From 2fd066e9c3cb0e45d7a055d090084f941a40fadb Mon Sep 17 00:00:00 2001 From: Jules Laplace Date: Thu, 8 Nov 2018 19:25:04 +0100 Subject: taking another look at the papers --- reports/first_pages.html | 11653 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 10922 insertions(+), 731 deletions(-) (limited to 'reports/first_pages.html') diff --git a/reports/first_pages.html b/reports/first_pages.html index 9280eca9..1fa50094 100644 --- a/reports/first_pages.html +++ b/reports/first_pages.html @@ -38,19 +38,73 @@
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 -('3173667', 'Mert Pilanci', 'mert pilanci')612075999e82596f3b42a80e6996712cc52880a3CNNs with Cross-Correlation Matching for Face Recognition in Video +('3173667', 'Mert Pilanci', 'mert pilanci')61f04606528ecf4a42b49e8ac2add2e9f92c0defDeep Deformation Network for Object Landmark +
Localization +
NEC Laboratories America, Department of Media Analytics +('39960064', 'Xiang Yu', 'xiang yu')
('46468682', 'Feng Zhou', 'feng zhou'){xiangyu,manu}@nec-labs.com, zhfe99@gmail.com +612075999e82596f3b42a80e6996712cc52880a3CNNs with Cross-Correlation Matching for Face Recognition in Video
Surveillance Using a Single Training Sample Per Person
University of Texas at Arlington, TX, USA
2École de technologie supérieure, Université du Québec, Montreal, Canada ('3046171', 'Mostafa Parchami', 'mostafa parchami')
('2805645', 'Saman Bashbaghi', 'saman bashbaghi')
('1697195', 'Eric Granger', 'eric granger')mostafa.parchami@mavs.uta.edu, bashbaghi@livia.etsmtl.ca and eric.granger@etsmtl.ca +61efeb64e8431cfbafa4b02eb76bf0c58e61a0faMerging Datasets Through Deep learning +
IBM Research +
Yeshiva University
IBM Research +('35970154', 'Kavitha Srinivas', 'kavitha srinivas')
('51428397', 'Abraham Gale', 'abraham gale')
('2828094', 'Julian Dolby', 'julian dolby')61e9e180d3d1d8b09f1cc59bdd9f98c497707effSemi-supervised learning of +
facial attributes in video +
1INRIA, WILLOW, Laboratoire d’Informatique de l’Ecole Normale Sup´erieure, +
ENS/INRIA/CNRS UMR 8548 +
University of Oxford('1877079', 'Neva Cherniavsky', 'neva cherniavsky')
('1785596', 'Ivan Laptev', 'ivan laptev')
('1782755', 'Josef Sivic', 'josef sivic')
('1688869', 'Andrew Zisserman', 'andrew zisserman')6193c833ad25ac27abbde1a31c1cabe56ce1515bTrojaning Attack on Neural Networks +
Purdue University, 2Nanjing University('3347155', 'Yingqi Liu', 'yingqi liu')
('2026855', 'Shiqing Ma', 'shiqing ma')
('3216258', 'Yousra Aafer', 'yousra aafer')
('2547748', 'Wen-Chuan Lee', 'wen-chuan lee')
('3293342', 'Juan Zhai', 'juan zhai')
('3155328', 'Weihang Wang', 'weihang wang')
('1771551', 'Xiangyu Zhang', 'xiangyu zhang')liu1751@purdue.edu, ma229@purdue.edu, yaafer@purdue.edu, lee1938@purdue.edu, zhaijuan@nju.edu.cn, +
wang1315@cs.purdue.edu, xyzhang@cs.purdue.edu 614a7c42aae8946c7ad4c36b53290860f62564411
Joint Face Detection and Alignment using
Multi-task Cascaded Convolutional Networks -('3393556', 'Kaipeng Zhang', 'kaipeng zhang')
('3152448', 'Zhanpeng Zhang', 'zhanpeng zhang')
('32787758', 'Zhifeng Li', 'zhifeng li')
('33427555', 'Yu Qiao', 'yu qiao')0d746111135c2e7f91443869003d05cde3044bebPARTIAL FACE DETECTION FOR CONTINUOUS AUTHENTICATION +('3393556', 'Kaipeng Zhang', 'kaipeng zhang')
('3152448', 'Zhanpeng Zhang', 'zhanpeng zhang')
('32787758', 'Zhifeng Li', 'zhifeng li')
('33427555', 'Yu Qiao', 'yu qiao')614079f1a0d0938f9c30a1585f617fa278816d53Automatic Detection of ADHD and ASD from Expressive Behaviour in +
RGBD Data +
School of Computer Science, The University of Nottingham
2Nottingham City Asperger Service & ADHD Clinic +
Institute of Mental Health, The University of Nottingham('2736086', 'Shashank Jaiswal', 'shashank jaiswal')
('1795528', 'Michel F. Valstar', 'michel f. valstar')
('38690723', 'Alinda Gillott', 'alinda gillott')
('2491166', 'David Daley', 'david daley')0d746111135c2e7f91443869003d05cde3044bebPARTIAL FACE DETECTION FOR CONTINUOUS AUTHENTICATION
(cid:63)Department of Electrical and Computer Engineering and the Center for Automation Research,
Rutgers, The State University of New Jersey, 723 CoRE, 94 Brett Rd, Piscataway, NJ
UMIACS, University of Maryland, College Park, MD
§Google Inc., 1600 Amphitheatre Parkway, Mountain View, CA 94043 ('3152615', 'Upal Mahbub', 'upal mahbub')
('1741177', 'Vishal M. Patel', 'vishal m. patel')
('2406413', 'Brandon Barbello', 'brandon barbello')
('9215658', 'Rama Chellappa', 'rama chellappa')umahbub@umiacs.umd.edu, vishal.m.patel@rutgers.edu,
dchandra@google.com, bbarbello@google.com, rama@umiacs.umd.edu -0d88ab0250748410a1bc990b67ab2efb370ade5dAuthor(s) : +0da75b0d341c8f945fae1da6c77b6ec345f47f2a121 +
The Effect of Computer-Generated Descriptions on Photo- +
Sharing Experiences of People With Visual Impairments +
YUHANG ZHAO, Information Science, Cornell Tech, Cornell University
SHAOMEI WU, Facebook Inc. +
LINDSAY REYNOLDS, Facebook Inc. +
SHIRI AZENKOT, Information Science, Cornell Tech, Cornell University
Like sighted people, visually impaired people want to share photographs on social networking services, but +
find it difficult to identify and select photos from their albums. We aimed to address this problem by +
incorporating state-of-the-art computer-generated descriptions into Facebook’s photo-sharing feature. We +
interviewed 12 visually impaired participants to understand their photo-sharing experiences and designed +
a photo description feature for the Facebook mobile application. We evaluated this feature with six +
participants in a seven-day diary study. We found that participants used the descriptions to recall and +
organize their photos, but they hesitated to upload photos without a sighted person’s input. In addition to +
basic information about photo content, participants wanted to know more details about salient objects and +
people, and whether the photos reflected their personal aesthetic. We discuss these findings from the lens +
of self-disclosure and self-presentation theories and propose new computer vision research directions that +
will better support visual content sharing by visually impaired people. +
CCS Concepts: • Information interfaces and presentations → Multimedia and information systems; • +
Computer and society → Social issues +
impairments; computer-generated descriptions; SNSs; photo sharing; self-disclosure; self- +
KEYWORDS +
Visual +
presentation +
ACM Reference format: +
2017. The Effect of Computer-Generated Descriptions On Photo-Sharing Experiences of People With Visual +
Impairments. Proc. ACM Hum.-Comput. Interact. 1, 1. 121 (January 2017), 24 pages. +
DOI: 10.1145/3134756 +
1 INTRODUCTION +
Sharing memories and experiences via photos is a common way to engage with others on social +
networking services (SNSs) [39,46,51]. For instance, Facebook users uploaded more than 350 +
million photos a day [24] and Twitter, which initially supported only text in tweets, now has +
more than 28.4% of tweets containing images [39]. Visually impaired people (both blind and low +
vision) have a strong presence on SNS and are interested in sharing photos [50]. They take +
photos for the same reasons that sighted people do: sharing daily moments with their sighted +
+
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 of this work owned by others than ACM must be honored. +0d88ab0250748410a1bc990b67ab2efb370ade5dAuthor(s) :
ERROR HANDLING IN MULTIMODAL BIOMETRIC SYSTEMS USING
RELIABILITY MEASURES (ThuPmOR6)
(EPFL, Switzerland) @@ -200,7 +254,13 @@
jyoti.joshi@uwaterloo.ca
jhoey@cs.uwaterloo.ca
tom.gedeon@anu.edu.au -0d735e7552af0d1dcd856a8740401916e54b7eee0d06b3a4132d8a2effed115a89617e0a702c957a0d2dd4fc016cb6a517d8fb43a7cc3ff62964832e0d1d9a603b08649264f6e3b6d5a66bf1e1ac39d2University of Nebraska - Lincoln
US Army Research +0d735e7552af0d1dcd856a8740401916e54b7eee0d06b3a4132d8a2effed115a89617e0a702c957a0d2dd4fc016cb6a517d8fb43a7cc3ff62964832e0d33b6c8b4d1a3cb6d669b4b8c11c2a54c203d1aDetection and Tracking of Faces in Videos: A Review +
© 2016 IJEDR | Volume 4, Issue 2 | ISSN: 2321-9939 +
of Related Work +
1Student, 2Assistant Professor +
1, 2Dept. of Electronics & Comm., S S I E T, Punjab, India +
________________________________________________________________________________________________________ +('48816689', 'Seema Saini', 'seema saini')0d1d9a603b08649264f6e3b6d5a66bf1e1ac39d2University of Nebraska - Lincoln
US Army Research
2015
U.S. Department of Defense
Effects of emotional expressions on persuasion @@ -212,6 +272,27 @@
University of Southern California, wangyuqiong@ymail.com
This Article is brought to you for free and open access by the U.S. Department of Defense at DigitalCommons@University of Nebraska - Lincoln. It has
been accepted for inclusion in US Army Research by an authorized administrator of DigitalCommons@University of Nebraska - Lincoln. +0da4c3d898ca2fff9e549d18f513f4898e960acaWang, Y., Thomas, J., Weissgerber, S. C., Kazemini, S., Ul-Haq, I., & +
Quadflieg, S. (2015). The Headscarf Effect Revisited: Further Evidence for a +
336. 10.1068/p7940 +
Peer reviewed version +
Link to published version (if available): +
10.1068/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 +
• Your contact details +
Bibliographic details for the item, including a URL
• An outline of the nature of the complaint +
On receipt of your message the Open Access Team will immediately investigate your claim, make an +
initial judgement of the validity of the claim and, where appropriate, withdraw the item in question +
from public view. +
open-access@bristol.ac.uk and include the following information in your message: 951368a1a8b3c5cd286726050b8bdf75a80f7c37A Family of Online Boosting Algorithms
University of California, San Diego
University of California, Merced
University of California, San Diego('2490700', 'Boris Babenko', 'boris babenko')
('37144787', 'Ming-Hsuan Yang', 'ming-hsuan yang')
('1769406', 'Serge Belongie', 'serge belongie')bbabenko@cs.ucsd.edu
mhyang@ucmerced.edu @@ -238,7 +319,13 @@
http://www.ieee.org/
Griffith Research Online
https://research-repository.griffith.edu.au -951f21a5671a4cd14b1ef1728dfe305bda72366fInternational Journal of Science and Research (IJSR) +959bcb16afdf303c34a8bfc11e9fcc9d40d76b1cTemporal Coherency based Criteria for Predicting +
Video Frames using Deep Multi-stage Generative +
Adversarial Networks +
Visualization and Perception Laboratory +
Department of Computer Science and Engineering +
Indian Institute of Technology Madras, Chennai, India('29901316', 'Prateep Bhattacharjee', 'prateep bhattacharjee')
('1680398', 'Sukhendu Das', 'sukhendu das')1prateepb@cse.iitm.ac.in, 2sdas@iitm.ac.in +951f21a5671a4cd14b1ef1728dfe305bda72366fInternational Journal of Science and Research (IJSR)
ISSN (Online): 2319-7064
Impact Factor (2012): 3.358
Use of ℓ2/3-norm Sparse Representation for Facial @@ -278,19 +365,31 @@
873
A Novel Incremental Principal Component Analysis
and Its Application for Face Recognition -('1776124', 'Haitao Zhao', 'haitao zhao')
('1768574', 'Pong Chi Yuen', 'pong chi yuen')958c599a6f01678513849637bec5dc5dba592394Noname manuscript No. +('1776124', 'Haitao Zhao', 'haitao zhao')
('1768574', 'Pong Chi Yuen', 'pong chi yuen')95ea564bd983129ddb5535a6741e72bb1162c779Multi-Task Learning by Deep Collaboration and +
Application in Facial Landmark Detection +
Laval University, Qu bec, Canada('2758280', 'Ludovic Trottier', 'ludovic trottier')
('2310695', 'Philippe Giguère', 'philippe giguère')
('1700926', 'Brahim Chaib-draa', 'brahim chaib-draa')ludovic.trottier.1@ulaval.ca +
{philippe.giguere,brahim.chaib-draa}@ift.ulaval.ca +958c599a6f01678513849637bec5dc5dba592394Noname manuscript No.
(will be inserted by the editor)
Generalized Zero-Shot Learning for Action
Recognition with Web-Scale Video Data
Received: date / Accepted: date -('2473509', 'Kun Liu', 'kun liu')
('8984539', 'Wenbing Huang', 'wenbing huang')59be98f54bb4ed7a2984dc6a3c84b52d1caf44ebA Deep-Learning Approach to Facial Expression Recognition +('2473509', 'Kun Liu', 'kun liu')
('8984539', 'Wenbing Huang', 'wenbing huang')950171acb24bb24a871ba0d02d580c09829de372Speeding up 2D-Warping for Pose-Invariant Face Recognition +
Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany('1804963', 'Harald Hanselmann', 'harald hanselmann')
('1685956', 'Hermann Ney', 'hermann ney')surname@cs.rwth-aachen.de +59be98f54bb4ed7a2984dc6a3c84b52d1caf44ebA Deep-Learning Approach to Facial Expression Recognition
with Candid Images
CUNY City College
Alibaba. Inc
IBM China Research Lab
CUNY Graduate Center and City College('40617554', 'Wei Li', 'wei li')
('1713016', 'Min Li', 'min li')
('1703625', 'Zhong Su', 'zhong su')
('4697712', 'Zhigang Zhu', 'zhigang zhu')lwei000@citymail.cuny.edu
mushi.lm@alibaba.inc
suzhong@cn.ibm.com
zhu@cs.ccny.cuny.edu -591a737c158be7b131121d87d9d81b471c400dbaAffect Valence Inference From Facial Action Unit Spectrograms +59fc69b3bc4759eef1347161e1248e886702f8f7Final Report of Final Year Project +
HKU-Face: A Large Scale Dataset for +
Deep Face Recognition +
3035141841 +
COMP4801 Final Year Project +
Project Code: 17007 +('40456402', 'Haoyu Li', 'haoyu li')591a737c158be7b131121d87d9d81b471c400dbaAffect Valence Inference From Facial Action Unit Spectrograms
MIT Media Lab
MA 02139, USA
MIT Media Lab @@ -305,7 +404,11 @@
picard@mit.edu 59bfeac0635d3f1f4891106ae0262b81841b06e4Face Verification Using the LARK Face
Representation -('3326805', 'Hae Jong Seo', 'hae jong seo')
('1718280', 'Peyman Milanfar', 'peyman milanfar')590628a9584e500f3e7f349ba7e2046c8c273fcf593234ba1d2e16a887207bf65d6b55bbc7ea2247Combining Language Sources and Robust +('3326805', 'Hae Jong Seo', 'hae jong seo')
('1718280', 'Peyman Milanfar', 'peyman milanfar')59efb1ac77c59abc8613830787d767100387c680DIF : Dataset of Intoxicated Faces for Drunk Person +
Identification +
Indian Institute of Technology Ropar
Indian Institute of Technology Ropar('46241736', 'Devendra Pratap Yadav', 'devendra pratap yadav')
('1735697', 'Abhinav Dhall', 'abhinav dhall')2014csb1010@iitrpr.ac.in +
abhinav@iitrpr.ac.in +590628a9584e500f3e7f349ba7e2046c8c273fcf593234ba1d2e16a887207bf65d6b55bbc7ea2247Combining Language Sources and Robust
Semantic Relatedness for Attribute-Based
Knowledge Transfer
1 Department of Computer Science, TU Darmstadt @@ -315,7 +418,29 @@
Cross-Pose Recognition ('24020847', 'Hung-Cheng Shie', 'hung-cheng shie')
('9640380', 'Cheng-Hua Hsieh', 'cheng-hua hsieh')59e2037f5079794cb9128c7f0900a568ced14c2aClothing and People - A Social Signal Processing Perspective
Faculty of Mathematics and Computer Science, University of Barcelona, Barcelona, Spain
2 Computer Vision Center, Barcelona, Spain -
University of Verona, Verona, Italy('2084534', 'Maedeh Aghaei', 'maedeh aghaei')
('10724083', 'Federico Parezzan', 'federico parezzan')
('2837527', 'Mariella Dimiccoli', 'mariella dimiccoli')
('1724155', 'Petia Radeva', 'petia radeva')
('1723008', 'Marco Cristani', 'marco cristani')59c9d416f7b3d33141cc94567925a447d0662d80Universität des Saarlandes +
University of Verona, Verona, Italy('2084534', 'Maedeh Aghaei', 'maedeh aghaei')
('10724083', 'Federico Parezzan', 'federico parezzan')
('2837527', 'Mariella Dimiccoli', 'mariella dimiccoli')
('1724155', 'Petia Radeva', 'petia radeva')
('1723008', 'Marco Cristani', 'marco cristani')59dac8b460a89e03fa616749a08e6149708dcc3aA Convergent Solution to Matrix Bidirectional Projection Based Feature +
Extraction with Application to Face Recognition ∗ +
School of Computer, National University of Defense Technology
No 137, Yanwachi Street, Kaifu District, +
Changsha, Hunan Province, 410073, P.R. China +('3144121', 'Yubin Zhan', 'yubin zhan')
('1969736', 'Jianping Yin', 'jianping yin')
('33793976', 'Xinwang Liu', 'xinwang liu')E-mail: {YubinZhan,JPYin,XWLiu}@nudt.edu.cn +59e9934720baf3c5df3a0e1e988202856e1f83ceUA-DETRAC: A New Benchmark and Protocol for +
Multi-Object Detection and Tracking +
University at Albany, SUNY
2 School of Computer and Control Engineering, UCAS +
3 Department of Electrical and Computer Engineering, UCSD +
4 National Laboratory of Pattern Recognition, CASIA +
University at Albany, SUNY
Division of Computer Science and Engineering, Hanyang University
7 Electrical Engineering and Computer Science, UCM +('39774417', 'Longyin Wen', 'longyin wen')
('1910738', 'Dawei Du', 'dawei du')
('1773408', 'Zhaowei Cai', 'zhaowei cai')
('39643145', 'Ming-Ching Chang', 'ming-ching chang')
('3245785', 'Honggang Qi', 'honggang qi')
('33047058', 'Jongwoo Lim', 'jongwoo lim')
('1715634', 'Ming-Hsuan Yang', 'ming-hsuan yang')59d225486161b43b7bf6919b4a4b4113eb50f039Complex Event Recognition from Images with Few Training Examples +
Irfan Essa∗ +
Georgia Institute of Technology
University of Southern California('2308598', 'Unaiza Ahsan', 'unaiza ahsan')
('1726241', 'Chen Sun', 'chen sun')
('1945508', 'James Hays', 'james hays')uahsan3@gatech.edu +
chensun@google.com +
hays@gatech.edu +
irfan@cc.gatech.edu +5945464d47549e8dcaec37ad41471aa70001907fNoname manuscript No. +
(will be inserted by the editor) +
Every Moment Counts: Dense Detailed Labeling of Actions in Complex +
Videos +
Received: date / Accepted: date +('34149749', 'Serena Yeung', 'serena yeung')
('3216322', 'Li Fei-Fei', 'li fei-fei')59c9d416f7b3d33141cc94567925a447d0662d80Universität des Saarlandes
Max-Planck-Institut für Informatik
AG5
Matrix factorization over max-times @@ -339,7 +464,11 @@
FOR FACE RECOGNITION
1. INTRODUCTION 59420fd595ae745ad62c26ae55a754b97170b01fObjects as Attributes for Scene Classification -
Stanford University('33642044', 'Li-Jia Li', 'li-jia li')
('2888806', 'Hao Su', 'hao su')
('7892285', 'Yongwhan Lim', 'yongwhan lim')
('3216322', 'Li Fei-Fei', 'li fei-fei')5922e26c9eaaee92d1d70eae36275bb226ecdb2eBoosting Classification Based Similarity +
Stanford University('33642044', 'Li-Jia Li', 'li-jia li')
('2888806', 'Hao Su', 'hao su')
('7892285', 'Yongwhan Lim', 'yongwhan lim')
('3216322', 'Li Fei-Fei', 'li fei-fei')599adc0dcd4ebcc2a868feedd243b5c3c1bd1d0aHow Robust is 3D Human Pose Estimation to Occlusion? +
Visual Computing Institute, RWTH Aachen University
2Robert Bosch GmbH, Corporate Research +('2699877', 'Timm Linder', 'timm linder')
('1789756', 'Bastian Leibe', 'bastian leibe'){sarandi,leibe}@vision.rwth-aachen.de +
{timm.linder,kaioliver.arras}@de.bosch.com +5922e26c9eaaee92d1d70eae36275bb226ecdb2eBoosting Classification Based Similarity
Learning by using Standard Distances
Departament d’Informàtica, Universitat de València
Av. de la Universitat s/n. 46100-Burjassot (Spain) @@ -362,6 +491,8 @@
Information and Communication Management School
The University of the Humanities
Ulaanbaatar, Mongolia e-mail: basubaer@gmail.com +59a6c9333c941faf2540979dcfcb5d503a49b91eSampling Clustering +
School of Computer Science and Technology, Shandong University, China('51016741', 'Ching Tarn', 'ching tarn')
('2413471', 'Yinan Zhang', 'yinan zhang')
('48260402', 'Ye Feng', 'ye feng')∗i@ctarn.io 59031a35b0727925f8c47c3b2194224323489d68Sparse Variation Dictionary Learning for Face Recognition with A Single
Training Sample Per Person
ETH Zurich @@ -373,15 +504,25 @@ ('38188040', 'Dong Xu', 'dong xu')
('1698982', 'Shuicheng Yan', 'shuicheng yan')
('1686911', 'Stephen Lin', 'stephen lin')
('1739208', 'Thomas S. Huang', 'thomas s. huang')
('9546964', 'Shih-Fu Chang', 'shih-fu chang')923ede53b0842619831e94c7150e0fc4104e62f7978-1-4799-9988-0/16/$31.00 ©2016 IEEE
1293
ICASSP 2016 -9264b390aa00521f9bd01095ba0ba4b42bf84d7eDisplacement Template with Divide-&-Conquer +92b61b09d2eed4937058d0f9494d9efeddc39002Under review in IJCV manuscript No. +
(will be inserted by the editor) +
BoxCars: Improving Vehicle Fine-Grained Recognition using +
3D Bounding Boxes in Traffic Surveillance +
Received: date / Accepted: date +('34891870', 'Jakub Sochor', 'jakub sochor')9264b390aa00521f9bd01095ba0ba4b42bf84d7eDisplacement Template with Divide-&-Conquer
Algorithm for Significantly Improving
Descriptor based Face Recognition Approaches -
Wenzhou University, China
University of Northern British Columbia, Canada
Aberystwyth University, UK('1692551', 'Liang Chen', 'liang chen')
('33500699', 'Ling Yan', 'ling yan')
('1990125', 'Yonghuai Liu', 'yonghuai liu')
('39388942', 'Lixin Gao', 'lixin gao')
('3779849', 'Xiaoqin Zhang', 'xiaoqin zhang')920a92900fbff22fdaaef4b128ca3ca8e8d54c3eLEARNING PATTERN TRANSFORMATION MANIFOLDS WITH PARAMETRIC ATOM +
Wenzhou University, China
University of Northern British Columbia, Canada
Aberystwyth University, UK('1692551', 'Liang Chen', 'liang chen')
('33500699', 'Ling Yan', 'ling yan')
('1990125', 'Yonghuai Liu', 'yonghuai liu')
('39388942', 'Lixin Gao', 'lixin gao')
('3779849', 'Xiaoqin Zhang', 'xiaoqin zhang')92be73dffd3320fe7734258961fe5a5f2a43390eTRANSFERRING FACE VERIFICATION NETS TO PAIN AND EXPRESSION REGRESSION +
Dept. of {Computer Science1, Electrical & Computer Engineering2, Radiation Oncology3, Cognitive Science4} +
Johns Hopkins University, 3400 N. Charles St, Baltimore, MD 21218, USA
5Dept. of EE, UESTC, 2006 Xiyuan Ave, Chengdu, Sichuan 611731, China +
Tsinghua University, Beijing 100084, China('39369840', 'Feng Wang', 'feng wang')
('40031188', 'Xiang Xiang', 'xiang xiang')
('1692867', 'Chang Liu', 'chang liu')
('1709073', 'Trac D. Tran', 'trac d. tran')
('3207112', 'Austin Reiter', 'austin reiter')
('1678633', 'Gregory D. Hager', 'gregory d. hager')
('2095823', 'Harry Quon', 'harry quon')
('1709439', 'Jian Cheng', 'jian cheng')
('1746141', 'Alan L. Yuille', 'alan l. yuille')920a92900fbff22fdaaef4b128ca3ca8e8d54c3eLEARNING PATTERN TRANSFORMATION MANIFOLDS WITH PARAMETRIC ATOM
SELECTION
Ecole Polytechnique F´ed´erale de Lausanne (EPFL)
Signal Processing Laboratory (LTS4)
Switzerland-1015 Lausanne -('12636684', 'Elif Vural', 'elif vural')
('1703189', 'Pascal Frossard', 'pascal frossard')924b14a9e36d0523a267293c6d149bca83e73f3bVolume 5, Number 2, pp. 133 -164 +('12636684', 'Elif Vural', 'elif vural')
('1703189', 'Pascal Frossard', 'pascal frossard')9207671d9e2b668c065e06d9f58f597601039e5eFace Detection Using a 3D Model on +
Face Keypoints +('2455529', 'Adrian Barbu', 'adrian barbu')
('3019469', 'Gary Gramajo', 'gary gramajo')924b14a9e36d0523a267293c6d149bca83e73f3bVolume 5, Number 2, pp. 133 -164
Development and Evaluation of a Method
Employed to Identify Internal State
Utilizing Eye Movement Data @@ -400,6 +541,14 @@
Department of Computer Science,
Centre of Biological Signalling Studies (BIOSS),
University of Freiburg, Germany('2127987', 'Benjamin Drayer', 'benjamin drayer')
('1710872', 'Thomas Brox', 'thomas brox'){drayer,brox}@cs.uni-freiburg.de +928b8eb47288a05611c140d02441660277a7ed54Exploiting Images for Video Recognition with Hierarchical Generative +
Adversarial Networks +
1 Beijing Laboratory of Intelligent Information Technology, School of Computer Science, +
Big Data Research Center, University of Electronic Science and Technology of China
Beijing Institute of Technology('3450614', 'Feiwu Yu', 'feiwu yu')
('2125709', 'Xinxiao Wu', 'xinxiao wu')
('9177510', 'Yuchao Sun', 'yuchao sun')
('2055900', 'Lixin Duan', 'lixin duan'){yufeiwu,wuxinxiao,sunyuchao}@bit.edu.cn, lxduan@uestc.edu.cn +926e97d5ce2a6e070f8ec07c5aa7f91d3df90ba0Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural +
Networks +
Department of Electrical and Computer Engineering +
University of Denver, Denver, CO('3093835', 'Mohammad H. Mahoor', 'mohammad h. mahoor')behzad.hasani@du.edu and mmahoor@du.edu 92c2dd6b3ac9227fce0a960093ca30678bceb364Provided by the author(s) and NUI Galway in accordance with publisher policies. Please cite the published
version when available.
Title @@ -424,7 +573,29 @@
http://hdl.handle.net/10379/1350
Some rights reserved. For more information, please see the item record link above.
Downloaded 2018-11-06T00:40:53Z -922838dd98d599d1d229cc73896d55e7a769aa7cLearning Hierarchical Representations for Face Verification +92e464a5a67582d5209fa75e3b29de05d82c7c86Reconstruction for Feature Disentanglement in Pose-invariant Face Recognition +
Rutgers University, NJ, USA
2NEC Labs America, CA, USA +('4340744', 'Xi Peng', 'xi peng')
('39960064', 'Xiang Yu', 'xiang yu')
('1729571', 'Kihyuk Sohn', 'kihyuk sohn'){xpeng.cs, dnm}@rutgers.edu, {xiangyu, ksohn, manu}@nec-labs.com +927ba64123bd4a8a31163956b3d1765eb61e4426Customer satisfaction measuring based on the most +
significant facial emotion +
To cite this version: +
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 +
archive 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 +
abroad, 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. +('50101862', 'Rostom Kachouri', 'rostom kachouri')
('50101862', 'Rostom Kachouri', 'rostom kachouri')922838dd98d599d1d229cc73896d55e7a769aa7cLearning Hierarchical Representations for Face Verification
with Convolutional Deep Belief Networks
Erik Learned-Miller
University of Massachusetts
University of Michigan
University of Massachusetts
Amherst, MA @@ -489,7 +660,9 @@
copy-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 -0c741fa0966ba3ee4fc326e919bf2f9456d0cd74Facial Age Estimation by Learning from Label Distributions +923ec0da8327847910e8dd71e9d801abcbc93b08Hide-and-Seek: Forcing a Network to be Meticulous for +
Weakly-supervised Object and Action Localization +
University of California, Davis('19553871', 'Krishna Kumar Singh', 'krishna kumar singh')
('1883898', 'Yong Jae Lee', 'yong jae lee')0c741fa0966ba3ee4fc326e919bf2f9456d0cd74Facial Age Estimation by Learning from Label Distributions
School of Mathematical Sciences, Monash University, VIC 3800, Australia
School of Computer Science and Engineering, Southeast University, Nanjing 210096, China
National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China('1735299', 'Xin Geng', 'xin geng')
('2848275', 'Kate Smith-Miles', 'kate smith-miles')
('1692625', 'Zhi-Hua Zhou', 'zhi-hua zhou')0c435e7f49f3e1534af0829b7461deb891cf540aCapturing Global Semantic Relationships for Facial Action Unit Recognition
Rensselaer Polytechnic Institute
School of Electrical Engineering and Automation, Harbin Institute of Technology
School of Computer Science and Technology, University of Science and Technology of China('2860279', 'Ziheng Wang', 'ziheng wang')
('1830523', 'Yongqiang Li', 'yongqiang li')
('1791319', 'Shangfei Wang', 'shangfei wang')
('1726583', 'Qiang Ji', 'qiang ji'){wangz10,liy23,jiq}@rpi.edu
sfwang@ustc.edu.cn @@ -521,7 +694,15 @@ 0c75c7c54eec85e962b1720755381cdca3f57dfb2212
Face Landmark Fitting via Optimized Part
Mixtures and Cascaded Deformable Model -('39960064', 'Xiang Yu', 'xiang yu')
('1768190', 'Junzhou Huang', 'junzhou huang')
('1753384', 'Shaoting Zhang', 'shaoting zhang')
('1711560', 'Dimitris N. Metaxas', 'dimitris n. metaxas')0c1d85a197a1f5b7376652a485523e616a406273Joint Registration and Representation Learning for Unconstrained Face +('39960064', 'Xiang Yu', 'xiang yu')
('1768190', 'Junzhou Huang', 'junzhou huang')
('1753384', 'Shaoting Zhang', 'shaoting zhang')
('1711560', 'Dimitris N. Metaxas', 'dimitris n. metaxas')0cf2eecf20cfbcb7f153713479e3206670ea0e9cPrivacy-Protective-GAN for Face De-identification +
Temple University('50117915', 'Yifan Wu', 'yifan wu')
('46319628', 'Fan Yang', 'fan yang')
('1805398', 'Haibin Ling', 'haibin ling'){yifan.wu, fyang, hbling} @temple.edu +0ca36ecaf4015ca4095e07f0302d28a5d9424254Improving Bag-of-Visual-Words Towards Effective Facial Expressive +
Image Classification +
1Univ. Grenoble Alpes, CNRS, Grenoble INP∗ , GIPSA-lab, 38000 Grenoble, France +
Keywords: +
BoVW, k-means++, Relative Conjunction Matrix, SIFT, Spatial Pyramids, TF.IDF. +('10762131', 'Dawood Al Chanti', 'dawood al chanti')
('1788869', 'Alice Caplier', 'alice caplier')dawood.alchanti@gmail.com +0c1d85a197a1f5b7376652a485523e616a406273Joint Registration and Representation Learning for Unconstrained Face
Identification
University of Canberra, Australia, Data61 - CSIRO and ANU, Australia
Khalifa University, Abu Dhabi, United Arab Emirates('2008898', 'Munawar Hayat', 'munawar hayat')
('1802072', 'Naoufel Werghi', 'naoufel werghi'){munawar.hayat,roland.goecke}@canberra.edu.au, salman.khan@csiro.au, naoufel.werghi@kustar.ac.ae 0ca66283f4fb7dbc682f789fcf6d6732006befd5Active Dictionary Learning for Image Representation @@ -533,7 +714,15 @@
of Doctor of Philosophy
in the Graduate School of Arts and Sciences
COLUMBIA UNIVERSITY
2003 -('1779052', 'Srinivasa G. Narasimhan', 'srinivasa g. narasimhan')0c20fd90d867fe1be2459223a3cb1a69fa3d44bfA Monte Carlo Strategy to Integrate Detection +('1779052', 'Srinivasa G. Narasimhan', 'srinivasa g. narasimhan')0cfca73806f443188632266513bac6aaf6923fa8Predictive 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: 1diego.vergara@alu.ucm.cl, 2shernandez@ucm.cl,3matias.valdenegro@dfki.de, +
4f.jorquera.uribe@gmail.com +0c20fd90d867fe1be2459223a3cb1a69fa3d44bfA Monte Carlo Strategy to Integrate Detection
and Model-Based Face Analysis
Department for Mathematics and Computer Science
University of Basel, Switzerland('2591294', 'Andreas Forster', 'andreas forster')
('34460642', 'Bernhard Egger', 'bernhard egger')
('1687079', 'Thomas Vetter', 'thomas vetter')sandro.schoenborn,andreas.forster,bernhard.egger,thomas.vetter@unibas.ch @@ -663,7 +852,12 @@
Aggregating Local Patches for Scene Recognition ('40184588', 'Zhe Wang', 'zhe wang')
('39709927', 'Limin Wang', 'limin wang')
('40457196', 'Yali Wang', 'yali wang')
('3047890', 'Bowen Zhang', 'bowen zhang')
('40285012', 'Yu Qiao', 'yu qiao')0c60eebe10b56dbffe66bb3812793dd5148659350c05f60998628884a9ac60116453f1a91bcd9ddaOptimizing Open-Ended Crowdsourcing: The Next Frontier in
Crowdsourced Data Management -
University of Illinois
cid:63)Stanford University('32953042', 'Akash Das Sarma', 'akash das sarma')
('8336538', 'Vipul Venkataraman', 'vipul venkataraman')660b73b0f39d4e644bf13a1745d6ee74424d4a163,250+OPEN ACCESS BOOKS106,000+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 Reviews, Refinements and New Ideas in Face RecognitionDownloaded from: http://www.intechopen.com/books/reviews-refinements-and-new-ideas-in-face-recognitionPUBLISHED BYWorld's largest Science,Technology & Medicine Open Access book publisherInterested in publishing with InTechOpen?Contact us at book.department@intechopen.com 66d512342355fb77a4450decc89977efe7e55fa2Under review as a conference paper at ICLR 2018 +
University of Illinois
cid:63)Stanford University('32953042', 'Akash Das Sarma', 'akash das sarma')
('8336538', 'Vipul Venkataraman', 'vipul venkataraman')6601a0906e503a6221d2e0f2ca8c3f544a4adab7SRTM-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 +660b73b0f39d4e644bf13a1745d6ee74424d4a163,250+OPEN ACCESS BOOKS106,000+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 Reviews, Refinements and New Ideas in Face RecognitionDownloaded from: http://www.intechopen.com/books/reviews-refinements-and-new-ideas-in-face-recognitionPUBLISHED BYWorld's largest Science,Technology & Medicine Open Access book publisherInterested in publishing with InTechOpen?Contact us at book.department@intechopen.com 66d512342355fb77a4450decc89977efe7e55fa2Under review as a conference paper at ICLR 2018
LEARNING NON-LINEAR TRANSFORM WITH DISCRIM-
INATIVE AND MINIMUM INFORMATION LOSS PRIORS
Anonymous authors @@ -686,7 +880,8 @@
jeffcohn@pitt.edu 6643a7feebd0479916d94fb9186e403a4e5f7cbfChapter 8
3D Face Recognition -('1737428', 'Nick Pears', 'nick pears')66dcd855a6772d2731b45cfdd75f084327b055c2Quality Classified Image Analysis with Application +('1737428', 'Nick Pears', 'nick pears')661ca4bbb49bb496f56311e9d4263dfac8eb96e9Datasheets for Datasets +('2076288', 'Timnit Gebru', 'timnit gebru')
('1722360', 'Hal Daumé', 'hal daumé')66dcd855a6772d2731b45cfdd75f084327b055c2Quality Classified Image Analysis with Application
to Face Detection and Recognition
International Doctoral Innovation Centre
University of Nottingham Ningbo China
School of Computer Science @@ -696,6 +891,12 @@ ('3247966', 'Jianlong Fu', 'jianlong fu')
('1783122', 'Jinqiao Wang', 'jinqiao wang')
('3349534', 'Xin-Jing Wang', 'xin-jing wang')
('3663422', 'Yong Rui', 'yong rui')
('1694235', 'Hanqing Lu', 'hanqing lu')1fjlfu, jqwang, luhqg@nlpr.ia.ac.cn, 2fxjwang, yongruig@microsoft.com 66330846a03dcc10f36b6db9adf3b4d32e7a3127Polylingual Multimodal Learning
Institute AIFB, Karlsruhe Institute of Technology, Germany('3219864', 'Aditya Mogadala', 'aditya mogadala'){aditya.mogadala}@kit.edu +66d087f3dd2e19ffe340c26ef17efe0062a59290Dog Breed Identification +
Brian Mittl +
Vijay Singh +wlarow@stanford.edu +
bmittl@stanford.edu +
vpsingh@stanford.edu 6618cff7f2ed440a0d2fa9e74ad5469df5cdbe4cOrdinal Regression with Multiple Output CNN for Age Estimation
Xidian University 2Xi an Jiaotong University 3Microsoft Research Asia('1786361', 'Zhenxing Niu', 'zhenxing niu')
('1745420', 'Gang Hua', 'gang hua')
('10699750', 'Xinbo Gao', 'xinbo gao')
('36497527', 'Mo Zhou', 'mo zhou')
('40367806', 'Le Wang', 'le wang'){zhenxingniu,cdluminate}@gmail.com, lewang@mail.xjtu.edu.cn, xinbogao@mail.xidian.edu.cn
ganghua@gmail.com @@ -720,7 +921,7 @@
for Exploring the Face Space
Escuela Superior Politecnica del Litoral (ESPOL)
Guayaquil-Ecuador -('3123974', 'Andres G. Abad', 'andres g. abad')
('3044670', 'Luis I. Reyes Castro', 'luis i. reyes castro')66886997988358847615375ba7d6e9eb0f1bb27f66a9935e958a779a3a2267c85ecb69fbbb75b8dcFAST AND ROBUST FIXED-RANK MATRIX RECOVERY +('3123974', 'Andres G. Abad', 'andres g. abad')
('3044670', 'Luis I. Reyes Castro', 'luis i. reyes castro')66886997988358847615375ba7d6e9eb0f1bb27f66837add89caffd9c91430820f49adb5d3f4093066a9935e958a779a3a2267c85ecb69fbbb75b8dcFAST AND ROBUST FIXED-RANK MATRIX RECOVERY
Fast and Robust Fixed-Rank Matrix
Recovery
Antonio Lopez @@ -911,6 +1112,11 @@
Recognition Systems by Segmenting Face Region
St. Xavier s Catholic College of Engineering, Nagercoil, India
Manonmaniam Sundaranar University, Tirunelveli, India('9375880', 'R. Reena Rose', 'r. reena rose')
('3311251', 'A. Suruliandi', 'a. suruliandi')mailtoreenarose@yahoo.in
suruliandi@yahoo.com +3e0a1884448bfd7f416c6a45dfcdfc9f2e617268Understanding and Controlling User Linkability in +
Decentralized Learning +
Max Planck Institute for Informatics
Saarland Informatics Campus +
Saarbrücken, Germany +('9517443', 'Tribhuvanesh Orekondy', 'tribhuvanesh orekondy')
('2390510', 'Seong Joon Oh', 'seong joon oh')
('1697100', 'Bernt Schiele', 'bernt schiele'){orekondy,joon,schiele,mfritz}@mpi-inf.mpg.de 3e4b38b0574e740dcbd8f8c5dfe05dbfb2a92c07FACIAL EXPRESSION RECOGNITION WITH LOCAL BINARY PATTERNS
AND LINEAR PROGRAMMING
Xiaoyi Feng1, 2, Matti Pietikäinen1, Abdenour Hadid1 @@ -999,7 +1205,9 @@ 3ee7a8107a805370b296a53e355d111118e96b7c3ebce6710135d1f9b652815e59323858a7c60025Component-based Face Detection
(cid:1)Center for Biological and Computational Learning, M.I.T., Cambridge, MA, USA
cid:2)Honda RandD Americas, Inc., Boston, MA, USA
University of Siena, Siena, Italy('1684626', 'Bernd Heisele', 'bernd heisele')(cid:1)heisele, serre, tp(cid:2) @ai.mit.edu pontil@dii.unisi.it -3e3f305dac4fbb813e60ac778d6929012b4b745aFeature sampling and partitioning for visual vocabulary +3e4acf3f2d112fc6516abcdddbe9e17d839f5d9bDeep Value Networks Learn to +
Evaluate and Iteratively Refine Structured Outputs +('3037160', 'Michael Gygli', 'michael gygli')3e3f305dac4fbb813e60ac778d6929012b4b745aFeature sampling and partitioning for visual vocabulary
generation on large action classification datasets.
