2013 ICCV 文章列表

链接：http://www.cs.toronto.edu/~kyros/local_outgoing/ICCV-Final-Results/

ICCV 2013 Results (29 Aug, 2013)

Papers submitted: 1629

Withdrawals and administrative rejections: 128

Accepted as Orals: 41 (2.52% oral acceptance rate)

Accepted as Posters: 413 (27.87% total acceptance rate)

Acceptances per Primary Subject Area # Papers Submitted# Papers AcceptedAcceptance ratePrimary Subject Area   Recognition: detection, categorization, classification, indexing, matching44413831.0810813D computer vision1534126.797386Motion and tracking1483825.675676Video: events, activities & surveillance1464228.767123Face and gesture1434027.972028Low-level vision and image processing1322821.212121Segmentation, grouping and shape representation1223125.409836Statistical methods and learning912224.175824Computational photography, sensing and display872326.436782Optimization methods632438.095238Physics-based vision and Shape-from-X29931.034483Medical and biological image analysis25416.000000Performance evaluation14428.571429Vision for the web11218.181818Vision for graphics9555.555556Document analysis6350.000000Robotics600.000000

Orals  TitleAuthorsPrimary Subject Area   3D computer vision39Elastic Fragments for Dense Scene ReconstructionQian-Yi Zhou*, Stanford University; Stephen Miller, Stanford University; Vladlen Koltun, Stanford University702A Global Linear Method for Camera Pose RegistrationNianjuan Jiang*, ADSC; Zhaopeng Cui, NUS; Ping Tan,748A Rotational Stereo Model Based On XSlit ImagingJinwei Ye*, University of Delaware; Yu Ji, University of Delaware; Jingyi Yu, University of Delaware1177Lifting 3D Manhattan Lines from a Single ImageSrikumar Ramalingam*, MERL; Matthew Brand, MERL1588Rolling Shutter StereoOlivier Saurer*, ETH Zurich; Kevin Koeser, ; Jean-Yves Bouguet, Google ; Marc Pollefeys, ETHComputational photography, sensing and display845Nonparametric Blind Super-ResolutionTomer Michaeli*, Weizmann Institute of Science; Michal Irani, Weizmann Institute, Israel1696Scene Intensity and Depth Acquisition from One Detected Photon per PixelAhmed Kirmani*, MIT; Dongeek Shin, MIT; Dheera Venkatraman, MIT; Franco Wong, MIT; Vivek Goyal, MITFace and gesture1680A Practical Transfer Learning Algorithm for Face VerificationXudong Cao*, Microsoft Research Asia; David Wipf,Low-level vision and image processing178Benchmarking Computational Model of Visual SaliencyAli Borji*, ; Dicky Sihite, University of Southern California (USC); Hamed Rezazadegan Tavakoli, University of Oulu; Laurent Itti, University of Southern California (USC)389A Color Constancy Model with Double-Opponency MechanismsShaobing Gao, UESTC; Kaifu Yang, UESTC; Yongjie Li*, UESTC436Estimating Human Scanpath Using Hidden Markov ModelHuiying Liu*, Institute of Computing Technol; Dong Xu, "NTU, Singapore"; Qingming Huang, Graduate Univ of Chinese Academy of Sciences; Wen LI, NTU; Stephen Lin, Microsoft Research Asia547Structured Forests for Fast Edge DetectionPiotr Dollar*, ; Larry Zitnick, "Microsoft Research, USA"Motion and tracking307Hierarchical Data-driven Descent for Efficient Optimal Deformation EstimationYuandong Tian*, Carnegie Mellon University; Srinivas Narasimhan, Carnegie Mellon University319Perspective Motion Segmentation via Collaborative ClusteringZhuwen Li*, NUS; Jiaming Guo, NUS; Loong-Fah Cheong, NUS; Zhiying Zhou, NUS1036Piecewise Rigid Scene FlowChristoph Vogel*, ETH Zurich; Konrad Schindler, ETH Zurich; Stefan Roth, "TU Darmstadt, Germany"1095Large displacement optical flow with deep matchingPhilippe Weinzaepfel*, INRIA; Jerome Revaud, ; Zaid Harchaoui, INRIA; Cordelia Schmid, "INRIA, France"1530Orderless Tracking through Model-Averaged Density EstimationSeunghoon Hong*, POSTECH; Suha Kwak, POSTECH; Bohyung Han, POSTECH1911The Way They Move: Tracking Multiple Targets with Similar AppearanceCaglayan Dicle, neu.edu; Octavia Camps*, ; Mario Sznaier, Northeastern UniversityOptimization methods68Active MAP Inference in CRFs for Efficient Semantic SegmentationGemma Roig, ETH; Xavier Boix*, ETH; Roderick De Nijs, TUM; Sebastian Ramos, Computer Vision Center (CVC); Luc Van Gool, ETH1031Potts model, parametric maxflow and k-submodular functionsIgor Gridchyn, IST Austria; Vladimir Kolmogorov*, "IST, Austria"1739Proportion Priors for Image Sequence SegmentationClaudia Nieuwenhuis*, ; Evgeny Strekalovskiy, TU Munich; Daniel Cremers, Technische Universitt Mnchen1900Coarse-to-fine Semantic Video Segmentation using Supervoxel TreesRene Vidal*, Johns Hopkins University; Aastha Jain, LinkedinPerformance evaluation1055Finding the Best from the Second Bests -- Inhibiting Subjective Bias in Evaluation of Visual Tracking AlgorithmsYU PANG*, Temple univeristy; Haibin Ling,Physics-based vision and Shape-from-X523Towards Guaranteed Illumination Models for Non-Convex ObjectsYuqian Zhang*, Columbia University; Cun Mu, Columbia University; Han-wen Kuo, Columbia University; John Wright,740Separating Reflective and Fluorescent Components using High Frequency Illumination in the Spectral DomainYing Fu*, The University of Tokyo; Antony Lam, National Institute of Informatics; Imari Sato, ; Takahiro Okabe, ; Yoichi Sato, The University of Tokyo, Japan"Recognition: detection, categorization, classification, indexing, matching52HOGgles: Visualizing Object Detection FeaturesCarl Vondrick*, MIT; Aditya Khosla, ; Tomasz Malisiewicz, ; Antonio Torralba, MIT81Regionlets for Generic Object DetectionXiaoyu Wang*, NEC Labs America; Ming Yang, NEC Labs America; Shenghuo Zhu, ; Yuanqing Lin,189How Do You Tell a Blackbird from a Crow?Thomas Berg*, Columbia University; Peter Belhumeur, "Columbia University, USA"454Learning to predict gaze in egocentric videoYin Li*, Georgia Institute of Technolog; Alireza Fathi, Georgia Institute of Technology; James Rehg, Georgia Institute of Technology569From Large Scale Image Categorization to Entry-Level CategoriesVicente Ordonez*, Stony Brook University; Jia Deng, Stanford University; Yejin Choi, Stony Brook University; Alexander Berg, Stony Brook University; Tamara Berg, "Stony Brook University, USA"738Style-aware Mid-level Representation for Discovering Visual Connections in Space and TimeYong Jae Lee*, Robotics Institute, Carnegie Mellon University; Alexei (Alyosha) Efros, CMU; Martial Hebert, "CMU, USA"884Shufflets: shiftable shared parts for multi-category detectionIasonas Kokkinos*, "Ecole Centrale Paris, France"965To aggregate or not to aggregate: Selective match kernels for image searchGiorgos Tolias, ; Yannis Avrithis, NTUA; Herv Jgou*, INRIA1173NEIL: Extracting Visual Knowledge from Web DataXinlei Chen, CMU; Abhinav Shrivastava, Carnegie Mellon University; Abhinav Gupta*,1546Learning Graphs to MatchMinsu Cho*, ; Karteek Alahari, ENS-Willow; Jean Ponce, "ENS, France"1649Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant DecompositionJoo Henriques, Institute of Systems and Robotics - University of Coimbra; Rui Caseiro*, Institute of Systems and Robotics - University of Coimbra; Joao Carreira, University of Coimbra; Jorge Batista, ISR1685Real-time Articulated Hand Pose Estimation using Semi-supervised Transductive Regression ForestsDanhang Tang*, Imperial College London1788Holistic Scene Understanding for 3D Object Detection with RGBD camerasDahua Lin*, TTIC; Sanja Fidler, TTI Chicago ; Raquel Urtasun, Toyota Technological Institute at Chicago1965Fast Subspace Search via Grassmannian Based HashingXu Wang*, University of Minnesota; Stefan Atev, ; John Wright, ; Gilad Lerman, University of MinnesotaSegmentation, grouping and shape representation1151Tree Shape Priors with Connectivity Constraints using Convex Relaxation on General GraphsJan Sthmer*, TU Munich; Peter Schrder, Caltech; Daniel Cremers, Technische Universitt Mnchen1500Weakly supervised learning of image partitioning using decision trees with structured split criteriaChristoph Straehle*, HCI, University of Heidelberg; Ullrich Koethe, ; Fred Hamprecht, HCI, University of Heidelberg

Posters  TitleAuthorsPrimary Subject Area   3D computer vision79Shape Anchors for Data-driven Multi-view ReconstructionAndrew Owens, MIT; Jianxiong Xiao*, MIT; Antonio Torralba, MIT; Bill Freeman, "MIT, USA"198Dynamic Probabilistic Volumetric ModelsAli Ulusoy*, Brown University; Joseph Mundy, Brown University309Street View Structure-from-MotionBryan Klingner*, Google; David Martin, Google; James Roseborough, Google3963D Scene Understanding by Voxel-CRFByung-soo Kim*, ; Pushmeet Kohli, "Microsoft Research, UK"; Silvio Savarese, "University of Michigan, USA"4003DNN: Viewpoint Invariant 3D Geometry Matching for Scene UnderstandingScott Satkin*, Carnegie Mellon University; Martial Hebert, "CMU, USA"418Revisiting the P\(n\)P Problem: A Fast, General and Optimal SolutionYinqiang Zheng*, Tokyo Institute of Technology; Yubin Kuang, Lund University; shigeki Sugimoto, Tokyo Institute of Technology; Kalle Astrom, Lund University ; Masatoshi Okutomi, Tokyo Institute of Technology462Line Assisted Light Field Triangulation and Stereo MatchingZhan Yu*, University of Delaware; Xinqing Guo, University of Delaware; Jingyi Yu, University of Delaware473Enhanced Continuous Tabu Search for Parameter Estimation in Multiview GeometryGuoqing Zhou, Northwestern Polytechnical University; Qing Wang*, Northwestern Polytechnical Uni509Deterministic Fitting of Multiple Structures using Iterative MaxFS with Inlier Scale EstimationKwang Hee Lee*, Sogang University; Sang Lee, "Sogang University, Korea"535Network Principles for SfM: Disambiguating Repeated Structures with Local ContextKyle Wilson*, Cornell University; Noah Snavely, "Cornell, USA"541A Robust Analytical Solution to Isometric Non-Rigid Pose with Focal Length CalibrationAdrien Bartoli*, Universit?d'Auvergne; Daniel Pizarro, ALCoV-ISIT; Toby Collins, ALCoV-ISIT582Complex 3D General