path: root/site/datasets/unknown/voc.json

{"id": "0ee1916a0cb2dc7d3add086b5f1092c3d4beb38a", "citations": [{"id": "c399c0089fb134d1476fadf5f0426e0e8b70eebd", "title": "The Lov\u00e1sz Hinge: A Novel Convex Surrogate for Submodular Losses.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1512.07797.pdf"]}, {"id": "6b6fcf1220ea100aa80004018c78b137289d3c50", "title": "CAD: Scale Invariant Framework for Real-Time Object Detection", "year": "2017", "pdf": []}, {"id": "656f05741c402ba43bb1b9a58bcc5f7ce2403d9a", "title": "Supervised Learning Approaches for Automatic Structuring of Videos. (M\u00e9thodes d'apprentissage supervis\u00e9 pour la structuration automatique de vid\u00e9os)", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/656f/05741c402ba43bb1b9a58bcc5f7ce2403d9a.pdf"]}, {"id": "25d7da85858a4d89b7de84fd94f0c0a51a9fc67a", "title": "Selective Search for Object Recognition", "year": "2013", "pdf": ["http://graphics.cs.cmu.edu/courses/16-824/2016_spring/slides/seg_3.pdf", "http://koen.me/research/pub/uijlings-ijcv2013-draft.pdf", "https://pure.uva.nl/ws/files/19494140/UijlingsIJCV2013.pdf", "https://staff.fnwi.uva.nl/th.gevers/pub/GeversIJCV2013.pdf", "https://webcourse.cs.technion.ac.il/236815/Spring2016/ho/WCFiles/01_object_proposals_6pp.pdf"]}, {"id": "aa3398e15395a2a380c7c6b3f274c8c60fb0b48c", "title": "Chained Cascade Network for Object Detection", "year": "2017", "pdf": []}, {"id": "fbb4f4959756798aabba8034cb3167756b191811", "title": "Supervised Infinite Feature Selection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.02665.pdf"]}, {"id": "e58434a01c45505995b000f5e631843a2f2ea582", "title": "Scale coding bag of deep features for human attribute and action recognition", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.04884.pdf"]}, {"id": "193a69489230de1013dff9af1232e5379cc5282f", "title": "Intelligent Multimodal Framework for Human Assistive Robotics Based on Computer Vision Algorithms", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/193a/69489230de1013dff9af1232e5379cc5282f.pdf"]}, {"id": "744108530678ee667b9c1220933bed074794d9e2", "title": "A Scene Recognition and Semantic Analysis Approach to Unhealthy Sitting Posture Detection during Screen-Reading", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/7441/08530678ee667b9c1220933bed074794d9e2.pdf"]}, {"id": "eaf65c7cf4e9f7868c61f48656cb608fae0adcee", "title": "Visual dictionaries as intermediate features in the human brain", "year": "2014", "pdf": ["http://journal-cdn.frontiersin.org/article/104962/files/pubmed-zip/versions/1/pdf", "http://journal.frontiersin.org/article/10.3389/fncom.2014.00168/pdf", "https://pure.uva.nl/ws/files/2455021/162945_fncom_08_00168.pdf"]}, {"id": "225c318f3143b9b9d6c0f7a87672bd1d9d2901f4", "title": "2 D-Driven 3 D Object Detection in RGB-D Images", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/225c/318f3143b9b9d6c0f7a87672bd1d9d2901f4.pdf"]}, {"id": "4c5d723dd83250c6b289c94318717de2d373a6ed", "title": "Learning Image Classification and Retrieval Models", "year": "2012", "pdf": []}, {"id": "841a5de1d71a0b51957d9be9d9bebed33fb5d9fa", "title": "PCANet: A Simple Deep Learning Baseline for Image Classification?", "year": "2015", "pdf": ["https://arxiv.org/pdf/1404.3606.pdf"]}, {"id": "095ccb4e2e0f3934dc1aa51c685b2f54c8a6e588", "title": "Derivate-based Component-Trees for Multi-Channel Image Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01906.pdf"]}, {"id": "a221588fd2d062462254481cfd9563fec2f7c387", "title": "Deep neural network ensemble architecture for eye movements classification", "year": "2018", "pdf": []}, {"id": "67126ad0af544740c455311d08cb180aec830a6c", "title": "Generating Descriptions of Spatial Relations between Objects in Images", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/6712/6ad0af544740c455311d08cb180aec830a6c.pdf"]}, {"id": "823db813f036365cf9b22b2081ec167a2b582532", "title": "Segmentation and Shape Extraction from Convolutional Neural Networks", "year": "2018", "pdf": []}, {"id": "5a0209515ab62e008efeca31f80fa0a97031cd9d", "title": "Dataset fingerprints: Exploring image collections through data mining", "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_046.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_046_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/3B_046_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Rematas_Dataset_Fingerprints_Exploring_2015_CVPR_paper.pdf", "https://homes.cs.washington.edu/~krematas/Publications/rematasCVPR2015.pdf"]}, {"id": "f3ccdf54a3384e601fa36969e7b3f657e2516a3b", "title": "Paying More A ention to Saliency : Image Captioning with Saliency and Context A ention 1 : 3", "year": "2017", "pdf": []}, {"id": "2c9c597ab660815e07980e9655c3c5989402205b", "title": "Vision-Based Reacquisition for Task-Level Control", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/2c9c/597ab660815e07980e9655c3c5989402205b.pdf"]}, {"id": "bea1958ecdcc5279672bed0f2ba8de5a84b0ce64", "title": "Towards reasoning based representations: Deep Consistence Seeking Machine", "year": "2018", "pdf": []}, {"id": "aae1bf434983545c8a99a5dbfc2ce37435c76e03", "title": "SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00248.pdf"]}, {"id": "ff18125a8f549135e6320fed91d0002bd2dae635", "title": "Colour Terms: a Categorisation Model Inspired by Visual Cortex Neurons", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.06300.pdf"]}, {"id": "3e50e351687779c05390daf117f0394d1556cd3c", "title": "Die Detektion interessanter Objekte unter Verwendung eines objektbasierten Aufmerksamkeitsmodells", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3e50/e351687779c05390daf117f0394d1556cd3c.pdf"]}, {"id": "d0b083befa0034bcd4a1349336fb30158157e6d8", "title": "A Semantic Distance Based Nearest Neighbor Method for Image Annotation", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/d0b0/83befa0034bcd4a1349336fb30158157e6d8.pdf"]}, {"id": "065f05c9cb2a6080191851dd82cd9b439a77499a", "title": "Comparing Boosted Cascades to Deep Learning Architectures for Fast and Robust Coconut Tree Detection in Aerial Images", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/065f/05c9cb2a6080191851dd82cd9b439a77499a.pdf"]}, {"id": "4ba503d8f173880d8e8402808f54b78b653e5d20", "title": "Accelerating Stochastic Gradient Descent via Online Learning to Sample", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/4ba5/03d8f173880d8e8402808f54b78b653e5d20.pdf"]}, {"id": "03a2235fea70317461222fac05e38ee35ead9711", "title": "Implementation of a Computer Vision Algorithm for Onboard Detection of Unmanned Aircraft submitted by Luk\u00e1\u0161 Bauer", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/03a2/235fea70317461222fac05e38ee35ead9711.pdf"]}, {"id": "d07dabdea9e2e4546b09d07a019723ceb6c61b84", "title": "Deep learning for text spotting", "year": "2015", "pdf": []}, {"id": "a1f33473ea3b8e98fee37e32ecbecabc379e07a0", "title": "Image Segmentation by Cascaded Region Agglomeration", "year": "2013", "pdf": ["http://cs.brown.edu/people/ren/publications/cvpr2013/cascade_final.pdf", "http://ttic.uchicago.edu/~gregory/papers/cascade_cvpr2013.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989c011.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Ren_Image_Segmentation_by_2013_CVPR_paper.pdf"]}, {"id": "7f66ff8dd0313fc9c7d67be7ea5aecdda956657c", "title": "Tracking-by-Segmentation with Online Gradient Boosting Decision Tree", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Son_Tracking-by-Segmentation_With_Online_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Son_Tracking-by-Segmentation_With_Online_ICCV_2015_paper.pdf"]}, {"id": "4896c9f6958137c88db29a3a707aafae3c29d106", "title": "Discriminative Re-ranking of Diverse Segmentations", "year": "2013", "pdf": []}, {"id": "858555b6f4663fe083d6c81a2671c9cd8130bbf3", "title": "Object Discovery via Cohesion Measurement", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.08944.pdf"]}, {"id": "f81f5da2a1e4eb80b465b8dffca4c9e583a8a8a6", "title": "Rapid Object Detection Systems , Utilising Deep Learning and Unmanned Aerial Systems ( Uas ) for Civil Engineering Applications", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f81f/5da2a1e4eb80b465b8dffca4c9e583a8a8a6.pdf"]}, {"id": "369bd35ab8bad4c7bc5e376cc776a5366d97b12e", "title": "An Object Detector Trained on Line Drawings", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/369b/d35ab8bad4c7bc5e376cc776a5366d97b12e.pdf"]}, {"id": "46971fb6caa61c606b046da855be4e196a830ccf", "title": "Identification of Scene Text by Character Descriptor in Smart Mobile Devices", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/4697/1fb6caa61c606b046da855be4e196a830ccf.pdf"]}, {"id": "1a20ddce2349bc995dceea66cd2378f8888c8027", "title": "SAN: Learning Relationship Between Convolutional Features for Multi-scale Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.04974.pdf"]}, {"id": "afad16c9fee11d8f78785af6b1856beb86b5ccf4", "title": "Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08011.pdf"]}, {"id": "9089280062cf40870a322d687c2850d45c02ebae", "title": "Single Image Action Recognition by Predicting Space-Time Saliency", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.04641.pdf"]}, {"id": "cf384eda31030a45238ebd8356ace7600da5076b", "title": "Cross-Domain CNN for Hyperspectral Image Classification", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.00093.pdf"]}, {"id": "44c5e66e58dd8212b753662e08cc0a7c8327ec50", "title": "Scene Parsing with Object Instance Inference Using Regions and Per-exemplar Detectors", "year": "2014", "pdf": ["http://slazebni.cs.illinois.edu/publications/jtighe-ijcv14.pdf", "http://wwwx.cs.unc.edu/~mn/sites/default/files/jtighe-ijcv14.pdf"]}, {"id": "83acbf0bee402b0472ff101cee5942f4137d91c3", "title": "Semi-automatic Annotation on Image Segmentation Hierarchies", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/83ac/bf0bee402b0472ff101cee5942f4137d91c3.pdf"]}, {"id": "e9af96d478b487fec9a06dde9e43b2ed3355ea7b", "title": "Automatic thresholding of SIFT descriptors", "year": "2016", "pdf": ["https://arxiv.org/pdf/1811.03173.pdf"]}, {"id": "393d34faf86df2c9d8246a7d6ba669133fe9207d", "title": "Visual tracking of a moving object via the soft cosine measure", "year": "2017", "pdf": []}, {"id": "b3d8705d46a1d63b40a76bbcf8822b2e90b3b9ad", "title": "Efficient Labelling of Pedestrian Supervisions", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/b3d8/705d46a1d63b40a76bbcf8822b2e90b3b9ad.pdf"]}, {"id": "59b21f61ac46e1f982cbd9f49cb855ba5fcd3c45", "title": "CCNY at TRECVID 2014 : Surveillance Event Detection", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/8028/6720d33e63f470f43db4723a58bdc6d8b450.pdf"]}, {"id": "4980511ea7ac286b7fff0456216425287bc9a083", "title": "Automatic Image Annotation Using Modified Keywords Transfer Mechanism Base on Image-Keyword Graph", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/4980/511ea7ac286b7fff0456216425287bc9a083.pdf"]}, {"id": "b1369e4785dd0b23f89ca76f45468049c8667863", "title": "1 DARTS : Deceiving Autonomous Cars with Toxic Signs", "year": "2018", "pdf": []}, {"id": "1a5151b4205ab27b1c76f98964debbfc11b124d5", "title": "Self Paced Deep Learning for Weakly Supervised Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.07651.pdf"]}, {"id": "f1d8c377093ecf64afd7f17383738e81666fe5ae", "title": "Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.10805.pdf"]}, {"id": "c14c2c3b9bbb3b232f601042fe9fde5fa450e595", "title": "Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection Challenge", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.01031.pdf"]}, {"id": "b61ae8216a7c3a5a3202478cd6f18bf3014e2342", "title": "Robust Pedestrian Detection by Combining Visible and Thermal Infrared Cameras", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1f50/d437901304a20f17713bc4a1935f842c57fa.pdf"]}, {"id": "12ff1c48f5776fda9d156c7b324af3f2674420a9", "title": "Are Large Scale Training Images or Discriminative Features Important for Codebook Construction?", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/12ff/1c48f5776fda9d156c7b324af3f2674420a9.pdf"]}, {"id": "e4dc24e4926df4de3e8d7ca7cd1f4115e91f03e1", "title": "Instance-level video segmentation from object tracks Anonymous CVPR submission", "year": "", "pdf": ["https://pdfs.semanticscholar.org/e4dc/24e4926df4de3e8d7ca7cd1f4115e91f03e1.pdf"]}, {"id": "194af94f1ea9357bebb0aab5ab98aa0daa21ddbd", "title": "Snapshot Distillation: Teacher-Student Optimization in One Generation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00123.pdf"]}, {"id": "6c289ce7cd1c8514f71bf7dc25b1b203b98f8129", "title": "Semantic-Aware