, Catalonia, Spain" afc7092987f0d05f5685e9332d83c4b27612f964,Person-independent facial expression detection using Constrained Local Models,"Person-Independent Facial Expression Detection using Constrained Local Models Sien. W. Chew, Patrick Lucey, Simon Lucey, Jason Saragih, Jeffrey F. Cohn and Sridha Sridharan" af8261ca1fc8e111cc344c0f3e26c09e39246983,Casualty Detection from 3D Point Cloud Data for Autonomous Ground Mobile Rescue Robots,"Casualty Detection from 3D Point Cloud Data for Autonomous Ground Mobile Rescue Robots Roni Permana Saputra1,2 and Petar Kormushev1" afe3a0d463e2f099305c745ddbf943844583795d,Learning Visual Question Answering by Bootstrapping Hard Attention,"Learning Visual Question Answering by Bootstrapping Hard Attention Mateusz Malinowski, Carl Doersch, Adam Santoro, and Peter Battaglia DeepMind, London, United Kingdom" af9cc1767f50f63291d7ca9ab709f6849cd1e46c,Graph-Driven Diffusion and Random Walk Schemes for Image Segmentation.,"IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 26, NO. 1, JANUARY 2017 Graph-Driven Diffusion and Random Walk Schemes for Image Segmentation Christos G. Bampis, Student Member, IEEE, Petros Maragos, Fellow, IEEE, and Alan C. Bovik, Fellow, IEEE" af6b14c0bf427b22baffc06a0bd515b30649d8c3,Face recognition using kernel scatter-difference-based discriminant analysis,"[23] Y. He, M. Wu, and J. H. She, “An improved global asymptotic stability riterion for delayed cellular neural networks,” IEEE Trans. Neural Netw., vol. 17, no. 1, pp. 250–252, Jan. 2006. [24] Z. Wang, D. W. C. Ho, and X. Liu, “State estimation for delayed neural networks,” IEEE Trans. Neural Netw., vol. 16, no. 1, pp. 279–284, Jan. 005. [25] V. T. S. Elanayar and Y. C. Shin, “Approximation and estimation of nonlinear stochastic dynamic systems using radial basis function neural networks,” IEEE Trans. Neural Netw., vol. 5, no. 4, pp. 594–603, Jul. 994. [26] R. Habtom and L. Litz, “Estimation of unmeasured inputs using re- urrent neural networks and the extended Kalman filter,” in Proc. Int. Conf. Neural Network, Houston, TX, 1997, vol. 4, pp. 2067–2071. [27] F. M. Salam and J. Zhang, “Adaptive neural observer with forward o-state propagation,” in Proc. Int. Joint Conf. Neural Networks (IJCNN’01), Washington, DC, 2001, vol. 1, pp. 675–680. [28] Y. He, M. Wu, J. H. She, and G. P. Liu, “Delay-dependent robust sta- ility criteria for uncertain neutral systems with mixed delays,” Syst. Contr. Lett., vol. 51, no. 1, pp. 57–65, 2004. [29] ——, “Parameter-dependent Lyapunov functional for stability of time-" afb51f0e173cd9ab1d41075862945ae6bc593cde,Large databases of real and synthetic images for feature evaluation and prediction,"Large databases of real and synthetic images for feature evaluation and prediction Biliana K. Kaneva B.A., Computer Science and Mathematics, Smith College (2000) M.S., Computer Science, University of Washington (2005) Submitted to the Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Electrical Engineering and Computer Science t the Massachusetts Institute of Technology February 2012 (cid:13) 2012 Massachusetts Institute of Technology All Rights Reserved. Author: Certified by: Certified by: Accepted by: Department of Electrical Engineering and Computer Science December 22, 2011 William T. Freeman, Professor of Computer Science" afaa607aa9ad0e9dad0ce2fe5b031eb4e525cbd8,Towards an automatic face indexing system for actor-based video services in an IPTV environment,"J. Y. Choi et al.: Towards an Automatic Face Indexing System for Actor-based Video Services in an IPTV Environment Towards an Automatic Face Indexing System for Actor-based Video Services in an IPTV Environment Jae Young Choi, Wesley De Neve, and Yong Man Ro, Senior Member, IEEE" af34388e69800a168876f7446a621f68ca2215c0,Low-cost scene modeling using a density function improves segmentation performance,"Low-Cost Scene Modeling using a Density Function Improves Segmentation Performance Vivek Sharma(cid:5)(cid:63), S¸ule Yildirim-Yayilgan(cid:63), and Luc Van Gool(cid:5)∓" af80dfe0dacf992c49543a4bac53d1974cb70e2e,When Holistic Processing is Not Enough : Local Features Save the Day Lingyun Zhang,"When Holistic Processing is Not Enough: Local Features Save the Day Lingyun Zhang and Garrison W. Cottrell UCSD Computer Science and Engineering 9500 Gilman Dr., La Jolla, CA 92093-0114 USA" af24595c0c8f1b317b6fe2f2b49417cc40094b5c,LSH Softmax : Sub-Linear Learning and Inference of the Softmax Layer in Deep Architectures,"LSH Softmax: Sub-Linear Learning and Inference of the Softmax Layer in Deep Daniel Levy∗ Architectures Danlu Chen† January 31, 2018" af267b44c3ae6c2a0587310021a6180962e835d6,Shape and Symmetry Induction for 3D Objects,"Shape and Symmetry Induction for 3D Objects Shubham Tulsiani1, Abhishek Kar1, Qixing Huang2, Jo˜ao Carreira1 and Jitendra Malik1 University of California, Berkeley 2Toyota Technological Institute at Chicago {shubhtuls, akar, carreira," af8cd04bbe4902123d7042985159a6a5da9d9fb9,Représenter pour suivre : Exploitation de représentations parcimonieuses pour le suivi multi-objets. (Representing to follow: Exploitation of parsimonious representations for multi-object tracking),"Représenter pour suivre : exploitation de représentations parcimonieuses pour le suivi multi-objets Loïc Pierre Fagot-Bouquet To cite this version: Loïc Pierre Fagot-Bouquet. Représenter pour suivre : exploitation de représentations parcimonieuses pour le suivi multi-objets. Automatique. Université Paul Sabatier - Toulouse III, 2017. Français. . HAL Id: tel-01516921 https://tel.archives-ouvertes.fr/tel-01516921v2 Submitted on 4 May 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" afad16c9fee11d8f78785af6b1856beb86b5ccf4,Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions,"Explain to Fix: A Framework to Interpret and Denis Gudovskiy, Alec Hodgkinson Panasonic Beta Research Lab, Mountain View, CA, 94043, USA {denis.gudovskiy, Takuya Yamaguchi, Yasunori Ishii, Sotaro Tsukizawa Panasonic AI Solutions Center, Osaka, Japan {yamaguchi.takuya2015, ishii.yasunori," af053b8cf39612cec0148e14a9c4b7a789d7db11,Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification,"Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification Xavier Roynard, Jean-Emmanuel Deschaud and François Goulette {xavier.roynard ; jean-emmanuel.deschaud ; Mines ParisTech, PSL Research University, Centre for Robotics" af8f59ceed0392159c3475c58af5b7ca8e4f6412,Facial Expression Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." afb6d1e72d5b5506867a74beeb1e661599b8fff3,Dynamic Feature Learning for Partial Face Recognition,"Dynamic Feature Learning for Partial Face Recognition Lingxiao He1 , Haiqing Li1 , Qi Zhang1 , and Zhenan Sun1 CRIPAC & NLPR, CASIA 2 University of Chinese Academy of Sciences, Beijing, P.R. China Center for Excellence in Brain Science and Intelligence Technology, CAS {lingxiao.he, hqli, qi.zhang," af97b793a61ba6e2b02d0d29503b73b5bdc2150d,Wavelet-Local binary pattern based face recognition Azad,"I S S N 2 2 7 7 - 3 0 6 1 V o l u m e 1 6 N u m b e r 1 I N T E R N A T I O N A L J O U R N A L O F C O M P U T E R S & T E C H N O L O G Y Wavelet-Local binary pattern based face recognition Azad Abdullah Ameen(1), Hardi M. M-Saleh(2) ,Zrar Kh. Abdul(3) (1) Charmo University, College of Basic Education, Computer Department,Chamchamal, Raperin, Iraq (2) Charmo University, College of Basic Education, Computer Department, Chamchamal, Raperin, Iraq (3)Charmo University, College of Basic Education, Computer Department, Chamchamal, Raperin, Iraq" af62621816fbbe7582a7d237ebae1a4d68fcf97d,Active Shape Model Based Recognition Of Facial Expression,"International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 International Conference on Humming Bird ( 01st March 2014) RESEARCH ARTICLE OPEN ACCESS Active Shape Model Based Recognition Of Facial Expression AncyRija V , Gayathri. S2 AncyRijaV,Author is currently pursuing M.E (Software Engineering) in Vins Christian College of Engineering, e-mail: Gayathri.S, M.E., Asst.Prof.,Department of Information Technology , Vins Christian college of Engineering." afb1bc830febdb9893fd938fbdb20856b4ff3922,Defoiling Foiled Image Captions,"Defoiling Foiled Image Captions Pranava Madhyastha, Josiah Wang and Lucia Specia Department of Computer Science University of Sheffield, UK {p.madhyastha, j.k.wang," af1fa9d29512fc8f4c07efdf75d3f640567a5262,Sparse Representation for Face Recognition Based on Constraint Sampling and Face Alignment,"TSINGHUA SCIENCE AND TECHNOLOGY ISSNll1007-0214ll08/12llpp62-67 Volume 18, Number 1, February 2013 Sparse Representation for Face Recognition Based on Constraint Sampling and Face Alignment Jing Wang, Guangda Su(cid:3), Ying Xiong, Jiansheng Chen, Yan Shang, Jiongxin Liu, and Xiaolong Ren" af740db182b541eef80bb0a2dfebd1f07bb0e316,Deformable Kernel Networks for Joint Image Filtering,"Deformable Kernel Networks for Joint Image Filtering Beomjun Kim, Jean Ponce, Bumsub Ham To cite this version: Beomjun Kim, Jean Ponce, Bumsub Ham. Deformable Kernel Networks for Joint Image Filtering. 018. HAL Id: hal-01857016 https://hal.archives-ouvertes.fr/hal-01857016v2 Submitted on 10 Oct 2018 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés." 39df6ca15f41e5a674ed8cd1654e699dbc8b8c11,Human tracking over camera networks: a review,"Hou et al. EURASIP Journal on Advances in Signal Processing (2017) 2017:43 DOI 10.1186/s13634-017-0482-z EURASIP Journal on Advances in Signal Processing R EV I E W Human tracking over camera networks: a review Li Hou1,2,3*, Wanggen Wan1,3, Jenq-Neng Hwang4, Rizwan Muhammad1,3, Mingyang Yang1,3 and Kang Han1,3 Open Access" 39d406df1823aad167a429f60ae8f1d3dc4250fa,Scaling for Multimodal 3D Object Detection,"Scaling for Multimodal 3D Object Detection Andrej Karpathy Stanford" 39803a9c075d543e19384d79fb4c36b207892179,Regression Techniques versus Discriminative Methods for Face Recognition,"Regression Techniques versus Discriminative Methods for Face Recognition Vitomir ˇStruc, France Miheliˇc, Rok Gajˇsek and Nikola Paveˇsi´c" 3903cbd56446436a4a3b8443c26c90fc1b69f5e0,Event driven software architecture for multi-camera and distributed surveillance research systems,"Event Driven Software Architecture for Multi-camera and Distributed Surveillance Research Systems Roberto Vezzani, Rita Cucchiara University of Modena and Reggio Emilia - Italy" 39ad6ce5f67c76fc1488ce6a31ebdf229b3f34df,Detection of Humans Using Color Information,"Detection of Humans Using Color Information V·(cid:17)t Nov·ak May 23, 2001" 39dc2ce4cce737e78010642048b6ed1b71e8ac2f,Recognition of six basic facial expressions by feature-points tracking using RBF neural network and fuzzy inference system,"Recognition of Six Basic Facial Expressions by Feature-Points Tracking using RBF Neural Network and Fuzzy Inference System Hadi Seyedarabi*, Ali Aghagolzadeh **, Sohrab Khanmohammadi ** *Islamic Azad University of AHAR **Elect. Eng. Faculty, Tabriz University, Tabriz, Iran" 39a71ceb241f34b30ffd248669346c059dd1ec97,Gait Recognition Based on Human Body Components,"-4244-1437-7/07/$20.00 ©2007 IEEE I - 353 ICIP 2007" 398ad0036b899aec04502c243dd129c1f3e4c21e,Object detection using voting spaces trained by few samples,"Downloaded From: https://www.spiedigitallibrary.org/journals/Optical-Engineering on 12/17/2017 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use ObjectdetectionusingvotingspacestrainedbyfewsamplesPeiXuMaoYeXueLiLishenPeiPengweiJiao" 399a5f7500648462fd8cf1704dfaeaea9d560e7e,Spoof Detection for Finger-Vein Recognition System Using NIR Camera,"Article Spoof Detection for Finger-Vein Recognition System Using NIR Camera Dat Tien Nguyen, Hyo Sik Yoon, Tuyen Danh Pham and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (D.T.N.); (H.S.Y.); (T.D.P.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Received: 15 August 2017; Accepted: 27 September 2017; Published: 1 October 2017" 390e212d4a874d8d2256e55fe0dee9193e4c376a,Just in Time: Controlling Temporal Performance in Crowdsourcing Competitions,"Just in Time: Controlling Temporal Performance in Crowdsourcing Competitions Markus Rokicki L3S Research Center, Hannover, Germany Electronics and Computer Science, University of Southampton, Southampton, Sergej Zerr" 39149c51c5ab3442b43b8d19eca704efde450f51,Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals,"Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals Suha Kwak1,∗ ´Ecole Normale Sup´erieure / PSL Research University Cordelia Schmid1,† Jean Ponce2,∗ Minsu Cho1,∗ Inria" 39a6b9c8d45aa3bf29aede1ba0d4060a4afb834a,Inferring The Latent Structure of Human Decision-Making from Raw Visual Inputs,"Inferring The Latent Structure of Human Decision-Making from Raw Visual Inputs Yunzhu Li 1 Jiaming Song 2 Stefano Ermon 2" 39c8b34c1b678235b60b648d0b11d241a34c8e32,Learning to Deblur Images with Exemplars,"Learning to Deblur Images with Exemplars Jinshan Pan∗, Wenqi Ren∗, Zhe Hu∗, and Ming-Hsuan Yang" 39df4f8ad7add3863208a5f7b71e22ed1970ca58,Bayesian supervised dictionary learning,"Bayesian Supervised Dictionary learning B. Babagholami-Mohamadabadi A. Jourabloo M. Zolfaghari M.T. Manzuri-Shalmani CE Dept. Sharif University Tehran, Iran CE Dept. Sharif University Tehran, Iran CE Dept. Sharif University Tehran, Iran CE Dept. Sharif University Tehran, Iran" 3910b1cc849f999dc8a2c02a0313be32dd5d2b43,A Systematic Comparison of Deep Learning Architectures in an Autonomous Vehicle,"A Systematic Comparison of Deep Learning Architectures in an Autonomous Vehicle Michael Teti1†, William Edward Hahn1, Shawn Martin2, Christopher Teti3, and Elan Barenholtz1 such tasks, or an attempt largely due to recent developments" 397085122a5cade71ef6c19f657c609f0a4f7473,Using Segmentation to Predict the Absence of Occluded Parts,"GHIASI, FOWLKES: USING SEGMENTATION TO DETECT OCCLUSION Using Segmentation to Predict the Absence of Occluded Parts Golnaz Ghiasi Charless C. Fowlkes Dept. of Computer Science University of California Irvine, CA" 39ed31ced75e6151dde41944a47b4bdf324f922b,Pose-Guided Photorealistic Face Rotation,"Pose-Guided Photorealistic Face Rotation Yibo Hu1,2, Xiang Wu1, Bing Yu3, Ran He1,2 ∗, Zhenan Sun1,2 CRIPAC & NLPR & CEBSIT, CASIA 2University of Chinese Academy of Sciences Noah’s Ark Laboratory, Huawei Technologies Co., Ltd. {yibo.hu, {rhe," 39b080aea9b342947058884ca25fb5bb1b8f6d66,Fully Automated and Highly Accurate Dense Correspondence for Facial Surfaces,"Fully Automated and Highly Accurate Dense Correspondence for Facial Surfaces C. Martin Grewe and Stefan Zachow Mathematics for Life and Materials Sciences, Zuse Institute Berlin, Germany Fig. 1: Two facial expressions (a,b) from our database set into dense correspon- dence using the proposed framework. High geometric and photometric details are ccurately morphed between both expressions via a dense corresponding mesh." 3964caa0a1d788eb30365972880f83b71df1ab21,Multi-Modal Obstacle Detection in Unstructured Environments with Conditional Random Fields,"Multi-Modal Obstacle Detection in Unstructured Environments with Conditional Random Fields Mikkel Kragh1 and James Underwood2" 39a76fdc4b2d4b9e8ef8f69a87d17ae930520acc,Occlusion-Aware Human Pose Estimation with Mixtures of Sub-Trees,"Occlusion-Aware Human Pose Estimation with Mixtures of Sub-Trees Ibrahim Radwan∗, Abhinav Dhall and Roland Goecke" 392c3cabe516c0108b478152902a9eee94f4c81e,Tiny images,"Computer Science and Artificial Intelligence Laboratory Technical Report MIT-CSAIL-TR-2007-024 April 23, 2007 Tiny images Antonio Torralba, Rob Fergus, and William T. Freeman m a s s a c h u s e t t s i n s t i t u t e o f t e c h n o l o g y, c a m b r i d g e , m a 0 213 9 u s a — w w w. c s a i l . m i t . e d u" 3918dcfddf2da218a615dd8f008f6fce436e06f7,Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning,"Int J Comput Vis manuscript No. (will be inserted by the editor) Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning Andrew Owens · Jiajun Wu · Josh H. McDermott · William T. Freeman · Antonio Torralba Received: date / Accepted: date" 3902f38412c6dd8915bb408dea500650864b8d6e,Predicting Actions from Static Scenes,"Predicting Actions from Static Scenes Tuan-Hung Vu1, Catherine Olsson2, Ivan Laptev1, Aude Oliva2, and Josef Sivic1 WILLOW, ENS/INRIA/CNRS UMR 8548, Paris, France CSAIL, MIT, Cambridge, Massachusetts, USA" 39a49d7d84305d334b5fb00c25b812bffdd772a6,Sélection de modèles en classification supervisée,"INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE Model selection in supervised classification Guillaume Bouchard — Gilles Celeux N° 5391 November 2004 Thème COG p p o r t (cid:13) (cid:13) d e r e c h e r c h e (cid:13)" 39fc0fe46ddf43f13073cbab077d981547889dc1,USING GRADIENT FEATURES FROM SCALE-INVARIANT KEYPOINTS ON FACE RECOGNITION,"International Journal of Innovative Computing, Information and Control Volume 7, Number 4, April 2011 ICIC International c⃝2011 ISSN 1349-4198 pp. 1639{1649 USING GRADIENT FEATURES FROM SCALE-INVARIANT KEYPOINTS ON FACE RECOGNITION Shinfeng D. Lin, Jia-Hong Lin and Cheng-Chin Chiang Department of Computer Science and Information Engineering National Dong Hwa University No. 1, Sec. 2, Da Hsueh Rd., Shoufeng, Hualien 97401, Taiwan f david; bbmac; Received November 2009; revised March 2010" 3917bf2cc075ef075d9c879fc9ec3349ea116735,Discriminant Analysis by Locally Linear Transformations,"Discriminant Analysis by Locally Linear Transformations Tae-Kyun Kim1,2, Josef Kittler2, Hyun-Chul Kim3, and Seok Cheol Kee1 : Samsung Advanced Institute of Technology, KOREA : Center for Vision, Speech and Signal Processing, University of Surrey,U.K. : Pohang University of Science and Technology, KOREA" 397fffa6f785762acb3cd3c96c4c6b65058b816f,Modeling mutual context of object and human pose in human-object interaction activities,"Modeling Mutual Context of Object and Human Pose in Human-object Interaction Activities •  Bangpeng Yao •  Li Fei-Fei Presented by Sahil Shah" 397c395aed9d96aef064b9ceb9f0eae9421eb00a,An Evaluation of the Pedestrian Classification in a Multi-Domain Multi-Modality Setup,"Sensors 2015, 15, 13851-13873; doi:10.3390/s150613851 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article An Evaluation of the Pedestrian Classification in Multi-Domain Multi-Modality Setup Alina Miron 1,*, Alexandrina Rogozan 2, Samia Ainouz 2, Abdelaziz Bensrhair 2 nd Alberto Broggi 3 ISR Laboratory, University of Reading, Reading RG6 6AY, UK INSA Rouen/LITIS laboratory - EA4108, Saint-Etienne du Rouvray 76801, France; E-Mails: (A.R.); (S.A.); (A.B.) VisLab, University of Parma, Parco Area delle Scienze 181A, 43100 Parma, Italy; E-Mail: * Author to whom correspondence should be addressed; E-Mail: Tel.: +44-118-378-7631. Academic Editor: Vittorio M.N. Passaro Received: 2 April 2015 / Accepted: 8 June 2015 / Published: 12 June 2015" 39d08fa8b028217384daeb3e622848451809a422,Variational Approaches for Auto-Encoding Generative Adversarial Networks,"Variational Approaches for Auto-Encoding Generative Adversarial Networks Mihaela Rosca∗ Balaji Lakshminarayanan∗ David Warde-Farley Shakir Mohamed DeepMind" 390dc36d547dbf9bc9774ec8de454e6317a2d170,InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity,"Improving Face Attribute Detection with Race and Gender Diversity InclusiveFaceNet: Hee Jung Ryu 1 Hartwig Adam * 1 Margaret Mitchell * 1" 39340257d9a478b3c3b736ad31df1c0a6a78c851,Parts-based object recognition seeded by frequency-tuned saliency for child detection in active safety,"Parts-based object recognition seeded by frequency-tuned saliency for Child Detection in Active Safety Shinko Y. Cheng, Jose Molineros, Yuri Owechko HRL Laboratories, LLC 011 Malibu Canyon Road Malibu CA 90265" 3965d73c9d7c97cdb391bfd86a15bfd3534cbd32,Deep Learning for Visual Question Answering,"Deep Learning for Visual Question Answering Avi Singh" 39b0bce87eec467adfe5bebcfe628ff5bd397fc7,"R 4-A . 