Oxford Brookes University
University of Oxford('3019396', 'Michael Sapienza', 'michael sapienza')
('1754181', 'Fabio Cuzzolin', 'fabio cuzzolin')3ea8a6dc79d79319f7ad90d663558c664cf298d4('40253814', 'IRA COHEN', 'ira cohen')3e4f84ce00027723bdfdb21156c9003168bc1c801979
© EURASIP, 2011 - ISSN 2076-1465 @@ -1046,7 +1254,12 @@
FOR FACE RECOGNITION BASED ON SPARSE REPRESENTATION
Tokyo Metropolitan University
6–6 Asahigaoka, Hino-shi, Tokyo 191–0065, Japan
† NTT Network Innovation Laboratories, Japan -('32403098', 'Yuichi Muraki', 'yuichi muraki')
('11129971', 'Masakazu Furukawa', 'masakazu furukawa')
('1728060', 'Masaaki Fujiyoshi', 'masaaki fujiyoshi')
('34638424', 'Yoshihide Tonomura', 'yoshihide tonomura')
('1737217', 'Hitoshi Kiya', 'hitoshi kiya')3e687d5ace90c407186602de1a7727167461194aPhoto Tagging by Collection-Aware People Recognition +('32403098', 'Yuichi Muraki', 'yuichi muraki')
('11129971', 'Masakazu Furukawa', 'masakazu furukawa')
('1728060', 'Masaaki Fujiyoshi', 'masaaki fujiyoshi')
('34638424', 'Yoshihide Tonomura', 'yoshihide tonomura')
('1737217', 'Hitoshi Kiya', 'hitoshi kiya')3e40991ab1daa2a4906eb85a5d6a01a958b6e674LIPNET: END-TO-END SENTENCE-LEVEL LIPREADING +
University of Oxford, Oxford, UK
Google DeepMind, London, UK 2 +
CIFAR, Canada 3 +
{yannis.assael,brendan.shillingford, +('3365565', 'Yannis M. Assael', 'yannis m. assael')
('3144580', 'Brendan Shillingford', 'brendan shillingford')
('1766767', 'Shimon Whiteson', 'shimon whiteson')shimon.whiteson,nando.de.freitas}@cs.ox.ac.uk +3e687d5ace90c407186602de1a7727167461194aPhoto Tagging by Collection-Aware People Recognition
UFF
UFF
Asla S´a @@ -1115,7 +1328,17 @@
Email: guyon@chalearn.org 501eda2d04b1db717b7834800d74dacb7df58f91('3846862', 'Pedro Miguel Neves Marques', 'pedro miguel neves marques')5083c6be0f8c85815ead5368882b584e4dfab4d1 Please do not quote. In press, Handbook of affective computing. New York, NY: Oxford
Automated Face Analysis for Affective Computing -('1737918', 'Jeffrey F. Cohn', 'jeffrey f. cohn')500b92578e4deff98ce20e6017124e6d2053b4515058a7ec68c32984c33f357ebaee96c59e269425A Comparative Evaluation of Regression Learning +('1737918', 'Jeffrey F. Cohn', 'jeffrey f. cohn')506c2fbfa9d16037d50d650547ad3366bb1e1cdeConvolutional Channel Features: Tailoring CNN to Diverse Tasks +
Junjie Yan +
Zhen Lei +
Center for Biometrics and Security Research & National Laboratory of Pattern Recognition +
Institute of Automation, Chinese Academy of Sciences, China('1716231', 'Bin Yang', 'bin yang')
('34679741', 'Stan Z. Li', 'stan z. li'){zlei, szli}@nlpr.ia.ac.cn +
{yb.derek, yanjjie}@gmail.com +500b92578e4deff98ce20e6017124e6d2053b451504028218290d68859f45ec686f435f473aa326cMulti-Fiber Networks for Video Recognition +
National University of Singapore
2 Facebook Research +
Qihoo 360 AI Institute('1713312', 'Yunpeng Chen', 'yunpeng chen')
('1944225', 'Yannis Kalantidis', 'yannis kalantidis')
('2757639', 'Jianshu Li', 'jianshu li')
('1698982', 'Shuicheng Yan', 'shuicheng yan')
('33221685', 'Jiashi Feng', 'jiashi feng'){chenyunpeng, jianshu}@u.nus.edu, yannisk@fb.com, +
{eleyans, elefjia}@nus.edu.sg +5058a7ec68c32984c33f357ebaee96c59e269425A Comparative Evaluation of Regression Learning
Algorithms for Facial Age Estimation
1 Herta Security
Pau Claris 165 4-B, 08037 Barcelona, Spain @@ -1150,7 +1373,18 @@ 5050807e90a925120cbc3a9cd13431b98965f4b9To appear in the ECCV Workshop on Parts and Attributes, Oct. 2012.
Unsupervised Learning of Discriminative
Relative Visual Attributes -
Boston University
Hacettepe University('2863531', 'Shugao Ma', 'shugao ma')
('2011587', 'Nazli Ikizler-Cinbis', 'nazli ikizler-cinbis')50eb2ee977f0f53ab4b39edc4be6b760a2b05f96Australian Journal of Basic and Applied Sciences, 11(5) April 2017, Pages: 1-11 +
Boston University
Hacettepe University('2863531', 'Shugao Ma', 'shugao ma')
('2011587', 'Nazli Ikizler-Cinbis', 'nazli ikizler-cinbis')50a0930cb8cc353e15a5cb4d2f41b365675b5ebf508702ed2bf7d1b0655ea7857dd8e52d6537e765ZUO, ORGANISCIAK, SHUM, YANG: SST-VLAD AND SST-FV FOR VAR +
Saliency-Informed Spatio-Temporal Vector +
of Locally Aggregated Descriptors and +
Fisher Vectors for Visual Action Recognition +
Department of Computer and +
Information Sciences +
Northumbria University
Newcastle upon Tyne, NE1 8ST, UK +('40760781', 'Zheming Zuo', 'zheming zuo')
('34975328', 'Daniel Organisciak', 'daniel organisciak')
('2840036', 'Hubert P. H. Shum', 'hubert p. h. shum')
('1706028', 'Longzhi Yang', 'longzhi yang')zheming.zuo@northumbria.ac.uk +
daniel.organisciak@northumbria.ac.uk +
hubert.shum@northumbria.ac.uk +
longzhi.yang@northumbria.ac.uk +50eb2ee977f0f53ab4b39edc4be6b760a2b05f96Australian 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 @@ -1392,12 +1626,14 @@ ('34964075', 'Satyanarayana Murty', 'satyanarayana murty')India, 1gsn_73@yahoo.co.in
2drvvk144@gmail.com
3obulesh.a@gmail.com -68a3f12382003bc714c51c85fb6d0557dcb154676859b891a079a30ef16f01ba8b85dc45bd22c352International Journal of Emerging Technology and Advanced Engineering +68d2afd8c5c1c3a9bbda3dd209184e368e4376b9Representation Learning by Rotating Your Faces +('1849929', 'Luan Tran', 'luan tran')
('2399004', 'Xi Yin', 'xi yin')
('1759169', 'Xiaoming Liu', 'xiaoming liu')68a3f12382003bc714c51c85fb6d0557dcb154676859b891a079a30ef16f01ba8b85dc45bd22c352International Journal of Emerging Technology and Advanced Engineering
Website: www.ijetae.com (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 4, Issue 10, October 2014)
2D Face Recognition Based on PCA & Comparison of
Manhattan Distance, Euclidean Distance & Chebychev
Distance -
RCC Institute of Information Technology, Kolkata, India('2467416', 'Rajib Saha', 'rajib saha')
('2144187', 'Sayan Barman', 'sayan barman')68003e92a41d12647806d477dd7d20e4dcde1354ISSN: 0976-9102 (ONLINE) +
RCC Institute of Information Technology, Kolkata, India('2467416', 'Rajib Saha', 'rajib saha')
('2144187', 'Sayan Barman', 'sayan barman')68d08ed9470d973a54ef7806318d8894d87ba610Drive Video Analysis for the Detection of Traffic Near-Miss Incidents +('1730200', 'Hirokatsu Kataoka', 'hirokatsu kataoka')
('5014206', 'Teppei Suzuki', 'teppei suzuki')
('6881850', 'Shoko Oikawa', 'shoko oikawa')
('1720770', 'Yasuhiro Matsui', 'yasuhiro matsui')
('1732705', 'Yutaka Satoh', 'yutaka satoh')68caf5d8ef325d7ea669f3fb76eac58e0170fff068003e92a41d12647806d477dd7d20e4dcde1354ISSN: 0976-9102 (ONLINE)
DOI: 10.21917/ijivp.2013.0101
ICTACT JOURNAL ON IMAGE AND VIDEO PROCESSING, NOVEMBER 2013, VOLUME: 04, ISSUE: 02
FUZZY BASED IMAGE DIMENSIONALITY REDUCTION USING SHAPE @@ -1416,7 +1652,10 @@
3 ITESM, Campus Saltillo, Saltillo 25270, Coahuila, M´exico
Veracruz, M´exico mario.castelan@cinvestav.edu.mx -68c5238994e3f654adea0ccd8bca29f2a24087fcPLSA-BASED ZERO-SHOT LEARNING +684f5166d8147b59d9e0938d627beff8c9d208ddIEEE TRANS. NNLS, JUNE 2017 +
Discriminative Block-Diagonal Representation +
Learning for Image Recognition +('38448016', 'Zheng Zhang', 'zheng zhang')
('40065614', 'Yong Xu', 'yong xu')
('40799321', 'Ling Shao', 'ling shao')
('49500178', 'Jian Yang', 'jian yang')68c5238994e3f654adea0ccd8bca29f2a24087fcPLSA-BASED ZERO-SHOT LEARNING
Centre of Image and Signal Processing
Faculty of Computer Science & Information Technology
University of Malaya, 50603 Kuala Lumpur, Malaysia('2800072', 'Wai Lam Hoo', 'wai lam hoo')
('2863960', 'Chee Seng Chan', 'chee seng chan'){wailam88@siswa.um.edu.my; cs.chan@um.edu.my} @@ -1428,7 +1667,10 @@
Link ping University
Face Recognition with
Preprocessing and Neural
Networks -687e17db5043661f8921fb86f215e9ca2264d4d2A Robust Elastic and Partial Matching Metric for Face Recognition +68484ae8a042904a95a8d284a7f85a4e28e37513Spoofing Deep Face Recognition with Custom Silicone Masks +
S´ebastien Marcel +
Idiap Research Institute. Centre du Parc, Rue Marconi 19, Martigny (VS), Switzerland('1952348', 'Sushil Bhattacharjee', 'sushil bhattacharjee'){sushil.bhattacharjee; amir.mohammadi; sebastien.marcel}@idiap.ch +687e17db5043661f8921fb86f215e9ca2264d4d2A Robust Elastic and Partial Matching Metric for Face Recognition
Microsoft Corporate
One Microsoft Way, Redmond, WA 98052 ('1745420', 'Gang Hua', 'gang hua')
('33474090', 'Amir Akbarzadeh', 'amir akbarzadeh'){ganghua, amir}@microsoft.com @@ -1553,7 +1795,38 @@
Florida International University
Miami, FL 33199, USA ('1685202', 'Lin Lin', 'lin lin')
('1693826', 'Mei-Ling Shyu', 'mei-ling shyu')
('1705664', 'Shu-Ching Chen', 'shu-ching chen')Email: l.lin2@umiami.edu, shyu@miami.edu
Email: chens@cs.fiu.edu -683ec608442617d11200cfbcd816e86ce9ec0899Dual Linear Regression Based Classification for Face Cluster Recognition +682760f2f767fb47e1e2ca35db3becbb6153756fThe Effect of Pets on Happiness: A Large-scale Multi-Factor +
Analysis using Social Multimedia +
From reducing stress and loneliness, to boosting productivity and overall well-being, pets are believed to play +
a significant role in people’s daily lives. Many traditional studies have identified that frequent interactions +
with pets could make individuals become healthier and more optimistic, and ultimately enjoy a happier life. +
However, most of those studies are not only restricted in scale, but also may carry biases by using subjective +
self-reports, interviews, and questionnaires as the major approaches. In this paper, we leverage large-scale +
data collected from social media and the state-of-the-art deep learning technologies to study this phenomenon +
in depth and breadth. Our study includes four major steps: 1) collecting timeline posts from around 20,000 +
Instagram users; 2) using face detection and recognition on 2-million photos to infer users’ demographics, +
relationship status, and whether having children, 3) analyzing a user’s degree of happiness based on images +
and captions via smiling classification and textual sentiment analysis; 3) applying transfer learning techniques +
to retrain the final layer of the Inception v3 model for pet classification; and 4) analyzing the effects of pets +
on happiness in terms of multiple factors of user demographics. Our main results have demonstrated the +
efficacy of our proposed method with many new insights. We believe this method is also applicable to other +
domains as a scalable, efficient, and effective methodology for modeling and analyzing social behaviors and +
psychological well-being. In addition, to facilitate the research involving human faces, we also release our +
dataset of 700K analyzed faces. +
CCS Concepts: • Human-centered computing → Social media; +
Additional Key Words and Phrases: Happiness analysis, happiness, user demographics, pet and happiness, +
social multimedia, social media. +
ACM Reference format: +
Analysis using Social Multimedia. ACM Trans. Intell. Syst. Technol. 9, 4, Article 39 (June 2017), 15 pages. +
https://doi.org/0000001.0000001 +
1 INTRODUCTION +
Happiness has always been a subjective and multidimensional matter; its definition varies individu- +
ally, and the factors impacting our feeling of happiness are diverse. A study in [21] has constructed +
We thank the support of New York State through the Goergen Institute for Data Science, our corporate research sponsors
Xerox and VisualDX, and NSF Award #1704309. +
Author s addresses: X. Peng, University of Rochester; L. Chi
University of Rochester and J. Luo, University of Rochester
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 of this work owned by others than the author(s) must be honored. +('1901094', 'Xuefeng Peng', 'xuefeng peng')
('35678395', 'Li-Kai Chi', 'li-kai chi')
('33642939', 'Jiebo Luo', 'jiebo luo')
('1901094', 'Xuefeng Peng', 'xuefeng peng')
('35678395', 'Li-Kai Chi', 'li-kai chi')
('33642939', 'Jiebo Luo', 'jiebo luo')683ec608442617d11200cfbcd816e86ce9ec0899Dual Linear Regression Based Classification for Face Cluster Recognition
University of Northern British Columbia
Prince George, BC, Canada V2N 4Z9 ('1692551', 'Liang Chen', 'liang chen')chen.liang.97@gmail.com 68c17aa1ecbff0787709be74d1d98d9efd78f410International Journal of Optomechatronics, 6: 92–119, 2012 @@ -1595,6 +1868,74 @@
ing.uchile.cl
92 ('32271973', 'Claudio Perez', 'claudio perez')
('40333310', 'Juan Tapia', 'juan tapia')
('32723983', 'Claudio Held', 'claudio held')
('32271973', 'Claudio Perez', 'claudio perez')
('32271973', 'Claudio Perez', 'claudio perez')Engineering, Universidad de Chile Casilla 412-3, Av. Tupper 2007, Santiago, Chile. E-mail: clperez@ +68f61154a0080c4aae9322110c8827978f01ac2eResearch Article +
Journal of the Optical Society of America A +
Recognizing blurred, non-frontal, illumination and +
expression variant partially occluded faces +
Indian Institute of Technology Madras, Chennai 600036, India
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 +
between 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 +
OCIS codes: +
(150.0150) Machine vision. +
http://dx.doi.org/10.1364/ao.XX.XXXXXX +
(100.0100) Image processing; (100.5010) Pattern recognition; (100.3008) Image recognition, algorithms and filters; +
1. INTRODUCTION +
State-of-the-art face recognition (FR) systems can outperform +
even humans when presented with images captured under con- +
trolled environments. However, their performance drops quite +
rapidly in unconstrained settings due to image degradations +
arising from blur, variations in pose, illumination, and expres- +
sion, partial occlusion etc. Motion blur is commonplace today +
owing to the exponential rise in the use and popularity of light- +
weight and cheap hand-held imaging devices, and the ubiquity +
of mobile phones equipped with cameras. Photographs cap- +
tured using a hand-held device usually contain blur when the +
illumination is poor because larger exposure times are needed +
to compensate for the lack of light, and this increases the possi- +
bility of camera shake. On the other hand, reducing the shutter +
speed results in noisy images while tripods inevitably restrict +
mobility. Even for a well-lit scene, the face might be blurred if +
the subject is in motion. The problem is further compounded +
in the case of poorly-lit dynamic scenes since the blur observed +
on the face is due to the combined effects of the blur induced +
by the motion of the camera and the independent motion of +
the subject. In addition to blur and illumination, practical face +
recognition algorithms must also possess the ability to recognize +
faces across reasonable variations in pose. Partial occlusion and +
facial expression changes, common in real-world applications, +
escalate the challenges further. Yet another factor that governs +
the performance of face recognition algorithms is the number +
of images per subject available for training. In many practical +
application scenarios such as law enforcement, driver license or +
passport identification, where there is usually only one training +
sample per subject in the database, techniques that rely on the +
size and representation of the training set suffer a serious perfor- +
mance drop or even fail to work. Face recognition algorithms +
can broadly be classified into either discriminative or genera- +
tive approaches. While the availability of large labeled datasets +
and greater computing power has boosted the performance of +
discriminative methods [1, 2] recently, generative approaches +
continue to remain very popular [3, 4], and there is concurrent +
research in both directions. The model we present in this paper +
falls into the latter category. In fact, generative models are even +
useful for producing training samples for learning algorithms. +
Literature on face recognition from blurred images can be +
broadly classified into four categories. It is important to note +
that all of them (except our own earlier work in [4]) are restricted +
to the convolution model for uniform blur. In the first approach +
[5, 6], the blurred probe image is first deblurred using standard +
deconvolution algorithms before performing recognition. How- +*Corresponding author: jithuthatswho@gmail.com 6821113166b030d2123c3cd793dd63d2c909a110STUDIA INFORMATICA
Volume 36
2015 @@ -2018,7 +2359,17 @@
[15 of 21] N. Pinto, J. J. DiCarlo, and D. D. Cox. How far can you get with a modern face recognition test set using only simple features? In IEEE CVPR, 2009.
[18 of 21] T. Sim, S. Baker, and M. Bsat. The CMU Pose, Illumination and Expression (PIE) Database. In Proceedings of the IEEE F&G, May 2002. ('31552290', 'Brian C. Parks', 'brian c. parks')
('2613438', 'Walter J. Scheirer', 'walter j. scheirer'){viyer,skirkbride,bparks,wscheirer,tboult}@vast.uccs.edu -5721216f2163d026e90d7cd9942aeb4bebc92334575141e42740564f64d9be8ab88d495192f5b3bcAge Estimation based on Multi-Region +574b62c845809fd54cc168492424c5fac145bc83Learning Warped Guidance for Blind Face +
Restoration +
School of Computer Science and Technology, Harbin Institute of Technology, China
School of Data and Computer Science, Sun Yat-sen University, China
University of Kentucky, USA('21515518', 'Xiaoming Li', 'xiaoming li')
('40508248', 'Yuting Ye', 'yuting ye')
('1724520', 'Wangmeng Zuo', 'wangmeng zuo')
('1737218', 'Liang Lin', 'liang lin')
('38958903', 'Ruigang Yang', 'ruigang yang')csxmli@hit.edu.cn, csmliu@outlook.com, yeyuting.jlu@gmail.com, +
wmzuo@hit.edu.cn +
linliang@ieee.org +
ryang@cs.uky.edu +57246142814d7010d3592e3a39a1ed819dd01f3bMITSUBISHI ELECTRIC RESEARCH LABORATORIES
http://www.merl.com +
Verification of Very Low-Resolution Faces Using An +
Identity-Preserving Deep Face Super-resolution Network +
TR2018-116 August 24, 2018 +5721216f2163d026e90d7cd9942aeb4bebc92334575141e42740564f64d9be8ab88d495192f5b3bcAge Estimation based on Multi-Region
Convolutional Neural Network
1Center for Biometrics and Security Research & National Laboratory of Pattern
Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
University of Chinese Academy of Sciences('40282288', 'Ting Liu', 'ting liu')
('1756538', 'Jun Wan', 'jun wan')
('39974958', 'Tingzhao Yu', 'tingzhao yu')
('1718623', 'Zhen Lei', 'zhen lei')
('34679741', 'Stan Z. Li', 'stan z. li'){ting.liu,jun.wan,zlei,szli}@nlpr.ia.ac.cn,yutingzhao2013@ia.ac.cn @@ -2033,7 +2384,35 @@
A Novel Approach for Face Recognition
Using PCA and Artificial Neural Network
Dayananda Sagar College of Engg., India
Dayananda Sagar College of Engg., India('9856026', 'Karthik G', 'karthik g')
('9856026', 'Karthik G', 'karthik g')1 email : karthik.knocks@gmail.com; 2 email : hcsateesh@gmail.com -5753b2b5e442eaa3be066daa4a2ca8d8a0bb172557b052cf826b24739cd7749b632f85f4b7bcf90bFast Fashion Guided Clothing Image Retrieval: +5753b2b5e442eaa3be066daa4a2ca8d8a0bb1725571b83f7fc01163383e6ca6a9791aea79cafa7ddSeqFace: Make full use of sequence information for face recognition +
College of Information Science and Technology
Beijing University of Chemical Technology, China
YUNSHITU Corp., China +('48594708', 'Wei Hu', 'wei hu')
('7524887', 'Yangyu Huang', 'yangyu huang')
('8451319', 'Guodong Yuan', 'guodong yuan')
('47191084', 'Fan Zhang', 'fan zhang')
('50391855', 'Ruirui Li', 'ruirui li')
('47113208', 'Wei Li', 'wei li')574ad7ef015995efb7338829a021776bf9daaa08AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks +
for Human Action Recognition in Videos +
1IIT Kanpur‡ +
2SRI International +
3UCSD +('24899770', 'Amlan Kar', 'amlan kar')
('12692625', 'Nishant Rai', 'nishant rai')
('39707211', 'Karan Sikka', 'karan sikka')
('39396475', 'Gaurav Sharma', 'gaurav sharma')57a14a65e8ae15176c9afae874854e8b0f23dca7UvA-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 +
DOI: +
10.1177/0022022117736270 +
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- +
148. 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. +
Download date: 08 Aug 2018 +
UvA-DARE is a service provided by the library of the University of Amsterdam (http://dare.uva.nl57b052cf826b24739cd7749b632f85f4b7bcf90bFast Fashion Guided Clothing Image Retrieval:
Delving Deeper into What Feature Makes
Fashion
School of Data and Computer Science, Sun Yat-sen University
Guangzhou, P.R China @@ -2060,6 +2439,11 @@
Center for Automation Research, UMIACS*
Department of Electrical and Computer Engineering†
University of Maryland, College Park('2747758', 'Maya Kabkab', 'maya kabkab')
('9215658', 'Rama Chellappa', 'rama chellappa')Email: {mayak, emhand, rama}@umiacs.umd.edu +3b73f8a2b39751efb7d7b396bf825af2aaadee24Connecting Pixels to Privacy and Utility: +
Automatic Redaction of Private Information in Images +
Max Planck Institute for Informatics
Saarland Informatics Campus +
Saabr¨ucken, Germany +('9517443', 'Tribhuvanesh Orekondy', 'tribhuvanesh orekondy')
('1739548', 'Mario Fritz', 'mario fritz')
('1697100', 'Bernt Schiele', 'bernt schiele'){orekondy,mfritz,schiele}@mpi-inf.mpg.de 3b2d5585af59480531616fe970cb265bbdf63f5bRobust Face Recognition under Varying Light
Based on 3D Recovery
Center of Computer Vision, School of @@ -2293,7 +2677,9 @@
Queen Mary University of London('1735328', 'Xun Xu', 'xun xu')
('1697755', 'Timothy M. Hospedales', 'timothy m. hospedales')
('2073354', 'Shaogang Gong', 'shaogang gong'){xun.xu,t.hospedales,s.gong}@qmul.ac.uk 3b9c08381282e65649cd87dfae6a01fe6abea79bCUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong
2Computer Vision Lab, ETH Zurich, Switzerland -
Shenzhen Institutes of Advanced Technology, CAS, China('3331521', 'Yuanjun Xiong', 'yuanjun xiong')
('33345248', 'Limin Wang', 'limin wang')
('1915826', 'Zhe Wang', 'zhe wang')
('3047890', 'Bowen Zhang', 'bowen zhang')
('2313919', 'Hang Song', 'hang song')
('1688012', 'Wei Li', 'wei li')
('1807606', 'Dahua Lin', 'dahua lin')
('1681236', 'Luc Van Gool', 'luc van gool')
('1741901', 'Xiaoou Tang', 'xiaoou tang')3b4fd2aec3e721742f11d1ed4fa3f0a86d988a10Glimpse: Continuous, Real-Time Object Recognition on +
Shenzhen Institutes of Advanced Technology, CAS, China('3331521', 'Yuanjun Xiong', 'yuanjun xiong')
('33345248', 'Limin Wang', 'limin wang')
('1915826', 'Zhe Wang', 'zhe wang')
('3047890', 'Bowen Zhang', 'bowen zhang')
('2313919', 'Hang Song', 'hang song')
('1688012', 'Wei Li', 'wei li')
('1807606', 'Dahua Lin', 'dahua lin')
('1681236', 'Luc Van Gool', 'luc van gool')
('1741901', 'Xiaoou Tang', 'xiaoou tang')3b84d074b8622fac125f85ab55b63e876fed4628End-to-End Localization and Ranking for +
Relative Attributes +
University of California, Davis('19553871', 'Krishna Kumar Singh', 'krishna kumar singh')
('1883898', 'Yong Jae Lee', 'yong jae lee')3b4fd2aec3e721742f11d1ed4fa3f0a86d988a10Glimpse: Continuous, Real-Time Object Recognition on
Mobile Devices
MIT CSAIL
Microsoft Research @@ -2305,7 +2691,11 @@
shuodeng@csail.mit.edu
bahl@microsoft.com
hari@csail.mit.edu -3bc376f29bc169279105d33f59642568de36f17fActive Shape Models with SIFT Descriptors and MARS +3be8f1f7501978287af8d7ebfac5963216698249Deep Cascaded Regression for Face Alignment +
School of Data and Computer Science, Sun Yat-Sen University, China
National University of Singapore, Singapore
algorithm refines the shape by estimating a shape increment +
∆S. In particular, a shape increment at stage k is calculated +
as: +('3124720', 'Shengtao Xiao', 'shengtao xiao')
('10338111', 'Zhen Cui', 'zhen cui')
('48815683', 'Yan Pan', 'yan pan')
('48258938', 'Chunyan Xu', 'chunyan xu')
('1698982', 'Shuicheng Yan', 'shuicheng yan')3bc376f29bc169279105d33f59642568de36f17fActive Shape Models with SIFT Descriptors and MARS
University of Cape Town, South Africa
Keywords:
Facial Landmark, Active Shape Model, Multivariate Adaptive Regression Splines ('2822258', 'Stephen Milborrow', 'stephen milborrow')
('2537623', 'Fred Nicolls', 'fred nicolls')milbo@sonic.net @@ -2332,7 +2722,10 @@
Date of Defense: 23rd of September, 2010
Darmstadt, 2010
D17 -('37718254', 'Michael Stark', 'michael stark')3b9b200e76a35178da940279d566bbb7dfebb787Learning Channel Inter-dependencies at Multiple Scales on Dense +('37718254', 'Michael Stark', 'michael stark')3baa3d5325f00c7edc1f1427fcd5bdc6a420a63fEnhancing Convolutional Neural Networks for Face Recognition with +
Occlusion Maps and Batch Triplet Loss +
aSchool of Engineering and Technology, University of Hertfordshire, Hat eld AL10 9AB, UK
bIDscan Biometrics (a GBG company), London E14 9QD, UK +('2133352', 'Li Meng', 'li meng')
('46301106', 'Margaret Hartnett', 'margaret hartnett')3b9b200e76a35178da940279d566bbb7dfebb787Learning Channel Inter-dependencies at Multiple Scales on Dense
Networks for Face Recognition
109 Research Way — PO Box 6109 Morgantown, West Virginia
West Virginia University
November 29, 2017 @@ -2408,7 +2801,10 @@
Face Recognition in Personal Photo Collections
Anonymous CVPR submission
Paper ID 2052 -3b557c4fd6775afc80c2cf7c8b16edde125b270eFace Recognition: Perspectives from the +3bb6570d81685b769dc9e74b6e4958894087f3f1Hu-Fu: Hardware and Software Collaborative +
Attack Framework against Neural Networks +
Beijing National Research Center for Information Science and Technology
Tsinghua University('3493074', 'Wenshuo Li', 'wenshuo li')
('1909938', 'Jincheng Yu', 'jincheng yu')
('6636914', 'Xuefei Ning', 'xuefei ning')
('2892980', 'Pengjun Wang', 'pengjun wang')
('49988678', 'Qi Wei', 'qi wei')
('47904166', 'Yu Wang', 'yu wang')
('39150998', 'Huazhong Yang', 'huazhong yang'){lws17@mails.tsinghua.edu.cn, yu-wang@tsinghua.edu.cn} +3b557c4fd6775afc80c2cf7c8b16edde125b270eFace Recognition: Perspectives from the