Image Smoothing", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6c28/9ce7cd1c8514f71bf7dc25b1b203b98f8129.pdf"]}, {"id": "0caef87116f62fcc86735401a9aa9d4e170ffbef", "title": "On Performance Evaluation of Driver Hand Detection Algorithms: Challenges, Dataset, and Metrics", "year": "2015", "pdf": ["http://cvrr.ucsd.edu/eshed/papers/Das_ITSC2015.pdf", "http://cvrr.ucsd.edu/publications/2015/DasOhnbarTrivedi_ITSC2015.pdf"]}, {"id": "806aea24148fc2ef851803c216a0a25894d78bf4", "title": "Correlation filter based visual trackers for person pursuit using a low-cost Quadrotor", "year": "2015", "pdf": []}, {"id": "63ed42249d7cbb21a4b0d42419d42b014ff114eb", "title": "Comprehensive Parameter Sweep for Learning-Based Detector on Traffic Lights", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/4817/826f1af10e0c31dee067f8d9255d6387d486.pdf"]}, {"id": "4682fee7dc045aea7177d7f3bfe344aabf153bd5", "title": "Tabula rasa: Model transfer for object category detection", "year": "2011", "pdf": ["http://cs.brown.edu/~ls/teaching_CMU_16-824/slides_tz-1.pdf", "http://eprints.pascal-network.org/archive/00008313/01/aytar11.pdf", "http://www.cs.utexas.edu/~cv-fall2012/slides/elad-paper.pdf", "http://www.robots.ox.ac.uk/~vgg/publications/2011/Aytar11/aytar11.pdf", "http://www.robots.ox.ac.uk/~vgg/publications/2011/Aytar11/poster.pdf"]}, {"id": "1b1323b4677c640ae8835a9ccab611ca1e9652e3", "title": "Robust object tracking with a hierarchical ensemble framework", "year": "2016", "pdf": ["https://arxiv.org/pdf/1509.06925.pdf"]}, {"id": "557e5e38a4c5b95e2bc86f491b03e5c8c7add857", "title": "Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Kwak_Thin-Slicing_for_Pose_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Kwak_Thin-Slicing_for_Pose_CVPR_2016_paper.pdf", "http://www.di.ens.fr/willow/pdfscurrent/kwak2016.pdf", "https://vlg.dgist.ac.kr/research/pose_emb/data/CVPR2016_pose.pdf"]}, {"id": "6bcc2b50e32bdbb0c668f75000badf21e6cd0839", "title": "Knowledge Projection for Deep Neural Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.09505.pdf"]}, {"id": "071680ca97de050a372ea79f2b99f102bb3ca6ef", "title": "Inferring Unseen Views of People", "year": "2014", "pdf": ["http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/inferring-unseen-views-of-people-paper.pdf", "http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/inferring-unseen-views-of-people-poster.pdf", "http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/supp.pdf", "http://www.cs.utexas.edu/~chaoyeh/cvpr_2014_Inferring_Unseen_Views_of_People%20(2).pdf", "http://www.cs.utexas.edu/~grauman/papers/chen-pose-cvpr2014.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Chen_Inferring_Unseen_Views_2014_CVPR_paper.pdf"]}, {"id": "415c0eecce9fde7d1ba9c70bd0bfa5471760c117", "title": "Oriented Object Proposals", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/He_Oriented_Object_Proposals_ICCV_2015_paper.pdf", "http://www.cs.cityu.edu.hk/~rynson/papers/iccv15.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/He_Oriented_Object_Proposals_ICCV_2015_paper.pdf"]}, {"id": "f865248065b8d6bcbce4a4053b73e4de2080ba23", "title": "Efficient object detection for high resolution images", "year": "2015", "pdf": ["https://arxiv.org/pdf/1510.01257.pdf"]}, {"id": "e0e19769ad446c2a74c0616fcfb551059c899ce6", "title": "Part level transfer regularization for enhancing exemplar SVMs", "year": "2015", "pdf": ["http://people.csail.mit.edu/yusuf/publications/2015/Aytar15/aytar15.pdf"]}, {"id": "eea9994c71831219aacd537f5f4ab8a91110a7e2", "title": "Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08707.pdf"]}, {"id": "009fba8df6bbca155d9e070a9bd8d0959bc693c2", "title": "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", "year": "2014", "pdf": []}, {"id": "a0703bef11c978cc8faf05eb229e29a889f8a0b1", "title": "Superpixel Hierarchy", "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.06325.pdf"]}, {"id": "472de7b3c674e8f06702385569779d11b71bc8f2", "title": "Superpixel Coherency and Uncertainty Models for Semantic Segmentation", "year": "2013", "pdf": ["http://cvlab.postech.ac.kr/~tgx.lim/paper/iccv2013_semantic.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_workshops_2013/W08/papers/Baek_Superpixel_Coherency_and_2013_ICCV_paper.pdf"]}, {"id": "73818ae13a89c2377c30cdb029fdb7e490fe5367", "title": "Joint cost minimization for multi-object tracking", "year": "2017", "pdf": []}, {"id": "ba51ce1ec7b18fa808985b919f4a201fe5e4bafb", "title": "Semantic parsing for priming object detection in indoors RGB-D scenes", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ba51/ce1ec7b18fa808985b919f4a201fe5e4bafb.pdf"]}, {"id": "23e707600c3e9a240e24eaa4ed4b0e4ec6a436c1", "title": "Automatic foreground extraction via joint CRF and online learning", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/7f3b/115dd38a933f3a88e3b20b58862216297d63.pdf"]}, {"id": "c5632e2117d268159225d5c307b7efbb6428ccba", "title": "Understanding image concepts using ISTOP model", "year": "2016", "pdf": ["http://www.cs.uu.nl/groups/MG/multimedia/publications/art/PR2016b.pdf"]}, {"id": "773fd71d3d24c268c99e1c53ae87a28da3bbe0f6", "title": "Conditional Entropies as Over-Segmentation and Under-Segmentation Metrics for Multi-Part Image Segmentation", "year": "2011", "pdf": []}, {"id": "0435a34e93b8dda459de49b499dd71dbb478dc18", "title": "VEGAC: Visual Saliency-based Age, Gender, and Facial Expression Classification Using Convolutional Neural Networks", "year": "2018", "pdf": []}, {"id": "02567fd428a675ca91a0c6786f47f3e35881bcbd", "title": "Deep Label Distribution Learning With Label Ambiguity", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.01731.pdf"]}, {"id": "9ea7205ef136f207123cd6b54e15075835ae0049", "title": "Self-supervised language grounding by active sensing combined with Internet acquired images and text", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9ea7/205ef136f207123cd6b54e15075835ae0049.pdf"]}, {"id": "6452d294af27b1f9408c9522bfb98bf00e1e4732", "title": "A novel infrared video surveillance system using deep learning based techniques", "year": "2018", "pdf": ["https://ore.exeter.ac.uk/repository/bitstream/handle/10871/32083/MTA-manuscript-revision-R2-accepted.pdf?isAllowed=y&sequence=1", "https://repository.edgehill.ac.uk/10281/6/MTA-manuscript-revision-R2.pdf"]}, {"id": "191beb87f84326d2cc9c427efe2a5abee8f67574", "title": "Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05462.pdf"]}, {"id": "5020a75c45416073d0b07b1deb7382bc80de1779", "title": "Human Detection Using Learned Part Alphabet and Pose Dictionary", "year": "2014", "pdf": ["http://cis-linux1.temple.edu/~latecki/Papers/HumanDetectionECCV2014.pdf", "http://mc.eistar.net/UpLoadFiles/Papers/%5B38%5D%202014%20ECCV%20Yaocong.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/ECCV_2014/papers/8693/86930251.pdf", "https://cis.temple.edu/~latecki/Papers/HumanDetectionECCV2014.pdf"]}, {"id": "6e7248f33be3f6b44d6089b7039a5c2d84acaed0", "title": "Object cosegmentation using deep Siamese network", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02555.pdf"]}, {"id": "b8ccc5341a1b0214e9d155b019962023f344c2ee", "title": "Incremental Learning of Object Detectors without Catastrophic Forgetting", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06977.pdf"]}, {"id": "8d2459ada191d496eeee70f1e817d0ba92075160", "title": "The evaluation of different approaches towards using Kinect sensor as a Laser scanner", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/8d24/59ada191d496eeee70f1e817d0ba92075160.pdf"]}, {"id": "37668092cf8b7695d4a85eb7a25e9a2ef0fd0739", "title": "Robust object detection under partial occlusion", "year": "2016", "pdf": []}, {"id": "49f276e1b8fd162ac3cd996becc63cab2b2535b7", "title": "Trained 3D Models for CNN based Object Recognition", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/49f2/76e1b8fd162ac3cd996becc63cab2b2535b7.pdf"]}, {"id": "44a3ee0429a6d1b79d431b4d396962175c28ace6", "title": "Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Yang_Exploit_All_the_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Yang_Exploit_All_the_CVPR_2016_paper.pdf", "http://www.nec-labs.com/uploads/images/Department-Images/MediaAnalytics/papers/cvpr16_scaledependentpooling.pdf", "http://www.umiacs.umd.edu/~fyang/papers/cvpr16.pdf"]}, {"id": "8047586d2223f3076a1fc028197f54d0997bccfc", "title": "Pelee: A Real-Time Object Detection System on Mobile Devices", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.06882.pdf"]}, {"id": "51a162f6d21e48c3731aec8f676ba7c18c65bd26", "title": "From trajectories to behaviors : an algorithm to track and describe dancing birds", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/51a1/62f6d21e48c3731aec8f676ba7c18c65bd26.pdf"]}, {"id": "1426045c4188f09fec46d0d2f246357a230a1748", "title": "Structured Labels in Random Forests for Semantic Labelling and Object Detection", "year": "2014", "pdf": []}, {"id": "efe133717899b41cd4c0b0c999da312d3af60a6e", "title": "Depth-Based Hand Pose Estimation: Methods, Data, and Challenges", "year": "2018", "pdf": ["https://arxiv.org/pdf/1504.06378.pdf"]}, {"id": "9caa7605c16da42761c8a27327f5f037dbf901fa", "title": "q-Gaussian mixture models for image and video semantic indexing", "year": "2013", "pdf": []}, {"id": "4bb84c9b24456fb0bb920ca83280bd9c48ad4b66", "title": "Instance-Level Video Segmentation from Object Tracks", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Seguin_Instance-Level_Video_Segmentation_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Seguin_Instance-Level_Video_Segmentation_CVPR_2016_paper.pdf", "http://www.di.ens.fr/willow/pdfscurrent/seguin2016.pdf", "http://www.di.ens.fr/willow/research/instancelevel/seguin16instancelevel.pdf", "http://www.di.ens.fr/~bojanowski/papers/seguin16instance.pdf"]}, {"id": "ce0dbe6b1abecb54dcc98dbe652aa63d190dbc94", "title": "Part-Based Models for Finding People and Estimating Their Pose", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/ce0d/be6b1abecb54dcc98dbe652aa63d190dbc94.pdf"]}, {"id": "a5683661e80668e05170bf17bcbd754d1b07af74", "title": "Comparison of Data Set Bias in Object Recognition Benchmarks", "year": "2015", "pdf": ["http://vfacstaff.ltu.edu/lshamir/publications/object_recognition_dataset_bias.pdf"]}, {"id": "646a669f1dc38ae961fe41fbd3c83cab64ce9d53", "title": "Real-Time Seamless Single Shot 6D Object Pose Prediction", "year": "2018", "pdf": []}, {"id": "575a0e97702edcb0621a47b574949bac50e34200", "title": "Unsupervised Learning by Predicting Noise", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.05310.pdf"]}, {"id": "b9128ff3b0b96815ff41a7d5fb2b4bef69f635ca", "title": "Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.04984.pdf"]}, {"id": "7c03a0ad5202a6a31ad3b78b11f6b45ecd840616", "title": "Scale-Invariant Feature Learning using Deconvolutional Neural Networks for Weakly-Supervised Semantic Segmentation", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/7c03/a0ad5202a6a31ad3b78b11f6b45ecd840616.pdf"]}, {"id": "17342b1c4caccfc499d9ae55a68d7b93285c5d6b", "title": "Action recognition in still images using a combination of human pose and context information", "year": "2012", "pdf": []}, {"id": "571d2b173c2db8ac751dabdfcf5a18c06f365e05", "title": "Improved Part Segmentation Performance by Optimising Realism of Synthetic Images using Cycle Generative Adversarial Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06301.pdf"]}, {"id": "90e36f66c25a4c73a252102c6c6c329c36d82676", "title": "Probably Unknown: Deep Inverse Sensor Modelling In Radar", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08151.pdf"]}, {"id": "fb710e9d897b7c1fd5275a0bcfa22711c5768990", "title": "A Graphical Model for Rapid Obstacle Image-Map Estimation from Unmanned Surface Vehicles", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/fb71/0e9d897b7c1fd5275a0bcfa22711c5768990.pdf"]}, {"id": "821ba3eba1e36a29cc482f5378f4a0d0f6893159", "title": "Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.07926.pdf"]}, {"id": "b50156e76ae03a1c0b04cd2076a99b7f2b441506", "title": "An image classification method that considers privacy-preservation", "year": "2016", "pdf": []}, {"id": "3481a544e28cfc14108b0785eef7c12747e622ee", "title": "Online Multi-object Tracking via Structural Constraint Event Aggregation", "year": "2016", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/cvpr16_mot.pdf", "http://vc.cs.nthu.edu.tw/home/paper/codfiles/melu/201703210652/Online%20Multi-Object%20Tracking%20via%20Structural%20Constraint%20Event%20Aggregation.