Object Reconstruction from Line DrawingsLinjie Yang*, CUHK; Jianzhuang Liu, CUHK; Xiaoou Tang, Chinese University of Hong Kong668Local Signal Equalization for Correspondence MatchingDerek Bradley*, Disney Research Zurich; Thabo Beeler, Disney Research Zurich682Direct Optimization of Frame-to-Frame RotationLaurent Kneip*, ETH Zurich; Simon Lynen, ETH Zurich813A Flexible Scene Representation for 3D Reconstruction Using RGB-D CameraDiego Thomas*, National Institute of Informat; Akihiro Sugimoto,889Global Fusion of Relative Motions for Robust, Accurate and Scalable Structure from Motion.Pierre Moulon*, Imagine; Pascal Monasse, ; Renaud Marlet,897Constant Time Weighted Median Filtering for Stereo Matching and BeyondZiyang Ma*, Institute of Software, CAS; Kaiming He, Mirosoft Research Asia; Yichen Wei, ; Jian Sun, "Microsoft Research, China"; Enhua Wu, Faculty of Science and Technology, University of Macau902Efficient and Robust Large-Scale Rotation AveragingAvishek Chatterjee, Indian Institute of Science; Venu Madhav Govindu*, Indian Institute of Science905Point-Based 3D Reconstruction of Thin ObjectsBenjamin Ummenhofer*, University of Freiburg; Thomas Brox,934Subpixel scanning invariant to indirect lighting using quadratic code lengthNicolas Martin*, ; Vincent Couture, ; Sebastien Roy,975Monocular Image 3D Human Pose Estimation under Self-OcclusionIbrahim Radwan*, University of Canberra; Abhinav Dhall, Australian National University; Roland Goecke,1121PM-Huber: PatchMatch with Huber Regularization for Stereo MatchingPhilipp Heise*, TU Mnchen; Sebastian Klose, TU Mnchen; Brian Jensen, TU Mnchen; Alois Knoll, TU Mnchen1158Image Aided Automatic Registration of Laser Scans via Salient DirectionsBernhard Zeisl*, ETH; Kevin Koeser, ; Marc Pollefeys, ETH1241Internet-based morphable modelIra Kemelmacher*, University of Washington1348Refractive Structure-from-Motion on Underwater ImagesAnne Jordt-Sedlazeck*, Kiel University; Reinhard Koch, Christian-Albrechts-Universitat Kiel1394Pose Estimation with Unknown Focal Length using Points, Directions and LinesYubin Kuang*, Lund University; Kalle Astrom, Lund University1535Space-Time Tradeoffs in Photo SequencingTali Basha Dekel*, TAU; Shai Avidan, Tel-Aviv University; Yael Moses,1567Real-Time Semi-Dense Monocular SLAM: A Statistical ApproachJakob Engel*, Technical University Munich; Juergen Sturm, TU Munich; Daniel Cremers, Technische Universitt Mnchen1584Multi-View 3D Reconstruction from Uncalibrated Radially-Symmetric CamerasJae-Hak Kim*, ANU; Yuchao Dai, Australian National University; Du Xin, ; Hongdong Li, Australia National University; Jonghyuk Kim, ANU1632Extrinsic Camera Calibration Without A Direct View Using Spherical MirrorAmit Agrawal*, MERL1657Real-time solution to the absolute pose problem with unknown radial distortion and focal lengthZuzana Kukelova*, ; Martin Bujnak, Bzovicka 24, 85107, Bratislava, Slovakia; Tomas Pajdla, Czech Technical University1688Large-Scale Multi-Resolution Surface Reconstruction from RGB-D SequencesFrank Steinbrcker*, Technical University of Munich; Christian Kerl, in.tum.de; Juergen Sturm, TU Munich; Daniel Cremers, in.tum.de1725Live Metric 3D Reconstruction on Mobile PhonesPetri Tanskanen, ETH Zurich; Kalin Kolev*, ETH Zurich; Lorenz Meier, ETH Zurich; Federico Camposeco Paulsen, ETH Zurich; Olivier Saurer, ETH Zurich; Marc Pollefeys, ETH1729Unsupervised intrinsic calibration from a single frame using a "plumb-line" approachRui Melo*, ISR-Coimbra; Michel Antunes, ; Joao Barreto, ; Gabriel Falco, ; Nuno Gonalves,1800An Enhanced Structure-from-Motion Paradigm based on the Absolute Dual Quadric and Images of Circular PointsLilian Calvet*, University of Toulouse; Pierre Gurdjos, IRIT1859Globally-Optimal ICP : Solving the 3D Registration Problem Efficiently and Globally OptimallyJiaolong Yang, Beijing Inst. of Tech.; Hongdong Li*, Australia National University; Yunde Jia,Computational photography, sensing and display54Joint Subspace Stabilization for Stereoscopic VideoFeng Liu*, Portland State University; Yuzhen Niu, ; Hailin Jin,100Structured Light in SunlightQi Yin*, Columbia University; Mohit Gupta, ; Shree Nayar, Columbia University122Image Guided Depth Upsampling using Anisotropic Total Generalized VariationDavid Ferstl*, Graz University of Technology; Christian Reinbacher, ; Matthias Rther, ; Horst Bischof, Graz University of Technology239Forward Motion DeblurringShicheng Zheng*, CUHK; Li Xu, CUHK; Jiaya Jia, Chinese University of Hong Kong249Corrected-Moment Illuminant EstimationGraham Finlayson*, University of East Anglia375Robust non-parametric Correspondence FittingWen-Yan Lin*, Oxford Brookes; Ming Ming Chen, ; Kyle Zheng, ; Jiangbo Lu, Advanced Digital Sciences Cent; Crook Nigel,409Rectangling Stereographic Projection for Wide-Angle Image VisualizationChe-Han Chang*, National Taiwan University; Yung-Yu Chuang, National Taiwan University424Dynamic Scene DeblurringTae Hyun Kim, Seoul National Univ.; Byeongjoo Ahn, Seoul National University; Kyoung Mu Lee*, Seoul National University514Video Synopsis by Heterogeneous Multi-Source CorrelationXiatian Zhu*, Queen Mary, Univ. of London; Chen Change Loy, CUHK; Shaogang Gong, EECS, QMUL644Content-Aware RotationKaiming He*, Mirosoft Research Asia; Huiwen Chang, Tsinghua University; Jian Sun, "Microsoft Research, China"710Fluttering Pattern Generation using Modified Legendre Sequence for Coded Exposure ImagingHae-Gon Jeon, KAIST; Joon-Young Lee, KAIST; Yudeog Han, KAIST; Seon Joo Kim, Yonsei University; Inso Kweon*, "KAIST, Korea"714Fibonacci Exposure Bracketing for High Dynamic Range ImagingMohit Gupta*, ; Daisuke Iso, Columbia University; Shree Nayar, Columbia University741Target-Driven Moire Pattern Synthesis by Phase ModulationPei-Hen Tsai, National Taiwan University; Yung-Yu Chuang*, National Taiwan University924Deblurring by Example using Dense CorrespondenceYoav HaCohen*, Hebrew University; Eli Shechtman, ; Dani Lischinski,935Accurate Blur Models vs. Image Priors in Super-ResolutionNetalee Efrat*, Weizmann institute; Daniel Glasner, Weizmann Institute; sasha Apartsin, weizmann institute; Boaz Nadler, weizmann institute; Anat Levin, Weizmann Institute, Israel1085Modeling the calibration pipeline of the Lytro camera and its application in high quality light-field image reconstructiondonghyeon Cho*, KAIST; Minhaeng Lee, KAIST; Sunyeong Kim, KAIST; Yu-Wing Tai, "KAIST, Korea"1298DCSH - Matching Patches in RGBD ImagesYaron Eshet, ; Simon Korman*, Tel-Aviv University; Eyal Ofek, Microsoft; Shai Avidan, Tel-Aviv University1360Fast Direct Super-Resolution by Simple FunctionsChih-Yuan Yang*, UC Merced; Ming-Hsuan Yang, "UC Merced, USA"1408Towards Motion-Aware Light Field Video for Dynamic ScenesSalil Tambe, Rice University; Ashok Veeraraghavan*, Rice University; Amit Agrawal, MERL1445Compensating for Motion During Direct-Global SeparationSupreeth Achar*, Carnegie Mellon University; Stephen Nuske, Carnegie Mellon University; Srinivas Narasimhan, Carnegie Mellon University1774Anchored Neighborhood Regression for Fast Example-Based Super-ResolutionRadu Timofte*, KU Leuven; Vincent De Smet, KU Leuven; Luc Van Gool, KU LeuvenDocument analysis150Scene Text Localization and Recognition with Oriented Stroke DetectionLukas Neumann*, ; Jiri Matas, Czech Technical University696Recognizing Text with Perspective Distortion in Natural ScenesTrung Quy Phan*, National University of Singapore; Palaiahnakote Shivakumara, University of Malaya; Shangxuan Tian, National University of Singapore; Chew Lim Tan, National University of Singapore1336Handwritten Word Spotting with Corrected AttributesJon Almazn*, Computer Vision Center; Albert Gordo, INRIA (?); Alicia Forns, Computer Vision Center; Ernest Valveny, Computer Vision CenterFace and gesture93Adapting Classification Cascades to New Domainsvidit Jain*, ; Sachin Farfade,99Rank Minimization across Appearance and Shape for AAM Ensemble FittingXin Cheng*, Queensland U of Tech; Sridharan Sridha, Queenland U of Tech; Jason Saragih, Queenland U of Tech; Simon Lucey,212Exemplar-based Graph Matching for Robust Facial Landmark LocalizationFeng Zhou*, Carnegie Mellon University; Jonathan Brandt, Adobe; Zhe Lin, Adobe Research254Hybrid Deep Learning for Computing Face SimilaritiesYi Sun*, CUHK; Xiaogang Wang, "The Chinese University of Hong Kong, Hongkong"316Multi-Scale Topological Features for Hand Posture Representation and AnalysisKaoning Hu*, SUNY - Binghamton; Lijun Yin, Binghamton University State University of New York403On One-Shot Kernels: explicit feature maps and propertiesStefanos Zafeiriou*, Imperial; Irene Kotsia, Imperial College London/Middlesex University404Learning Slow Features for Behavior AnalysisLazaros Zafeiriou, Imperial College London; Mihalis Nicolaou, Imperial College London; Stefanos Zafeiriou*, Imperial; Symeon Nikitidis, Imperial College London; Maja Pantic, Imperial College520Face Recognition via Random Path Measure Over Face Patch NetworkChaochao Lu*, CUHK; Deli Zhao, The Chinese University of Hong Kong598Learning Identity-Preserving FeaturesZhenyao Zhu*, CUHK; Ping Luo, CUHK601Face Recognition via Ranking over An Archetype HullYuanjun Xiong*, The Chinese University of Hong Kong; Wei Liu, Columbia University; Deli Zhao, The Chinese University of Hong Kong660Cascaded Shape Space Pruning for Robust Facial Landmark DetectionXiaowei Zhao*, ICT,CAS; Shiguang Shan, "Chinese Academy of Sciences, China"; Xiujuan Chai, jdl; Xilin Chen,695Like Father, Like Son: Facial Expression Dynamics for Kinship VerificationHamdi Dibeklioglu*, University of Amsterdam; Albert Salah, Bogazici University; Theo Gevers, University of Amsterdam705Sieving Regression Forest Votes for Facial Feature Detection in the WildHeng Yang*, Queen Mary Uni. of London ; Ioannis Patras,712Facial Action