Real-World
Institute for Infocomm Research, A*STAR
1 Fusionopolis Way, #21-01 Connexis (South Tower), Singapore 138632.
Phone: +65 6408 2071; Fax: +65 6776 1378; @@ -2435,7 +2831,10 @@ 3b470b76045745c0ef5321e0f1e0e6a4b1821339Consensus of Regression for Occlusion-Robust
Facial Feature Localization
Rutgers University, Piscataway, NJ 08854, USA
2 Adobe Research, San Jose, CA 95110, USA -('39960064', 'Xiang Yu', 'xiang yu')
('1721019', 'Jonathan Brandt', 'jonathan brandt')
('1711560', 'Dimitris N. Metaxas', 'dimitris n. metaxas')6f288a12033fa895fb0e9ec3219f3115904f24deLearning Expressionlets via Universal Manifold +('39960064', 'Xiang Yu', 'xiang yu')
('1721019', 'Jonathan Brandt', 'jonathan brandt')
('1711560', 'Dimitris N. Metaxas', 'dimitris n. metaxas')6f5ce5570dc2960b8b0e4a0a50eab84b7f6af5cbLow Resolution Face Recognition Using a +
Two-Branch Deep Convolutional Neural Network +
Architecture +('19189138', 'Erfan Zangeneh', 'erfan zangeneh')
('1772623', 'Mohammad Rahmati', 'mohammad rahmati')
('3071758', 'Yalda Mohsenzadeh', 'yalda mohsenzadeh')6f288a12033fa895fb0e9ec3219f3115904f24deLearning Expressionlets via Universal Manifold
Model for Dynamic Facial Expression Recognition ('1730228', 'Mengyi Liu', 'mengyi liu')
('1685914', 'Shiguang Shan', 'shiguang shan')
('3373117', 'Ruiping Wang', 'ruiping wang')
('1710220', 'Xilin Chen', 'xilin chen')6fa0c206873dcc5812f7ea74a48bb4bf4b273494Real-time Mobile Facial Expression Recognition System – A Case Study
Department of Computer Engineering @@ -2471,7 +2870,14 @@
Blood Reveal Novel Biomarkers for Early Detection Of
Clinical Alzheimer’s Disease
Centre for Bioinformatics, Biomarker Discovery and Information-Based Medicine, The University of Newcastle, Callaghan, Australia, 2 Departamento de Engenharia de
Produc¸a˜o, Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, Brazil -('8423987', 'Mateus Rocha de Paula', 'mateus rocha de paula')
('34861417', 'Regina Berretta', 'regina berretta')
('1738680', 'Pablo Moscato', 'pablo moscato')6f75697a86d23d12a14be5466a41e5a7ffb79fad6f6b4e2885ea1d9bea1bb2ed388b099a5a6d9b81Structured Output SVM Prediction of Apparent Age, +('8423987', 'Mateus Rocha de Paula', 'mateus rocha de paula')
('34861417', 'Regina Berretta', 'regina berretta')
('1738680', 'Pablo Moscato', 'pablo moscato')6f75697a86d23d12a14be5466a41e5a7ffb79fad6f7d06ced04ead3b9a5da86b37e7c27bfcedbbddPages 51.1-51.12 +
DOI: https://dx.doi.org/10.5244/C.30.51 +6f7a8b3e8f212d80f0fb18860b2495be4c363eacCreating Capsule Wardrobes from Fashion Images +
UT-Austin +
UT-Austin +('22211024', 'Wei-Lin Hsiao', 'wei-lin hsiao')
('1794409', 'Kristen Grauman', 'kristen grauman')kimhsiao@cs.utexas.edu +
grauman@cs.utexas.edu +6f6b4e2885ea1d9bea1bb2ed388b099a5a6d9b81Structured Output SVM Prediction of Apparent Age,
Gender and Smile From Deep Features
Michal Uˇriˇc´aˇr
CMP, Dept. of Cybernetics @@ -2510,6 +2916,17 @@
*AICTE Emeritus Fellow ('1694317', 'Mrinal Kanti Bhowmik', 'mrinal kanti bhowmik')
('1721942', 'Debotosh Bhattacharjee', 'debotosh bhattacharjee')
('1729425', 'Mita Nasipuri', 'mita nasipuri')
('1679476', 'Dipak Kumar Basu', 'dipak kumar basu')
('1727663', 'Mahantapas Kundu', 'mahantapas kundu')mkb_cse@yahoo.co.in
debotosh@indiatimes.com, mitanasipuri@gmail.com, dipakkbasu@gmail.com, mkundu@cse.jdvu.ac.in +6fea198a41d2f6f73e47f056692f365c8e6b04ceVideo Captioning with Boundary-aware Hierarchical Language +
Decoding and Joint Video Prediction +
Nanyang Technological University
Nanyang Technological University
Singapore, Singapore +
Singapore, Singapore +
Nanyang Technological University
Singapore, Singapore +
Shafiq Joty +
Nanyang Technological University
Singapore, Singapore +('8668622', 'Xiangxi Shi', 'xiangxi shi')
('1688642', 'Jianfei Cai', 'jianfei cai')
('2174964', 'Jiuxiang Gu', 'jiuxiang gu')xxshi@ntu.edu.sg +
JGU004@e.ntu.edu.sg +
asjfcai@ntu.edu.sg +
srjoty@ntu.edu.sg 6fbb179a4ad39790f4558dd32316b9f2818cd106Input Aggregated Network for Face Video Representation
Beijing Laboratory of IIT, School of Computer Science, Beijing Institute of Technology, Beijing, China
Stony Brook University, Stony Brook, USA('40061483', 'Zhen Dong', 'zhen dong')
('3306427', 'Su Jia', 'su jia')
('1690083', 'Chi Zhang', 'chi zhang')
('35371203', 'Mingtao Pei', 'mingtao pei')6f84e61f33564e5188136474f9570b1652a0606fDual Motion GAN for Future-Flow Embedded Video Prediction
Carnegie Mellon University('40250403', 'Xiaodan Liang', 'xiaodan liang')
('3682478', 'Lisa Lee', 'lisa lee'){xiaodan1,lslee}@cs.cmu.edu @@ -2521,7 +2938,14 @@
c(cid:1) Springer-Verlag 2005
intelligent
interaction, -('1703601', 'Nicu Sebe', 'nicu sebe')
('1695527', 'Theo Gevers', 'theo gevers')6fa3857faba887ed048a9e355b3b8642c6aab1d8Face Recognition in Challenging Environments: +('1703601', 'Nicu Sebe', 'nicu sebe')
('1695527', 'Theo Gevers', 'theo gevers')6f3054f182c34ace890a32fdf1656b583fbc7445Article +
Age Estimation Robust to Optical and Motion +
Blurring by Deep Residual CNN +
Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro, 1-gil, Jung-gu
Received: 9 March 2018; Accepted: 10 April 2018; Published: 13 April 2018 +('31515471', 'Jeon Seong Kang', 'jeon seong kang')
('31864414', 'Chan Sik Kim', 'chan sik kim')
('29944844', 'Se Woon Cho', 'se woon cho')
('4634733', 'Kang Ryoung Park', 'kang ryoung park')Seoul 100-715, Korea; kjs2605@dgu.edu (J.S.K.); kimchsi9004@naver.com (C.S.K.); +
lyw941021@dongguk.edu (Y.W.L.); jsu319@naver.com (S.W.C.) +
* Correspondence: parkgr@dongguk.edu; Tel.: +82-10-3111-7022; Fax: +82-2-2277-8735 +6fa3857faba887ed048a9e355b3b8642c6aab1d8Face Recognition in Challenging Environments:
An Experimental and Reproducible Research
Survey ('2121764', 'Laurent El Shafey', 'laurent el shafey')6fda12c43b53c679629473806c2510d84358478fJournal of Academic and Applied Studies @@ -2532,13 +2956,23 @@
Islamic Azad University
Iran Available online @ www.academians.org
Email:a.jamshidnejad@yahoo.com +6fef65bd7287b57f0c3b36bf8e6bc987fd161b7dDeep Discriminative Model for Video +
Classification +
Center for Machine Vision and Signal Analysis (CMVS) +
University of Oulu, Finland('2014145', 'Mohammad Tavakolian', 'mohammad tavakolian')
('1751372', 'Abdenour Hadid', 'abdenour hadid')firstname.lastname@oulu.fi 6f7ce89aa3e01045fcd7f1c1635af7a09811a1fe978-1-4673-0046-9/12/$26.00 ©2012 IEEE
937
ICASSP 2012 6fe2efbcb860767f6bb271edbb48640adbd806c3SOFT BIOMETRICS: HUMAN IDENTIFICATION USING COMPARATIVE DESCRIPTIONS
Soft Biometrics; Human Identification using
Comparative Descriptions -('34386180', 'Daniel A. Reid', 'daniel a. reid')
('1727698', 'Mark S. Nixon', 'mark s. nixon')
('2093843', 'Sarah V. Stevenage', 'sarah v. stevenage')6f5151c7446552fd6a611bf6263f14e729805ec75KHHAO /7 %:0 7 +('34386180', 'Daniel A. Reid', 'daniel a. reid')
('1727698', 'Mark S. Nixon', 'mark s. nixon')
('2093843', 'Sarah V. Stevenage', 'sarah v. stevenage')6fdc0bc13f2517061eaa1364dcf853f36e1ea5aeDAISEE: Dataset for Affective States in +
E-Learning Environments +
1 Microsoft India R&D Pvt. Ltd. +
2 Department of Computer Science, IIT Hyderabad +('50178849', 'Abhay Gupta', 'abhay gupta')
('3468123', 'Richik Jaiswal', 'richik jaiswal')
('3468212', 'Sagar Adhikari', 'sagar adhikari')
('1973980', 'Vineeth Balasubramanian', 'vineeth balasubramanian')abhgup@microsoft.com +
{cs12b1032, cs12b1034, vineethnb}@iith.ac.in +6f5151c7446552fd6a611bf6263f14e729805ec75KHHAO /7 %:0 7
)>IJH=?J 9EJDE JDA ?JANJ B=?A ANFHAIIE ?=IIE?=JE KIEC JDA
FH>=>EEJEAI JD=J A=?D A B IALAH= ?O ??KHHEC )7 CHKFI EI
?=IIIAF=H=>EEJO MAECDJEC @@ -2575,7 +3009,11 @@
D=I >AA BK@ DMALAH JD=J ?F=H=>A H >AJJAH HAIKJI ?= >A >J=EA@ >O
J=EC = HA DEIJE? =FFH=?D J BA=JKHA ANJH=?JE KIEC AJD@I IK?D =I
?F=HA JM IK?D AJD@I =AO 2+) " =@ ?= >E=HO F=JJAH *2 -03d9ccce3e1b4d42d234dba1856a9e1b28977640036c41d67b49e5b0a578a401eb31e5f46b3624e0The Tower Game Dataset: A Multimodal Dataset +03c56c176ec6377dddb6a96c7b2e95408db65a7aA Novel Geometric Framework on Gram Matrix +
Trajectories for Human Behavior Understanding +('46243486', 'Anis Kacem', 'anis kacem')
('2909056', 'Mohamed Daoudi', 'mohamed daoudi')
('2125606', 'Boulbaba Ben Amor', 'boulbaba ben amor')
('2507859', 'Stefano Berretti', 'stefano berretti')03d9ccce3e1b4d42d234dba1856a9e1b289776400322e69172f54b95ae6a90eb3af91d3daa5e36eaFace Classification using Adjusted Histogram in +
Grayscale +036c41d67b49e5b0a578a401eb31e5f46b3624e0The Tower Game Dataset: A Multimodal Dataset
for Analyzing Social Interaction Predicates
∗ SRI International
University of California, Santa Cruz
University of California, Berkeley('1955011', 'David A. Salter', 'david a. salter')
('1860011', 'Amir Tamrakar', 'amir tamrakar')
('1832513', 'Behjat Siddiquie', 'behjat siddiquie')
('4599641', 'Mohamed R. Amer', 'mohamed r. amer')
('1696401', 'Ajay Divakaran', 'ajay divakaran')
('40530418', 'Brian Lande', 'brian lande')
('2108704', 'Darius Mehri', 'darius mehri')Email: {david.salter, amir.tamrakar, behjat.siddiquie, mohamed.amer, ajay.divakaran}@sri.com @@ -2586,7 +3024,9 @@
Cortexica Vision Systems Limited ('39599054', 'Biswa Sengupta', 'biswa sengupta')
('29742002', 'Yu Qian', 'yu qian')b.sengupta@imperial.ac.uk 03f7041515d8a6dcb9170763d4f6debd50202c2bClustering Millions of Faces by Identity -('40653304', 'Charles Otto', 'charles otto')
('7496032', 'Dayong Wang', 'dayong wang')
('40217643', 'Anil K. Jain', 'anil k. jain')03b99f5abe0e977ff4c902412c5cb832977cf18eCROWLEY AND ZISSERMAN: OF GODS AND GOATS +('40653304', 'Charles Otto', 'charles otto')
('7496032', 'Dayong Wang', 'dayong wang')
('40217643', 'Anil K. Jain', 'anil k. jain')03ce2ff688f9b588b6f264ca79c6857f0d80ceaeAttention Clusters: Purely Attention Based +
Local Feature Integration for Video Classification +
Tsinghua University, 2Rutgers University, 3Massachusetts Institute of Technology, 4Baidu IDL('1716690', 'Xiang Long', 'xiang long')
('2551285', 'Chuang Gan', 'chuang gan')
('1732213', 'Gerard de Melo', 'gerard de melo')
('3045089', 'Jiajun Wu', 'jiajun wu')
('48033101', 'Xiao Liu', 'xiao liu')
('35247507', 'Shilei Wen', 'shilei wen')03b99f5abe0e977ff4c902412c5cb832977cf18eCROWLEY AND ZISSERMAN: OF GODS AND GOATS
Of Gods and Goats: Weakly Supervised
Learning of Figurative Art
Elliot J. Crowley @@ -2697,7 +3137,17 @@ 03f98c175b4230960ac347b1100fbfc10c100d0cSupervised Descent Method and its Applications to Face Alignment
The Robotics Institute, Carnegie Mellon University, Pittsburgh PA('3182065', 'Xuehan Xiong', 'xuehan xiong')
('1707876', 'Fernando De la Torre', 'fernando de la torre')xxiong@andrew.cmu.edu
ftorre@cs.cmu.edu -03264e2e2709d06059dd79582a5cc791cbef94b1Convolutional Neural Networks for Facial Attribute-based Active Authentication +032825000c03b8ab4c207e1af4daeb1f225eb025J. Appl. Environ. Biol. Sci., 7(10)159-164, 2017 +
ISSN: 2090-4274 +
© 2017, TextRoad Publication +
Journal of Applied Environmental +
and Biological Sciences +
www.textroad.com +
A Novel Approach for Human Face Detection in Color Images Using Skin +
Color and Golden Ratio +
Bacha Khan University, Charsadda, KPK, Pakistan
Abdul WaliKhan University, Mardan, KPK, Pakistan
Received: May 9, 2017 +
Accepted: August 2, 2017 +('12144785', 'Faizan Ullah', 'faizan ullah')
('49669073', 'Dilawar Shah', 'dilawar shah')
('46463663', 'Sabir Shah', 'sabir shah')
('47160013', 'Abdus Salam', 'abdus salam')
('12579194', 'Shujaat Ali', 'shujaat ali')03264e2e2709d06059dd79582a5cc791cbef94b1Convolutional Neural Networks for Facial Attribute-based Active Authentication
On Mobile Devices
University of Maryland, College Park
University of Maryland, College Park
MD, USA
MD, USA @@ -2837,7 +3287,38 @@
Ben Amar1
Research Groups on Intelligent Machines, University of Sfax, Sfax 3038, Tunisia
University of Houston, Houston, TX 77204, USA('2791150', 'Mohamed Anouar Borgi', 'mohamed anouar borgi')
('8847309', 'Demetrio Labate', 'demetrio labate'){anoir.borgi@ieee.org ; dlabate@math.uh.edu ;
maher.elarbi@gmail.com; chokri.benamar@ieee.org} -03baf00a3d00887dd7c828c333d4a29f3aacd5f5Entropy Based Feature Selection for 3D Facial +03ac1c694bc84a27621da6bfe73ea9f7210c6d45Chapter 1 +
Introduction to information security +
foundations and applications +
1.1 Background +
Information security has extended to include several research directions like user +
authentication 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 +
an 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 +
computing 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 +
new design approaches consider security-in-design process where security is consid- +
ered at the early phase of the design process. The new designed systems should be +
well protected against the available security attacks. Having new systems such as IoT +
or healthcare without enough security may lead to a leakage of sensitive data and, in +
some cases, life threatening situations. +
Taking the social aspect into account, security education is a vital need for both +
practitioners and system users [6]. Users’ misbehaviour due to a lack of security +
knowledge is the weakest point in the system security chain. The users’ misbehaviour +
is considered as a security vulnerability that may be exploited for launching security +
attacks. A successful security attack such as distributed denial-of-service attack will +
impose incident recovery cost in addition to the downtime cost. +
Electrical and Space Engineering, Lule University of Technology
Sweden +
Faculty of Engineering, Al Azhar University, Qena, Egypt('4073409', 'Ali Ismail Awad', 'ali ismail awad')03baf00a3d00887dd7c828c333d4a29f3aacd5f5Entropy Based Feature Selection for 3D Facial
Expression Recognition
Submitted to the
Institute of Graduate Studies and Research
in partial fulfillment of the requirements for the Degree of @@ -3020,7 +3501,128 @@ 03701e66eda54d5ab1dc36a3a6d165389be0ce79179
Improved Principal Component Regression for Face
Recognition Under Illumination Variations -('1776127', 'Shih-Ming Huang', 'shih-ming huang')
('1749263', 'Jar-Ferr Yang', 'jar-ferr yang')9b318098f3660b453fbdb7a579778ab5e9118c4c3931 +('1776127', 'Shih-Ming Huang', 'shih-ming huang')
('1749263', 'Jar-Ferr Yang', 'jar-ferr yang')03fe3d031afdcddf38e5cc0d908b734884542eebDOI: http://dx.doi.org/10.14236/ewic/EVA2017.60 +
Engagement with Artificial Intelligence +
through Natural Interaction Models +
Sara (Salevati) Feldman +
Simon Fraser University
Vancouver, Canada +
Simon Fraser University
Vancouver, Canada +
Simon Fraser University
Vancouver, Canada +
As Artificial Intelligence (AI) systems become more ubiquitous, what user experience design +
paradigms will be used by humans to impart their needs and intents to an AI system, in order to +
engage in a more social interaction? In our work, we look mainly at expression and creativity +
based systems, where the AI both attempts to model or understand/assist in processes of human +
expression and creativity. We therefore have designed and implemented a prototype system with +
more natural interaction modes for engagement with AI as well as other human computer +
interaction (HCI) where a more open natural communication stream is beneficial. Our proposed +
conversational agent system makes use of the affective signals from the gestural behaviour of the +
user and the semantic information from the speech input in order to generate a personalised, +
human-like conversation that is expressed in the visual and conversational output of the 3D virtual +
avatar system. We describe our system and two application spaces we are using it in – a care +
advisor / assistant for the elderly and an interactive creative assistant for uses to produce art +
forms. +
Artificial Intelligence. Natural user interfaces. Voice systems. Expression systems. ChatBots. +
1. INTRODUCTION +
is +
for +
way +
there +
sensor +
natural +
devices, +
understand +
requirement +
to +
the human +
Due to the increase of natural user interfaces and +
untethered +
a +
corresponding +
for computational +
models that can utilise interactive and affective +
user data in order to understand and emulate a +
more +
conversational +
communication. From an emulation standpoint, it is +
the mechanisms +
important +
underlying +
to human multilayered +
semantic communication to achieve a more natural +
user experience. Humans tend to make use of +
gestures and expressions +
in a conversational +
setting in addition to the linguistic components that +
allow them to express more than the semantics of +
is usually +
the utterances. This phenomenon +
automated +
current +
disregarded +
to +
conversational +
due +
being +
computationally demanding and +
requiring a +
cognitive component to be able to model the +
complexity of the additional signals. With the +
advances in the current technology we are now +
closer to achieve more natural-like conversational +
systems. Gesture capture and recognition systems +
for video and sound input can be combined with +
output systems such as Artificial Intelligence (AI) +
based conversational +
tools and 3D modelling +
systems +
the +
in +
© Feldman et al. Published by +
BCS Learning and Development Ltd. +
Proceedings of Proceedings of EVA London 2017, UK +
296 +
to +
include +
in order +
systems +
to achieve human-level +
meaningful communication. This may allow the +
interaction to be more intuitive, open and fluent that +
can be more helpful in certain situations. In this +
work, we attempt +
the affective +
components from these input signals in order to +
generate a compatible and personalised character +
that can reflect some human-like qualities. +
Given +
these goals, we overview our 3D +
conversational avatar system and describe its use +
in our two application spaces, stressing its use +
where AI systems are involved. Our first application +
space is CareAdvisor, for maintaining active and +
healthy aging in older adults through a multi- +
modular Personalised Virtual Coaching system. +
Here the natural communication system is better +
suited for the elderly, who are technologically less +
experienced, +
non- +
confrontationally and as an assistant conduit to +
health data from other less conversational devices. +
Our second application space is in the interactive +
art exhibition area, where our avatar system is able +
to converse with users in a more open way, +
compared to say forms and input systems, on +
issues of art and creativity. This allows for more +
open, +
to an +
intuitive conversation +
especially when +
leading +
used +('22588208', 'Ozge Nilay Yalcin', 'ozge nilay yalcin')
('1700040', 'Steve DiPaola', 'steve dipaola')sara_salevati@sfu.ca +
oyalcin@sfu.ca +
sdipaola@sfu.ca +9b318098f3660b453fbdb7a579778ab5e9118c4c3931
Joint Patch and Multi-label Learning for Facial
Action Unit and Holistic Expression Recognition
classifiers without @@ -3034,6 +3636,13 @@
doi: 10.1049/iet-bmt.2015.0008
www.ietdl.org
North Dakota State University, Fargo, ND 58108-6050, USA
Faculty of Computer Science, Mathematics, and Engineering, University of Twente, Enschede, Netherlands('3001880', 'Zahid Mahmood', 'zahid mahmood')
('1798087', 'Tauseef Ali', 'tauseef ali')✉ E-mail: zahid.mahmood@ndsu.edu +9bd35145c48ce172b80da80130ba310811a44051Face Detection with End-to-End Integration of a +
ConvNet and a 3D Model +
1Nat’l Engineering Laboratory for Video Technology, +
Key Laboratory of Machine Perception (MoE), +
Cooperative Medianet Innovation Center, Shanghai +
Sch l of EECS, Peking University, Beijing, 100871, China
2Department of ECE and the Visual Narrative Cluster, +
North Carolina State University, Raleigh, USA('3422021', 'Yunzhu Li', 'yunzhu li')
('3423002', 'Benyuan Sun', 'benyuan sun')
('47353858', 'Tianfu Wu', 'tianfu wu')
('1717863', 'Yizhou Wang', 'yizhou wang'){leo.liyunzhu, sunbenyuan, Yizhou.Wang}@pku.edu.cn, tianfu wu@ncsu.edu 9b000ccc04a2605f6aab867097ebf7001a52b4599b0489f2d5739213ef8c3e2e18739c4353c3a3b7Visual Data Augmentation through Learning
Imperial College London, UK
Middlesex University London, UK('34586458', 'Grigorios G. Chrysos', 'grigorios g. chrysos')
('1780393', 'Yannis Panagakis', 'yannis panagakis')
('1776444', 'Stefanos Zafeiriou', 'stefanos zafeiriou'){g.chrysos, i.panagakis, s.zafeiriou}@imperial.ac.uk 9b474d6e81e3b94e0c7881210e249689139b3e04VG-RAM Weightless Neural Networks for @@ -3076,9 +3685,22 @@ ('1699216', 'Alberto F. De Souza', 'alberto f. de souza')
('3015563', 'Claudine Badue', 'claudine badue')
('3158075', 'Felipe Pedroni', 'felipe pedroni')
('3169286', 'Hallysson Oliveira', 'hallysson oliveira')9b928c0c7f5e47b4480cb9bfdf3d5b7a29dfd493Close the Loop: Joint Blind Image Restoration and Recognition
with Sparse Representation Prior
School of Computer Science, Northwestern Polytechnical University, Xi an China
Beckman Institute, University of Illinois at Urbana-Champaign, IL USA
U.S. Army Research Laboratory, 2800 Powder Mill Road, Adelphi, MD USA('40479011', 'Haichao Zhang', 'haichao zhang')
('1706007', 'Jianchao Yang', 'jianchao yang')
('1801395', 'Yanning Zhang', 'yanning zhang')
('8147588', 'Nasser M. Nasrabadi', 'nasser m. nasrabadi')
('1739208', 'Thomas S. Huang', 'thomas s. huang')‡{hczhang,jyang29,huang}@ifp.uiuc.edu †ynzhang@nwpu.edu.cn §nasser.m.nasrabadi.civ@mail.mil +9bc01fa9400c231e41e6a72ec509d76ca797207c9b2c359c36c38c289c5bacaeb5b1dd06b464f301Dense Face Alignment +
Michigan State University, MI
2Monta Vista High School, Cupertino, CA +('6797891', 'Yaojie Liu', 'yaojie liu')
('2357264', 'Amin Jourabloo', 'amin jourabloo')
('26365310', 'William Ren', 'william ren')
('1759169', 'Xiaoming Liu', 'xiaoming liu')1{liuyaoj1,jourablo,liuxm}@msu.edu, 2williamyren@gmail.com 9bcfadd22b2c84a717c56a2725971b6d49d3a804How to Detect a Loss of Attention in a Tutoring System
using Facial Expressions and Gaze Direction -('2975858', 'Mark ter Maat', 'mark ter maat')9b07084c074ba3710fee59ed749c001ae70aa408698535 CDPXXX10.1177/0963721417698535MartinezComputational Models of Face Perception +('2975858', 'Mark ter Maat', 'mark ter maat')9b1bcef8bfef0fb5eb5ea9af0b699aa0534fcecaPosition-Squeeze and Excitation Module +
for Facial Attribute Analysis +
Shanghai Key Laboratory of +
Multidimensional Information +
Processing, +
East China Normal University
200241 Shanghai, China +('36124320', 'Yan Zhang', 'yan zhang')
('7962836', 'Wanxia Shen', 'wanxia shen')
('49755228', 'Li Sun', 'li sun')
('12493943', 'Qingli Li', 'qingli li')
('36124320', 'Yan Zhang', 'yan zhang')
('7962836', 'Wanxia Shen', 'wanxia shen')
('49755228', 'Li Sun', 'li sun')
('12493943', 'Qingli Li', 'qingli li')452642781@qq.com +
51151214005@ecnu.cn +
sunli@ee.ecnu.edu.cn +
qlli@cs.ecnu.edu.cn +9b07084c074ba3710fee59ed749c001ae70aa408698535 CDPXXX10.1177/0963721417698535MartinezComputational Models of Face Perception
research-article2017
Computational Models of Face Perception
Aleix M. Martinez @@ -3092,7 +3714,10 @@
DOI: 10.1177/0963721417698535
https://doi.org/10.1177/0963721417698535
www.psychologicalscience.org/CDPS -9b246c88a0435fd9f6d10dc88f47a1944dd8f89ePICODES: Learning a Compact Code for +9be653e1bc15ef487d7f93aad02f3c9552f3ee4aComputer Vision for Head Pose Estimation: +
Review of a Competition +
Tampere University of Technology, Finland
University of Paderborn, Germany
3 Zorgon, The Netherlands +('1847889', 'Heikki Huttunen', 'heikki huttunen')
('40394658', 'Ke Chen', 'ke chen')
('2364638', 'Abhishek Thakur', 'abhishek thakur')
('2558923', 'Artus Krohn-Grimberghe', 'artus krohn-grimberghe')
('2300445', 'Oguzhan Gencoglu', 'oguzhan gencoglu')
('3328835', 'Xingyang Ni', 'xingyang ni')
('2067035', 'Mohammed Al-Musawi', 'mohammed al-musawi')
('40448210', 'Lei Xu', 'lei xu')
('3152947', 'Hendrik Jacob van Veen', 'hendrik jacob van veen')9b246c88a0435fd9f6d10dc88f47a1944dd8f89ePICODES: Learning a Compact Code for
Novel-Category Recognition
Dartmouth College
Hanover, NH, U.S.A.
Andrew Fitzgibbon @@ -3107,7 +3732,9 @@
Contour Detection
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 -9b93406f3678cf0f16451140ea18be04784faeeeA Bayesian Approach to Alignment-Based +9bac481dc4171aa2d847feac546c9f7299cc5aa0Matrix Product State for Higher-Order Tensor +
Compression and Classification +('2852180', 'Johann A. Bengua', 'johann a. bengua')
('2839912', 'Ho N. Phien', 'ho n. phien')
('1834451', 'Minh N. Do', 'minh n. do')9b93406f3678cf0f16451140ea18be04784faeeeA Bayesian Approach to Alignment-Based
Image Hallucination
University of Central Florida
2 Microsoft Research New England ('1802944', 'Marshall F. Tappen', 'marshall f. tappen')
('1681442', 'Ce Liu', 'ce liu')mtappen@eecs.ucf.edu @@ -3117,6 +3744,17 @@ ('3057167', 'Renjie Liu', 'renjie liu')
('36485086', 'Ruofei Du', 'ruofei du')
('40371477', 'Bao-Liang Lu', 'bao-liang lu')9b6d0b3fbf7d07a7bb0d86290f97058aa6153179NII, Japan at the first THUMOS Workshop 2013
National Institute of Informatics
2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo, Japan 101-8430 ('39814149', 'Sang Phan', 'sang phan')
('1802416', 'Duy-Dinh Le', 'duy-dinh le')
('40693818', 'Shin’ichi Satoh', 'shin’ichi satoh'){plsang,ledduy,satoh}@nii.ac.jp +9b684e2e2bb43862f69b12c6be94db0e7a756187Differentiating Objects by Motion: +
Joint Detection and Tracking of Small Flying Objects +
The University of Tokyo
CSIRO-Data61 +
Australian National University
The University of Tokyo
Figure 1: Importance of multi-frame information for recognizing apparently small flying objects (birds in these examples). +
While visual features in single frames are vague and limited, multi-frame information, including deformation and pose
changes, provides better clues with which to recognize birds. To extract such useful motion patterns, tracking is necessary for +
compensating translation of objects, but the tracking itself is a challenge due to the limited visual information. The blue boxes +
are birds tracked by our method that utilizes multi-frame representation for detection, while the red boxes are the results of a +
single-frame handcrafted-feature-based tracker [11] , which tends to fail when tracking small objects. +('1890560', 'Ryota Yoshihashi', 'ryota yoshihashi')
('38621343', 'Tu Tuan Trinh', 'tu tuan trinh')
('48727803', 'Rei Kawakami', 'rei kawakami')
('2941564', 'Shaodi You', 'shaodi you')
('33313329', 'Makoto Iida', 'makoto iida')
('48795689', 'Takeshi Naemura', 'takeshi naemura'){yoshi, tu, rei, naemura}@hc.ic.i.u-tokyo.ac.jp +
iida@ilab.eco.rcast.u-tokyo.ac.jp +
shaodi.you@data61.csiro.au 9e8637a5419fec97f162153569ec4fc53579c21eSegmentation and Normalization of Human Ears
using Cascaded Pose Regression
University of Applied Sciences Darmstadt - CASED
Haardtring 100, @@ -3124,6 +3762,11 @@
http://www.h-da.de ('1742085', 'Christoph Busch', 'christoph busch')anika.pflug@cased.de
christoph.busch@hig.no +9ea223c070ec9a00f4cb5ca0de35d098eb9a8e32Exploring Temporal Preservation Networks for Precise Temporal Action +
Localization +
National Laboratory for Parallel and Distributed Processing, +
National University of Defense Technology
Changsha, China +('2352864', 'Ke Yang', 'ke yang')
('2292038', 'Peng Qiao', 'peng qiao')
('1718853', 'Dongsheng Li', 'dongsheng li')
('1893776', 'Shaohe Lv', 'shaohe lv')
('1791001', 'Yong Dou', 'yong dou'){yangke13,pengqiao,dongshengli,yongdou,shaohelv}@nudt.edu.cn 9e4b052844d154c3431120ec27e78813b637b4fcJournal of AI and Data Mining
Vol. 2, No .1, 2014, 33-38.
Local gradient pattern - A novel feature representation for facial @@ -3184,7 +3827,9 @@ ('4241648', 'M. Saquib Sarfraz', 'm. saquib sarfraz')
('6262445', 'Muhammad Adnan Siddique', 'muhammad adnan siddique')
('1742325', 'Rainer Stiefelhagen', 'rainer stiefelhagen')saquib.sarfraz@kit.edu
siddique@ifu.baug.ethz.ch
rainer.stiefelhagen@kit.edu -9e8d87dc5d8a6dd832716a3f358c1cdbfa97074cWhat Makes an Image Popular? +9e182e0cd9d70f876f1be7652c69373bcdf37fb4Talking Face Generation by Adversarially +
Disentangled Audio-Visual Representation +
The Chinese University of Hong Kong('40576774', 'Hang Zhou', 'hang zhou')
('1715752', 'Yu Liu', 'yu liu')
('3243969', 'Ziwei Liu', 'ziwei liu')
('47571885', 'Ping Luo', 'ping luo')
('31843833', 'Xiaogang Wang', 'xiaogang wang')9e8d87dc5d8a6dd832716a3f358c1cdbfa97074cWhat Makes an Image Popular?
Massachusetts Institute
of Technology
eBay Research Labs
DigitalGlobe ('2556428', 'Aditya Khosla', 'aditya khosla')
('2541992', 'Atish Das Sarma', 'atish das sarma')
('37164887', 'Raffay Hamid', 'raffay hamid')khosla@csail.mit.edu @@ -3193,7 +3838,11 @@ 9e5c2d85a1caed701b68ddf6f239f3ff941bb707044d9a8c61383312cdafbcc44b9d00d650b21c70300 Faces in-the-Wild Challenge: The first facial landmark localization
Challenge
Imperial College London, UK
School of Computer Science, University of Lincoln, U.K
EEMCS, University of Twente, The Netherlands('3320415', 'Christos Sagonas', 'christos sagonas')
('2610880', 'Georgios Tzimiropoulos', 'georgios tzimiropoulos')
('1776444', 'Stefanos Zafeiriou', 'stefanos zafeiriou')
('1694605', 'Maja Pantic', 'maja pantic'){c.sagonas, gt204, s.zafeiriou, m.pantic}@imperial.ac.uk -04bb3fa0824d255b01e9db4946ead9f856cc0b5904f0292d9a062634623516edd01d92595f03bd3fDistribution-based Iterative Pairwise Classification of +04bb3fa0824d255b01e9db4946ead9f856cc0b59040dc119d5ca9ea3d5fc39953a91ec507ed8cc5dNoname manuscript No. +
(will be inserted by the editor) +
Large-scale Bisample Learning on ID vs. Spot Face Recognition +
Received: date / Accepted: date +('8362374', 'Xiangyu Zhu', 'xiangyu zhu')
('34679741', 'Stan Z. Li', 'stan z. li')04f0292d9a062634623516edd01d92595f03bd3fDistribution-based Iterative Pairwise Classification of
Emotions in the Wild Using LGBP-TOP
The University of Nottingham
Mised Reality Lab
Anıl Yüce @@ -3211,6 +3860,11 @@
Using DCT for Face Detection
Technical University of Ostrava, FEECS
17. listopadu 15, 708 33 Ostrava-Poruba, Czech Republic ('2467747', 'Radovan Fusek', 'radovan fusek')
('2557877', 'Eduard Sojka', 'eduard sojka'){radovan.fusek,eduard.sojka,karel.mozdren,milan.surkala}@vsb.cz +04b851f25d6d49e61a528606953e11cfac7df2b2Optical Flow Guided Feature: A Fast and Robust Motion Representation for +
Video Action Recognition +
The University of Sydney 2SenseTime Research 3The Chinese University of Hong Kong('1837024', 'Shuyang Sun', 'shuyang sun')
('1874900', 'Zhanghui Kuang', 'zhanghui kuang')
('37145669', 'Lu Sheng', 'lu sheng')
('3001348', 'Wanli Ouyang', 'wanli ouyang')
('1726357', 'Wei Zhang', 'wei zhang'){shuyang.sun wanli.ouyang}@sydney.edu.au +
{wayne.zhang kuangzhanghui}@sensetime.com +
lsheng@ee.cuhk.edu.hk 04522dc16114c88dfb0ebd3b95050fdbd4193b90Appears in 2nd Canadian Conference on Computer and Robot Vision, Victoria, Canada, 2005.