2 : Rapid Similarity Prediction , Forensic Search & Retrieval in Video","R4-A.2: Rapid Similarity Prediction, Forensic Search & Retrieval in Video PARTICIPANTS Venkatesh Saligrama David Castañón Ziming Zhang Gregory Castañón Yuting Chen Marc Eder Faculty/Staff Institution Title Co-PI Co-PI Post-Doc Graduate, Undergraduate and REU Students Degree Pursued Institution Email Month/Year of Graduation" 395978c1dee9fd75bbcb249e74ad6fb4d3c2b9fc,A Reliable Hybrid Technique for Human Face Detection,"Hakim A., Marsland S. and W. Guesgen H. (2010). A RELIABLE HYBRID TECHNIQUE FOR HUMAN FACE DETECTION. In Proceedings of the International Conference on Computer Vision Theory and Applications, pages 241-244 Copyright c(cid:13) SciTePress" 39bce1d5e4b31a555f12f0a44e92abcad73aab4f,"Explorer "" Here ' s looking at you , kid ""","""Here's looking at you, kid"" Citation for published version: Marin-Jimenez, M, Zisserman, A & Ferrari, V 2011, ""Here's looking at you, kid"": Detecting people looking at each other in videos. in Proceedings of the British Machine Vision Conference (BMVC): Dundee, September 011. BMVA Press, pp. 22.1-22.12. DOI: 10.5244/C.25.22 Digital Object Identifier (DOI): 0.5244/C.25.22 Link: Link to publication record in Edinburgh Research Explorer Document Version: Peer reviewed version Published In: Proceedings of the British Machine Vision Conference (BMVC) General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) nd / or other copyright owners and it is a condition of accessing these publications that users recognise and bide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer ontent complies with UK legislation. If you believe that the public display of this file breaches copyright please" 39af7f265dc9d647d97d94a1d0c12fa36f9f79e9,Deep Anticipation: Light Weight Intelligent Mobile Sensing in IoT by Recurrent Architecture,"JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 Deep Anticipation: Lightweight Intelligent Mobile Sensing in IoT by Recurrent Architecture Guang Chen*1,4, Shu Liu*2, Kejia Ren1, Zhongnan Qu2, Changhong Fu5, Gereon Hinz3, and Alois Knoll4" 3979e8ddcf95fedf7a220b7d39a72fa120d436f8,Deep Learning Applied to Image and Text Matching,"Deep Learning applied to Image and Text matching MASTER THESIS IN COMPUTER SCIENCE Author: Afroze Ibrahim Baqapuri Supervisors: Dr. François Fleuret Dr. Eric Cosatto January 15, 2016" 39e7ac344b17d97267ec80681aeded17e3e6d786,Joint Parsing of Cross-view Scenes with Spatio-temporal Semantic Parse Graphs,"Joint Parsing of Cross-view Scenes with Spatio-temporal Semantic Parse Graphs∗ Hang Qi1∗, Yuanlu Xu1∗, Tao Yuan1∗, Tianfu Wu2, Song-Chun Zhu1 Dept. Computer Science and Statistics, University of California, Los Angeles (UCLA) {hangqi, tianfu Dept. Electrical and Computer Engineering, NC State University" 39db2ff704cc30a7e94989de33ff4290ea4a6df1,Low-Cost Visual Feature Representations For Image Retrieval,"Low-Cost Visual Feature Representations For Image Retrieval Ramon F. Pessoa, William R. Schwartz, Jefersson A. dos Santos Department of Computer Science Universidade Federal de Minas Gerais (UFMG) Belo Horizonte - Minas Gerais, Brazil, 31270-901 Email: {ramon.pessoa, william," 391e52ac04408d3e6496614ffafd6ac89c1b6c45,Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models,"Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models Mathieu Aubry1,∗ Daniel Maturana2 Alexei A. Efros3,∗ Bryan C. Russell4 Josef Sivic1,∗ INRIA 2Carnegie Mellon University UC Berkeley Intel Labs" 3988ed2b900af26c07432d0f9f3c2679f3c532ac,Vision Meets Drones: A Challenge,"Vision Meets Drones: A Challenge Pengfei Zhu, Longyin Wen, Xiao Bian, Haibin Ling and Qinghua Hu" 399f321089a3a35ddf0e92435dfc374cbcc3dbbd,A Novel Approach for Automatic Standing Upper Body Extraction Based on Skin Detection and Anthropometric Constraint from Single Image,"International Journal of Engineering, Management & Sciences (IJEMS) ISSN-2348 –3733, Volume-3, Issue-6, JUNE- 2016 A Novel Approach for Automatic Standing Upper Body Extraction Based on Skin Detection and Anthropometric Constraint from Single Image Rashmi sinha, Vijay Kumar Sharma" 3933e323653ff27e68c3458d245b47e3e37f52fd,Evaluation of a 3 D-aided Pose Invariant 2 D Face Recognition System,"Evaluation of a 3D-aided Pose Invariant 2D Face Recognition System Xiang Xu, Ha A. Le, Pengfei Dou, Yuhang Wu, Ioannis A. Kakadiaris {xxu18, hale4, pdou, ywu35, Computational Biomedicine Lab 800 Calhoun Rd. Houston, TX, USA" 395dadff1eab9c8177f843326ec864567342eba5,Vision-Based People Detection System for Heavy Machine Applications,"Article Vision-Based People Detection System for Heavy Machine Applications Vincent Fremont 1,*, Manh Tuan Bui 1, Djamal Boukerroui 1 and Pierrick Letort 2 Received: 12 October 2015; Accepted: 13 January 2016; Published: 20 January 2016 Academic Editor: Vittorio M. N. Passaro Sorbonne Universités, Université de Technologie de Compiègne, CNRS, UMR 7253, Heudiasyc-CS 60 319, 60 203 Compiègne Cedex, France; (M.T.B.); (D.B.) Technical Center for the Mechanical Industry (CETIM), 60300 Senlis, France; * Correspondence: Tel.: +33-344-237-917; Fax: +33-344-234-477" 3921afded8bc8471d784df86f64432fb14b8ef58,Egocentric Gesture Recognition for Head-Mounted AR devices,"Egocentric Gesture Recognition for Head-Mounted AR devices Tejo Chalasani* Jan Ondrej† Aljosa Smolic‡ V-SENSE, School of Computer Science and Statistics Trinity College Dublin" 3998c5aa6be58cce8cb65a64cb168864093a9a3e,Understanding head and hand activities and coordination in naturalistic driving videos,Intelligent Vehicles Symposium 2014 3907d83f14ba9e2b8a93c3f02b04ca0b81901c4b,Semantic segmentation-using Convolutional Neural Networks and Sparse Dictionaries,"Master of Science Thesis in Electrical Engineering Department of Electrical Engineering, Linköping University, 2017 Semantic segmentation - using Convolutional Neural Networks nd Sparse Dictionaries Viktor Andersson" 39d900da87fa2f8987567d22a924fb7674f9be67,Generating Notifications for Missing Actions: Don't Forget to Turn the Lights Off!,"Generating Notifications for Missing Actions: Don’t forget to turn the lights off! Bilge Soran*, Ali Farhadi*†, Linda Shapiro* *University of Washington Allen Institute for Artificial Intelligence {bilge, ali, Figure 1: Our purpose is to issue notifications about missing actions given an unsegmented input stream of egocentric video. For the latte making sequence above, our system recognizes the actions that happened so far, predicts the ongoing action, reasons about missing actions and the associated cost, and generates notifications for the costly missing actions. In this figure, the brackets refer to segmented action boundaries, the blue arrows show the prediction points and the graphs below show the inter-action dependencies. The most recently completed action is marked in red, the predicted action is marked in blue, and the missing action is marked in orange. In this example, the actor is about to miss an important action: steam milk, and a reminder for that is given." 399ab5652908d99a5be1a664425f6463f67df2aa,Mechanisms of Diminished Attention to Eyes in Autism.,"Mechanisms of diminished attention to eyes in utism Jennifer M. Moriuchi, Emory University Ami Klin, Emory University Warren R Jones, Emory University Journal Title: American Journal of Psychiatry Volume: Volume 174, Number 1 Publisher: American Psychiatric Publishing | 2017-01-01, Pages 26-35 Type of Work: Article | Post-print: After Peer Review Publisher DOI: 10.1176/appi.ajp.2016.15091222 Permanent URL: https://pid.emory.edu/ark:/25593/s8mpz Final published version: http://dx.doi.org/10.1176/appi.ajp.2016.15091222 Copyright information: 018 American Psychiatric Association Accessed June 11, 2018 8:03 PM EDT" 39a19a687b3182054b30f36f627bc6875b09dbd3,A new boostrapping strategy for the AdaBoost-based face detector T.-J. Chin and D. Suter A new boostrapping strategy for the AdaBoost-based face detector,"Department of Electrical Computer Systems Engineering Technical Report MECSE-13-2005 A new boostrapping strategy for the AdaBoost-based face detector T.-J. Chin and D. Suter" 39c6897ed1a7157cd8370f2b9269f9cfc477d64b,Intent-Aware Diverse Social Image Retrieval,Intent-AwareDiverseSocialImageRetrievalWangBo 399e1b0b84d6b5199646892e8bddb9e4d7f45362,Memorable Maps: A Framework for Re-defining Places in Visual Place Recognition,"Memorable Maps: A Framework for Re-defining Places in Visual Place Recognition Mubariz Zaffar1, Shoaib Ehsan1, Michael Milford2 and Klaus Mcdonald Maier1" a2505774d5654685c6d899760759520b339e6c1e,Ranking Eigenfaces Through Adaboost and Perceptron Ensembles,"Ranking Eigenfaces Through Adaboost and Perceptron Ensembles Tiene A. Filisbino, Gilson A. Giraldi Laborat´orio Nacional de Computac¸˜ao Cient´ıfica - LNCC Petr´opolis, Brasil Email: Carlos Eduardo Thomaz Departamento de Engenharia El´etrica Centro Universit´ario da FEI S˜ao Bernardo do Campo - Brasil Email:" a271f83cb1f72e0f9ca077499f51adb086fb449d,Unsupervised and Semi-supervised Methods for Human Action Analysis,"Unsupervised and Semi-supervised Methods for Human Action Analysis Simon Jones September 22, 2014 A thesis submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy Department of Electronic and Electrical Engineering The University of Shef‌f‌ield" a2268e3ec394bd8e7dfb131b931fdc00547d3f39,Neural learning methods for visual object detection; Neuronale Lernverfahren zur visuellen Objekterkennung,"Neural learning methods for visual object detection (Neuronale Lernverfahren zur visuellen Objekterkennung) Dissertation zur Erlangung des Grades ”Doktor der Naturwissenschaften” n der Fakult¨at f¨ur Physik und Astronomie der Ruhr-Universit¨at Bochum vorgelegt von Alexander Rainer Tassilo Gepperth m 19.April 2006" a237e3d89c460e1b2e3f12c5d4275bd0c6eb47a8,Domain Adaptation on Graphs by Learning Aligned Graph Bases,"Domain Adaptation on Graphs by Learning Aligned Graph Bases Mehmet Pilancı and Elif Vural" a2ad9ae7c5adbbce9ded16ac3ebdfa96505c0f46,Déjà Image-Captions: A Corpus of Expressive Descriptions in Repetition,"Human Language Technologies: The 2015 Annual Conference of the North American Chapter of the ACL, pages 504–514, Denver, Colorado, May 31 – June 5, 2015. c(cid:13)2015 Association for Computational Linguistics" a24a0126f76ba1423ac3548ef95aa24ac4e670dd,How Would You Say It ? Eliciting Lexically Diverse Data for Supervised Semantic Parsing,"Saarbr¨ucken, Germany, 15-17 August 2017. c(cid:13)2017 Association for Computational Linguistics Proceedings of the SIGDIAL 2017 Conference, pages 374–383," a22b6aa079c07229d813c53663db689f34290d4d,Dropout Distillation for Efficiently Estimating Model Confidence,"Dropout Distillation for Efficiently Estimating Model Confidence Corina Gurau, Alex Bewley and Ingmar Posner" a2b78155f74ba697b76f83aa3cf2d4935434628d,An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark,"An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark. Stefan Becker ∗, Ronny Hug ∗, Wolfgang H¨ubner and Michael Arens Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation IOSB Gutleuthausstr. 1, 76275 Ettlingen, Germany" a248805c5d9a5626dbd4f58906b35d991e2aec4b,Multi-Hypothesis Visual-Inertial Flow,"Multi-Hypothesis Visual-Inertial Flow E. Jared Shamwell1, William D. Nothwang2, Donald Perlis3" a2c08d63682b348a9848a77f9b97378a37a6b447,Curriculum Adversarial Training, a23e7e71fb92a56c2e7717f6356e8b69fc2f4bfc,"Multimodal fusion of audio, scene, and face features for first impression estimation","Multimodal Fusion of Audio, Scene, and Face Features for First Impression Estimation Furkan G¨urpınar Program of Computational Science and Engineering Bo˘gazic¸i University Bebek, Istanbul, Turkey Email: Heysem Kaya Albert Ali Salah Department of Computer Engineering Department of Computer Engineering Namık Kemal University C¸ orlu, Tekirda˘g, Turkey Email: Bo˘gazic¸i University Bebek, Istanbul, Turkey Email:" a212be7ec1ff75ecfee52c7c49c73d7244a87eb7,Video Scene-Aware Dialog Track in DSTC 7,"Video Scene-Aware Dialog Track in DSTC7 Chiori Hori∗, Tim K. Marks∗, Devi Parikh∗∗, and Dhruv Batra∗∗ Mitsubishi Electric Research Laboratories Cambridge, MA, USA {chori, School of Interactive Computing Georgia Tech {parikh," a2bfab80a4b48717aa647cb38069632c5962c6a6,Countering Bias in Tracking Evaluations, a21b8aadb27cd10d8a228fe1aad27c0c88d67f15,Design and Implementation of PC Operated Flying Robot for Rescue Operation in Coalmines,"ISSN: 2278 – 7798 International Journal of Science, Engineering and Technology Research (IJSETR) Volume 2, Issue 1, January 2013 Design and Implementation of PC Operated Flying Robot for Rescue Operation in Coalmines Aditya Kumar T , Pravin A, M S Madhan mohan, T V Janardhanarao" a27735e4cbb108db4a52ef9033e3a19f4dc0e5fa,Intention from Motion,"Intention from Motion Andrea Zunino, Jacopo Cavazza, Atesh Koul, Andrea Cavallo, Cristina Becchio and Vittorio Murino" a2afaa782be91f5baf9e9f1794d57dd29143cbf4,IGCV$2$: Interleaved Structured Sparse Convolutional Neural Networks,"IGCV2: Interleaved Structured Sparse Convolutional Neural Networks Guotian Xie1,2,∗ Jingdong Wang3 Ting Zhang3 Jianhuang Lai1,2 Richang Hong4 Guo-Jun Qi5 Sun Yat-Sen University 2Guangdong Key Laboratory of Information Security Technology Microsoft Research 4Hefei University of Technology 5University of Central Florida" a2db611b6179f3bc4cfe0e891df7b9d4ab58d642,On the usability of deep networks for object-based image analysis,"ON THE USABILITY OF DEEP NETWORKS FOR OBJECT-BASED IMAGE ANALYSIS Nicolas Audeberta, b, Bertrand Le Sauxa, Sébastien Lefèvreb ONERA, The French Aerospace Lab, F-91761 Palaiseau, France Univ. Bretagne-Sud, UMR 6074, IRISA, F-56000 Vannes, France - KEY WORDS: deep learning, vehicle detection, semantic segmentation, object classification" a2359c0f81a7eb032cff1fe45e3b80007facaa2a,Towards Structured Analysis of Broadcast Badminton Videos,"Towards Structured Analysis of Broadcast Badminton Videos Anurag Ghosh Suriya Singh C.V.Jawahar {anurag.ghosh, CVIT, KCIS, IIIT Hyderabad" a27c7afac5a34141ec5415defed6d4d85325230a,Utrecht Multi-Person Motion ( UMPM ) benchmark,"Utrecht Multi-Person Motion (UMPM) enchmark N.P. van der Aa, X. Luo, G.-J. Giezeman R.T. Tan, R.C. Veltkamp Technical Report UU-CS-2011-027 September 2011 Department of Information and Computing Sciences Utrecht University, Utrecht, The Netherlands www.cs.uu.nl" a2fce1c551a3c3b1cac16a96f86a59cd7fbd4c80,Attachment and Children’s Biased Attentional Processing: Evidence for the Exclusion of Attachment-Related Information,"Attachment and Children’s Biased Attentional Processing: Evidence for the Exclusion of Attachment- Related Information Eva Vandevivere1*, Caroline Braet1, Guy Bosmans2, Sven C. Mueller3, Rudi De Raedt3 Department of Developmental, Personality and Social Psychology, Ghent University, Gent, Belgium, 2 Parenting and Special Education Research Unit, Leuven, Belgium, Department of Experimental Clinical and Health Psychology, Ghent University, Ghent, Belgium" a2b9c998264ab1920ea8f2e07c3590ebb3dc6f35,Shopper Analytics: A Customer Activity Recognition System Using a Distributed RGB-D Camera Network,"Shopper Analytics: a customer activity recognition system using a distributed RGB-D amera network Daniele Liciotti, Marco Contigiani, Emanuele Frontoni, Adriano Mancini, Primo Zingaretti1, and Valerio Placidi2 Dipartimento di Ingegneria dell’Informazione, Universit`a Politecnica delle Marche, {d.liciotti, m.contigiani,e.frontoni, a.mancini, Via Brecce Bianche, 60131 Ancona, Italy, Grottini Lab srl, Via S.Maria in Potenza, 62017, Porto Recanati, Italy," a2f2996145d3d670608af1cbbda59c1ac28d4f7c,Real-Time Hand Posture Recognition for Human-Robot Interaction Tasks,"Article Real-Time Hand Posture Recognition for Human-Robot Interaction Tasks Uriel Haile Hernandez-Belmonte and Victor Ayala-Ramirez * Received: 30 October 2015; Accepted: 18 December 2015; Published: 4 January 2016 Academic Editor: Lianqing Liu Universidad de Guanajuato DICIS, Carr. Salamanca-Valle Km. 3.5 + 1.8, Palo Blanco, Salamanca, C.P. 36885, Mexico; * Correspondence: Tel.: +52-464-647-9940 (ext. 2413); Fax: +52-464-647-9940 (ext. 2311)" a24f84b156bbb1edeb1d0761f5940de318b7ed9d,Copula Eigenfaces - Semiparametric Principal Component Analysis for Facial Appearance Modeling, a290019f7125f6ebdc0dcec3b03b771de6905dd0,Heterogeneous AdaBoost with Real-time Constraints - Application to the Detection of Pedestrians by Stereovision,"HETEROGENEOUS ADABOOST WITH REAL-TIME Application to the Detection of Pedestrians by stereovision CONSTRAINTS Lo¨ıc Jourdheuil1, Nicolas Allezard1, Thierry Chateau2 and Thierry Chesnais1 CEA, LIST, Laboratoire Vision et Ing´enierie des Contenus, Gif-sur-Yvette, France LASMEA, UMR UBP-CNRS 6602, 24 Avenue des Landais, AUBIERE, France {loic.jourdheuil, nicolas.allezard, Keywords: Adaboost. stereovision. real time." a2a42aa37641490213b2de9eb8e83f3dab75f5ed,Multilinear Supervised Neighborhood Preserving Embedding Analysis of Local Descriptor Tensor,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." a28f831b4014fa75a69f3c56e39d9c40fc0af48f,AAD: Adaptive Anomaly Detection through traffic surveillance videos,"AAD: Adaptive Anomaly Detection through traffic surveillance videos Mohammad Farhadi Bajestani Seyed Soroush Heidari Rahmat Abadi Seyed Mostafa Derakhshandeh Fard Roozbeh Khodadadeh" a2aa272b32c356ec9933b32ca5809c09f2d21b9f,Clockwork Convnets for Video Semantic Segmentation,"Clockwork Convnets for Video Semantic Segmentation Evan Shelhamer(cid:63) Kate Rakelly(cid:63) Judy Hoffman(cid:63) Trevor Darrell UC Berkeley" a27740f8a3834d6bc605a6b383c4d802ced373c9,"Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification","Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification Julio C. S. Jacques Juniora,b,∗, Xavier Bar´oa,b, Sergio Escalerac,b Faculty of Computer Science, Multimedia and Telecommunication - Universitat Oberta de Catalunya, Spain Computer Vision Center - Universitat Aut`onoma de Barcelona, Spain Department of Mathematics and Informatics - University of Barcelona, Spain" f3a9651405695d03bb76e141a7999f2addc4225d,Constellation Models for Recognition of Generic Objects, f3b56b873c48929361c1cada7b18177e3f4d2727,"Development of a N-type GM-PHD Filter for Multiple Target, Multiple Type Visual Tracking","Development of a N-type GM-PHD Filter for Multiple Target, Multiple Type Visual Tracking Nathanael L. Baisa , Student Member, IEEE, and Andrew Wallace, Fellow, IET faced challenges not only in the uncertainty caused by data ssociation but also in algorithmic complexity that increases exponentially with the number of targets and measurements. For instance, the MHT has an exponential complexity with time and cubic with the number of targets. To address the problems of increasing complexity, a unified framework which directly extends single to multiple target tracking by representing multi-target states and observations s random finite sets (RFS) was developed by Mahler [7]. This estimates the states and cardinality of an unknown and time varying number of targets in the scene, and allows for target birth, death, handling clutter (false alarms), and missing detections. Mahler [7] proposed to propagate the first-order moment of the multi-target posterior, called the Probability Hypothesis Density (PHD), rather than the full multi-target