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Yoon_Online_Multi-Object_Tracking_CVPR_2016_paper.pdf"]}, {"id": "7fd5d2b0a034da43a747f6b8be3e51d775a05625", "title": "A Method to Detect Boats in Images of the Amazonian Rivers", "year": "2017", "pdf": []}, {"id": "13105c611a059b4825bc92ff9778f532b6a849b2", "title": "Compressing Sparse Feature Vectors Using Random Ortho-Projections", "year": "2010", "pdf": ["http://www.ee.oulu.fi/mvg/files/pdf/PID1267977.pdf", "http://www.ee.oulu.fi/research/mvmp/mvg/files/pdf/PID1267977.pdf", "http://www.rni.helsinki.fi/~msa/pub/ICPR2010.pdf"]}, {"id": "0967341790643f680f3fc9dc87bfe311723be4e4", "title": "A Perception-Driven Transcale Display Scheme for Space Image Sequences", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0967/341790643f680f3fc9dc87bfe311723be4e4.pdf"]}, {"id": "a8bf49021017e19df051a3efb7337d93ea263e37", "title": "Deep Multiple Instance Hashing for Object-based Image Retrieval", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a8bf/49021017e19df051a3efb7337d93ea263e37.pdf"]}, {"id": "347ce37f15cea5bb8d0a676562664f80e3609b78", "title": "Pixel Objectness: Learning to Segment Generic Objects Automatically in Images and Videos", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.04702.pdf"]}, {"id": "0755ee472e2bc2968b16f851a16c39b3f3e2d0d0", "title": "From Weakly Supervised Object Localization to Semantic Segmentation by Probabilistic Image Modeling", "year": "2017", "pdf": []}, {"id": "659fc2a483a97dafb8fb110d08369652bbb759f9", "title": "Improving the Fisher Kernel for Large-Scale Image Classification", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/659f/c2a483a97dafb8fb110d08369652bbb759f9.pdf"]}, {"id": "1e02dfeb93e8fd8753d2e69baf705baf8996cb81", "title": "Online Object Tracking, Learning and Parsing with And-Or Graphs", "year": "2014", "pdf": ["https://arxiv.org/pdf/1509.08067.pdf"]}, {"id": "bdfb5f11d497b44b17d0315c3b6892f835723832", "title": "Object Captioning and Retrieval with Natural Language", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06152.pdf"]}, {"id": "43fe9006b90137d6ce85a539685ce66c13f0e38e", "title": "A review of image-based automatic facial landmark identification techniques", "year": "", "pdf": ["https://pdfs.semanticscholar.org/43fe/9006b90137d6ce85a539685ce66c13f0e38e.pdf"]}, {"id": "e6cd10c6de16ae2fba499762f2d6242990e1d35c", "title": "Improved Person Detection on Omnidirectional Images with Non-maxima Supression.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08503.pdf"]}, {"id": "642772c38ff690d17a3ce84a1d8646aefc802139", "title": "VIDEO OBJECT TRACKING BASED ON AUTOMATIC BACKGROUND SEGMENTATION : A SURVEY", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/6427/72c38ff690d17a3ce84a1d8646aefc802139.pdf"]}, {"id": "56c24b33d9efd05effe8afcbfa68fe27b5738cc2", "title": "Regularized Geometric Hulls for Bio-medical Image Segmentation", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/56c2/4b33d9efd05effe8afcbfa68fe27b5738cc2.pdf"]}, {"id": "7653af14cf2b220da07252df585c443985ea9f8b", "title": "Human Detection Based on the Generation of a Background Image by Using a Far-Infrared Light Camera", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/7653/af14cf2b220da07252df585c443985ea9f8b.pdf"]}, {"id": "303c08071500421c3aca758e6c7cd6a9fcbda1a8", "title": "Scene understanding with complete scenes and structured representations", "year": "2014", "pdf": []}, {"id": "86f0f71bff42e4bdc60014e4f94ec76d52c8eccf", "title": "Felzenszwalb-Baum-Welch: Event Detection by Changing Appearance", "year": "2013", "pdf": ["https://arxiv.org/pdf/1306.4746.pdf"]}, {"id": "d9cc8bc5c4a4b29ab40f75b721bd9e5140d2baf6", "title": "Object Detection for Crime Scene Evidence Analysis Using Deep Learning", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6926/4f28158f9245a06f7a2c1ae666241261cc0e.pdf"]}, {"id": "d3f6b3ce8f7b67c1e112a79b3fe9764242c655f5", "title": "Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks", "year": "2018", "pdf": []}, {"id": "9b6538d09e914c41345812b3086feff1dc1ae218", "title": "Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08937.pdf"]}, {"id": "16741cad4175adf065d6adbfdfa27acdcda2b26b", "title": "Deep Learning Approach for Building Detection in Satellite Multispectral Imagery", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.04247.pdf"]}, {"id": "bf417e1c265b31720b4fb980afb83cc3a573fa6f", "title": "Representations and Similarities of Images for Visual Classification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bf41/7e1c265b31720b4fb980afb83cc3a573fa6f.pdf"]}, {"id": "4dc57432fa8fea1614a39c324bf11ae0620cb26f", "title": "Aalborg Universitet Detection of U . S . Traffic", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/6e53/63af2bfb7d1b2bd13feb41c2688bd0cf12b3.pdf"]}, {"id": "878169be6e2c87df2d8a1266e9e37de63b524ae7", "title": "Image interpretation above and below the object level.", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/8781/69be6e2c87df2d8a1266e9e37de63b524ae7.pdf"]}, {"id": "3daafe6389d877fe15d8823cdf5ac15fd919676f", "title": "Human Action Localization with Sparse Spatial Supervision", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05197.pdf"]}, {"id": "04f9b591cdfa1e3667230ae1224b1dfdac0a8ef1", "title": "Discriminative Segment Annotation in Weakly Labeled Video", "year": "2013", "pdf": []}, {"id": "4e4f2c4d2ea47636ca2ab795770d6b3214640f37", "title": "Efficient Maximum Appearance Search for Large-Scale Object Detection", "year": "2013", "pdf": ["http://researcher.watson.ibm.com/researcher/files/us-liangliang.cao/qiangcvpr2013_final.pdf", "http://rogerioferis.com/publications/ChenCVPR2013.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d190.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Chen_Efficient_Maximum_Appearance_2013_CVPR_paper.pdf"]}, {"id": "9434524669777d281a8a7358f20181c9e157942e", "title": "VSEM: An open library for visual semantics representation", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/9434/524669777d281a8a7358f20181c9e157942e.pdf"]}, {"id": "0e0900b88c33b671be5dd2ded9885b6526d6b429", "title": "From captions to visual concepts and back", "year": "2015", "pdf": ["https://arxiv.org/pdf/1411.4952.pdf"]}, {"id": "4d910c5ab0b70ddbef6be944077ed63821608135", "title": "On Dimensionality Reduction for Indexing and Retrieval of Large-Scale Solar Image Data", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/4d91/0c5ab0b70ddbef6be944077ed63821608135.pdf"]}, {"id": "9076183dcdb28ebb3e547f7ffd3f9d5d0faec531", "title": "Describing Video Contents in Natural Language", "year": "2012", "pdf": []}, {"id": "07764e1607d9e3d8094455adb658077996eb38c4", "title": "End-to-End Trained CNN Encoder-Decoder Networks for Image Steganography", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.07201.pdf"]}, {"id": "46f135110c5fc5f158bc3ffce21b9ae946c7ff68", "title": "Adaptive NormalHedge for robust visual tracking", "year": "2015", "pdf": ["https://core.ac.uk/download/pdf/33581176.pdf", "https://pure.qub.ac.uk/portal/files/13941301/main_huiyu.pdf"]}, {"id": "b961009dedea99f948650df7291a28f18bbfc1dc", "title": "Towards Automated Visual Monitoring of Individual Gorillas in the Wild", "year": "2017", "pdf": []}, {"id": "7dbc61e2dc497e9dcff98e7df832780cc8a2b60c", "title": "A Flexible Object-of-Interest Annotation Framework for Online Video Portals", "year": "2012", "pdf": ["http://www.mdpi.com/1999-5903/4/1/179/pdf"]}, {"id": "d4f454b24a7901dea14858808bbe277c7bee8ffb", "title": "Edge-based Component-Trees for Multi-Channel Image Segmentation", "year": "2017", "pdf": []}, {"id": "6768b558cc58e113096540c123ef3b2c2d2469a1", "title": "Maximum Margin Linear Classifiers in Unions of Subspaces", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/1a06/e518bf15015153b4973bb2e9e06e51485a4c.pdf"]}, {"id": "ba6c19771926564e89be4ace7c33dc3da580249e", "title": "Utilisation du contexte pour l'indexation s\u00e9mantique des images et vid\u00e9os. (Using context for semantic indexing of images and videos)", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/ba6c/19771926564e89be4ace7c33dc3da580249e.pdf"]}, {"id": "70d71c2f8c865438c0158bed9f7d64e57e245535", "title": "Higher Order Priors for Joint Intrinsic Image, Objects, and Attributes Estimation", "year": "2013", "pdf": ["http://cms.brookes.ac.uk/research/visiongroup/publications/2013/intr_obj_vrt_nips13.pdf", "http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2013_5198.pdf", "http://papers.nips.cc/paper/5198-higher-order-priors-for-joint-intrinsic-image-objects-and-attributes-estimation.pdf", "http://www.robots.ox.ac.uk/~tvg/publications/2013/intr_obj_vrt_nips13.pdf", "http://wwwpub.zih.tu-dresden.de/~cvweb/publications/papers/2013/nips13_vinett_torr_rother.pdf"]}, {"id": "447b28c347172c6da0fb4d764a534fdee557b7f8", "title": "Studying Relationships between Human Gaze, Description, and Computer Vision", "year": "2013", "pdf": []}, {"id": "782b21e803d149955c627c063ae60efeae04a9b1", "title": "Analysis of Multilayer Neural Networks for Object Recognition", "year": "2014", "pdf": []}, {"id": "3e01f2fefe219bfeb112f1d82e76ebba4c0e2aac", "title": "Transfer learning via attributes for improved on-the-fly classification", "year": "2014", "pdf": []}, {"id": "ba156b81fe8fca1fd1bfb1c822e39205c4ff355b", "title": "Unsupervised Multi-class Joint Image Segmentation", "year": "2014", "pdf": []}, {"id": "72048081cfe678f700c52e1c7a56713a8e0865b6", "title": "Unsupervised Adversarial Visual Level Domain Adaptation for Learning Video Object Detectors from Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02074.pdf"]}, {"id": "9cd8a2d07f07d888fcf50aa0735d0831edcf5e46", "title": "Bag of contour fragments for robust shape classification", "year": "2014", "pdf": ["http://cis-linux1.temple.edu/~latecki/Papers/XinggangPR2014.pdf", "http://mc.eistar.net/~xwang/pubs/BagOfShape.pdf", "http://mclab.eic.hust.edu.cn/~xwang/pubs/BagOfShape.pdf", "https://cis.temple.edu/~latecki/Papers/XinggangPR2014.pdf"]}, {"id": "8c21cd8d5e98c77d727fc900450c6223f9e1fa24", "title": "DARE: Dynamic Adaptive Mobile Augmented Reality with Edge Computing", "year": "2018", "pdf": []}, {"id": "7fe203374ba3ddc8462a7c775b276e53f09dd036", "title": "NavigationNet: A Large-scale Interactive Indoor Navigation Dataset", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.08374.pdf"]}, {"id": "8f8599012002dd3bbb6526b3be92d7a7355ad22a", "title": "Construction et \u00e9valuation d'un corpus pour la recherche d'instances d'images mus\u00e9ales", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8f85/99012002dd3bbb6526b3be92d7a7355ad22a.pdf"]}, {"id": "ebf35073e122782f685a0d6c231622412f28a53b", "title": "A High-Quality Denoising Dataset for Smartphone Cameras", "year": "2018", "pdf": []}, {"id": "9463f71b2d8e291d5fc5a7db6b95b3d01e759b29", "title": "Describing Spatial Relationships between Objects in Images in English and French", "year": "2015", "pdf": ["http://www.emnlp2015.org/proceedings/VL/pdf/VL16.pdf"]}, {"id": "aaa6fe8045e1a071e1762cffe4f59e0bd508daf9", "title": "Single-Pedestrian Detection Aided by Two-Pedestrian Detection", "year": "2015", "pdf": ["http://www.ee.cuhk.edu.hk/~wlouyang/Papers/tpami15-ouyang_xgWang_xyZeng.pdf", "http://www.ee.cuhk.edu.hk/~xgwang/papers/ouyangZWtpami15.pdf"]}, {"id": "2a7007555f71e559c6aa33efbd3bd8b401638d82", "title": "Full interpretation of minimal images", "year": "2018", "pdf": ["https://perso.telecom-paristech.fr/bloch/AIC/articles/BenYosef2017.pdf"]}, {"id": "08c71fe89af5f168b373e92b44a7cf9d1755fb8c", "title": "The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition", "year": "2013", "pdf": ["http://infoscience.epfl.ch/record/182860/files/2013_ChavarriagaPRLETTERS_preprint.pdf?version=1", "https://www.researchgate.net/profile/Ricardo_Chavarriaga/publication/258031577_The_Opportunity_challenge_A_benchmark_database_for_on-body_sensor-based_activity_recognition/links/02e7e528146aa12213000000.pdf"]}, {"id": "8d73906f0a232e8b94200017e512446c1af4dd9d", "title": "Detection of U.S. Traffic Signs", "year": "2015", "pdf": []}, {"id": "497857bce6ea1ed4889fb949a2f176072e2509c7", "title": "A Comparison of L_1 Norm and L_2 Norm Multiple Kernel SVMs in Image and Video Classification", "year": "2009", "pdf": []}, {"id": "a0b9a6123fa8113ad3ddc44614941c73512b9dca", "title": "Multi-class object segmentation based on jointly integrating segment-level and image-level object priors", "year": "2016", "pdf": []}, {"id": "1d5f704a98d82c34de96ceb80fa06552082effd3", "title": "Dynamic Zoom-in Network for Fast Object Detection in Large Images", "year": "2018", "pdf": []}, {"id": "3de71ddc07619c0dd6bbaa3f7b412a9262a0e761", "title": "Discriminatively Trained And-Or Tree Models for Object Detection", "year": "2013", "pdf": ["http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d278.