Minimum Bayes Error Features for Visual Recognition by Sequential Feature
Selection and Extraction @@ -3268,6 +3922,19 @@
cropped face, we pass the cropped face on the Deep Multi-
for ('27343041', 'Ayesha Gurnani', 'ayesha gurnani')
('23922616', 'Vandit Gajjar', 'vandit gajjar')
('22239413', 'Viraj Mavani', 'viraj mavani')
('26425477', 'Yash Khandhediya', 'yash khandhediya'){gurnani.ayesha.52, gajjar.vandit.381, mavani.viraj.604, khandhediya.yash.364}@ldce.ac.in +043efe5f465704ced8d71a067d2b9d5aa5b59c29EGGER ET AL.: OCCLUSION-AWARE 3D MORPHABLE FACE MODELS +
Occlusion-aware 3D Morphable Face Models +
Department of Mathematics and +
Computer Science +
University of Basel
Basel Switzerland +
http://gravis.cs.unibas.ch +
Andreas Morel-Forster +('34460642', 'Bernhard Egger', 'bernhard egger')
('49462138', 'Andreas Schneider', 'andreas schneider')
('39550224', 'Clemens Blumer', 'clemens blumer')
('1987368', 'Sandro Schönborn', 'sandro schönborn')
('1687079', 'Thomas Vetter', 'thomas vetter')bernhard.egger@unibas.ch +
andreas.schneider@unibas.ch +
clemens.blumer@unibas.ch +
andreas.forster@unibas.ch +
sandro.schoenborn@unibas.ch +
thomas.vetter@unibas.ch 044ba70e6744e80c6a09fa63ed6822ae241386f2TO APPEAR IN AUTONOMOUS ROBOTS, SPECIAL ISSUE IN LEARNING FOR HUMAN-ROBOT COLLABORATION
Early Prediction for Physical Human Robot
Collaboration in the Operating Room @@ -3292,7 +3959,17 @@ ('1707922', 'Hongli Liu', 'hongli liu')04250e037dce3a438d8f49a4400566457190f4e20431e8a01bae556c0d8b2b431e334f7395dd803aLearning Localized Perceptual Similarity Metrics for Interactive Categorization
Google Inc.
google.com -('2367820', 'Catherine Wah', 'catherine wah')04616814f1aabe3799f8ab67101fbaf9fd115ae4UNIVERSIT´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`ese04c2cda00e5536f4b1508cbd80041e9552880e67Hipster Wars: Discovering Elements +('2367820', 'Catherine Wah', 'catherine wah')04b4c779b43b830220bf938223f685d1057368e9Video retrieval based on deep convolutional +
neural network +
Yajiao Dong +
School of Information and Electronics, +
Beijing Institution of Technology, Beijing, China +
Jianguo Li +
School of Information and Electronics, +
Beijing Institution of Technology, Beijing, China +yajiaodong@bit.edu.cn +
jianguoli@bit.edu.cn +04616814f1aabe3799f8ab67101fbaf9fd115ae4UNIVERSIT´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`ese04c2cda00e5536f4b1508cbd80041e9552880e67Hipster Wars: Discovering Elements
of Fashion Styles
University of North Carolina at Chapel Hill, NC, USA
Tohoku University, Japan('1772294', 'M. Hadi Kiapour', 'm. hadi kiapour')
('1721910', 'Kota Yamaguchi', 'kota yamaguchi')
('39668247', 'Alexander C. Berg', 'alexander c. berg')
('1685538', 'Tamara L. Berg', 'tamara l. berg'){hadi,aberg,tlberg}@cs.unc.edu
kyamagu@vision.is.tohoku.ac.jp @@ -3325,11 +4002,34 @@
´emanant des ´etablissements d’enseignement et de
recherche fran¸cais ou ´etrangers, des laboratoires
publics ou priv´es. -('3307172', 'Antoine Deleforge', 'antoine deleforge')
('1794229', 'Radu Horaud', 'radu horaud')
('2159538', 'Yoav Y. Schechner', 'yoav y. schechner')
('1780746', 'Laurent Girin', 'laurent girin')
('3307172', 'Antoine Deleforge', 'antoine deleforge')
('1794229', 'Radu Horaud', 'radu horaud')
('2159538', 'Yoav Y. Schechner', 'yoav y. schechner')
('1780746', 'Laurent Girin', 'laurent girin')046865a5f822346c77e2865668ec014ec3282033Discovering Informative Social Subgraphs and Predicting +('3307172', 'Antoine Deleforge', 'antoine deleforge')
('1794229', 'Radu Horaud', 'radu horaud')
('2159538', 'Yoav Y. Schechner', 'yoav y. schechner')
('1780746', 'Laurent Girin', 'laurent girin')
('3307172', 'Antoine Deleforge', 'antoine deleforge')
('1794229', 'Radu Horaud', 'radu horaud')
('2159538', 'Yoav Y. Schechner', 'yoav y. schechner')
('1780746', 'Laurent Girin', 'laurent girin')04317e63c08e7888cef480fe79f12d3c255c5b00Face 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, +
2016, 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
copyright 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 +
Download date:12. Sep. 2018 +Research Portal that you believe breaches copyright or violates any law, please contact openaccess@qub.ac.uk. +046865a5f822346c77e2865668ec014ec3282033Discovering Informative Social Subgraphs and Predicting
Pairwise Relationships from Group Photos
National Taiwan University, Taipei, Taiwan
†Academia Sinica, Taipei, Taiwan ('35081710', 'Yan-Ying Chen', 'yan-ying chen')
('1716836', 'Winston H. Hsu', 'winston h. hsu')
('1704678', 'Hong-Yuan Mark Liao', 'hong-yuan mark liao')yanying@cmlab.csie.ntu.edu.tw, winston@csie.ntu.edu.tw, liao@iis.sinica.edu.tw -0470b0ab569fac5bbe385fa5565036739d4c37f8Automatic Face Naming with Caption-based Supervision +047bb1b1bd1f19b6c8d7ee7d0324d5ecd1a3efffUnsupervised Training for 3D Morphable Model Regression +
Princeton University
2Google Research +
3MIT CSAIL +('32627314', 'Kyle Genova', 'kyle genova')
('39578349', 'Forrester Cole', 'forrester cole')0470b0ab569fac5bbe385fa5565036739d4c37f8Automatic Face Naming with Caption-based Supervision
To cite this version:
with Caption-based Supervision. CVPR 2008 - IEEE Conference on Computer Vision
Pattern Recognition, @@ -3370,7 +4070,7 @@
Max Planck Institute f ur biologische Kybernetik
Spemannstr. 38, D-72076 T¨ubingen, Germany
http://www.kyb.tuebingen.mpg.de/ ('1808255', 'Kwang In Kim', 'kwang in kim')
('30541601', 'Matthias O. Franz', 'matthias o. franz'){kimki, mof, bs}@tuebingen.mpg.de -6a184f111d26787703f05ce1507eef5705fdda836a16b91b2db0a3164f62bfd956530a4206b23feaA Method for Real-Time Eye Blink Detection and Its Application +6ad107c08ac018bfc6ab31ec92c8a4b234f67d496a184f111d26787703f05ce1507eef5705fdda836a16b91b2db0a3164f62bfd956530a4206b23feaA Method for Real-Time Eye Blink Detection and Its Application
Mahidol Wittayanusorn School
Puttamonton, Nakornpatom 73170, Thailand Chinnawat.Deva@gmail.com @@ -3399,6 +4099,10 @@
rrji@xmu.edu.cn
dmeyer@math.ucsd.edu
jsmith@us.ibm.com +6a52e6fce541126ff429f3c6d573bc774f5b8d89Role of Facial Emotion in Social Correlation +
Department of Computer Science and Engineering +
Nagoya Institute of Technology, Gokiso, Showa-ku, Nagoya, 466-8555 Japan('2159044', 'Pankaj Mishra', 'pankaj mishra')
('47865262', 'Takayuki Ito', 'takayuki ito'){pankaj.mishra, rafik}@itolab.nitech.ac.jp, +
ito.takayuki@nitech.ac.jp 6a5fe819d2b72b6ca6565a0de117c2b3be448b02Supervised and Projected Sparse Coding for Image Classification
Computer Science and Engineering Department
University of Texas at Arlington
Arlington,TX,76019 @@ -3429,6 +4133,9 @@
This Thesis is brought to you for free and open access by the Dietrich College of Humanities and Social Sciences at Research Showcase @ CMU. It has
been accepted for inclusion in Dietrich College Honors Theses by an authorized administrator of Research Showcase @ CMU. For more information,
please contact research-showcase@andrew.cmu.edu. +6a4419ce2338ea30a570cf45624741b754fa52cbStatistical transformer networks: learning shape +
and appearance models via self supervision +
University of York('39180407', 'Anil Bas', 'anil bas')
('1687021', 'William A. P. Smith', 'william a. p. smith'){ab1792,william.smith}@york.ac.uk 6af65e2a1eba6bd62843e7bf717b4ccc91bce2b8A New Weighted Sparse Representation Based
on MSLBP and Its Application to Face Recognition
School of IoT Engineering, Jiangnan University, Wuxi 214122, China('1823451', 'He-Feng Yin', 'he-feng yin')
('37020604', 'Xiao-Jun Wu', 'xiao-jun wu')yinhefeng@126.com, wu_xiaojun@yahoo.com.cn @@ -3477,7 +4184,13 @@
Deep Belief Networks ∗
Instituto de Sistemas e Rob´otica
Instituto Superior T´ecnico, Portugal -('3259175', 'Jacinto C. Nascimento', 'jacinto c. nascimento')6a4ebd91c4d380e21da0efb2dee276897f56467aHOG ACTIVE APPEARANCE MODELS +('3259175', 'Jacinto C. Nascimento', 'jacinto c. nascimento')6a2ac4f831bd0f67db45e7d3cdaeaaa075e7180aExcitation Dropout: +
Encouraging Plasticity in Deep Neural Networks +
1Pattern Analysis & Computer Vision (PAVIS), Istituto Italiano di Tecnologia +
Boston University
3Adobe Research +
University of Verona('40063519', 'Andrea Zunino', 'andrea zunino')
('3298267', 'Sarah Adel Bargal', 'sarah adel bargal')
('2322579', 'Pietro Morerio', 'pietro morerio')
('1701293', 'Jianming Zhang', 'jianming zhang')
('1749590', 'Stan Sclaroff', 'stan sclaroff')
('1727204', 'Vittorio Murino', 'vittorio murino'){andrea.zunino,vittorio.murino}@iit.it, +
{sbargal,sclaroff}@bu.edu, jianmzha@adobe.com +6a4ebd91c4d380e21da0efb2dee276897f56467aHOG ACTIVE APPEARANCE MODELS
cid:2)Imperial College London, U.K
University of Lincoln, School of Computer Science, U.K('2788012', 'Epameinondas Antonakos', 'epameinondas antonakos')
('2575567', 'Joan Alabort-i-Medina', 'joan alabort-i-medina')
('2610880', 'Georgios Tzimiropoulos', 'georgios tzimiropoulos')
('1776444', 'Stefanos Zafeiriou', 'stefanos zafeiriou')6a1beb34a2dfcdf36ae3c16811f1aef6e64abff26a7e464464f70afea78552c8386f4d2763ea1d9cReview Article
International Journal of Current Engineering and Technology
E-ISSN 2277 – 4106, P-ISSN 2347 - 5161 @@ -3568,7 +4281,9 @@ ('3469125', 'Congzheng Song', 'congzheng song')
('1723945', 'Vitaly Shmatikov', 'vitaly shmatikov')
('1707461', 'Thomas Ristenpart', 'thomas ristenpart')cs2296@cornell.edu
ristenpart@cornell.edu
shmat@cs.cornell.edu -324f39fb5673ec2296d90142cf9a909e595d82cfHindawi Publishing Corporation +3294e27356c3b1063595885a6d731d625b15505aIllumination Face Spaces are Idiosyncratic +
2, H. Kley1, C. Peterson1 ∗ +
Colorado State University, Fort Collins, CO 80523, USA('2640182', 'Jen-Mei Chang', 'jen-mei chang')324f39fb5673ec2296d90142cf9a909e595d82cfHindawi Publishing Corporation
Mathematical Problems in Engineering
Volume 2011, Article ID 864540, 15 pages
doi:10.1155/2011/864540 @@ -3612,7 +4327,10 @@
Entropy-weighted feature-fusion method
for head-pose estimation
Open Access -('40579241', 'Kang Liu', 'kang liu')
('2076553', 'Xu Qian', 'xu qian')32b8c9fd4e3f44c371960eb0074b42515f318ee732575ffa69d85bbc6aef5b21d73e809b37bf376d-)5741/ *1-641+ 5)2- 37)16; 1 6-45 . *1-641+ 1.4)61 +('40579241', 'Kang Liu', 'kang liu')
('2076553', 'Xu Qian', 'xu qian')3240c9359061edf7a06bfeb7cc20c103a65904c2PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise +
R-FCN +
Columbia University, National University of Singapore('5462268', 'Hanwang Zhang', 'hanwang zhang')
('26538630', 'Zawlin Kyaw', 'zawlin kyaw')
('46380822', 'Jinyang Yu', 'jinyang yu')
('9546964', 'Shih-Fu Chang', 'shih-fu chang'){hanwangzhang, kzl.zawlin, yjy941124}@gmail.com; shih.fu.chang@columbia.edu +32b8c9fd4e3f44c371960eb0074b42515f318ee732575ffa69d85bbc6aef5b21d73e809b37bf376d-)5741/ *1-641+ 5)2- 37)16; 1 6-45 . *1-641+ 1.4)61
7ELAHIEJO B JJ=M=
)*564)+6
IKHA L=HE=JEI E >EAJHE? I=FA GK=EJO 9A >ACE MEJD @@ -3766,7 +4484,9 @@
Representation for Face Recognition with
Margin Distribution Optimization
Biometric Research Center
The Hong Kong Polytechnic University
School of Computer Science and Technology, Tianjin University('2873638', 'Pengfei Zhu', 'pengfei zhu')
('36685537', 'Lei Zhang', 'lei zhang')
('1688792', 'Qinghua Hu', 'qinghua hu'){cspzhu,cslzhang}@comp.polyu.edu.hk -350da18d8f7455b0e2920bc4ac228764f8fac292From: AAAI Technical Report SS-03-08. Compilation copyright © 2003, AAAI (www.aaai.org). All rights reserved. +352d61eb66b053ae5689bd194840fd5d33f0e9c0Analysis Dictionary Learning based +
Classification: Structure for Robustness +('49501811', 'Wen Tang', 'wen tang')
('1733181', 'Ashkan Panahi', 'ashkan panahi')
('1769928', 'Hamid Krim', 'hamid krim')
('2622498', 'Liyi Dai', 'liyi dai')350da18d8f7455b0e2920bc4ac228764f8fac292From: AAAI Technical Report SS-03-08. Compilation copyright © 2003, AAAI (www.aaai.org). All rights reserved.
Automatic Detecting Neutral Face for Face Authentication and
Facial Expression Analysis
Exploratory Computer Vision Group @@ -3791,7 +4511,12 @@
Unconstrained Still/Video-Based Face Verification with Deep
Convolutional Neural Networks
Received: date / Accepted: date -('36407236', 'Jun-Cheng Chen', 'jun-cheng chen')
('2682056', 'Ching-Hui Chen', 'ching-hui chen')
('9215658', 'Rama Chellappa', 'rama chellappa')
('26988560', 'Rajeev Ranjan', 'rajeev ranjan')35f03f5cbcc21a9c36c84e858eeb15c5d6722309Placing Broadcast News Videos in their Social Media +('36407236', 'Jun-Cheng Chen', 'jun-cheng chen')
('2682056', 'Ching-Hui Chen', 'ching-hui chen')
('9215658', 'Rama Chellappa', 'rama chellappa')
('26988560', 'Rajeev Ranjan', 'rajeev ranjan')35b1c1f2851e9ac4381ef41b4d980f398f1aad68Geometry Guided Convolutional Neural Networks for +
Self-Supervised Video Representation Learning +('2551285', 'Chuang Gan', 'chuang gan')
('40206014', 'Boqing Gong', 'boqing gong')
('2473509', 'Kun Liu', 'kun liu')
('49466491', 'Hao Su', 'hao su')
('1744254', 'Leonidas J. Guibas', 'leonidas j. guibas')351c02d4775ae95e04ab1e5dd0c758d2d80c3dddActionSnapping: Motion-based Video +
Synchronization +
Disney Research +('2893744', 'Alexander Sorkine-Hornung', 'alexander sorkine-hornung')35f03f5cbcc21a9c36c84e858eeb15c5d6722309Placing Broadcast News Videos in their Social Media
Context using Hashtags
Columbia University('2136860', 'Joseph G. Ellis', 'joseph g. ellis')
('2602265', 'Svebor Karaman', 'svebor karaman')
('1786871', 'Hongzhi Li', 'hongzhi li')
('36009509', 'Hong Bin Shim', 'hong bin shim')
('9546964', 'Shih-Fu Chang', 'shih-fu chang'){jge2105, svebor.karaman, hongzhi.li, h.shim, sc250}@columbia.edu 35e4b6c20756cd6388a3c0012b58acee14ffa604Gender Classification in Large Databases @@ -3846,7 +4571,20 @@
University of Perugia
Trento, Italy
Perugia, Italy
University of Trento
Trento, Italy -('2933565', 'Gloria Zen', 'gloria zen')
('1716310', 'Enver Sangineto', 'enver sangineto')
('40811261', 'Elisa Ricci', 'elisa ricci')
('1703601', 'Nicu Sebe', 'nicu sebe')353a89c277cca3e3e4e8c6a199ae3442cdad59b535e87e06cf19908855a16ede8c79a0d3d7687b5cStrategies for Multi-View Face Recognition for +('2933565', 'Gloria Zen', 'gloria zen')
('1716310', 'Enver Sangineto', 'enver sangineto')
('40811261', 'Elisa Ricci', 'elisa ricci')
('1703601', 'Nicu Sebe', 'nicu sebe')353a89c277cca3e3e4e8c6a199ae3442cdad59b535e0256b33212ddad2db548484c595334f15b4daAttentive Fashion Grammar Network for +
Fashion Landmark Detection and Clothing Category Classification +
Beijing Lab of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, China
University of California, Los Angeles, USA('2693875', 'Wenguan Wang', 'wenguan wang')
('2762640', 'Yuanlu Xu', 'yuanlu xu')
('34926055', 'Jianbing Shen', 'jianbing shen')
('3133970', 'Song-Chun Zhu', 'song-chun zhu')35e6f6e5f4f780508e5f58e87f9efe2b07d8a864This 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
advertising 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; +
action recognition; deep learning; long short-term memory; user-generated video, +
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8259321&isnumber=4456689 +35e87e06cf19908855a16ede8c79a0d3d7687b5cStrategies for Multi-View Face Recognition for
Identification of Human Faces: A Review
Department of Computer Science
Mahatma Gandhi Shikshan Mandal’s, @@ -3859,7 +4597,10 @@ 352110778d2cc2e7110f0bf773398812fd905eb1TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. X, NO. X, JUNE 2014
Matrix Completion for Weakly-supervised
Multi-label Image Classification -('31671904', 'Ricardo Cabral', 'ricardo cabral')
('1683568', 'Fernando De la Torre', 'fernando de la torre')
('2884203', 'Alexandre Bernardino', 'alexandre bernardino')697b0b9630213ca08a1ae1d459fabc13325bdcbb69ff40fd5ce7c3e6db95a2b63d763edd8db3a102HUMAN AGE ESTIMATION VIA GEOMETRIC AND TEXTURAL +('31671904', 'Ricardo Cabral', 'ricardo cabral')
('1683568', 'Fernando De la Torre', 'fernando de la torre')
('2884203', 'Alexandre Bernardino', 'alexandre bernardino')6964af90cf8ac336a2a55800d9c510eccc7ba8e1Temporal Relational Reasoning in Videos +
MIT CSAIL +('1804424', 'Bolei Zhou', 'bolei zhou')
('50112310', 'Alex Andonian', 'alex andonian')
('1690178', 'Antonio Torralba', 'antonio torralba'){bzhou,aandonia,oliva,torralba}@csail.mit.edu +697b0b9630213ca08a1ae1d459fabc13325bdcbb69ff40fd5ce7c3e6db95a2b63d763edd8db3a102HUMAN AGE ESTIMATION VIA GEOMETRIC AND TEXTURAL
FEATURES
Merve KILINC1 and Yusuf Sinan AKGUL2
1TUBITAK BILGEM UEKAE, Anibal Street, 41470, Gebze, Kocaeli, Turkey @@ -3867,13 +4608,22 @@
Keywords:
Age estimation:age classification:geometric features:LBP:Gabor:LGBP:cross ratio:FGNET:MORPH mkilinc@uekae.tubitak.gov.tr1, mkilinc@gyte.edu.tr2, akgul@bilmuh.gyte.edu.tr2 -69d29012d17cdf0a2e59546ccbbe46fa49afcd68Subspace clustering of dimensionality-reduced data +69adbfa7b0b886caac15ebe53b89adce390598a3Face hallucination using cascaded +
super-resolution and identity priors +
University of Ljubljana, Faculty of Electrical Engineering
University of Notre Dame
Fig. 1. Sample face hallucination results generated with the proposed method. +('3387470', 'Klemen Grm', 'klemen grm')
('2613438', 'Walter J. Scheirer', 'walter j. scheirer')69d29012d17cdf0a2e59546ccbbe46fa49afcd68Subspace clustering of dimensionality-reduced data
ETH Zurich, Switzerland ('1730683', 'Reinhard Heckel', 'reinhard heckel')
('2208878', 'Michael Tschannen', 'michael tschannen')Email: {heckel,boelcskei}@nari.ee.ethz.ch, michaelt@student.ethz.ch 69a68f9cf874c69e2232f47808016c2736b90c35Learning Deep Representation for Imbalanced Classification
The Chinese University of Hong Kong
2SenseTime Group Limited
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences('2000034', 'Chen Huang', 'chen huang')
('9263285', 'Yining Li', 'yining li')
('1741901', 'Xiaoou Tang', 'xiaoou tang'){chuang,ly015,ccloy,xtang}@ie.cuhk.edu.hk -69de532d93ad8099f4d4902c4cad28db958adfea69b18d62330711bfd7f01a45f97aaec71e9ea6a5RESEARCH ARTICLE +69de532d93ad8099f4d4902c4cad28db958adfea69a55c30c085ad1b72dd2789b3f699b2f4d3169fInternational Journal of Computer Trends and Technology (IJCTT) – Volume 34 Number 3 - April 2016 +
Automatic Happiness Strength Analysis of a +
Group of People using Facial Expressions +
Sagiri Prasanthi#1, Maddali M.V.M. Kumar*2, +
#1PG Student, #2Assistant Professor +
St. Ann s College of Engineering and Technology, Andhra Pradesh, India
is a collective concern +69b18d62330711bfd7f01a45f97aaec71e9ea6a5RESEARCH ARTICLE
M-Track: A New Software for Automated
Detection of Grooming Trajectories in Mice
State University of New York Polytechnic Institute, Utica, New York
United States of America, State University of New York Albany, Albany, New York
United States of America, State University of New York Albany, Albany
New York, United States of America @@ -3909,11 +4659,17 @@
201 Broadway, Cambridge MA
MIT Media Lab
75 Amherst St, Cambridge, MA -('1912905', 'Rohit Pandharkar', 'rohit pandharkar')
('1785066', 'Ashok Veeraraghavan', 'ashok veeraraghavan')
('1717566', 'Ramesh Raskar', 'ramesh raskar')69eb6c91788e7c359ddd3500d01fb73433ce2e65CAMGRAPH: Distributed Graph Processing for +('1912905', 'Rohit Pandharkar', 'rohit pandharkar')
('1785066', 'Ashok Veeraraghavan', 'ashok veeraraghavan')
('1717566', 'Ramesh Raskar', 'ramesh raskar')6993bca2b3471f26f2c8a47adfe444bfc7852484The Do’s and Don’ts for CNN-based Face Verification +
Carlos Castillo +
University of Maryland, College Park
UMIACS +('2068427', 'Ankan Bansal', 'ankan bansal')
('48467498', 'Rajeev Ranjan', 'rajeev ranjan')
('9215658', 'Rama Chellappa', 'rama chellappa'){ankan,carlos,rranjan1,rama}@umiacs.umd.edu +69eb6c91788e7c359ddd3500d01fb73433ce2e65CAMGRAPH: Distributed Graph Processing for
Camera Networks
College of Computing
Georgia Institute of Technology
Atlanta, GA, USA ('3427189', 'Steffen Maass', 'steffen maass')
('5540701', 'Kirak Hong', 'kirak hong')
('1751741', 'Umakishore Ramachandran', 'umakishore ramachandran')steffen.maass@gatech.edu,khong9@cc.gatech.edu,rama@cc.gatech.edu -69063f7e0a60ad6ce16a877bc8f11b59e5f7348eClass-Specific Image Deblurring +691964c43bfd282f6f4d00b8b0310c554b613e3bTemporal Hallucinating for Action Recognition with Few Still Images +
2† +
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China
The Chinese University of Hong Kong 3 SenseTime Group Limited('46696518', 'Lei Zhou', 'lei zhou')
('33427555', 'Yu Qiao', 'yu qiao')69063f7e0a60ad6ce16a877bc8f11b59e5f7348eClass-Specific Image Deblurring
2, Fatih Porikli1
The Australian National University Canberra ACT 2601, Australia
2NICTA, Locked Bag 8001, Canberra ACT 2601, Australia ('33672969', 'Saeed Anwar', 'saeed anwar')
('1774721', 'Cong Phuoc Huynh', 'cong phuoc huynh')69a9da55bd20ce4b83e1680fbc6be2c97606763169c2ac04693d53251500557316c854a625af84eeJID: PATREC @@ -4003,7 +4759,33 @@
enhancing Human Action Recognition
O.V. Ramana Murthy1 and Roland Goecke1,2
Vision and Sensing, HCC Lab, ESTeM, University of Canberra
IHCC, RSCS, CECS, Australian National UniversityEmail: O.V.RamanaMurthy@ieee.org, roland.goecke@ieee.org -3c78b642289d6a15b0fb8a7010a1fb829beceee2Analysis of Facial Dynamics +3cb2841302af1fb9656f144abc79d4f3d0b27380See 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 +
4 authors: +
READS +
33 +
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 +
University of Houston
468 PUBLICATIONS 5,233 CITATIONS +
SEE PROFILE +
SEE PROFILE +
Some of the authors of this publication are also working on these related projects: +
3D-Aided 2D Face Recognition View project +
iRay: mobile medical AR View project +
All content following this page was uploaded by Xiang Xu on 27 September 2017. +
The user has requested enhancement of the downloaded file. +3c78b642289d6a15b0fb8a7010a1fb829beceee2Analysis of Facial Dynamics
Using a Tensor Framework
University of Bristol
Department of Computer Science
Bristol, United Kingdom @@ -4043,7 +4825,18 @@
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 -3c03d95084ccbe7bf44b6d54151625c68f6e74d03c57e28a4eb463d532ea2b0b1ba4b426ead8d9a0Defeating Image Obfuscation with Deep Learning +3c563542db664321aa77a9567c1601f425500f94TV-GAN: Generative Adversarial Network Based Thermal to Visible Face +
Recognition +
The University of Queensland, School of ITEE, QLD 4072, Australia('50615828', 'Teng Zhang', 'teng zhang')
('2331880', 'Arnold Wiliem', 'arnold wiliem')
('1973322', 'Siqi Yang', 'siqi yang')
('2270092', 'Brian C. Lovell', 'brian c. lovell')[patrick.zhang, a.williem, siqi.yang]@uq.edu.au, lovell@itee.uq.edu.au +3c03d95084ccbe7bf44b6d54151625c68f6e74d03cd7b15f5647e650db66fbe2ce1852e00c05b2e43c6cac7ecf546556d7c6050f7b693a99cc8a57b3Robust Facial Landmark Detection in the Wild +
Submitted for the Degree of +
Doctor of Philosophy +
from the +
University of Surrey
Centre for Vision, Speech and Signal Processing +
Faculty of Engineering and Physical Sciences +
University of Surrey
Guildford, Surrey GU2 7XH, U.K. +
January 2016 +('37705062', 'Zhenhua Feng', 'zhenhua feng')
('37705062', 'Zhenhua Feng', 'zhenhua feng')3c57e28a4eb463d532ea2b0b1ba4b426ead8d9a0Defeating Image Obfuscation with Deep Learning
The University of Texas at
Austin
Cornell Tech
Cornell Tech @@ -4066,7 +4859,16 @@
Amherst MA 01003 ('40175280', 'Huaizu Jiang', 'huaizu jiang')hzjiang@cs.umass.edu
elm@cs.umass.edu -3ce2ecf3d6ace8d80303daf67345be6ec33b3a933c374cb8e730b64dacb9fbf6eb67f5987c7de3c8Measuring Gaze Orientation for Human-Robot +3ce2ecf3d6ace8d80303daf67345be6ec33b3a933c1aef7c2d32a219bdbc89a44d158bc2695e360aAdversarial Attack Type I: Generating False Positives +
Shanghai Jiao Tong University
Shanghai, P.R. China 200240 +
Shanghai Jiao Tong University
Shanghai, P.R. China 200240 +
Shanghai Jiao Tong University
Shanghai, P.R. China 200240 +
Shanghai Jiao Tong University
Shanghai, P.R. China 200240 +('51428687', 'Sanli Tang', 'sanli tang')
('13858459', 'Mingjian Chen', 'mingjian chen')
('2182657', 'Xiaolin Huang', 'xiaolin huang')
('1688428', 'Jie Yang', 'jie yang')tangsanli@sjtu.edu.cn +
w179261466@sjtu.edu.cn +
xiaolinhuang@sjtu.edu.cn +
jieyang@sjtu.edu.cn +3c374cb8e730b64dacb9fbf6eb67f5987c7de3c8Measuring Gaze Orientation for Human-Robot
Interaction
∗ CNRS; LAAS; 7 avenue du Colonel Roche, 31077 Toulouse Cedex, France
† Universit´e de Toulouse; UPS; LAAS-CNRS : F-31077 Toulouse, France @@ -4135,7 +4937,9 @@
TR4 8UN, UK.
Moscow Institute of Physics and Technology, Institutskiy per., 9, Dolgoprudny, 141701, Russia('3888942', 'Konstantin Chekanov', 'konstantin chekanov')
('4017984', 'Polina Mamoshina', 'polina mamoshina')
('1976753', 'Roman V. Yampolskiy', 'roman v. yampolskiy')
('1732855', 'Radu Timofte', 'radu timofte')
('40336662', 'Alex Zhavoronkov', 'alex zhavoronkov')Morten Scheibye-Knudsen: ​mscheibye@sund.ku.dk
Alex Zhavoronkov: ​alex@biogerontology.org -3cc46bf79fb9225cf308815c7d41c8dd5625cc29AGE INTERVAL AND GENDER PREDICTION USING PARAFAC2 APPLIED TO SPEECH +3c56acaa819f4e2263638b67cea1ec37a226691dBody Joint guided 3D Deep Convolutional +
Descriptors for Action Recognition +('3201156', 'Congqi Cao', 'congqi cao')
('46867228', 'Yifan Zhang', 'yifan zhang')
('1713887', 'Chunjie Zhang', 'chunjie zhang')
('1694235', 'Hanqing Lu', 'hanqing lu')3cc46bf79fb9225cf308815c7d41c8dd5625cc29AGE INTERVAL AND GENDER PREDICTION USING PARAFAC2 APPLIED TO SPEECH
UTTERANCES
Aristotle University of Thessaloniki
Thessaloniki 54124, GREECE
Cyprus University of Technology
3040 Limassol, Cyprus @@ -4184,7 +4988,12 @@ 56359d2b4508cc267d185c1d6d310a1c4c2cc8c2Shape Driven Kernel Adaptation in
Convolutional Neural Network for Robust Facial Trait Recognition
1Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), -
Institute of Computing Technology, CAS, Beijing, 100190, China
National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, 100190, China
National University of Singapore, Singapore('1688086', 'Shaoxin Li', 'shaoxin li')
('1757173', 'Junliang Xing', 'junliang xing')
('1773437', 'Zhiheng Niu', 'zhiheng niu')
('1685914', 'Shiguang Shan', 'shiguang shan')
('1698982', 'Shuicheng Yan', 'shuicheng yan')56e6f472090030a6f172a3e2f46ef9daf6cad757Asian Face Image Database PF01 +
Institute of Computing Technology, CAS, Beijing, 100190, China
National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, 100190, China
National University of Singapore, Singapore('1688086', 'Shaoxin Li', 'shaoxin li')
('1757173', 'Junliang Xing', 'junliang xing')
('1773437', 'Zhiheng Niu', 'zhiheng niu')
('1685914', 'Shiguang Shan', 'shiguang shan')
('1698982', 'Shuicheng Yan', 'shuicheng yan')56e079f4eb40744728fd1d7665938b06426338e5Bayesian Approaches to Distribution Regression +
University of Oxford
University College London
University of Oxford
Imperial College London('35142231', 'Ho Chung Leon Law', 'ho chung leon law')
('36326783', 'Dougal J. Sutherland', 'dougal j. sutherland')
('1698032', 'Dino Sejdinovic', 'dino sejdinovic')
('2127497', 'Seth Flaxman', 'seth flaxman')ho.law@spc.ox.ac.uk +
dougal@gmail.com +
dino.sejdinovic@stats.ox.ac.uk +
s.flaxman@imperial.ac.uk +56e6f472090030a6f172a3e2f46ef9daf6cad757Asian Face Image Database PF01
Intelligent Multimedia Lab.