posterior." f3b3d2c0d1d84a7f7bbaaaecb58457c15a947544,Understanding Grounded Language Learning Agents,"UNDERSTANDING GROUNDED LANGUAGE LEARNING AGENTS Felix Hill, Karl Moritz Hermann, Phil Blunsom & Stephen Clark Deepmind London {felixhill, kmh, pblunsom," f3dc67bb4cd3601ae9bdb7df4ed5036f525ff21d,Multimodal 2 DCNN action recognition from RGB-D Data with Video Summarization,"Master’s Thesis Multimodal 2DCNN action recognition from RGB-D Data with Video Summarization Vicent Roig Ripoll Master Artificial Intelligence Advisor: Sergio Escalera Guerrero Co-advisor: Maryam Asadi-Aghbolaghi October, 2017" f308e00f4fa0f0a995a82e9b825ebcfa3ba0d9f1,Embedded System for Biometric Identiication,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." f3a34525fa7021322f132c80c9517f240cf1e742,Pose and Pathosformel in Aby Warburg's Bilderatlas,"Pose and Pathosformel in Aby Warburg’s Bilderatlas Leonardo Impett, Sabine S¨usstrunk School of Computer and Communication Sciences, ´Ecole F´ed´erale Polytechnique de Lausanne, Switzerland" f3161b75de1e37b0591f250068b676ea72d1ba22,"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning Michael Everett‡, Yu Fan Chen†, and Jonathan P. How‡" f3412c087282fcd60f08083515714f97179bedcb,"A study on different experimental configurations for age, race, and gender estimation problems","Carcagnì et al. EURASIP Journal on Image and Video Processing (2015) 2015:37 DOI 10.1186/s13640-015-0089-y RESEARCH Open Access A study on different experimental onfigurations for age, race, and gender estimation problems Pierluigi Carcagnì*, Marco Del Coco, Dario Cazzato, Marco Leo and Cosimo Distante" f34c85c24661ba9990146737fd557f7508677263,A New Pedestrian Detection Descriptor Based on the Use of Spatial Recurrences,"A New Pedestrian Detection Descriptor Based on the Use of Spatial Recurrences Carlos Serra-Toro and V. Javier Traver Departamento de Lenguajes y Sistemas Inform´aticos & Institute of New Imaging Technologies, Universitat Jaume I, 12071 Castell´on, Spain" f3d9e347eadcf0d21cb0e92710bc906b22f2b3e7,"NosePose : a competitive , landmark-free methodology for head pose estimation in the wild","NosePose: a competitive, landmark-free methodology for head pose estimation in the wild Fl´avio H. B. Zavan, Antonio C. P. Nascimento, Olga R. P. Bellon and Luciano Silva IMAGO Research Group - Universidade Federal do Paran´a" f33c427dc152c20537d2857bee1dda2287e85860,Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks, f3c60536cf7a397c9df6bca549824841a6d7598c,Automatic architecture selection for probability density function estimation in computer vision,"7308011 UNIVERSITY OF SURREY LIBRARY" f36c3ddd43ea7c2e803694aad89e5fd903715c81,"Biometric quality: a review of fingerprint, iris, and face","Bharadwaj et al. EURASIP Journal on Image and Video Processing 2014, 2014:34 http://jivp.eurasipjournals.com/content/2014/1/34 REVIEW Open Access Biometric quality: a review of fingerprint, iris, nd face Samarth Bharadwaj, Mayank Vatsa* and Richa Singh" f31c9328b5b4678388c19a39064a8056313f7cf4,Two-Stream Multi-Rate Recurrent Neural Network for Video-Based Pedestrian Re-Identification,"IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. XX, NO. XX, AUGUST 201X Two-Stream Multi-Rate Recurrent Neural Network for Video-Based Pedestrian Re-Identification Zhiqiang Zeng, Zhihui Li*, De Cheng, Huaxiang Zhang, Kun Zhan and Yi Yang" f3002f126f7da75f838637cc314b5f8adc09da53,Robust Face Sketch Synthesis via Generative Adversarial Fusion of Priors and Parametric Sigmoid,"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) CUHK(b) XM2VTS(c) AR(d) Lighting(e) Pose(f) CelebrityPhotoMWFcGANpGANFigure1:Examplesoffacesketchesgeneratedfromfacephotostakeninthewild,i.e.,underuncontrolledconditions.Weonlyse-lect88subjectsintheCUHKstudentdatasetfortraining.Thesketchesgeneratedbydata-drivenmethod(MWF),model-basedmethod(cGAN)andourmethod(pGAN)arelistedinthesecond,thirdandfourthrows,respectively.(a)-(f)aretheresultsofdifferenttestingphotosfrom(a)theCUHKstudentdataset,(b)theXM2VTSdataset,(c)theARdataset,(d)thelightingvariationset,(e)theposevariationsetand(f)celebrityphotosobtainedfromtheWeb.Ourmethodachievessatisfactoryresultsundersuchuncontrolledcondi-tions.stillfailtosynthesizefacesketchesinthewild.Insuchcir-cumstances,thetestingphotosaretakenunderdifferentcon-ditionsfromthetrainingphotos,containingvariationsofil-lumination,pose,backgroundandethnicorigin,asshowninFigure1.Althoughtherearesomeworks[Zhangetal.,2010;Zhangetal.,2015b;Pengetal.,2016;Zhangetal.,2017;Songetal.,2017;Zhuetal.,2017b]payingattentiontothischallengingproblem,thesemethodsonlydealwithcertainaspects,suchasthelightingandposevariations[Zhangetal.,2010],thebackgroundandnon-facialfactors[Zhangetal.,2015b]orthelightingvariationsandclutterbackground[Pengetal.,2016].Mostexistingmethodssimulatethepro-cessofsketchsynthesisbyusinglowlevelfeatures,whichishardlytobegeneralizedtouncontrolledconditions.Incon-" f3cf10c84c4665a0b28734f5233d423a65ef1f23,Title Temporal Exemplar-based Bayesian Networks for facialexpression recognition,"Title Temporal Exemplar-based Bayesian Networks for facial expression recognition Author(s) Shang, L; Chan, KP Citation Proceedings - 7Th International Conference On Machine Learning And Applications, Icmla 2008, 2008, p. 16-22 Issued Date http://hdl.handle.net/10722/61208 Rights This work is licensed under a Creative Commons Attribution- NonCommercial-NoDerivatives 4.0 International License.; International Conference on Machine Learning and Applications Proceedings. Copyright © IEEE.; ©2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted omponent of this work in other works must be obtained from" f32db58cbb8319eb8f2cfa2720c810f8410eb569,A software suite for large-scale video- and image-based analytics,"The 8th International Conference on Bioinspired Information and Communications Technologies (BICT2014), pp. 384-385, Boston, December 1-3, 2014 A software suite for large-scale video- and image-based nalytics Jasmin Léveillé Isao Hayashi Kansai University" f3062992cb10107b9d1e3699c8a61d5281886c4b,Foreground Consistent Human Pose Estimation Using Branch and Bound,"Foreground Consistent Human Pose Estimation Using Branch and Bound(cid:2) Jens Puwein1, Luca Ballan1, Remo Ziegler2, and Marc Pollefeys1 Department of Computer Science, ETH Zurich, Switzerland Vizrt" f39b88ac61264e9a33dcdf47722f0d048a8e490f,Interactive Data Integration and Entity Resolution for Exploratory Visual Data Analytics,"(cid:13)Copyright 2015 Kristi Morton" f3ea181507db292b762aa798da30bc307be95344,Covariance Pooling For Facial Expression Recognition,"Covariance Pooling for Facial Expression Recognition Computer Vision Lab, ETH Zurich, Switzerland VISICS, KU Leuven, Belgium Dinesh Acharya†, Zhiwu Huang†, Danda Pani Paudel†, Luc Van Gool†‡ {acharyad, zhiwu.huang, paudel," f3ca251ac3b05397ea6d72f2a9a6f0cf619a2a32,Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction,"Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction Charles Corbi`ere1, Hedi Ben-Younes1,2, Alexandre Ram´e1, and Charles Ollion1 Heuritech, Paris, France UPMC-LIP6, Paris, France" f375bc91a5f7b1f2d36e41841ccc22f202be2dcf,Unsupervised Learning of Depth and Ego-Motion from Video,"Unsupervised Learning of Depth and Ego-Motion from Video Tinghui Zhou∗ UC Berkeley Matthew Brown Google Noah Snavely Google David G. Lowe Google" 934a77d099a38374ef1babe02d95952c089cce5f,Set of texture descriptors for music genre classification,"Set of texture descriptors for music genre classification Loris Nanni Yandre Costa Department of Information Engineering University of Padua viale Gradenigo 6 5131, Padua, Italy State University of Maringa (UEM) Av. Colombo, 5790 87020-900, Maringa, Parana, Brazil" 93dce341666b6a57f8888dddb25a3fd37df69b02,Deep Layer Aggregation,"Deep Layer Aggregation Fisher Yu Dequan Wang Evan Shelhamer Trevor Darrell UC Berkeley" 9391618c09a51f72a1c30b2e890f4fac1f595ebd,Globally Tuned Cascade Pose Regression via Back Propagation with Application in 2D Face Pose Estimation and Heart Segmentation in 3D CT Images,"Globally Tuned Cascade Pose Regression via Back Propagation with Application in 2D Face Pose Estimation and Heart Segmentation in 3D CT Images Peng Sun James K Min Guanglei Xiong Dalio Institute of Cardiovascular Imaging, Weill Cornell Medical College April 1, 2015 This work was submitted to ICML 2015 but got rejected. We put the initial submission ”as is” in Page 2 - 11 and add updated contents at the tail. The ode of this work is available at https://github.com/pengsun/bpcpr5." 93cbb3b3e40321c4990c36f89a63534b506b6daf,Learning from examples in the small sample case: face expression recognition,"IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, VOL. 35, NO. 3, JUNE 2005 Learning From Examples in the Small Sample Case: Face Expression Recognition Guodong Guo and Charles R. Dyer, Fellow, IEEE" 93cfc6fd29d50fe6589f9506b503f32f6d0372f4,A Face-to-Face Neural Conversation Model,"A Face-to-Face Neural Conversation Model Hang Chu1,2 Daiqing Li1 Sanja Fidler1,2 University of Toronto 2Vector Institute {chuhang1122, daiqing," 939cd1da477fb04ffbe95b20d0ebe0853cb86025,Äääöòòòò Äó Blockin Blockinððþþøøóò Ù××òò Àààööö Blockin Blockin Blockinð Êê Blockinùöööòø Aeaeøûóöö× Ëúò Òò,"eaigFa izai igiea eewk SveBehke FeieUivei(cid:127)aBeii efC eS Tak .914195BeiGeay ehkeif.f bei.dewww.if.f bei.de/(cid:24)behke Aba .efheajaih a  eiefa eai i hafa giiadvide eehy iiheexa izaifafa eiaiage. eewee ehiea e aewkwih" 936c7406de1dfdd22493785fc5d1e5614c6c2882,Detecting Visual Text,"012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 762–772, Montr´eal, Canada, June 3-8, 2012. c(cid:13)2012 Association for Computational Linguistics" 93d3f2e546314305e8102538c4714e30e9146858,Image categorization combining neighborhood methods and boosting,"Image Categorization Combining Neighborhood Methods nd Boosting Matthew Cooper FX Palo Alto Laboratory Palo Alto, CA 94304 USA" 93e962f8886eae13b02ad2aa98bdedfbd7e68709,Dual Conditional GANs for Face Aging and Rejuvenation,"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) Source： datasets(b)Target: our outputs are a series of images belonging to the same person010Input FaceOutputs2 78x/Age groupy/Personality 2178Non-sequential facial imagesSequential facial imagesFigure1:Anillustrationofourfaceagingandrejuvenationpro-cess.As(a)shows,ourtrainingexamplesarenon-sequentialandun-paired,andweaimtosimultaneouslyrenderaseriesofage-changedfacialimagesofapersonandpreservepersonality,asshownin(b).specificallydescribethechangesoffacesindifferentages.Thesemethodsparametricallymodelshapeandtexturepa-rametersfordifferentfeaturesofeachagegroup,e.g.,mus-cles[Suoetal.,2012],wrinkles[RamanathanandChellappa,2008;Suoetal.,2010]andfacialstructure[RamanathanandChellappa,2006;Lanitisetal.,2002].Ontheotherhand,prototype-basedmethods[KemelmacherShlizermanetal.,2014;Tiddemanetal.,2001]dividefacesintogroupsbyage,andthenconstructanaveragefaceasitsprototypeforeachagegroup.Afterthat,thesemethodscantransferthetexturedifferencebetweentheprototypestotheinputfacialimage.Morerecently,thedeeplearning-basedmethod[Wangetal.,2016;Liuetal.,2017]achievedthestate-of-the-artper-formance.In[Wangetal.,2016],RNNisappliedonthecoefficientsofeigenfacesforagepatterntransition.Itper-formsthegroup-basedlearningwhichrequiresthetrueageoftestingfacestolocalizethetransitionstatewhichmightnotbeconvenient.Inaddition,theseapproachesonlypro-videageprogressionfromyoungerfacetoolderones.Toachieveflexiblebidirectionalagechanges,itmayneedtoretrainthemodelinversely.GenerativeAdversarialNet-" 93a4c7ac0b09671db8cd3adbe62851d7befc4658,Machine Analysis of Facial Expressions,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 936627bb98bc9dfe8feef0621af2865356a49e4b,The Future of Video Analytics for Surveillance and Its Ethical Implications,"The Future of Video Analytics for Surveillance nd Its Ethical Implications Andrew A. Adams* James M. Ferryman** Keywords: Surveillance, CCTV, Video Analytics, Ethics, Regulation, Facial Recognition, Computer Vision, Cognitive Vision" 9339123da4b56f695b952ca08a052446e6303ed6,Pose2Seg: Detection Free Human Instance Segmentation,"Pose2Seg: Detection Free Human Instance Segmentation Song-Hai Zhang1, Ruilong Li1, Xin Dong1, Paul Rosin2, Zixi Cai1, Xi Han1, Dingcheng Yang1, Hao-Zhi Huang3 and Shi-Min Hu1 {li-rl16, dong-x16, caizx15, hanx15, Tsinghua University 2 Cardiff University 3 Tencent AI Lab" 938566dc8ee83a12d07e4d26bbb75e65ca7963cd,Multi-Scale Singularity Trees (MSSTs),"Multi-Scale Singularity Trees (MSSTs) Kerawit Somchaipeng" 93ed1c9274906f1916d58cd618a9a82858448a3f,Deep Learning for Accurate Population Counting in Aerial Imagery,"Deep Learning for Accurate Population Counting in Aerial Imagery Matt Epperson, James Rotenberg, Eric Lo, Sebastian Afshari & Brian Kim" 93798ead90afe86636ca582a92cadd846905a95d,Title of dissertation : Learning Visual Classifiers From Limited Labeled Images, 93498110032a458fddebfae80d7a93991e11673d,Brownian descriptor: A rich meta-feature for appearance matching,"Brownian descriptor: a Rich Meta-Feature for Appearance Matching Sławomir B ˛ak Ratnesh Kumar François Brémond INRIA Sophia Antipolis, STARS group 004, route des Lucioles, BP93 06902 Sophia Antipolis Cedex - France" 931a70ec0bfc1d86894ff37a6f702a033e0129e3,ParlAI: A Dialog Research Software Platform,"ParlAI: A Dialog Research Software Platform Alexander H. Miller, Will Feng, Adam Fisch, Jiasen Lu, Dhruv Batra, Antoine Bordes, Devi Parikh and Jason Weston Facebook AI Research" 930a6ea926d1f39dc6a0d90799d18d7995110862,Privacy-preserving photo sharing based on a secure JPEG,"Privacy-Preserving Photo Sharing ased on a Secure JPEG Lin Yuan, Pavel Korshunov, and Touradj Ebrahimi Multimedia Signal Processing Group, EPFL, Lausanne, Switzerland Email: {lin.yuan, pavel.korshunov," 93610676003ef1dcda3864b236bca3852cb05388,RECOGNIZING ACTIVITIES WITH CLUSTER-TREES OF TRACKLETS 1 Recognizing activities with cluster-trees of tracklets,"Recognizing activities with cluster-trees of tracklets Adrien Gaidon, Zaid Harchaoui, Cordelia Schmid To cite this version: Adrien Gaidon, Zaid Harchaoui, Cordelia Schmid. Recognizing activities with cluster-trees of tracklets. Richard Bowden and John P. Collomosse and Krystian Mikolajczyk. BMVC 2012 - British Machine Vision Conference, Sep 2012, Guildford, United Kingdom. BMVA Press, pp.30.1-30.13, 2012, <10.5244/C.26.30>. HAL Id: hal-00722955 https://hal.inria.fr/hal-00722955v2 Submitted on 7 Aug 2012 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destin´ee au d´epˆot et `a la diffusion de documents scientifiques de niveau recherche, publi´es ou non, ´emanant des ´etablissements d’enseignement et de" 930663a0812a7a53963563b647c5957807d3d97d,A unified view of non-monotonic core selection and application steering in heterogeneous chip multiprocessors,"A Unified View of Non-monotonic Core Selection nd Application Steering in Heterogeneous Chip Multiprocessors Sandeep Navada*, Niket K. Choudhary*, Salil V. Wadhavkar* CPU Design Center Qualcomm Raleigh, NC, USA {snavada, niketc," dcc414adda5432011bfc53359075dd341b924910,LF-Net: Learning Local Features from Images,"LF-Net: Learning Local Features from Images Yuki Ono Sony Imaging Products & Solutions Inc. Eduard Trulls École Polytechnique Fédérale de Lausanne Pascal Fua École Polytechnique Fédérale de Lausanne Visual Computing Group, University of Victoria Kwang Moo Yi" dc452f3e531c4057c930f0538d5652ad9034d1aa,Quality metrics for practical face recognition,"1st International Conference on Pattern Recognition (ICPR 2012) November 11-15, 2012. Tsukuba, Japan 978-4-9906441-0-9 ©2012 ICPR" dcf17cc3b4f8519a6789c1ea086689bcbc1d6f11,Unsupervised Learning of Deep Feature Representation for Clustering Egocentric Actions,Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) dcc064b8bf7744801ae7dfe4cbfd11b7e5a5b673,Men's physical strength moderates conceptualizations of prospective foes in two disparate societies.,"Hum Nat DOI 10.1007/s12110-014-9205-4 Men’s Physical Strength Moderates Conceptualizations of Prospective Foes in Two Disparate Societies Daniel M. T. Fessler & Colin Holbrook & Matthew M. Gervais # Springer Science+Business Media New York 2014" dce44d81e06f6703b0e85e778e7afbf3c8d0a401,Multispectral Pedestrian Detection using Deep Fusion Convolutional Neural Networks,"Multispectral Pedestrian Detection using Deep Fusion Convolutional Neural Networks J¨org Wagner1,2, Volker Fischer1, Michael Herman1 and Sven Behnke2 - Robert Bosch GmbH - 70442 Stuttgart - Germany - University Bonn - Computer Science VI, Autonomous Intelligent Systems Friedrich-Ebert-Allee 144, 53113 Bonn - Germany" dc6c47d15ffc0fd59e51ed03556c3566afe5710b,Robust Object Recognition Through Symbiotic Deep Learning In Mobile Robots *,"CONFIDENTIAL. Limited circulation. For review only. Preprint submitted to 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems. Received March 1, 2018." dc2c353fa43a75ec92327e323ba5715c400bf92b,Face Recognition in Hyperspectral Images,"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 25, NO. 12, DECEMBER 2003 Face Recognition in Hyperspectral Images Zhihong Pan, Student Member, IEEE, Glenn Healey, Senior Member, IEEE, Manish Prasad, and Bruce Tromberg" dc2e805d0038f9d1b3d1bc79192f1d90f6091ecb,Face Recognition and Facial Attribute Analysis from Unconstrained Visual Data, dc090aea412cef17c7a68ec84c34797806feab24,A mixture of gated experts optimized using simulated annealing for 3D face recognition,"978-1-4577-1302-6/11/$26.00 ©2011 IEEE D FACE RECOGNITION . INTRODUCTION" dcace6f0611b77177f4aff4bb650afab0a819575,3D Face Recognition,BMVC 2006 doi:10.5244/C.20.89 dc92aee7d44223cdfa85a8f196d24594703d6ff5,Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving,"Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving Ganesh Sistu1, Isabelle Leang2 and Senthil Yogamani1 : Valeo Vision Systems, Ireland : Valeo Bobigny, France" dc771cd7780538953811a5b6ae0e901ca68cce3d,Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification,"Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification Maryam Babaee∗ Ali Athar∗ Gerhard Rigoll Institute for Human-Machine Communication, Technical University of Munich Arcisstrasse 21, Munich, Germany" dc23beb1e5c7402b1a9d5a7c854e62a253d0815e,Microscopic crowd simulation : evaluation and development of algorithms. (Simulation microscopique de foules : évaluation et développement d'algorithmes),"Microscopic crowd simulation : evaluation and development of algorithms David Wolinski To cite this version: David Wolinski. Microscopic crowd simulation : evaluation and development of algorithms. Data Structures and Algorithms [cs.DS]. Université Rennes 1, 2016. English. . HAL Id: tel-01420105 https://tel.archives-ouvertes.fr/tel-01420105 Submitted on 20 Dec 2016 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de" dceaef5e7cbfc4d0150c2d765cc3df4349b8b2bd,Sentiment Analysis Using Social Multimedia,"Chapter 2 Sentiment Analysis Using Social Multimedia Jianbo Yuan, Quanzeng You and Jiebo Luo" dc0c7d66d46919fe5f9fb2b5dde8bf3ab7972d1d,Construction of a Multi-Modal Database for the Evaluation of Person Authentication Systems operating under Near Infrared Illumination,"Construction of a Multi-Modal Database for the Evaluation of Person Authentication Systems operating under Near Infrared Illumination Shuyan Zhao and Ralph Kricke and Rolf-Rainer Grigat TUHH Vision Systems (E-2) Harburger Schloßstr. 