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Song_Discriminatively_Trained_And-Or_2013_CVPR_paper.pdf", "http://www.stat.ucla.edu/~sczhu/papers/Conf_2013/DiscriminativeAOG_cvpr2013.pdf"]}, {"id": "18b4a20ed465972d9d8f3f8d8982d321acf45907", "title": "Mod\u00e9lisation de contextes pour l'annotation s\u00e9mantique de vid\u00e9os. (Context based modeling for video semantic annotation)", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/18b4/a20ed465972d9d8f3f8d8982d321acf45907.pdf"]}, {"id": "992a614aa601c52b20729538ea25b62471ffe8bc", "title": "Towards Automatic Construction of Diverse, High-quality Image Dataset", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06495.pdf"]}, {"id": "53822d61e829ef02a95a6c89fea082114fd3e16b", "title": "A General Framework for Tracking Multiple People from a Moving Camera", "year": "2013", "pdf": ["http://www.willowgarage.com/sites/default/files/pami_preprint.pdf"]}, {"id": "323eb410e0d0978901a8baa670f905f280ab19ff", "title": "Inner-Scene Similarities as a Contextual Cue for Object Detection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.04406.pdf"]}, {"id": "7532996c27b199ed89b412a9f0df7483df83ea72", "title": "Committees of deep feedforward networks trained with few data", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.5947.pdf"]}, {"id": "bf7238df8b3a7fc0ebf0e8028a417c7e99fca8d8", "title": "An ontology-based framework for the automated analysis and interpretation of comic books' images", "year": "2017", "pdf": []}, {"id": "c6e042f9db094d3a01c13a9d3120fc6898f40cb8", "title": "Multi-label Classification for Image Annotation via Sparse Similarity Voting", "year": "2010", "pdf": ["http://naosite.lb.nagasaki-u.ac.jp/dspace/bitstream/10069/27087/1/LNCS6469_344.pdf", "https://page-one.springer.com/pdf/preview/10.1007/978-3-642-22819-3_35"]}, {"id": "2dd6749ddffa620d2ac40275a436ecd89aa51a45", "title": "Learning Dual Multi-Scale Manifold Ranking for Semantic Segmentation of High-Resolution Images", "year": "2017", "pdf": ["http://www.mdpi.com/2072-4292/9/5/500/pdf"]}, {"id": "478261574ddc6cf297611000735aa9808f8f0030", "title": "ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.04405.pdf"]}, {"id": "c5fcc36768428185c0ec0f04c82c9204c9ba962c", "title": "Deep Material-Aware Cross-Spectral Stereo Matching", "year": "2018", "pdf": []}, {"id": "e4fc560a78e48bd927c2f6253f5fc489927bb15f", "title": "Detecting objects in internet videos AIMS Project Report", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/e4fc/560a78e48bd927c2f6253f5fc489927bb15f.pdf"]}, {"id": "2049db406168f63c46e5efd2d5ceb5941e3fdc7c", "title": "Region detection and matching for object recognition", "year": "2013", "pdf": []}, {"id": "030646f4fc694ffea5d4f77203cbbc5d02aae797", "title": "Cognitive Deep Machine Can Train Itself", "year": "2016", "pdf": ["https://arxiv.org/pdf/1612.00745.pdf"]}, {"id": "e42b89b6ed1c6d79286a62ded1e4c090f474eb40", "title": "Using image analytics to monitor retail store shelves", "year": "2015", "pdf": []}, {"id": "64fb6a04a3ec96b2ad266c381c75f4dc16ce3460", "title": "Hole-based traffic sign detection method for traffic signs with red rim", "year": "2013", "pdf": []}, {"id": "24c20c28871fa923c3f45b745b9b9f2d3d280e81", "title": "Harmony potentials for joint classification and segmentation", "year": "2010", "pdf": []}, {"id": "06f1c079303937f6022e6157e6341c7921fe9428", "title": "Efficient Dense Rigid-Body Motion Segmentation and Estimation in RGB-D Video", "year": "2014", "pdf": ["http://ais.uni-bonn.de/papers/IJCV_2015_Stueckler_Motion_Segmentation.pdf", "http://www.ais.uni-bonn.de/papers/IJCV_2015_Stueckler_Motion_Segmentation.pdf"]}, {"id": "038e2f45575c234358325dd0dd16421136882191", "title": "Planar Object Detection using Local Feature Descriptors", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/038e/2f45575c234358325dd0dd16421136882191.pdf"]}, {"id": "333b877ea761c5c1d4ffa39654fc19bd015e245d", "title": "Ontology-Based Semantic Image Segmentation Using Mixture Models and Multiple CRFs", "year": "2016", "pdf": []}, {"id": "0ecaabbf846bbc78c91bf7ff71b998b61c0082d8", "title": "Automated Visual Fin Identification of Individual Great White Sharks", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.06323.pdf"]}, {"id": "28863c0f3a1aa186bf1c281c73784cf36e2bf361", "title": "Efficient Non-iterative Domain Adaptation of Pedestrian Detectors to Video Scenes", "year": "2014", "pdf": ["http://eprints.whiterose.ac.uk/84865/1/ICPR14.pdf"]}, {"id": "c0c3e0161a1007a5edf701a6b4a201ca06922559", "title": "Enhancing Multi-Camera People Detection by Online Automatic Parametrization Using Detection Transfer and Self-Correlation Maximization \u2020", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c0c3/e0161a1007a5edf701a6b4a201ca06922559.pdf"]}, {"id": "6b8c4082cff10a893efa172da0ca1d31e166be0f", "title": "Enhancing Energy Minimization Framework for Scene Text Recognition with Top-Down Cues", "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.03128.pdf"]}, {"id": "054738ce39920975b8dcc97e01b3b6cc0d0bdf32", "title": "Towards the design of an end-to-end automated system for image and video-based recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.07883.pdf"]}, {"id": "4446924885545b255164b32e42b8375bac699f23", "title": "Object semantic categorization based on ensemble SVM classifiers", "year": "2016", "pdf": []}, {"id": "fc2c39b6439623c00b10e8d9826b1c82e8487805", "title": "Generalized Semantic Preserving Hashing for N-Label Cross-Modal Retrieval", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Mandal_Generalized_Semantic_Preserving_CVPR_2017_paper.pdf"]}, {"id": "92cd808bba43c3702d8cbddde65ee42bf01676d4", "title": "A MultiPath Network for Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.02135.pdf"]}, {"id": "f2f086b4ea5c37712b8fbcbcb4af6d24d4f2b78b", "title": "Comparative Analysis of Face Detection Algorithms: Novice to Novel", "year": "2018", "pdf": []}, {"id": "3bccc5621b14f2e6b07a5936acecdf957724c6ff", "title": "Convolutional Fisher Kernels for RGB-D Object Recognition", "year": "2015", "pdf": []}, {"id": "0b67879b1d5db9da12490b41b4f52d12626e87bc", "title": "The KIT object models database: An object model database for object recognition, localization and manipulation in service robotics", "year": "2012", "pdf": ["http://ijr.sagepub.com/content/31/8/927.full.pdf"]}, {"id": "98b4bf8cf8890f50b12e4fabe78bafd687a598c2", "title": "Semantic Labeling Based Vehicle Detection in Aerial Imagery", "year": "2018", "pdf": []}, {"id": "e03a2299caf2febcc7b87ee4e61e78ad8cb24e45", "title": "Combined Holistic and Local Patches for Recovering 6D Object Pose", "year": "2017", "pdf": []}, {"id": "26eadb307d62ab28713931beb8be9ff0f04c6ea0", "title": "Synthetic Viewpoint Prediction", "year": "2016", "pdf": []}, {"id": "55d01b7314d78fe3bc5ae03b6e414ecba14188f8", "title": "Cognitive Inspired WOR Framework to Reveal Image Semantics, for Efficient Content Based Image Retrieval", "year": "2015", "pdf": []}, {"id": "05e9e85b5137016c93d042170e82f77bb551a108", "title": "A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation", "year": "2016", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Perazzi_A_Benchmark_Dataset_CVPR_2016_paper.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_poster_cvpr_2016.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_supplementary.pdf"]}, {"id": "64bff565c83c6ce3fac783d8d67191af99803701", "title": "Learning to Co-Generate Object Proposals with a Deep Structured Network", "year": "2016", "pdf": ["http://infoscience.epfl.ch/record/217984/files/HayderHeSalzmannCVPR16.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf"]}, {"id": "66dcc6771e35068a1ea2f6e6f4cdb9a40a4df450", "title": "A Linear Approximation to the chi^2 Kernel with Geometric Convergence", "year": "2012", "pdf": ["https://arxiv.org/pdf/1206.4074.pdf"]}, {"id": "dbf2d57def648d1dae7717c92a32ff02157e5cb5", "title": "RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.01054.pdf"]}, {"id": "2284ba28bd3b1afaf06afb8c2a94638e350b3ecb", "title": "Boosting Object Proposals: From Pascal to COCO", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01226.pdf"]}, {"id": "174b6d661b96840e27cd9435c2dbb8e538b2c8a6", "title": "Progressive Representation Adaptation for Weakly Supervised Object Localization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.04647.pdf"]}, {"id": "b95cdaaa0d6c191bcc8169ce555219ad545258fb", "title": "Online streaming feature selection: a minimum redundancy, maximum significance approach", "year": "2018", "pdf": []}, {"id": "0f780a8cb09627bec41000345c2771df2853224a", "title": "Automatic inspection of aeronautic components", "year": "2017", "pdf": []}, {"id": "c1206330ba57a27fd0acc29dd39825bbf2d91060", "title": "A Shape Reconstructability Measure of Object Part Importance with Applications to Object Detection and Localization", "year": "2014", "pdf": ["http://www.stat.ucla.edu/~yuille/Pubs10_12/PartImportance_IJCV2014_online.pdf"]}, {"id": "4c500c84e16e5ebb50b33f9bcff36854e5131c16", "title": "All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification", "year": "2016", "pdf": ["https://arxiv.org/pdf/1711.04450.pdf"]}, {"id": "02f86370fd467f0d03948a94a346034d8a111ffd", "title": "Semantic Video Retrieval Using High Level Context", "year": "2008", "pdf": ["https://pdfs.semanticscholar.org/02f8/6370fd467f0d03948a94a346034d8a111ffd.pdf"]}, {"id": "d111faa1990f80e3351ea1eef0e5fc177d4e44b4", "title": "Iteratively Training Look-Up Tables for Network Quantization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.05355.pdf"]}, {"id": "165c27a4bfb56562c807279bef9d15f1bced5ca0", "title": "Scene parsing using inference Embedded Deep Networks", "year": "2016", "pdf": ["http://www.adv-ci.com/publications/2016_PR_Bu.pdf"]}, {"id": "f348d23a88fd81e05585897629f2f230fcfe77c7", "title": "Transfer Learning of Deep Neural Networks for Visual Collaborative Maritime Asset Identification", "year": "2018", "pdf": []}, {"id": "87fe38a79ee12531bb618d4006a476b3a5256f3e", "title": "Relative Saliency and Ranking: Models, Metrics, Data, and Benchmarks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02426.pdf"]}, {"id": "d8b8e165279ca2091d5af1440ed974db4792250f", "title": "Mean Response-Time Minimization of a Soft-Cascade Detector", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ad73/ff39869e223dba6e0ee94481b6c32766df86.pdf"]}, {"id": "0f6a2ea69c325bcbfca85fb05cb5f542873b1bf8", "title": "Food Recognition and Detection with Minimum Supervision", "year": "2016", "pdf": []}, {"id": "df8aee8aef6f0c71f968979318dafcd53da04bdc", "title": "Bending the Curve: Improving the ROC Curve Through Error Redistribution", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.06652.pdf"]}, {"id": "70918453e9f147747b7a37d9159c8c1515a55ae4", "title": "Visual object tracking via the local soft cosine similarity", "year": "2018", "pdf": []}, {"id": "1876095a9387a84e594d81675c9c2c17cb10f7cf", "title": "Accurate segmentation of complex document image using digital shearlet transform with neutrosophic set as uncertainty handling tool", "year": "2017", "pdf": ["http://fs.gallup.unm.edu/neut/AccurateSegmentationOfComplex.pdf"]}, {"id": "ad52d047a44f20416f9dd6655cef54169d481454", "title": "Perceptual modeling in the problem of active object recognition in visual scenes", "year": "2016", "pdf": []}, {"id": "e096b11b3988441c0995c13742ad188a80f2b461", "title": "DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers", "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.04702.pdf"]}, {"id": "56e95fa26fb417776824e5adf6d6d511e5b30110", "title": "Object and Action Classification with Latent Window Parameters", "year": "2013", "pdf": ["http://homepages.inf.ed.ac.uk/hbilen/assets/pdf/Bilen14.pdf", "http://www.cse.iitk.ac.in/users/cs365/2014/_papers/bilen-namboodri-vanGool-13_object-action-classify-latent-windows.pdf", "http://www.cse.iitk.ac.in/users/vinaypn/papers/bilen2013ijcv.pdf"]}, {"id": "e7df750805d6c025d0a1a74a05a83bcf8cc63dd7", "title": "Assessment of crowdsourcing and gamification loss in user-assisted object segmentation", "year": "2015", "pdf": ["http://upcommons.upc.edu/bitstream/handle/2117/81293/asknseek.pdf;jsessionid=469B72384B7C56D4A331D68A53942294?sequence=1"]}, {"id": "85eedee59aca5f2a591265a2173cf3a2799cdc94", "title": "Action and Event Recognition with Fisher Vectors on a Compact Feature Set", "year": "2013", "pdf": []}, {"id": "3463aeda3a8d33bc88d8383cc4ad451a6775c75a", "title": "Understanding Indoor Scenes Using 3D Geometric Phrases", "year": "2013", "pdf": ["http://courses.cs.washington.edu/courses/cse590v/13au/choi_cvpr13.