†Department of Computer Science and Engineering
Pohang University of Science and Technology
San 31, Hyoja-Dong, Nam-Gu, Pohang, 790-784, Korea @@ -4239,10 +5048,16 @@
Concepts Not Alone: Exploring Pairwise Relationships
for Zero-Shot Video Activity Recognition
IIIS, Tsinghua University, Beijing, China
QCIS, University of Technology Sydney, Sydney, Australia
DCMandB, University of Michigan, Ann Arbor, USA 4 SCS, Carnegie Mellon University, Pittsburgh, USA('2551285', 'Chuang Gan', 'chuang gan')
('2735055', 'Ming Lin', 'ming lin')
('39033919', 'Yi Yang', 'yi yang')
('1732213', 'Gerard de Melo', 'gerard de melo')
('7661726', 'Alexander G. Hauptmann', 'alexander g. hauptmann')560e0e58d0059259ddf86fcec1fa7975dee6a868Face Recognition in Unconstrained Videos with Matched Background Similarity -
The Blavatnik School of Computer Science, Tel-Aviv University, Israel
Computer Science Division, The Open University of Israel('1776343', 'Lior Wolf', 'lior wolf')
('3352629', 'Itay Maoz', 'itay maoz')566038a3c2867894a08125efe41ef0a40824a090978-1-4244-2354-5/09/$25.00 ©2009 IEEE +
The Blavatnik School of Computer Science, Tel-Aviv University, Israel
Computer Science Division, The Open University of Israel('1776343', 'Lior Wolf', 'lior wolf')
('3352629', 'Itay Maoz', 'itay maoz')56a677c889e0e2c9f68ab8ca42a7e63acf986229Mining Spatial and Spatio-Temporal ROIs for Action Recognition +
Jiang Wang2 Alan Yuille1,3 +
University of California, Los Angeles
Baidu Research, USA 3John Hopkins University('5964529', 'Xiaochen Lian', 'xiaochen lian'){lianxiaochen@,yuille@stat.}ucla.edu +
{chenzhuoyuan,yangyi05,wangjiang03}@baidu.com +566038a3c2867894a08125efe41ef0a40824a090978-1-4244-2354-5/09/$25.00 ©2009 IEEE
1945
ICASSP 2009 -56ae6d94fc6097ec4ca861f0daa87941d1c10b70Distance Estimation of an Unknown Person +56dca23481de9119aa21f9044efd7db09f618704Riemannian Dictionary Learning and Sparse +
Coding for Positive Definite Matrices +('2691929', 'Anoop Cherian', 'anoop cherian')
('3072326', 'Suvrit Sra', 'suvrit sra')56ae6d94fc6097ec4ca861f0daa87941d1c10b70Distance Estimation of an Unknown Person
from a Portrait
1 Technicolor - Cesson S´evign´e, France
California Institute of Technology, Pasadena, CA, USA('2232848', 'Xavier P. Burgos-Artizzu', 'xavier p. burgos-artizzu')
('3339867', 'Matteo Ruggero Ronchi', 'matteo ruggero ronchi')
('1690922', 'Pietro Perona', 'pietro perona')xavier.burgos@technicolor.com, {mronchi,perona}@caltech.edu @@ -4257,7 +5072,12 @@ ('1708679', 'Yun Fu', 'yun fu')
('37575012', 'Liangliang Cao', 'liangliang cao')
('1822413', 'Guodong Guo', 'guodong guo')
('1739208', 'Thomas S. Huang', 'thomas s. huang'){yunfu2,cao4}@uiuc.edu
gdguo@nccu.edu
huang@ifp.uiuc.edu -512befa10b9b704c9368c2fbffe0dc3efb1ba1bfEvidence and a Computational Explanation of Cultural Differences in +516a27d5dd06622f872f5ef334313350745eadc3> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < +
1 +
Fine-Grained Facial Expression Analysis Us- +
ing Dimensional Emotion Model +
 +('41179750', 'Feng Zhou', 'feng zhou')
('34362536', 'Shu Kong', 'shu kong')
('3157443', 'Charless C. Fowlkes', 'charless c. fowlkes')
('29889388', 'Tao Chen', 'tao chen')
('40216538', 'Baiying Lei', 'baiying lei')512befa10b9b704c9368c2fbffe0dc3efb1ba1bfEvidence and a Computational Explanation of Cultural Differences in
Facial Expression Recognition
Matthew N. Dailey
Computer Science and Information Management @@ -4330,7 +5150,9 @@ ('2635321', 'Josiah Wang', 'josiah wang')
('1686341', 'Katja Markert', 'katja markert')
('3056091', 'Mark Everingham', 'mark everingham')scs6jwks@comp.leeds.ac.uk
markert@comp.leeds.ac.uk
me@comp.leeds.ac.uk -51c7c5dfda47647aef2797ac3103cf0e108fdfb4CS 395T: Celebrity Look-Alikes ∗ +5180df9d5eb26283fb737f491623395304d57497Scalable Angular Discriminative Deep Metric Learning +
for Face Recognition +
aCenter for Combinatorics, Nankai University, Tianjin 300071, China
bCenter for Applied Mathematics, Tianjin University, Tianjin 300072, China('2143751', 'Bowen Wu', 'bowen wu')51c7c5dfda47647aef2797ac3103cf0e108fdfb4CS 395T: Celebrity Look-Alikes ∗ ('2362854', 'Adrian Quark', 'adrian quark')quark@mail.utexas.edu 519f4eb5fe15a25a46f1a49e2632b12a3b18c94dNon-Lambertian Reflectance Modeling and
Shape Recovery of Faces using Tensor Splines @@ -4362,14 +5184,27 @@
Fernando De la Torre, Co-chair
Submitted in partial fulfillment of the requirements
for the degree of Doctor of Philosophy in Robotics. -('39336289', 'Wen-Sheng Chu', 'wen-sheng chu')
('1737918', 'Jeffrey F. Cohn', 'jeffrey f. cohn')
('1820249', 'Simon Lucey', 'simon lucey')
('1770537', 'Deva Ramanan', 'deva ramanan')
('1736042', 'Vladimir Pavlovic', 'vladimir pavlovic')
('39336289', 'Wen-Sheng Chu', 'wen-sheng chu')51cc78bc719d7ff2956b645e2fb61bab59843d2bFace and Facial Expression Recognition with an +('39336289', 'Wen-Sheng Chu', 'wen-sheng chu')
('1737918', 'Jeffrey F. Cohn', 'jeffrey f. cohn')
('1820249', 'Simon Lucey', 'simon lucey')
('1770537', 'Deva Ramanan', 'deva ramanan')
('1736042', 'Vladimir Pavlovic', 'vladimir pavlovic')
('39336289', 'Wen-Sheng Chu', 'wen-sheng chu')51faacfa4fb1e6aa252c6970e85ff35c5719f4ffZoom-Net: Mining Deep Feature Interactions for +
Visual Relationship Recognition +
University of Science and Technology of China, Key Laboratory of Electromagnetic
Space Information, the Chinese Academy of Sciences, 2SenseTime Group Limited, +
CUHK-SenseTime Joint Lab, The Chinese University of Hong Kong
SenseTime-NTU Joint AI Research Centre, Nanyang Technological University('4332039', 'Guojun Yin', 'guojun yin')
('37145669', 'Lu Sheng', 'lu sheng')
('50677886', 'Bin Liu', 'bin liu')
('1708598', 'Nenghai Yu', 'nenghai yu')
('31843833', 'Xiaogang Wang', 'xiaogang wang')
('49895575', 'Jing Shao', 'jing shao')
('1717179', 'Chen Change Loy', 'chen change loy')gjyin@mail.ustc.edu.cn, {flowice,ynh}@ustc.edu.cn, ccloy@ieee.org, +
{lsheng,xgwang}@ee.cuhk.edu.hk, shaojing@sensetime.com +51cc78bc719d7ff2956b645e2fb61bab59843d2bFace and Facial Expression Recognition with an
Embedded System for Human-Robot Interaction
School of Computer Engineering, Sejong University, Seoul, Korea('2241562', 'Yang-Bok Lee', 'yang-bok lee')
('2706430', 'Yong-Guk Kim', 'yong-guk kim')*ykim@sejong.ac.kr 511b06c26b0628175c66ab70dd4c1a4c0c19aee9International Journal of Engineering Research and General ScienceVolume 2, Issue 5, August – September 2014
ISSN 2091-2730
Face Recognition using Laplace Beltrami Operator by Optimal Linear
Approximations -
Institute of Engineering and Technology, Alwar, Rajasthan Technical University, Kota(Raj
Research Scholar (M.Tech, IT), Institute of Engineering and Technology51528cdce7a92835657c0a616c0806594de7513b514a74aefb0b6a71933013155bcde7308cad2b46CARNEGIE MELLON UNIVERSITY
OPTIMAL CLASSIFIER ENSEMBLES +
Institute of Engineering and Technology, Alwar, Rajasthan Technical University, Kota(Raj
Research Scholar (M.Tech, IT), Institute of Engineering and Technology51528cdce7a92835657c0a616c0806594de7513b51cb09ee04831b95ae02e1bee9b451f8ac4526e3Beyond Short Snippets: Deep Networks for Video Classification +
Matthew Hausknecht2 +
University of Maryland, College Park
University of Texas at Austin
Google, Inc('2340579', 'Joe Yue-Hei Ng', 'joe yue-hei ng')
('1689108', 'Oriol Vinyals', 'oriol vinyals')
('3089272', 'Rajat Monga', 'rajat monga')
('2259154', 'Sudheendra Vijayanarasimhan', 'sudheendra vijayanarasimhan')
('1805076', 'George Toderici', 'george toderici')yhng@umiacs.umd.edu +
mhauskn@cs.utexas.edu +
svnaras@google.com +
vinyals@google.com +
rajatmonga@google.com +
gtoderici@google.com +514a74aefb0b6a71933013155bcde7308cad2b46CARNEGIE MELLON UNIVERSITY
OPTIMAL CLASSIFIER ENSEMBLES
FOR IMPROVED BIOMETRIC VERIFICATION
A Dissertation
Submitted to the Faculty of Graduate School @@ -4466,9 +5301,17 @@
Manuscript received 23 June 2002; revised 27 January 2003
Communicated by Ladislav Hluch´y ('2366162', 'Yongzhong Lu', 'yongzhong lu')
('1711876', 'Jingli Zhou', 'jingli zhou')
('1714618', 'Shengsheng Yu', 'shengsheng yu')e-mail: luyongz0@sohu.com -5121f42de7cb9e41f93646e087df82b573b23311CLASSIFYING ONLINE DATING PROFILES ON TINDER USING FACENET FACIAL +5161e38e4ea716dcfb554ccb88901b3d97778f64SSPP-DAN: DEEP DOMAIN ADAPTATION NETWORK FOR +
FACE RECOGNITION WITH SINGLE SAMPLE PER PERSON +
School of Computing, KAIST, Republic of Korea +('2487892', 'Sungeun Hong', 'sungeun hong')
('40506942', 'Woobin Im', 'woobin im')5121f42de7cb9e41f93646e087df82b573b23311CLASSIFYING ONLINE DATING PROFILES ON TINDER USING FACENET FACIAL
EMBEDDINGS
FLCharles F. Jekel (cjekel@ufl.edu; cj@jekel.me) and Raphael T. Haftka +51d1a6e15936727e8dd487ac7b7fd39bd2baf5eeJOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 +
A Fast and Accurate System for Face Detection, +
Identification, and Verification +('48467498', 'Rajeev Ranjan', 'rajeev ranjan')
('2068427', 'Ankan Bansal', 'ankan bansal')
('7674316', 'Jingxiao Zheng', 'jingxiao zheng')
('2680836', 'Hongyu Xu', 'hongyu xu')
('35199438', 'Joshua Gleason', 'joshua gleason')
('2927406', 'Boyu Lu', 'boyu lu')
('8435884', 'Anirudh Nanduri', 'anirudh nanduri')
('36407236', 'Jun-Cheng Chen', 'jun-cheng chen')
('38171682', 'Carlos D. Castillo', 'carlos d. castillo')
('9215658', 'Rama Chellappa', 'rama chellappa')5141cf2e59fb2ec9bb489b9c1832447d3cd93110Learning Person Trajectory Representations for Team Activity Analysis +
Simon Fraser University('10386960', 'Nazanin Mehrasa', 'nazanin mehrasa')
('19198359', 'Yatao Zhong', 'yatao zhong')
('2123865', 'Frederick Tung', 'frederick tung')
('3004771', 'Luke Bornn', 'luke bornn')
('10771328', 'Greg Mori', 'greg mori'){nmehrasa, yataoz, ftung, lbornn}@sfu.ca, mori@cs.sfu.ca 5185f2a40836a754baaa7419a1abdd1e7ffaf2adA Multimodality Framework for Creating Speaker/Non-Speaker Profile
Databases for Real-World Video
Beckman Institute
University of Illinois
Urbana, IL 61801 @@ -4477,18 +5320,101 @@ ('3082579', 'Jehanzeb Abbas', 'jehanzeb abbas')
('1804874', 'Charlie K. Dagli', 'charlie k. dagli')
('1739208', 'Thomas S. Huang', 'thomas s. huang')jabbas2@ifp.uiuc.edu
dagli@ifp.uiuc.edu
huang@ifp.uiuc.edu -5160569ca88171d5fa257582d161e9063c8f898dLocal Binary Patterns as an Image Preprocessing for Face Authentication +511a8cdf2127ef8aa07cbdf9660fe9e0e2dfbde7Hindawi +
Computational Intelligence and Neuroscience +
Volume 2018, Article ID 4512473, 10 pages +
https://doi.org/10.1155/2018/4512473 +
Research Article +
A Community Detection Approach to Cleaning Extremely +
Large Face Database +
Computer School, University of South China, Hengyang, China
National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China
Received 11 December 2017; Accepted 12 March 2018; Published 22 April 2018 +
Academic Editor: Amparo Alonso-Betanzos +
permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. +
Though it has been easier to build large face datasets by collecting images from the Internet in this Big Data era, the time-consuming +
manual annotation process prevents researchers from constructing larger ones, which makes the automatic cleaning of noisy labels +
highly desirable. However, identifying mislabeled faces by machine is quite challenging because the diversity of a person’s face +
images that are captured wildly at all ages is extraordinarily rich. In view of this, we propose a graph-based cleaning method that +
mainly employs the community detection algorithm and deep CNN models to delete mislabeled images. As the diversity of faces is +
preserved in multiple large communities, our cleaning results have both high cleanness and rich data diversity. With our method, we +
clean the extremely large MS-Celeb-1M face dataset (approximately 10 million images with noisy labels) and obtain a clean version +
of it called C-MS-Celeb (6,464,018 images of 94,682 celebrities). By training a single-net model using our C-MS-Celeb dataset, +
without fine-tuning, we achieve 99.67% at Equal Error Rate on the LFW face recognition benchmark, which is comparable to other +
state-of-the-art results. This demonstrates the data cleaning positive effects on the model training. To the best of our knowledge, +
our C-MS-Celeb is the largest clean face dataset that is publicly available so far, which will benefit face recognition researchers. +
1. Introduction +
In the last few years, researchers have witnessed the remark- +
able progress in face recognition due to the significant success +
of deep convolutional neural networks [1] and the emergence +
of large scale face datasets [2]. Although the data explosion +
has made it easier to build datasets by collecting real world +
images from the Internet [3], constructing a large scale face +
dataset remains a highly time-consuming and costly task +
because the mislabeled images returned by search engines +
need to be manually removed [4]. Thus, automatic cleaning +
of noisy labels in the raw dataset is strongly desirable. +
However, identifying mislabeled faces automatically by +
machine is by no means easy. The main reason for this is that, +
for faces that are captured wildly, the variation of a man’s faces +
can be so large that some of his images may easily be identified +
as someone else’s [5]. Thus, a machine may be misled by this +
rich data diversity within one person and delete correctly +
labeled images. For example, if old faces of a man are the +
majority in the dataset, a young face of him may be regarded +
as someone else and removed. Another challenge is that, due +
to the ambiguity of people’s names, searching for someone’s +
pictures online usually returns images from multiple people +
[2], which requires the cleaning method to be tolerant to the +
high proportion of noisy labels in the raw dataset constructed +
by online searching. +
In order to clean noisy labels and meanwhile preserve +
the rich data diversity of various faces, we propose a three- +
stage graph-based method to clean large face datasets using +
the community detection algorithm. For each image in the +
raw dataset, we firstly use pretrained deep CNN models to +
align the face and extract a feature vector to represent each +
face. Secondly, for features of the same identity, based on the +
cosine similarity between different features, we construct an +
undirected graph, named “face similarity graph,” to quantify +
the similarity between different images. After deleting weak +
edges and applying the community detection algorithm, we +
delete mislabeled images by removing minor communities. In +
the last stage, we try to relabel each previously deleted image +('3335298', 'Chi Jin', 'chi jin')
('9856301', 'Ruochun Jin', 'ruochun jin')
('38536592', 'Kai Chen', 'kai chen')
('1791001', 'Yong Dou', 'yong dou')
('3335298', 'Chi Jin', 'chi jin')Correspondence should be addressed to Ruochun Jin; sczjrc@163.com +51d048b92f6680aca4a8adf07deb380c0916c808This is the accepted version of the following article: "State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications", +
which has been published in final form at http://onlinelibrary.wiley.com. This article may be used for non-commercial purposes in accordance +
with the Wiley Self-Archiving Policy [http://olabout.wiley.com/WileyCDA/Section/id-820227.html]. +
EUROGRAPHICS 2018 +
K. Hildebrandt and C. Theobalt +
(Guest Editors) +
Volume 37 (2018), Number 2 +
STAR – State of The Art Report +
State of the Art on Monocular 3D Face +
Reconstruction, Tracking, and Applications +
M. Zollhöfer1,2 +
J. Thies3 P. Garrido1,5 D. Bradley4 T. Beeler4 P. Pérez5 M. Stamminger6 M. Nießner3 C. Theobalt1 +
Max Planck Institute for Informatics
Stanford University
Technical University of Munich
4Disney Research +
5Technicolor +
University of Erlangen-Nuremberg
Figure 1: This state-of-the-art report provides an overview of monocular 3D face reconstruction and tracking, and highlights applications. +5134353bd01c4ea36bd007c460e8972b1541d0adFace Recognition with Multi-Resolution Spectral Feature +
Images +
School of Electrical Engineering and Automation, Anhui University, Hefei, China, Hong Kong Polytechnic
University, Hong Kong, China, 3 Center for Intelligent Electricity Networks, University of Newcastle, Newcastle, Australia, 4 School of Electrical and Electronic Engineering
Nanyang Technological University, Singapore, Singapore('31443079', 'Zhan-Li Sun', 'zhan-li sun')
('1703078', 'Kin-Man Lam', 'kin-man lam')
('50067626', 'Zhao-yang Dong', 'zhao-yang dong')
('40465036', 'Han Wang', 'han wang')
('29927490', 'Qing-wei Gao', 'qing-wei gao')5160569ca88171d5fa257582d161e9063c8f898dLocal Binary Patterns as an Image Preprocessing for Face Authentication
IDIAP Research Institute, Martigny, Switzerland
Ecole Polytechnique F´ed´erale de Lausanne (EPFL), Switzerland ('16602458', 'Guillaume Heusch', 'guillaume heusch')
('2820403', 'Yann Rodriguez', 'yann rodriguez')fheusch, rodrig, marcelg@idiap.ch 5157dde17a69f12c51186ffc20a0a6c6847f1a29Evolutionary Cost-sensitive Extreme Learning
Machine
1 -('40613723', 'Lei Zhang', 'lei zhang')
('1698371', 'David Zhang', 'david zhang')51dc127f29d1bb076d97f515dca4cc42dda3d25b3d143cfab13ecd9c485f19d988242e7240660c86Discriminative Collaborative Representation for +('40613723', 'Lei Zhang', 'lei zhang')
('1698371', 'David Zhang', 'david zhang')51dc127f29d1bb076d97f515dca4cc42dda3d25b3d18ce183b5a5b4dcaa1216e30b774ef49eaa46fFace Alignment Across Large Poses: A 3D Solution +
Hailin Shi1 +
Institute of Automation, Chinese Academy of Sciences
Michigan State University('8362374', 'Xiangyu Zhu', 'xiangyu zhu')
('1718623', 'Zhen Lei', 'zhen lei')
('1759169', 'Xiaoming Liu', 'xiaoming liu')
('34679741', 'Stan Z. Li', 'stan z. li'){xiangyu.zhu,zlei,hailin.shi,szli}@nlpr.ia.ac.cn +
liuxm@msu.edu +3d143cfab13ecd9c485f19d988242e7240660c86Discriminative Collaborative Representation for
Classification
Academic Center for Computing and Media Studies, Kyoto University, Kyoto 606-8501, Japan
Institute of Scienti c and Industrial Research, Osaka University, Ibaraki-shi 567-0047, Japan
3 OMRON Social Solutions Co., LTD, Kyoto 619-0283, Japan ('2549020', 'Yang Wu', 'yang wu')
('40400215', 'Wei Li', 'wei li')
('1707934', 'Masayuki Mukunoki', 'masayuki mukunoki')
('1681266', 'Michihiko Minoh', 'michihiko minoh')
('1710195', 'Shihong Lao', 'shihong lao')yangwu@mm.media.kyoto-u.ac.jp,seuliwei@126.com,
{minoh,mukunoki}@media.kyoto-u.ac.jp,lao_shihong@oss.omron.co.jp -3dabf7d853769cfc4986aec443cc8b6699136ed0In A. Esposito, N. Bourbakis, N. Avouris, and I. Hatzilygeroudis. (Eds.) Lecture Notes in +3daafe6389d877fe15d8823cdf5ac15fd919676fHuman Action Localization +
with Sparse Spatial Supervision +('2492127', 'Philippe Weinzaepfel', 'philippe weinzaepfel')
('49142153', 'Xavier Martin', 'xavier martin')
('2462253', 'Cordelia Schmid', 'cordelia schmid')3dabf7d853769cfc4986aec443cc8b6699136ed0In A. Esposito, N. Bourbakis, N. Avouris, and I. Hatzilygeroudis. (Eds.) Lecture Notes in
Computer Science, Vol 5042: Verbal and Nonverbal Features of Human-human and Human-
machine Interaction, Springer Verlag, p. 1-21.
Data mining spontaneous facial behavior with @@ -4560,7 +5486,7 @@
Center for Arti cial Vision Research, Korea University
Anam-dong, Seongbuk-ku, Seoul 136-713, Korea ('2348968', 'Sang-Woong Lee', 'sang-woong lee')
('1703007', 'Seong-Whan Lee', 'seong-whan lee')rhiephil@cs.cmu.edu
swlee@image.korea.ac.kr -3d0c21d4780489bd624a74b07e28c16175df6355Deep or Shallow Facial Descriptors? A Case for +3d6ee995bc2f3e0f217c053368df659a5d14d5b53d0c21d4780489bd624a74b07e28c16175df6355Deep or Shallow Facial Descriptors? A Case for
Facial Attribute Classification and Face Retrieval
1 Faculty of Engineering,
Multimedia University, Cyberjaya, Malaysia
2 Faculty of Computing & Informatics, @@ -4600,7 +5526,11 @@
Revised: February 2010
A Thesis submitted to McGill University in partial fulfillment of the requirements for the
degree of Master of Engineering
i -('2376514', 'Malika Meghjani', 'malika meghjani')
('2376514', 'Malika Meghjani', 'malika meghjani')3d1af6c531ebcb4321607bcef8d9dc6aa9f0dc5a1892 +('2376514', 'Malika Meghjani', 'malika meghjani')
('2376514', 'Malika Meghjani', 'malika meghjani')3dfb822e16328e0f98a47209d7ecd242e4211f82Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in +
Unconstrained Environments +
Beijing University of Posts and Telecommunications
Beijing 100876,China +('15523767', 'Tianyue Zheng', 'tianyue zheng')
('1774956', 'Weihong Deng', 'weihong deng')
('23224233', 'Jiani Hu', 'jiani hu')2231135739@qq.com, whdeng@bupt.edu.cn, 40902063@qq.com +3d1af6c531ebcb4321607bcef8d9dc6aa9f0dc5a1892
Random Multispace Quantization as
an Analytic Mechanism for BioHashing
of Biometric and Random Identity Inputs @@ -4675,6 +5605,14 @@
Frontiers in ICT | www.frontiersin.org
June 2016 | Volume 3 | Article 11 ('30772945', 'Chunfeng Liu', 'chunfeng liu')
('1742162', 'Rafael A. Calvo', 'rafael a. calvo')
('36807976', 'Renee Lim', 'renee lim')
('1742162', 'Rafael A. Calvo', 'rafael a. calvo')rafael.calvo@sydney.edu.au +580f86f1ace1feed16b592d05c2b07f26c429b4bDense-Captioning Events in Videos +
Stanford University('2580593', 'Ranjay Krishna', 'ranjay krishna')
('35163655', 'Kenji Hata', 'kenji hata')
('3260219', 'Frederic Ren', 'frederic ren')
('3216322', 'Li Fei-Fei', 'li fei-fei')
('9200530', 'Juan Carlos Niebles', 'juan carlos niebles'){ranjaykrishna, kenjihata, fren, feifeili, jniebles}@cs.stanford.edu +58d47c187b38b8a2bad319c789a09781073d052dFactorizable Net: An Efficient Subgraph-based +
Framework for Scene Graph Generation +
The Chinese University of Hong Kong, Hong Kong SAR, China
The University of Sydney, SenseTime Computer Vision Research Group
3 MIT CSAIL, USA +
4 Sensetime Ltd, Beijing, China +
Samsung Telecommunication Research Institute, Beijing, China('2180892', 'Yikang Li', 'yikang li')
('3001348', 'Wanli Ouyang', 'wanli ouyang')
('1804424', 'Bolei Zhou', 'bolei zhou')
('1788070', 'Jianping Shi', 'jianping shi')
('31843833', 'Xiaogang Wang', 'xiaogang wang'){ykli, xgwang}@ee.cuhk.edu.hk, wanli.ouyang@sydney.edu.au, +
bzhou@csail.mit.edu, shijianping@sensetime.com, c0502.zhang@samsung.com 582edc19f2b1ab2ac6883426f147196c8306685aDo We Really Need to Collect Millions of Faces
for Effective Face Recognition?
Institute for Robotics and Intelligent Systems, USC, CA, USA
Information Sciences Institute, USC, CA, USA
The Open University of Israel, Israel('11269472', 'Iacopo Masi', 'iacopo masi')
('2955822', 'Jatuporn Toy Leksut', 'jatuporn toy leksut')
('1756099', 'Tal Hassner', 'tal hassner')5859774103306113707db02fe2dd3ac9f91f1b9e5892f8367639e9c1e3cf27fdf6c09bb3247651edEstimating Missing Features to Improve Multimedia Information Retrieval @@ -4784,7 +5722,17 @@ ('1756099', 'Tal Hassner', 'tal hassner')
('1776343', 'Lior Wolf', 'lior wolf')
('1759551', 'Nachum Dershowitz', 'nachum dershowitz')Email: hassner@openu.ac.il
Email: wolf@cs.tau.ac.il
Email: nachumd@tau.ac.il -58823377757e7dc92f3b70a973be697651089756Technical Report +58bf72750a8f5100e0c01e55fd1b959b31e7dbcePyramidBox: A Context-assisted Single Shot +
Face Detector. +
Baidu Inc. +('48785141', 'Xu Tang', 'xu tang')
('14931829', 'Daniel K. Du', 'daniel k. du')
('31239588', 'Zeqiang He', 'zeqiang he')
('2272123', 'Jingtuo Liu', 'jingtuo liu')tangxu02@baidu.com,daniel.kang.du@gmail.com,{hezeqiang,liujingtuo}@baidu.com +58542eeef9317ffab9b155579256d11efb4610f2International Journal of Science and Research (IJSR) +
ISSN (Online): 2319-7064 +
Index Copernicus Value (2013): 6.14 | Impact Factor (2014): 5.611 +
Face Recognition Revisited on Pose, Alignment, +
Color, Illumination and Expression-PyTen +
Computer Science, BIT Noida, India +58823377757e7dc92f3b70a973be697651089756Technical Report
UCAM-CL-TR-861
ISSN 1476-2986
Number 861 @@ -4950,7 +5898,9 @@
i∈Y
yi, j .
(2) -('2682056', 'Ching-Hui Chen', 'ching-hui chen')
('1741177', 'Vishal M. Patel', 'vishal m. patel')
('9215658', 'Rama Chellappa', 'rama chellappa')676f9eabf4cfc1fd625228c83ff72f6499c67926FACE IDENTIFICATION AND CLUSTERING +('2682056', 'Ching-Hui Chen', 'ching-hui chen')
('1741177', 'Vishal M. Patel', 'vishal m. patel')
('9215658', 'Rama Chellappa', 'rama chellappa')677585ccf8619ec2330b7f2d2b589a37146ffad7A flexible model for training action localization +
with varying levels of supervision +('1902524', 'Guilhem Chéron', 'guilhem chéron')
('2285263', 'Jean-Baptiste Alayrac', 'jean-baptiste alayrac')
('1785596', 'Ivan Laptev', 'ivan laptev')
('2462253', 'Cordelia Schmid', 'cordelia schmid')676f9eabf4cfc1fd625228c83ff72f6499c67926FACE IDENTIFICATION AND CLUSTERING
A thesis submitted to the
Graduate School—New Brunswick
Rutgers, The State University of New Jersey
in partial fulfillment of the requirements @@ -4962,10 +5912,15 @@
and approved by
New Brunswick, New Jersey
May, 2017 -('34805991', 'Atul Dhingra', 'atul dhingra')677477e6d2ba5b99633aee3d60e77026fb0b9306679b7fa9e74b2aa7892eaea580def6ed4332a228Communication and automatic +('34805991', 'Atul Dhingra', 'atul dhingra')677477e6d2ba5b99633aee3d60e77026fb0b93066789bddbabf234f31df992a3356b36a47451efc7Unsupervised Generation of Free-Form and +
Parameterized Avatars +('33964593', 'Adam Polyak', 'adam polyak')
('2188620', 'Yaniv Taigman', 'yaniv taigman')
('1776343', 'Lior Wolf', 'lior wolf')679b7fa9e74b2aa7892eaea580def6ed4332a228Communication and automatic
interpretation of affect from facial
expressions1 -
University of Amsterdam, the Netherlands
University of Trento, Italy
University of Amsterdam, the Netherlands('1764521', 'Albert Ali Salah', 'albert ali salah')
('1703601', 'Nicu Sebe', 'nicu sebe')
('1695527', 'Theo Gevers', 'theo gevers')670637d0303a863c1548d5b19f705860a23e285cFace Swapping: Automatically Replacing Faces in Photographs +
University of Amsterdam, the Netherlands
University of Trento, Italy
University of Amsterdam, the Netherlands('1764521', 'Albert Ali Salah', 'albert ali salah')
('1703601', 'Nicu Sebe', 'nicu sebe')
('1695527', 'Theo Gevers', 'theo gevers')675b2caee111cb6aa7404b4d6aa371314bf0e647AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions +
Carl Vondrick∗ +('39599498', 'Chunhui Gu', 'chunhui gu')
('1758054', 'Yeqing Li', 'yeqing li')
('1726241', 'Chen Sun', 'chen sun')
('48536531', 'David A. Ross', 'david a. ross')
('2259154', 'Sudheendra Vijayanarasimhan', 'sudheendra vijayanarasimhan')
('1805076', 'George Toderici', 'george toderici')
('2997956', 'Caroline Pantofaru', 'caroline pantofaru')
('2262946', 'Susanna Ricco', 'susanna ricco')
('1694199', 'Rahul Sukthankar', 'rahul sukthankar')
('2462253', 'Cordelia Schmid', 'cordelia schmid')
('1689212', 'Jitendra Malik', 'jitendra malik')679b72d23a9cfca8a7fe14f1d488363f2139265f67484723e0c2cbeb936b2e863710385bdc7d5368Anchor Cascade for Efficient Face Detection +('2425630', 'Baosheng Yu', 'baosheng yu')
('1692693', 'Dacheng Tao', 'dacheng tao')670637d0303a863c1548d5b19f705860a23e285cFace Swapping: Automatically Replacing Faces in Photographs
Columbia University
Peter Belhumeur
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 @@ -5015,12 +5970,27 @@
Accepted by . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Arthur C. Smith
Chairman, Department Committee on Graduate Students -67c703a864aab47eba80b94d1935e6d244e00bcb (IJACSA) International Journal of Advanced Computer Science and Applications +673d4885370b27c863e11a4ece9189a6a45931ccRecurrent Residual Module for Fast Inference in Videos +
Shanghai Jiao Tong University, 2Zhejiang University, 3Massachusetts Institute of Technology
networks for video recognition are more challenging. For +
example, for Youtube-8M dataset [1] with over 8 million +
video clips, it will take 50 years for a CPU to extract the +
deep features using a standard CNN model. +('35654996', 'Bowen Pan', 'bowen pan')
('35992009', 'Wuwei Lin', 'wuwei lin')
('2126444', 'Xiaolin Fang', 'xiaolin fang')
('35933894', 'Chaoqin Huang', 'chaoqin huang')
('1804424', 'Bolei Zhou', 'bolei zhou')
('1830034', 'Cewu Lu', 'cewu lu')†{googletornado,linwuwei13, huangchaoqin}@sjtu.edu.cn, ¶fxlfang@gmail.com +
§bzhou@csail.mit.edu; ‡lu-cw@cs.sjtu.edu.cn +67c703a864aab47eba80b94d1935e6d244e00bcb (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
University of Science, VNU-HCM, Viet Nam
face searching, -('3911040', 'Phan Khoi', 'phan khoi')677ebde61ba3936b805357e27fce06c44513a455Facial Expression Recognition Based on Facial +('3911040', 'Phan Khoi', 'phan khoi')6754c98ba73651f69525c770fb0705a1fae78eb5Joint Cascade Face Detection and Alignment +
University of Science and Technology of China
2 Microsoft Research +('39447786', 'Dong Chen', 'dong chen')
('3080683', 'Shaoqing Ren', 'shaoqing ren')
('1732264', 'Yichen Wei', 'yichen wei')
('47300766', 'Xudong Cao', 'xudong cao')
('40055995', 'Jian Sun', 'jian sun'){chendong,sqren}@mail.ustc.edu.cn +
{yichenw,xudongca,jiansun}@microsoft.com +672fae3da801b2a0d2bad65afdbbbf1b2320623ePose-Selective Max Pooling for Measuring Similarity +
1Dept. of Computer Science +
2Dept. of Electrical & Computer Engineering +
Johns Hopkins University, 3400 N. Charles St, Baltimore, MD 21218, USA('40031188', 'Xiang Xiang', 'xiang xiang')
('1709073', 'Trac D. Tran', 'trac d. tran')xxiang@cs.jhu.edu +677ebde61ba3936b805357e27fce06c44513a455Facial Expression Recognition Based on Facial
Components Detection and HOG Features
The Hong Kong Polytechnic University, Hong Kong
Chu Hai College of Higher Education, Hong Kong('2366262', 'Junkai Chen', 'junkai chen')
('1715231', 'Zenghai Chen', 'zenghai chen')
('8590720', 'Zheru Chi', 'zheru chi')
('1965426', 'Hong Fu', 'hong fu')Email: Junkai.Chen@connect.polyu.hk 67ba3524e135c1375c74fe53ebb03684754aae56978-1-5090-4117-6/17/$31.00 ©2017 IEEE @@ -5028,6 +5998,20 @@
ICASSP 2017 6769cfbd85329e4815bb1332b118b01119975a95Tied factor analysis for face recognition across
large pose changes +0be43cf4299ce2067a0435798ef4ca2fbd255901Title +
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 +
2011 +
URL +
http://hdl.handle.net/10722/142604 +
Rights +
Creative Commons: Attribution 3.0 Hong Kong License 0bc53b338c52fc635687b7a6c1e7c2b7191f42e5ZHANG, BHALERAO: LOGLET SIFT FOR PART DESCRIPTION
Loglet SIFT for Part Description in
Deformable Part Models: Application to Face @@ -5097,7 +6081,9 @@
Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore
College of Computer Science, Sichuan University, Chengdu 610065, P.R. China('8249791', 'Xi Peng', 'xi peng')
('9276020', 'Zhang Yi', 'zhang yi')
('3134548', 'Huajin Tang', 'huajin tang')pangsaai@gmail.com, zhangyi@scu.edu.cn, htang@i2r.a-star.edu.sg. 0b20f75dbb0823766d8c7b04030670ef7147ccdd1
Feature selection using nearest attributes -('1744784', 'Alex Pappachen James', 'alex pappachen james')
('1697594', 'Sima Dimitrijev', 'sima dimitrijev')0b174d4a67805b8796bfe86cd69a967d357ba9b6 Research Journal of Recent Sciences _________________________________________________ ISSN 2277-2502 +('1744784', 'Alex Pappachen James', 'alex pappachen james')
('1697594', 'Sima Dimitrijev', 'sima dimitrijev')0b5a82f8c0ee3640503ba24ef73e672d93aeebbfOn Learning 3D Face Morphable Model +
from In-the-wild Images +('1849929', 'Luan Tran', 'luan tran')
('1759169', 'Xiaoming Liu', 'xiaoming liu')0b174d4a67805b8796bfe86cd69a967d357ba9b6 Research Journal of Recent Sciences _________________________________________________ ISSN 2277-2502
Vol. 3(4), 56-62, April (2014)
Res.J.Recent Sci. 0ba449e312894bca0d16348f3aef41ca018723830b87d91fbda61cdea79a4b4dcdcb6d579f063884The Open Automation and Control Systems Journal, 2015, 7, 569-579 @@ -5119,7 +6105,9 @@
Cambridge, MA  , USA ('1780935', 'Baback Moghaddam', 'baback moghaddam')
('1768120', 'Tony Jebara', 'tony jebara')
('1682773', 'Alex Pentland', 'alex pentland')baback@merl.com
fjebara,sandyg@media.mit.edu -0b85b50b6ff03a7886c702ceabad9ab8c8748fdchttp://www.journalofvision.org/content/11/3/17 +0b572a2b7052b15c8599dbb17d59ff4f02838ff7Automatic Subspace Learning via Principal +
Coefficients Embedding +('8249791', 'Xi Peng', 'xi peng')
('1697700', 'Jiwen Lu', 'jiwen lu')
('1709367', 'Zhang Yi', 'zhang yi')
('1680126', 'Rui Yan', 'rui yan')0b85b50b6ff03a7886c702ceabad9ab8c8748fdchttp://www.journalofvision.org/content/11/3/17
Is there a dynamic advantage for facial expressions?