20, 21079 Hamburg, Germany Tel: +49 40 42878-3125, Fax: +49 40 42878-2911 http://www.ti1.tu-harburg.de in: WSEAS Transactions on Signal Processing. See also BIBTEX entry below. BIBTEX: uthor = {Shuyan Zhao and Ralph Kricke and Rolf-Rainer Grigat}, title = {Construction of a Multi-Modal Database for the Evaluation of Person Authentication Systems operating under Near Infrared Illumination}, journal = {WSEAS Transactions on Signal Processing}, year = {2007}, volume = {3}, pages = {249-254}, number = {2}, month = {Feb.}, © copyright by the author(s)" dc041f307d467918ba684d3c425fb23016f3b28e,A survey of 3d face recognition methods,"A Survey of 3D Face Recognition Methods Alize Scheenstra1, Arnout Ruifrok2, and Remco C. Veltkamp1 Utrecht University, Institute of Information and Computing Sciences, Padualaan 14, 3584 CH Utrecht, The Netherlands Netherlands Forensic Institute, Laan van Ypenburg 6, 2497 GB Den Haag, The Netherlands," dc6d518585c18504b2e69223c062cdd691c79bbd,Domain Adaptation Through Synthesis for Unsupervised Person Re-identification, dc7a4d5ba20ca07d29c360b26e1e72afae9a77be,The ApolloScape Open Dataset for Autonomous Driving and its Application,"The ApolloScape Open Dataset for Autonomous Driving and its Application Xinyu Huang*, Peng Wang*, Xinjing Cheng, Dingfu Zhou, Qichuan Geng, Ruigang Yang" dcb44fc19c1949b1eda9abe998935d567498467d,Ordinal Zero-Shot Learning,"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17) labelunseen labelFigure1:Supervisionintensityfordifferentlabels.Greenrepre-sentsseenlabelsandredrepresentsunseenlabels.Thegroundtruthlabelofthisinstanceis“Good”,soithasthestrongestsupervisionintensity.Although“Common”isanunseenlabel,itstillhascertainsupervisioninformationbecauseitiscloselyrelatedto“Good”.classifier;[ZhangandSaligrama,2016]learnsajointlatentspaceusingstructuredlearning.Thedifficultyinobtainingthesideinformationorusingothertechniquestoprocessthesideinformationarethemostseriousissuesformanyexistingzero-shotlearningmethods.Fortheattribute-basedmethods,humanexpertsareneededtolabelattributesandthisisverytime-consumingandnoteasytoobtainthediscriminativecategory-levelattributes.Somemethodsdiscoverattributesinteractively[ParikhandGrau-man,2011][Bransonetal.,2010],butthisalsorequiresla-borioushumanparticipation.Althoughmanyalgorithmscandiscoverattribute-relatedconceptsontheWeb[Rohrbachetal.,2010][Bergetal.,2010],theycanalsobebiasedorlackinformationthatiscriticaltoaparticulartask[ParikhandGrauman,2011].Forthetextcorpora-basedmethods,theyfirstrequirealargelanguagecorpora,suchasWikipedia,andthenneedtolearnwordrepresentation[Socheretal.,2013]orusestandardNaturalLanguageProcessing(NLP)techniquestoproduceclassdescriptions[Elhoseinyetal.,2013].Itishardtoguaranteethecorrectnessofsuchclassdescriptionsforzero-shotlearning.Conclusively,althoughsideinforma-tionishelpfulforzero-shotlearning,ithasmanydisadvan-tages.Generatingthesesideinformationisverytediousandsometimeswecannotknowwhichsideinformationistrulywanted.IfwedependonhumanlabororNLPtechniques,noisysideinformationwillbecomealmostinevitableandin-fluencethefinalperformance.Toavoidtheseproblems,itisimportanttosolvezero-shotlearninginwhateverpossiblecasesthathavesomepropertieswecanutilizetoavoidusingsideinformation." dc22de0ed56958013234cf7128952390fb47345a,Towards dense object tracking in a 2D honeybee hive,"Towards dense object tracking in a 2D honeybee hive Katarzyna Bozek a, Laetitia Hebert a, Alexander S Mikheyev a & Greg J Stephens a,b∗ Okinawa Institute of Science and Technology, 1919-1 Tancha Onna-son, Kunigami-gun, Okinawa 904-0495, Japan Department of Physics and Astronomy, VU University Amsterdam, 1081 HV Amsterdam, The Netherlands From human crowds to cells in tissue, the detection and ef‌f‌icient tracking of multiple objects in dense configurations is an important and unsolved problem. In the past, limitations of image nalysis have restricted studies of dense groups to tracking a single or subset of marked individ- uals, or to coarse-grained group-level dynamics, all of which yield incomplete information. Here, we combine convolutional neural networks (CNNs) with the model environment of a honeybee hive to automatically recognize all individuals in a dense group from raw image data. We create new, dapted individual labeling and use the segmentation architecture U-Net with a loss function depen- dent on both object identity and orientation. We additionally exploit temporal regularities of the video recording in a recurrent manner and achieve near human-level performance while reducing the network size by 94% compared to the original U-Net architecture. Given our novel applica- tion of CNNs, we generate extensive problem-specific image data in which labeled examples are produced through a custom interface with Amazon Mechanical Turk. This dataset contains over 75,000 labeled bee instances across 720 video frames at 2 FPS, representing an extensive resource location error of ∼ 7% of a typical body dimension, and orientation error of 12◦, approximating the variability of human raters. Our results provide an important step towards ef‌f‌icient image-based dense object tracking by allowing for the accurate determination of object location and orientation" dc9a6a821689de877bd07e970e52d4cdb1dd2714,Transfer of gender aftereffects in face silhouettes reveals face-specific mechanisms,"Transfer of gender aftereffects in face silhouettes reveals face-specific mechanisms Nicolas Davidenko Nathan Witthoft Jonathan Winawer Department of Psychology, 450 Serra Street, Building 420 Stanford, CA 94305 USA" dc9f29118e38602c03bb2866f8b12ce478aad52c,Large scale evolution of convolutional neural networks using volunteer computing,"Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing Travis Desell∗ March 17, 2017" dcce157aa2e5db081b36fd16544a038becb408ab,Fast and Accurate Pedestrian Detection in a Truck's Blind Spot Camera,"Fast and Accurate Pedestrian Detection in a Truck’s Blind Spot Camera Kristof Van Beeck1,2(B) and Toon Goedem´e1,2 EAVISE, KU Leuven - Campus De Nayer, J. De Nayerlaan 5, 2860 ESAT/PSI - VISICS, KU Leuven, Kasteelpark Arenberg 10, 3001 Leuven, Belgium Sint-katelijne-waver, Belgium" dc53c4bb04e787a0d45dd761ba2101cc51c17b82,Multiple-Person Tracking by Detection,"http://excel.fit.vutbr.cz Multiple-Person Tracking by Detection Jakub Vojvoda*" dc94db59fddedb3fc6ae5317ad719808bb5482f2,Humanitarian Logistics and Cultural Diversity within Crowd Simulation,"Humanitarian logistics and cultural diversity within rowd simulation Alberto Ochoa, Isaac Rudomin, Genoveva Vargas-Solar, Javier Espinosa-Oviedo, Hugo Pérez, José-Luis Zechinelli-Martini To cite this version: Alberto Ochoa, Isaac Rudomin, Genoveva Vargas-Solar, Javier Espinosa-Oviedo, Hugo Pérez, et al.. Humanitarian logistics and cultural diversity within crowd simulation. computacion y sistemas, Centro de Investigación en computación, 2017, 21 (1), pp.7-21. HAL Id: hal-01517161 https://hal.archives-ouvertes.fr/hal-01517161 Submitted on 2 May 2017 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non," dcd2ac544a8336d73e4d3d80b158477c783e1e50,Improving Landmark Localization with Semi-Supervised Learning,"Improving Landmark Localization with Semi-Supervised Learning Sina Honari1∗, Pavlo Molchanov2, Stephen Tyree2, Pascal Vincent1,4,5, Christopher Pal1,3, Jan Kautz2 MILA-University of Montreal, 2NVIDIA, 3Ecole Polytechnique of Montreal, 4CIFAR, 5Facebook AI Research. {honaris, {pmolchanov, styree," dc3cd4e110b526cb59bd7527d540120c5fae77ce,Adversarially Tuned Scene Generation,"Adversarially Tuned Scene Generation VSR Veeravasarapu1, Constantin Rothkopf2, Ramesh Visvanathan1 Center for Cognition and Computation, Dept. of Computer Science, Goethe University, Frankfurt Center for Cognitive Science & Dept. of Psychology, Technical University Darmstadt." dca246cd06666a331b0203cb09a6ef51727bfdcc,The micro-foundations of email communication networks,"The Micro-Foundations of Email Communication Networks Ofer Engel London School of Economics and Political Science Department of Management Information Systems and Innovation Group Thesis submitted for the degree of PhilosophiæDoctor (PhD) 013 June" dc6263270cd23a51d8fffdfd7e408250442b40f3,"SimpleElastix: A User-Friendly, Multi-lingual Library for Medical Image Registration","SimpleElastix: A user-friendly, multi-lingual library for medical image registration Kasper Marstal1, Floris Berendsen2, Marius Staring2 and Stefan Klein1 Biomedical Imaging Group Rotterdam (BIGR), Department of Radiology & Medical Informatics, Erasmus Medical Center, PO Box 2040, Rotterdam, 3000 CA, the Netherlands, Division of Image Processing (LKEB), Department of Radiology, Leiden University Medical Center, PO Box 9600, 2300 RC Leiden, the Netherlands," 8768b8a972debe697ee5f8c3bd67a6df6ff44977,A Comparative Study on Image Hashing for Document Authentication,"A Comparative Study on Image Hashing for Document Authentication ∗ Dominik Klein† Bundesamt f¨ur Sicherheit in der Informationstechnik, 53133 Bonn Jan Kruse‡ Hochschule Emden/Leer, 26723 Emden Stadt" 87a937dff0ecffefd8a7e4ca4ce068aca9731a0a,Embracing Error to Enable Rapid Crowdsourcing,"Embracing Error to Enable Rapid Crowdsourcing Ranjay Krishna1, Kenji Hata1, Stephanie Chen1, Joshua Kravitz1, David A. Shamma2, Li Fei-Fei1, Michael S. Bernstein1 {ranjaykrishna, kenjihata, stephchen, kravitzj, feifeili, Stanford University1, Yahoo! Labs2" 87ea22438e33fd98a5bac577598f26a6a02cf8a3,Deteksi Pemain Basket Terklasifikasi Berbasis Histogram of Oriented Gradients,"INFORM : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi Vol.3 No.1, Januari 2018, P-ISSN : 2502-3470, EISSN : 2581-0367 Deteksi Pemain Basket Terklasifikasi Berbasis Histogram of Oriented Gradients Nisa’ul Hafidhoh1, Septian Enggar Sukmana2 1, 2 Program Studi Teknik Informatika, Fakultas Ilmu Komputer, Universitas Dian Nuswantoro ,2{nisa," 8796f2d54afb0e5c924101f54d469a1d54d5775d,Illumination Invariant Face Recognition Using Fuzzy LDA and FFNN,"Journal of Signal and Information Processing, 2012, 3, 45-50 http://dx.doi.org/10.4236/jsip.2012.31007 Published Online February 2012 (http://www.SciRP.org/journal/jsip) Illumination Invariant Face Recognition Using Fuzzy LDA nd FFNN Behzad Bozorgtabar, Hamed Azami, Farzad Noorian School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran. Email: Received October 20th, 2011; revised November 24th, 2011; accepted December 10th, 2011" 87bee0e68dfc86b714f0107860d600fffdaf7996,Automated 3D Face Reconstruction from Multiple Images Using Quality Measures,"Automated 3D Face Reconstruction from Multiple Images using Quality Measures Marcel Piotraschke and Volker Blanz Institute for Vision and Graphics, University of Siegen, Germany" 877aff9bd05de7e9d82587b0e6f1cda28fd33171,Long-Term Visual Localization Using Semantically Segmented Images,"Long-term Visual Localization using Semantically Segmented Images Erik Stenborg1,2 Carl Toft1 and Lars Hammarstrand1" 87ad56e06d48fa9b30e2915473c488c1b4b7e6ae,Learn from experience: Probabilistic prediction of perception performance to avoid failure,"Article Learn from experience: probabilistic prediction of perception performance to void failure The International Journal of Robotics Research © The Author(s) 2017 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav DOI: 10.1177/0278364917730603 journals.sagepub.com/home/ijr Corina Gur˘au1, Dushyant Rao1, Chi Hay Tong2, and Ingmar Posner1" 87f0a779ce4e060e3e076df3cc651e0f3f01b2ae,Bimodal Biometric Person Identification System Under Perturbations,"Bimodal Biometric Person Identification System Under Perturbations Miguel Carrasco1, Luis Pizarro2, and Domingo Mery1 Pontificia Universidad Cat´olica de Chile Av. Vicu˜na Mackenna 4860(143), Santiago, Chile Mathematical Image Analysis Group Faculty of Mathematics and Computer Science Saarland University, Bldg. E11, 66041 Saarbr¨ucken, Germany" 87f285782d755eb85d8922840e67ed9602cfd6b9,INCORPORATING BOLTZMANN MACHINE PRIORS FOR SEMANTIC LABELING IN IMAGES AND VIDEOS,"INCORPORATING BOLTZMANN MACHINE PRIORS FOR SEMANTIC LABELING IN IMAGES AND VIDEOS A Dissertation Presented ANDREW KAE Submitted to the Graduate School of the University of Massachusetts Amherst in partial fulfillment of the requirements for the degree of DOCTOR OF PHILOSOPHY May 2014 Computer Science" 87da8bd9eb2fff2d77809c8bee3bed8c93cb5b4b,A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders,"A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders Ashish Mishra1 , Shiva Krishna Reddy1, Anurag Mittal, and Hema A Murthy Indian Institute of Technology Madras" 8765f22fbcdcf610a08b01db01edc4b8cc67d082,Probability Models for Open Set Recognition,"for all other uses, © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any opyrighted component of this work in other works. in any current or future media, Pre-print of article that will appear in T-PAMI." 87c2806f1fd20287f00b43dab07822ab13035169,Verfahren zur Analyse von Ähnlichkeit im Ortsbereich,"Matthias Fiedler Verfahren zur Analyse von Ähnlichkeit im Ortsbereich" 87363751b8e3d51a002dea6d32df553ee5315cb7,Conventional SBIR Fine-grained SBIR Conventional Methods Our Method,"Fine-Grained Sketch-Based Image Retrieval: The Role of Part-Aware Attributes Ke Li1&2 Kaiyue Pang1&2 Yi-Zhe Song2 Timothy Hospedales2 Honggang Zhang1 School of Electronic Engineering and Computer Science Queen Mary University of London. Beijing University of Posts and Telecommunications. Yichuan Hu1" 878169be6e2c87df2d8a1266e9e37de63b524ae7,Image interpretation above and below the object level.,"CBMM Memo No. 089 May 10, 2018 Image interpretation above and below the object level Guy Ben-Yosef, Shimon Ullman" 87bb183d8be0c2b4cfceb9ee158fee4bbf3e19fd,Craniofacial Image Analysis,"Craniofacial Image Analysis Ezgi Mercan, Indriyati Atmosukarto, Jia Wu, Shu Liang and Linda G. Shapiro" 878301453e3d5cb1a1f7828002ea00f59cbeab06,Faceness-Net: Face Detection through Deep Facial Part Responses,"Faceness-Net: Face Detection through Deep Facial Part Responses Shuo Yang, Ping Luo, Chen Change Loy, Senior Member, IEEE and Xiaoou Tang, Fellow, IEEE" 87ba4cce558c2defde90f4b42853262fd572ca3e,Silhouette estimation.,"J. Opt. Soc. Am. A / Vol. 31, No. 7 / July 2014 Paxman et al. Silhouette estimation Richard G. Paxman,1,* David A. Carrara,1 Paul D. Walker,1 and Nicolas Davidenko2 General Dynamics Advanced Information Systems, P.O. Box 990, Ypsilanti, Michigan 48197, USA Psychology Department, UC Santa Cruz, 1156 High Street, Santa Cruz, California 95064, USA *Corresponding author: Received February 13, 2014; revised April 8, 2014; accepted April 9, 2014; posted May 23, 2014 (Doc. ID 206333); published June 30, 2014 Silhouettes arise in a variety of imaging scenarios. Pristine silhouettes are often degraded via blurring, detector sampling, and detector noise. We present a maximum a posteriori estimator for the restoration of parameterized facial silhouettes. Extreme dealiasing and dramatic superresolution, well beyond the diffraction limit, are demonstrated through the use of strong prior knowledge. © 2014 Optical Society of America OCIS codes: (100.3010) Image reconstruction techniques; (100.3008) Image recognition, algorithms and filters; (100.1830) Deconvolution. http://dx.doi.org/10.1364/JOSAA.31.001636 . INTRODUCTION A. Silhouettes in Imaging A silhouette is the image of an object represented as a solid" 871001c87c2c1b4059576ca5dcb95ab61afd3c9a,Improving Generalization via Scalable Neighborhood Component Analysis,"Improving Generalization via Scalable Neighborhood Component Analysis Zhirong Wu1,2, Alexei A. Efros1, and Stella X. Yu1 UC Berkeley / ICSI Microsoft Research Asia" 871f5f1114949e3ddb1bca0982086cc806ce84a8,Discriminative learning of apparel features,"Discriminative Learning of Apparel Features Rasmus Rothe1, Marko Ristin1, Matthias Dantone1, and Luc Van Gool1,2 Computer Vision Laboratory, D-ITET, ETH Z¨urich, Switzerland ESAT - PSI / IBBT, K.U. Leuven, Belgium" 87dd3fd36bccbe1d5f1484ac05f1848b51c6eab5,SPATIO-TEMPORAL MAXIMUM AVERAGE CORRELATION HEIGHT TEMPLATES IN ACTION RECOGNITION AND VIDEO SUMMARIZATION by MIKEL RODRIGUEZ,"SPATIO-TEMPORAL MAXIMUM AVERAGE CORRELATION HEIGHT TEMPLATES IN ACTION RECOGNITION AND VIDEO SUMMARIZATION MIKEL RODRIGUEZ B.A. Earlham College, Richmond Indiana M.S. University of Central Florida A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the School of Electrical Engineering and Computer Science in the College of Engineering and Computer Science t the University of Central Florida Orlando, Florida Summer Term Major Professor: Mubarak Shah" 8765f312e35bba0650aa769b59da7e8fac9e98aa,A Cognitively-Motivated Framework for Partial Face Recognition in Unconstrained Scenarios,"Sensors 2015, 15, 1903-1924; doi:10.3390/s150101903 OPEN ACCESS sensors ISSN 1424-8220 www.mdpi.com/journal/sensors Article A Cognitively-Motivated Framework for Partial Face Recognition in Unconstrained Scenarios João C. Monteiro * and Jaime S. Cardoso INESC TEC and Faculdade de Engenharia, Universidade do Porto, Campus da FEUP, Rua Dr. Roberto Frias, n 378, 4200-465 Porto, Portugal; E-Mail: * Author to whom correspondence should be addressed; E-Mail: Tel.: +351-22-209-4299. Academic Editor: Vittorio M.N. Passaro Received: 24 November 2014 / Accepted: 7 January 2015 / Published: 16 January 2015" 878f70f6abb83f5158ca0bacfc2bacd49b1886b1,Aligning Artificial Neural Networks to the Brain Yields Shallow Recurrent Architec- Tures,"Under review as a conference paper at ICLR 2019 ALIGNING ARTIFICIAL NEURAL NETWORKS TO THE BRAIN YIELDS SHALLOW RECURRENT ARCHITEC- TURES Anonymous authors Paper under double-blind review" 874082164d9ab9fced08b9890c009b91a2e846f1,Understanding Convolution for Semantic Segmentation,"Understanding Convolution for Semantic Segmentation Panqu Wang1, Pengfei Chen1, Ye Yuan2, Ding Liu3, Zehua Huang1, Xiaodi Hou1, Garrison Cottrell4 TuSimple, 2Carnegie Mellon University, 3University of Illinois Urbana-Champaign, 4UC San Diego" 87bdafbcf3569c06eef4a397beffc451f5101f94,Facial expression: An under-utilised tool for the assessment of welfare in mammals.,"published February 8, 2017 Review article Facial expression: An under-utilised tool for the assessment of welfare in mammals1 Kris A. Descovich1,2,3, Jennifer Wathan4, Matthew C. Leach5, Hannah M. Buchanan-Smith1, Paul Flecknell6, David Farningham7 and Sarah-Jane Vick1 Psychology, Faculty of Natural Sciences, University of Stirling; 2Environmental and Animal Sciences, Unitec Institute of Technology; 3Centre for Animal Welfare and Ethics, University of Queensland; 4School of Psychology, University of Sussex, United Kingdom; 5School of Agriculture, Food & Rural Development, University of Newcastle; 6Comparative Biology Centre, University of Newcastle; 7Centre for Macaques, Medical Research Council Summary Animal welfare is a key issue for industries that use or impact upon animals. The accurate identification of welfare states is particularly relevant to the field of bioscience, where the 3Rs framework encourages refinement of experimental procedures involving animal models. The assessment and improvement of welfare states in animals is reliant on reliable and valid measurement tools. Behavioural measures (activity, attention, posture and vocalisation) are frequently used because they are immediate and non-invasive, however no single indicator can yield a complete picture of the internal state of an animal. Facial expressions are extensively studied in humans s a measure of psychological and emotional experiences but are infrequently used in animal studies, with the exception of emerging research on pain behaviour. In this review, we discuss current evidence for facial representations of underlying affective states, and how communicative or