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989a033.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Choi_Understanding_Indoor_Scenes_2013_CVPR_paper.pdf", "https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/41340.pdf"]}, {"id": "8ba686c99684c6be46988ed3ab1003312c2fbf80", "title": "A non-temporal texture driven approach to real-time fire detection", "year": "2011", "pdf": ["http://breckon.eu/toby/publications/papers/chenebert11fire.pdf", "https://dspace.lib.cranfield.ac.uk/bitstream/handle/1826/7588/Real-time_fire_detection-2011.pdf;jsessionid=BFF4BCF2CC5EF353D82416490C8E1B85?sequence=1"]}, {"id": "985b6a10c1bb9c8908d6d299c7ab0bba76df2259", "title": "Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Bilinski_Dense_Decoder_Shortcut_CVPR_2018_paper.pdf"]}, {"id": "82451d0ae2e0154b5f9cd096af199c35319e911a", "title": "Image spam filtering using convolutional neural networks", "year": "2018", "pdf": []}, {"id": "8ff6294535acf46abf523b879f20685de0692a8c", "title": "Bayes Risk for Large Scale Hierarchical Top-K Image Classification", "year": "2013", "pdf": ["https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/153936/eth-6877-01.pdf?isAllowed=y&sequence=1"]}, {"id": "d97224063697392f073e467005e89973d2be7d65", "title": "Recherche de motifs fr\u00e9quents dans une base de cartes combinatoires. (Frequent pattern discovery in combinatorial maps databases)", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/02d1/8e600804a1a6ff354856d8dcb80ceb4c8a43.pdf"]}, {"id": "74a1336f1fbc8b7bb3b6e159711af1a91336ce22", "title": "An overview of traffic sign detection methods", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/74a1/336f1fbc8b7bb3b6e159711af1a91336ce22.pdf"]}, {"id": "e33bc0cd79d92d6868989a29c3ab06b75f808590", "title": "Deep Nets: What have they ever done for Vision?", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04025.pdf"]}, {"id": "0b4d3e59a0107f0dad22e74054bab1cf1ad9c32e", "title": "Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.07332.pdf"]}, {"id": "14d1a458f49e251cbbab34349e379469300a2bae", "title": "Scene Parsing with Object Instances and Occlusion Ordering", "year": "2014", "pdf": ["http://slazebni.cs.illinois.edu/publications/jtighe-cvpr14.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Tighe_Scene_Parsing_with_2014_CVPR_paper.pdf", "http://wwwx.cs.unc.edu/~mn/sites/default/files/jtighe-cvpr14.pdf"]}, {"id": "a6cd743c29667ab5baef9d66d6558247b1cd00b0", "title": "New in-situ training image and one-shot detection model without adaptation GENETIM detection model for synset bottle", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/a6cd/743c29667ab5baef9d66d6558247b1cd00b0.pdf"]}, {"id": "9b8746e9480c3bdcaa6efca33096369422c624aa", "title": "Algae Detection Using Computer Vision and Deep Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10847.pdf"]}, {"id": "3325860c0c82a93b2eac654f5324dd6a776f609e", "title": "2D Human Pose Estimation: New Benchmark and State of the Art Analysis", "year": "2014", "pdf": []}, {"id": "896e2776174dcb86d311789ab83a266151d0595b", "title": "A Novel Performance Evaluation Methodology for Single-Target Trackers", "year": "2016", "pdf": ["https://arxiv.org/pdf/1503.01313.pdf"]}, {"id": "4a31ca27b987606ae353b300488068b5240633ee", "title": "WSABIE: scaling up to large vocabulary image annotation", "year": "2011", "pdf": ["http://bengio.abracadoudou.com/cv/publications/pdf/weston_2011_ijcai.pdf", "http://ijcai.org/Proceedings/11/Papers/460.pdf", "http://www.thespermwhale.com/jaseweston/papers/wsabie-ijcai.pdf"]}, {"id": "bf26ccc92bca086195c5f250aef2e409a1c7cd85", "title": "Local Bayes Risk Minimization Based Stopping Strategy for Hierarchical Classification", "year": "2017", "pdf": []}, {"id": "ff3a9545e73adea5275a1c7c71c5e3fe2e35a9a1", "title": "An Enhanced Feature Extraction Technique for Diagnosis of Pathological Problems in Mango Crop", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ff3a/9545e73adea5275a1c7c71c5e3fe2e35a9a1.pdf"]}, {"id": "21d1225296aad388406824eb113715c4b90ed3da", "title": "Dirichlet-Based Concentric Circle Feature Transform for Breast Mass Classification", "year": "2015", "pdf": []}, {"id": "3f0b0ffe315ee111fc028561ec4ecf2c93f94a05", "title": "Pose Normalization Network for Object Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3f0b/0ffe315ee111fc028561ec4ecf2c93f94a05.pdf"]}, {"id": "6a405e7284ff7e2127a241d60646b4abd3da92f2", "title": "Generate To Adapt : Unsupervised Domain Adaptation using Generative Adversarial Networks", "year": "2017", "pdf": []}, {"id": "8cded4bbe4202ee81c2b75ebe27f839c87b0755e", "title": "Objectness to improve the bag of visual words model", "year": "2014", "pdf": []}, {"id": "c0e551acb063c9cd73dea28ab8963f850b6f1148", "title": "A Comparison of Techniques based on Image Classification and Object Detection to Count Cars and Non-empty Stalls in Parking Spaces", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c0e5/51acb063c9cd73dea28ab8963f850b6f1148.pdf"]}, {"id": "8b45a87f3dfc8eccd745161effbf2457a9097e6a", "title": "WEAKLY SUPERVISED SEMANTIC SEGMENTATION 3 priors can give good pixel labelling results", "year": "2017", "pdf": []}, {"id": "25d75339720787e7003f2f103cf38cee8175972a", "title": "Optimistic and Pessimistic Neural Networks for Scene and Object Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.07982.pdf"]}, {"id": "12d9a4233a16ea08fbb1de853b6a97b4f4952c23", "title": "Tractable Structured Prediction using the Permutohedral Lattice", "year": "2017", "pdf": ["https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-01.pdf?isAllowed=y&sequence=1", "https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-02.pdf?isAllowed=y&sequence=2"]}, {"id": "33d101fe276fd5e6220c9b40c33e1a1d1389e5bb", "title": "DOC: DEEP OCCLUSION ESTIMATION FROM A SIN-", "year": "2016", "pdf": []}, {"id": "c6c691b772822881c5c52b779100928f0d54fdd7", "title": "Using Visual Saliency to Improve Human Detection with Convolutional Networks", "year": "2018", "pdf": []}, {"id": "11a3084768f035c824662a85a348f02466693d2a", "title": "Lifting Object Detection Datasets into 3D", "year": "2016", "pdf": ["https://arxiv.org/pdf/1503.06465.pdf"]}, {"id": "4be10db13a9210e078d78a4a072c569d9bbd9939", "title": "Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.06098.pdf"]}, {"id": "18a849b1f336e3c3b7c0ee311c9ccde582d7214f", "title": "Efficiently Scaling Up Crowdsourced Video Annotation A Set of Best Practices for High Quality , Economical Video Labeling", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/18a8/49b1f336e3c3b7c0ee311c9ccde582d7214f.pdf"]}, {"id": "13e424d502bf539108ad6f5cc877cfb1255dbee0", "title": "Improving Vision-Based Self-Positioning in Intelligent Transportation Systems via Integrated Lane and Vehicle Detection", "year": "2015", "pdf": []}, {"id": "1dbd7653ede6af15d539f64cb2128752ca029e44", "title": "Hollywood 3D: Recognizing Actions in 3D Natural Scenes", "year": "2013", "pdf": []}, {"id": "ab88c48e7829029c47ac6deea5c0ccbff3614c5c", "title": "Rethinking Visual Relationships for High-level Image Understanding", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.00313.pdf"]}, {"id": "f4c45108cb41051010d8a5175b8da23eb246c967", "title": "Improving Image Captioning by Leveraging Knowledge Graphs", "year": "2019", "pdf": []}, {"id": "1b3ee5455956a40c6e9e09ccda0f4fb162838629", "title": "The Recognition of License Plate Restrictions Based on Faster R-CNN", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1b3e/e5455956a40c6e9e09ccda0f4fb162838629.pdf"]}, {"id": "0394acc70f58fbb6326d1fbf44e0a6da5a0345d1", "title": "Automated Recognition of Text in Images : A Survey", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/0394/acc70f58fbb6326d1fbf44e0a6da5a0345d1.pdf"]}, {"id": "5c45a1abc51fe059987bcfba19b1d5076a8d9afb", "title": "Autonomous Object Category Learning for Service Robots Using Internet Resources", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5c45/a1abc51fe059987bcfba19b1d5076a8d9afb.pdf"]}, {"id": "81ea29bde0216e41420c4591bebb800142fa3269", "title": "Learning Active Learning from Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.03365.pdf"]}, {"id": "4a31b3fcc346bf3235efe1c0fb310833570cef27", "title": "Learning Intelligent Dialogs for Bounding Box Annotation", "year": "2018", "pdf": []}, {"id": "ed62a56b81511d7fcf6d247014987163d9668982", "title": "\"What happens if...\" Learning to Predict the Effect of Forces in Images", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.05600.pdf"]}, {"id": "59b6e9320a4e1de9216c6fc49b4b0309211b17e8", "title": "Robust Representations for unconstrained Face Recognition and its Applications", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/59b6/e9320a4e1de9216c6fc49b4b0309211b17e8.pdf"]}, {"id": "29aa3dc15450e6eb46c34f30f0e224e5ea16615e", "title": "Sketch Me That Shoe", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Yu_Sketch_Me_That_CVPR_2016_paper.pdf", "http://vision.cs.utexas.edu/381V-fall2016/slides/hsiao_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Yu_Sketch_Me_That_CVPR_2016_paper.pdf", "https://www.eecs.qmul.ac.uk/~qian/SketchMeThatShoe.pdf"]}, {"id": "1999d5e0700bf8fa50bb1bab5b981bda1d111a4f", "title": "Monocular Road Terrain Detection by Combining Visual and Spatial Information", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/73b1/10df4809d0a015f90fa6e7a7dce351bcc52e.pdf", "https://www.researchgate.net/profile/Jannik_Fritsch/publication/261073577_Monocular_Road_Terrain_Detection_by_Combining_Visual_and_Spatial_Information/links/5475ef240cf29afed612e5a8.pdf"]}, {"id": "34072c31c2c778df471c9f0c43ba6198dfd0db32", "title": "Arbitrary Category Classification of Websites Based on Image Content", "year": "2015", "pdf": ["http://users.ics.aalto.fi/juha/papers/ELM2014.pdf", "http://www.engineering.uiowa.edu/sites/default/files/files/newpaper.pdf"]}, {"id": "d23ac99cdab20a9a3eca2784a5b262649c717988", "title": "Rotation Invariant Angular Descriptor Via A Bandlimited Gaussian-like Kernel", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.02753.pdf"]}, {"id": "22cf367d14e646914cc959bbcd402df0c20cd0dc", "title": "Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.04024.pdf"]}, {"id": "451ed51346fe2e6c5de2dbf29733711b31f5fd68", "title": "Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.05573.pdf"]}, {"id": "f8f14c0248a4974ce9a6226db81f9745a6b1ea97", "title": "Part based pedestrian detection based on Logic inference", "year": "2013", "pdf": ["http://portal.uc3m.es/portal/page/portal/dpto_ing_sistemas_automatica/investigacion/lab_sist_inteligentes_old/publications/2013-ITSC-Olmeda.pdf"]}, {"id": "c9d73438bf5e66bd0c4f512c5a4e53c3e33e721e", "title": "Adding spatial distribution clue to aggregated vector in image retrieval", "year": "2018", "pdf": ["https://jivp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13640-018-0247-0?site=jivp-eurasipjournals.springeropen.com"]}, {"id": "a74b045f28670e8f85173e0e483581520d667f02", "title": "Object tracking using Langevin Monte Carlo particle filter and locality sensitive histogram based likelihood model", "year": "2018", "pdf": []}, {"id": "c56da136b8d62125009a131f6dc21fcd0dd6a559", "title": "ICDAR2017 Robust Reading Challenge on Text Extraction from Biomedical Literature Figures (DeTEXT)", "year": "2017", "pdf": []}, {"id": "02e5372e439c09f8a8ce8c4784b044ce116ca11c", "title": "DeepCorrect: Correcting DNN models against Image Distortions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02406.pdf"]}, {"id": "e8b2a98f87b7b2593b4a046464c1ec63bfd13b51", "title": "CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.05413.pdf"]}, {"id": "19d4855f064f0d53cb851e9342025bd8503922e2", "title": "Learning SURF Cascade for Fast and Accurate Object Detection", "year": "2013", "pdf": ["http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d468.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/supp/4989d468s1.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Li_Learning_SURF_Cascade_2013_CVPR_paper.pdf", "https://16cbeb23-a-62cb3a1a-s-sites.googlegroups.com/site/leeplus/publications/learningsurfcascadeforfastandaccurateobjectdetection/cvsurf13.pdf?attachauth=ANoY7cprgGHyp0x1H24zmTyefmyqoRoMJFJxg9j-BM6Rh9vToSM_0gtVNgtcm7pgFG_yr6TS1gMJe7AEGilvP9MEizPWXUkP-NHn4b6wB49ETjP5XUJo93ObOe7SWdAUiCTeHWGdjA3aFjtBPOiSWteKMqeMeteYqnVW7e3NpALb8cnhR4TFfbcT82NKsxTv_XgJNenB-1UGij2Ayg0COitzW-6AVpls1e5yGDCdzMc-Ij8VgOxAWfLbiKzodL1hmPHLsrT4yM_cXV3B0vgpjQSmVzNgViA1s5cANrI-EjUTpxRczBT_RIA%3D&attredirects=3&d=1"]}, {"id": "5fdbebf417da2427744d2c60f413b5375e68993e", "title": "Discriminative Sub-categorization", "year": "2013", "pdf": []}, {"id": "32bebe84ffbd4fd81f0e5bb30dbc90774aa3b14b", "title": "Segmentation Results Stimuli Final Saliency Map Ground Truth Constructed Graph CCA", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/32be/be84ffbd4fd81f0e5bb30dbc90774aa3b14b.pdf"]}, {"id": "a02e5d8e2a10176dc5e2566e1b492823a0cb6ee2", "title": "A learning framework for higher-order consistency models in multi-class pixel labeling problems", "year": "2014", "pdf": []}, {"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"]}, {"id": "64c1158a4061882d610f1cffd5ddb1e8fc9a74b4", "title": "Gated Feedback Refinement Network for Dense Image Labeling", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Islam_Gated_Feedback_Refinement_CVPR_2017_paper.pdf", "http://www.cs.umanitoba.ca/~ywang/papers/cvpr17.pdf"]}, {"id": "284be8be0c6bedc36dfe43229bc84345ab0aedc2", "title": "Faster Training of Mask R-CNN by Focusing on Instance Boundaries", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07069.pdf"]}, {"id": "80ab008243b5a61c8a74a0a3e2aaf702b1f906b3", "title": "Ship detection for automating navigational watch", "year": "2014", "pdf": []}, {"id": "be2d326fa588b4ffd1d8d3d4408ae680e1a26277", "title": "JOURNA A Survey on Modern Era \u2019 s Online Object Tracking Algorithms", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/be2d/326fa588b4ffd1d8d3d4408ae680e1a26277.pdf"]}, {"id": "2a2232f2972191a0606d588aa4f13c9f27d1972d", "title": "InstanceCut: From Edges to Instances with MultiCut", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.08272.pdf"]}, {"id": "029cabb6f3f6a824590e735feb1d8557646db8a6", "title": "One-Bit Object Detection: On learning to localize objects with minimal supervision", "year": "2014", "pdf": ["https://arxiv.org/pdf/1403.1024.pdf"]}, {"id": "fd23dda0abe2d6a3ae0c8253c89110364cdecbc9", "title": "Deep Learning for People Detection on Beach Images", "year": "2018", "pdf": []}, {"id": "c3c4f0caf1b42b6466306360c4ebe16f66489df0", "title": "Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.11266.pdf"]}, {"id": "2d15a7546c16d5821ffa8f769eb7ec18e435e64d", "title": "Recognition in Terra Incognita", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.04975.pdf"]}, {"id": "03fd6774f57aaed9320060e4527121c59e9eca2b", "title": "Intrinsic spatial pyramid matching for deformable 3D shape retrieval", "year": "2013", "pdf": []}, {"id": "46c82cfadd9f885f5480b2d7155f0985daf949fc", "title": "3D Shape Attributes", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Fouhey_3D_Shape_Attributes_CVPR_2016_paper.pdf", "http://www.cs.cmu.edu/~dfouhey/2016/shapeAttr/shapeAttr.pdf", "http://www.cs.cmu.edu/~dfouhey/2016/shapeAttr/talk_final.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Fouhey_3D_Shape_Attributes_CVPR_2016_paper.pdf", "http://www.robots.ox.ac.uk/~vgg/publications/2016/Fouhey16/fouhey16.pdf", "https://people.eecs.berkeley.edu/~dfouhey/2016/shapeAttr/shapeAttr.pdf", "https://people.eecs.berkeley.edu/~dfouhey/2016/shapeAttr/talk_final.pdf"]}, {"id": "304aa9bfd6bc32d3d87abce6a229d973270bbd73", "title": "Fast Neural Cell Detection Using Light-Weight SSD Neural Network", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w8/papers/Yi_Fast_Neural_Cell_CVPR_2017_paper.pdf"]}, {"id": "c8ba499e8d8daa32637885f03137f41d61023bf9", "title": "Weak supervision for detecting object classes from activities", "year": "2017", "pdf": ["https://ps.is.tue.mpg.de/uploads_file/attachment/attachment/296/weak_supervision_object_detection.pdf"]}, {"id": "cd1a636c1261208084cb8395c877c7ca22c76df1", "title": "Fast Deep Vehicle Detection in Aerial Images", "year": "2017", "pdf": ["https://www.computer.org/csdl/proceedings/wacv/2017/4822/00/07926624.pdf"]}, {"id": "101c7305f141145c4d168dfa40284e0ad86a0d9b", "title": "Active Object Localization with Deep Reinforcement Learning", "year": "2015", "pdf": []}, {"id": "af7310abcbac6b43ffa850be2315282185b933bc", "title": "Detection and recognition of traffic signs inside the attentional visual field of drivers", "year": "2017", "pdf": []}, {"id": "48922520e6de0954a83f26977b2b50b7fbfdcf61", "title": "A survey of sketch-based image retrieval", "year": "2018", "pdf": []}, {"id": "e047bcb9721c36fb61df1f4d6f7de83f290ec1d4", "title": "Flower classification: Training augmentation using manifold images", "year": "2015", "pdf": []}, {"id": "0083a395fded81d562317d83e194dfbc47b5c04a", "title": "AT&T Research at TRECVID 2010", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/955f/e9a0ba02d82e469c5e719bbde9a5f14a3d32.pdf"]}, {"id": "c37fe13f94dfc2f3494a35a63336689ce4392135", "title": "MPNET: An End-to-End Deep Neural Network for Object Detection in Surveillance Video", "year": "2018", "pdf": []}, {"id": "0f8f9253c81fd90fe44d474cc185d4ae2487e5b4", "title": "NYC3DCars: A Dataset of 3D Vehicles in Geographic Context", "year": "2013", "pdf": ["http://nyc3d.cs.cornell.edu/static/paper.pdf", "http://www.cs.cornell.edu/~snavely/publications/papers/nyc3dcars_iccv13.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Matzen_NYC3DCars_A_Dataset_2013_ICCV_paper.pdf"]}, {"id": "e8ffef3d4d74720e766e506e175e533bdc8ee705", "title": "Object Detection Networks on Convolutional Feature Maps", "year": "2017", "pdf": ["https://arxiv.org/pdf/1504.06066.pdf"]}, {"id": "1daf971c087f5e21dbae831231377cbe9bb2f188", "title": "Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection", "year": "2013", "pdf": []}, {"id": "8d74fbd46f9d5d615e350c4593cbc5b5ca63fa8b", "title": "Data driven visual tracking via representation learning and online multi-class LPBoost learning", "year": "2016", "pdf": []}, {"id": "182c91f619e0b7a8cd2120139d530750aa0b85a7", "title": "Compressing the Input for CNNs with the First-Order Scattering Transform", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.10200.pdf"]}, {"id": "7af667b6c1b4b32f513dd70fe3ef36fcf344a741", "title": "A transfer learning based approach for automated grading of Gliomas using deep Residual Networks", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/7af6/67b6c1b4b32f513dd70fe3ef36fcf344a741.pdf"]}, {"id": "d9dafc343727db2b6060c868d748f97eff6bac7d", "title": "Improved pedestrian detection using motion segmentation and silhouette orientation", "year": "2017", "pdf": []}, {"id": "3b304585d5af0afe98a85d6e0559315fbf3a7807", "title": "An Improved Labelling for the INRIA Person Data Set for Pedestrian Detection", "year": "2013", "pdf": ["http://welcome.isr.ist.utl.pt/img/pdfs/2999_2013_IbPRIA_Taiana_Nascimento_Bernardino.pdf", "http://welcome.isr.tecnico.ulisboa.pt/wp-content/uploads/2015/05/2999_2013_IbPRIA_Taiana_Nascimento_Bernardino.pdf"]}, {"id": "99df9e95b3f3d187636918a65277baf7c98cbfc5", "title": "An efficient subsequence search for video anomaly detection and localization", "year": "2015", "pdf": []}, {"id": "832246357de85108cb910e773c203997448c570a", "title": "Recurrently Target-Attending Tracking", "year": "2016", "pdf": []}, {"id": "74031f12dde0be772a742b96bf5f4c8d9fa41ec7", "title": "Joint Object-Material Category Segmentation from Audio-Visual Cues", "year": "2015", "pdf": ["https://arxiv.org/pdf/1601.02220.pdf"]}, {"id": "9452d029f5d140aece06619b6fd8e47b070cacd1", "title": "Urban classification by pixel and object-based approaches for very high resolution imagery", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9452/d029f5d140aece06619b6fd8e47b070cacd1.pdf"]}, {"id": "7268747251a61d1ce3285baade15c372d4c566d6", "title": "Person Attribute Recognition with a Jointly-Trained Holistic CNN Model", "year": "2015", "pdf": ["http://web-info8.informatik.rwth-aachen.de/media/papers/sudowe_spitzer_leibe_ICCV_LaP_2015.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w11/papers/Sudowe_Person_Attribute_Recognition_ICCV_2015_paper.pdf"]}, {"id": "81763bb718dc6630be210c056a250b1c2ed57fd7", "title": "3D Semantic Parsing of Large-Scale Indoor Spaces", "year": "2016", "pdf": ["http://buildingparser.stanford.edu/images/CVPR_2016_poster.pdf", "http://buildingparser.stanford.edu/images/supp_mat.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/papers/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.pdf"]}, {"id": "9d5db7427b44d83bf036ff4cff382c23c6c7b6d8", "title": "Video redaction: a survey and comparison of enabling technologies", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f78d/6d092deaafee550fb58d6ea6e8b559325876.pdf"]}, {"id": "a228ba020bd321d29ab24485cb2988a62707fd64", "title": "Using objective ground-truth labels created by multiple annotators for improved video classification: A comparative study", "year": "2013", "pdf": ["https://engineering.purdue.edu/RVL/Publications/Srivastava2013.pdf"]}, {"id": "037f2e9d2d2aa15c3d476f4aa358da96707b4b44", "title": "Square Localization for Efficient and Accurate Object Detection", "year": "2015", "pdf": []}, {"id": "bf3aae7293f664d512c0904916d804327af22f52", "title": "STDnet: A ConvNet for Small Target Detection", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bf3a/ae7293f664d512c0904916d804327af22f52.pdf"]}, {"id": "d6b514a68abff3ab14af9fc0152cd5b28bd0192c", "title": "Instance Segmentation by Deep Coloring", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.10007.pdf"]}, {"id": "0de46e6768acaa71745406d646573644b975dc62", "title": "Scene-Domain Active Part Models for Object Representation", "year": "2015", "pdf": []}, {"id": "e24792ec2a6cb8971b2f6befb4b97b9fe2d79952", "title": "Bottom-up Object Detection by Grouping Extreme and Center Points", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08043.pdf"]}, {"id": "1d7029a974f950de61f3980704956b43f1a06e7b", "title": "Efficient Optimization for Rank-Based Loss Functions", "year": "2018", "pdf": []}, {"id": "22a8b7ca2e6449cad31ae4f71bb3587751087e77", "title": "DeepBox: Learning Objectness with Convolutional Networks", "year": "2015", "pdf": []}, {"id": "9c4365a56fb3cf41b15712657b15f7422ca0dab2", "title": "A Hybrid Supervised-Unsupervised Vocabulary Generation Algorithm for Visual Concept Recognition", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/9c43/65a56fb3cf41b15712657b15f7422ca0dab2.pdf"]}, {"id": "37b9ea1bf5b6ce8ecb656628af3933c64c632c2b", "title": "Transfer Learning for 3 D LiDAR-based Human Classification with a Mobile Robot", "year": "2018", "pdf": []}, {"id": "f79c4bf83371627ba139b61eb427463b93cd687b", "title": "Learning from Few Examples for Visual Recognition Problems", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/f79c/4bf83371627ba139b61eb427463b93cd687b.pdf"]}, {"id": "084bd219dd239dc4c9a02621a5333d3bc1446566", "title": "DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking", "year": "2015", "pdf": ["https://arxiv.org/pdf/1503.00072.pdf"]}, {"id": "1c9da6cef6b1be9c116b26dd52c341c0adcf7db2", "title": "Interactive Perception: Leveraging Action in Perception and Perception in Action", "year": "2017", "pdf": ["https://arxiv.org/pdf/1604.03670.pdf"]}, {"id": "66586f1d755362f485f25acfc60153c2a5ed1533", "title": "A Comparison of Deep Learning Architectures for Semantic Mapping of Very High Resolution Images", "year": "2018", "pdf": []}, {"id": "549c719c4429812dff4d02753d2db11dd490b2ae", "title": "YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00824.pdf"]}, {"id": "2851efe83633a1c80272ba2c9302a1333dd32523", "title": "Understanding and localizing activities from correspondences of clustered trajectories", "year": "2017", "pdf": ["https://www.micc.unifi.it/wp-content/uploads/2017/01/1-s2.0-S1077314216301965-main.pdf"]}, {"id": "094f5e36dae2602e179f2c1d95a616df3dbe967f", "title": "Bilinear classifiers for visual recognition", "year": "2009", "pdf": ["https://pdfs.semanticscholar.org/094f/5e36dae2602e179f2c1d95a616df3dbe967f.pdf"]}, {"id": "e430d1ae3a28ec342f767cdfb19aeb76c20a3f21", "title": "Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV", "year": "2018", "pdf": []}, {"id": "3b4ad6b789837a6a878f33c0b7ddb1b1fc7daaf8", "title": "Fine-grained recognition of plants from images", "year": "2017", "pdf": ["https://plantmethods.biomedcentral.com/track/pdf/10.1186/s13007-017-0265-4?site=plantmethods.biomedcentral.com"]}, {"id": "f92ceb6875f614bbccb25e4b11ca55353773890f", "title": "Saliency Detection via Boundary Prior and Center Prior", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f92c/eb6875f614bbccb25e4b11ca55353773890f.pdf"]}, {"id": "2114b25727a21275e88e30dad0423752f6047dae", "title": "Generic Visual Recognition on Non-Uniform Distributions Based on AdaBoost Codebooks", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/cac0/c534e02784a3a873690d213dd8c92b81992f.pdf"]}, {"id": "c11a2501204e9e7c4a53d8a3c87055b2b11c73df", "title": "Adaptive Learning Algorithms for Transferable Visual Recognition", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/c11a/2501204e9e7c4a53d8a3c87055b2b11c73df.pdf"]}, {"id": "748305f0b2d686d51ccf893207697d6cfb39e890", "title": "COVER LOCALIZATION IN AERIAL IMAGES WITH A DEEP LEARNING APPROACH", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/7483/05f0b2d686d51ccf893207697d6cfb39e890.pdf"]}, {"id": "7cb4d30b3bfb0d4b02499c15c7c7a9dfddda8049", "title": "Object Tracking using L 1 / L 2 Sparse Coding and Multi Scale Max Pooling", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/7cb4/d30b3bfb0d4b02499c15c7c7a9dfddda8049.pdf"]}, {"id": "b7efecec654acd8831d045e728b54356c697c9c8", "title": "Learning Semantic Segmentation with Diverse Supervision", "year": "2018", "pdf": []}, {"id": "eacb95e81156c48f4ff7470567ba205225170fa7", "title": "Learning Aerial Image Segmentation From Online Maps", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06879.pdf"]}, {"id": "14b311b848b51b7b5345573a289b1cedcbb4d581", "title": "Instance Similarity Deep Hashing for Multi-Label Image Retrieval", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02987.pdf"]}, {"id": "24ff832171cb774087a614152c21f54589bf7523", "title": "Beat-Event Detection in Action Movie Franchises", "year": "2015", "pdf": ["https://arxiv.org/pdf/1508.03755.pdf"]}, {"id": "ffd73d1956163a4160ec2c96b3ab256f79fc92e8", "title": "Attributes as Semantic Units between Natural Language and Visual Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03249.pdf"]}, {"id": "99c37dba394b100ba8f3d895c0ee0e57d5852347", "title": "Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects", "year": "2014", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2014/papers/Zia_Are_Cars_Just_2014_CVPR_paper.pdf", "http://resources.mpi-inf.mpg.de/publications/D2/2014/zia14cvpr.pdf", "http://www.igp.ethz.ch/photogrammetry/publications/pdf_folder/cvpr2014zz.pdf"]}, {"id": "f6b649023e49a341f042f9a17b2f923db58ccf35", "title": "Feature representation of RGB-D images using joint spatial-depth feature pooling", "year": "2016", "pdf": []}, {"id": "1c8897aaac36c9f96b86b4e6d412e91512429cde", "title": "Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation", "year": "2015", "pdf": ["https://arxiv.org/pdf/1506.04924.pdf"]}, {"id": "f9f86d087e84eaf0e6a09575982aa7b41fa62451", "title": "Image Synthesis for Self-Supervised Visual Representation Learning", "year": "2018", "pdf": []}, {"id": "b85c198ce09ffc4037582a544c7ffb6ebaeff198", "title": "Efficient Multiple Instance Metric Learning Using Weakly Supervised Data", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Law_Efficient_Multiple_Instance_CVPR_2017_paper.pdf", "http://www.cs.toronto.edu/~law/publications/CVPR/2017/mimlca_cvpr_2017.pdf"]}, {"id": "c77c094faf7b1a4e293609a0909c7c50b468675a", "title": "Satyam: Democratizing Groundtruth for Machine Vision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.03621.pdf"]}, {"id": "2a5667702b0f1ff77dde8fb3e2e10d4e05e8de9d", "title": "Scene Parsing through ADE20K Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhou_Scene_Parsing_Through_CVPR_2017_paper.pdf", "http://people.csail.mit.edu/bzhou/publication/scene-parse-camera-ready.pdf"]}, {"id": "a422c2bd9030c8a2c89b6db79be2743c4a4609fb", "title": "Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02886.pdf"]}, {"id": "46a1172c784c3741e79781ef2353209b08dbea67", "title": "YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shot Recognition", "year": "2013", "pdf": ["http://www.cs.utexas.edu/users/ml/papers/guadarrama.iccv13.pdf", "http://www.cs.utexas.edu/users/ml/posters/guadarrama.iccv13.pdf", "http://www.eecs.berkeley.edu/~sguada/pdfs/2013-ICCV-YouTube2Text-final.pdf", "https://www.cs.utexas.edu/~vsub/pdf/YouTube2Text_Recognizing_and_2013_ICCV_paper.pdf", "https://www.icsi.berkeley.edu/pubs/vision/youtube2text13.pdf"]}, {"id": "670b10569c5f978ee70d99cf8c14ad9cabb9d454", "title": "Masked face detection via a modified LeNet", "year": "2016", "pdf": []}, {"id": "4acf31294e940d85a4eea56c244205e3a66d8b8e", "title": "Improving Product Classification Using Images", "year": "2011", "pdf": ["http://talukdar.net/papers/ImageText-ICDM2011.pdf"]}, {"id": "057f5ffda59a3412f1e62159e96f84faa352628e", "title": "Tracking with scattering descriptor", "year": "2014", "pdf": []}, {"id": "8a382f000f98cdab7f7b79e543c75c6b8f93b6f9", "title": "Learning Semantic Image Representations at a Large Scale", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/8a38/2f000f98cdab7f7b79e543c75c6b8f93b6f9.pdf"]}, {"id": "7d35fe4f4a932d7598d94d64b72cfa7e6a70286d", "title": "Experimental Evaluation of Multiplicative Kernel SVM Classifiers for Multi-Class Detection", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/7d35/fe4f4a932d7598d94d64b72cfa7e6a70286d.pdf"]}, {"id": "a887937b813f267507203d4faef1013043cf09d0", "title": "Automatic Process to Build a Contextualized Detector", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/5891/b87c0eecd76f067c5bafd9cd0702ac6d2fc7.pdf"]}, {"id": "4404a99e2f6db3e703609168a3595e0fbdeabc38", "title": "Online Video SEEDS for Temporal Window Objectness", "year": "2013", "pdf": ["http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Van_Den_Bergh_Online_Video_SEEDS_2013_ICCV_paper.pdf", "http://www.mvdblive.org/research/videoseeds.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01056.pdf"]}, {"id": "59ee0f67bcf2d8ea0bbbfcbc71159725fc3a7059", "title": "Object Detection with Appearance-based Mixture Models Anonymous CVPR submission", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/59ee/0f67bcf2d8ea0bbbfcbc71159725fc3a7059.pdf"]}, {"id": "e478c322de923337627487d8a688f5922b45b2ff", "title": "Automatic Garage Door Opening Using License Plate Recognition and Fingerprint Verification", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/e478/c322de923337627487d8a688f5922b45b2ff.pdf"]}, {"id": "1642358cd9410abe9ee512d34ba68296b308770e", "title": "Robustness Analysis of Pedestrian Detectors for Surveillance", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.04562.pdf"]}, {"id": "73c9cbbf3f9cea1bc7dce98fce429bf0616a1a8c", "title": "Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02193.pdf"]}, {"id": "8a3b481d8e06b4acf6e95d8bc2484016f5862668", "title": "Text Detection in Traffic Informatory Signs Using Synthetic Data", "year": "2017", "pdf": []}, {"id": "7c594c0b9482624745dd95767f3eebde1ee7f043", "title": "Representing Visual Scenes for Robot Control", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/7c59/4c0b9482624745dd95767f3eebde1ee7f043.pdf"]}, {"id": "0ceda9dae8b9f322df65ca2ef02caca9758aec6f", "title": "Context-Aware CNNs for Person Head Detection", "year": "2015", "pdf": []}, {"id": "5f0e9cc18374a670dfea4698424c9d48494f3093", "title": "Online Domain Adaptation for Multi-Object Tracking", "year": "2015", "pdf": ["https://arxiv.org/pdf/1508.00776.pdf"]}, {"id": "d47d72afc590f5b96117a5227d45157135da21ad", "title": "Attribute-based knowledge transfer learning for human pose estimation", "year": "2013", "pdf": []}, {"id": "0d4cdadd765c3003b0bd5f762b84bef93408f548", "title": "Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks", "year": "2014", "pdf": []}, {"id": "397bfda299f789f0c84bf284a868b9ca005c7f84", "title": "Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02700.pdf"]}, {"id": "a13dac9255dd738932f463a8f462c11419f072db", "title": "Use of Generative Adversarial Network for Cross-Domain Change Detection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.08868.pdf"]}, {"id": "5d16ce0c66cd87dd48cb8c53f5b6a7ee73d33abb", "title": "Robust and Real-Time Object Tracking Using Scale-Adaptive Correlation Filters", "year": "2016", "pdf": []}, {"id": "050e5b4043009e54dff9319877fe947885db2d6e", "title": "Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Lai_Saliency_Guided_Dictionary_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Lai_Saliency_Guided_Dictionary_CVPR_2016_paper.pdf"]}, {"id": "926dd1c4db38356ac5bf87c1a4c6b93625f9a850", "title": "Pulling Actions out of Context: Explicit Separation for Effective Combination", "year": "2018", "pdf": []}, {"id": "b705ca751a947e3b761e2305b41891051525d9df", "title": "Exploring Context with Deep Structured Models for Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1603.03183.pdf"]}, {"id": "be48b5dcd10ab834cd68d5b2a24187180e2b408f", "title": "Constrained Low-Rank Learning Using Least Squares-Based Regularization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.04870.pdf"]}, {"id": "b2f63863e73a8565895ca3d9d7d6a1e10a7695b1", "title": "Efficient Neural Network Compression via Transfer Learning for Industrial Optical Inspection", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b2f6/3863e73a8565895ca3d9d7d6a1e10a7695b1.pdf"]}, {"id": "044ae9738c2445d4fda30fcd6c289eddf8b3add9", "title": "Multiple Instance Learning: A Survey of Problem Characteristics and Applications", "year": "2018", "pdf": ["https://arxiv.org/pdf/1612.03365.pdf"]}, {"id": "2ba540ca70c7dee81e13768792aa7571952987f6", "title": "Drivable Road Detection Based on Dilated FPN with Feature Aggregation", "year": "2017", "pdf": []}, {"id": "6c9f45c76b4f96fe66d8e1d7b31f89b7cc6caa44", "title": "DeNet: Scalable Real-Time Object Detection with Directed Sparse Sampling", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.10295.pdf"]}, {"id": "a0ae4ffe252f32514240cf6d82d52538de5fb78c", "title": "AN ALGORITHM FOR PEDESTRIAN DETECTION IN MULTISPECTRAL IMAGE SEQUENCES", "year": "", "pdf": ["https://pdfs.semanticscholar.org/a0ae/4ffe252f32514240cf6d82d52538de5fb78c.pdf"]}, {"id": "115e8a4f76a57b893c985ea4f7530b90d071679c", "title": "FSSD: Feature Fusion Single Shot Multibox Detector", "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.00960.pdf"]}, {"id": "c2be82ed0db509087b08423c8cf39ab3c36549c3", "title": "Pixel-level guided face editing with fully convolution networks", "year": "2017", "pdf": []}, {"id": "92f2639dbd9f7c4284b7012809e4d2c407834774", "title": "Point-based Medialness 2 D Shape Description and Identification", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/92f2/639dbd9f7c4284b7012809e4d2c407834774.pdf"]}, {"id": "4ace7c8edd9467c7d5bfa00e942531e7b889e650", "title": "Depth-Based Hand Pose Estimation: Data, Methods, and Challenges", "year": "2015", "pdf": ["http://vision.ics.uci.edu/papers/SupancicRYSR_ICCV_2015/SupancicRYSR_ICCV_2015.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Supancic_Depth-Based_Hand_Pose_ICCV_2015_paper.pdf"]}, {"id": "4c454fda214e00c9cba4bb759da78949a4130873", "title": "Specialization of a Generic Pedestrian Detector to a Specific Traffic Scene by the Sequential Monte-Carlo Filter and the Faster R-CNN", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/4c45/4fda214e00c9cba4bb759da78949a4130873.pdf"]}, {"id": "f541dac9d0d49cadb3cfd018e87b26e03e3f13aa", "title": "Trio Constrained Adaptive Noise Removal ( TCANR ) Mechanism for Salt and Pepper Noise in Image Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f541/dac9d0d49cadb3cfd018e87b26e03e3f13aa.pdf"]}, {"id": "aa2ad3df24d8d8c4a4d2fe85f0d4e635d595f0a2", "title": "PedCut: an iterative framework for pedestrian segmentation combining shape models and multiple data cues", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/c029/edca476ddda4050c3c67748056c6189cd1e3.pdf"]}, {"id": "d250e57f6b7e06bb1dac41c8b89700086a85999e", "title": "Self-Supervised Generalisation with Meta Auxiliary Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08933.pdf"]}, {"id": "de35ea60396629b2d1ceb73df56a97ed21012680", "title": "Robust object tracking via multi-scale patch based sparse coding histogram", "year": "2016", "pdf": []}, {"id": "a0e286f3c6a72c857ffd03bd8ab9a9f9b98c4432", "title": "AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04452.pdf"]}, {"id": "19339e816d8006ad462868b01812b03eb463ead1", "title": "Collective activity localization by spatiality preservation search", "year": "2016", "pdf": []}, {"id": "899e7ff67aa2630edc8776758cc5d65823f099c1", "title": "G-CNN: Object Detection via Grid Convolutional Neural Network", "year": "2017", "pdf": []}, {"id": "18ccd8bd64b50c1b6a83a71792fd808da7076bc9", "title": "Object detection and segmentation from joint embedding of parts and pixels", "year": "2011", "pdf": ["http://ttic.uchicago.edu/~mmaire/papers/pdf/seg_obj_iccv2011.pdf", "http://ttic.uchicago.edu/~mmaire/papers/pdf/seg_obj_iccv2011_slides.pdf", "http://vision.caltech.edu/~mmaire/papers/pdf/seg_obj_iccv2011.pdf", "http://vision.caltech.edu/~mmaire/papers/pdf/seg_obj_iccv2011_slides.pdf", "http://www.eecs.berkeley.edu/~stellayu/publication/doc/2011objSlides.pdf", "http://www1.icsi.berkeley.edu/~stellayu/publication/doc/2011objSlides.pdf"]}, {"id": "139ab79a0aae5d4346f907b7b29288d09ef373fa", "title": "A Baseline for Multi-Label Image Classification Using Ensemble Deep CNN", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08412.pdf"]}, {"id": "94780b00dc2807ec507ae91500b622ec7a8ddb12", "title": "Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.06295.pdf"]}, {"id": "fa496716a5b8520e94a0126b5baa4f636623c997", "title": "Revisiting Knowledge Transfer for Training Object Class Detectors", "year": "2018", "pdf": ["https://arxiv.org/pdf/1708.06128.pdf"]}, {"id": "c2cb4da617168c76c4560a01de8b5e68b5250749", "title": "FineTag: Multi-attribute Classification at Fine-grained Level in Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.07124.pdf"]}, {"id": "87d5b53580ca5f77ccc3ff157337ef3456308943", "title": "Augmented Autoencoders for object orientation estimation trained on synthetic RGB images", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/87d5/b53580ca5f77ccc3ff157337ef3456308943.pdf"]}, {"id": "eb2333a759788903848c49111a03c4c00d188e70", "title": "Color-based and Rotation Invariant Self-similarities", "year": "2017", "pdf": ["http://www.scitepress.org/Papers/2017/61075/61075.pdf"]}, {"id": "af9cc1767f50f63291d7ca9ab709f6849cd1e46c", "title": "Graph-Driven Diffusion and Random Walk Schemes for Image Segmentation.", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/af9c/c1767f50f63291d7ca9ab709f6849cd1e46c.pdf"]}, {"id": "4fe91feab83d947a0d3bd85adcf18ab1b3d9e05f", "title": "Transductive People Tracking in Unconstrained Surveillance", "year": "2016", "pdf": ["http://imagelab.ing.unimore.it/Pubblicazioni/pubblicazioni/2015TCSVT.pdf"]}, {"id": "8eaade06b75dac977574d05ce1058b86df059d47", "title": "Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation", "year": "2014", "pdf": ["http://people.eecs.berkeley.edu/~sgupta/pdf/ijcv14a.pdf"]}, {"id": "b9b21cfa7de32677151571ab44d27d2d246b7a03", "title": "Towards Explanation of DNN-based Prediction with Guided Feature Inversion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00506.pdf"]}, {"id": "4152d2c8585f7e3f85d3b3d84036171de104cbd7", "title": "Rethinking ImageNet Pre-training", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08883.pdf"]}, {"id": "b31f37fd71b7b45e6fd8978960e271a7db1ee212", "title": "DICTING IMAGE ROTATIONS", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b31f/37fd71b7b45e6fd8978960e271a7db1ee212.pdf"]}, {"id": "1a1654456decd116f4ca84c98006dfda0a8a3134", "title": "INTEGRATED VISUAL INFORMATION FOR MARITIME SURVEILLANCE", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1a16/54456decd116f4ca84c98006dfda0a8a3134.pdf"]}, {"id": "8f76401847d3e3f0331bab24b17f76953be66220", "title": "Deep Coding Network", "year": "2010", "pdf": ["http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2010_1077.pdf", "http://papers.nips.cc/paper/3929-deep-coding-network.pdf", "http://stat.rutgers.edu/home/tzhang/papers/nips10-coding.pdf", "http://www.linyq.com/DCN_slides.pdf"]}, {"id": "55f7699e768457d40c5232448cdca4503db2821b", "title": "Temporal consistency object tracker with ranking mechanism", "year": "2015", "pdf": []}, {"id": "3e00dd86c084d8680409c65c1a48f1b3aa864eb7", "title": "Deep Crisp Boundaries: From Boundaries to Higher-Level Tasks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1801.02439.pdf"]}, {"id": "1e5edbd39b4c61f785515e117a74e2d280aefbe7", "title": "The urrent tate and TRL ssessment of eople racking echnology for ideo urveillance pplications", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1e5e/dbd39b4c61f785515e117a74e2d280aefbe7.pdf"]}, {"id": "2e1f0b522014c942197e51b556eeb48b6ad66cda", "title": "Automatic object classification using motion blob based local feature fusion for traffic scene surveillance", "year": "2012", "pdf": []}, {"id": "e295c1aa47422eb35123053038e62e9aa50a2e3a", "title": "ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition Datasets and Results", "year": "2015", "pdf": ["http://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w11/papers/Escalera_ChaLearn_Looking_at_ICCV_2015_paper.pdf"]}, {"id": "25858dc59faf2630bf0eefe23297ce262370cff0", "title": "Monitoring Giraffe Behavior in Thermal Video", "year": "2015", "pdf": []}, {"id": "e545f1c06799bfd2bd5f7eaed085fd60a388202f", "title": "A top-down manner-based DCNN architecture for semantic image segmentation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/e545/f1c06799bfd2bd5f7eaed085fd60a388202f.pdf"]}, {"id": "7b3a63d030d03e536ddcbc217bc8d6fd630e3b53", "title": "xView: Objects in Context in Overhead Imagery", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.07856.pdf"]}, {"id": "4a6049e1926cc8e574301cfb229599cdc0a64e62", "title": "Characterizing the performance of an image-based recognizer for planar mechanical linkages in textbook graphics and hand-drawn sketches", "year": "2015", "pdf": ["http://vdel.me.cmu.edu/publications/2015cag/paper.pdf"]}, {"id": "ec6f1a4b9367675833f0111c44a22ba217fcbd23", "title": "Visual Tracking via Constrained Incremental Non-negative Matrix Factorization", "year": "2015", "pdf": []}, {"id": "5950512e21114236208b9eaeebc9a09735e367a6", "title": "Master research Internship Internship report Segmentation and recognition of symbols for printed and handwritten music scores", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5950/512e21114236208b9eaeebc9a09735e367a6.pdf"]}, {"id": "c7780cff11068fecb322a43e459c56267a88aee7", "title": "DeepVoting: An Explainable Framework for Semantic Part Detection under Partial Occlusion", "year": "2017", "pdf": []}, {"id": "98bf42055160845e6f8f3c022298e3b8e4e55f80", "title": "Vision Meets Drones: A Challenge", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.07437.pdf"]}, {"id": "19b6b0649cc669791c799c52fc56bdc556f06916", "title": "Efficient Model Evaluation with Bilinear Separation Model", "year": "2015", "pdf": []}, {"id": "4ff486644be5e451784d6ae83f8073c8320fa974", "title": "Visual Tracking with Convolutional Neural Network", "year": "2015", "pdf": []}, {"id": "a43f460f6c1abbe8eb0097594df6eafc0f651d49", "title": "Saliency-based object recognition in video", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a43f/460f6c1abbe8eb0097594df6eafc0f651d49.pdf"]}, {"id": "b4df58f1fd8a3bd0815e7fb957f7f07fddd77338", "title": "Rethinking the sGLOH Descriptor", "year": "2018", "pdf": ["http://cvg.dsi.unifi.it/colombo_now/CC/Public/sGLOH2_TPAMI_2017.pdf"]}, {"id": "ceee9ba72a021ae5604db04a93fdcff421d60216", "title": "Encoder Based Lifelong Learning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.01920.pdf"]}, {"id": "c4a0e89793961dc486964802df55ae73fbba60ee", "title": "Soccer: Who Has the Ball? Generating Visual Analytics and Player Statistics", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w34/Theagarajan_Soccer_Who_Has_CVPR_2018_paper.pdf", "http://vislab.ucr.edu/PUBLICATIONS/pubs/Journal%20and%20Conference%20Papers/after10-1-1997/Conference/2018/FINAL-published-soccer-ball-generating.pdf"]}, {"id": "2622d2467f19bc60427f8ea495515e7da82316c9", "title": "Tell Me Where to Look: Guided Attention Inference Network", "year": "2018", "pdf": []}, {"id": "ccee8af5667d1d3bccf30baf2c6f049f031bb5ad", "title": "Mixing Hierarchical Contexts for Object Recognition", "year": "2011", "pdf": ["http://web.ing.puc.cl/~asoto/papers/Peralta-2011.pdf"]}, {"id": "36aa5dd816553ba2e666d2a4b7d2f346e4b56be2", "title": "Variable scale and anti-occlusion object tracking method with multiple feature integration", "year": "2016", "pdf": []}, {"id": "c96f012f4915398259e7e223810c57898b5e1a76", "title": "Fast LIDAR-based Road Detection Using Convolutional Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c96f/012f4915398259e7e223810c57898b5e1a76.pdf"]}, {"id": "7142e659d6466717cdb8a242d8e34fce176b3f4a", "title": "Improved scene identification and object detection on egocentric vision of daily activities", "year": "2017", "pdf": ["http://crcv.ucf.edu/news&info/DefenseBooklet_FA17.pdf", "http://crcv.ucf.edu/papers/cviu2016-gonzalo.pdf", "http://vision.eecs.ucf.edu/papers/cviu2016-gonzalo.pdf"]}, {"id": "3b483c986b973856e016f761ec312c1a339766a5", "title": "DOTA: A Large-Scale Dataset for Object Detection in Aerial Images", "year": "2018", "pdf": []}, {"id": "e9d82ae7530e605c03440d362d78663c4af0edb6", "title": "Object Detection Using Color Entropies and a Fuzzy Classifier", "year": "2013", "pdf": []}, {"id": "1281e443d2cf1c1dd71ed3b7b0376d408d0958af", "title": "SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks", "year": "2015", "pdf": ["http://www.cs.cornell.edu/~xhuang/publications/salicon_poster.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Huang_SALICON_Reducing_the_ICCV_2015_paper.pdf"]}, {"id": "71f7be73a575f3689b0137446289d02462e1c5b0", "title": "Adaptive Multi-Scale Information Flow for Object Detection.", "year": "2018", "pdf": ["http://bmvc2018.org/contents/papers/0266.pdf"]}, {"id": "581fb0f0405c7f0e60610d88ceaceb9af44d8569", "title": "Final Report : Smart Trash Net : Waste Localization and Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/581f/b0f0405c7f0e60610d88ceaceb9af44d8569.pdf"]}, {"id": "eaa7c6293c9d858bd4c9897a5dfc7c670f2a8671", "title": "Distant Vehicle Detection Using Radar and Vision", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.10951.pdf"]}, {"id": "2cea306754ed83eaf1d0433abbfb05b5a4c4cf48", "title": "BIG-OH: BInarization of gradient orientation histograms", "year": "2014", "pdf": ["http://vgl-ait.org/mdailey/uploads/publication_file/filename/110/Baber-BIG-OH.pdf"]}, {"id": "eb2ab9caa61b021c1cd7aff6d08163768faba99e", "title": "Cleaning Up Multiple Detections Caused by Sliding Window Based Object Detectors", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/eb2a/b9caa61b021c1cd7aff6d08163768faba99e.pdf"]}, {"id": "5a364ecb2d10b637c63b885d27eb372390232277", "title": "Unsupervised Robust Feature-Based Partition Ensembling to Discover Categories", "year": "2016", "pdf": []}, {"id": "1114c2aba97a5782a48341817811df2438d0fdbf", "title": "Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07498.pdf"]}, {"id": "367008b91eb57c5ea64ef7520dfcabc0c5c85532", "title": "Person Re-identification: Past, Present and Future", "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.02984.pdf"]}, {"id": "8211c974ec152e79235cb57a03ba2971e913508f", "title": "Multimodal Image Retrieval", "year": "2012", "pdf": []}, {"id": "eb69f89588e9538194750f12bf8c8df6d5301f3b", "title": "Object Tracking by a Combination of Discriminative Global and Generative Multi-Scale Local Models", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/eb69/f89588e9538194750f12bf8c8df6d5301f3b.pdf"]}, {"id": "c23734cf46af7c299b72089e5cbc0e50b833e434", "title": "Edge color transform: a new operator for natural scene text localization", "year": "2017", "pdf": []}, {"id": "d6bdc70d259b38bbeb3a78db064232b4b4acc88f", "title": "Video-Based Face Association and Identification", "year": "2017", "pdf": []}, {"id": "d2e8efaa0d095c22455fe4eab260f94994bfb116", "title": "Stand-alone quality estimation of background subtraction algorithms", "year": "2017", "pdf": []}, {"id": "abe9f3b91fd26fa1b50cd685c0d20debfb372f73", "title": "The Pascal Visual Object Classes Challenge: A Retrospective", "year": "2014", "pdf": ["http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc14.pdf", "http://www.robots.ox.ac.uk/~vgg/publications/2015/Everingham15/everingham15.pdf", "https://www.research.ed.ac.uk/portal/files/20017166/ijcv_voc14.pdf"]}, {"id": "10d3f77225eca1d576268ba84ed83f230a5e47c4", "title": "Crafting a multi-task CNN for viewpoint estimation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.03894.pdf"]}, {"id": "a01c7eec51fa901b2526325f563480c152c58ee5", "title": "Contour Box: Rejecting Object Proposals without Explicit Closed Contours", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Lu_Contour_Box_Rejecting_ICCV_2015_paper.pdf", "http://www.cse.cuhk.edu.hk/leojia/papers/contour_iccv15.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Lu_Contour_Box_Rejecting_ICCV_2015_paper.pdf"]}, {"id": "3db4bdee7bc03239ef25d23cf8dc14ce5a5300e2", "title": "Sparse Coding for Object Recognition", "year": "2013", "pdf": []}]}