Institute of Child Health, University College London, UK
Laboratory of Neuromotor Physiology, Santa Lucia
Foundation, Rome, Italy @@ -5209,7 +6197,9 @@
How Important is Weight Symmetry in
Backpropagation?
by -
Center for Brains, Minds and Machines, McGovern Institute, MIT('1694846', 'Qianli Liao', 'qianli liao')
('1700356', 'Joel Z. Leibo', 'joel z. leibo')0b50e223ad4d9465bb92dbf17a7b79eccdb997fbImplicit Elastic Matching with Random Projections for Pose-Variant Face +
Center for Brains, Minds and Machines, McGovern Institute, MIT('1694846', 'Qianli Liao', 'qianli liao')
('1700356', 'Joel Z. Leibo', 'joel z. leibo')0ba1d855cd38b6a2c52860ae4d1a85198b304be4Variable-state Latent Conditional Random Fields +
for Facial Expression Recognition and Action Unit Detection +
Imperial College London, UK
Rutgers University, USA('2616466', 'Robert Walecki', 'robert walecki')
('1729713', 'Ognjen Rudovic', 'ognjen rudovic')
('1736042', 'Vladimir Pavlovic', 'vladimir pavlovic')
('1694605', 'Maja Pantic', 'maja pantic')0b50e223ad4d9465bb92dbf17a7b79eccdb997fbImplicit Elastic Matching with Random Projections for Pose-Variant Face
Recognition
Electrical and Computer Engineering
University of Illinois at Urbana-Champaign
Microsoft Live Labs Research @@ -5222,6 +6212,12 @@
under Pose Variations
Computer vision and Remote Sensing, Berlin university of Technology
Sekr. FR-3-1, Franklinstr. 28/29, Berlin, Germany ('2326207', 'M. Saquib', 'm. saquib')
('2962236', 'Olaf Hellwich', 'olaf hellwich'){saquib;hellwich}@fpk.tu-berlin.de +0bce54bfbd8119c73eb431559fc6ffbba741e6aaPublished as a conference paper at ICLR 2018 +
SKIP RNN: LEARNING TO SKIP STATE UPDATES IN +
RECURRENT NEURAL NETWORKS +
†Barcelona Supercomputing Center, ‡Google Inc, +
Universitat Polit`ecnica de Catalunya, Columbia University('2447185', 'Brendan Jou', 'brendan jou')
('1711068', 'Jordi Torres', 'jordi torres')
('9546964', 'Shih-Fu Chang', 'shih-fu chang'){victor.campos, jordi.torres}@bsc.es, bjou@google.com, +
xavier.giro@upc.edu, shih.fu.chang@columbia.edu 0b2966101fa617b90510e145ed52226e79351072Beyond Verbs: Understanding Actions in Videos
with Text
Department of Computer Science @@ -5354,6 +6350,12 @@
Harvard University
Stony Brook University('2321406', 'Le Hou', 'le hou')
('2576295', 'Chen-Ping Yu', 'chen-ping yu')
('1686020', 'Dimitris Samaras', 'dimitris samaras')lehhou@cs.stonybrook.edu
chenpingyu@fas.harvard.edu
samaras@cs.stonybrook.edu +0bf0029c9bdb0ac61fda35c075deb1086c116956Article +
Modelling of Orthogonal Craniofacial Profiles +
University of York, Heslington, York YO10 5GH, UK
Received: 20 October 2017; Accepted: 23 November 2017; Published: 30 November 2017 +('1694260', 'Hang Dai', 'hang dai')
('1737428', 'Nick Pears', 'nick pears')
('1678859', 'Christian Duncan', 'christian duncan')nick.pears@york.ac.uk +
2 Alder Hey Children’s Hospital, Liverpool L12 2AP, UK; Christian.Duncan@alderhey.nhs.uk +
* Correspondence: hd816@york.ac.uk; Tel.: +44-1904-325-643 0b3f354e6796ef7416bf6dde9e0779b2fcfabed29391618c09a51f72a1c30b2e890f4fac1f595ebdGlobally Tuned Cascade Pose Regression via
Back Propagation with Application in 2D Face
Pose Estimation and Heart Segmentation in 3D @@ -5433,6 +6435,19 @@
1920 Martigny ('2121764', 'Laurent El Shafey', 'laurent el shafey')laurent.el-shafey@idiap.ch
sebastien.marcel@idiap.ch +93420d9212dd15b3ef37f566e4d57e76bb2fab2fAn All-In-One Convolutional Neural Network for Face Analysis +
Center for Automation Research, UMIACS, University of Maryland, College Park, MD('48467498', 'Rajeev Ranjan', 'rajeev ranjan')
('2716670', 'Swami Sankaranarayanan', 'swami sankaranarayanan')
('38171682', 'Carlos D. Castillo', 'carlos d. castillo')
('9215658', 'Rama Chellappa', 'rama chellappa'){rranjan1,swamiviv,carlos,rama}@umiacs.umd.edu +93af36da08bf99e68c9b0d36e141ed8154455ac2Workshop track - ICLR 2018 +
ADDITIVE MARGIN SOFTMAX +
FOR FACE VERIFICATION +
Department of Information and Communication Engineering +
University of Electronic Science and Technology of China
Chengdu, Sichuan 611731 China +
College of Computing
Georgia Institute of Technology
Atlanta, United States. +
Department of Information and Communication Engineering +
University of Electronic Science and Technology of China
Chengdu, Sichuan 611731 China +('47939378', 'Feng Wang', 'feng wang')
('51094998', 'Weiyang Liu', 'weiyang liu')
('8424682', 'Haijun Liu', 'haijun liu')feng.wff@gmail.com +
{wyliu, hanjundai}@gatech.edu +
haijun liu@126.com chengjian@uestc.edu.cn 93cbb3b3e40321c4990c36f89a63534b506b6dafIEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, VOL. 35, NO. 3, JUNE 2005
477
Learning From Examples in the Small Sample Case: @@ -5440,6 +6455,14 @@ ('1822413', 'Guodong Guo', 'guodong guo')
('1724754', 'Charles R. Dyer', 'charles r. dyer')937ffb1c303e0595317873eda5ce85b1a17f9943Eyes Do Not Lie: Spontaneous versus Posed Smiles
Intelligent Systems Lab Amsterdam, University of Amsterdam
Science Park 107, Amsterdam, The Netherlands ('9301018', 'Roberto Valenti', 'roberto valenti')
('1764521', 'Albert Ali Salah', 'albert ali salah')
('1695527', 'Theo Gevers', 'theo gevers')h.dibeklioglu@uva.nl, r.valenti@uva.nl, a.a.salah@uva.nl, th.gevers@uva.nl +93f37c69dd92c4e038710cdeef302c261d3a4f92Compressed Video Action Recognition +
Philipp Kr¨ahenb¨uhl1 +
The University of Texas at Austin, 2Carnegie Mellon University
University of Southern California, 4A9, 5Amazon('2978413', 'Chao-Yuan Wu', 'chao-yuan wu')
('1771307', 'Manzil Zaheer', 'manzil zaheer')
('2804000', 'Hexiang Hu', 'hexiang hu')
('1691629', 'Alexander J. Smola', 'alexander j. smola')
('1758550', 'R. Manmatha', 'r. manmatha')cywu@cs.utexas.edu +
manzil@cmu.edu +
smola@amazon.com +
hexiangh@usc.edu +
philkr@cs.utexas.edu +
manmatha@a9.com 936227f7483938097cc1cdd3032016df54dbd5b6Learning to generalize to new compositions in image understanding
Gonda Brain Research Center, Bar Ilan University, Israel
3Google Research, Mountain View CA, USA
Tel Aviv University, Israel('34815079', 'Yuval Atzmon', 'yuval atzmon')
('1750652', 'Jonathan Berant', 'jonathan berant')
('3451674', 'Vahid Kezami', 'vahid kezami')
('1786843', 'Amir Globerson', 'amir globerson')
('1732280', 'Gal Chechik', 'gal chechik')yuval.atzmon@biu.ac.il @@ -5447,12 +6470,31 @@
Classification via BeFIT Protocols
Idiap Research Institute
Centre du Parc, Rue Marconi 19, CH-1920, Martigny, Switzerland ('2128163', 'Nesli Erdogmus', 'nesli erdogmus')
('2059725', 'Matthias Vanoni', 'matthias vanoni')Email: nesli.erdogmus, matthias.vanoni, marcel@idiap.ch +938ae9597f71a21f2e47287cca318d4a2113feb2Classifier Learning with Prior Probabilities +
for Facial Action Unit Recognition +
1National Laboratory of Pattern Recognition, CASIA +
University of Chinese Academy of Sciences
Rensselaer Polytechnic Institute('49889545', 'Yong Zhang', 'yong zhang')
('38690089', 'Weiming Dong', 'weiming dong')
('39495638', 'Bao-Gang Hu', 'bao-gang hu')
('1726583', 'Qiang Ji', 'qiang ji')zhangyong201303@gmail.com, weiming.dong@ia.ac.cn, hubg@nlpr.ia.ac.cn, qji@ecse.rpi.edu 94b9c0a6515913bad345f0940ee233cdf82fffe1International Journal of Science and Research (IJSR)
ISSN (Online): 2319-7064
Impact Factor (2012): 3.358
Face Recognition using Local Ternary Pattern for
Low Resolution Image -
Research Scholar, CGC Group of Colleges, Gharuan, Punjab, India
Chandigarh University, Gharuan, Punjab, India('40440964', 'Amanpreet Kaur', 'amanpreet kaur')9458c518a6e2d40fb1d6ca1066d6a0c73e1d6b735967 +
Research Scholar, CGC Group of Colleges, Gharuan, Punjab, India
Chandigarh University, Gharuan, Punjab, India('40440964', 'Amanpreet Kaur', 'amanpreet kaur')946017d5f11aa582854ac4c0e0f1b18b06127ef1Tracking Persons-of-Interest +
via Adaptive Discriminative Features +
Xi an Jiaotong University
Hanyang University
University of Illinois, Urbana-Champaign
University of California, Merced
http://shunzhang.me.pn/papers/eccv2016/ +('2481388', 'Shun Zhang', 'shun zhang')
('1698965', 'Yihong Gong', 'yihong gong')
('3068086', 'Jia-Bin Huang', 'jia-bin huang')
('33047058', 'Jongwoo Lim', 'jongwoo lim')
('32014778', 'Jinjun Wang', 'jinjun wang')
('1752333', 'Narendra Ahuja', 'narendra ahuja')
('1715634', 'Ming-Hsuan Yang', 'ming-hsuan yang')94eeae23786e128c0635f305ba7eebbb89af0023Journal 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∗ +
Department of Computer Science +
University of California
Los Angeles, CA 90095, USA +
Department of Computer Science +
University of California
Los Angeles, CA 90095, USA +
Editor: Yoshua Bengio +('16163297', 'Alessandro Achille', 'alessandro achille')
('1715959', 'Stefano Soatto', 'stefano soatto')achille@cs.ucla.edu +
soatto@cs.ucla.edu +944faf7f14f1bead911aeec30cc80c861442b610Action Tubelet Detector for Spatio-Temporal Action Localization +('1881509', 'Vicky Kalogeiton', 'vicky kalogeiton')
('2492127', 'Philippe Weinzaepfel', 'philippe weinzaepfel')
('1749692', 'Vittorio Ferrari', 'vittorio ferrari')
('2462253', 'Cordelia Schmid', 'cordelia schmid')9458c518a6e2d40fb1d6ca1066d6a0c73e1d6b735967
A Benchmark and Comparative Study of
Video-Based Face Recognition
on COX Face Database @@ -5461,7 +6503,8 @@
International Symposium on Robotics and Intelligent Sensors 2012 (IRIS 2012)
Face Recognition From Single Sample Per Person by Learning of
Generic Discriminant Vectors -
aFaculty of Electrical Engineering, University of Technology MARA, Shah Alam, 40450 Selangor, Malaysia
bFaculty of Engineering, International Islamic University, Jalan Gombak, 53100 Kuala Lumpur, Malaysia('7453141', 'Fadhlan Hafiz', 'fadhlan hafiz')
('2412523', 'Amir A. Shafie', 'amir a. shafie')
('9146253', 'Yasir Mohd Mustafah', 'yasir mohd mustafah')94aa8a3787385b13ee7c4fdd2b2b2a574ffcbd819441253b638373a0027a5b4324b4ee5f0dffd670A Novel Scheme for Generating Secure Face +
aFaculty of Electrical Engineering, University of Technology MARA, Shah Alam, 40450 Selangor, Malaysia
bFaculty of Engineering, International Islamic University, Jalan Gombak, 53100 Kuala Lumpur, Malaysia('7453141', 'Fadhlan Hafiz', 'fadhlan hafiz')
('2412523', 'Amir A. Shafie', 'amir a. shafie')
('9146253', 'Yasir Mohd Mustafah', 'yasir mohd mustafah')94aa8a3787385b13ee7c4fdd2b2b2a574ffcbd8194325522c9be8224970f810554611d6a73877c139487cea80f23afe9bccc94deebaa3eefa6affa99Fast, Dense Feature SDM on an iPhone +
Queensland University of Technology, Brisbane, Queensland, Australia
Carnegie Mellon University, Pittsburgh, PA, USA('3231493', 'Ashton Fagg', 'ashton fagg')
('1820249', 'Simon Lucey', 'simon lucey')
('1729760', 'Sridha Sridharan', 'sridha sridharan')9441253b638373a0027a5b4324b4ee5f0dffd670A Novel Scheme for Generating Secure Face
Templates Using BDA
P.G. Student, Department of Computer Engineering,
Associate Professor, Department of Computer @@ -5481,7 +6524,7 @@
2 Matsushita Electric Industrial Co., Ltd.
Okayama University
Okayama-shi, Okayama 700-8530, JAPAN ('3155610', 'Yasuhiro Mukaigawa', 'yasuhiro mukaigawa')
('2740479', 'Yasunori Ishii', 'yasunori ishii')
('1695509', 'Takeshi Shakunaga', 'takeshi shakunaga')mukaigaw@am.sanken.osaka-u.ac.jp -0efdd82a4753a8309ff0a3c22106c570d8a84c20LDA WITH SUBGROUP PCA METHOD FOR FACIAL IMAGE RETRIEVAL +94a11b601af77f0ad46338afd0fa4ccbab909e820efdd82a4753a8309ff0a3c22106c570d8a84c20LDA WITH SUBGROUP PCA METHOD FOR FACIAL IMAGE RETRIEVAL
Human Computer Interaction Lab., Samsung Advanced Institute of Technology, Korea('34600044', 'Wonjun Hwang', 'wonjun hwang')
('1700968', 'Tae-Kyun Kim', 'tae-kyun kim')
('37980373', 'Seokcheol Kee', 'seokcheol kee')wjhwang@sait.samsung.co.kr 0e5dcc6ae52625fd0637c6bba46a973e46d58b9cPareto Models for Multiclass Discriminative Linear
Dimensionality Reduction @@ -5758,7 +6801,9 @@
School of Computing, National University of Singapore, Singapore
Electrical and Computer Engineering, National University of Singapore, Singapore
Beijing Institute of Technology University, P. R. China
4 SAP Innovation Center Network Singapore, Singapore ('2757639', 'Jianshu Li', 'jianshu li')
('2052311', 'Jian Zhao', 'jian zhao')
('1715286', 'Terence Sim', 'terence sim')
('1698982', 'Shuicheng Yan', 'shuicheng yan')
('3124720', 'Shengtao Xiao', 'shengtao xiao')
('33221685', 'Jiashi Feng', 'jiashi feng')
('40345914', 'Fang Zhao', 'fang zhao')
('1943724', 'Jianan Li', 'jianan li'){jianshu,xiao_shengtao,zhaojian90}@u.nus.edu,lijianan15@gmail.com
{elezhf,elefjia,eleyans}@nus.edu.sg,tsim@comp.nus.edu.sg -0ee661a1b6bbfadb5a482ec643573de53a9adf5eJOURNAL OF LATEX CLASS FILES, VOL. X, NO. X, MONTH YEAR +0ee737085af468f264f57f052ea9b9b1f58d7222SiGAN: Siamese Generative Adversarial Network +
for Identity-Preserving Face Hallucination +('3192517', 'Chih-Chung Hsu', 'chih-chung hsu')
('1685088', 'Chia-Wen Lin', 'chia-wen lin')
('3404171', 'Weng-Tai Su', 'weng-tai su')
('1705205', 'Gene Cheung', 'gene cheung')0ee661a1b6bbfadb5a482ec643573de53a9adf5eJOURNAL OF LATEX CLASS FILES, VOL. X, NO. X, MONTH YEAR
On the Use of Discriminative Cohort Score
Normalization for Unconstrained Face Recognition ('1725688', 'Massimo Tistarelli', 'massimo tistarelli')
('2384894', 'Yunlian Sun', 'yunlian sun')
('2404207', 'Norman Poh', 'norman poh')0e36ada8cb9c91f07c9dcaf196d036564e117536Much Ado About Time: Exhaustive Annotation of Temporal Data @@ -5791,7 +6836,11 @@
Multimedia University (MMU), Cyberjaya, Malaysia
2 Faculty of Computing & Informatics,
Multimedia University (MMU), Cyberjaya, Malaysia('2339975', 'John See', 'john see')lengoanhcat@gmail.com, raphael@mmu.edu.my
johnsee@mmu.edu.my -0ed1c1589ed284f0314ed2aeb3a9bbc760dcdeb5Max-Margin Early Event Detectors +0e93a5a7f6dbdb3802173dca05717d27d72bfec0Attribute Recognition by Joint Recurrent Learning of Context and Correlation +
Queen Mary University of London
Vision Semantics Ltd.2 +('48093957', 'Jingya Wang', 'jingya wang')
('2171228', 'Xiatian Zhu', 'xiatian zhu')
('2073354', 'Shaogang Gong', 'shaogang gong')
('47113208', 'Wei Li', 'wei li'){jingya.wang, s.gong, wei.li}@qmul.ac.uk +
eddy@visionsemantics.com +0e2ea7af369dbcaeb5e334b02dd9ba5271b102650ed1c1589ed284f0314ed2aeb3a9bbc760dcdeb5Max-Margin Early Event Detectors
Minh Hoai
Robotics Institute, Carnegie Mellon University('1707876', 'Fernando De la Torre', 'fernando de la torre')0e7c70321462694757511a1776f53d629a1b38f3NIST Special Publication 1136
2012 Proceedings of the @@ -5895,6 +6944,10 @@
light source direction makes with the camera's axis.
1039 ('13801076', 'Feng Xie', 'feng xie')
('3265275', 'Linmi Tao', 'linmi tao')xiefeng97@mails.tsinghua.edu.cn
{linmi, xgy-dcs}@tsinghua.edu.cn +0ee5c4112208995bf2bb0fb8a87efba933a94579Understanding Clothing Preference Based on Body Shape From Online Sources +
Fashion is Taking Shape: +
1Scalable Learning and Perception Group, 2Real Virtual Humans +
Max Planck Institute for Informatics, Saarbr ucken, Germany('26879574', 'Hosnieh Sattar', 'hosnieh sattar')
('1739548', 'Mario Fritz', 'mario fritz')
('2635816', 'Gerard Pons-Moll', 'gerard pons-moll'){sattar,mfritz,gpons}@mpi-inf.mpg.de 0e1a18576a7d3b40fe961ef42885101f4e2630f8Automated Detection and Identification of
Persons in Video
Visual Geometry Group @@ -5918,7 +6971,20 @@
Department of Computer Science and Engineering
Ultra College of Engineering and Technology for Women, India
2Assistant Professor
Department of Computer Science and Engineering -
Vickram College of Engineering, Enathi, Tamil Nadu, India60d765f2c0a1a674b68bee845f6c02741a49b44e60d4cef56efd2f5452362d4d9ac1ae05afa970d1Learning End-to-end Video Classification with Rank-Pooling +
Vickram College of Engineering, Enathi, Tamil Nadu, India60d765f2c0a1a674b68bee845f6c02741a49b44e60c24e44fce158c217d25c1bae9f880a8bd19fc3Controllable Image-to-Video Translation: +
A Case Study on Facial Expression Generation +
MIT CSAIL +
Wenbing Huang +
Tencent AI Lab +
MIT-Waston Lab +
Tencent AI Lab +
Tencent AI Lab +('2548303', 'Lijie Fan', 'lijie fan')
('2551285', 'Chuang Gan', 'chuang gan')
('1768190', 'Junzhou Huang', 'junzhou huang')
('40206014', 'Boqing Gong', 'boqing gong')60e2b9b2e0db3089237d0208f57b22a3aac932c1Frankenstein: Learning Deep Face Representations +
using Small Data +('38819702', 'Guosheng Hu', 'guosheng hu')
('1766837', 'Xiaojiang Peng', 'xiaojiang peng')
('2653152', 'Yongxin Yang', 'yongxin yang')
('1697755', 'Timothy M. Hospedales', 'timothy m. hospedales')
('34602236', 'Jakob Verbeek', 'jakob verbeek')60542b1a857024c79db8b5b03db6e79f74ec8f9fLearning to Detect Human-Object Interactions +
University of Michigan, Ann Arbor
Washington University in St. Louis('2820136', 'Yu-Wei Chao', 'yu-wei chao')
('1860829', 'Yunfan Liu', 'yunfan liu')
('9539636', 'Xieyang Liu', 'xieyang liu')
('9344937', 'Huayi Zeng', 'huayi zeng')
('8342699', 'Jia Deng', 'jia deng'){ywchao,yunfan,lxieyang,jiadeng}@umich.edu +
{zengh}@wustl.edu +60d4cef56efd2f5452362d4d9ac1ae05afa970d1Learning End-to-end Video Classification with Rank-Pooling
Research School of Engineering, The Australian National University, ACT 2601, Australia
Research School of Computer Science, The Australian National University, ACT 2601, Australia('1688071', 'Basura Fernando', 'basura fernando')
('2377076', 'Stephen Gould', 'stephen gould')BASURA.FERNANDO@ANU.EDU.AU
STEPHEN.GOULD@ANU.EDU.AU 60ce4a9602c27ad17a1366165033fe5e0cf68078TECHNICAL NOTE @@ -6164,7 +7230,10 @@
National University of Singapore
4 State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science
and Engineering, Beihang University, Beijing, China('1719250', 'Xiaochun Cao', 'xiaochun cao')
('38188331', 'Hua Zhang', 'hua zhang')
('33465926', 'Xiaojie Guo', 'xiaojie guo')
('2705801', 'Si Liu', 'si liu')
('33610144', 'Xiaowu Chen', 'xiaowu chen')caoxiaochun@iie.ac.cn, huazhang@tju.edu.cn, xj.max.guo@gmail.com,
dcslius@nus.edu.sg, chen@buaa.edu.cn -34d484b47af705e303fc6987413dc0180f5f04a9RI:Medium: Unsupervised and Weakly-Supervised +345cc31c85e19cea9f8b8521be6a37937efd41c2Deep Manifold Traversal: Changing Labels with +
Convolutional Features +
Cornell University, Washington University in St. Louis
*Authors contributing equally +('31693738', 'Jacob R. Gardner', 'jacob r. gardner')
('3222840', 'Paul Upchurch', 'paul upchurch')
('1940272', 'Matt J. Kusner', 'matt j. kusner')
('7769997', 'Yixuan Li', 'yixuan li')
('1706504', 'John E. Hopcroft', 'john e. hopcroft')34d484b47af705e303fc6987413dc0180f5f04a9RI:Medium: Unsupervised and Weakly-Supervised
Discovery of Facial Events
1 Introduction
The face is one of the most powerful channels of nonverbal communication. Facial expression has been a @@ -6204,11 +7273,18 @@
possible facial movement combinations, and characterization of subtle facial behavior.
• We propose two novel non-parametric algorithms for unsupervised and weakly-supervised time-series
analysis. In preliminary experiments these algorithms were able to discover meaningful facial events -345bea5f7d42926f857f395c371118a00382447fTransfiguring Portraits +341002fac5ae6c193b78018a164d3c7295a495e4von Mises-Fisher Mixture Model-based Deep +
learning: Application to Face Verification +('1773090', 'Md. Abul Hasnat', 'md. abul hasnat')
('34767162', 'Jonathan Milgram', 'jonathan milgram')
('34086868', 'Liming Chen', 'liming chen')34ce703b7e79e3072eed7f92239a4c08517b0c55What impacts skin color in digital photos? +
Advanced Digital Sciences Center, University of Illinois at Urbana-Champaign, Singapore('3213946', 'Albrecht Lindner', 'albrecht lindner')
('1702224', 'Stefan Winkler', 'stefan winkler')345bea5f7d42926f857f395c371118a00382447fTransfiguring Portraits
Computer Science and Engineering, University of Washington
Figure 1: Our system’s goal is to let people imagine and explore how they may look like in a different country, era, hair style, hair color, age,
and anything else that can be queried in an image search engine. The examples above show a single input photo (left) and automatically
synthesized appearances of the input person with ”curly hair” (top row), in ”india” (2nd row), and at ”1930” (3rd row). -('2419955', 'Ira Kemelmacher-Shlizerman', 'ira kemelmacher-shlizerman')3463f12ad434d256cd5f94c1c1bfd2dd6df36947Article +('2419955', 'Ira Kemelmacher-Shlizerman', 'ira kemelmacher-shlizerman')34ec83c8ff214128e7a4a4763059eebac59268a6Action Anticipation By Predicting Future +
Dynamic Images +
Australian Centre for Robotic Vision, ANU, Canberra, Australia +('46771280', 'Cristian Rodriguez', 'cristian rodriguez')
('1688071', 'Basura Fernando', 'basura fernando')
('40124570', 'Hongdong Li', 'hongdong li'){cristian.rodriguez, basura.fernando, hongdong.li}@.anu.edu.au +3463f12ad434d256cd5f94c1c1bfd2dd6df36947Article
Facial Expression Recognition with Fusion Features
Extracted from Salient Facial Areas
School of Control Science and Engineering, Shandong University, Jinan 250061, China
Academic Editors: Xue-Bo Jin; Shuli Sun; Hong Wei and Feng-Bao Yang @@ -6327,7 +7403,9 @@
Dimensional Data on Large Scale Dictionaries
Princeton University
Princeton, NJ 08544, USA ('1730249', 'Zhen James Xiang', 'zhen james xiang')
('1693135', 'Peter J. Ramadge', 'peter j. ramadge'){zxiang,haoxu,ramadge}@princeton.edu -5a93f9084e59cb9730a498ff602a8c8703e5d8a5HUSSAIN ET. AL: FACE RECOGNITION USING LOCAL QUANTIZED PATTERNS +5a3da29970d0c3c75ef4cb372b336fc8b10381d7CNN-based Real-time Dense Face Reconstruction +
with Inverse-rendered Photo-realistic Face Images +('8280113', 'Yudong Guo', 'yudong guo')
('2938279', 'Juyong Zhang', 'juyong zhang')
('1688642', 'Jianfei Cai', 'jianfei cai')
('15679675', 'Boyi Jiang', 'boyi jiang')
('48510441', 'Jianmin Zheng', 'jianmin zheng')5a93f9084e59cb9730a498ff602a8c8703e5d8a5HUSSAIN ET. AL: FACE RECOGNITION USING LOCAL QUANTIZED PATTERNS
Face Recognition using Local Quantized
Patterns
Fréderic Jurie @@ -6372,7 +7450,17 @@
gassassa@coeia.edu.sa
monmursi@coeia.edu.sa 5a34a9bb264a2594c02b5f46b038aa1ec3389072Label-Embedding for Image Classification -('2893664', 'Zeynep Akata', 'zeynep akata')
('1723883', 'Florent Perronnin', 'florent perronnin')
('2462253', 'Cordelia Schmid', 'cordelia schmid')5a4c6246758c522f68e75491eb65eafda375b701978-1-4244-4296-6/10/$25.00 ©2010 IEEE +('2893664', 'Zeynep Akata', 'zeynep akata')
('1723883', 'Florent Perronnin', 'florent perronnin')
('2462253', 'Cordelia Schmid', 'cordelia schmid')5a5f9e0ed220ce51b80cd7b7ede22e473a62062cVideos as Space-Time Region Graphs +
Robotics Institute, Carnegie Mellon University
Figure 1. How do you recognize simple actions such as opening book? We argue action +
understanding requires appearance modeling but also capturing temporal dynamics +
(how shape of book changes) and functional relationships. We propose to represent +
videos as space-time region graphs followed by graph convolutions for inference. +('39849136', 'Xiaolong Wang', 'xiaolong wang')
('1737809', 'Abhinav Gupta', 'abhinav gupta')5ac946fc6543a445dd1ee6d5d35afd3783a31353FEATURELESS: BYPASSING FEATURE EXTRACTION IN ACTION CATEGORIZATION +
S. L. Pinteaa, P. S. Mettesa +
J. C. van Gemerta,b, A. W. M. Smeuldersa +
aIntelligent Sensory Information Systems, +
University of Amsterdam
Amsterdam, Netherlands +5a4c6246758c522f68e75491eb65eafda375b701978-1-4244-4296-6/10/$25.00 ©2010 IEEE
1118
ICASSP 2010 5aad5e7390211267f3511ffa75c69febe3b84cc7Driver Gaze Estimation @@ -6390,7 +7478,8 @@
Facial Emotion Recognition and Classification Using Hybridization
Method
Chandigarh Engg. College, Mohali, Punjab, India('6010530', 'Anchal Garg', 'anchal garg')
('9744572', 'Rohit Bajaj', 'rohit bajaj')anchalgarg949@gmail.com, 07696449500 -5aa57a12444dbde0f5645bd9bcec8cb2f573c6a0The International Arab Journal of Information Technology, Vol. 11, No. 2, March 2014 +5a4ec5c79f3699ba037a5f06d8ad309fb4ee682cDownloaded 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. 5aa57a12444dbde0f5645bd9bcec8cb2f573c6a0The International Arab Journal of Information Technology, Vol. 11, No. 2, March 2014

149
@@ -6398,9 +7487,43 @@
Criterion and Linear Discriminant Analysis

(AMFC-LDA) -
COMSATS Institute of Information Technology, Pakistan('2151799', 'Marryam Murtaza', 'marryam murtaza')
('33088042', 'Muhammad Sharif', 'muhammad sharif')
('36739230', 'Mudassar Raza', 'mudassar raza')
('1814986', 'Jamal Hussain Shah', 'jamal hussain shah')5a7520380d9960ff3b4f5f0fe526a00f63791e99The Indian Spontaneous Expression +
COMSATS Institute of Information Technology, Pakistan('2151799', 'Marryam Murtaza', 'marryam murtaza')
('33088042', 'Muhammad Sharif', 'muhammad sharif')
('36739230', 'Mudassar Raza', 'mudassar raza')
('1814986', 'Jamal Hussain Shah', 'jamal hussain shah')5aed0f26549c6e64c5199048c4fd5fdb3c5e69d6International 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 and Science
Thanjavur. +
Affiliated to Anna university, Chennai
recognition can be used +5a7520380d9960ff3b4f5f0fe526a00f63791e99The Indian Spontaneous Expression
Database for Emotion Recognition -('38657440', 'Priyadarshi Patnaik', 'priyadarshi patnaik')
('2680543', 'Aurobinda Routray', 'aurobinda routray')
('2730256', 'Rajlakshmi Guha', 'rajlakshmi guha')5f871838710a6b408cf647aacb3b198983719c311716 +('38657440', 'Priyadarshi Patnaik', 'priyadarshi patnaik')
('2680543', 'Aurobinda Routray', 'aurobinda routray')
('2730256', 'Rajlakshmi Guha', 'rajlakshmi guha')5a07945293c6b032e465d64f2ec076b82e113fa6Pulling Actions out of Context: Explicit Separation for Effective Combination +
Stony Brook University, Stony Brook, NY 11794, USA('50874742', 'Yang Wang', 'yang wang'){wang33, minhhoai}@cs.stonybrook.edu +5fff61302adc65d554d5db3722b8a604e62a8377Additive Margin Softmax for Face Verification +
UESTC +
Georgia Tech +
UESTC +
UESTC +('47939378', 'Feng Wang', 'feng wang')
('51094998', 'Weiyang Liu', 'weiyang liu')
('8424682', 'Haijun Liu', 'haijun liu')
('1709439', 'Jian Cheng', 'jian cheng')feng.wff@gmail.com +
wyliu@gatech.edu +
haijun liu@126.com +
chengjian@uestc.edu.cn +5f771fed91c8e4b666489ba2384d0705bcf75030Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning +
and A New Benchmark for Multi-Human Parsing +
National University of Singapore
National University of Defense Technology
Qihoo 360 AI Institute('46509484', 'Jian Zhao', 'jian zhao')
('2757639', 'Jianshu Li', 'jianshu li')
('48207454', 'Li Zhou', 'li zhou')
('1715286', 'Terence Sim', 'terence sim')
('1698982', 'Shuicheng Yan', 'shuicheng yan')
('33221685', 'Jiashi Feng', 'jiashi feng')chengyu996@gmail.com zhouli2025@gmail.com +
{eleyans, elefjia}@nus.edu.sg +
{zhaojian90, jianshu}@u.nus.edu +
tsim@comp.nus.edu.sg +5fa04523ff13a82b8b6612250a39e1edb5066521Dockerface: an Easy to Install and Use Faster R-CNN Face Detector in a Docker +
Container +
Center for Behavioral Imaging +
College of Computing
Georgia Institute of Technology('31601235', 'Nataniel Ruiz', 'nataniel ruiz')
('1692956', 'James M. Rehg', 'james m. rehg')nataniel.ruiz@gatech.edu +
rehg@gatech.edu +5fa6e4a23da0b39e4b35ac73a15d55cee8608736IJCV 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 +
Submitted: April 19 2017 / Revised: December 12 2017 +('4340744', 'Xi Peng', 'xi peng')5f871838710a6b408cf647aacb3b198983719c311716
Locally Linear Regression for Pose-Invariant
Face Recognition ('1695600', 'Xiujuan Chai', 'xiujuan chai')
('1685914', 'Shiguang Shan', 'shiguang shan')
('1710220', 'Xilin Chen', 'xilin chen')
('1698902', 'Wen Gao', 'wen gao')5f64a2a9b6b3d410dd60dc2af4a58a428c5d85f95f344a4ef7edfd87c5c4bc531833774c3ed23542c Copyright by Ira Cohen, 2003 @@ -6415,12 +7538,128 @@ ('8060096', 'Sheng-hung Hu', 'sheng-hung hu')
('2180892', 'Yikang Li', 'yikang li')
('2913552', 'Baoxin Li', 'baoxin li')Email:shenghun@asu.edu
Email:yikangli@asu.edu
Email:Baoxin.Li@asu.edu -5fa0e6da81acece7026ac1bc6dcdbd8b204a5f0a5feb1341a49dd7a597f4195004fe9b59f67e6707A Deep Ranking Model for Spatio-Temporal Highlight Detection +5f7c4c20ae2731bfb650a96b69fd065bf0bb950eTurk J Elec Eng & Comp Sci +
(2016) 24: 1797 { 1814 +
c⃝ T (cid:127)UB_ITAK +
doi:10.3906/elk-1310-253 +
A new fuzzy membership assignment and model selection approach based on +
dynamic class centers for fuzzy SVM family using the (cid:12)re(cid:13)y algorithm +
Young Researchers and Elite Club, Mashhad Branch, Islamic Azad University, Mashhad, Iran
Faculty of Engineering, Ferdowsi University, Mashhad, Iran
Received: 01.11.2013 +
(cid:15) +
Accepted/Published Online: 30.06.2014 +
(cid:15) +
Final Version: 23.03.2016 +('9437627', 'Omid Naghash Almasi', 'omid naghash almasi')
('4945660', 'Modjtaba Rouhani', 'modjtaba rouhani')5f94969b9491db552ffebc5911a45def99026afeMultimodal Learning and Reasoning for Visual +
Question Answering +
Integrative Sciences and Engineering +
National University of Singapore
Electrical and Computer Engineering +
National University of Singapore('3393294', 'Ilija Ilievski', 'ilija ilievski')
('33221685', 'Jiashi Feng', 'jiashi feng')ilija.ilievski@u.nus.edu +
elefjia@nus.edu.sg +5f758a29dae102511576c0a5c6beda264060a401Fine-grained Video Attractiveness Prediction Using Multimodal +
Deep Learning on a Large Real-world Dataset +
Wuhan University, Tencent AI Lab, National University of Singapore, University of Rochester('3179887', 'Xinpeng Chen', 'xinpeng chen')
('47740660', 'Jingyuan Chen', 'jingyuan chen')
('34264361', 'Lin Ma', 'lin ma')
('1849993', 'Jian Yao', 'jian yao')
('46641573', 'Wei Liu', 'wei liu')
('33642939', 'Jiebo Luo', 'jiebo luo')
('38144094', 'Tong Zhang', 'tong zhang')5fa0e6da81acece7026ac1bc6dcdbd8b204a5f0a5feb1341a49dd7a597f4195004fe9b59f67e6707A Deep Ranking Model for Spatio-Temporal Highlight Detection
from a 360◦ Video
Seoul National University('7877122', 'Youngjae Yu', 'youngjae yu')
('1693291', 'Sangho Lee', 'sangho lee')
('35272603', 'Joonil Na', 'joonil na')
('35365676', 'Jaeyun Kang', 'jaeyun kang')
('1743920', 'Gunhee Kim', 'gunhee kim'){yj.yu, sangho.lee, joonil}@vision.snu.ac.kr, {kjy13411}@gmail.com, gunhee@snu.ac.kr -5f57a1a3a1e5364792b35e8f5f259f92ad561c1fImplicit Sparse Code Hashing +5f0d4a0b5f72d8700cdf8cb179263a8fa866b59bCBMM Memo No. 85 +
06/2018 +
Deep Regression Forests for Age Estimation +
Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University
Johns Hopkins University
College of Computer and Control Engineering, Nankai University 4: Hikvision Research('41187410', 'Wei Shen', 'wei shen')
('9544564', 'Yilu Guo', 'yilu guo')
('46394340', 'Yan Wang', 'yan wang')
('1681247', 'Kai Zhao', 'kai zhao')
('46172451', 'Bo Wang', 'bo wang')
('35922327', 'Alan Yuille', 'alan yuille')5f57a1a3a1e5364792b35e8f5f259f92ad561c1fImplicit Sparse Code Hashing
Institute of Information Science
Academia Sinica, Taiwan -('2144284', 'Tsung-Yu Lin', 'tsung-yu lin')
('2301765', 'Tsung-Wei Ke', 'tsung-wei ke')
('1805102', 'Tyng-Luh Liu', 'tyng-luh liu')5fa932be4d30cad13ea3f3e863572372b915bec85f5906168235613c81ad2129e2431a0e5ef2b6e4Noname manuscript No. +('2144284', 'Tsung-Yu Lin', 'tsung-yu lin')
('2301765', 'Tsung-Wei Ke', 'tsung-wei ke')
('1805102', 'Tyng-Luh Liu', 'tyng-luh liu')5f27ed82c52339124aa368507d66b71d96862cb7Semi-supervised Learning of Classifiers: Theory, Algorithms +
and Their Application to Human-Computer Interaction +
This work has been partially funded by NSF Grant IIS 00-85980. +
DRAFT +('1774778', 'Ira Cohen', 'ira cohen')
('1703601', 'Nicu Sebe', 'nicu sebe')
('1739208', 'Thomas S. Huang', 'thomas s. huang')Ira Cohen: Hewlett-Packard Labs, Palo Alto, CA, USA, ira.cohen@hp.com +
Fabio G. Cozman and Marcelo C. Cirelo: Escola Polit´ecnica, Universidade de S˜ao Paulo, S˜ao Paulo,Brazil. fgcozman@usp.br, +
marcelo.cirelo@poli.usp.br +
Nicu Sebe: Faculty of Science, University of Amsterdam, The Netherlands. nicu@science.uva.nl +
Thomas S. Huang: Beckman Institute, University of Illinois at Urbana-Champaign, USA. huang@ifp.uiuc.edu +5fa932be4d30cad13ea3f3e863572372b915bec85fea26746f3140b12317fcf3bc1680f2746e172eDense Supervision for Visual Comparisons via Synthetic Images +
Semantic Jitter: +
University of Texas at Austin
University of Texas at Austin
Distinguishing subtle differences in attributes is valuable, yet +
learning to make visual comparisons remains non-trivial. Not +
only is the number of possible comparisons quadratic in the +
number of training images, but also access to images adequately +
spanning the space of fine-grained visual differences is limited. +
We propose to overcome the sparsity of supervision problem +
via synthetically generated images. Building on a state-of-the- +
art image generation engine, we sample pairs of training images +
exhibiting slight modifications of individual attributes. Augment- +
ing real training image pairs with these examples, we then train +
attribute ranking models to predict the relative strength of an +
attribute in novel pairs of real images. Our results on datasets of +
faces and fashion images show the great promise of bootstrapping +
imperfect image generators to counteract sample sparsity for +
learning to rank. +
INTRODUCTION +
Fine-grained analysis of images often entails making visual +
comparisons. For example, given two products in a fashion +
catalog, a shopper may judge which shoe appears more pointy +
at the toe. Given two selfies, a teen may gauge in which one he +
is smiling more. Given two photos of houses for sale on a real +
estate website, a home buyer may analyze which facade looks +
better maintained. Given a series of MRI scans, a radiologist +
may judge which pair exhibits the most shape changes. +
In these and many other such cases, we are interested in +
inferring how a pair of images compares in terms of a par- +
ticular property, or “attribute”. That is, which is more pointy, +
smiling, well-maintained, etc. Importantly, the distinctions of +
interest are often quite subtle. Subtle comparisons arise both +
in image pairs that are very similar in almost every regard +
(e.g., two photos of the same individual wearing the same +
clothing, yet smiling more in one photo than the other), as +
well as image pairs that are holistically different yet exhibit +
only slight differences in the attribute in question (e.g., two +
individuals different in appearance, and one is smiling slightly +
more than the other). +
A growing body of work explores computational models +
for visual comparisons [1], [2], [3], [4], [5], [6], [7], [8], [9], +
[10], [11], [12]. In particular, ranking models for “relative +
attributes” [2], [3], [4], [5], [9], [11] use human-ordered pairs +
of images to train a system to predict the relative ordering in +
novel image pairs. +
A major challenge in training a ranking model is the sparsity +
of supervision. That sparsity stems from two factors: label +
availability and image availability. Because training instances +
consist of pairs of images—together with the ground truth +
human judgment about which exhibits the property more +
Fig. 1: Our method “densifies” supervision for training ranking functions to +
make visual comparisons, by generating ordered pairs of synthetic images. +
Here, when learning the attribute smiling, real training images need not be +
representative of the entire attribute space (e.g., Web photos may cluster +
around commonly photographed expressions, like toothy smiles). Our idea +
“fills in” the sparsely sampled regions to enable fine-grained supervision. +
Given a novel pair (top), the nearest synthetic pairs (right) may present better +
training data than the nearest real pairs (left). +
or less—the space of all possible comparisons is quadratic +
in the number of potential +
training images. This quickly +
makes it intractable to label an image collection exhaustively +
for its comparative properties. At the same time, attribute +
comparisons entail a greater cognitive load than, for example, +
object category labeling. Indeed, the largest existing relative +
attribute datasets sample only less than 0.1% of all image pairs +
for ground truth labels [11], and there is a major size gap +
between standard datasets labeled for classification (now in +
the millions [13]) and those for comparisons (at best in the +
thousands [11]). A popular shortcut is to propagate category- +
level comparisons down to image instances [4], [14]—e.g., +
deem all ocean scenes as “more open” than all forest scenes— +
but +
label noise and in practice +
underperforms training with instance-level comparisons [2]. +
this introduces substantial +
Perhaps more insidious than the annotation cost, however, +
is the problem of even curating training images that suf- +
ficiently illustrate fine-grained differences. Critically, sparse +
supervision arises not simply because 1) we lack resources +
to get enough image pairs labeled, but also because 2) we +
lack a direct way to curate photos demonstrating all sorts +
of subtle attribute changes. For example, how might we +
gather unlabeled image pairs depicting all subtle differences +
Novel PairReal PairsSynthetic Pairsvs. ('2206630', 'Aron Yu', 'aron yu')
('1794409', 'Kristen Grauman', 'kristen grauman')aron.yu@utexas.edu +
grauman@cs.utexas.edu +5f5906168235613c81ad2129e2431a0e5ef2b6e4Noname manuscript No.