functional expressions can be useful" 8722ab37a03336f832e4098224cb63cd02cdfe0a,Face recognition with 3 D face asymmetry,"Face recognition with 3D face asymmetry Janusz Bobulski Czestochowa University of Technology Institute of Computer and Information Sciences Dabrowskiego 73, 42-200, Czestochowa, Poland Summary. Using of 3D images for the identification was in a field of the interest of many researchers which developed a few methods offering good results. However, there are few techniques exploiting the 3D asymmetry amongst these methods. We propose fast algorithm for rough extraction face asymmetry that is used to 3D face recognition with hidden Markov models. This paper presents conception of fast method for determine 3D face asymmetry. The research results indicate that face recognition with 3D face asymmetry may be used in biometrics systems. Introduction Biometrics systems use individual and unique biological features of person for user identification. The most popular features are: fingerprint, iris, voice, palm print, face image et al. Most of them are not accepted by users, because they feel under surveillance or as criminals. Others, in turn, are characterized y problems with the acquisition of biometric pattern and require closeness to the reader. Among the biometric methods popular technique is to identify people on the basis of the face image, the advantage is the ease of obtaining" 87c6ba55b0f817de4504e39dbb201842ae102c9f,Three Dimensional Face Recognition Using Iso-Geodesic and Iso-Depth Curves,"Three Dimensional Face Recognition Using Iso-Geodesic and Iso-Depth Curves Sina Jahanbin, Hyohoon Choi, Yang Liu, Alan C. Bovik" 877d083b2a3a75cc1bb25f770a9c5684bf5f6f44,Learning to Hash with Binary Reconstructive Embeddings,"Learning to Hash with Binary Reconstructive Embeddings Brian Kulis and Trevor Darrell UC Berkeley EECS and ICSI Berkeley, CA" 87d5b53580ca5f77ccc3ff157337ef3456308943,Augmented Autoencoders for object orientation estimation trained on synthetic RGB images,MasterarbeitAugmented Autoencoders for object orientation estimation trained on synthetic RGB imagesMartin Sundermeyer 0b4d3e59a0107f0dad22e74054bab1cf1ad9c32e,Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations,"Int J Comput Vis DOI 10.1007/s11263-016-0981-7 Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations · Yuke Zhu1 · Oliver Groth2 · Justin Johnson1 · Kenji Hata1 · Ranjay Krishna1 Joshua Kravitz1 · Stephanie Chen1 · Yannis Kalantidis3 · Li-Jia Li4 · David A. Shamma5 · Michael S. Bernstein1 · Li Fei-Fei1 Received: 23 February 2016 / Accepted: 12 September 2016 © The Author(s) 2017. This article is published with open access at Springerlink.com" 0b61cad6ae6e7ab99f2e3c187bd8530da71f10ae,Gameplay Genre Video Classification by Using Mid-Level Video Representation,"Gameplay genre video classification by using mid-level video representation Renato Augusto de Souza‡, Raquel Pereira de Almeida‡, Arghir-Nicolae Moldovan∗, Zenilton Kleber G. do Patrocínio Jr.‡, Silvio Jamil F. Guimarães‡ Audio-Visual Information Proc. Lab. (VIPLAB) Computer Science Department – ICEI – PUC Minas School of Computing, National College of Ireland, Dublin, Ireland named GameGenre, consists of 700 videos (more than 116 hours), classified into 7 game genres." 0b5c3cf7c8c643cb09d55a08b15de22e134081be,Online Tracking and Offline Recognition Using Scale Invariant Feature Transform,"IJMTES | International Journal of Modern Trends in Engineering and Science ISSN: 2348-3121 Online Tracking and Offline Recognition Using Scale Invariant Feature Transform A. Bahmidha Banu1; Dr. V. Venkatesa kumar2 PG Scholar, Department of CSE, Anna University Regional Centre, Tamilnadu, Assistant Professor, Department of CSE, Anna University Regional Centre, , Tamilnadu, ________________________________________________________________________________________________________" 0bce54bfbd8119c73eb431559fc6ffbba741e6aa,Recurrent Neural Networks,"Published as a conference paper at ICLR 2018 SKIP RNN: LEARNING TO SKIP STATE UPDATES IN RECURRENT NEURAL NETWORKS V´ıctor Campos∗†, Brendan Jou‡, Xavier Gir´o-i-Nieto§, Jordi Torres†, Shih-Fu ChangΓ Barcelona Supercomputing Center, ‡Google Inc, §Universitat Polit`ecnica de Catalunya, ΓColumbia University {victor.campos," 0b0eb562d7341231c3f82a65cf51943194add0bb,Facial Image Analysis Based on Local Binary Patterns : A Survey,"> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < Facial Image Analysis Based on Local Binary Patterns: A Survey Di Huang, Caifeng Shan, Mohsen Ardebilian, Liming Chen" 0b0e29ff990877127963eb064ea12926f7aeb52a,A Cost-Effective Framework for Automated Vehicle-Pedestrian Near-Miss Detection Through Onboard Monocular Vision,"A Cost-effective Framework for Automated Vehicle-pedestrian Near-miss Detection through Onboard Monocular Vision Ruimin Ke1 Jerome Lutin2 Jerry Spears3 Yinhai Wang1,* University of Washingtion 2New Jersey Transit 3Washington State Transit Insurance Pool {ker27," 0b19177107a102ee81e5ef1bb9fb2f2881441503,Comparing Robustness of Pairwise and Multiclass Neural-Network Systems for Face Recognition,"Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2008, Article ID 468693, 7 pages doi:10.1155/2008/468693 Research Article Comparing Robustness of Pairwise and Multiclass Neural-Network Systems for Face Recognition J. Uglov, L. Jakaite, V. Schetinin, and C. Maple Computing and Information System Department, University of Bedfordshire, Luton LU1 3JU, UK Correspondence should be addressed to V. Schetinin, Received 16 June 2007; Revised 28 August 2007; Accepted 19 November 2007 Recommended by Konstantinos N. Plataniotis Noise, corruptions, and variations in face images can seriously hurt the performance of face-recognition systems. To make these systems robust to noise and corruptions in image data, multiclass neural networks capable of learning from noisy data have been suggested. However on large face datasets such systems cannot provide the robustness at a high level. In this paper, we explore a pairwise neural-network system as an alternative approach to improve the robustness of face recognition. In our experiments, the pairwise recognition system is shown to outperform the multiclass-recognition system in terms of the predictive accuracy on the test face images. Copyright © 2008 J. Uglov et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited." 0b174d4a67805b8796bfe86cd69a967d357ba9b6,A Survey on Face Detection and Recognition Approaches,"Research Journal of Recent Sciences _________________________________________________ ISSN 2277-2502 Vol. 3(4), 56-62, April (2014) Res.J.Recent Sci." 0b8c92463f8f5087696681fb62dad003c308ebe2,On matching sketches with digital face images,"On Matching Sketches with Digital Face Images Himanshu S. Bhatt, Samarth Bharadwaj, Richa Singh, and Mayank Vatsa in local" 0b0535fbdc468d1fd6ff32545a717a8af14f634f,The Discriminative Generalized Hough Transform as a Proposal Generator for a Deep Network in Automatic Pedestrian Localization, 0b9db62b26b811e8c24eb9edc37901a4b79a897f,Structured Face Hallucination,"Structured Face Hallucination Chih-Yuan Yang Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science University of California at Merced {cyang35, sliu32," 0b70facac4d10c7c73e7fdf3a85848ce429d98ab,"Segmentation features, visibility modeling and shared parts for object detection","Segmentation Features, Visibility Modeling and Shared Parts for Object Detection Patrick Ott Submitted in accordance with the requirements for the degree of Doctor of Philosophy. The University of Leeds School of Computing February 2012 The candidate confirms that the work submitted is his own and that the appropriate redit has been given where reference has been made to the work of others. This copy has been supplied on the understanding that it is copyright material nd that no quotation from the thesis may be published without proper cknowledgment." 0b9ce839b3c77762fff947e60a0eb7ebbf261e84,LOGARITHMIC FOURIER PCA : A NEW APPROACH TO FACE RECOGNITION 1,"Proceedings of the IASTED International Conference Computer Vision (CV 2011) June 1 - 3, 2011 Vancouver, BC, Canada LOGARITHMIC FOURIER PCA: A NEW APPROACH TO FACE RECOGNITION Lakshmiprabha Nattamai Sekar, Jhilik Bhattacharya, omjyoti Majumder Surface Robotics Lab Central Mechanical Engineering Research Institute Mahatma Gandhi Avenue, Durgapur - 713209, West Bengal, India. email: 1 n prabha 2 3" 0bc7d8e269a8c8018a7cb120ff25adf02d45c7ed,Exploiting dissimilarity representations for person re-identification,"Exploiting Dissimilarity Representations for Person Re-Identification Riccardo Satta, Giorgio Fumera, and Fabio Roli Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d’Armi, 09123 Cagliari, Italy" 0b0958493e43ca9c131315bcfb9a171d52ecbb8a,A Unified Neural Based Model for Structured Output Problems,"A Unified Neural Based Model for Structured Output Problems Soufiane Belharbi∗1, Cl´ement Chatelain∗1, Romain H´erault∗1, and S´ebastien Adam∗2 LITIS EA 4108, INSA de Rouen, Saint ´Etienne du Rouvray 76800, France LITIS EA 4108, UFR des Sciences, Universit´e de Rouen, France. April 13, 2015" 0b1cf351a4a6758606bea32d29c7d529e79ab7ce,Fake Face Detection System Using Pupil Reflection 양재준,"한국지능시스템학회 논문지 2010, Vol. 20, No. 5, pp. 645-651 동공의 반사특징을 이용한 얼굴위조판별 시스템 Fake Face Detection System Using Pupil Reflection 양재준*․조성원*․정선태** JaeJun Yang, Seongwon Cho and Sun-Tae Chung * 홍익대학교 전기정보제어공학과 **숭실대학교 정보통신전자공학부 최근 지능형 범죄가 늘면서 첨단 보안 기술에 대한 요구가 점차 늘어나고 있다. 현재까지 보고된 위조영상검출방법은 실용 화를 위하여 정확도 개선이 요구된다. 본 논문에서는 사람의 얼굴에 대하여 동공의 반사광을 이용한 얼굴위조판별 시스템 을 제안한다. 제안된 시스템은 먼저 다중 스케일 가버특징 벡터를 기반으로 눈의 위치를 찾은 후 2단계의 템플릿 매칭을 통해서 설정된 적용범위를 벗어나는 눈에 대하여 위조판별을 고려하지 않음으로써 정확도를 높이는 방법을 사용한다. 신뢰 도가 확보된 눈의 위치를 기반으로 적외선 조명에 반사되는 동공의 특징을 이용하여 눈위치 근처에서의 화소값을 계산하 여 위조 여부를 판단한다. 실험을 통하여 본 논문에서 제안한 방법이 더욱 신뢰성 높은 위조판별시스템임을 확인하였다. 키워드 : 변조영상 검출, 얼굴 검출, EBGM, 템플릿 매칭, 얼굴 식별" 0be43cf4299ce2067a0435798ef4ca2fbd255901,Title A temporal latent topic model for facial expression recognition,"Title A temporal latent topic model for facial expression recognition Author(s) Shang, L; Chan, KP Citation The 10th Asian Conference on Computer Vision (ACCV 2010), Queenstown, New Zealand, 8-12 November 2010. In Lecture Notes in Computer Science, 2010, v. 6495, p. 51-63 Issued Date http://hdl.handle.net/10722/142604 Rights Creative Commons: Attribution 3.0 Hong Kong License" 0bb574ad77f55f395450b4a9f863ecfdd4880bcd,Learning the Base Distribution in Implicit Generative Models,"Learning the Base Distribution in Implicit Generative Models Y. Cem Subakan(cid:91), Oluwasanmi Koyejo(cid:91), Paris Smaragdis(cid:91),(cid:93) (cid:91)UIUC, (cid:93)Adobe Inc." 0b4189d874ee67f259a1a366ac93740d500064a5,Single-Shot Multi-person 3D Pose Estimation from Monocular RGB,"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB Dushyant Mehta[1,2], Oleksandr Sotnychenko[1,2], Franziska Mueller[1,2], Weipeng Xu[1,2], Srinath Sridhar[3], Gerard Pons-Moll[1,2], Christian Theobalt[1,2] [1] MPI For Informatics [2] Saarland Informatics Campus [3] Stanford University" 0b888196dda951287dddb60bd44798aab16d6fca,Learning Common Sense through Visual Abstraction, 0b937abb3b356a2932d804f9fc4b463485f63d0e,Visual word disambiguation by semantic contexts,"Visual word disambiguation by semantic contexts Yu Su, Frédéric Jurie To cite this version: Yu Su, Frédéric Jurie. Visual word disambiguation by semantic contexts. IEEE Intenational Confer- ence on Computer Vision (ICCV), 2011, Spain. pp.311-318, 2011, <10.1109/ICCV.2011.6126257>. HAL Id: hal-00808655 https://hal.archives-ouvertes.fr/hal-00808655 Submitted on 5 Apr 2013 HAL is a multi-disciplinary open access rchive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not. The documents may come from teaching and research institutions in France or broad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires" 0bc0f9178999e5c2f23a45325fa50300961e0226,Recognizing facial expressions from videos using Deep Belief Networks,"Recognizing facial expressions from videos using Deep Belief Networks CS 229 Project Advisor: Prof. Andrew Ng Adithya Rao Narendran Thiagarajan" 0bc9f1749e23b37ea5b5588c5bfe23879174d343,Pythia v0.1: the Winning Entry to the VQA Challenge 2018,"Pythia v0.1: the Winning Entry to the VQA Challenge 2018 Yu Jiang∗, Vivek Natarajan∗, Xinlei Chen∗, Marcus Rohrbach, Dhruv Batra, Devi Parikh Facebook AI Research" 0bdd8f824fa4d4e770e34268a78dca12fb6a135b,Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases,"Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases Simone Ercoli, Marco Bertini and Alberto Del Bimbo Media Integration and Communication Center, Università degli Studi di Firenze Viale Morgagni 65 - 50134 Firenze, Italy" 0bbd0060e79c5370c6d07bef7b5830e8732e7c1b,Automatic tracker selection w.r.t object detection performance,"Automatic Tracker Selection w.r.t Object Detection Performance Duc Phu Chau Monique Thonnat Franc¸ois Br´emond Slawomir Bak STARS team, INRIA, France {Duc-Phu.Chau, Francois.Bremond, Monique.Thonnat, Slawomir.Bak} 004 route des Lucioles, 06560 Valbonne, France" 0ba544ff0d837ba5279b03eb91246d00f2c78817,Direct Prediction of 3D Body Poses from Motion Compensated Sequences,"Direct Prediction of 3D Body Poses from Motion Compensated Sequences Bugra Tekin1 Artem Rozantsev1 Vincent Lepetit1,2 Pascal Fua1 CVLab, EPFL, Lausanne, Switzerland, TU Graz, Graz, Austria," 0b32cd6dff1561889652450cac5c1abb9833557d,Face Verification in Polar Frequency Domain: A Biologically Motivated Approach,"Face Verification in Polar Frequency Domain: a Biologically Motivated Approach Yossi Zana1, Roberto M. Cesar-Jr1, Rogerio S. Feris2, and Matthew Turk2 ⋆ Dept. of Computer Science, IME-USP, Brazil, University of California, Santa Barbara," 0b24cca96ca61248a3fa3973525a967f94292835,Two Novel Face Recognition Approaches,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 0b6f810f287561ff694a9406c7b319fd8549ca68,Face Recognition Based on Texture Features using Local Ternary Patterns,"I.J. Image, Graphics and Signal Processing, 2015, 10, 37-46 Published Online September 2015 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijigsp.2015.10.05 Face Recognition Based on Texture Features using Local Ternary Patterns Associate Professor, Dept. of CSE, BVRIT Hyderabad College of Engineering for Women, Hyderabad, T.S., India. K. Srinivasa Reddy Director-CACR, Dean-Computer Sciences (CSE & IT), Anurag Group of Institutions, Hyderabad, T.S., India. Email: V. Vijaya Kumar Email: B. Eswara Reddy Professor, Dept. of CSE, JNTUA, Ananthapuram, A.P., India. Email:" 0b57eb772ad9129ea4011c7fcb16c57967409018,Identifying Paintings from Text Descriptions,"Proceedings of 2016 NAACL Human-Computer Question Answering Workshop, pages 43–47, San Diego, California, June 12-17, 2016. c(cid:13)2016 Association for Computational Linguistics" 0bf26d2fd1b375f50c0a6bef086f09f7698c3156,Predicting Entry-Level Categories,"Noname manuscript No. (will be inserted by the editor) Predicting Entry-Level Categories Vicente Ordonez · Wei Liu · Jia Deng · Yejin Choi · Alexander C. Berg · Tamara L. Berg Received: date / Accepted: date" 0b2c543e0c47454c4512569175094e6cb6ae02a9,The VizWiz Grand Challenge : A Large Visual Question Answering Dataset from Blind People Anonymous CVPR submission,"#1687 CVPR 2016 Submission #1687. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE. The VizWiz Grand Challenge: A Large Visual Question Answering Dataset from Blind People Anonymous CVPR submission Paper ID 1687" 0bbaa29d1203d3a241074d4c6c7d01171b15afdb,AN EFFICIENT FRAMEWORK FOR IMAGE DATA RECOGNITION & RETRIEVAL,"ISSN: 2277-9655 [Singh* et al., 5.(7): July, 2016] IC™ Value: 3.00 Impact Factor: 4.116 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY AN EFFICIENT FRAMEWORK FOR IMAGE DATA RECOGNITION & RETRIEVAL Diljot Singh*, Tejpreet Singh, Sanjeev Kumar * M.Tech Research Scholar, KCET, Amritsar Assistant Professor, Department of CSE, KCET, Amritsar Assistant Professor, Department of ECE, KCET, Amritsar DOI: 10.5281/zenodo.57938" 0b02bfa5f3a238716a83aebceb0e75d22c549975,Learning Probabilistic Models for Recognizing Faces under Pose Variations,"Learning Probabilistic Models for Recognizing Faces under Pose Variations M. Saquib Sarfraz and Olaf Hellwich Computer vision and Remote Sensing, Berlin university of Technology Sekr. FR-3-1, Franklinstr. 28/29, Berlin, Germany" 0b635b58cd4d739bed415f77de8d1ec3d79e26d4,Chapter 8 . Face Tracking and Recognition from Video ?,"Stan Z. Li Anil K. Jain (Eds.) Handbook of Face Recognition Springer" 0ba6f4fb548d8289fb42d68ac64d55f9e3a274ca,Auto-Context and Its Application to High-Level Vision Tasks and 3D Brain Image Segmentation,"Auto-context and Its Application to High-level Vision Tasks nd 3D Brain Image Segmentation Lab of Neuro Imaging, University of California, Los Angeles Zhuowen Tu and Xiang Bai July 9, 2009" 0bcd89b356dc78aaf3573086f13e94b8e7b5bee6,Comparative Testing of Face Detection Algorithms,"Comparative Testing of Face Detection Algorithms⋆ Nikolay Degtyarev and Oleg Seredin Tula State University http://lda.tsu.tula.ru" 0babc4af06d210cf38bdf8324c339b6cf3f424fa,A Predictive Model of Patient Readmission Using Combined ICD-9 Codes as Engineered Features,"A Predictive Model of Patient Readmission Using Combined ICD-9 Codes as Engineered Features" 0b4c4ea4a133b9eab46b217e22bda4d9d13559e6,MORF: Multi-Objective Random Forests for face characteristic estimation,"MORF: Multi-Objective Random Forests for Face Characteristic Estimation Dario Di Fina1 MICC - University of Florence Svebor Karaman1,3 Andrew D. Bagdanov2 {dario.difina, CVC - Universitat Autonoma de Barcelona Alberto Del Bimbo1 DVMM Lab - Columbia University" 0beaf17d42b1171dd245131825d2de67000f45ac,Expert Gate: Lifelong Learning with a Network of Experts,"Expert Gate: Lifelong Learning with a Network of Experts Rahaf Aljundi Punarjay Chakravarty Tinne Tuytelaars KU Leuven, ESAT-PSI, iMinds, Belgium {rahaf.aljundi, Punarjay.Chakravarty," 0b4453df81091bcdafedc07b64bea946bf3441b2,Fast and Accurate 3 D Face Recognition Using Registration to an Intrinsic Coordinate System and Fusion of Multiple Region Classifiers,"Int J Comput Vis DOI 10.1007/s11263-011-0426-2 Fast and Accurate 3D Face Recognition Using Registration to an Intrinsic Coordinate System and Fusion of Multiple Region Classifiers Luuk Spreeuwers Received: 20 September 2010 / Accepted: 7 February 2011 © The Author(s) 2011. This article is published with open access at Springerlink.com" 0b02365863b5037cb64a7de0aee805d0371f6b21,"Face Recognition Committee Machine : Methodology , Experiments and A System Application","Face Recognition Committee Machine: Methodology, Experiments and A System Application Tang Ho-Man A Thesis Submitted in Partial Ful(cid:12)lment of the Requirements for the Degree of Master of Philosophy Computer Science and Engineering Supervised by Prof. Michael R. Lyu (cid:13)The Chinese University of Hong Kong July 2003 The Chinese University of Hong Kong holds the copyright of this thesis. Any person(s) intending to use a part or whole of the materials in the thesis in proposed publication must seek copyright release from the Dean of the Graduate School." 