Unit Event Detection by Cascade of TasksXiaoyu Ding*, Carnegie Mellon University; Wen-Sheng Chu, Carnegie Mellon University; Fernando de la Torre, Carnegie Mellon University ; Jeffrey Cohn, ; Qiao Wang, Southeast University716Fast Face Detector Training Using Tailored ViewsKristina Scherbaum*, MMCI; Rogerio Feris, ; James Petterson, ; Volker Blanz , University of Siegen; Hans-Peter Seidel, MPI Saarland736Coupling Alignments with Recognition for Still-to-Video Face RecognitionZhiwu Huang*, ICT, CAS; Xiaowei Zhao, ICT,CAS; Shiguang Shan, "Chinese Academy of Sciences, China"; Ruiping Wang, Institute of Computing Technology, Chinese Academy of Sciences; Xilin Chen,757A Cascaded Deep Learning Architecture for Pedestrian DetectionXingyu ZENG*, The Chinese University of HK; Wanli Ouyang, The Chinese University of HK; Xiaogang Wang, "The Chinese University of Hong Kong, Hongkong"916Optimization problems for fast AAM fitting in-the-wildGeorgios Tzimiropoulos*, University of Lincoln/Imperial College London; Maja Pantic, Imperial College932Two-Point Gait: Decoupling Gait from Body ShapeStephen Lombardi*, Drexel Unversity; Ko Nishino, "Drexel University, USA"; Yasushi Makihara, Osaka university; Yasushi Yagi,963Handling Occlusions with Franken-classifiersMarkus Mathias*, KU Leuven; Rodrigo Benenson, MPI-Inf; Radu Timofte, KU Leuven; Luc Van Gool, KU Leuven972Pose-free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape ModelXiang Yu*, Rutgers University; Junzhou Huang, University of Texas at Arlington; Shaoting Zhang, Rutgers University; Wang Yan, Rutgers University; Dimitris Metaxas, Rutgers University1040Similarity Metric Learning for Face RecognitionQiong Cao, University of Exeter; Yiming Ying*, University of Exeter; Peng Li, University of Bristol1071Simultaneous Clustering and Tracklet Linking for Multi-Face Tracking in VideosBaoyuan Wu*, CASIA & RPI; Siwei Lyu, SUNY Albany; Baogang Hu, CASIA; Qiang Ji,1074Capturing Global Semantic Relationships for Facial Action Unit RecognitionZiheng Wang*, RPI; Yongqiang Li, Harbin Institute of Technology; SHANGFEI WANG, USTC; Qiang Ji,1075Unsupervised Random Forest Manifold Alignment for LipreadingYuru PEI*, Peking University; Tae-Kyun Kim, ; Hongbin Zha, "Peking University, China"1133Robust Feature Set Matching for Partial Face RecognitionRENLIANG WENG*, Nanyang Technological Universi; Jiwen Lu, Advanced Digital Sciences Center, Singapore; Junlin Hu, NTU; Gao Yang, Nanyang Technological University; Yap-Peng Tan,1178Learning People Detectors for Tracking in Crowded ScenesSiyu Tang*, Max planck institute ; Mykhaylo Andriluka, Max Planck Institute for Informatics; Anton Milan, TU Darmstadt; Konrad Schindler, ETH Zurich; Stefan Roth, "TU Darmstadt, Germany"; Bernt Schiele, "MPI Informatics, Germany"1239Robust face landmark estimation under occlusionXavier Burgos Artizzu*, Caltech; Pietro Perona, "Caltech, USA"; Piotr Dollar,1252Markov Network-based Unified Classifier for Face IdentificationWonjun Hwang*, Samsung AIT; Kyungshik Roh, ; Junmo Kim, KAIST1377Random Faces Guided Sparse Many-to-One Encoder for Pose-Invariant Face RecognitionYizhe Zhang*, ; Ming Shao, Northeastern University; Edward Wong, Polytechnic Institute of NYU; Yun Fu, Northeastern University1487A Deep Sum-Product Architecture for Robust Facial Attributes AnalysisPing Luo*, CUHK1489Estimating Human Pose with Flowing PuppetsSilvia Zuffi*, ; Javier Romero, MPI PS; Cordelia Schmid, "INRIA, France"; Michael Black, "Max Planck Institute for Intelligent Systems, Germany"1563Calibration-free Gaze Estimation using Human Gaze PatternsFares Alnajar*, University of Amsterdam; Theo Gevers, University of Amsterdam; Roberto Valenti, ; Sennay Ghebreab, University of Amsterdam1579Cross-view Action Recognition over Heterogeneous Feature SpacesXinxiao Wu*, ; Han Wang, Beijing Insititute of technolo; Cuiwei Liu, ; Yunde Jia,1624Efficient pedestrian detection by directly optimizing the partial area under the ROC curveSakrapee Paisitkriangkrai*, The University of Adelaide; Chunhua Shen, The University of Adelaide; Anton Van den Hengel, University of Adelaide1728Fingerspelling recognition with semi-Markov conditional random fieldsTaehwan Kim, TTIC; Gregory Shakhnarovich, TTIC; Karen Livescu*, TTIC1804Supervised and Unsupervised Within Class Covariance Normalization for Efficient Face RecognitionOren Barkan*, Tel Aviv University; Jonathan Weill, Tel Aviv University; Lior Wolf, "Tel Aviv University, Israel"; Hagai Aronowitz, IBM Research; Amir Averbuch, Tel Aviv University1839Breaking the chain: liberation from the temporal Markov assumption for tracking human posesryan Tokola*, ; Wongun Choi, University of Michigan; Silvio Savarese, "University of Michigan, USA"1930Hidden Factor Analysis for Age Invariant Face RecognitionDihong GONG, SIAT; Zhifeng LI*, SIAT; Dahua Lin, TTIC; Jianzhuang Liu, CUHK; Xiaoou Tang, Chinese University of Hong KongLow-level vision and image processing185Partial Sum Minimization of Singular Values in RPCA for Low-Level VisionTae-Hyun Oh, KAIST; Hyeongwoo Kim, KAIST; Yu-Wing Tai, "KAIST, Korea"; Jean-Charles Bazin, ETH-Z; In So Kweon*, KAIST205Efficient Image Dehazing with Boundary Constraint and Contextual RegularizationGaofeng MENG*, Chinese Academy of Sciences; Ying WANG, ; Jiangyong DUAN, ; Shiming Xiang, NLPR, CASIA; Chunhong Pan, NLPR, CASIA233Example-based Facade Texture SynthesisDengxin Dai*, CVL, ETH Zurich; Hayko Riemenschneider, CVL, ETH Zurich; Luc Van Gool, ETH; gerhard Schmitt, ETH Zurich266Efficient Salient Region Detection with Soft Image AbstractionMing-Ming Cheng*, Oxford Brookes University; Shuai Zheng, Oxford Brookes University; Jonathan Warrell, Oxford Brookes University; Vibhav Vineet, Oxford Brookes University; Wenyan Lin, Oxford Brookes University292A Generalized Low-Rank Appearance Model for Spatio-Temporally Correlated Rain StreaksYi-Lei Chen*, NTHU, Taiwan; Chiou-Ting Hsu, NTHU, Taiwan320Exploiting Reflection Change for Automatic Reflection RemovalYu Li*, NUS; Michael Brown, National University of Singapore328A Learning-Based Approach to Reduce JPEG Artifacts in Image MattingInchang Choi, ; Sunyeong Kim, KAIST; Michael Brown, National University of Singapore; Yu-Wing Tai*, "KAIST, Korea"340Illuminant Chromaticity from Image SequencesVeronique Prinet*, Hebrew University of Jerusalem; Dani Lischinski, ; Michael Werman,537Saliency Detection: A Boolean Map ApproachJianming Zhang*, Boston University; Stan Sclaroff, Boston University546From Where and How to What We SeeKarthikeyan Shanmuga Vadivel*, UCSB; Vignesh Jagadeesh, UCSB; Renuka Shenoy, UCSB; Miguel Eckstein, UCSB; B.S. Manjunath, UCSB661Single-patch low-rank prior for non-pointwise impulse noise removalRuixuan Wang*, University of Dundee; Emanuele Trucco, University of Dundee664Cross-Field Joint Image Restoration via Scale MapQiong Yan*, CUHK; Xiaoyong Shen, CUHK; Li Xu, CUHK; Shaojie Zhuo, qualcomm.com; Xiaopeng Zhang, ; Liang Shen, ; Jiaya Jia, Chinese University of Hong Kong840Salient Region Detection by UFO: Uniqueness, Focusness and ObjectnessPeng Jiang*, Shandong University; Jingliang Peng, cs.sdu.edu.cn; Haibin Ling,849Shape Index Descriptors Applied to Texture-Based Galaxy AnalysisKim Pedersen*, diku.dk; Kristoffer Stensbo-Smidt, DIKU; Andrew Zirm, NBI KU; Christian Igel, DIKU1101A New Image Quality Metric for Image Auto-DenoisingXiangfei Kong*, City University of Hong Kong; Kuan Li, NUDT; Qingxiong Yang, City University of Hong Kong; Ming-Hsuan Yang, "UC Merced, USA"; Liu Wenyin, Shanghai University of Electronic Power1186Contextual Hypergraph Modeling for Salient Object DetectionXi Li*, University of Adelaide; Yao Li, University of Adelaide; Chunhua Shen, The University of Adelaide; Anthony Dick, University of Adelaide ; Anton Van den Hengel, University of Adelaide1322EVSAC: Accelerating Hypotheses Generation by Modeling Matching Scores with Extreme Value TheoryVictor Fragoso*, UCSB; Pradeep Sen, UCSB; Sergio Rodriguez, UCSB; Matthew Turk, "UC Santa Barbara, USA"1342Restoring An Image Taken Through a Window Covered with Dirt or RainDavid Eigen*, Courant Institute, NYU; Dilip Krishnan, NYU; Rob Fergus, New York University1525SGTD: Structure Gradient and Texture Decorrelating Regularization for Image DecompositionQiegen Liu, ; Jianbo Liu, ; Pei Dong, ; Dong Liang*, Shenzhen Institutes of Advance1614A Joint Intensity and Depth Co-Sparse Analysis Model for Depth Map Super-ResolutionMartin Kiechle*, Technische Universitt Mnchen; Simon Hawe, Technische Universitt Mnchen; Martin Kleinsteuber, Technische Universitt Mnchen1719Estimating the Material Properties of Fabric Through Observation of MotionKatherine Bouman*, Massachusetts Institute of Tec; Bill Freeman, "MIT, USA"; Bei Xiao, ; Peter Battaglia, ; Wojciech Matusik, ; John Fisher, MIT1767Robust Tucker Tensor Decomposition for Efficient Image StorageMiao Zhang*, University of Texas at Arlingt; Chris Ding,1787Joint Noise Level Estimation from Personal Photo CollectionsYiChang Shih*, M.I.T.; Vivek Kwatra, ; Sergey Ioffe, ; Hui Fang, ; Troy Chinen,1898Super-resolution via Transform-invariant Group-sparse RegularizationCarlos Fernandez-Granda*, Stanford UniversityMedical and biological image analysis1215Tissue Classification via Unsupervised Feature Learning and Spatial Pyramid MatchingHang Chang*, Lawrence Berkeley National Lab; Nandita Nayak, ; Paul Spellman, ; Bahram Parvin,1317Uncertainty-driven Efficiently-Sampled Sparse Graphical Models for Concurrent Tumor Segmentation and Atlas RegistrationSarah Parisot*, Ecole Centrale Paris; William Wells, Surgical Planning Laboratory, Harvard Medical School; Stphane Chemouny, Intrasense SA; Hugues Duffau, Hpital Gui de Chauliac; Nikos Paragios, Ecole Centrale de Paris1550Drosophila Embryo Stage Annotation using Label PropagationTomas Kazmar*, IMP/ISTA; Evgeny