(will be inserted by the editor)
A Unified Framework for Compositional Fitting of
Active Appearance Models @@ -6437,6 +7676,19 @@
of Online Advertising (SARA) for Audience Behavior Analysis
College of Electronics and Information Engineering, Sichuan University, Chengdu 610064, China
BRIC, University of North Carolina at Chapel Hill, NC 27599, USA
3 HP Labs, Palo Alto, CA 94304, USA
Center for Research in Intelligent Systems, University of California, Riverside, CA 92521, USA('1803478', 'Songfan Yang', 'songfan yang')
('39776603', 'Le An', 'le an')
('1784929', 'Mehran Kafai', 'mehran kafai')
('1707159', 'Bir Bhanu', 'bir bhanu')syang@scu.edu.cn, lan004@unc.edu, mehran.kafai@hp.com, bhanu@cris.ucr.edu +5f453a35d312debfc993d687fd0b7c36c1704b16Clemson University
TigerPrints +
All Theses +
12-2015 +
Theses +
A Training Assistant Tool for the Automated Visual +
Inspection System +
Follow this and additional works at: http://tigerprints.clemson.edu/all_theses +
Part of the Electrical and Computer Engineering Commons +
Recommended Citation +
Ramaraj, Mohan Karthik, "A Training Assistant Tool for the Automated Visual Inspection System" (2015). All Theses. Paper 2285. +
This Thesis is brought to you for free and open access by the Theses at TigerPrints. It has been accepted for inclusion in All Theses by an authorized +('4154752', 'Mohan Karthik Ramaraj', 'mohan karthik ramaraj')Clemson University, rmohankarthik91@gmail.com +
administrator of TigerPrints. For more information, please contact awesole@clemson.edu. 5fc664202208aaf01c9b62da5dfdcd71fdadab29arXiv:1504.05308v1 [cs.CV] 21 Apr 2015 5fac62a3de11125fc363877ba347122529b5aa50AMTnet: Action-Micro-Tube Regression by
End-to-end Trainable Deep Architecture @@ -6451,7 +7703,20 @@
in the Continuous Pose Space
Boston University, USA
2 Disney Research Pittsburgh, USA ('1702188', 'Kun He', 'kun he')
('14517812', 'Leonid Sigal', 'leonid sigal'){hekun,sclaroff}@cs.bu.edu, lsigal@disneyresearch.com -33ac7fd3a622da23308f21b0c4986ae8a86ecd2bBuilding an On-Demand Avatar-Based Health Intervention for Behavior Change +33548531f9ed2ce6f87b3a1caad122c97f1fd2e9International Journal of Computer Applications (0975 – 8887) +
Volume 104 – No.2, October 2014 +
Facial Expression Recognition in Video using +
Adaboost and SVM +
Surabhi Prabhakar +
Department of CSE +
Amity University
Noida, India +
Jaya Sharma +
Shilpi Gupta +
Department of CSE +
Department of CSE +
Amity University
Noida, India +
Amity University
Noida, India +33ac7fd3a622da23308f21b0c4986ae8a86ecd2bBuilding an On-Demand Avatar-Based Health Intervention for Behavior Change
School of Computing and Information Sciences
Florida International University
Miami, FL, 33199, USA
Department of Computer Science @@ -6507,6 +7772,12 @@
Phone: 650-428-1805,650-723-5499
Fax: 650-725-2472 brave,nass@stanford.edu +3328413ee9944de1cc7c9c1d1bf2fece79718ba1Co-Training of Audio and Video Representations +
from Self-Supervised Temporal Synchronization +
Dartmouth College
Facebook Research +
Dartmouth College('3443095', 'Bruno Korbar', 'bruno korbar')
('1687325', 'Du Tran', 'du tran')
('1732879', 'Lorenzo Torresani', 'lorenzo torresani')bruno.18@dartmouth.edu +
trandu@fb.com +
LT@dartmouth.edu 3399f8f0dff8fcf001b711174d29c9d4fde89379Face R-CNN
Tencent AI Lab, China ('39049654', 'Hao Wang', 'hao wang'){hawelwang,michaelzfli,denisji,yitongwang}@tencent.com @@ -6533,10 +7804,12 @@
gshine@stanford.edu
chriseng@stanford.edu 33402ee078a61c7d019b1543bb11cc127c2462d2Self-Supervised Video Representation Learning With Odd-One-Out Networks -
ACRV, The Australian National University University of Oxford QUVA Lab, University of Amsterdam('1688071', 'Basura Fernando', 'basura fernando')33ae696546eed070717192d393f75a1583cd8e2c33f2b44742cc828347ccc5ec488200c25838b664Pooling the Convolutional Layers in Deep ConvNets for Action Recognition +
ACRV, The Australian National University University of Oxford QUVA Lab, University of Amsterdam('1688071', 'Basura Fernando', 'basura fernando')33aa980544a9d627f305540059828597354b076c33ae696546eed070717192d393f75a1583cd8e2c33f2b44742cc828347ccc5ec488200c25838b664Pooling the Convolutional Layers in Deep ConvNets for Action Recognition
School of Computer Science and Technology, Tianjin University, China
School of Computer and Information, Hefei University of Technology, China('2905510', 'Shichao Zhao', 'shichao zhao')
('1732242', 'Yanbin Liu', 'yanbin liu')
('2302512', 'Yahong Han', 'yahong han')
('2248826', 'Richang Hong', 'richang hong'){zhaoshichao, csyanbin, yahong}@tju.edu.cn, hongrc.hfut@gmail.com 3393459600368be2c4c9878a3f65a57dcc0c2cfaEigen-PEP for Video Face Recognition -
Stevens Institute of Technology Adobe Systems Inc('3131569', 'Haoxiang Li', 'haoxiang li')
('1745420', 'Gang Hua', 'gang hua')
('1720987', 'Xiaohui Shen', 'xiaohui shen')
('1721019', 'Jonathan Brandt', 'jonathan brandt')334d6c71b6bce8dfbd376c4203004bd4464c2099BICONVEX RELAXATION FOR SEMIDEFINITE PROGRAMMING IN +
Stevens Institute of Technology Adobe Systems Inc('3131569', 'Haoxiang Li', 'haoxiang li')
('1745420', 'Gang Hua', 'gang hua')
('1720987', 'Xiaohui Shen', 'xiaohui shen')
('1721019', 'Jonathan Brandt', 'jonathan brandt')3352426a67eabe3516812cb66a77aeb8b4df4d1bJOURNAL OF LATEX CLASS FILES, VOL. 4, NO. 5, APRIL 2015 +
Joint Multi-view Face Alignment in the Wild +('3234063', 'Jiankang Deng', 'jiankang deng')
('2814229', 'George Trigeorgis', 'george trigeorgis')
('47943220', 'Yuxiang Zhou', 'yuxiang zhou')334d6c71b6bce8dfbd376c4203004bd4464c2099BICONVEX RELAXATION FOR SEMIDEFINITE PROGRAMMING IN
COMPUTER VISION ('36861219', 'Sohil Shah', 'sohil shah')
('1746575', 'Christoph Studer', 'christoph studer')
('1962083', 'Tom Goldstein', 'tom goldstein')33695e0779e67c7722449e9a3e2e55fde64cfd99Riemannian Coding and Dictionary Learning: Kernels to the Rescue
Australian National University and NICTA
While sparse coding on non-flat Riemannian manifolds has recently become @@ -6623,7 +7896,9 @@
Facial Expression Analysis using Deep Learning
M.Tech Student, SSG Engineering College, Odisha, India
---------------------------------------------------------------------***---------------------------------------------------------------------
examination structures need to analyse the facial exercises -('13518951', 'Raman Patel', 'raman patel')33403e9b4bbd913ae9adafc6751b52debbd45b0e33ad23377eaead8955ed1c2b087a5e536fecf44eAugmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling +('13518951', 'Raman Patel', 'raman patel')33403e9b4bbd913ae9adafc6751b52debbd45b0e33ef419dffef85443ec9fe89a93f928bafdc922eSelfKin: Self Adjusted Deep Model For +
Kinship Verification +
Faculty of Engineering, Bar-Ilan University, Israel('32450996', 'Eran Dahan', 'eran dahan')
('1926432', 'Yosi Keller', 'yosi keller')33ad23377eaead8955ed1c2b087a5e536fecf44eAugmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
∗ indicates equal contribution ('2177037', 'Andrew Kae', 'andrew kae')
('1729571', 'Kihyuk Sohn', 'kihyuk sohn')
('1697141', 'Honglak Lee', 'honglak lee')1 University of Massachusetts, Amherst, MA, USA, {akae,elm}@cs.umass.edu
2 University of Michigan, Ann Arbor, MI, USA, {kihyuks,honglak}@umich.edu @@ -6722,7 +7997,12 @@
© Impact Journals
PERFORMANCE EVALUATION OF ILLUMINATION NORMALIZATION TECHNIQUES
FOR FACE RECOGNITION -
PSG College of Technology, Coimbatore, Tamil Nadu, India0568fc777081cbe6de95b653644fec7b766537b2Learning Expressionlets on Spatio-Temporal Manifold for Dynamic Facial +
PSG College of Technology, Coimbatore, Tamil Nadu, India05891725f5b27332836cf058f04f18d74053803fOne-shot Action Localization by Learning Sequence Matching Network +
The Australian National University
ShanghaiTech University
Fatih Porikli +
The Australian National University('51050729', 'Hongtao Yang', 'hongtao yang')
('33913193', 'Xuming He', 'xuming he')u5226028@anu.edu.au +
hexm@shanghaitech.edu.cn +
fatih.porikli@anu.edu.au +0568fc777081cbe6de95b653644fec7b766537b2Learning Expressionlets on Spatio-Temporal Manifold for Dynamic Facial
Expression Recognition
1Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),
Institute of Computing Technology, CAS, Beijing, 100190, China
University of Chinese Academy of Sciences (UCAS), Beijing, 100049, China
University of Oulu, Finland('1730228', 'Mengyi Liu', 'mengyi liu')
('1685914', 'Shiguang Shan', 'shiguang shan')
('3373117', 'Ruiping Wang', 'ruiping wang')
('1710220', 'Xilin Chen', 'xilin chen')mengyi.liu@vipl.ict.ac.cn, {sgshan, wangruiping, xlchen}@ict.ac.cn @@ -7061,11 +8341,15 @@
lips, eyelids, and eyebrows as well as facial skin texture patterns (Pantic & Rothkrantz,
2000). Typical facial expressions last for a few seconds, normally between 250 milliseconds
and five seconds (Fasel & Luettin, 2003). According to psychologists Ekman and Friesen -('2647218', 'Bogdan J. Matuszewski', 'bogdan j. matuszewski')
('2343120', 'Wei Quan', 'wei quan')05a7be10fa9af8fb33ae2b5b72d108415519a698Multilayer and Multimodal Fusion of Deep Neural Networks +('2647218', 'Bogdan J. Matuszewski', 'bogdan j. matuszewski')
('2343120', 'Wei Quan', 'wei quan')052f994898c79529955917f3dfc5181586282cf8Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos +
1NEC Labs America +
2UC Merced +
Dalian University of Technology
4UC San Diego +('1729571', 'Kihyuk Sohn', 'kihyuk sohn')05a7be10fa9af8fb33ae2b5b72d108415519a698Multilayer and Multimodal Fusion of Deep Neural Networks
for Video Classification
NVIDIA ('2214162', 'Xiaodong Yang', 'xiaodong yang'){xiaodongy, pmolchanov, jkautz}@nvidia.com -05318a267226f6d855d83e9338eaa9e718b2a8dd_______________________________________________________PROCEEDING OF THE 16TH CONFERENCE OF FRUCT ASSOCIATION +050a149051a5d268fcc5539e8b654c2240070c82MAGISTERSKÉ A DOKTORSKÉSTUDIJNÍ PROGRAMY31. 5. 2018SBORNÍKSTUDENTSKÁ VĚDECKÁ KONFERENCE 05318a267226f6d855d83e9338eaa9e718b2a8dd_______________________________________________________PROCEEDING OF THE 16TH CONFERENCE OF FRUCT ASSOCIATION
Age Estimation from Face Images: Challenging
Problem for Audience Measurement Systems
Yaroslavl State University
Russia @@ -7086,6 +8370,10 @@
1 Tel.: 023-65112784, fax: 023-65112784
Received: 26 April 2013 /Accepted: 14 June 2013 /Published: 25 June 2013 ('2623870', 'Lifang Zhou', 'lifang zhou')
('1713814', 'Bin Fang', 'bin fang')
('1964987', 'Weisheng Li', 'weisheng li')
('2103166', 'Lidou Wang', 'lidou wang')1 E-mail: zhoulf@cqupt.edu.cn +053931267af79a89791479b18d1b9cde3edcb415Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) +
Attributes for Improved Attributes: A Multi-Task Network +
Utilizing Implicit and Explicit Relationships for Facial Attribute Classification +
University of Maryland, College Park
College Park, MD('3351637', 'Emily M. Hand', 'emily m. hand')
('9215658', 'Rama Chellappa', 'rama chellappa'){emhand, rama}@umiacs.umd.edu 05f3d1e9fb254b275354ca69018e9ed321dd8755Face Recognition using Optimal Representation
Ensemble
NICTA , Queensland Research Laboratory, QLD, Australia
Grif th University, QLD, Australia
University of Adelaide, SA, Australia
29·4·2013 @@ -7093,6 +8381,11 @@
Partial Face Recognition: An Alignment Free Approach
Department of Computer Science and Engineering
Michigan State University, East Lansing, MI 48824, U.S.A('40397682', 'Shengcai Liao', 'shengcai liao')
('6680444', 'Anil K. Jain', 'anil k. jain'){scliao,jain}@cse.msu.edu +9d58e8ab656772d2c8a99a9fb876d5611fe2fe20Beyond Temporal Pooling: Recurrence and Temporal +
Convolutions for Gesture Recognition in Video +
{lionel.pigou,aaron.vandenoord,sander.dieleman, +
Ghent University
February 11, 2016 +('2660640', 'Lionel Pigou', 'lionel pigou')
('48373216', 'Sander Dieleman', 'sander dieleman')
('10182287', 'Mieke Van Herreweghe', 'mieke van herreweghe')mieke.vanherreweghe, joni.dambre}@ugent.be 9d8ff782f68547cf72b7f3f3beda9dc3e8ecfce6International Journal of Pattern Recognition
and Arti¯cial Intelligence
Vol. 26, No. 1 (2012) 1250002 (9 pages) @@ -7176,7 +8469,9 @@
Savitribai Phule Pune University
D.Y.Patil Institute of Engineering and Technology, Pimpri, Pune
Mahatma Phulenagar, 120/2 Mahaganpati soc, Chinchwad, Pune-19, MH, India
D.Y.Patil Institute of Engineering and Technology, Pimpri, Pune
Computer Department, D.Y.PIET, Pimpri, Pune-18, MH, India
presents -('15731441', 'Shital Shinde', 'shital shinde')
('3392505', 'Archana Chaugule', 'archana chaugule')9d941a99e6578b41e4e32d57ece580c10d578b22Sensors 2015, 15, 4326-4352; doi:10.3390/s150204326 +('15731441', 'Shital Shinde', 'shital shinde')
('3392505', 'Archana Chaugule', 'archana chaugule')9d57c4036a0e5f1349cd11bc342ac515307b6720Landmark Weighting for 3DMM Shape Fitting +
aSchool of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China
bCVSSP, University of Surrey, Guildford, GU2 7XH, UK
A B S T R A C T +('51232704', 'Yu Yanga', 'yu yanga')
('37020604', 'Xiao-Jun Wu', 'xiao-jun wu')
('1748684', 'Josef Kittler', 'josef kittler')9d941a99e6578b41e4e32d57ece580c10d578b22Sensors 2015, 15, 4326-4352; doi:10.3390/s150204326
OPEN ACCESS
sensors
ISSN 1424-8220 @@ -7215,6 +8510,9 @@
Intelligence
Cyprus University of Technology
P.O Box 50329, Lemesos, 3066, Cyprus ('1830709', 'Andreas Lanitis', 'andreas lanitis')andreas.lanitis@cut.ac.cy +9db4b25df549555f9ffd05962b5adf2fd9c86543Nonlinear 3D Face Morphable Model +
Department of Computer Science and Engineering +
Michigan State University, East Lansing MI('1849929', 'Luan Tran', 'luan tran')
('1759169', 'Xiaoming Liu', 'xiaoming liu'){tranluan, liuxm}@msu.edu 9d06d43e883930ddb3aa6fe57c6a865425f28d44Clustering Appearances of Objects Under Varying Illumination Conditions
Computer Science & Engineering
University of California at San Diego
cid:1) Honda Research Institute
David Kriegman @@ -7244,7 +8542,35 @@
Regression for Object Part Localization
Center for Biometrics and Security Research & National Laboratory
of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China('1721677', 'Junjie Yan', 'junjie yan')
('1718623', 'Zhen Lei', 'zhen lei')
('1708973', 'Yang Yang', 'yang yang')
('34679741', 'Stan Z. Li', 'stan z. li'){jjyan,zlei,yang.yang,szli}@nlpr.ia.ac.cn -9c25e89c80b10919865b9c8c80aed98d223ca0c6GENDER PREDICTION BY GAIT ANALYSIS BASED ON TIME SERIES VARIATION OF +9ca7899338129f4ba6744f801e722d53a44e4622Deep Neural Networks Regularization for Structured +
Output Prediction +
Soufiane Belharbi∗ +
INSA Rouen, LITIS +
76000 Rouen, France +
INSA Rouen, LITIS +
76000 Rouen, France +
INSA Rouen, LITIS +
76000 Rouen, France +
INSA Rouen, LITIS +
76000 Rouen, France +
Normandie Univ, UNIROUEN, UNIHAVRE, +
Normandie Univ, UNIROUEN, UNIHAVRE, +
Normandie Univ, UNIROUEN, UNIHAVRE, +
Normandie Univ, UNIROUEN, UNIHAVRE, +('1712446', 'Clément Chatelain', 'clément chatelain')
('1782268', 'Romain Hérault', 'romain hérault')
('37078795', 'Sébastien Adam', 'sébastien adam')soufiane.belharbi@insa-rouen.fr +
romain.herault@insa-rouen.fr +
clement.chatelain@insa-rouen.fr +
sebastien.adam@univ-rouen.fr +9c1664f69d0d832e05759e8f2f001774fad354d6Action representations in robotics: A +
taxonomy and systematic classification +
Journal Title +
XX(X):1–32 +
c(cid:13)The Author(s) 2016 +
Reprints and permission: +
sagepub.co.uk/journalsPermissions.nav +
DOI: 10.1177/ToBeAssigned +
www.sagepub.com/ +('33237072', 'Philipp Zech', 'philipp zech')
('2898615', 'Erwan Renaudo', 'erwan renaudo')
('36081156', 'Simon Haller', 'simon haller')
('46447747', 'Xiang Zhang', 'xiang zhang')9c25e89c80b10919865b9c8c80aed98d223ca0c6GENDER PREDICTION BY GAIT ANALYSIS BASED ON TIME SERIES VARIATION OF
JOINT POSITIONS
Dept. of Computer Science
School of Science and Technology @@ -7261,7 +8587,11 @@
© 2009 Science Publications
Boosting Kernel Discriminative Common Vectors for Face Recognition
1Department of Computer Science and Engineering, -
SRM University, Kattankulathur, Chennai-603 203, Tamilnadu, India
Bharathidasan University, Trichy, India('34608395', 'C. Lakshmi', 'c. lakshmi')
('2594379', 'M. Ponnavaikko', 'm. ponnavaikko')9c781f7fd5d8168ddae1ce5bb4a77e3ca12b40b6 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 +
SRM University, Kattankulathur, Chennai-603 203, Tamilnadu, India
Bharathidasan University, Trichy, India('34608395', 'C. Lakshmi', 'c. lakshmi')
('2594379', 'M. Ponnavaikko', 'm. ponnavaikko')9c065dfb26ce280610a492c887b7f6beccf27319Learning from Video and Text via Large-Scale Discriminative Clustering +
1 ´Ecole Normale Sup´erieure +
2Inria +
3CIIRC +('19200186', 'Antoine Miech', 'antoine miech')
('2285263', 'Jean-Baptiste Alayrac', 'jean-baptiste alayrac')
('2329288', 'Piotr Bojanowski', 'piotr bojanowski')
('1785596', 'Ivan Laptev', 'ivan laptev')
('1782755', 'Josef Sivic', 'josef sivic')9c781f7fd5d8168ddae1ce5bb4a77e3ca12b40b6 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
Research Scholar, PSGR Krishnammal College for Women, Coimbatore
PSGR Krishnammal College for Women, Coimbatore9c373438285101d47ab9332cdb0df6534e3b93d1Occupancy Detection in Vehicles Using Fisher Vector @@ -7271,7 +8601,26 @@ ('1762503', 'Yusuf Artan', 'yusuf artan')
('5942563', 'Peter Paul', 'peter paul')Yusuf.Artan@xerox.com
Peter.Paul@xerox.com 9cbb6e42a35f26cf1d19f4875cd7f6953f10b95dExpression Recognition with Ri-HOG Cascade -
Graduate School of System Informatics, Kobe University, Kobe, 657-8501, Japan
RIEB, Kobe University, Kobe, 657-8501, Japan('2866465', 'Jinhui Chen', 'jinhui chen')
('2834542', 'Zhaojie Luo', 'zhaojie luo')
('1744026', 'Tetsuya Takiguchi', 'tetsuya takiguchi')
('1678564', 'Yasuo Ariki', 'yasuo ariki')9c4cc11d0df2de42d6593f5284cfdf3f05da402aAppears in the 14th International Conference on Pattern Recognition, ICPR’98, Queensland, Australia, August 17-20, 1998. +
Graduate School of System Informatics, Kobe University, Kobe, 657-8501, Japan
RIEB, Kobe University, Kobe, 657-8501, Japan('2866465', 'Jinhui Chen', 'jinhui chen')
('2834542', 'Zhaojie Luo', 'zhaojie luo')
('1744026', 'Tetsuya Takiguchi', 'tetsuya takiguchi')
('1678564', 'Yasuo Ariki', 'yasuo ariki')9ce0d64125fbaf625c466d86221505ad2aced7b1Saliency Based Framework for Facial Expression +
Recognition +
To cite this version: +
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 +
archive 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 +
abroad, 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. +('1943666', 'Rizwan Ahmed Khan', 'rizwan ahmed khan')
('39469581', 'Alexandre Meyer', 'alexandre meyer')
('1971616', 'Hubert Konik', 'hubert konik')
('1768560', 'Saïda Bouakaz', 'saïda bouakaz')
('1943666', 'Rizwan Ahmed Khan', 'rizwan ahmed khan')
('39469581', 'Alexandre Meyer', 'alexandre meyer')
('1971616', 'Hubert Konik', 'hubert konik')
('1768560', 'Saïda Bouakaz', 'saïda bouakaz')9c4cc11d0df2de42d6593f5284cfdf3f05da402aAppears in the 14th International Conference on Pattern Recognition, ICPR’98, Queensland, Australia, August 17-20, 1998.