0b8c9acb478c856eb157c648b25b3d60117392fd,Learning to Divide and Conquer for Online Multi-target Tracking,"Learning to Divide and Conquer for Online Multi-Target Tracking Francesco Solera Simone Calderara Rita Cucchiara Department of Engineering University of Modena and Reggio Emilia" 0b605b40d4fef23baa5d21ead11f522d7af1df06,Label-Embedding for Attribute-Based Classification,"Label-Embedding for Attribute-Based Classification Zeynep Akataa,b, Florent Perronnina, Zaid Harchaouib and Cordelia Schmidb Computer Vision Group∗, XRCE, France LEAR†, INRIA, France" 0b6bd0a6f396e1479dc30318102bf49c12959783,griffith . edu . au Face recognition using local binary decisions,"Face recognition using local binary decisions Author James, Alex, Dimitrijev, Sima Published Journal Title IEEE Signal Processing Letters https://doi.org/10.1109/LSP.2008.2006339 Copyright Statement © 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Downloaded from http://hdl.handle.net/10072/23556 Griffith Research Online https://research-repository.griffith.edu.au" 0bc82ec532228427a497ac47391d524e3b4537ae,Fluid Annotation: A Human-Machine Collaboration Interface for Full Image Annotation,"Fluid Annotation: A Human-Machine Collaboration Interface for Full Image Annotation Mykhaylo Andriluka∗ Jasper R. R. Uijlings∗ Google Research Z¨urich, Switzerland Vi(cid:138)orio Ferrari" 0bbde476713458acbdbe86157bc5067b36cad2ad,Automated Pain Detection from Facial Expressions using FACS: A Review,"Automated Pain Detection from Facial Expressions using FACS: A Review Zhanli Chen, Student Member, IEEE, Rashid Ansari, Fellow, IEEE, and Diana J. Wilkie, Fellow, AAN," 0b8ef6f5ec5dfc3eded5241fd3d636a596b94d26,Stereological analysis of amygdala neuron number in autism.,"7674 • The Journal of Neuroscience, July 19, 2006 • 26(29):7674 –7679 Neurobiology of Disease Stereological Analysis of Amygdala Neuron Number in Autism Cynthia Mills Schumann and David G. Amaral Department of Psychiatry and Behavioral Sciences and The M.I.N.D. Institute, University of California, Davis, Sacramento, California 95817 The amygdala is one of several brain regions suspected to be pathological in autism. Previously, we found that young children with autism have a larger amygdala than typically developing children. Past qualitative observations of the autistic brain suggest increased cell density in some nuclei of the postmortem autistic amygdala. In this first, quantitative stereological study of the autistic brain, we counted and measured neurons in several amygdala subdivisions of 9 autism male brains and 10 age-matched male control brains. Cases with omorbid seizure disorder were excluded from the study. The amygdaloid complex was outlined on coronal sections then partitioned into five reliably defined subdivisions: (1) lateral nucleus, (2) basal nucleus, (3) accessory basal nucleus, (4) central nucleus, and (5) remaining nuclei. There is no difference in overall volume of the amygdala or in individual subdivisions. There are also no changes in cell size. However, there are significantly fewer neurons in the autistic amygdala overall and in its lateral nucleus. In conjunction with the findings from previous magnetic resonance imaging studies, the autistic amygdala appears to undergo an abnormal pattern of postnatal devel- opment that includes early enlargement and ultimately a reduced number of neurons. It will be important to determine in future studies whether neuron loss in the amygdala is a consistent characteristic of autism and whether cell loss occurs in other brain regions as well. Key words: autism; neuropathology; stereology; neuronal density; medial temporal lobe; neuroanatomy; amygdaloid complex Introduction Autism is a lifelong neurodevelopmental disorder characterized" 0b4b6932d5df74b366d9235b40334bc40d719c72,Temporal Ensembling for Semi-Supervised Learning,"Temporal Ensembling for Semi-Supervised Learning Samuli Laine NVIDIA Timo Aila NVIDIA" 0bdfc21178347ed4f137d4c7d0ba14c996c66b6e,Automated X-Ray Object Recognition Using an Efficient Search Algorithm in Multiple Views,"Automated X-ray object recognition using n efficient search algorithm in multiple views Domingo Mery, Vladimir Riffo, Irene Zuccar, Christian Pieringer Department of Computer Science – Pontificia Universidad Cat´olica de Chile Av. Vicu˜na Mackenna 4860(143) – Santiago de Chile http://dmery.ing.puc.cl" 0b3a146c474166bba71e645452b3a8276ac05998,Who ’ s in the Picture ?,"Who’s in the Picture? Tamara L. Berg, Alexander C. Berg, Jaety Edwards and D.A. Forsyth Berkeley, CA 94720 Computer Science Division U.C. Berkeley" b47ea4d5b0040d85181925bda74da4ab5303768f,LIFEisGAME: A Facial Character Animation System to Help Recognize Facial Expressions,"LIFEisGAME:A Facial Character Animation System to Help Recognize Facial Expressions Tiago Fernandes1,5, Samanta Alves2, José Miranda3,5, Cristina Queirós2, Verónica Orvalho1,4 Instituto de Telecomunicações, Lisboa, Portugal, Faculdade de Psicologia da Universidade do Porto, Porto, Portugal, Instituto Politécnico da Guarda, Porto, Portugal, Faculdade de Ciências da Universidade do Porto, Porto, Portugal, 5 Faculdade de Engenharia da Universidade do Porto, Porto, Portugal," b4a16fe1469f2048d031db626b7cbc5bec7f4055,ONLINE FACIAL CARICATURE GENERATOR,"ONLINE FACIAL CARICATURE GENERATOR Rudy Adipranata Informatics Department Petra Chistian University Siwalankerto 121-131 Surabaya, Indonesia 62-31-8439040 Stephanus Surya Jaya Informatics Department Petra Chistian University Siwalankerto 121-131 Surabaya, Indonesia 62-31-8439040 Kartika Gunadi Informatics Department Petra Chistian University Siwalankerto 121-131 Surabaya, Indonesia 62-31-8439040" b4fe9594e1de682e7270645ba95ab64727b6632e,Generative Adversarial Positive-Unlabelled Learning,"Generative Adversarial Positive-Unlabelled Learning Ming Hou1, Brahim Chaib-draa2, Chao Li1, Qibin Zhao1, Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan Department of Computer Science and Software Engineering, Laval University, Quebec, Canada" b4f6962068c27d10df9016090a0ca14f65f26b70,A Statisitical Shape Model for Deformable Surface Registration.,"A STATISITICAL SHAPE MODEL FOR DEFORMABLE SURFACE REGISTRATION Wei Quan, Bogdan J. Matuszewski and Lik-Kwan Shark Applied Digital Signal and Image Processing (ADSIP) Research Centre University of Central Lancashire, Preston PR1 2HE, United Kingdom {wquan, bmatuszewski1, Keywords: Deformable Registration, Surface Matching, Shape Modelling and Face Articulation." b40290a694075868e0daef77303f2c4ca1c43269,Combining Local and Global Information for Hair Shape Modeling,"第 40 卷 第 4 期 014 年 4 月 自 动 化 学 报 ACTA AUTOMATICA SINICA Vol. 40, No. 4 April, 2014 融合局部与全局信息的头发形状模型 王 楠 1 艾海舟 1 摘 要 头发在人体表观中具有重要作用, 然而, 因为缺少有效的形状模型, 头发分割仍然是一个非常具有挑战性的问题. 本 文提出了一种基于部件的模型, 它对头发形状以及环境变化更加鲁棒. 该模型将局部与全局信息相结合以描述头发的形状. 局 部模型通过一系列算法构建, 包括全局形状词表生成, 词表分类器学习以及参数优化; 而全局模型刻画不同的发型, 采用支持 向量机 (Support vector machine, SVM) 来学习, 它为所有潜在的发型配置部件并确定势函数. 在消费者图片上的实验证明 了本文算法在头发形状多变和复杂环境等条件下的准确性与有效性. 关键词 头发形状建模, 部件模型, 部件配置算法, 支持向量机 引用格式 王楠, 艾海舟. 融合局部与全局信息的头发形状模型. 自动化学报, 2014, 40(4): 615−623 DOI 10.3724/SP.J.1004.2014.00615 Combining Local and Global Information for Hair Shape Modeling WANG Nan1 AI Hai-Zhou1" b4d117e109b3a6762d1b675defd9f2b228613ac1,Financialized methods for market-based multi-sensor fusion,"Congress Center Hamburg Sept 28 - Oct 2, 2015. Hamburg, Germany 978-1-4799-9993-4/15/$31.00 ©2015 IEEE" b4a3f480e2004bdc8106de2f772283101bb290d0,Multi-stage ranking approach for fast person re-identification,"IET Research Journals A Multi-Stage Ranking Approach for Fast Person Re-Identification A Multi-Stage Ranking Approach for Fast Person Re-Identification Bahram Lavi, Giorgio Fumera , Fabio Roli Department of Electrical and Electronic Engineering, University of Cagliari Piazza d’Armi, 09123, Cagliari, Italy E-mail: ISSN 1751-8644 doi: 0000000000 www.ietdl.org" b408b939c0f3be9cce0f84871a78a71d1684cd77,Identifying spatial relations in images using convolutional neural networks,"Identifying Spatial Relations in Images using Convolutional Neural Networks Mandar Haldekar, Ashwinkumar Ganesan Dept. Of Computer Science & Engineering, Tim Oates Dept. Of Computer Science & Engineering, UMBC, Baltimore, MD mandarh1, UMBC, Baltimore, MD" b44d8ecac21867c540d9122a150c8d8c0875cbe6,Mixture Density Generative Adversarial Networks,"Mixture Density Generative Adversarial Networks Hamid Eghbal-zadeh1 ∗ Werner Zellinger2 Gerhard Widmer1 LIT AI Lab & Institute of Computational Perception Department of Knowledge-Based Mathematical Systems {hamid.eghbal-zadeh, werner.zellinger, Johannes Kepler University of Linz, Austria" b498640d8f0ac5a628563ff84dbef8d35d12a7ec,Overcoming catastrophic forgetting with hard attention to the task,"Overcoming Catastrophic Forgetting with Hard Attention to the Task Joan Serr`a 1 D´ıdac Sur´ıs 1 2 Marius Miron 1 3 Alexandros Karatzoglou 1" b47386e10125462d60d66f8d6d239a69c5966853,ROBUST MULTI GRADIENT ENTROPY METHOD FOR FACE RECOGNITION SYSTEM FOR LOW CONTRAST NOISY IMAGES,"International Journal of Emerging Trends & Technology in Computer Science (IJETTCS) Web Site: www.ijettcs.org Email: ISSN 2278-6856 Volume 2, Issue 3, May – June 2013 ROBUST MULTI GRADIENT ENTROPY METHOD FOR FACE RECOGNITION SYSTEM FOR LOW CONTRAST NOISY IMAGES C. Naga Raju1, P.Prathap Naidu2, R. Pradeep Kumar Reddy3, G. Sravana Kumari4 Associate Professor, CSE Dept, YSR Engg College of YVU Asst. Professor, CSE Dept, RGM Engg College Asst. Professor, CSE Dept, YSR Engg College. M.Tech In CSE RGM Engg College the most recognition under difficult" b4616157d8f602bedf7b4f69db73f6b28a08bf9e,Multiclass semantic segmentation of faces using CRFs,"Turk J Elec Eng & Comp Sci (2017) 25: 3164 { 3174 ⃝ T (cid:127)UB_ITAK doi:10.3906/elk-1607-332 Multiclass semantic segmentation of faces using CRFs Khalil KHAN1;(cid:3) , Nasir AHMAD2, Khalil ULLAH3, Irfanud DIN4 Department of Electrical Engineering, University of Poonch, Rawlakot, Pakistan Department of Computer Engineering, University of Engineering & Technology, Peshawar, Pakistan Department of Electrical Engineering, National University of Computer & Emerging Sciences, Peshawar, Pakistan Department of Information Engineering, Inha University, Tashkent, Uzbekistan Received: 30.07.2016 (cid:15) Accepted/Published Online: 23.12.2016 (cid:15) Final Version: 30.07.2017" b41374f4f31906cf1a73c7adda6c50a78b4eb498,Iterative Gaussianization: From ICA to Random Rotations,"This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. Iterative Gaussianization: From ICA to Random Rotations Valero Laparra, Gustavo Camps-Valls, Senior Member, IEEE, and Jesús Malo" b4223cc72543656c28b55af1ffdabb1e47a0f2dd,Stacking with Auxiliary Features for Visual Question Answering,"New Orleans, Louisiana, June 1 - 6, 2018. c(cid:13)2018 Association for Computational Linguistics Proceedings of NAACL-HLT 2018, pages 2217–2226" b4c48aa7a93f38d2eb60209120a1a8daa61c4545,Diversity in Object Proposals,"DIVERSITY IN OBJECT PROPOSALS Anton Winschel Rainer Lienhart Christian Eggert Multimedia Computing and Computer Vision Lab {anton.winschel, rainer.lienhart, University of Augsburg, Germany" b49aa569ff63d045b7c0ce66d77e1345d4f9745c,Convolutional Neural Networks for Crop Yield Prediction using Satellite Images,"Convolutional Neural Networks for Crop Yield Prediction using Satellite Images H. Russello" b4270de7380d305b4417f662686093c40d842da4,UNIVERSITY OF CALIFORNIA RIVERSIDE Graphical Models for Wide-Area Activity Analysis in Continuous Videos A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy,"UNIVERSITY OF CALIFORNIA RIVERSIDE Graphical Models for Wide-Area Activity Analysis in Continuous Videos A Dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy Computer Science Nandita M. Nayak May 2014 Dissertation Committee: Professor Amit K. Roy-Chowdhury, Chairperson Professor Christian Shelton Professor Eamonn Keogh Professor Victor Zordan" b4ee2a6b5fdf66f57e94a998cff2acef4af7d256,Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes,"Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes Christian Wojek, Stefan Walk, Stefan Roth, Konrad Schindler, Bernt Schiele" b49425f78907fcc447d181eb713abffc74dd85e4,Sampling Matters in Deep Embedding Learning,"Sampling Matters in Deep Embedding Learning Chao-Yuan Wu∗ UT Austin R. Manmatha A9/Amazon Alexander J. Smola Amazon Philipp Kr¨ahenb¨uhl UT Austin" b4a5136a5080f62a4123b6218e7a3570da6d5d3b,Robust human detection using multiple scale of cell based histogram of oriented gradients and adaboost learning,"Robust Human Detection Using Multiple Scale of Cell Based Histogram of Oriented Gradients nd AdaBoost Learning Van-Dung Hoang, My-Ha Le, and Kang-Hyun Jo School of Electrical Engineering, University of Ulsan, Korea" b411850a3614fbb06bc77e6f776b2f23af563a90,Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters,"Size does matter: improving object recognition nd 3D reconstruction with cross-media analysis of image clusters Stephan Gammeter1, Till Quack1, David Tingdahl2, and Luc van Gool1,2 BIWI, ETH Z¨urich1 http://www.vision.ee.ethz.ch VISICS, K.U. Leuven2 http://www.esat.kuleuven.be/psi/visics" b4b1b39f8902208bbd37febfb68e08809098036d,TRECVid Semantic Indexing of Video : A 6-year Retrospective,"UvA-DARE (Digital Academic Repository) TRECVid Semantic Indexing of Video: A 6-year Retrospective Awad, G.; Snoek, C.G.M.; Smeaton, A.F.; Quénot, G. Published in: ITE Transactions on Media Technology and Applications 0.3169/mta.4.187 Link to publication Citation for published version (APA): Awad, G., Snoek, C. G. M., Smeaton, A. F., & Quénot, G. (2016). TRECVid Semantic Indexing of Video: A 6- year Retrospective. ITE Transactions on Media Technology and Applications, 4(3), 187-208. DOI: 0.3169/mta.4.187 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Download date: 02 Nov 2018" b46f96ee1ef0c7b31e5cec9abc60aa5f77fe4245,Literature Review on Real Time People Tracking in a Camera Network,"________________________________________________________________________________________________ International Journal of Electrical, Electronics and Computer Systems (IJEECS) Literature Review on Real Time People Tracking in a Camera Network Khan Farheen Wahab, 2Aniruddha Kailuke ,2Department of Electronics (Communication), Priyadarshini Institute of Engineering, The University of Nagpur (RTMNU) Nagpur" b4b6a0129bf6a716fca80a4cfc322687a72fa927,Automatic Generation of Planar Marionettes from Frontal Images,"Automatic Generation of Planar Marionettes from Frontal Images Elad Richardson and Gil Ben-Shachar Supervised by Anastasia Dubrovina and Aaron Weltzer" b4c02e071432a9a986501b7317b524f216e87ec8,Visual Saliency Prediction using Deep learning Techniques,"Visual Saliency Prediction using Deep learning Techniques A Degree Thesis Submitted to the Faculty of the Escola Tècnica d'Enginyeria de Telecomunicació de Barcelona Universitat Politècnica de Catalunya Junting Pan In partial fulfilment of the requirements for the degree in TELECOMUNICATION ENGINEERING Advisor: Xavier Giró i Nieto Barcelona, July 2015" b49affdff167f5d170da18de3efa6fd6a50262a2,Linking Names and Faces : Seeing the Problem in Different Ways,"Author manuscript, published in ""Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recognition, Marseille : France (2008)""" b4ee64022cc3ccd14c7f9d4935c59b16456067d3,Unsupervised Cross-Domain Image Generation,"Unsupervised Cross-Domain Image Generation Xinru Hua, Davis Rempe, and Haotian Zhang" b40881a905cf6c4963658df4f64b860f9b1755fe,Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation,"Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation Matan Sela Elad Richardson Ron Kimmel Department of Computer Science, Technion - Israel Institute of Technology Figure 1: Results of the proposed method. Reconstructed geometries are shown next to the corresponding input images." b4e0e4e8b92067ac4d31961832ce30543cffff0a,Using lip features for multimodal speaker verification,"ISCA Archive http://www.isca-speech.org/archive 001: A Speaker Odyssey The Speaker Recognition Workshop Crete, Greece June 18-22, 2001 Using Lip Features for Multimodal Speaker Verification Xiaozheng Zhang† and Charles C. Broun‡ The Georgia Institute of Technology, Atlanta, Georgia , USA Motorola Human Interface Lab, Tempe, Arizona, USA" a0e03c5b647438299c79c71458e6b1776082a37b,Areas of Attention for Image Captioning,"transformerFigure1.Weproposeanattentionmechanismthatjointlypredictsthenextcaptionwordandthecorrespondingregionateachtime-stepgiventheRNNstate(top).BesidesimplementingourmodelusingattentionareasdefinedoverCNNactivationgridsorobjectproposals,asusedinpreviouswork,wealsopresentaend-to-endtrainableconvolutionalspatialtransformerapproachtocomputeimagespecificattentionareas(bottom).typeorlocation,objectproperties,andtheirinteractions.Neuralencoder-decoderbasedapproaches,similartothoseusedinmachinetranslation[30],havebeenfoundveryeffectiveforthistask,seee.g.[19,23,32].Thesemethodsuseaconvolutionalneuralnetwork(CNN)toen-codetheinputimageintoacompactrepresentation.Are-currentneuralnetwork(RNN)isusedtodecodethisrepre-sentationword-by-wordintoanaturallanguagedescriptionoftheimage.Whileeffective,thesemodelsarelimitedinthattheimageanalysisis(i)static,i.e.doesnotchangeovertimeasthedescriptionisproduced,and(ii)notspatiallylo-calized,i.e.describesthesceneasawholeinsteadoffo-cousingonlocalaspectsrelevanttopartsofthedescription.Attentionmechanismscanaddresstheselimitationsbydy-namicallyfocusingondifferentpartsoftheinputastheout-putsequenceisgenerated.Suchmechanismsareeffectiveforavarietyofsequentialpredictiontasks,includingma-1" a0e3775fd5d5df951ac7f65d3a9165bf4b96fbd8,Towards Automatic Image Editing: Learning to See another You,"Towards Automatic Image Editing: Learning to See another You Amir Ghodrati1∗, Xu Jia1∗, Marco Pedersoli2†, Tinne Tuytelaars1 KU Leuven, ESAT-PSI, iMinds INRIA" a0dfb8aae58bd757b801e2dcb717a094013bc178,Reconocimiento de expresiones faciales con base en la dinámica de puntos de referencia faciales,"Reconocimiento de expresiones faciales con base en la din´amica de puntos de referencia faciales E. Morales-Vargas, C.A. Reyes-Garcia, Hayde Peregrina-Barreto Instituto Nacional de Astrof´ısica ´Optica y Electr´onica, Divisi´on de Ciencias Computacionales, Tonantzintla, Puebla, M´exico Resumen. Las expresiones faciales permiten a las personas comunicar emociones, y es pr´acticamente lo primero que observamos al interactuar on alguien. En el ´area de computaci´on, el reconocimiento de expresiones faciales es importante debido a que su an´alisis tiene aplicaci´on directa en ´areas como psicolog´ıa, medicina, educaci´on, entre otras. En este articulo se presenta el proceso de dise˜no de un sistema para el reconocimiento de expresiones faciales utilizando la din´amica de puntos de referencia ubi- ados en el rostro, su implementaci´on, experimentos realizados y algunos de los resultados obtenidos hasta el momento. Palabras clave: Expresiones faciales, clasificaci´on, m´aquinas de soporte vectorial,modelos activos de apariencia. Facial Expressions Recognition Based on Facial Landmarks Dynamics" a0541d4a28d90a17cd3eaa9d1797882eacc8ccf0,Improving Person Re-identification via Pose-Aware Multi-shot Matching,"Improving Person Re-identification via Pose-aware Multi-shot Matching Yeong-Jun Cho and Kuk-Jin Yoon Computer Vision Laboratory, GIST, South Korea {yjcho," a06ef8ef4838c048b814563f7cca479c7d4513f2,Multi-module Singular Value Decomposition for Face Recognition,"ORIENTAL JOURNAL OF COMPUTER SCIENCE & TECHNOLOGY An International Open Free Access, Peer Reviewed Research Journal Published By: Oriental Scientific Publishing Co., India. www.computerscijournal.org ISSN: 0974-6471 April 2014, Vol. 7, No. (1): Pgs. 09-14 Multi-module Singular Value Decomposition for Face Recognition A. NAMACHIVAYAM and KALIYAPERUMAL KARTHIKEYAN Eritrea Institute of Technology, Asmara, Eritrea, North East Africa. (Received: March 20, 2014; Accepted: March 30, 2014)" a0303a4d37e8264028808661050c4443b6b880de,Robust Video Object Tracking in Distributed Camera Networks,"(cid:13)Copyright 2017 Younggun Lee" a06761b3181a003c2297d8e86c7afc20e17fd2c6,Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors,"Article Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors Jong Hyun Kim, Hyung Gil Hong and Kang Ryoung Park * Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 100-715, Korea; (J.H.K.); (H.G.H.) * Correspondence: Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 Academic Editor: Vittorio M. N. Passaro Received: 31 March 2017; Accepted: 4 May 2017; Published: 8 May 2017" a022eff5470c3446aca683eae9c18319fd2406d5,Deep learning for semantic description of visual human traits. (Apprentissage profond pour la description sémantique des traits visuels humains),"017-ENST-0071 EDITE - ED 130 Doctorat ParisTech T H È S E pour obtenir le grade de docteur délivré par TÉLÉCOM ParisTech Spécialité « SIGNAL et IMAGES » présentée et soutenue publiquement par Grigory ANTIPOV le 15 décembre 2017 Apprentissage Profond pour la Description Sémantique des Traits Visuels Humains Directeur de thèse : Jean-Luc DUGELAY Co-encadrement de la thèse : Moez BACCOUCHE Mme Bernadette DORIZZI, PRU, Télécom SudParis Mme Jenny BENOIS-PINEAU, PRU, Université de Bordeaux M. Christian WOLF, MC/HDR, INSA de Lyon M. Patrick PEREZ, Chercheur/HDR, Technicolor Rennes M. Moez BACCOUCHE, Chercheur/Docteur, Orange Labs Rennes M. Jean-Luc DUGELAY, PRU, Eurecom Sophia Antipolis" a044dc0ff3fa2a8f0a80afff9eb2cbc762996e3b,An Efficient Face Recognition System Based On the Hybridization of Pose Invariant and Illumination Process,"An An An An Efficient Face Recognition System Based On Efficient Face Recognition System Based On thethethethe Efficient Face Recognition System Based On Efficient Face Recognition System Based On Pose Invariant andandandand Illumination Process Hybridization ofofofof Pose Invariant Hybridization Illumination Process Pose Invariant Hybridization Hybridization Pose Invariant Illumination Process Illumination Process S. Muruganantham† and Dr. T. Jebarajan††, Assistant Professor, S.T.Hindu College, Nagercoil. Principal, Kings College of Engineering, Chennai. that compensates" a01f9461bc8cf8fe40c26d223ab1abea5d8e2812,Facial Age Estimation Through the Fusion of Texture and Local Appearance Descriptors,"Facial Age Estimation Through the Fusion of Texture nd local appearance Descriptors Ivan Huerta1, Carles Fern´andez2, and Andrea Prati1 DPDCE, University IUAV, Santa Croce 1957, 30135 Venice, Italy Herta Security, Pau Claris 165 4-B, 08037 Barcelona, Spain" a0e5afb1237d47f7a8ac66e7b5ada24cec5222cb,Semantic pooling for image categorization using multiple kernel learning,"SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING Thibaut Durand(1,2), David Picard(1), Nicolas Thome(2), Matthieu Cord(2) (1) ETIS, UMR 8051 / ENSEA, Universit´e Cergy-Pontoise, CNRS, F-95000, Cergy, (2) Sorbonne Universit´es, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005, Paris, France" a080154a6668cc9d37944a9ae4650a14b9146aa7,Enhanced maximum likelihood face recognition,"Enhanced maximum likelihood face recognition X.D. Jiang, B. Mandal and A. Kot A method to enhance maximum likelihood face recognition is presented. It selects a more robust weighting parameter and discards unreliable dimensions to circumvent problems of the unreliable small nd zero eigenvalues. This alleviates the over-fitting problem in face recognition, where the high dimensionality and limited number of training samples are critical issues. The proposed method gives superior experimental results. Introduction: The maximum likelihood (ML) method [1] is one of the est performing face recognition approaches. It decomposes the face image space into a principal subspace F and a residual subspace F¯ . A main contribution of ML is the replacement of the unreliable eigen- values in F¯ by a constant. This solves the singularity problem of the ovariance matrix. However, ML does not well solve the over-fitting problem. The constant used to replace the eigenvalues in F¯ estimated as the average eigenvalue over F¯. The high-dimensional face image and the limited number of training samples result in over-" a00c0928a03d58a365d086a8df76ae93caf7cc63,Improving condition- and environment-invariant place recognition with semantic place categorization,"© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtainedfor all other uses, in any current or future media, including reprinting/republishing this materialfor advertising or promotional purposes, creating new collective works, for resale or redistributionto servers or lists, or reuse of any copyrighted component of this work in other works.Pre-print of article that will appear at the 2017 IEEE International Conference on IntelligentRobots and Systems.Please cite this paper as:S. Garg, A. Jacobson, S. Kumar, and M. Milford, “Improving Condition- and Environment-Invariant Place Recognition with Semantic Place Categorization,” in Intelligent Robots and Systems (IROS), 2017 IEEE/RSJ International Conference on. IEEE, author = {Garg, Sourav and Jacobson, Adam and Kumar, Swagat and Milford, Michael}, booktitle = {Intelligent Robots and Systems (IROS), 2017 IEEE/RSJ International Conference on}, organization = {IEEE}, title = {{Improving Condition- and Environment-Invariant Place Recognition with Semantic Place Categorization}}, year = {2017} }" a01ba008252d2ce32f326f50c208c9ad9d5c78a6,Detecting Sudden Pedestrian Crossings and Avoiding Accidents Using Arm 11 K,"K. Sri Krishna Aditya et al Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 3, Issue 5, Sep-Oct 2013, pp.1213-1216 RESEARCH ARTICLE OPEN ACCESS Detecting Sudden Pedestrian Crossings and Avoiding Accidents Using Arm 11 K. Sri Krishna Aditya1, T. Surya Kavita2, U. Yedukondalu3 Assistant Professor, 2Associate Professor, 3Head of the Department E.C.E. Aditya Engineering College, 2Aditya Engineering College, 3Aditya Engineering College" a079309d28b6f8753ca26a789bd0bc43de9bd9f8,Interpretable Counting for Visual Question Answering,"Published as a conference paper at ICLR 2018 INTERPRETABLE COUNTING FOR VISUAL QUESTION ANSWERING Alexander Trott, Caiming Xiong∗, & Richard Socher Salesforce Research Palo Alto, CA" a000149e83b09d17e18ed9184155be140ae1266e,Chapter 9 Action Recognition in Realistic Sports Videos,"Chapter 9 Action Recognition in Realistic Sports Videos Khurram Soomro and Amir R. Zamir" a016fbe8d09402316c7b38946ccd502d76aa8c74,Using a Single RGB Frame for Real Time 3D Hand Pose Estimation in the Wild,"Using a single RGB frame for real time 3D hand pose estimation in the wild Paschalis Panteleris1 Iason Oikonomidis1 Institute of Computer Science, FORTH Computer Science Department, UOC Antonis Argyros1,2" a0c37f07710184597befaa7e6cf2f0893ff440e9,Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning, a098fab95db313d8bd2a5175b519d7de5a3a675a,Performance evaluation and comparison of PCA Based human face recognition methods for distorted images,"Int. J. Mach. Learn. & Cyber. (2011) 2:245–259 DOI 10.1007/s13042-011-0023-2 O R I G I N A L A R T I C L E Performance evaluation and comparison of PCA Based human face recognition methods for distorted images Bruce Poon • M. Ashraful Amin • Hong Yan Received: 7 April 2011 / Accepted: 27 May 2011 / Published online: 5 July 2011 Ó Springer-Verlag 2011" a0798a0a422520241cc02282946882dd1ef853cd,Full Quantification of Left Ventricle via Deep Multitask Learning Network Respecting Intra- and Inter-Task Relatedness,"Full Quantification of Left Ventricle via Deep Multitask Learning Network Respecting Intra- and Inter-Task Relatedness Wufeng Xue, Andrea Lum, Ashley Mercado, Mark Landis, James Warrington, nd Shuo Li* Department of Medical Imaging, Western University, ON, Canada Digital Imaging Group of London, ON, Canada" a090d61bfb2c3f380c01c0774ea17929998e0c96,On the dimensionality of video bricks under varying illumination,"On the Dimensionality of Video Bricks under Varying Illumination Beijing Lab of Intelligent Information Technology, School of Computer Science, Youdong Zhao, Xi Song, Yunde Jia Beijing Institute of Technology, Beijing 100081, PR China {zyd458, songxi," a06805d4de16df54395e1700ec51797e5a65eb64,Fusion of Stereo Vision for Pedestrian Recognition using Convolutional Neural Networks,"Fusion of Stereo Vision for Pedestrian Recognition using Convolutional Neural Networks D˘anut¸ Ovidiu Pop1,2,3, Alexandrina Rogozan2, Fawzi Nashashibi1, Abdelaziz Bensrhair2 - INRIA Paris - RITS Team Paris - France - INSA Rouen - LITIS Laboratory Rouen - France - Babe¸s-Bolyai University - Department of Computer Science Cluj Napoca- Romania Pedestrian detection is a highly debated issue in the sci-" a0a950f513b4fd58cee54bccc49b852943ffd02c,Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart,"Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart Chao Yang1, Yuhang Song1, Xiaofeng Liu2, Qingming Tang3, and C.-C. Jay Kuo1 USC, 2Carnegie Mellon University, 3Toyota Technological Institute at Chicago," a010835842ac0e49eade395f056e1e33d45b6ea5,Four Way Local Binary Pattern for Gender Classification Using Periocular Images,"Four Way Local Binary Pattern for Gender Classification Using Periocular Images Md. Siyam Sajeeb Khan (2014-1-60-024) Rifat Mehreen Amin (2014-1-60-003) Department of Computer Science and Engineering East West University Aftabnagar, Dhaka-1212, Bangladesh August, 2017" a0e286f3c6a72c857ffd03bd8ab9a9f9b98c4432,AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018,"AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018 Sharif Amit Kamran Ahmed Imtiaz Humayun Bengali.AI Dhaka, Bangladesh Bengali.AI Dhaka, Bangladesh Samiul Alam Bengali.AI Dhaka, Bangladesh Rashed Mohammad Doha Bengali.AI Dhaka, Bangladesh Manash Kumar Mandal Bengali.AI Dhaka, Bangladesh Tahsin Reasat Bengali.AI Dhaka, Bangladesh" a0b2df8f72ff672cb0760c5221657a5f48f0ec5d,Searching Image Databases Using Appearance Models,"Searching Image Databases Using Appearance Models A thesis submitted to the University of Manchester for the degree of Doctor of Philosophy in the Faculty of Medicine, Dentistry, Nursing nd Pharmacy Ian M. Scott Division of Imaging Science and Biomedical Engineering" a021b2bc1ec07ca751f6ecec5527a4205f843e1b,Fast LIDAR-based road detection using fully convolutional neural networks,"Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks Luca Caltagirone, Samuel Scheidegger, Lennart Svensson, Mattias Wahde {luca.caltagirone, samsch, lennart.svensson," 43e11904ca961006be79f650025b5d8fbac9913f,Unsupervised Deep Video Hashing with Balanced Rotation,"Unsupervised Deep Video Hashing with Balanced Rotation IJCAI Anonymous Submission 2367" 434fe2cca3321c08ef30a0076864298cf608e0d5,Multiple Human Tracking in High-Density Crowds,"Multiple Human Tracking in High-Density Crowds Irshad Ali1, Matthew N. Dailey 2 Computer Science and Information Management Program, Asian Institute of Technology (AIT), Pathumthani, Thailand" 433a7ee7c30a4d0b7035a1bace3b8ffc9229791b,A Novel Biometric Personal Verification System Based on the Combination of Palmprints and Faces,"INFORMATICA, 2008, Vol. 19, No. 1, 81–100 © 2008 Institute of Mathematics and Informatics, Vilnius A Novel Biometric Personal Verification System Based on the Combination of Palmprints and Faces Slobodan RIBARI ´C, Ivan FRATRI ´C, Kristina KIŠ Faculty of Electrical Engineering and Computing, University of Zagreb Unska 3, 10000 Zagreb, Croatia e-mail: Received: February 2007" 434ad689f9f8bc034fa8489f80f851686b8b449e,Regularized Multi-Concept MIL for weakly-supervised facial behavior categorization.,"A.RUIZ, X.BINEFA, J.VAN DE WEIJER: RMC-MIL FACIAL BEHAVIOR CATEGORIZATION 1 Regularized Multi-Concept MIL for weakly-supervised facial behavior ategorization Adria Ruiz1 Joost Van de Weijer2 Xavier Binefa1 Universitat Pompeu Fabra (DTIC) Barcelona, Spain Centre de Visió per Computador Barcelona, Spain" 43cb50f669a0d492256d11c6cc4128ba0ce79a3e,Per-Pixel Feedback for improving Semantic Segmentation,"Indian Institute of Technology Roorkee Department of Mathematics Per-Pixel Feedback for improving Semantic Segmentation Aditya Ganeshan Submitted in part fulfilment of the requirements for the degree of Integrated Masters of Science in Applied Mathematics, May 2017" 43461e78874aff6b33b8231daf6068ec7ff15098,Automated tracing of myelinated axons and detection of the nodes of Ranvier in serial images of peripheral nerves.,"Received 19 September 2014; accepted 18 April 2015 doi: 10.1111/jmi.12266 Automated tracing of myelinated axons and detection of the nodes of Ranvier in serial images of peripheral nerves A . K R E S H U K∗, R . W A L E C K I∗, U . K O E T H E∗, M . G I E R T H M U E H L E N†, D . P L A C H T A‡, C . G E N O U D §, K . H A A S T E R T - T A L I N I(cid:3) & F . A . H A M P R E C H T∗ Heidelberg Collaboratory for Image Processing (HCI), Interdisciplinary Center for Scientific Computing (IWR), University of Heidelberg, Heidelberg, Germany Department of Neurosurgery, University Medical Center, Freiburg, Germany Department of Microsystems, Engineering, University of Freiburg, Freiburg, Germany §Facility for Advanced Imaging and Microscopy, Friedrich Miescher Institute for Biomedical Research (FMI), Basel, Switzerland (cid:3)Institute of Neuroanatomy, Hannover Medical School, Hannover, Germany and Center for Systems Neurosciences (ZSN), Hannover, Germany Key words. Axon, detection, nerve, Ranvier, segmentation, tracing. Summary The development of realistic neuroanatomical models of pe- ripheral nerves for simulation purposes requires the recon- struction of the morphology of the myelinated fibres in the nerve, including their nodes of Ranvier. Currently, this infor- mation has to be extracted by semimanual procedures, which severely limit the scalability of the experiments. In this contribution, we propose a supervised machine learn-" 430482d92007a3eec7009a2603aa5c1f2e63f661,Synaesthesia : mechanisms and broader traits,"Synaesthesia: mechanisms and broader traits. Agnieszka Barbara Janik Department of Psychology Goldsmiths University of London PhD in Psychology I, Agnieszka Barbara Janik, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been indicated in the thesis." 43c1bf9bd7b18c9603324c328f0f2696278c5327,Tracking Multiple Players using a Single Camera,"Noname manuscript No. (will be inserted by the editor) Tracking Multiple Players using a Single Camera Horesh BenShitrit · Mirko Raca · Fran¸cois Fleuret · Pascal Fua Received: date / Accepted: date" 43f6953804964037ff91a4f45d5b5d2f8edfe4d5,Multi-feature fusion in advanced robotics applications,"Multi-Feature Fusion in Advanced Robotics Applications Zahid Riaz, Christoph Mayer, Michael Beetz, Bernd Radig Institut für Informatik Technische Universität München D-85748 Garching, Germany" 43e3cd896d4dada4114a8961b98ae9f6d6ff9401,Image 2 speech : Automatically generating audio descriptions of images,"Image2speech: Automatically generating audio descriptions of images Mark Hasegawa-Johnson1, Alan Black2, Lucas Ondel3, Odette Scharenborg4, Francesco Ciannella2 . University of Illinois, Urbana, IL USA 2. Carnegie-Mellon University, Pittsburgh, PA USA . Brno University of Technology, Brno, Czech Republic . Centre for Language Studies, Radboud University, Nijmegen, Netherlands" 4353d0dcaf450743e9eddd2aeedee4d01a1be78b,Learning Discriminative LBP-Histogram Bins for Facial Expression Recognition,"Learning Discriminative LBP-Histogram Bins for Facial Expression Recognition Caifeng Shan and Tommaso Gritti Philips Research, High Tech Campus 36, Eindhoven 5656 AE, The Netherlands {caifeng.shan," 4344413b7814b2ba99cc79ead2903f259e98ed4b,Modelling Uncertainty in Representation of Facial Features for Face Recognition,"We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists ,800 16,000 Open access books available International authors and editors Downloads Our authors are among the Countries delivered to TOP 1% 2.2% most cited scientists Contributors from top 500 universities Selection of our books indexed in the Book Citation Index in Web of Science™ Core Collection (BKCI) Interested in publishing with us? Contact Numbers displayed above are based on latest data collected." 43bb20ccfda7b111850743a80a5929792cb031f0,Discrimination of Computer Generated versus Natural Human Faces,"PhD Dissertation International Doctorate School in Information and Communication Technologies DISI - University of Trento Discrimination of Computer Generated versus Natural Human Faces Duc-Tien Dang-Nguyen Advisor: Prof. Giulia Boato Universit`a degli Studi di Trento Co-Advisor: Prof. Francesco G. B. De Natale Universit`a degli Studi di Trento February 2014" 43d8a8737d763f2aba1d1aabbf1d9c74c25308ec,Visual Interaction Including Biometrics Information for a Socially Assistive Robotic Platform,"Visual interaction including biometrics information for socially assistive robotics platform Pierluigi Carcagn`ı, Dario Cazzato, Marco Del Coco, Cosimo Distante, and Marco Leo National Research Council of Italy - Institute of Optics, Arnesano (LE), Italy" 43476cbf2a109f8381b398e7a1ddd794b29a9a16,A Practical Transfer Learning Algorithm for Face Verification,"A Practical Transfer Learning Algorithm for Face Verification Xudong Cao David Wipf Fang Wen Genquan Duan Jian Sun" 43de246e9cc197623e27ab41a69530a8d121c77e,Developmental disruption of amygdala transcriptome and socioemotional behavior in rats exposed to valproic acid prenatally,"Barrett et al. Molecular Autism (2017) 8:42 DOI 10.1186/s13229-017-0160-x R ES EAR CH Developmental disruption of amygdala transcriptome and socioemotional behavior in rats exposed to valproic acid prenatally Catherine E. Barrett 1,2*, Thomas M. Hennessey1,2, Katelyn M. Gordon1,2, Steve J. Ryan1,2, Morgan L. McNair1,2, Kerry J. Ressler3 and Donald G. Rainnie1,2 Open Access" 439da29cf857151f386e6af488b2d60c098c4fd8,Person Authentication Using Color Face Recognition,"Kiran Davakhar et al. Int. Journal of Engineering Research and Applications www.ijera.com Vol. 3, Issue 5, Sep-Oct 2013, pp.178-182 RESEARCH ARTICLE OPEN ACCESS Person Authentication Using Color Face Recognition Kiran Davakhar1, S. B. Mule2, Achala Deshmukh3 (Department of E&TC, Sinhgad COE, Vadgaon, Pune, Pune University, India) (Department of E&TC, Sinhgad COE, Vadgaon, Pune, Pune University, India) (Department of E&TC, Sinhgad COE, Vadgaon, Pune, Pune University, India)" 43d4927f5113c5e376ab05d41e33063a6d06d727,Pedestrian Detection : Exploring Virtual Worlds,"Pedestrian Detection: Exploring Virtual Worlds Javier Mar´ın Computer Vision Center, Universitat Aut`onoma de Barcelona, Spain David Ger´onimo, David V´azquez, Antonio M. L´opez Computer Vision Center and Computer Science Department, Universitat Aut`onoma de Barcelona, Spain Introduction The objective of advanced driver assistance systems (ADAS) is to improve traffic safety by assisting the driver through warnings and by even automatically taking active countermeasures. Two examples of successfully com- mercialised ADAS are lane departure warnings and adaptive cruise control, which make use of either active (e.g., radar) or passive (e.g., cameras) sensors to keep the vehicle on the lane and maintain a safe distance from the preceding vehicle, respectively. One of the most complex safety systems are pedestrian protection systems (PPSs) (Bishop, 2005; Gandhi & Trivedi, 2007; Enzweiler & Gavrila, 2009; Ger´onimo et al., 2010), which are specialised in avoiding vehicle-to-pedestrian collisions. In fact, this kind of accidents results in approximately 50000 injuries and 7000 killed pedestrians every year just in the European Union (UN-ECE, 2007). Similar statistics apply to the United States, while underdeveloped countries are increasing theirs year after year. In the ase of PPSs, the most promising approaches make use of images as main source of information, as can be seen in the large amount of proposals exploiting them (Ger´onimo et al., 2010). Hence, the core of a PPS is a forward facing camera that acquires images and processes them using Computer Vision techniques. In fact, the Computer" 43836d69f00275ba2f3d135f0ca9cf88d1209a87,Effective hyperparameter optimization using Nelder-Mead method in deep learning,"Ozaki et al. IPSJ Transactions on Computer Vision and Applications (2017) 9:20 DOI 10.1186/s41074-017-0030-7 IPSJ Transactions on Computer Vision and Applications RESEARCH PAPER Open Access Effective hyperparameter optimization using Nelder-Mead method in deep learning Yoshihiko Ozaki1,2, Masaki Yano1,2 and Masaki Onishi1,2*" 438b88fe40a6f9b5dcf08e64e27b2719940995e0,Building a classification cascade for visual identification from one example,"Building a Classi(cid:2)cation Cascade for Visual Identi(cid:2)cation from One Example Andras Ferencz Erik G. Learned-Miller Computer Science, U.C. Berkeley Computer Science, UMass Amherst Jitendra Malik Computer Science, U.C. Berkeley" 43ed518e466ff13118385f4e5d039ae4d1c000fb,Classification of Occluded Objects Using Fast Recurrent Processing,"Classification of Occluded Objects using Fast Recurrent Processing Ozgur Yilmaza,∗ Turgut Ozal University, Department of Computer Engineering, Ankara Turkey" 43f7aeea3ff5bbcbff6cce387f8e9b6c588e4f66,Systematic Review and Classification on Video Surveillance Systems,"I.J. Information Technology and Computer Science, 2013, 07, 87-102 Published Online June 2013 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijitcs.2013.07.11 Systematic Review and Classification on Video Surveillance Systems Fereshteh Falah Chamasemani, Lilly Suriani Affendey Faculty of Computer Science and Information Technology, University Putra Malaysia, Malaysia E-mail: systems surveillance" 43167658228d59b81d48fce14bba4ae616b866ec,Face Recognition Using Multi-Classifier,"Applied Mathematical Sciences, Vol. 6, 2012, no. 45, 2235 - 2244 Face Recognition Using Multi-Classifier Mohammad Said El-Bashir Faculty of Computer Science and Information Technology Al-al Bayt University - Jordan" 43fbe350681185ec9a18991dbcb19d694ce4f245,The Perspective Face Shape Ambiguity,"The Perspective Face Shape Ambiguity William A. P. Smith" 43c76cf17767a43a345cd1a8d7c08d18578b53ec,Boosting Color Feature Selection for Color Face Recognition,"Accepted Manuscript for Publication in IEEE Transaction on Image Processing Boosting Color Feature Selection for Color Face Recognition Jae Young Choi, Student Member, IEEE, Yong Man Ro, Senior Member, IEEE, and Konstantinos N. Plataniotis, Senior Member, IEEE" 43fe9006b90137d6ce85a539685ce66c13f0e38e,A review of image-based automatic facial landmark identification techniques,"Johnston and Chazal EURASIP Journal on Image and Video Processing (2018) 2018:86 https://doi.org/10.1186/s13640-018-0324-4 EURASIP Journal on Image nd Video Processing REVIEW Open Access A review of image-based automatic facial landmark identification techniques Benjamin Johnston1,2* nd Philip de Chazal1" 43cff54bb47d0e96cda86671b2fdd9a0d09f4060,Unsupervised Learning of Head Pose through Spike-Timing Dependent Plasticity,"Unsupervised Learning of Head Pose through Spike-Timing Dependent Plasticity Ulrich Weidenbacher and Heiko Neumann University of Ulm, Institute of Neural Information Processing, 89069 Ulm" 430e0b4577b7b2a82461241bb509b6830139b924,Decoding hazardous Events in driving Videos,"DECODING HAZARDOUS EVENTS IN DRIVING VIDEOS H. Kolkhorst1, W. Burgard1, M. Tangermann1 Cluster of Excellence BrainLinks-BrainTools Department of Computer Science University of Freiburg, Freiburg, Germany E-mail:" 4350bb360797a4ade4faf616ed2ac8e27315968e,What Is the Range of Surface Reconstructions from a Gradient Field?,"MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Edge Suppression by Gradient Field Transformation using Cross-Projection Tensors Amit Agrawal, Ramesh Raskar, Rama Chellappa TR2006-058 June 2006" 43b8b5eeb4869372ef896ca2d1e6010552cdc4d4,Large-scale Supervised Hierarchical Feature Learning for Face Recognition,"Large-scale Supervised Hierarchical Feature Learning for Face Recognition Jianguo Li, Yurong Chen Intel Labs China" 43e63603a5794c4e289d1f41d7079ed9620a355e,Invisible Mask: Practical Attacks on Face Recognition with Infrared,"Invisible Mask: Practical Attacks on Face Recognition with Infrared Zhe Zhou1, Di Tang2, Xiaofeng Wang3, Weili Han1, Xiangyu Liu4, Kehuan Zhang2 Fudan Univiersity, 2CUHK, 3IUB, 4Alibaba Inc." 43a2c871450ba4d8888e8692aa98cb10e861ea71,Learning Generative ConvNet with Continuous Latent Factors by Alternating Back-Propagation,"Alternating Back-Propagation for Generator Network Tian Han †, Yang Lu †, Song-Chun Zhu, Ying Nian Wu Department of Statistics, University of California, Los Angeles, USA" 431fc5903ab4853820eac6614073c5b7aec0ac31,Semantic-visual concept relatedness and co-occurrences for image retrieval,"978-1-4673-2533-2/12/$26.00 ©2012 IEEE ICIP 2012" 439ec47725ae4a3660e509d32828599a495559bf,Facial Expressions Tracking and Recognition : Database Protocols for Systems Validation and Evaluation,"Facial Expressions Tracking and Recognition: Database Protocols for Systems Validation nd Evaluation" 432a78fce47e2cc38fd742ab10cf80dec82ad49a,Boost K-Means,"Boost K-Means Wan-Lei Zhao, Cheng-Hao Deng, and Chong-Wah Ngo, Senior Memeber, IEEE" 4332314ac4ab56153f68a9e55e92b3659e93a5b4,Learning Collective Crowd Behaviors with Dynamic Pedestrian-Agents,"Int J Comput Vis DOI 10.1007/s11263-014-0735-3 Learning Collective Crowd Behaviors with Dynamic Pedestrian-Agents Bolei Zhou · Xiaoou Tang · Xiaogang Wang Received: 9 September 2013 / Accepted: 24 May 2014 © Springer Science+Business Media New York 2014" 434bf475addfb580707208618f99c8be0c55cf95,DeXpression: Deep Convolutional Neural Network for Expression Recognition,"UNDER CONSIDERATION FOR PUBLICATION IN PATTERN RECOGNITION LETTERS DeXpression: Deep Convolutional Neural Network for Expression Recognition Peter Burkert∗‡, Felix Trier∗‡, Muhammad Zeshan Afzal†‡, Andreas Dengel†‡ and Marcus Liwicki‡ German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany University of Kaiserslautern, Gottlieb-Daimler-Str., Kaiserslautern 67663, Germany" 439ac8edfa1e7cbc65474cab544a5b8c4c65d5db,Face authentication with undercontrolled pose and illumination,"SIViP (2011) 5:401–413 DOI 10.1007/s11760-011-0244-6 ORIGINAL PAPER Face authentication with undercontrolled pose and illumination Maria De Marsico · Michele Nappi · Daniel Riccio Received: 15 September 2010 / Revised: 14 December 2010 / Accepted: 17 February 2011 / Published online: 7 August 2011 © Springer-Verlag London Limited 2011" 434627a03d4433b0df03058724524c3ac1c07478,Online Multi-Target Tracking With Unified Handling of Complex Scenarios,"IEEE TRANSANCTIONS ON IMAGE PROCESSING, VOL. XX, NO. XX, NOVEMBER 2014 Online Multi-Target Tracking with Unified Handling of Complex Scenarios Huaizu Jiang, Jinjun Wang, Yihong Gong, Senior Member, IEEE Na Rong, Zhenhua Chai, and Nanning Zheng, Fellow, IEEE" 434c2c53af7b3cb3c0a47583a372fa3dc8143951,DeeSIL: Deep-Shallow Incremental Learning,"DeeSIL: Deep-Shallow Incremental Learning Eden Belouadah, Adrian Popescu CEA, LIST, Vision and Content Engineering Lab, F-91191 Gif-sur-Yvette, France" 432be99dde7d93001044048501c72c70e4ea2927,People and Mobile Robot Classification Through Spatio-Temporal Analysis of Optical Flow,"June 3, 2015 3:29 WSPC/INSTRUCTION FILE People and mobile robot classification through spatio-temporal analysis of optical flow Plinio Moreno and Dario Figueira and Alexandre Bernardino and Jos´e Santos-Victor Institute for Systems and Robotics (ISR/IST) LARSyS, Instituto Superior T´ecnico Universidade de Lisboa {plinio, dfigueira, alex, Lisboa, Portugal The goal of this work is to distinguish between humans and robots in a mixed human- robot environment. We analyze the spatio-temporal patterns of optical flow-based fea- tures along several frames. We consider the Histogram of Optical Flow (HOF) and the Motion Boundary Histogram (MBH) features, which have shown good results on people detection. The spatio-temporal patterns are composed by groups of feature components that have similar values on previous frames. The groups of features are fed into the FuzzyBoost algorithm, which at each round selects the spatio-temporal pattern (i.e. feature set) having the lowest classification error. The search for patterns is guided by grouping feature dimensions, considering three algorithms: (a) similarity of weights from dimensionality reduction matrices, (b) Boost Feature Subset Selection (BFSS) and (c)" b008d973ee93fd3b13d1148fb7533dbdbc8374d6,New Representations for Analyzing Motion and Applications,"New Representations for Analyzing Motion and Applications Ce Liu Submitted to the Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the degree of Doctor of Philosophy Electrical Engineering and Computer Science t the Massachusetts Institute of Technology June 2009 (cid:13) 2009 Massachusetts Institute of Technology All Rights Reserved. Signature of Author: Certified by: Accepted by: Department of Electrical Engineering and Computer Science May 1, 2009 William T. Freeman, Professor of EECS Thesis Supervisor Terry P. Orlando, Professor of Electrical Engineering Chair, Department Committee on Graduate Students" b08203fca1af7b95fda8aa3d29dcacd182375385,Object and Text-guided Semantics for CNN-based Activity Recognition,"OBJECT AND TEXT-GUIDED SEMANTICS FOR CNN-BASED ACTIVITY RECOGNITION (cid:63)Sungmin Eum †§, (cid:63)Christopher Reale †, Heesung Kwon†, Claire Bonial †, Clare Voss† U.S. Army Research Laboratory, Adelphi, MD, USA §Booz Allen Hamilton Inc., McLean, VA, USA" b0c3bc3e3ca143444f5193735f2aad89d1776276,Training Generative Reversible Networks,"Training Generative Reversible Networks Robin Tibor Schirrmeister 1 2 Patryk Chrab ˛aszcz 2 Frank Hutter 2 Tonio Ball 1" b0554290e1c1d19ee5378485fadd1ff99c31bf2d,VANETs Meet Autonomous Vehicles: A Multimodal 3D Environment Learning Approach,"VANETs Meet Autonomous Vehicles: A Multimodal 3D Environment Learning Approach Yassine Maalej, Sameh Sorour, Ahmed Abdel-Rahim and Mohsen Guizani University of Idaho, Moscow, ID, USA" b05ac3b2286c30fcab385f682b3519a823857112,UvA-DARE ( Digital Academic Repository ) Spatial frequency information modulates response inhibition and decision-making processes,"UvA-DARE (Digital Academic Repository) Spatial frequency information modulates response inhibition and decision-making processes Jahfari, S.; Ridderinkhof, K.R.; Scholte, H.S. Published in: PLoS One 0.1371/journal.pone.0076467 Link to publication Citation for published version (APA): Jahfari, S., Ridderinkhof, K. R., & Scholte, H. S. (2013). Spatial frequency information modulates response inhibition and decision-making processes. PLoS One, 8(10), e76467. [e76467]. DOI: 0.1371/journal.pone.0076467 General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulations If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible." b069e125442995787119db3bfa71dff5d965f3aa,MCYT baseline corpus : a bimodal biometric database,"BIOMETRICS ON THE INTERNET MCYT baseline corpus: a bimodal biometric database J. Ortega-Garcia, J. Fierrez-Aguilar, D. Simon, J. Gonzalez, M. Faundez-Zanuy, V. Espinosa, A. Satue, I. Hernaez, J.-J. Igarza, C. Vivaracho, D. Escudero and Q.-I. Moro" b0d6e204c36f029300787f6334cb727325f8983a,Neural networks related to dysfunctional face processing in autism spectrum disorder,"Brain Struct Funct DOI 10.1007/s00429-014-0791-z O R I G I N A L A R T I C L E Neural networks related to dysfunctional face processing in autism spectrum disorder Thomas Nickl-Jockschat • Claudia Rottschy • Johanna Thommes • Frank Schneider • Angela R. Laird • Peter T. Fox • Simon B. Eickhoff Received: 6 September 2013 / Accepted: 28 April 2014 Ó Springer-Verlag Berlin Heidelberg 2014" b028e74cbbba184e2ae01f10290961ddd1d09b9b,Audio-Visual Speech Recognition for Slavonic Languages ( Czech and Russian ),"Audio-Visual Speech Recognition for Slavonic Languages (Czech and Russian) Petr Císař1, Jan Zelinka1, Miloš Železný1, Alexey Karpov2, Andrey Ronzhin2 Department of Cybernetics, University of West Bohemia in Pilsen (UWB), Czech Republic Speech Informatics Group, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), Russian Federation" b00796447d670f9413e831ffb4ed548a380816a2,Servoing across object instances: Visual servoing for object category,"Servoing Across Object Instances: Visual Servoing for Object Category Harit Pandya1, K Madhava Krishna1 and C. V. Jawahar1" b00d87ca1398fe8df674292740f87dfa1fdd5802,Neuro-memristive Circuits for Edge Computing: A review,"Neuro-memristive Circuits for Edge Computing: A Review Olga Krestinskaya, Student Member, IEEE, Alex James, Senior Member, IEEE and Leon O. Chua, Fellow, IEEE" b0c1615ebcad516b5a26d45be58068673e2ff217,How Image Degradations Affect Deep CNN-Based Face Recognition?,"How Image Degradations Affect Deep CNN-based Face Recognition? S¸amil Karahan1 Merve Kılınc¸ Yıldırım1 Kadir Kırtac¸1 Ferhat S¸ ¨ukr¨u Rende1 G¨ultekin B¨ut¨un1Hazım Kemal Ekenel2" b0e7c177084be76fb73df3c4bcf1846676a2d615,Joint action recognition and pose estimation from video,"Joint Action Recognition and Pose Estimation From Video Bruce Xiaohan Nie, Caiming Xiong and Song-Chun Zhu Center for Vision, Cognition, Learning and Art University of California, Los Angeles, USA" b0c379f740292ad2cad2c990a445f69167e18894,Knowledge distillation using unlabeled mismatched images,"Workshop track - ICLR 2017 KNOWLEDGE DISTILLATION USING UNLABELED MIS- MATCHED IMAGES Mandar Kulkarni(*), Kalpesh Patil(**), Shirish Karande(*) TCS Innovation Labs, Pune, India (*), IIT Bombay, Mumbai, India(**)" b007ba011ba7876ca8fdb10a44bb6b2ea4dadbc6,"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation Nikolaus Mayer∗1, Eddy Ilg∗1, Philip H¨ausser∗2, Philipp Fischer∗1† University of Freiburg Technical University of Munich Alexey Dosovitskiy, Thomas Brox University of Freiburg Daniel Cremers Technical University of Munich" b0d607d5e9e79540c9f2673f2224b2d51be3393c,Kernel Truncated Regression Representation for Robust Subspace Clustering,"Kernel Truncated Regression Representation for Robust Subspace Clustering Liangli Zhen, Dezhong Peng, Xin Yao" b07546f26a99b61c5045e313bc024b0fe7de590a,Bilinear CNNs for Fine-grained Visual Recognition,"Bilinear CNNs for Fine-grained Visual Recognition Tsung-Yu Lin Aruni RoyChowdhury Subhransu Maji" b03d5ed5b3f253703fa37d6445fab0e7cdf38ba1,Separate-Group Covariance Estimation With Insufficient Data for Object Recognition,"Separate-Group Covariance Estimation With Insufficient Data for Object Recognition Carlos Eduardo Thomaz1, Raul Queiroz Feitosa2, Álvaro Veiga3 ,2,3Catholic University of Rio de Janeiro Department of Electrical Engineering Department of Computer Engineering University of Rio de Janeiro r. Marquês de São Vicente 225,22453-900, Rio de r. São Francisco Xavier, 524, 20559-900, Rio de Janeiro, Brazil Janeiro, Brazil" b0c651f23516055583060e2197756e1390455de5,Multimodal verification of identity for a realistic access control application,"Multimodal Verification of Identity for a Realistic Access Control Application Thesis submitted in partial fulfilment of the requirements for the degree Doctor Ingeneriae Mechanical Engineering Rand Afrikaans University Supervisor: Professor A.L. Nel Nele Denys t the May 2004" b0070d14db2f0e9cbd48b96af3dde66b0461c555,Humans Differ: So Should Models - Systematic Differences Call for Per-subject Modeling,"HUMANS DIFFER: SO SHOULD MODELS Systematic Differences Call for Per-subject Modeling Wolfgang Heidl, Stefan Thumfart and Christian Eitzinger Profactor GmbH, Im Stadtgut A2, 4407 Steyr-Gleink, Austria Keywords: Machine learning, Human diversity." b04d4b1e8b510180726f49a66dbaaf23c9ef64a0,Introspective Generative Modeling: Decide Discriminatively.,"Introspective Generative Modeling: Decide Discriminatively Justin Lazarow ∗ Dept. of CSE Long Jin∗ Dept. of CSE Zhuowen Tu Dept. of CogSci" b0158b26f01d5fa18aac51ece055cad9a12f6d87,Memory-based Gait Recognition,"Pages 82.1-82.12 DOI: https://dx.doi.org/10.5244/C.30.82" b09b693708f412823053508578df289b8403100a,Two-Stream SR-CNNs for Action Recognition in Videos,"WANG et al.: TWO-STREAM SR-CNNS FOR ACTION RECOGNITION IN VIDEOS Two-Stream SR-CNNs for Action Recognition in Videos Yifan Wang1 Jie Song1 Limin Wang2 Luc Van Gool2 Otmar Hilliges1 Advanced Interactive Technologies Lab ETH Zurich Zurich, Switzerland Computer Vision Lab ETH Zurich Zurich, Switzerland" b0623c1d8493d273d704ba1d0413db0de579ae77,Attributes-Based Re-identification,"Attributes-based Re-Identification Ryan Layne, Timothy M. Hospedales and Shaogang Gong" b0a376888a33defd6fcfe396a11e6ea6d4f99f0e,Soft Measure of Visual Token Occurrences for Object Categorization,"Soft Measure of Visual Token Occurrences for Object Categorization Yanjie Wang, Xiabi Liu(cid:2), and Yunde Jia Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology Tel.: +86-10-68913447, Fax: +86-10-86343158" b0de0892d2092c8c70aa22500fed31aa7eb4dd3f,A Robust and Efficient Video Representation for Action Recognition,"(will be inserted by the editor) A robust and efficient video representation for action recognition Heng Wang · Dan Oneata · Jakob Verbeek · Cordelia Schmid Received: date / Accepted: date" b07582d1a59a9c6f029d0d8328414c7bef64dca0,Employing Fusion of Learned and Handcrafted Features for Unconstrained Ear Recognition,"Employing Fusion of Learned and Handcrafted Features for Unconstrained Ear Recognition Maur´ıcio Pamplona Segundo∗† Earnest E. Hansley∗ Sudeep Sarkar∗‡ October 24, 2017" b0fafe26b03243a22e12b021266872afdb96572c,Factors of Transferability for a Generic ConvNet Representation,"Factors of Transferability for a Generic ConvNet Representation Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson {azizpour, razavian, sullivan, atsuto, Computer Vision and Active Perception (CVAP), Royal Institute of Technology (KTH), Stockholm, SE-10044 Sweden Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units ctivation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target). Recent studies have shown this form of representation transfer to be suitable for a wide range of target visual recognition tasks. This paper introduces and investigates several factors affecting the transferability of such representations. It includes parameters for training of the source ConvNet such as its architecture, distribution of the training data, etc. and also the parameters of feature extraction such as layer of the trained ConvNet, dimensionality reduction, etc. Then, y optimizing these factors, we show that significant improvements can be achieved on various (17) visual recognition tasks. We further show that these visual recognition tasks can be categorically ordered based on their distance from the source task such that correlation between the performance of tasks and their distance from the source task w.r.t. the proposed factors is observed. Index Terms—Convolutional Neural Networks, Transfer Learning, Representation Learning, Deep Learning, Visual Recognition I. INTRODUCTION C ONVOLUTIONAL NETWORKS (ConvNets) trace back to the early works on digit and character recognition [11], [23]. Prior to 2012, though, in computer vision field, neural networks were more renowned for their propensity to"