Kvon, IMP; Alexander Stark, IMP; Christoph Lampert, Institute of Science and Technology Austria1893Detecting Irregular Curvilinear Structures in Gray Scale and Color Imagery using Multi-Directional Oriented FluxEngin Turetken*, EPFL; Carlos Becker, EPFL; Przemyslaw Glowacki, EPFL; fethallah Benmansour, ; Pascal Fua, "EPFL, Switzerland"Motion and tracking260Higher Order Matching for Consistent Multiple Target TrackingChetan Arora*, ; Amir Globerson,261Tracking via Robust Multi-Task Multi-View Joint Sparse RepresentationZhibin Hong*, University of Technology, Sydney; Xue Mei, Future Mobility Research department, Toyota Research Institute, North America; Danil Prokhorov, TTC; Dacheng Tao, University of Technology, Sydney263Measuring Flow Complexity in VideosSaad Ali*,282STAR3D: Simultaneous Tracking And Reconstruction of 3D Objects Using RGB-D DataYuheng(Carl) Ren*, Oxford University; Victor Prisacariu, Oxford ; David Murray, Oxford ; Ian Reid, University of Adelaide286Multiple Non-Rigid Surface Detection and RegistrationYi Wu*, UC Merced; Yoshihisa Ijiri, OMRON; Ming-Hsuan Yang, "UC Merced, USA"335Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth DataSrinath Sridhar*, Max-Planck-Institut Informatik; Antti Oulasvirta, Max-Planck-Institut Informatik; Christian Theobalt, MPI fuer Informatik336Latent Data Association: Bayesian Model Selection for Multitarget TrackingAleksandr Segal*, Oxford University Robotics Lab; Ian Reid, University of Adelaide423Optical Flow via Locally Adaptive Fusion of Complementary Data CostsTae Hyun Kim, Seoul National Univ.; Heeseok Lee, Seoul National University; Kyoung Mu Lee*, Seoul National University506Image Matching: a General Framework Combining Direct and Feature-based CostsJim Braux-Zin*, CEA, LIST; Adrien Bartoli, Universit?d'Auvergne; Romain Dupont, CEA, LIST516Online Robust Non-negative Dictionary Learning for Visual TrackingNaiyan Wang*, HKUST; Jingdong Wang, Microsoft Research Asia; Dit-Yan Yeung, HKUST651Real-time Body Tracking with One Depth Camera and Inertial SensorsThomas Helten*, MPI Informatik; Meinard Mller, International Audio Laboratories Erlangen; Hans-Peter Seidel, MPI Informatik; Christian Theobalt, MPI fuer Informatik655Discriminant Tracking Using Tensor Representation with Semi-supervised ImprovementJin Gao*, Institute of Automation Chinese Academy of Sciences; Weiming Hu, Institute of Automation Chinese Academy of Sciences; Junliang Xing, Institute of Automation, Chinese Academy of Sciences718Discriminative Label Propagation for Multi-object Tracking with Sporadic Appearance FeaturesAmit K.C.*, Universit catholique de Louva; Christophe De Vleeschouwer, UCL742Video Motion for Every Visible PointSusanna Ricco*, Duke University; Carlo Tomasi, Duke University825Initialization-Insensitive Visual Tracking Through Voting with Salient Local FeaturesKwang Yi*, Seoul National University; Hawook Jeong, Seoul National University; Byeongho Heo, Seoul National University; Hyung Jin Chang, Imperial College London; Jin Young Choi, Seoul National University832Optimal Orthogonal Basis and Image Assimilation: Motion ModelingIsabelle Herlin*, ; Etienne Huot, Inria; Giuseppe Papari, Lithicon921Revisiting Example Dependent Cost-Sensitive Learning with Decision TreesOisin Mac Aodha*, UCL; Gabriel Brostow,1007Robust Object Tracking with Online Multi-lifespan Dictionary LearningJunliang Xing*, Institute of Automation, Chinese Academy of Sciences; Jin Gao, Institute of Automation Chinese Academy of Sciences; Bing Li, NLPR, CASIA; Weiming Hu, Institute of Automation Chinese Academy of Sciences; Shuicheng Yan, "NUS, Singapore"1017Constructing Adaptive Complex Cells for Robust Visual TrackingDapeng Chen*, Xi'an Jiaotong University; Zejian Yuan, Xi'an jiaotong University; Yang Wu, Kyoto University; Geng Zhang, Xi'an Jiaotong University; Nanning Zheng, Xi'an Jiaotong University1041Coherent motion segmentation in moving camera videos using optical flow orientationsManjunath Narayana*, ; Erik Learned-Miller, University of Massachusetts at Amherst; Allen Hanson, University of Massachusetts Amherst1153Online Motion Segmentation using Dynamic Label PropagationAli Elqursh*, Rutgers University; Ahmed Elgammal,1159Topology-Constrained Layered Tracking with Latent FlowJason Chang*, CSAIL, MIT; John Fisher, MIT1160Pose-Configurable Generic Tracking of Elongated ObjectsDaniel Wesierski*, University; Patrick Horain,1278A Generic Deformation Model for Dense Non-Rigid Surface Registration: a Higher-Order MRF-based ApproachYun Zeng*, Harvard; Chaohui Wang, MPI ; David Gu, ; Dimitris Samaras, Stony Brook Univ.; Nikos Paragios, Ecole Centrale de Paris1345Modeling Self-Occlusions in Dynamic Shape and Appearance TrackingYanchao Yang, KAUST; Ganesh Sundaramoorthi*, KAUST1356Randomized Ensemble TrackingQinxun Bai*, Boston University; Zheng Wu, ; Stan Sclaroff, Boston University; Margrit Betke, Boston University; Camille Monnier,1400Camera Alignment using Trajectory Intersections in Unsynchronized VideosThomas Kuo*, UC Santa Barbara; Santhoshkumar Sunderrajan, UCSB; B.S. Manjunath, UCSB1690Minimal Basis Facility Location for Subspace SegmentationChoon Meng Lee*, NUS; Loong-Fah Cheong, NUS1718A Unified Rolling Shutter and Motion Blur Model for Dense 3D Visual TrackingMaxime Meilland*, I3S-CNRS-UNS; Andrew Comport, CNRS-I3S/UNS; Tom Drummond, Monash University1769PixelTrack: a fast adaptive algorithm for tracking non-rigid objectsStefan Duffner*, LIRIS, INSA de Lyon; Christophe Garcia, LIRIS, INSA de Lyon1826Conservation TrackingMartin Schiegg*, University of Heidelberg, HCI; Philipp Hanslovsky, Universitt Heidelberg, HCI; Bernhard Kausler, University of Heidelberg, HCI; Lars Hufnagel, EMBL, Heidelberg; Fred Hamprecht, HCI, University of Heidelberg1951Bayesian 3D tracking from monocular videoErnesto Brau*, ; Kobus Barnard, "University of Arizona, USA"; Jinyan Guan, University of Arizona; Kyle Simek, University of Arizona; Luca del Pero, ; Colin Dawson, University of ArizonaOptimization methods61A Convex Optimization Framework for Active LearningEhsan Elhamifar*, UC Berkeley; Guillermo Sapiro, Duke ; Shankar Sastry, UC Berkeley83Affine Constraint Group Sparse CodingYu-Tseh Chi*, University of Florida; Mohsen Ali, ; Muhammad Rushdi, ; Jeffrey Ho, University of Florida119Slice Sampling Particle Belief PropagationOliver Mller*, Leibniz Universitt Hannover; Michael Ying Yang, tnt.uni-hannover.de; Bodo Rosenhahn,141Non-Convex P-norm Projection for Robust SparsityMithun Das Gupta*, Ricoh Innovations Pvt. Ltd.; Sanjeev Kumar, Qualcomm232Shortest Paths with Curvature and TorsionPetter Strandmark*, Lund Univeristy; Johannes Uln, Lund University; Fredrik Kahl, Lund University242Unifying Nuclear Norm and Bilinear Factorization Approaches for Low-rank Matrix DecompositionRicardo Cabral*, Carnegie Mellon University; Fernando de la Torre, Carnegie Mellon University ; Joao Costeira, Instituto de Sistemas e Robotica; Alexandre Bernardino, Instituto de Sistemas e Robotica333Curvature Regularization using Partial EnumerationCarl Olsson*, ; Johannes Uln, Lund University; Yuri Boykov, "University of Western Ontario, Canada"; Vladimir Kolmogorov, "IST, Austria"342GOSUS: Grassmannian Online Subspace Updates with Structured-sparsityJia Xu*, UW-Madison; Vamsi Ithapu, ; Lopamudra Mukherjee, University of Wisc Whitewater; James Rehg, Georgia Institute of Technology ; Vikas Singh,369A Generalized Iterated Shrinkage Algorithm for Non-convex Sparse CodingWangmeng Zuo, Harbin Institute of Technology; Deyu Meng, Xi'an Jiaotong University; Lei Zhang*, The Hong Kong Polytechnic University; Xiangchu Feng, School of Science, Xidian University; David Zhang, The Hong Kong Polytechnic University466Sparse Variation Dictionary Learning for Face Recognition with A Single Training Sample Per PersonMeng YANG*, ETH Zuricn; Luc Van Gool, ETH; Lei Zhang, The Hong Kong Polytechnic University524Multi-Attributed Dictionary Learning for Sparse CodingChen-Kuo Chiang*, National Tsing Hua University; Te-Feng Su, ; Yen Chih, ; Shang-Hong Lai, NTHU1019Log-Euclidean Kernels for Sparse Representation and Dictionary LearningPeihua Li*, Dalian University of Technolog; Qilong Wang, ; Wangmeng Zuo, Harbin Institute of Technology; Lei Zhang, The Hong Kong Polytechnic University1179Bounded Labeling Function for Global Segmentation of Multi-Part Objects with Geometric ConstraintsMasoud S. Nosrati*, Simon Fraser University; Shawn Andrews, SFU; Ghassan Hamarneh, SFU1245Coupled Dictionary and Feature Space Learning with Applications to Cross-Domain Image Synthesis and RecognitionDe-An Huang, Academia Sinica; Yu-Chiang Frank Wang*, Academia Sinica1335Total Variation Regularization for Functions with Values in a ManifoldJan Lellmann*, University of Cambridge; Evgeny Strekalovskiy, TU Munich; Sabrina Koetter, TU Munich; Daniel Cremers, Technische Universitt Mnchen1486Fast online orthogonal dictionary learning and image restorationChenglong Bao, nus.edu.sg; Jianfeng Cai, uiowa.edu; Hui Ji*, "NUS, Singapore"1616Latent Space Sparse Subspace ClusteringVishal Patel*, UMIACS; Hien Nguyen , UMIACS; Rene Vidal, Johns Hopkins University1641On the Mean Curvature Flow on Graphs with Applications in Image and Manifold ProcessingEl chakik Abdallah*, Greyc Laboratory; abderrahim ELmoataz, ; ahcen Sadi,1779Semi-Supervised Robust Dictionary Learning via Efficient L2,0+-Norms MinimizationHua Wang*, Colorado School of Mines; Feiping Nie, University of Texas at Arlington; Heng Huang, UTA1825Large-scale Image Annotation by Efficient and Robust Kernel Metric LearningZheyun Feng*, Michigan State University; Rong Jin, Michigan State University; Anil Jain, Michigan State UniversityPerformance evaluation78Tracking Revisited using RGBD Camera: Benchmark and BaselinesShuran Song, HKUST; Jianxiong Xiao*, MIT767Perceptual Fidelity Aware Mean Squared ErrorWufeng Xue, Xi'an Jiaotong University; Xuanqin Mou*, Xi'an Jiaotong University; Lei Zhang, The Hong Kong Polytechnic University; Xiangchu Feng, School of Science, Xidian University1620Saliency and Human Fixations: State-of-the-art and Study of Comparison MetricsNicolas Riche*, UMONS; Matthieu Duvinage, UMONS; Matei Mancas, UMONS; Bernard Gosselin, UMONS; Thierry Dutoit, UMONSPhysics-based vision and Shape-from-X42A Simple Model for Intrinsic Image Decomposition with Depth CuesQifeng Chen, ; Vladlen Koltun*, Stanford University188Real-World Normal Map Capture for Nearly Flat Reflective SurfacesBastien Jacquet*, ETH Zurich; Christian Hne, ETH Zrich; Kevin Koeser, ; Marc Pollefeys, ETH223Multiview Photometric Stereo using Planar Mesh ParameterizationJaesik Park, KAIST; Sudipta Sinha, ; Yasuyuki Matsushita, Microsoft Research Asia; Yu-Wing Tai, "KAIST, Korea"; In So Kweon*, KAIST230High Quality Shape from a single RGB-D Image under Uncalibrated Natural IlluminationYudeog Han*, KAIST; Joon-Young Lee, KAIST; Inso Kweon, "KAIST, Korea"231Depth from Combining Defocus and Correspondence Using Light-Field CamerasMichael Tao*, ; Sunil Hadap, Adobe Inc.; Jitendra Malik, UC Berkeley; Ravi Ramamoorthi, U.C. Berkeley885Multi-View Normal Field Integration for 3D Reconstruction of Mirroring ObjectsMichael Weinmann*, University of Bonn; Aljosa Osep, University of Bonn; Roland Ruiters, University of Bonn; Reinhard Klein, University of Bonn1539Matching Dry to Wet MaterialsYaser Yacoob*, Univ of MarylandRecognition: detection, categorization, classification, indexing, matching24Quadruplet-wise Image Similarity LearningMarc Law*, LIP6; Nicolas Thome, LIP6; Matthieu Cord,37Human Attribute Recognition By Rich Appearance DictionaryJungseock Joo*, UCLA; Shuo Wang, ; Song Chun Zhu, UCLA69Elastic Net Constraints for Shape MatchingEmanuele Rodola*, The University of Tokyo; Andrea Torsello, ; Tatsuya Harada, University of Tokyo; Yasuo Kuniyoshi, The University of Tokyo77Semantic RGB-D Bundle Adjustment with Human in the LoopJianxiong Xiao*, MIT; Andrew Owens, MIT; Antonio Torralba, MIT85Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable ApproachReyes Rios-Cabrera*, KULeuven; Tinne Tuytelaars, KU Leuven89Discovering Object FunctionalityBangpeng Yao*, Stanford University; Jiayuan Ma, ; Fei-Fei Li, Stanford University96Unsupervised Visual Domain Adaptation Using Subspace AlignmentBasura Fernando*, KU Leuven; Amaury Habrard, University Jean Monnet of Saint-Etienne; Marc Sebban, University of Jean Monnet in Saint-Etienne, Hubert Curien Laboratory; Tinne Tuytelaars, KU Leuven97Data-Driven 3D Primitives for Single Image UnderstandingDavid Fouhey*, Carnegie Mellon University; Abhinav Gupta, ; Martial Hebert, "CMU, USA"110Complementary Projection HashingZhongming Jin*, Zhejiang University; Deng Cai, ; Yao Hu, Zhejiang university; Debing Zhang, Zhejiang university; Xuelong Li,127Deformable Part Descriptors for Fine-grained Recognition and Attribute PredictionNing Zhang*, EECS, UC Berkeley; Ryan Farrell, ICSI, UC Berkeley; Trevor Darrell,145No Matter Where You Are: Flexible Graph-guided Multi-task Learning for Multi-view Head Pose Classification Under Target MotionYan Yan*, University of Trento; Elisa Ricci, University of Perugia; Ramanathan Subramanian, Advanced Digital Sciences Center in Singapore; Oswald Lanz, FBK Fondazione Bruno Kessler; nicu Sebe, University of Trento158The Interestingness of ImagesMichael Gygli*, ETH Zurich; Helmut Grabner, ; Hayko Riemenschneider, CVL, ETH Zurich; Luc Van Gool, ETH170Joint Deep Learning for Pedestrian DetectionWanli Ouyang*, The Chinese University of HK; Xiaogang Wang, "The Chinese University of Hong Kong, Hongkong"190Bird Part Localization Using Exemplar-Based Models with Enforced Pose and Subcategory ConsistencyJiongxin Liu*, COLUMBIA UNIVERSITY; Peter Belhumeur, "Columbia University, USA"196Segmentation Driven Object Detection with Fisher VectorsRamazan Gokberk CINBIS*, INRIA Grenoble; Jakob Verbeek, "INRIA, France"; Cordelia Schmid, "INRIA, France"206Learning Discriminative Part Detectors for Image Classification and CosegmentationJian Sun*, Xi'an Jiaotong University; Jean Ponce, "ENS, France"224Find the Best Path: an Efcient and Accurate Classier for Image HierarchiesMin Sun*, ; Wan Huang, University of Michigan at Ann Arbor; Silvio Savarese, University of Michigan at Ann Arbor245Handling Uncertain Tags in Visual RecognitionArash Vahdat*, Simon Fraser University; Greg Mori, Simon Fraser University246Compositional Models for Video Event Detection: A Multiple Kernel Learning Latent Variable ApproachArash Vahdat*, Simon Fraser University; Kevin Cannons, Simon Fraser University; Greg Mori, Simon Fraser University ; Sangmin Oh, Kitware Inc.; Ilseo Kim,253Hierarchical Part Matching for Fine-Grained Visual CategorizationLingxi Xie*, Tsinghua University; Qi Tian, University of Texas at San Antonio; Shuicheng Yan, "NUS, Singapore"; Bo Zhang, Tsinghua University268Detecting avocados to zucchinis: what have we done, and where are we going?Olga Russakovsky*, ; Jia Deng, Stanford University; Zhiheng Huang, Stanford University; Alexander Berg, Stony Brook University; Fei-Fei Li, Stanford University291Person Re-identification by Salience MatchingRui Zhao*, CUHK; Wanli Ouyang, The Chinese University of HK; Xiaogang Wang, "The Chinese University of Hong Kong, Hongkong"294Saliency Detection via Dense and Sparse ReconstructionXiaohui Li*, DUT, China; huchuan Lu, DUT,China; Ming-Hsuan Yang, "UC Merced, USA"; Lihe Zhang, DUT, China; Xiang Ruan,295A Deformable Mixture Parsing Model with ParseletsJian Dong*, NUS; Qiang Chen, ; Wei Xia, NUS; Zhongyang Huang, ; Shuicheng Yan, "NUS, Singapore"310Detecting Dynamic Objects with Multi-View Background SubtractionRal Daz, University of California, Irvine; Sam Hallman, University of California, Irvine; Charless Fowlkes*, University of California, Irvine338Implied Feedback: Learning Nuances of User Behavior in Image SearchDevi Parikh*, Virginia Tech; Kristen Grauman, University of Texas at Austin343A Data Set and a Stopwatch Hidden Markov Model for Event Recognition in Photo CollectionsLukas Bossard*, ETH Zurich; Matthieu Guillaumin, ETH Zurich; Luc Van Gool, ETH350Joint optimization for consistent multiple graph matchingJunchi Yan*, Shanghai Jiao Tong University; Yu Tian, Shanghai Jiao Tong University; Hongyuan Zha, Georgia Tech; Xiaokang Yang, ; Ya Zhang, Shanghai Jiao Tong University376Ensemble Projections for Semi-supervised Image ClassificationDengxin Dai*, CVL, ETH Zurich; Luc Van Gool, ETH379Prime Object Proposals with Randomized Prim's AlgorithmSantiago Manen*, BIWI ETH Zurich; Hayko Riemenschneider, CVL, ETH Zurich; Matthieu Guillaumin, ETH Zurich; Luc Van Gool, ETH381Bayesian Joint Topic Modelling for Weakly Supervised Object LocalisationZhiyuan Shi*, Queen Mary Univ.of London; Timothy Hospedales, EECS, QMUL; Tao Xiang, EECS,QMUL411Joint Inverted IndexingYan Xia*, USTC; Kaiming He, Mirosoft Research Asia; Fang Wen, ; Jian Sun, "Microsoft Research, China"426Low-Rank Sparse Coding for Image ClassificationTianzhu Zhang*, ADSC of UIUC in Singapore; Bernard Ghanem, KAUST; Si Liu, National University of Singapore; Changsheng Xu, CASIA; Narendra Ahuja,533Learning Near-Optimal Cost-Sensitive Decision Policy for Object DetectionTianfu Wu*, UCLA; Song Chun Zhu, UCLA539Nested Shape DescriptorsJeffrey Byrne*, University of Pennsylvania540Unbiased Metric Learning: Utilize Biased Datasets and Web ImagesChen Fang*, Dartmouth College; Ye Xu, Dartmouth College; Daniel Rockmore, Dartmouth College542Latent Task Adaptation with Large-scale HierarchiesYangqing Jia*, UC Berkeley; Trevor Darrell,545Mining Multiple Queries for Image Retrieval: On-the-fly learning of an Object-specific Mid-level RepresentationBasura Fernando*, KU Leuven; Tinne Tuytelaars, KU Leuven549Parsing IKEA Objects: Fine Pose EstimationJoseph Lim*, MIT; Hamed Pirsiavash, MIT; Antonio Torralba, MIT566Improving Graph Matching via Density MaximizationChao Wang*, University of Wollongong ; Lei Wang, University of Wollongong607Allocentric Pose EstimationJos Oramas*, KULeuven - ESAT; Luc De Raedt, KUleuven - CS; Tinne Tuytelaars, KU Leuven614NYC3DCars: A Dataset of 3D Vehicles in Geographic ContextKevin Matzen*, Cornell University; Noah Snavely, "Cornell, USA"624Collaborative Active Learning of a Kernel Machine Ensemble for RecognitionGang Hua*, Stevens Institute of Technology; Chengjiang Long, Stevens Institute of Technology; Ming Yang, NEC Labs America; Yan Gao, Northwestern University632Saliency Detection via Absorbing Markov ChainBowen Jiang*, DUT; Lihe Zhang, DUT, China; huchuan Lu, DUT,China; Ming-Hsuan Yang, "UC Merced, USA"; Chuan Yang,683Learning Coupled Feature Spaces for Cross-modal MatchingKaiye Wang*, NLPR; Ran He, NLPR, CASIA; Wei Wang, NLPR; Liang Wang, unknown; Tieniu Tan, "NLPR, China"690A General Two-step Approach to Learning-Based HashingGuosheng Lin*, The University of Adelaide; Chunhua Shen, The University of Adelaide; Anton Van den Hengel, University of Adelaide ; David Suter,692Active Visual Recognition with Expertise Estimation in CrowdsourcingChengjiang Long, Stevens Institute of Technology; Gang Hua*, Stevens Institute of Technology; Ashish Kapoor, Microsoft Research719Attribute Adaptation for Personalized Image SearchAdriana Kovashka*, ; Kristen Grauman, University of Texas at Austin723Attribute Pivots for Guiding Relevance Feedback in Image SearchAdriana Kovashka*, ; Kristen Grauman, University of Texas at Austin729Unsupervised Domain Adaptation by Domain Invariant ProjectionMahsa Baktashmotlagh*, University of Queensland; Mehrtash Harandi, NICTA; Brian Lovell, ; Mathieu Salzmann, NICTA759Look Into Sparse Representation-based Classification: A Margin-based PerspectiveZhaowen Wang*, UIUC; Jianchao Yang, Adobe Systems Inc.; Nasser Nasrabadi, US Army Research Lab; Thomas Huang, University of Illinois at Urbana-Champaign770Semantic-aware Co-indexing for Near-duplicate Image RetrievalShiliang Zhang, UTSA; Ming Yang*, NEC Labs America; Xiaoyu Wang, NEC Labs America; Yuanqing Lin, ; Qi Tian, University of Texas at San Antonio780CoDeL: An Efficient Human Co-detection and Labeling FrameworkJianping Shi*, CUHK ; Renjie Liao, CUHK; Jiaya Jia, Chinese University of Hong Kong781Modeling Occlusion by Discriminative AND-OR StructuresBo Li*, Beijing Institute of Tech.; Wenze Hu, ; Tianfu Wu, UCLA; Song Chun Zhu, UCLA782A Scalable Unsupervised Feature Merging Approach to Efficient Dimensionality Reduction of High-dimensional Visual DataLingqiao Liu*, Australian National University; Lei Wang, University of Wollongong784Feature Weighting via Optimal Thresholding for Video AnalysisZhongwen Xu*, Zhejiang University; Yi Yang, cmu.edu; Ivor Tsang, ; nicu Sebe, University of Trento; Alexander Hauptmann, Carnegie Mellon University847Decomposing Bag of Words HistogramsAnkit Gandhi*, IIIT Hyderabad; Karteek Alahari, ENS-Willow; c. v. Jawahar, IIIT Hyderabad869SIFTpack: a compact representation for efficient SIFT matchingAlexandra Gilinsky*, Technion; Lihi Zelnik-Manor, "Technion, Israel"880Attribute Dominance: What Pops Out?Naman Turakhia, ; Devi Parikh*, Virginia Tech907Learning the Visual Interpretation of SentencesLarry Zitnick*, "Microsoft Research, USA"; Devi Parikh, Virginia Tech; Lucy Vanderwende, Microsoft Research910How Related Exemplars Help Complex Event Detection in Web Videos?Yi Yang*, cmu.edu; Zhigang Ma, The University of Trento; Zhongwen Xu, Carnegie Mellon University; Shuicheng Yan, "NUS, Singapore"; Alexander Hauptmann, Carnegie Mellon University915An Adaptive Descriptor Design for Object Recognition in the WildZhenyu Guo*, University of British Columbia; Z.Jane Wang, University of British Columbia949Training deformable part models with decorrelated featuresRoss Girshick*, UC Berkeley; Jitendra Malik, UC Berkeley950Volumetric Semantic Segmentation using Pyramid Context FeaturesJonathan Barron*, UC Berkeley; Pablo Arbelaez, ; Soile Keranen, LBL; David Knowles, LBL; Mark Biggin, LBL; Jitendra Malik, UC Berkeley973SYM-FISH: A Symmetry-aware Flip Invariant Sketch Histogram Shape DescriptorXiaochun Cao, Chinese Academy of Sciences; Hua Zhang*, Tju; Si Liu, National University of Singapore; Xiaojie Guo, Tianjin University978PhotoOCR: Reading Text in Uncontrolled ConditionsMark Cummins*, Google; Alessandro Bissacco, Google Inc.; Yuval Netzer, Google; Hartmut Neven, Google1000Neighbor-To-Neighbor Search for Fast Coding of Feature VectorsNakamasa Inoue*, Tokyo Institute of Technology; Koichi Shinoda, Tokyo Institute of Technology1018A Novel Earth Mover's Distance Methodology for Image Matching with Gaussian Mixture ModelsPeihua Li*, Dalian University of Technolog; Qilong Wang, ; Lei Zhang, The Hong Kong Polytechnic University1043Pose Estimation and Segmentation of People in 3D MoviesKarteek Alahari*, ENS-Willow; Guillaume Seguin, ; Josef Sivic, Ecole Normale Suprieure; Ivan Laptev, "INRIA, France"1049Coherent Object Detection with 3D Geometric Context from a Single ImageJiyan Pan*, Carnegie Mellon University; Takeo Kanade,1061Quantize and Conquer: A dimensionality-recursive solution to nearest neighbor search, clustering, and image retrievalYannis Avrithis*, NTUA1078Efficient Hand Pose Estimation from a Single Depth ImageChi Xu, Bioinformatics Institute; Li Cheng*, Bioinformatics Institute1132Symbiotic Segmentation and Part Localization for Fine-Grained CategorizationYuning Chai*, University of Oxford; Victor Lempitsky, Skolkovo Institute of Science and Technology; Andrew Zisserman, University of Oxford1137Probabilistic Elastic Part Model for Unsupervised Face Detector AdaptationHaoxiang Li, Stevens Institute of Technology; Gang Hua*, Stevens Institute of Technology; Zhe Lin, Adobe Research; Jonathan Brandt, Adobe; Jianchao Yang, Adobe Systems Inc.1141Text Localization in Natural Images using Stroke Feature Transform and Text Covariance DescriptorsWeilin Huang, Adobe Research; Zhe Lin, Adobe Research; Jianchao Yang, Adobe Systems Inc.; Jue Wang*,1187Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual RecognitionHans Lbel*, Universidad Catlica de Chile; Rene Vidal, Johns Hopkins University; lvaro Soto, Universidad Catlica de Chile1193A Unified Probabilistic Approach Modeling Relationships between Attributes and ObjectsXiaoyang Wang*, RPI; Qiang Ji,1202Write a Classifier: Zero Shot Learning Using Purely Textual DescriptionsMohamed Elhoseiny*, Rutgers Universeity; Ahmed Elgammal, ; Babak Saleh, Rutgers University1207Learning Hash Codes with Listwise Supervision for Web-Scale Image SearchJun Wang*, IBM T. J. Watson Research; Wei Liu, Columbia University; Andy Sun, IBM ; Yugang Jiang, Fudan University1214Synergistic Clustering of Image and Segment Descriptors for Unsupervised Scene UnderstandingDaniel Steinberg*, ACFR; Oscar Pizarro, ACFR; Stefan Williams, ACFR1224Image Set Classification Using Holistic Multiple Order Statistics Features and Localized Multi-Kernel Metric LearningJiwen Lu*, Advanced Digital Sciences Center, Singapore; Gang Wang, NTU; Pierre Moulin, UIUC1225Multi-Label Image Annotations Using New Graph Structured Sparsity Modelxiao Cai, University of Texas at Arlington; Feiping Nie, University of Texas at Arlington; Heng Huang*, UTA1226A Framework for Shape Analysis via Hilbert Space EmbeddingSadeep Jayasumana*, ANU; Mathieu Salzmann, NICTA; Hongdong Li, Australia National University; Mehrtash Harandi, NICTA1235Query-adaptive asymmetrical dissimilarities for visual object retrievalCai-Zhi Zhu*, National Institute of Informatics; Herv Jgou, INRIA; shin'ichi satoh, NII1263Fast Neighborhood Graph Search using Cartesian ConcatenationJing Wang, Peking University; Jingdong Wang*, Microsoft Research Asia; Gang Zeng, Peking University; Shipeng Li,1274Random Forests of Local Experts for Pedestrian DetectionJavier Marin*, Computer Vision Center; David Vazquez, Computer Vision Center, UAB; Jaume Amores, Computer Vision Center, UAB; Antonio Lopez, Computer Vision Center, UAB; Bastian Leibe, "RWTH Aachen University, Germany"1287Image Retrieval using Textual CuesAnand Mishra*, IIIT Hyderabad; Karteek Alahari, ENS-Willow; c. v. Jawahar, IIIT Hyderabad1294Random Grids: Fast Approximate Nearest Neighbors and Range Searching for Image SearchDror Aiger*, Google; Effrosyni Kokiopoulou, Google; Ehud Rivlin, Google Research1302Learning a Dictionary of Shape Epitomes with Application to Semantic LabelingLiang-Chieh Chen*, UCLA; George Papandreou, UCLA; Alan Yuille, UCLA1320Heterogeneous Auto-Similarities of Characteristics (HASC): exploiting relational information for classificationMarco San Biagio*, IIT; Marco Crocco, IIT; Marco Cristani, IIT; Samuele Martelli, IIT; Vittorio Murino, Istituto Italiano di Tecnologia1352Offline Mobile Instance Retrieval with a Small Memory FootprintJayaguru Panda*, IIIT Hyderabad; Michael Brown, National University of Singapore; c. v. Jawahar, IIIT Hyderabad1354Fine-Grained Categorization by AlignmentsEfstratios Gavves*, University of Amsterdam; Basura Fernando, KU Leuven; Cees Snoek, University of Amsterdam; Arnold Smeulders, ; Tinne Tuytelaars, KU Leuven1359Codemaps Segment, Classify and Search Objects LocallyZhenyang Li*, University of Amsterdam; Efstratios Gavves, University of Amsterdam; Koen van de Sande, ; Cees Snoek, University of Amsterdam; Arnold Smeulders,1392Visual Reranking through Weakly Supervised Multi-Graph LearningCheng Deng*, Xidian University; Rongrong Ji, Columbia University; Wei Liu, Columbia University; Dacheng Tao, """University of Technology, Sydney"""; xinbo Gao,1411Scene Collaging: Analysis and Synthesis of Natural Images with Semantic LayersPhillip Isola*, MIT; Ce Liu, Microsoft Research New England1423Discovering Details and Scene Structure with Hierarchical Iconoid ShiftTobias Weyand*, RWTH Aachen; Bastian Leibe, RWTH Aachen1454Pyramid Coding for Functional Scene Element Recognition in Video ScenesEran Swears*, Kitware Inc.; Anthony Hoogs, Kitware, USA; Kim Boyer, RPI1469A Fully Hierarchical Approach for Finding Correspondences in Non-rigid ShapesIvan Sipiran*, University of Chile; Benjamin Bustos, University of Chile1477BOLD features to detect texture-less objectsFederico Tombari*, University of Bologna; Alessandro Franchi, ; Luigi Di Stefano,1479Locally Affine Sparse-to-Dense Matching for Motion and Occlusion EstimationMarius Leordeanu*, Institute of Mathematics of the Romanian Academy; Andrei Zanfir, ; Cristian Sminchisescu, Lund University1506Support surface prediction in indoor scenesRuiqi Guo*, UIUC; Derek Hoiem, University of Illinois at Urbana-Champaign1526Domain Adaptive ClassificationFatemeh Mirrashed*, University of Maryland; Mohammad Rastegari, University of Maryland1534Understanding High-Level Semantics by Modeling Traffic PatternsHongyi Zhang, Peking University; Andreas Geiger*, KIT ; Raquel Urtasun, Toyota Technological Institute at Chicago1541Strong Appearance and Expressive Spatial Models for Human Pose EstimationLeonid Pishchulin*, Max Planck Institute for Infor; Mykhaylo Andriluka, Max Planck Institute for Informatics; Peter Gehler, Max Planck ; Bernt Schiele, "MPI Informatics, Germany"1548Box In the Box: Joint 3D Layout and Object Reasoning from Single ImagesAlexander Schwing*, ETH Zurich; Sanja Fidler, TTIC; Marc Pollefeys, ETH; Raquel Urtasun, Toyota Technological Institute at Chicago1552Learning to Transfer Privileged InformationViktoriia Sharmanska*, IST Austria; Novi Quadrianto, University of Cambridge; Christoph Lampert, Institute of Science and Technology Austria1553Estimating the 3D Layout of Indoor Scenes and its Clutter from Depth SensorsJian Zhang, ; Kan Chen, ; Alexander Schwing*, ETH Zurich; Raquel Urtasun, Toyota Technological Institute at Chicago1558Predicting an Object Location using a Global Image RepresentationJose Rodriguez-Serrano*, ; Diane Larlus,1575Take Your Favorite Cloud with YouKuan-Chuan Peng*, Cornell University; Tsuhan Chen,1592Supervise Binary Hash Code Learning With Jensen Shannon DivergenceLixin Fan*, Nokia Research Center1603Efficient 3D Scene Labeling Using Fields of TreesOlaf Khler*, University of Oxford; Ian Reid, University of Adelaide16693D Sub-Query Expansion for Improving Sketch-based Multi-View Image RetrievalYenliang Lin*, National Taiwan University; Cheng Yu Huang, ; Hao Jeng Wang, ; Winston Hsu,1675Quasi-Unsupervised Learning for Reliably Relating Visual AttributesSukrit Shankar*, Cambridge University; Joan Lasenby, Univerity of Cambridge; Roberto Cipolla, Cambridge University1677Simultaneous Segmentation and Pose Tracking in Moving CameraTaegyu Lim*, Samsung; Seunghoon Hong, POSTECH; Bohyung Han, POSTECH; JoonHee Han, POSTECH1684A Non-parametric Bayesian Network Prior of Human PoseAndreas Lehrmann*, MPI for Intelligent Systems; Peter Gehler, Max Planck ; Sebastian Nowozin, Microsoft Research Cambridge1775Heterogeneous Image Feature Integration via Multi-Modal Semi-Supervised Learning for Image Categorizationxiao Cai*, University of Texas at Arlington; Feiping Nie, University of Texas at Arlington; Heng Huang, UTA1851Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right ThingAmir Sadovnik*, Cornell University; Andrew Gallagher, ; Devi Parikh, Virginia Tech; Tsuhan Chen,1857Model Recommendation with Virtual Probes for Ego-Centric Hand DetectionCheng Li, Tsinghua University; Kris Kitani*, Carnegie Mellon University1862Multi-Channel Correlation FiltersHamed Kiani galoogahi*, NUS; Terence Sim, NUS; Simon Lucey,1863Predicting Primary Gaze Behavior using Social Saliency FieldsHyun Soo Park*, CMU; Eakta Jain, TI; Yaser Sheikh,1865From Subcategories to Visual Composites: A Multi-Level Framework for Object DetectionTian Lan*, Simon Fraser University; Leonid Sigal, ; Michalis Raptis, Disney Research Pittsburgh; Greg Mori, Simon Fraser University1874Characterizing Layouts of Outdoor Scenes Using Spatial Topic ProcessesDahua Lin*, TTIC; Jianxiong Xiao, MIT1902Pictorial Human Spaces: How Well do Humans Perceive a 3D Articulated Pose?Elisabeta Marinoiu*, Romanian Academy of Science; Dragos Papava, Institute of Mathematics of the Romanian Academy; Cristian Sminchisescu, Lund University1909Building Parts-based Object Detectors via 3D GeometryAbhinav Shrivastava, Carnegie Mellon University; Abhinav Gupta*,Segmentation, grouping and shape representation67Online Video Superpixels for Temporal Window ObjectnessMichael Van den Bergh, ETH; Gemma Roig, ETH; Xavier Boix*, ETH; Santiago Manen, BIWI ETH Zurich; Luc Van Gool, ETH87Image Co-Segmentation via Consistent Functional MapsFan Wang*, Stanford University; Qixing Huang, Stanford University; Leonidas Guibas, Stanford University102Co-Segmentation by CompositionAlon Faktor*, Weizmann Institute of Science; Michal Irani, Weizmann Institute, Israel148Detecting Curved Symmetric Parts using a Deformable Disc ModelTom Lee*, University of Toronto; Sanja Fidler, TTI Chicago ; Sven Dickinson, University of Toronto244Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal NetworksMojtaba Seyedhosseini*, SCI; Mehdi Sajjadi, SCI; Tolga Tasdizen, SCI311Geometric Registration Based on Distortion EstimationWei Zeng*, Florida International Univ.; Mayank Goswami, Stony Brook University; Feng Luo, Rutgers University; xianfeng Gu, Stony Brook University339Learning CRFs for Image Parsing with Adaptive Subgradient DescentHonghui Zhang*, HKUST; Long Quan, "The Hong Kong University of Science and Technology, China"; Ping Tan, ; Jingdong Wang, Microsoft Research Asia346Efficient Higher-Order Clustering on the Grassmann ManifoldSuraj Jain, Indian Institute of Science; Venu Madhav Govindu*, Indian Institute of Science447Temporally Consistent SuperpixelsMatthias Reso*, TNT LUH Hannover; Joern Jachalsky, Technicolor; Joern Ostermann, Institut fr Informationsverarbeitung / Universitt Hannover; Bodo Rosenhahn,487Exemplar CutJimei Yang*, UC Merced; Yi-Hsuan Tsai, UC Merced; Ming-Hsuan Yang, "UC Merced, USA"617Cosegmentation and Cosketch by Unsupervised LearningJifeng Dai*, Tsinghua University; UCLA; Ying Nian Wu, UCLA; Jie Zhou, Tsinghua University; Song Chun Zhu, UCLA619Category-Independent Object-level Saliency DetectionYangqing Jia*, UC Berkeley; Mei Han, Google Research638Semantic Segmentation without Annotating SegmentsWei Xia*, NUS; Csaba Domokos, NUS; Jian Dong, NUS; Loong-Fah Cheong, NUS; Shuicheng Yan, "NUS, Singapore"674Multi-View Object Segmentation in Space and TimeAbdelaziz Djelouah*, Technicolor; Edmond Boyer, ; Jean-Sebastien Franco, Grenoble Universities; Patrick Perez, "Technicolor, France"; Franois Le Clerc,766Robust Trajectory Clustering for Motion SegmentationFeng Shi, Beihang University; zhong Zhou*, ; Jiangjian Xiao, ; Wei Wu,943Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing ItemsKota Yamaguchi*, ; M. Hadi Kiapour, Stony Brook University; Tamara Berg, "Stony Brook University, USA"983Semi-supervised learning for large scale image cosegmentationZhengxiang Wang*, Fujitsu R&D Center ; Rujie Liu, Fujitsu R&D Center1192Parallel Transport of Deformations in Shape Space of Elastic SurfacesQIAN XIE*, Florida State University; Sebastian Kurtek, Ohiao State University; Huiling Le, ; Anuj Srivastava,1391Predicting Sufficient Annotation Strength for Interactive Foreground SegmentationSuyog Jain*, ; Kristen Grauman, University of Texas at Austin1431GrabCut in One CutMeng Tang, University of Western Ontario; Lena Gorelick*, University of Western Ontario; Olga Veksler, University of Western Ontario; Yuri Boykov, "University of Western Ontario, Canada"1434Progressive Multigrid Eigensolvers for Multiscale Spectral SegmentationMichael Maire*, California Institute of Technology; Stella Yu, ICSI; Pietro Perona, "Caltech, USA"1485Pedestrian Parsing via Deep Decompositional NetworkPing Luo*, CUHK1577Robust Subspace Clustering via Half-Quadratic MinimizationYingya Zhang*, NLPR, CASIA; Zhenan Sun, NLPR, CASIA; Ran He, NLPR, CASIA; Tieniu Tan, "NLPR, China"1674A Unified Video Segmentation Benchmark: Annotation, Metrics and AnalysisFabio Galasso*, MPI Informatics; Naveen Nagaraja, University of Freiburg; Tatiana Jimenez Cardenas, University of Freiburg; Thomas Brox, ; Bernt Schiele, "MPI Informatics, Germany"1695Automatic Kronecker Product Model Based Detection of Repeated Patterns in 2D Urban ImagesJuan Liu, Graduate Center City University of New York; Emmanouil Psarakis, University of Patras; Ioannis Stamos*, CUNY1742A Method of Perceptual-based Shape DecompositionChang Ma, Peking University; Zhongqian Dong, Peking University; Tingting Jiang, Peking University; yizhou Wang*, Peking University1786Sequential Bayesian Model Update under Structured Scene Prior for Semantic Road Scenes LabelingEvgeny Levinkov, MPII; Mario Fritz*, MPI Informatics1966Fast object segmentation in unconstrained videoAnestis Papazoglou*, University of Edinburgh; Vitto Ferrari, University of Edinburgh1974Video Segmentation by Tracking Many Figure-Ground SegmentsFuxin Li*, Georgia Inst. of Tech.; Taeyoung Kim, Georgia Institute of Technology; Ahmad Humayun, ; Wei Cai, Georgia Institute of Technology; James Rehg, Georgia Institute of TechnologyStatistical methods and learning73Group Norm for Learning Structured SVMs with Unstructured Latent VariablesDaozheng Chen, UMD; Dhruv Batra*, Virginia Tech; Bill Freeman, "MIT, USA"94Curvature-aware Regularization on Riemannian SubmanifoldsKwang In Kim*, MPI for Informatics; James Tompkin, MPI Informatik; Christian Theobalt, MPI fuer Informatik258Learning Graph Matching for Category Modeling from Large ScenesQuanshi Zhang*, University of Tokyo; Xuan Song, University of Tokyo; Xiaowei Shao, University of Tokyo; Ryosuke Shibasaki, University of Tokyo; Huijing Zhao, Peking University306Bayesian Robust Matrix Factorization for Image and Video ProcessingNaiyan Wang*, HKUST; Dit-Yan Yeung, HKUST360Transfer Feature Learning with Joint Distribution AdaptationMingsheng Long*, Tsinghua University; Jianmin Wang, Tsinghua University; Guiguang Ding, Tsinghua University; Philip Yu, University of Illinois at Chicago442Dynamic Structured Model SelectionDavid Weiss*, University of Pennsylvania; Benjamin Sapp, Google; Ben Taskar, University of Washington482Structured learning of sum-of-submodular higher order energy functionsAlex Fix, Cornel; Thorsten Joachims, Cornell; Sam Park, Cornell; Ramin Zabih*, Cornell University484What Is the Most Efficient Way to Select Nearest Neighbor Candidates for Fast Approximate Nearest Neighbor Search?Masakazu Iwamura*, Osaka Prefecture University; Tomokazu Sato, Osaka Prefecture University; Koichi Kise, Osaka Prefecture University641Alternating Regression Forests for Object Detection and Pose EstimationSamuel Schulter*, TUGraz; Christian Leistner, Microsoft; Paul Wohlhart, TU Graz; Peter Roth, ; Horst Bischof, Graz University of Technology642Linear Sequence Discriminant Analysis: A Model-Based Dimensionality Reduction Method for Vector SequencesBing Su*, Tsinghua University; Xiaoqing Ding, Tsinghua University930Robust Matrix Factorization with Unknown NoiseDeyu Meng*, Xi'an Jiaotong University; Fernando de la Torre, Carnegie Mellon University957Recursive Estimation of the Stein Center of SPD Matrices and its ApplicationsHesamoddin Salehian*, University of Florida; Guang Cheng, ; Baba Vemuri, "University of Florida, USA"; Jeffrey Ho, University of Florida968Manifold based Image Synthesis from Sparse SamplesHongteng Xu*, Georgia Tech; Hongyuan Zha, Georgia Tech988From Point to Set: Extend the Learning of Distance MetricsPengfei Zhu, The Hong Kong Polytechnic University; Lei Zhang*, The Hong Kong Polytechnic University; Wangmeng Zuo, Harbin Institute of Technology; David Zhang, The Hong Kong Polytechnic University1010Discriminative Metric and Prototype LearningMartin Kstinger*, Graz University of Technology; Peter Roth, ; Horst Bischof, Graz University of Technology1082Divide-and-Conquer Subspace SegmentationAmeet Talwalkar*, UC Berkeley; Lester Mackey, Stanford University; Yadong MU, Columbia University; Shih-Fu Chang, Columbia University; Michael Jordan, Berkeley1405Dynamic Label Propagation for Semi-supervised Multi-class Multi-label ClassificationBo Wang*, York University; John Tsotsos, "York University, Canada"1420Frustratingly Easy NBNN Domain AdaptationTatiana Tommasi*, IDIAP Martigny ; Barbara Caputo,1503Correlation Adaptive Subspace Segmentation by Trace LassoCanyi Lu*, National University of Singapo; Jiashi Feng, NUS; Zhouchen Lin, Peking University ; Shuicheng Yan, "NUS, Singapore"1504Correntropy Induced L2 Graph for Robust Subspace ClusteringCanyi Lu*, National University of Singapo; Zhouchen Lin, Peking University ; Shuicheng Yan, "NUS, Singapore"1647Robust Dictionary Learning by Error Source DecompositionZhuoyuan Chen*, Northwestern University; Ying Wu, Northwestern University1941Class-Specific Simplex-Latent Dirichlet Allocation for Image ClassificationMandar Dixit*, UC San Diego; Nikhil Rasiwasia, Yahoo Research; Nuno Vasconcelos, "UC San Diego, USA"Video: events, activities & surveillance23Monte Carlo Tree Search for Scheduling Activity RecognitionMohamed Amer*, OREGON STATE UNIVERSITY; Sinisa Todorovic, "Oregon State University, USA"; Alan Fern, Oregon State University; Song Chun Zhu, UCLA183Video Event Understanding using Natural Language DescriptionsVignesh Ramanathan*, Stanford University; Percy Liang, Stanford University; Fei-Fei Li, Stanford University204Translating video into natural language descriptionsMarcus Rohrbach*, MPI Informatics; Wei Qiu, Coli.uni-saarland.de; Ivan Titov, Saarland University; Stefan Thater, ; Manfred Pinkal, Saarland University; Bernt Schiele, "MPI Informatics, Germany"219Group Sparsity and Geometry Constrained Dictionary Learning for Action Recognition from Depth MapsJiajia Luo*, The University of Tennessee; Wei Wang, ; Hairong Qi,308Inferring "Dark Matter" and "Dark Energy" from VideosDan Xie, University of California Los Angeles; Sinisa Todorovic*, "Oregon State University, USA"; Song Chun Zhu, UCLA367Mining Motion Atoms and Phrases for Complex Action RecognitionLiMin Wang*, CUHK; Yu Qiao, SIAT395View-Invariant Action Recognition via Finding Canonical Views and PartsBehrooz Mahasseni*, Oregon State Univeristy; Sinisa Todorovic, "Oregon State University, USA"433Action recognition with improved trajectoriesHeng Wang*, ; Cordelia Schmid, "INRIA, France"438Person Re-Identification Post-Rank OptimisationChunxiao Liu, Tsinghua University; Chen Change Loy, CUHK; Shaogang Gong*, EECS, QMUL; Guijin Wang, Tsinghua University456ACTIVE: Activity Concept Transitions in Video Event ClassificationChen Sun*, University of Southern Califor; Ram Nevatia,492Manipulation Pattern Discovery: A Nonparametric Bayesian ApproachBingbing NI*, """""""""""""""""""""""""""""""Advanced Digital Sciences Center (ADSC), Singapor; Pierre Moulin, UIUC522Action and Event Recognition with Fisher vectors on a Compact Feature SetDan Oneata*, INRIA; Jakob Verbeek, "INRIA, France"; Cordelia Schmid, "INRIA, France"584Video Co-segmentation for Meaningful Action ExtractionJiaming Guo*, NUS; Zhuwen Li, NUS; Loong-Fah Cheong, NUS; Zhiying Zhou, NUS611Learning Maximum Margin Temporal Warping for Action RecognitionJiang Wang*, Northwestern University; Ying Wu, Northwestern University680Concurrent Action Detection with Structural PredictionPing Wei*, Xi'an Jiaotong University,UCLA; Nanning Zheng, Xi'an Jiaotong University ; Yibiao Zhao, UCLA; Song Chun Zhu, UCLA704Action Recognition with ActiontonJun Zhu*, Shanghai Jiao Tong University; baoyuan Wang, ; Zhuowen Tu, UCLA; Xiaokang Yang, ; Wenjun Zhang,864Stable hyper-pooling and query expansion for event detectionMatthijs Douze, INRIA; Jerome Revaud, ; Cordelia Schmid, "INRIA, France"; Herv Jgou*, INRIA946Active Learning of an Action Detector from Untrimmed VideosSunil Bandla, University of Texas at Austin; Kristen Grauman*, University of Texas at Austin954Flattening Supervoxel Hierarchies by the Uniform Entropy SliceChenliang Xu*, SUNY at Buffalo; Spencer Whitt, SUNY at Buffalo; Jason Corso, "SUNY Buffalo, USA"970From Actemes to Action: A Strongly-supervised Representation for Detailed Action UnderstandingWeiyu Zhang*, University of Pennsylvania; Konstantinos Derpanis, University of Pennsylvania; Menglong Zhu, University of Pennsylvania976From Semi-Supervised to Transfer Counting of CrowdsChen Change Loy*, CUHK; Shaogang Gong, EECS, QMUL; Tao Xiang, EECS,QMUL977Combining the Right Features for Complex Event RecognitionKevin Tang*, Stanford U.; Bangpeng Yao, Stanford University; Fei-Fei Li, Stanford University; Daphne Koller,984Understanding Human-Object Interaction via Exemplar based ModellingJian-Fang Hu*, Sun yat-sen university; Wei-Shi Zheng, ; Jian-Huang Lai, Sun Yat-sen University; Shaogang Gong, EECS, QMUL; Tao Xiang, EECS,QMUL1011Domain Transfer Support Vector Ranking for Person Re-Identification without Target Camera Label InformationAndy Jinhua Ma, Hong Kong Baptist University; Pong Chi Yuen*, Hong Kong Baptist University; Jiawei Li,1026Learning to Share Latent Tasks for Action RecognitionQiang Zhou*, NUS, Singapore; Gang Wang, NTU; Qi Zhao, National Univ. of Singapore1064Large Scale Video Hashing via Structure LearningGuangnan Ye*, Columbia University; Dong Liu, Columbia University; Jun Wang, IBM T. J. Watson Research; Shih-Fu Chang, Columbia University1116Finding Actors and Actions in MoviesPiotr Bojanowski*, INRIA; Francis Bach, "ENS and INRIA, France"; Ivan Laptev, "INRIA, France"; Jean Ponce, "ENS, France"; Cordelia Schmid, "INRIA, France"; Josef Sivic, Ecole Normale Suprieure1127Space-Time Robust Video Representation for Action RecognitionNicolas Ballas*, CEA/Mines-ParisTech; Yi Yang, cmu.edu; Lan Zshzsh, CMU; Betrand Delezoide, CEA; Franoise Preteux, Mines ParisTech; Alexander Hauptmann, Carnegie Mellon University1218YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shoot RecognitionSergio Guadarrama*, University of California, Berk; Niveda Krishnamoorthy, UT Austin; Girish Malkarnenkar, UT Austin; Raymond Mooney, ; Trevor Darrell, ; Kate Saenko, UMass Lowell1255Very Fast Abnormal Event DetectionCewu Lu*, The Chinese University of Hong; Jianping Shi, CUHK ; Jiaya Jia, Chinese University of Hong Kong1273Human Re-identification by Matching Compositional Template with Cluster SamplingYuanlu Xu, Sun Yat-Sen University; Liang Lin*, Sun Yat-Sen University; Weishi Zheng, ; Xiaobai Liu, Ucla.edu1331Finding Causal Interactions in Video SequencesMustafa Ayazoglu, Notheastern University; Burak Yilmaz, Northeastern University; Mario Sznaier*, Northeastern University; Octavia Camps,1382Dynamic Pooling for Complex Event RecognitionWeixin Li*, UC San Diego; Qian Yu, Sarnoff; Nuno Vasconcelos, UC San Diego1442Relative Attributes For Large-scale Abandoned Object DetectionQuanfu Fan*, IBM; Prasad Gabbur, ; Sharath Pankanti,1457Action Recognition and Localization by Hierarchical Space-Time SegmentsShugao Ma*, Boston University; Stan Sclaroff, Boston University; Jianming Zhang, Boston University; nazli Ikizler-cinbis, Department of Computer Engineering, Hacettepe University1501The "Moving Pose": An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and DetectionMihai Zanfir, ; Marius Leordeanu*, Institute of Mathematics of the Romanian Academy; Cristian Sminchisescu, Lund University1510Modeling 4D Human-Object Interactions for Event and Object RecognitionPing Wei*, Xi'an Jiaotong University,UCLA; Yibiao Zhao, UCLA; Nanning Zheng, Xi'an Jiaotong University ; Song Chun Zhu, UCLA1658DIRECTED ACYCLIC GRAPH KERNELS FOR ACTION RECOGNITIONLing WANG*, Telecom ParisTech; Hichem SAHBI, LTCI, CNRS, (TELECOM ParisTech)1670Learning View-invariant Sparse Representations for Cross-view Action RecognitionJingjing Zheng*, University of Maryland; Zhuolin Jiang, University of Maryland1709A New Adaptive Segmental Matching Measure for Human Activity RecognitionShahriar Shariat*, Rutgers; Vladimir Pavlovic,1841Event Detection in Complex Scene Using Interval Temporal ConstraintsYifan Zhang*, CASIA; Qiang Ji, ; Hanqing Lu,1978Towards understanding action recognitionHueihan Jhuang*, ; Juergen Gall, Max Planck Institute for Intelligent Systems; Michael Black, "Max Planck Institute for Intelligent Systems, Germany"; Cordelia Schmid, INRIAVision for graphics201Modifying the Memorability of Face PhotographsAditya Khosla*, MIT; Wilma Bainbridge, MIT; Antonio Torralba, MIT; Aude Oliva,283Saliency Detection in Large Point SetsElizabeth Shtrom*, Technion; George Leifman, Technion; Ayellet Tal, Technion669Motion-Aware KNN Laplacian for Video MattingDingzeyu Li*, Columbia University; Qifeng Chen, ; Chi-Keung Tang, "Hong Kong University of Science and Technology, Hongkong"961Viewing Real-World Faces in 3DTal Hassner*,1242Accurate and Robust 3D Facial Performance Capture using Single RGBD ImagesYen-Lin Chen, Texas A&M University; Muscle Wu, Microsoft Research Asia; Fuhao SHi, Texas A&M University; Xin Tong, Microsoft Asia; Jinxiang Chai*, TAMUVision for the web1304Visual Semantic Complex Network for Web ImagesShi Qiu*, CUHK; Xiaogang Wang, "The Chinese University of Hong Kong, Hongkong"; Xiaoou Tang, Chinese University of Hong Kong1427What Do You Do? Recognize Occupations in a Photo via Social ContextMing Shao*, Northeastern University; Liangyue Li, Northeastern University; Yun Fu, Northeastern University