Enhanced Fisher Linear Discriminant Models for Face Recognition
George Mason University
University Drive, Fairfax, VA 22030-4444, USA
cliu, wechsler ('39664966', 'Chengjun Liu', 'chengjun liu')
('1781577', 'Harry Wechsler', 'harry wechsler')@cs.gmu.edu @@ -7385,7 +8734,9 @@ ('40845190', 'L. Jason Anastasopoulos', 'l. jason anastasopoulos')
('2007721', 'Dhruvil Badani', 'dhruvil badani')
('2647307', 'Crystal Lee', 'crystal lee')
('2361255', 'Shiry Ginosar', 'shiry ginosar')
('40411568', 'Jake Williams', 'jake williams')02e133aacde6d0977bca01ffe971c79097097b7f02567fd428a675ca91a0c6786f47f3e35881bcbdACCEPTED BY IEEE TIP
Deep Label Distribution Learning
With Label Ambiguity -('2226422', 'Bin-Bin Gao', 'bin-bin gao')
('1694501', 'Chao Xing', 'chao xing')
('3407628', 'Chen-Wei Xie', 'chen-wei xie')
('1808816', 'Jianxin Wu', 'jianxin wu')
('1735299', 'Xin Geng', 'xin geng')029b53f32079063047097fa59cfc788b2b550c4b02bd665196bd50c4ecf05d6852a4b9ba027cd9d0026b5b8062e5a8d86c541cfa976f8eee97b30ab8MDLFace: Memorability Augmented Deep Learning for Video Face Recognition +('2226422', 'Bin-Bin Gao', 'bin-bin gao')
('1694501', 'Chao Xing', 'chao xing')
('3407628', 'Chen-Wei Xie', 'chen-wei xie')
('1808816', 'Jianxin Wu', 'jianxin wu')
('1735299', 'Xin Geng', 'xin geng')02f4b900deabbe7efa474f2815dc122a4ddb5b76Local and Global Optimization Techniques in Graph-based Clustering +
The University of Tokyo, Japan('11682769', 'Daiki Ikami', 'daiki ikami')
('2759239', 'Toshihiko Yamasaki', 'toshihiko yamasaki')
('1712839', 'Kiyoharu Aizawa', 'kiyoharu aizawa'){ikami, yamasaki, aizawa}@hal.t.u-tokyo.ac.jp +029b53f32079063047097fa59cfc788b2b550c4b02bd665196bd50c4ecf05d6852a4b9ba027cd9d0026b5b8062e5a8d86c541cfa976f8eee97b30ab8MDLFace: Memorability Augmented Deep Learning for Video Face Recognition
IIIT-Delhi, India ('1931069', 'Gaurav Goswami', 'gaurav goswami')
('1875774', 'Romil Bhardwaj', 'romil bhardwaj')
('39129417', 'Richa Singh', 'richa singh')
('2338122', 'Mayank Vatsa', 'mayank vatsa'){gauravgs,romil11092,rsingh,mayank}@iiitd.ac.in 0235b2d2ae306b7755483ac4f564044f46387648Recognition of Facial Attributes @@ -7448,6 +8799,11 @@
1Department of Electrical and Computer Engineering and the Center for Automation Research,
UMIACS, University of Maryland, College Park, MD
Rutgers, The State University of New Jersey, 508 CoRE, 94 Brett Rd, Piscataway, NJ('3152615', 'Upal Mahbub', 'upal mahbub')
('40599829', 'Sayantan Sarkar', 'sayantan sarkar'){umahbub, ssarkar2, rama}@umiacs.umd.edu
vishal.m.patel@rutgers.edu∗ +a40edf6eb979d1ddfe5894fac7f2cf199519669fImproving Facial Attribute Prediction using Semantic Segmentation +
Center for Research in Computer Vision +
University of Central Florida('3222250', 'Mahdi M. Kalayeh', 'mahdi m. kalayeh')
('40206014', 'Boqing Gong', 'boqing gong')
('1745480', 'Mubarak Shah', 'mubarak shah')Mahdi@eecs.ucf.edu +
bgong@crcv.ucf.edu +
shah@crcv.ucf.edu a46283e90bcdc0ee35c680411942c90df130f448a4a5ad6f1cc489427ac1021da7d7b70fa9a770f2Yudistira and Kurita EURASIP Journal on Image and Video
Processing (2017) 2017:85
DOI 10.1186/s13640-017-0235-9 @@ -7582,7 +8938,13 @@
ASL4GUP 2017
Held in conjunction with IEEE FG 2017, in May 30, 2017,
Washington DC, USA -a3017bb14a507abcf8446b56243cfddd6cdb542bFace Localization and Recognition in Varied +a3d8b5622c4b9af1f753aade57e4774730787a00Pose-Aware Person Recognition +
Anoop Namboodiri (cid:63) +
(cid:63) CVIT, IIIT Hyderabad, India +
† Facebook AI Research +('37956314', 'Vijay Kumar', 'vijay kumar')
('2210374', 'Manohar Paluri', 'manohar paluri')
('1694502', 'C. V. Jawahar', 'c. v. jawahar')a322479a6851f57a3d74d017a9cb6d71395ed806Towards Pose Invariant Face Recognition in the Wild +
National University of Singapore
National University of Defense Technology
Nanyang Technological University
4Panasonic R&D Center Singapore +
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Qihoo 360 AI Institute('2668358', 'Sugiri Pranata', 'sugiri pranata')
('3493398', 'Shengmei Shen', 'shengmei shen')
('1757173', 'Junliang Xing', 'junliang xing')
('46509407', 'Jian Zhao', 'jian zhao')
('5524736', 'Yu Cheng', 'yu cheng')
('33419682', 'Lin Xiong', 'lin xiong')
('2757639', 'Jianshu Li', 'jianshu li')
('40345914', 'Fang Zhao', 'fang zhao')
('1698982', 'Shuicheng Yan', 'shuicheng yan')
('33221685', 'Jiashi Feng', 'jiashi feng')a3017bb14a507abcf8446b56243cfddd6cdb542bFace Localization and Recognition in Varied
Expressions and Illumination
Hui-Yu Huang, Shih-Hang Hsu
@@ -7603,7 +8965,11 @@ ('1848243', 'Erjin Zhou', 'erjin zhou')
('2695115', 'Zhimin Cao', 'zhimin cao')
('2274228', 'Qi Yin', 'qi yin')zej@megvii.com
czm@megvii.com
yq@megvii.com -a3dc109b1dff3846f5a2cc1fe2448230a76ad83fJ.Savitha et al, International Journal of Computer Science and Mobile Computing, Vol.4 Issue.4, April- 2015, pg. 722-731 +a301ddc419cbd900b301a95b1d9e4bb770afc6a3Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) +
DECK: Discovering Event Composition Knowledge from +
Web Images for Zero-Shot Event Detection and Recounting in Videos +
University of Southern California
IIIS, Tsinghua University
‡ Google Research +('2551285', 'Chuang Gan', 'chuang gan')
('1726241', 'Chen Sun', 'chen sun')a3dc109b1dff3846f5a2cc1fe2448230a76ad83fJ.Savitha et al, International Journal of Computer Science and Mobile Computing, Vol.4 Issue.4, April- 2015, pg. 722-731
Available Online at www.ijcsmc.com
International Journal of Computer Science and Mobile Computing
A Monthly Journal of Computer Science and Information Technology @@ -7616,6 +8982,23 @@
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, IndiaEmail: savitha.sanjay1@gmail.com
Email: avsenthilkumar@gmail.com +a3f69a073dcfb6da8038607a9f14eb28b5dab2dbProceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) +
1184 +a38045ed82d6800cbc7a4feb498e694740568258UNLV 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 Scholarship@UNLV. It has been accepted for inclusion in UNLV Theses, Dissertations, +
Professional Papers, and Capstones by an authorized administrator of Digital Scholarship@UNLV. For more information, please contact +
digitalscholarship@unlv.edu. a3f684930c5c45fcb56a2b407d26b63879120cbfLPM for Fast Action Recognition with Large Number of Classes
School of Electrical Engineering and Computer Scinece
University of Ottawa, Ottawa, On, Canada
Department of Electronics and Information Engineering @@ -7689,12 +9072,15 @@
3https://github.com/fshi/actionMBH ('36925389', 'Feng Shi', 'feng shi')
('1745632', 'Emil Petriu', 'emil petriu')fshi98@gmail.com, {laganier, petriu}@site.uottawa.ca
zhenhaiyu@mail.hust.edu.cn -a33f20773b46283ea72412f9b4473a8f8ad751aea3a6a6a2eb1d32b4dead9e702824375ee76e3ce7Multiple Local Curvature Gabor Binary +a3f78cc944ac189632f25925ba807a0e0678c4d5Action Recognition in Realistic Sports Videos +('1799979', 'Khurram Soomro', 'khurram soomro')
('40029556', 'Amir Roshan Zamir', 'amir roshan zamir')a33f20773b46283ea72412f9b4473a8f8ad751aea3a6a6a2eb1d32b4dead9e702824375ee76e3ce7Multiple Local Curvature Gabor Binary
Patterns for Facial Action Recognition
Signal Processing Laboratory (LTS5),
´Ecole Polytechnique F´ed´erale de Lausanne, Switzerland ('2383305', 'Nuri Murat Arar', 'nuri murat arar')
('1710257', 'Jean-Philippe Thiran', 'jean-philippe thiran'){anil.yuce,murat.arar,jean-philippe.thiran}@epfl.ch -a32d4195f7752a715469ad99cb1e6ebc1a099de6Hindawi Publishing Corporation +a32c5138c6a0b3d3aff69bcab1015d8b043c91fbDownloaded 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. a32d4195f7752a715469ad99cb1e6ebc1a099de6Hindawi Publishing Corporation
e Scientific World Journal
Volume 2014, Article ID 749096, 10 pages
http://dx.doi.org/10.1155/2014/749096 @@ -7856,7 +9242,15 @@
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 -a3a97bb5131e7e67316b649bbc2432aaa1a6556eCogn Affect Behav Neurosci +a36c8a4213251d3fd634e8893ad1b932205ad1caVideos from the 2013 Boston Marathon: +
An Event Reconstruction Dataset for +
Synchronization and Localization +
CMU-LTI-018 +
Language Technologies Institute
School of Computer Science +
Carnegie Mellon University
5000 Forbes Ave., Pittsburgh, PA 15213 +
www.lti.cs.cmu.edu +
© October 1, 2016 +('1915796', 'Junwei Liang', 'junwei liang')
('47896638', 'Han Lu', 'han lu')
('2927024', 'Shoou-I Yu', 'shoou-i yu')
('7661726', 'Alexander G. Hauptmann', 'alexander g. hauptmann')a3a97bb5131e7e67316b649bbc2432aaa1a6556eCogn 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 @@ -7918,12 +9312,19 @@
Yining Wang (ynwang.yining@gmail.com)
Zhulin Li (li-zl12@mails.tsinghua.edu.cn)
Zhuowen Tu (ztu@ucsd.edu) -b5cd9e5d81d14868f1a86ca4f3fab079f63a366dTag-based Video Retrieval by Embedding Semantic Content in a Continuous +b5968e7bb23f5f03213178c22fd2e47af3afa04cMulti-Human Parsing in the Wild +
National University of Singapore
Beijing Jiaotong University
March 16, 2018 +('2757639', 'Jianshu Li', 'jianshu li')
('2263674', 'Yidong Li', 'yidong li')
('46509407', 'Jian Zhao', 'jian zhao')
('1715286', 'Terence Sim', 'terence sim')
('33221685', 'Jiashi Feng', 'jiashi feng')
('1698982', 'Shuicheng Yan', 'shuicheng yan')b5cd9e5d81d14868f1a86ca4f3fab079f63a366dTag-based Video Retrieval by Embedding Semantic Content in a Continuous
Word Space
University of Southern California
Ram Nevatia
Cees G.M. Snoek
University of Amsterdam('3407713', 'Arnav Agharwal', 'arnav agharwal')
('3407447', 'Rama Kovvuri', 'rama kovvuri'){agharwal,nkovvuri,nevatia}@usc.edu
cgmsnoek@uva.nl +b558be7e182809f5404ea0fcf8a1d1d9498dc01aBottom-up and top-down reasoning with convolutional latent-variable models +
UC Irvine +
UC Irvine +('2894848', 'Peiyun Hu', 'peiyun hu')
('1770537', 'Deva Ramanan', 'deva ramanan')peiyunh@ics.uci.edu +
dramanan@ics.uci.edu b5cd8151f9354ee38b73be1d1457d28e39d3c2c6Finding Celebrities in Video
Electrical Engineering and Computer Sciences
University of California at Berkeley
Technical Report No. UCB/EECS-2006-77 @@ -7935,7 +9336,7 @@
Significance of image representation for face verification
Received: 29 August 2006 / Revised: 28 March 2007 / Accepted: 28 March 2007 / Published online: 1 May 2007
© Springer-Verlag London Limited 2007 -('2627097', 'Anil Kumar Sao', 'anil kumar sao')
('1783087', 'B. V. K. Vijaya Kumar', 'b. v. k. vijaya kumar')b506aa23949b6d1f0c868ad03aaaeb5e5f7f6b57UNIVERSITY OF CALIFORNIA
RIVERSIDE +('2627097', 'Anil Kumar Sao', 'anil kumar sao')
('1783087', 'B. V. K. Vijaya Kumar', 'b. v. k. vijaya kumar')b562def2624f59f7d3824e43ecffc990ad780898b506aa23949b6d1f0c868ad03aaaeb5e5f7f6b57UNIVERSITY OF CALIFORNIA
RIVERSIDE
Modeling Social and Temporal Context for Video Analysis
A Dissertation submitted in partial satisfaction
of the requirements for the degree of @@ -7960,7 +9361,15 @@
Spring Term
2015
Major Professor: Gita R. Sukthankar -b5da4943c348a6b4c934c2ea7330afaf1d655e79Facial Landmarks Detection by Self-Iterative Regression based +b5f2846a506fc417e7da43f6a7679146d99c5e96UCF101: A Dataset of 101 Human Actions +
Classes From Videos in The Wild +
CRCV-TR-12-01 +
November 2012 +
Keywords: Action Dataset, UCF101, UCF50, Action Recognition +
Center for Research in Computer Vision +
University of Central Florida
4000 Central Florida Blvd. +
Orlando, FL 32816-2365 USA +('1799979', 'Khurram Soomro', 'khurram soomro')
('40029556', 'Amir Roshan Zamir', 'amir roshan zamir')
('1745480', 'Mubarak Shah', 'mubarak shah')b5da4943c348a6b4c934c2ea7330afaf1d655e79Facial Landmarks Detection by Self-Iterative Regression based
Landmarks-Attention Network
University of Chinese Academy of Sciences, Beijing, China
2 Microsoft Research Asia, Beijing, China ('33325349', 'Tao Hu', 'tao hu')
('3245785', 'Honggang Qi', 'honggang qi')
('1697982', 'Jizheng Xu', 'jizheng xu')
('1689702', 'Qingming Huang', 'qingming huang')hutao16@mails.ucas.ac.cn, hgqi@ucas.ac.cn @@ -8076,7 +9485,7 @@
1Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
2IRISA & Inria Rennes , CNRS, Rennes, France ('2823797', 'Cassio E. dos Santos', 'cassio e. dos santos')
('1708671', 'Guillaume Gravier', 'guillaume gravier')
('1679142', 'William Robson Schwartz', 'william robson schwartz')cass@dcc.ufmg.br, guig@irisa.fr, william@dcc.ufmg.br -b51e3d59d1bcbc023f39cec233f38510819a2cf9CBMM Memo No. 003 +b59f441234d2d8f1765a20715e227376c7251cd7b51e3d59d1bcbc023f39cec233f38510819a2cf9CBMM Memo No. 003
March 27, 2014
Can a biologically-plausible hierarchy effectively
replace face detection, alignment, and @@ -8204,6 +9613,15 @@
for
techniques ('29695322', 'Ben Fielding', 'ben fielding')
('1921534', 'Philip Kinghorn', 'philip kinghorn')
('2801063', 'Kamlesh Mistry', 'kamlesh mistry')
('1712838', 'Li Zhang', 'li zhang'){ben.fielding, philip.kinghorn, kamlesh.mistry, li.zhang (corr. author)}@northumbria.ac.uk +b59cee1f647737ec3296ccb3daa25c890359c307Continuously Reproducing Toolchains in Pattern +
Recognition and Machine Learning Experiments +
A. Anjos +
Idiap Research Institute
Martigny, Switzerland +
M. G¨unther +
Vision and Security Technology +
University of Colorado
Colorado Springs, USA +andre.anjos@idiap.ch +
mgunther@vast.uccs.edu b249f10a30907a80f2a73582f696bc35ba4db9e2Improved graph-based SFA: Information preservation
complements the slowness principle
Institut f¨ur Neuroinformatik @@ -8318,7 +9736,14 @@
For Rapid Annotation
1 CSIRO, Brisbane, QLD, Australia
Queensland University of Technology, Brisbane, QLD, Australia
Carnegie Mellon University, Pittsburgh, PA, USA('3231493', 'Ashton Fagg', 'ashton fagg')
('1729760', 'Sridha Sridharan', 'sridha sridharan')
('1820249', 'Simon Lucey', 'simon lucey')ashton@fagg.id.au, s.sridharan@qut.edu.au, slucey@cs.cmu.edu -b235b4ccd01a204b95f7408bed7a10e080623d2eRegularizing Flat Latent Variables with Hierarchical Structures +b2c60061ad32e28eb1e20aff42e062c9160786beDiverse and Controllable Image Captioning with +
Part-of-Speech Guidance +
University of Illinois at Urbana-Champaign('2118997', 'Aditya Deshpande', 'aditya deshpande')
('29956361', 'Jyoti Aneja', 'jyoti aneja')
('46659761', 'Liwei Wang', 'liwei wang'){ardeshp2, janeja2, lwang97, aschwing, daf}@illinois.edu +b2b535118c5c4dfcc96f547274cdc05dde629976JOURNAL OF IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, VOL. XX, NO. X, XXX 2017 +
Automatic Recognition of Facial Displays of +
Unfelt Emotions +
Escalera, Xavier Bar´o, Sylwia Hyniewska, Member, IEEE, J¨uri Allik, +('38370357', 'Kaustubh Kulkarni', 'kaustubh kulkarni')
('22197083', 'Ciprian Adrian Corneanu', 'ciprian adrian corneanu')
('22211769', 'Ikechukwu Ofodile', 'ikechukwu ofodile')
('47608164', 'Gholamreza Anbarjafari', 'gholamreza anbarjafari')b235b4ccd01a204b95f7408bed7a10e080623d2eRegularizing Flat Latent Variables with Hierarchical Structures ('7246002', 'Rongcheng Lin', 'rongcheng lin')
('2703486', 'Huayu Li', 'huayu li')
('38472218', 'Xiaojun Quan', 'xiaojun quan')
('2248826', 'Richang Hong', 'richang hong')
('2737890', 'Zhiang Wu', 'zhiang wu')
('1874059', 'Yong Ge', 'yong ge')(cid:117)UNC Charlotte. Email: {rlin4, hli38, yong.ge}@uncc.edu,
(cid:63) Hefei University of Technology. Email: hongrc@hfut.edu.cn
† Institute for Infocomm Research. Email: quanx@i2r.a-star.edu.sg @@ -8346,6 +9771,28 @@
Department of Signal Processing
Tampere University of Technology
Tampere 33720, Finland ('40394658', 'Ke Chen', 'ke chen')firstname.lastname@tut.fi +d904f945c1506e7b51b19c99c632ef13f340ef4cA scalable 3D HOG model for fast object detection and viewpoint estimation +
KU Leuven, ESAT/PSI - iMinds +
Kasteelpark Arenberg 10 B-3001 Leuven, Belgium +('3048367', 'Marco Pedersoli', 'marco pedersoli')
('1704728', 'Tinne Tuytelaars', 'tinne tuytelaars')firstname.lastname@esat.kuleuven.be +d949fadc9b6c5c8b067fa42265ad30945f9caa99Rethinking Feature Discrimination and +
Polymerization for Large-scale Recognition +
The Chinese University of Hong Kong('1715752', 'Yu Liu', 'yu liu')
('46382329', 'Hongyang Li', 'hongyang li')
('31843833', 'Xiaogang Wang', 'xiaogang wang'){yuliu, yangli, xgwang}@ee.cuhk.edu.hk +d93baa5ecf3e1196b34494a79df0a1933fd2b4ecPrecise Temporal Action Localization by +
Evolving Temporal Proposals +
East China Normal University
Shanghai, China +
University of Washington
Seattle, WA, USA +
Shanghai Advanced Research +
Institute, CAS, China
East China Normal University
Shanghai, China +
Shanghai Advanced Research +
Institute, CAS, China
Liang He +
East China Normal University
Shanghai, China +('31567595', 'Haonan Qiu', 'haonan qiu')
('1803391', 'Yao Lu', 'yao lu')
('3015119', 'Yingbin Zheng', 'yingbin zheng')
('47939010', 'Feng Wang', 'feng wang')
('1743864', 'Hao Ye', 'hao ye')hnqiu@ica.stc.sh.cn +
luyao@cs.washington.edu +
zhengyb@sari.ac.cn +
fwang@cs.ecnu.edu.cn +
yeh@sari.ac.cn +
lhe@cs.ecnu.edu.cn d961617db4e95382ba869a7603006edc4d66ac3bExperimenting Motion Relativity for Action Recognition
with a Large Number of Classes
East China Normal University
500 Dongchuan Rd., Shanghai, China @@ -8402,7 +9849,21 @@
Available online at: www.ijarcsse.com
A Research - Face Recognition by Using Near Set Theory
Department of Computer Science and Engineering -
Abha Gaikwad -Patil College of Engineering, Nagpur, Maharashtra, India('9231464', 'Bhakti Kurhade', 'bhakti kurhade')d9327b9621a97244d351b5b93e057f159f24a21eSCIENCE CHINA +
Abha Gaikwad -Patil College of Engineering, Nagpur, Maharashtra, India('9231464', 'Bhakti Kurhade', 'bhakti kurhade')d9c4b1ca997583047a8721b7dfd9f0ea2efdc42cLearning Inference Models for Computer Vision +d9bad7c3c874169e3e0b66a031c8199ec0bc2c1fIt All Matters: +
Reporting Accuracy, Inference Time and Power Consumption +
for Face Emotion Recognition on Embedded Systems +
Institute of Telecommunications, TU Wien
Movidius an Intel Company +
Dexmont Pe˜na +
Movidius an Intel Company +
Movidius an Intel Company +
ALaRI, Faculty of Informatics, USI +('48802034', 'Jelena Milosevic', 'jelena milosevic')
('51129064', 'Andrew Forembsky', 'andrew forembsky')
('9151916', 'David Moloney', 'david moloney')
('1697550', 'Miroslaw Malek', 'miroslaw malek')jelena.milosevic@tuwien.ac.at +
andrew.forembsky2@mail.dcu.ie +
dexmont.pena@intel.com +
david.moloney@intel.com +
miroslaw.malek@usi.ch +d9327b9621a97244d351b5b93e057f159f24a21eSCIENCE CHINA
Information Sciences
. RESEARCH PAPERS .
December 2010 Vol. 53 No. 12: 2415–2428 @@ -8415,7 +9876,12 @@ d915e634aec40d7ee00cbea96d735d3e69602f1aTwo-Stream convolutional nets for action recognition in untrimmed video
Stanford University
Stanford University('3308619', 'Kenneth Jung', 'kenneth jung')
('5590869', 'Song Han', 'song han')kjung@stanford.edu
songhan@stanford.edu -ac1d97a465b7cc56204af5f2df0d54f819eef8a6A Look at Eye Detection for Unconstrained +aca232de87c4c61537c730ee59a8f7ebf5ecb14fEBGM VS SUBSPACE PROJECTION FOR FACE RECOGNITION +
19.5 Km Markopoulou Avenue, P.O. Box 68, Peania, Athens, Greece +
Athens Information Technology +
Keywords: +
Human-Machine Interfaces, Computer Vision, Face Recognition. +('40089976', 'Andreas Stergiou', 'andreas stergiou')
('1702943', 'Aristodemos Pnevmatikakis', 'aristodemos pnevmatikakis')
('1725498', 'Lazaros Polymenakos', 'lazaros polymenakos')ac1d97a465b7cc56204af5f2df0d54f819eef8a6A Look at Eye Detection for Unconstrained
Environments
Key words: Unconstrained Face Recognition, Eye Detection, Machine Learning,
Correlation Filters, Photo-head Testing Protocol @@ -8444,7 +9910,9 @@
Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland('1848903', 'James Booth', 'james booth')
('2931390', 'Anastasios Roussos', 'anastasios roussos')
('1776444', 'Stefanos Zafeiriou', 'stefanos zafeiriou')
('5137183', 'Allan Ponniah', 'allan ponniah')
('2421231', 'David Dunaway', 'david dunaway')⋆{james.booth,troussos,s.zafeiriou}@imperial.ac.uk, †{allan.ponniah,david.dunaway}@gosh.nhs.uk ac6c3b3e92ff5fbcd8f7967696c7aae134bea209Deep Cascaded Bi-Network for
Face Hallucination(cid:63) -
The Chinese University of Hong Kong
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
University of California, Merced('2226254', 'Shizhan Zhu', 'shizhan zhu')
('2391885', 'Sifei Liu', 'sifei liu')
('1717179', 'Chen Change Loy', 'chen change loy')
('1741901', 'Xiaoou Tang', 'xiaoou tang')ac21c8aceea6b9495574f8f9d916e571e2fc497fPose-Independent Identity-based Facial Image +
The Chinese University of Hong Kong
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
University of California, Merced('2226254', 'Shizhan Zhu', 'shizhan zhu')
('2391885', 'Sifei Liu', 'sifei liu')
('1717179', 'Chen Change Loy', 'chen change loy')
('1741901', 'Xiaoou Tang', 'xiaoou tang')ac855f0de9086e9e170072cb37400637f0c9b735Fast Geometrically-Perturbed Adversarial Faces +
West Virginia University('35477977', 'Ali Dabouei', 'ali dabouei')
('30319988', 'Sobhan Soleymani', 'sobhan soleymani')
('8147588', 'Nasser M. Nasrabadi', 'nasser m. nasrabadi'){ad0046, ssoleyma}@mix.wvu.edu, {jeremy.dawson, nasser.nasrabadi}@mail.wvu.edu +ac21c8aceea6b9495574f8f9d916e571e2fc497fPose-Independent Identity-based Facial Image
Retrieval using Contextual Similarity
King Abdullah University of Science and Technology 4700, Thuwal, Saudi Arabia('3036634', 'Islam Almasri', 'islam almasri')ac6a9f80d850b544a2cbfdde7002ad5e25c05ac6779
Privacy-Protected Facial Biometric Verification @@ -8452,6 +9920,89 @@ ('1690116', 'Ahmed Bouridane', 'ahmed bouridane')
('1691478', 'Danny Crookes', 'danny crookes')
('1739563', 'M. Emre Celebi', 'm. emre celebi')
('39486168', 'Hua-Liang Wei', 'hua-liang wei')aca273a9350b10b6e2ef84f0e3a327255207d0f5aca75c032cfb0b2eb4c0ae56f3d060d8875e43f9Co-Regularized Ensemble for Feature Selection
School of Computer Science and Technology, Tianjin University, China
School of Information Technology and Electrical Engineering, The University of Queensland
3Tianjin Key Laboratory of Cognitive Computing and Application ('2302512', 'Yahong Han', 'yahong han')
('1698559', 'Yi Yang', 'yi yang')
('1720932', 'Xiaofang Zhou', 'xiaofang zhou')yahong@tju.edu.cn, yee.i.yang@gmail.com, zxf@itee.uq.edu.au +accbd6cd5dd649137a7c57ad6ef99232759f7544FACIAL EXPRESSION RECOGNITION WITH LOCAL BINARY PATTERNS +
AND LINEAR PROGRAMMING +
1 Machine Vision Group, Infotech Oulu and Dept. of Electrical and Information Engineering +
P. O. Box 4500 Fin-90014 University of Oulu, Finland
College of Electronics and Information, Northwestern Polytechnic University
710072 Xi’an, China +
In this work, we propose a novel approach to recognize facial expressions from static +
images. First, the Local Binary Patterns (LBP) are used to efficiently represent the facial +
images and then the Linear Programming (LP) technique is adopted to classify the seven +
facial expressions anger, disgust, fear, happiness, sadness, surprise and neutral. +
Experimental results demonstrate an average recognition accuracy of 93.8% on the JAFFE +
database, which outperforms the rates of all other reported methods on the same database. +
Introduction +
Facial expression recognition from static +
images is a more challenging problem +
than from image sequences because less +
information for expression actions +
is +
available. However, information in a +
single image is sometimes enough for +
expression recognition, and +
in many +
applications it is also useful to recognize +
single image’s facial expression. +
In the recent years, numerous approaches +
to facial expression analysis from static +
images have been proposed [1] [2]. These +
methods +
face +
representation and similarity measure. +
For instance, Zhang [3] used two types of +
features: the geometric position of 34 +
manually selected fiducial points and a +
set of Gabor wavelet coefficients at these +
points. These two types of features were +
used both independently and jointly with +
a multi-layer perceptron for classification. +
Guo and Dyer [4] also adopted a similar +
face representation, combined with linear +
to carry out +
programming +
selection +
simultaneous +
and +
classifier +
they reported +
technique +
feature +
training, and +
differ +
generally +
in +
a +
simple +
imperative question +
better result. Lyons et al. used a similar face +
representation with +
LDA-based +
classification scheme [5]. All the above methods +
required the manual selection of fiducial points. +
Buciu et al. used ICA and Gabor representation for +
facial expression recognition and reported good result +
on the same database [6]. However, a suitable +
combination of feature extraction and classification is +
still one +
for expression +
recognition. +
In this paper, we propose a novel method for facial +
expression recognition. In the feature extraction step, +
the Local Binary Pattern (LBP) operator is used to +
describe facial expressions. In the classification step, +
seven expressions (anger, disgust, fear, happiness, +
sadness, surprise and neutral) are decomposed into 21 +
expression pairs such as anger-fear, happiness- +
sadness etc. 21 classifiers are produced by the Linear +
Programming (LP) technique, each corresponding to +
one of the 21 expression pairs. A simple binary tree +
tournament scheme with pairwise comparisons is +
Face Representation with Local Binary Patterns +
+
Fig.1 shows the basic LBP operator [7], in which the +
original 3×3 neighbourhood at the left is thresholded +
by the value of the centre pixel, and a binary pattern +('4729239', 'Xiaoyi Feng', 'xiaoyi feng')
('1714724', 'Matti Pietikäinen', 'matti pietikäinen')
('1751372', 'Abdenour Hadid', 'abdenour hadid'){xiaoyi,mkp,hadid}@ee.oulu.fi +
fengxiao@nwpu.edu.cn ac51d9ddbd462d023ec60818bac6cdae83b66992Hindawi Publishing Corporation
Computational Intelligence and Neuroscience
Volume 2015, Article ID 709072, 10 pages @@ -8566,11 +10117,26 @@
anger, disgust, and surprise). In their approach, the amount of
facial movements change and timing have been quantified by ('40432410', 'Peng Wu', 'peng wu')
('34068333', 'Isabel Gonzalez', 'isabel gonzalez')
('3348420', 'Dongmei Jiang', 'dongmei jiang')
('1970907', 'Hichem Sahli', 'hichem sahli')
('3041213', 'Eric Kerckhofs', 'eric kerckhofs')
('2540163', 'Marie Vandekerckhove', 'marie vandekerckhove')
('40432410', 'Peng Wu', 'peng wu')Correspondence should be addressed to Peng Wu; pwu@etro.vub.ac.be -ac820d67b313c38b9add05abef8891426edd5afbac9a331327cceda4e23f9873f387c9fd161fad76Deep Convolutional Neural Network for Age Estimation based on +acee2201f8a15990551804dd382b86973eb7c0a8To Boost or Not to Boost? On the Limits of +
Boosted Trees for Object Detection +
Computer Vision and Robotics Research Laboratory
University of California San Diego('1802326', 'Eshed Ohn-Bar', 'eshed ohn-bar'){eohnbar, mtrivedi}@ucsd.edu +ac0d3f6ed5c42b7fc6d7c9e1a9bb80392742ad5eac820d67b313c38b9add05abef8891426edd5afbac9a331327cceda4e23f9873f387c9fd161fad76Deep Convolutional Neural Network for Age Estimation based on
VGG-Face Model
University of Bridgeport
University of Bridgeport
Technology Building, Bridgeport CT 06604 USA ('7404315', 'Zakariya Qawaqneh', 'zakariya qawaqneh')
('34792425', 'Arafat Abu Mallouh', 'arafat abu mallouh')
('2791535', 'Buket D. Barkana', 'buket d. barkana')Emails: {zqawaqneh; aabumall@my.bridgeport.edu}, bbarkana@bridgeport.edu -ac12ba5bf81de83991210b4cd95b4ad048317681Combining Deep Facial and Ambient Features +ac26166857e55fd5c64ae7194a169ff4e473eb8bPersonalized Age Progression with Bi-level +
Aging Dictionary Learning +('2287686', 'Xiangbo Shu', 'xiangbo shu')
('8053308', 'Jinhui Tang', 'jinhui tang')
('3233021', 'Zechao Li', 'zechao li')
('2356867', 'Hanjiang Lai', 'hanjiang lai')
('1698982', 'Shuicheng Yan', 'shuicheng yan')ac559873b288f3ac28ee8a38c0f3710ea3f986d9Team DEEP-HRI Moments in Time Challenge 2018 Technical Report +
Hikvision Research Institute('39816387', 'Chao Li', 'chao li')
('48375401', 'Zhi Hou', 'zhi hou')
('35843399', 'Jiaxu Chen', 'jiaxu chen')
('9162532', 'Jiqiang Zhou', 'jiqiang zhou')
('50322310', 'Di Xie', 'di xie')
('3290437', 'Shiliang Pu', 'shiliang pu')ac8e09128e1e48a2eae5fa90f252ada689f6eae7Leolani: a reference machine with a theory of +
mind for social communication +
VU University Amsterdam, Computational Lexicology and Terminology Lab, De
Boelelaan 1105, 1081HV Amsterdam, The Netherlands +
www.cltl.nl +('50998926', 'Bram Kraaijeveld', 'bram kraaijeveld'){p.t.j.m.vossen,s.baezsantamaria,l.bajcetic,b.kraaijeveld}@vu.nl +ac8441e30833a8e2a96a57c5e6fede5df81794afIEEE TRANSACTIONS ON IMAGE PROCESSING +
Hierarchical Representation Learning for Kinship +
Verification +('1952698', 'Naman Kohli', 'naman kohli')
('2338122', 'Mayank Vatsa', 'mayank vatsa')
('39129417', 'Richa Singh', 'richa singh')
('2487227', 'Afzel Noore', 'afzel noore')
('2641605', 'Angshul Majumdar', 'angshul majumdar')ac86ccc16d555484a91741e4cb578b75599147b2Morphable Face Models - An Open Framework +
Gravis Research Group, University of Basel('3277377', 'Thomas Gerig', 'thomas gerig')
('39550224', 'Clemens Blumer', 'clemens blumer')
('34460642', 'Bernhard Egger', 'bernhard egger')
('1687079', 'Thomas Vetter', 'thomas vetter')ac12ba5bf81de83991210b4cd95b4ad048317681Combining Deep Facial and Ambient Features
for First Impression Estimation
Program of Computational Science and Engineering, Bo gazi ci University
Bebek, Istanbul, Turkey
Nam k Kemal University
C¸ orlu, Tekirda˘g, Turkey @@ -8728,7 +10294,15 @@
Dr. Antonio Criminisi
Florian Schroff
St. Anne s College
Trinity, 2009 -adfaf01773c8af859faa5a9f40fb3aa9770a8aa7LARGE SCALE VISUAL RECOGNITION +ad0d4d5c61b55a3ab29764237cd97be0ebb0ddffWeakly Supervised Action Localization by Sparse Temporal Pooling Network +
University of California
Irvine, CA, USA +
Google +
Venice, CA, USA +
Seoul National University
Seoul, Korea +('1998374', 'Phuc Nguyen', 'phuc nguyen')
('40282288', 'Ting Liu', 'ting liu')
('2775959', 'Gautam Prasad', 'gautam prasad')
('40030651', 'Bohyung Han', 'bohyung han')nguyenpx@uci.edu +
{liuti, gautamprasad}@google.com +
bhhan@snu.ac.kr +adfaf01773c8af859faa5a9f40fb3aa9770a8aa7LARGE SCALE VISUAL RECOGNITION
A DISSERTATION
PRESENTED TO THE FACULTY
OF PRINCETON UNIVERSITY
IN CANDIDACY FOR THE DEGREE @@ -8842,6 +10416,8 @@
l.ball@abertay.ac.uk
j.archibald @abertay.ac.uk
l.carson@abertay.ac.uk +ad2339c48ad4ffdd6100310dcbb1fb78e72fac98Video Fill In the Blank using LR/RL LSTMs with Spatial-Temporal Attentions +
Center for Research in Computer Vision, University of Central Florida, Orlando, FL('33209161', 'Amir Mazaheri', 'amir mazaheri')
('46335319', 'Dong Zhang', 'dong zhang')
('1745480', 'Mubarak Shah', 'mubarak shah')amirmazaheri@cs.ucf.edu, dzhang@cs.ucf.edu, shah@crcv.ucf.edu ad247138e751cefa3bb891c2fe69805da9c293d7American Journal of Networks and Communications
2015; 4(4): 90-94
Published online July 7, 2015 (http://www.sciencepublishinggroup.com/j/ajnc) @@ -8853,6 +10429,74 @@
To cite this article:
Decomposition. American Journal of Networks and Communications. Vol. 4, No. 4, 2015, pp. 90-94. doi: 10.11648/j.ajnc.20150404.12 ('2653670', 'Vahid Haji Hashemi', 'vahid haji hashemi')
('2153844', 'Abdorreza Alavi Gharahbagh', 'abdorreza alavi gharahbagh')
('2653670', 'Vahid Haji Hashemi', 'vahid haji hashemi')
('2153844', 'Abdorreza Alavi Gharahbagh', 'abdorreza alavi gharahbagh')hajihashemi.vahid@yahoo.com (V. H. Hashemi), R_alavi@iau-shahrood.ac.ir (A. A. Gharahbagh) +adf62dfa00748381ac21634ae97710bb80fc2922ViFaI: A trained video face indexing scheme +
1. 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 +
access 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 +
an extremely valuable potential training set. +
In this work, we explore how to leverage the afore- +
mentioned training set to solve the video indexing +
problem. +
2. Problem Statement +
Use a labeled (tagged) training set of face images +
to extract relevant indexes from a collection of videos, +
and use these indexes to answer boolean queries of the +
form: “videos with ‘Person 1’ OP1 ‘Person 2’ OP2 ... +
OP(N-1) ‘Person N’ ”, where ‘Person N’ corresponds +
to a training label (tag) and OPN is a boolean operand +
such as AND, OR, NOT, XOR, and so on. +
3. Proposed Scheme +
In this section, we outline our proposed scheme to +
address the problem we postulate in the previous sec- +
tion. We provide further details about the system im- +
plementation in Section 4. +
At a high level, we subdivide the problem into two +
key phases: the first ”off-line” executed once, and the +
second ”on-line” phase instantiated upon each query. +
For the purposes of this work, we define an index as +
follows: