ECCV 2012 List of accepted papers

Oral presentation

 oral出来了,只有40篇文章,录取率只有大概2.3%。先Mark一下,等出来后选感兴趣的看几篇

Paper id Paper title Author names
13 Diverse M-Best Solutions in Markov Random Fields Dhruv Batra*, Toyota Technological Institute at Chicago (TTIC) ; Payman Yadollahpour, TTIC; Abner Guzman-Rivera, UIUC; Greg Shakhnarovich, TTIC
17 Attributes for classifier feedback Amar Prakash, IIIT-D; Devi Parikh*, TTIC
85 Reconstructing the World’s Museums Jianxiong Xiao*, MIT; Yasutaka Furukawa, Google
100 Frequency-Space Decomposition and Acquisition of Light Transport under Spatially Varying Illumination Dikpal Reddy*, UC Berkeley; Ravi Ramamoorthi, ; Brian Curless,
127 Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Thomas Mensink*, INRIA Rhone Alpes; Jakob Verbeek, ; Gabriela Csurka, XRCE; Florent Perronnin, XRCE
150 Segmentation Propagation in ImageNet Daniel Kuettel*, ETH Zurich; Matthieu Guillaumin, ETH Zürich; Vittorio Ferrari,
152 A Unified Framework for Multi-Target Tracking and Collective Activity Recognition Wongun Choi*, The University of Michigan; Silvio Savarese, The University of Michigan, Ann Arbor
175 Exact Acceleration of Linear Object Detectors Charles Dubout*, Idiap; François Fleuret, Idiap
214 Shape Sharing for Object Segmentation Jaechul Kim*, University of Texas at Austin; Kristen Grauman,
236 Activity Forecasting Kris Kitani*, Carnegie Mellon University; James Bagnell, ; Martial Hebert,
276 Action Recognition with Exemplar Based 2.5D Graph Matching Bangpeng Yao*, Stanford University; Li Fei-fei,
331 People Watching: Human Actions as a Cue for Single View Geometry David Fouhey*, Carnegie Mellon University; Vincent Delaitre, ; Alyosha Efros, CMU; Abhinav Gupta, ; Ivan Laptev, ; Josef Sivic, INRIA / Ecole Normale Superieure
354 Depth Extraction from Video Using Non-parametric Sampling Kevin Karsch*, UIUC; Ce Liu, Microsoft Research New England; Sing Bing Kang, Microsoft Research
405 Constrained Bootstrapping for Image Classification via Attributes and Comparative Attributes Abhinav Shrivastava*, Carnegie Mellon University; Saurabh Singh, Carnegie Mellon University; Abhinav Gupta, Carnegie Mellon University
440 “Clustering by Composition” for Unsupervised Discovery of Image Categories Michal Irani; Alon Faktor
708 Detecting and Localizing Activities at Different Scales under Budget Mohamed Amer*, Oregon State University; Dan Xie, UCLA; Mingtian Zhao , UCLA; Yaofei Feng, OREGON STATE UNIVERSITY; Behrooz Mahasseni, OREGON STATE UNIVERSITY; Sinisa Todorovic, Oregon State University; Song-Chun Zhu, UCLA
811 Latent Hough Transform for Object Detection Nima Razavi*, ETH Zurich; Juergen Gall, ETH Zurich; Pushmeet Kohli, ; Luc Van Gool,
848 A QCQP Approach to Triangulation Chris Aholt*, University of Washington; Sameer Agarwal, Google; Rekha Thomas, University of Washington
866 Recognizing Actions, Poses, and Objects with Relational Phraselets Chaitanya Desai*, University of California Irvine; Deva Ramanan,
880 Generic Cuts: An Efficient Optimal Algorithm for Submodular MRF-MAP Problems with Higher Order Cliques Chetan Arora*, IIT Delhi; Subhashis Banerjee, IIT Delhi; Prem Kalra, IIT Delhi; S.N. Maheshwari, IIT Delhi
959 A Three-Layered Approach to Facade Parsing Andelo Martinovic*, KU Leuven; Markus Mathias, KU Leuven; Julien Weissenberg, ETHZ; Luc Van Gool, KU Leuven
981 Multiple View Object Cosegmentation using Appearance and Stereo Cues Adarsh Kowdle*, Cornell University; Sudipta Sinha, ; Rick Szeliski,
1024 Using linking features in learning non-parametric part models Leonid Karlinsky*, Weizmann Institute of Science; Shimon Ullman, Weizmann Institute of Science
1035 Patch Complexity, Finite Pixel Correlations and Optimal Denoising Anat Levin*, Weizmann Institute; Boaz Nadler, Weizmann Inst; Fredo Durand, MIT; William Freeman, Massachusetts Institute of Technology
1051 Filter-based Mean-Field Inference for Random Fields with Higher Order Terms and Product Label-Spaces Jonathan Warrell*, Oxford Brookes University; Phil Torr, ; Vibhav Vineet, Oxford Brookes University
1071 Good Regions to Deblur Zhe Hu*, UC Merced; Ming-Hsuan Yang, University of California at Merced
1079 Indoor Segmentation and Support Inference from RGBD Images Nathan Silberman*, NYU; Rob Fergus, ; Derek Hoiem, UIUC; Pushmeet Kohli,
1110 Reflectance and Natural Illumination from a Single Image Stephen Lombardi*, Drexel University; Ko Nishino, Drexel University
1171 Diagnosing Error in Object Detectors Derek Hoiem*, University of Illinois; Yodsawalai Chodpathumwan, University of Illinois; Qieyun Dai, University of Illinois
1181 A Naturalistic Open Source Movie for Optical Flow Evaluation Daniel Butler*, University of Washington; Jonas Wulff, Max Planck Institute for Intelligent Systems; Garrett Stanley, Department of Biomedical Engineering, Georgia Institute of Technology; Michael Black, Max Planck Institute for Intelligent Systems
1243 Efficient Optimization For Low-Rank Integrated Bilinear Classifiers Takumi Kobayashi*, National Institute of AIST; Nobuyuki Otsu,
1258 PlantID: A Computer Vision System for Automatic Plant Species Identification Neeraj Kumar*, University of Washington; David Jacobs, ; Peter Belhumeur, Columbia University; Arijit Biswas, University of Maryland; Joao Soares, University of Maryland
1330 Semantic Segmentation with Second-Order Pooling Joao Carreira*, University of Coimbra; Rui Caseiro, Institute Systems Robotics; Jorge Batista, Institute Systems Robotics – University Coimbra – Portugal; Cristian Sminchisescu, University of Bonn
1383 Photo-Sequencing Tali Basha*, Tel Aviv University; Shai Avidan, ; Yael Moses, IDC
1422 Continuous Markov Random Fields for Robust Stereo Estimation Koichiro Yamaguchi, TTI Chicago; Tamir Hazan, TTI Chicago; David McAllester, TTI Chicago; Raquel Urtasun*, TTIC
1429 Fourier Kernel Learning Eduard-Gabriel Bazavan*, IMAR; Fuxin Li, Georgia Inst. of Tech.; Cristian Sminchisescu, University of Bonn
1436 Large Scale Visual Geo-Localization of Images in Mountainous Terrain Georges Baatz*, ETHZ; Olivier Saurer, ETHZ; Kevin Koeser, ETHZ; Marc Pollefeys,
1543 Streaming Hierarchical Video Segmentation Chenliang Xu, SUNY at Buffalo; Caiming Xiong, SUNY at Buffalo; Jason Corso*, SUNY at Buffalo
1619 Motion Capture of Hands in Action using Discriminative Salient Points Luca Ballan*, ETH Zurich; Aparna Taneja, ETH Zurich; Juergen Gall, ETH Zurich; Luc Van Gool, ; Marc Pollefeys,
1707 Beyond the line of sight: labeling the underlying surfaces

还看不出谁是oral,谁是poster,也没有查到oral录取率和总录取率。粗略数了数,录取率大概是410/1712=23.9%(总篇数用最后一篇的序号来估算)。无聊统计了一下,录取的前100篇对应的录取率是100/376=26.6%,前200篇对应的录取率是200/816=24.5%,前300篇对应的录取率是300/1176=25.5%。这也说明,投稿先后对录取没什么影响^_^



Paper ID Paper Title Author Names
1 Semi-Intrinsic Mean shift on Riemannian Manifolds Rui Caseiro*, Institute Systems Robotics; Jo„o F Henriques, ISR; PedroMartins, ISR; Jorge Batista, Institute Systems Robotics – University Coimbra- Portugal
5 Online Learning of Linear Predictors for Real-Time Tracking Stefan Holzer*, Technische Universität München; Marc Pollefeys;Slobodan Ilic, TUM; David Joseph Tan, Technische Universität München; NassirNavab, Technische Universität München
6 Learning to Efficiently Detect Repeatable Interest Points in Depth Data Stefan Holzer*, Technische Universität München; Jamie Shotton, MicrosoftResearch Cambridge; Pushmeet Kohli 
10 Effective Use of Frequent Itemset Mining for Image Classification Basura Fernando*, K.U. Leuven; Elisa Fromont, University Jean MonnetSaint Etienne France; Tinne Tuytelaars 
13 M-Best Modes Payman Yadollahpour, TTIC; Dhruv Batra*, Toyota Technological Instituteat Chicago (TTIC) ; Abner Guzman-Rivera, UIUC; Greg Shakhnarovich, TTIC
17 Attributes for classifier feedback Amar Prakash, IIIT-D; Devi Parikh*, TTIC
21 Lie Bodies: A Manifold Representation of 3D Human Shape Oren Freifeld*, Brown University; Michael Black, Max Planck Institute forIntelligent Systems
25 Modeling Complex Temporal Composition of Actionlets for ActivityPrediction Kang Li; Jie Hu, State University of New York (SUNY) at Buffalo; YunFu*, SUNY at Buffalo
35 Object Co-detection Yinzge Bao*, U of Michigan at Ann Arbor; Yu Xiang, University ofMichigan; Silvio Savarese, The University of Michigan, Ann Arbor
41 What Do You Do: Occupation Recognition in a Photo Ming Shao*; Liangyue Li, SUNY at Buffalo; Yun Fu, SUNY at Buffalo
46 Shape and Material Under Natural Illumination Geoffrey Oxholm*, Drexel University; Ko Nishino, Drexel University
47 Efficient Discriminative Projections for Compact Binary Descriptors Tomasz Trzcinski*, EPFL; Vincent Lepetit 
57 Efficient Nonlocal Regularization for Optical Flow Philipp Krähenb¸hl*, Stanford University; Vladlen Koltun, StanfordUniversity
64 Morphable Displacement Field based Image Matching for Face RecognitionAcross Pose shaoxin Li*, ICT, CAS; xin Liu, Institute of Computing Chinese Academy ofScience; Xiujuan Chai, ICT,CAS; Haihong Zhang, Omron; Shihong Lao, Omron;Shiguang Shan, ICT, CAS
70 Frequency Analysis of Transient Light Transport with Applications in BareSensor Imaging Di Wu, MIT Media Lab; GordonWetzstein*, MIT Media Lab; Christopher Barsi, MIT Media Lab; ThomasWillwacher, Harvard University; Matthew O’Toole, University of Toronto;Nikhil Naik, MIT Media Lab; Qionghai Dai, Tsinghua University; KyrosKutulakos; Ramesh Raskar, MIT Media Lab
82 Descriptor Learning Revisited Karen Simonyan*, University of Oxford; Andrea Vedaldi, Oxford U; AndrewZisserman 
85 Reconstructing the World’s Museums Jianxiong Xiao*, MIT; Yasutaka Furukawa, Google
86 Online Learned Discriminative Part-Based Appearance Models forMulti-Human Tracking Bo Yang*, USC; Ram Nevatia 
87 A New Combinatorial Algorithm with Applications in Multi-Model Estimation Andrew Delong*, University of Western Ontario; Olga Veksler, Universityof Western Ontario; Yuri Boykov, University of Western Ontario
88 Segmentation with non-linear regional constraints via line-search cuts Lena Gorelick*, UWO; Frank Schmidt, ESIEE; Yuri Boykov, University ofWestern Ontario; Andrew Delong, University of Western Ontario; Aaron Ward,UWO
97 Hausdorff Distance Constraint for Multi-Surface Segmentation Frank Schmidt*, ESIEE; Yuri Boykov, University of Western Ontario
98 Background Subtraction using Group Sparsity and Low Rank constraint Xinyi Cui*, Rutgers University; Junzhou Huang; shaoting Zhang, RutgersUniversity; Dimitris Metaxas, Rutgers University
99 Exposure Stacks of Live Scenes with Hand-held Cameras Jun Hu, Duke University; Orazio Gallo*, NVIDIA, Corp.; Kari Pulli, NVIDIAResearch
100 Frequency-Space Decomposition and Acquisition of Light Transport underSpatially Varying Illumination Dikpal Reddy*, UC Berkeley; Ravi Ramamoorthi; Brian Curless 
107 Worldwide Pose Estimation Using 3D Point Cloud Models Yunpeng Li*, EPFL; Noah Snavely, Cornell University; Daniel Huttenlocher,; Pascal Fua, EPFL
108 Combining Per-Frame and Per-Track Cues for Multi-Person ActionRecognition Sameh Khamis*, University of Maryland; Vlad Morariu, University ofMaryland; Larry Davis, University of Maryland
111 A graph cut algorithm based on approximating the signed bi-form graph Alex Fix, Cornell; Joyce Chen, Cornell; Endre Boros, Rutgers; RaminZabih* 
113 Recursive Bilateral Filtering Qingxiong Yang*, City University of Hong Kong
115 Accelerated Large-Scale Optimization by Concomitant Hashing Yadong Mu*, Columbia University; John Wright, Columbia University;Shih-Fu Chang, Columbia
118 Graph Degree Linkage: Agglomerative Clustering on a Directed Graph Wei Zhang*, CUHK; Xiaogang Wang, The Chinese University of HK; Deli Zhao,CUHK; Xiaoou Tang 
120 Joint Image and Word Sense Discrimination For Image Retrieval Aurelien Lucchi*, EPFL; Jason Weston, google
122 Supervised Earth Mover’s Distance Learning and Its Computer VisionApplications Fan Wang*, Stanford University; Leonidas Guibas, Stanford University
127 Metric Learning for Large Scale Image Classification: Generalizing to NewClasses at Near-Zero Cost Thomas Mensink*, INRIA Rhone Alpes; Jakob Verbeek; Gabriela Csurka,XRCE; Florent Perronnin, XRCE
128 Knowledge-Oriented Sketch Segmentation Zhenbang Sun*, Shanghai Jiao Tong University; Changhu Wang, MicrosoftResearch Asia; Liqing Zhang, Shanghai Jiao Tong University; Lei Zhang, MSRA
135 Global Optimization of Object Pose and Motion from a Single RollingShutter Image with Automatic 2D-3D Matching Ludovic MAGERAND*, Clermont-UniversitÈ
136 Script Data for Attribute-based Recognition of Composite Activities Marcus Rohrbach*, MPI Informatics; Michaela Regneri, Saarland University;Mykhaylo Andriluka, MPI Informatik; Sikandar Amin, Max-Planck, TU Munich;Manfred Pinkal; Bernt Schiele 
141 Auto-grouped Sparse Representation for Visual Analysis Jiashi Feng*, NUS; Xiaotong Yuan; zilei Wang; Huan Xu; ShuichengYan 
145 Dual-force Metric Learning for Robust Distractor Resistant Tracker Zhibin Hong*, University of Technology, Sydn
149 Undoing the Damage of Dataset Bias Aditya Khosla*, MIT; Tinghui Zhou, CMU; Tomasz Malisiewicz, MIT; AlyoshaEfros, CMU; Antonio Torralba, MIT
150 Segmentation Propagation in ImageNet Daniel Kuettel*, ETH Zurich; Matthieu Guillaumin, ETH Z¸rich; VittorioFerrari 
151 Improved Reconstruction of Deforming Surfaces by Cancelling AmbientOcclusion Thabo Beeler, ETH; Derek Bradley*, Disney Research Zurich; HenningZimmer, ETH Zurich; Markus Gross, ETH Zurich
152 A Unified Framework for Multi-Target Tracking and Collective ActivityRecognition Wongun Choi*, The University of Michigan; Silvio Savarese, The Universityof Michigan, Ann Arbor
157 Dog Breed Classi?cation Using Part Localization Jiongxin Liu*, Columbia University; Angjoo Kanazawa; David Jacobs;Peter Belhumeur, Columbia University
158 On the statistical determination of optimal camera configurations inmulti-camera surveillance networks Junbin Liu*, QUT; Tim Wark, CSIRO; Sridha Sridharan, QueenslandUniversity of Technology
165 A Dictionary Learning Approach for Classification: Separating theParticularity and the Commonality Donghui Wang*, Zhejiang University; Shu Kong, Zhejiang University
175 Exact Acceleration of Linear Object Detectors Charles Dubout*, Idiap; François Fleuret, Idiap
180 Bottom-Up Perceptual Organization of Images into Object Part Hypotheses Maruthi Narayanan*, Brown University; Benjamin Kimia, Brown University
181 Learning Human Interaction by Interactive Phrases Yu Kong*, Beijing Institute of Technology; Yunde Jia, Beijing Inst. ofTech.; Yun Fu, SUNY at Buffalo
182 Structured Image Segmentation using Kernelized Features Aurelien Lucchi*, EPFL; Yunpeng Li, EPFL; Kevin Smith, EHTZ; Pascal Fua,EPFL
185 The Scale of Geometric Texture Geoffrey Oxholm*, Drexel University; Ko Nishino, Drexel University
187 Salient Object Detection: A Benchmark Ali Borji*, University of Southern Califor; Dicky Sihite, University ofSouthern California; Laurent Itti, University of Southern California
195 Multi-Task Order Preserving Sparse Coding For Time SequenceClassification Bingbing Ni*, ADSC; Shuicheng Yan; Pierre Moulin, UIUC
214 Shape Sharing for Object Segmentation Jaechul Kim*, University of Texas at Austin; Kristen Grauman 
217 Efficient Articulated Trajectory Reconstruction using Dynamic Programmingand Filters Jack Valmadre*, CSIRO; Yingying Zhu, Csiro; Sridha Sridharan, QueenslandUniversity of Technology; Simon Lucey, CSIRO
219 Nonuniform Lattice Regression for Modeling the Camera Imaging Pipeline Hai Ting Lin*, NUS; Zheng Lu, University of Texas At Austin; Seon JooKim, SUNY Korea; Michael S. Brown 
229 Background Inpainting for Videos with Dynamic Objects and a Free-movingCamera Miguel Granados*, MPI Informatik; Kwang In Kim, MPI for Informatics;James Tompkin, UCL; Jan Kautz, UCL; Christian Theobalt, MPI Informatik
230 Match Graph Construction for Large Image Databases Kwang In Kim*, MPI for Informatics; James Tompkin, University CollegeLondon; Martin Theobald; Jan Kautz, UCL; Christian Theobalt, MPI forInformatics
231 From Meaningful Contours to Discriminative Object Shape Pradeep krishna Yarlagadda*, University of Heidelberg; Bjorn Ommer 
236 Activity Forecasting Kris Kitani*, Carnegie Mellon University; James Bagnell; MartialHebert 
239 Context-Based Automatic Local Image Enhancement Sung Ju Hwang*, University of Texas, Austin; Ashish Kapoor, MicrosoftResearch; Sing Bing Kang, Microsoft Research
243 Statistics of Patch Offsets for Image Completion Kaiming He*, Microsoft Research Asia; Jian Sun, Microsoft Research Asia
245 Min-Space Integral Histogram SÈverine Dubuisson*, LIP6 – UPMC; Christophe Gonzales, LIP6 – UPMC
247 Automatic Segmentation of Unknown Objects, with Application to BaggageSecurity Leo Grady*, Siemens Corporate Research; Vivek Singh; Timo Kohlberger;Christopher Alvino; Claus Bahlmann 
254 Optimal Templates for Non-Rigid Surface Reconstruction Markus Moll*, K.U.Leuven; Luc Van Gool 
270 Heliometric Stereo: Shape from Sun Position Austin Abrams*, Washington University; Christopher Hawley; RobertPless, Washington University
273 Multi-channel Shape-Flow Kernel Descriptors for Robust Video EventDetection and Retrieval Pradeep Natarajan*, Raytheon BBNTechnologies; Shuang Wu, Raytheon BBN Technologies; Unsang Park, Raytheon BBNTechnologies; Shiv Vitaladevuni, Raytheon BBN Technologies; Rohit Prasad,Raytheon BBN Technologies, Inc; Premkumar Natarajan, Raytheon BBN Technologies,Inc  
275 A Particle Filter Framework for Contour Detection Nicolas Widynski*, University of Montreal; Max Mignotte, University ofMontreal
276 Action Recognition with Exemplar Based 2.5D Graph Matching Bangpeng Yao*, Stanford University; Li Fei-fei 
277 TriCoS: A Tri-level Class-Discriminative Co-Segmentation Method for ImageClassification Yuning Chai*, ETH Zurich; Esa Rahtu; Andrew Zisserman; VictorLempitsky; Luc Van Gool 
281 On Learning Higher-Order Consistency Potentials for Multi-class PixelLabeling Kyoungup Park*, ANU; Stephen Gould, ANU
286 Spectral Demons – Image Registration via Global Spectral Correspondence ée Lombaert*, Polytechnique; Leo Grady, Siemens Corporate Research;Xavier Pennec, INRIA Sophia-Antipolis; Nicholas Ayache, INRIASophia-Antipolis; Farida Cheriet, Polytechnique
287 Multi-view Discriminant Analysis Meina Kan*, ICT, GUCAS, China; Shiguang Shan, ICT, CAS; Haihong Zhang,Omron; Shihong Lao, Omron Company; xilin Chen 
290 Multi-scale Patch based Collaborative Representation for Face Recognitionwith Margin Distribution Optimization Pengfei Zhu, The Hong Kong PolyU; Lei Zhang*, The Hong Kong PolytechnicUniv; Qinghua Hu, Tianjin University; Simon Shiu, The Hong Kong PolyU
292 Learning to Recognize Daily Actions using Gaze Alireza Fathi*, Georgia Institute of Technolog; James Rehg, GeorgiaInstitute of Technology
296 Multi-Scale Clustering of Frame-to-Frame Correspondences for MotionSegmentation Ralf Dragon*, Leibniz Universität Hannover; Bodo Rosenhahn; JoernOstermann 
298 Learning Domain Knowledge for Facade Labelling Dengxin Dai*, ETH Zurich; Mukta Prasad, ETH Zurich; Gerhard Schmitt,ETHZ; Luc Van Gool 
301 Object detection using strongly-supervised deformable part models Hossein Azizpour, KTH; Ivan Laptev* 
313 Simultaneous Shape and Pose Adaption of Articulated Models using LinearOptimization Matthias Straka*, Graz University Of Technology; Stefan Hauswiesner, GrazUniversity of Technology; Matthias R¸ther, Graz University of Technology;Horst Bischof 
314 Efficient Misalignment-Robust Representation for Real-Time FaceRecognition Meng Yang, The Hong Kong Polytechnic Univ; Lei Zhang*, The Hong Kong Polytechnic Univ; David Zhang, The Hong Kong Polytechnic Univ
319 Monocular Object Detection using 3D Geometric Primitives Peter Carr*, Disney Research; Yaser Sheikh, CMU; Iain Matthews, DisneyResearch
321 Object-centric spatial pooling for image classification Olga Russakovsky*, Stanford University; Yuanqing Lin, NEC Laboratories America; Kai Yu, NEC Laboratories America; Li Fei-fei 
323 Efficient Spanning Structure Mining in Large Image Collections Yin Lou*, Cornell University; Noah Snavely, Cornell University; JohannesGehrke 
325 Sparse Coding and Dictionary Learning for Symmetric Positive DefiniteMatrices: A Kernel Approach Mehrtash Harandi*, National ICT Australia (NICTA); Conrad Sanderson,National ICT Australia (NICTA); Richard Hartley, National ICT Australia(NICTA); Brian Lovell, National ICT Australia (NICTA)
328 V1-Inspired Features Induce a Weighted Margin in SVMs Hilton Bristow*, CSIRO; Simon Lucey, CSIRO
329 Propagative Hough Voting for Human Activity Recognition Gang YU*, NTU; Junsong Yuan, NTU; Zicheng Liu, MSR
331 People Watching: Human Actions as a Cue for Single View Geometry David Fouhey*, Carnegie Mellon University; Vincent Delaitre; AlyoshaEfros, CMU; Abhinav Gupta; Ivan Laptev; Josef Sivic, INRIA / EcoleNormale Superieure
335 Renormalization Returns: Hyper-renormalization and Its Applications Kenichi Kanatani*, Okayama University; Ali Al-Sharadqah, University ofMississippi; Nikolai Chernov, University of Alabama at Birmingham; YasuyukiSugaya, Toyohashi University of Technology
344 Real-time Compressive Tracking Kaihua Zhang, The HK PolyU; Lei Zhang*, The Hong Kong Polytechnic Univ;Ming-Hsuan Yang, University of California at Merced
351 Shape from Single Scattering for Translucent Objects Chika Inoshita*, Osaka University; Yasuhiro Mukaigawa, Osaka University;Yasu Matsushita; Yasushi Yagi, Osaka University
352 Joint Face Alignment: Rescue Bad Alignments with Good Ones by RegularizedRe-fitting Xiaowei Zhao*, ICT,CAS,China; Xiujuan Chai, ICT,CAS; Shiguang Shan, ICT,CAS
354 Depth Extraction from Video Using Non-parametric Sampling Kevin Karsch*, UIUC; Ce Liu, Microsoft Research New England; Sing BingKang, Microsoft Research
356 Scale Invariant Optical Flow Li Xu*, CUHK; Zhenlong Dai, CUHK; jiaya Jia, CUHK
359 Learning Class-to-Image Distance via Large Margin and L1-normRegularization Zhengxiang Wang*, NanyangTechnologicalUniversity; Shenghua Gao;Liang-Tien Chia 
361 Taxonomic Multi-class Prediction and Person Layout using EfficientStructured Ranking Arpit Mittal*, University of Oxford; Matthew Blaschko, …cole CentraleParis; Andrew Zisserman; Phil Torr 
362 Unsupervised Discovery of Mid-Level Discriminative Patches Saurabh Singh*, Carnegie Mellon University; Abhinav Gupta; AlyoshaEfros, CMU
363 Self-Similar Sketch Andrea Vedaldi*, Oxford U; Andrew Zisserman 
367 Blind Correction of Optical Aberrations Christian Schuler*, MPI for Intelligent Systems; Michael Hirsch, MPI forIntelligent Systems; Stefan Harmeling, MPI for Intelligent Systems; BernhardSchˆlkopf, MPI for Intelligent Systems
370 Depth Matters: Influence of Depth Cues on Visual Saliency Lang Congyan, Beijijng Jiaotong University; Tam Nguyen*, NUS, Singapore;harish Katti, National University of Singapore; Karthik Yadati, NationalUniversity of Singapore; Shuicheng Yan; Mohan Kankanhalli, NationalUniversity of Singapore
375 Gait Recognition by Ranking Ra˙l MartÌn FÈlez*, Universitat Jaume I; Tao  Xiang, Queen Mary University of London
376 Robust Point Matching Revisited: A Concave Optimization Approach Wei Lian, Changzhi Univ; Lei Zhang*, The Hong Kong Polytechnic Univ
380 Quaternion-based Spectral Saliency Detection for Human Eye Fixation PointPrediction Boris Schauerte*, Karlsruhe Inst. Tech.; Rainer Stiefelhagen, KarlsruheInst. of Technology
383 Learning Discriminative Spatial Relations for Detector Dictionaries:  an Application to Pedestrian Detection Enver Sangineto*, Istituto Italiano di Tecnologi; Marco Cristani;Alessio Del Bue; Vittorio Murino 
385 Learning Deformations with Parallel Transport Donglai Wei*, Mit; Dahua Lin, MIT; John Fisher III, MIT
387 Dynamic Facial Expression Recognition using Longitudinal FacialExpression Atlases Yimo Guo*, Oulu University; Guoying Zhao, Oulu University; MattiPietikäinen, Oulu University
391 Polynomial Regression on Riemannian Manifolds Jacob Hinkle*, University of Utah; Prasanna Muralidharan, University ofUtah; P Thomas Fletcher, University of Utah; Sarang Joshi, University of Utah
398 Crosstalk Cascades for Frame-Rate Pedestrian Detection Piotr Dollar*, Microsoft Research; Ron Appel, Caltech; Wolf Kienzle,Microsoft Research
400 Query Specific Fusion for Image Retrieval shaoting Zhang, Rutgers University; Ming Yang*, NEC laboratories America;Timothee Cour, NEC Laboratories America; Kai Yu, NEC Laboratories Amertica;Dimitris Metaxas, Rutgers University
401 Approximate Gaussian Mixtures for Large Scale Vocabularies Yannis Avrithis*, NTUA; Yannis Kalantidis, NTUA
403 Tracking Using Motion Patterns for Very Crowded Scenes Xuemei Zhao*, Univ. of Southern California; Dian Gong, Univ. of SouthernCalifornia; Gerard Medioni, University of Southern California
405 Constrained Bootstrapping for Image Classi?cation via Attributes andComparative Attributes Abhinav Shrivastava*, Carnegie Mellon University; Saurabh Singh, CarnegieMellon University; Abhinav Gupta 
415 Long-Range Spatio-Temporal Modeling with Application to Fire Detection Avinash Ravichandran*, UCLA; Stefano Soatto, UCLA
419 Geodesic Saliency Using Background Priors Yichen Wei*, Microsoft Research; Fang Wen; Wangjiang Zhu, TsinghuaUniversity; Jian Sun, Microsoft Research Asia
420 Human Actions as Stochastic Kronecker Graphs Sinisa Todorovic*, Oregon State University
422 GMCP-Tracker: Global Multi-object Tracking Using Generalized MinimumClique Graphs Amir Roshan Zamir*, UCF; Afshin Dehghan, University of Central Florida
429 Robust Fitting for Multiple View Geometry Olof Enqvist*, Lund University; Erik Ask, Lund University; Fredrik Kahl,Lund University; Kalle ≈strˆm, Lund University
431 Improving Image-Based Localization by Active Correspondence Search Torsten Sattler*, RWTH Aachen University; Bastian Leibe, RWTH AachenUniversity; Leif Kobbelt, RWTH Aachen University
432 Nested Sparse Quantization for Efficient Feature Coding Gemma Roig Noguera, ETH; Xavier Boix*, ETH; Christian Leistner; Luc VanGool 
433 Inverse Rendering of Faces on a Cloudy Day Oswald Aldrian*, University of York; William A. P. Smith, University ofYork
438 On Tensor-Based PDEs and their Corresponding Variational Formulationswith Application to Color Image Denoising Freddie Åström*, Linköping University; George Baravdish, Linköping University; Michael Felsberg, Linköping University  
439 Size Matters: Exhaustive Geometric Verification for Image Retrieval  Henrik Stewenius*, Google; Steinar Gunderson, Google; Julien Pilet,Google
440 "Clustering by Composition" for Unsupervised Discovery of ImageCategories Alon Faktor*, Weizmann Institute of Science; Michal Irani 
446 Joint Face Alignment with Non-Parametric Shape Models Brandon Smith*, Univ. of Wisconsin – Madison; Li Zhang, Univ. ofWisconsin – Madison
451 Kernelized Temporal Cut for Online Hierarchical Human Action Segmentationand Recognition Dian Gong*, Univ. of Southern California; Gerard Medioni, University ofSouthern California; Sikai Zhu, University of Southern California; XuemeiZhao, Univ. of Southern California
456 Scene Aligned Pooling for Complex Video Recognition Liangliang Cao*, IBM Research; Yadong Mu, Columbia University;Apostol  Natsev, Google; Shih-FuChang, Columbia; Gang Hua, Stevens Institute of Technolog; John Smith, IBM
460 Comparative Evaluation of Binary Features Jared Heinly*, UNC Chapel Hill; Enrique Dunn, UNC; Jan-Michael Frahm,UNC-CH
462 Group Tracking: Exploring Mutual Relations for Multiple Object Tracking Genquan Duan*, Tsinghua University; Song Cao, Tsinghua University;Haizhou Ai, Tsinghua University; Shihong Lao, Omron Company
464 Discovering Latent Domains for Multisource Domain Adaptation Judy Hoffman*, UC Berkeley; Kate Saenko, UC Berkeley, Harvard, ICSI;Brian Kulis, Ohio State; Trevor Darrell, UC Berkeley, ICSI
476 Grain Segmentation of 3D Superalloy Images Using MultiChannel EWCVT underHuman Annotation Constraints Yu Cao*, University of South Carolina; Lili Ju, University of SouthCarolina; Song Wang, University of South Carolina
493 A Discrete Chain Graph Model for 3d+t Cell Tracking with HighMisdetection Robustness Bernhard Kausler*, University ofHeidelberg; Martin Schiegg, University of Heidelberg; Bjoern Andres, HarvardUniversity; Martin Lindner, University of Heidelberg; Heike Leitte,University of Heidelberg; Lars Hufnagel, European Molecular Biology Laboratory;Ullrich Koethe, University of Heidelberg, Germany; Fred Hamprecht, Universityof Heidelberg, Germany
498 Image Enhancement using Calibrated Lens Simulations YiChang Shih*, M.I.T.; Neel Joshi, Microsoft Research; Brian Guenter,Microsoft Research
502 Hough Regions for Joining Instance Localization and Segmentation Hayko Riemenschneider*, Graz University of Technology; Sabine Sternig,Graz University of Technology; Michael Donoser, Graz University ofTechnology; Peter Roth, Graz University of Technology; Horst Bischof 
507 Exploiting Color in Shape, Albedo, and Illumination from Shading Jonathan Barron*, UC Berkeley; Jitendra Malik, UC Berkeley
508 Discriminative Bayesian Active Shape Models Pedro Martins*, ISR; Jo„o F Henriques, ISR; Rui Caseiro, InstituteSystems Robotics; Jorge Batista, Institute Systems Robotics – UniversityCoimbra – Portugal
513 Patch Based Synthesis for Single Depth Image Super-Resolution Oisin Mac Aodha*, UCL; Neill Campbell; Arun Nair; GabrielBrostow 
516 Facial Action Transfer with Personalized Bilinear Regression Dong Huang*, Carnegie Mellon University; Fernando De la Torre, CarnegieMellon University
520 A Fast Illumination and Deformation Insensitive Image ComparisonAlgorithm Using Wavelet-Based Geodesics Anne Jorstad*, University of Maryland, CP; David Jacobs 
526 Point of Gaze Estimation through Corneal Surface Reflection in an ActiveIllumination Environment Atsushi Nakazawa*, Osaka University, Cybermedia Center; ChristianNitschke, Osaka University, Cybermedia C
527 Manifold Statistics for Essential Matrices Gijs Dubbelman*, CMU
534 Robust Tracking with Weighted Online Structured Learning Rui Yao*, NWPU; Qinfeng Shi, University of Adelaide; Chunhua Shen,University of Adelaide; Yanning Zhang, Northwestern Polytechnical Univ.;Anton van den hengel, University of Adelaide
535 Annotation Propagation in Large Image Databases via Dense ImageCorrespondence Michael Rubinstein*, MIT; Ce Liu, Microsoft Research New England; WilliamFreeman, Massachusetts Institute of Technology 
560 Covariance Propagation and Next Best View Planning for 3D Reconstruction Sebastian Haner*, Lund University; Anders Heyden, Lund University
574 Dilated Divergence based Scale-Space Representation for Curve Analysis Max W.K. Law*, GE Healthcare; Andrew Leung, Western University; Keng-YeowTay, Western University; Shuo Li, GE Healthcare
576 Parameterless Line Segment and Elliptical Arc Detector with ControlledNumber of False Positives Viorica Patraucean*, University of Toulouse; Pierre Gurdjos; RafaelGrompone von Gioi; GÈraldine Morin, University of Toulouse
579 Learning to segment a video to clips based on scene and camera motion Adarsh Kowdle*, Cornell University; Tsuhan Chen, Cornell University
582 Numerically Stable Optimization of Polynomial Solvers for MinimalProblems Yubin Kuang*, Lund University; Kalle ≈strˆm, Lund University
593 Has my algorithm succeeded? Evaluating human pose estimators Nataraj Jammalamadaka*, IIIT, Hyderabad; Andrew Zisserman; MarcinEichner, ETH zurich; Vittorio Ferrari; Jawahar C. V. , IIIT, Hyderabad
598 Full Body Performance Capture under Uncontrolled and VaryingIllumination: A Shading-based Approach Chenglei Wu*, Max Planck Institut Informatik; Kiran Varanasi, MPIInformatik; Christian Theobalt, MPI for Informatics
601 Visual Recognition using Local Quantized Patterns Sibt ul Hussain*, UniversitÈ de Caen; Bill Triggs, Laboratoire JeanKuntzmann
602 Detecting and Reconstructing 3D Mirror Symmetric Objects Rick Szeliski*; Krishnan Ramnath, Microsoft Research; Sudipta Sinha,Microsoft Research; Sudipta Sinha 
607 3D Reconstruction of Dynamic Scenes with Multiple Handheld Cameras Hanqing Jiang, Zhejiang University; Haomin Liu, Zhejiang University; PingTan, National University of Singapore; Guofeng Zhang*, Zhejiang University;Hujun Bao, Zhejiang University
616 Globally Optimal Closed-surface Segmentation for Connectomics Bjoern Andres*, Harvard University;Thorben Kroeger, HCI, University of Heidelberg; Kevin Briggman, NIH; WinfriedDenk, Max-Planck-Institute for Medical Research; Natalya Korogod, EPFL;Graham Knott, EPFL; Ullrich Koethe, University of Heidelberg, Germany; FredHamprecht, University of Heidelberg, Germany
619 Performance Capture of Interacting Characters with Handheld Kinects Genzhi Ye*, Tsinghua University; Yebin Liu, Tsinghua University; NilsHasler, Max-Planck-Institute for Informatics; Xiangyang Ji, TsinghuaUniversity; Qionghai Dai, Tsinghua University; Christian Theobalt, MPI forInformatics
620 Reduced Analytical Dependency Modeling for Classifier Fusion Andy Jinhua Ma, Hong Kong Baptist University; Pong Yuen*, Hong KongBaptist University
626 Randomized Spatial Partition for Scene Recognition Yuning Jiang*, NTU; Junsong Yuan, NTU; Gang YU, NTU
633 Evaluation of Image Segmentation Quality by Adaptive Ground TruthComposition Bo Peng, The Hong Kong Polytechnic University; Lei Zhang*, The Hong KongPolytechnic Univ
634 Ensemble Partitioning for Unsupervised Image Categorization Dengxin Dai*, ETH Zurich; Mukta Prasad, ETH Zurich; Christian Leistner;Luc Van Gool; Gerhard Schmitt, ETHZ
642 Set Based Discriminative Ranking for Recognition Yang Wu*, Kyoto University; Michihiko Minoh, Kyoto University; MasayukiMukunoki, Kyoto University; Shihong Lao, Omron Company
643 A Global Hypotheses Verification Method for 3D Object Recognition Aitor Aldoma*, TU Wien; Federico Tombari, University of Bologna; Luigi DiStefano; Markus Vincze, TU Wien
653 Learning to Match Appearances by Correlations in a Covariance MetricSpace Slawomir Bak*, INRIA; Guillaume Charpiat, INRIA; Etienne Corvee, INRIA;Francois Bremond, INRIA; Monique Thonnat, INRIA
654 Scale Robust Multi View Stereo Christian Bailer; Manuel Finckh*, Tuebingen University; Hendrik Lensch,Tuebingen University
655 Fast Regularization of Matrix-Valued Images Guy Rosman*, Technion; Yu Wang; Xue-Cheng Tai, University of Bergen;Ron Kimmel, Technion; Alfred Bruckstein, Technion
656 Tracking feature points in uncalibrated images with radial distortion Miguel  LourenÁo*,ISR-Coimbra; Jo„o Pedro Barreto, ISR
660 Laplacian Meshes for Monocular 3D Shape Recovery Jonas ÷stlund*, CVLab, EPFL, Lausanne; Aydin Varol, EPFL; Pascal Fua,EPFL
673 On the Convergence of Graph Matching: Graduated Assignment Revisited Yu Tian; Junchi Yan*, Shanghai Jiao Tong University; Hequan Zhang,Beijing Institute of Technology
675 Divergence-free motion estimation Dominque BÈrÈziat*, UPMC; Isabelle Herlin, INRIA; Nicolas Mercier, INRIA;Sergiy Zhuk, CWI
677 Negative evidences and co-occurences in image retrieval: the benefit ofPCA and whitening éÈ JÈgou*, INRIA; Ondrej Chum, CVUT
681 Large-Scale Gaussian Process Classification with Flexible AdaptiveHistogram Kernels Erik Rodner*, University of Jena; Alexander L¸tz; Paul Bodesheim,University of Jena, Germany; Joachim Denzler 
683 Visual Tracking via Adaptive Tracker Selection with Multiple Features Ju Hong Yoon*, GIST; Du Yong Kim, Gwangju Institute of Science andTechnology; Kuk-Jin Yoon, GIST
684 Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles Hamdi Dibeklioglu*, University of Amsterdam; Theo Gevers, UvA; AlbertSalah, Bogazici University
689 Background Subtraction with Dirichlet Processes Tom Haines*, Queen Mary, Uni. of London; Tao  Xiang, Queen Mary University of London
691 Soft inextensibility constraints for template-free non-rigidreconstruction Sara Vicente*, Queen Mary University of Londo; Lourdes Agapito, QueenMary University of Londo
692 Image Annotation Using Metric Learning in Semantic Neighbourhoods Yashaswi Verma*, IIIT, Hyderabad; Jawahar C. V. , IIIT, Hyderabad
694 Movies and Sports: Large-Scale Dynamic Human Eye  Movement Datasets and ConsistencyStudies for Visual Action Recognition Stefan Mathe*, Romanian Academy of Science; Cristian Sminchisescu,University of Bonn
695 Efficient Monte Carlo sampler for detecting parametric objects in largescenes Yannick VerdiÈ, INRIA; Florent Lafarge*, INRIA
698 Exploiting the Circulant Structure of Tracking-by-detection Jo„o F Henriques*, ISR; Rui Caseiro, Institute Systems Robotics; PedroMartins, ISR; Jorge Batista, Institute Systems Robotics – University Coimbra- Portugal
702 Weighted $\alpha$-Shapes for Local Feature Detection Christos Varytimidis*, NTUA; Konstantinos Rapantzikos, NTUA; YannisAvrithis, NTUA
708 Detecting and Localizing Activities at Different Scales under Budget Mohamed Amer*, Oregon State University; Dan Xie, UCLA; Mingtian Zhao ,UCLA; Yaofei Feng, OREGON STATE UNIVERSITY; Behrooz Mahasseni, OREGON STATEUNIVERSITY; Sinisa Todorovic, Oregon State University; Song-Chun Zhu, UCLA
711 Dynamic programming for Expansion Algorithm Olga Veksler*, University of Western Ontario
713 Sparselet Models for Efficient Multiclass Object Detection Hyun Oh Song*, UC Berkeley; Stefan Zickler, IRobot Corp.; Tim Althoff, UCBerkeley; Ross Girshick, University of Chicago; Christopher Geyer, IRobotCorporation; Mario Fritz, MPI Informatik; Pedro Felzenszwalb, BrownUniversity; Trevor Darrell, UC Berkeley, ICSI
721 Mobile Product Image Search by Automatic Query Object Extraction Xiaohui Shen*, Northwestern University; Zhe Lin, Adobe; Jonathan Brandt,Adobe Systems; Ying Wu, Northwestern University
723 Fast Tiered Labeling with Topological Priors Ying Zheng, Duke University, Computer Science; Steve Gu*, DukeUniversity, Computer Scie; Carlo Tomasi 
724 Nested Pictorial Structures Steve Gu*, Duke University, Computer Scie; Ying Zheng, Duke University,Computer Science; Carlo Tomasi 
727 Describing Clothing by Semantic Attributes Huizhong Chen*, Stanford University; andrew Gallagher, Eastman Kodak;Bernd Girod, Stanford University
739 Analyzing the Subspace Structure of Related Images: ConcurrentSegmentation of Image Sets Lopamudra Mukherjee*, University of Wisc Whitewater; Vikas Singh,University of Wisconsin Madison
752 Graph Matching via Sequential Monte Carlo Yumin Suh, Seoul National University; Minsu Cho, Seoul NationalUniversity; Kyoung Mu Lee*, Seoul National University
756 Artistic image classification: an analysis on the ART database Gustavo Carneiro*, The University of Adelaide; Nuno Pinho da Silva,ISR@IST-UTL; Alessio Del Bue; Joao Costeira, Instituto Superior Tecnico
759 Supervised Geodesic Propagation for Semantic Label Transfer Xiaowu Chen, Beihang University; Qing Li*, Beihang University; YafeiSong, Beihang University; Xin Jin, Beihang; Qinping Zhao, Beihang University
760 Bayesian Face Revisited: A Joint Formulation Dong Chen*, University of Science and Technology of China; Xudong Cao,MSRA; Liwei Wang, The Chinese University of Hong Kong; Fang Wen; Jian Sun,Microsoft Research Asia
763 Coherent Filtering: Detecting Coherent Motions from Clutters Bolei Zhou*, The Chinese University of HK; Xiaogang Wang, The ChineseUniversity of HK; Xiaoou Tang 
774 Beyond Bounding Boxes: Learning Object-Form by Model-driven Grouping Juan Antonio  Monroy*, IWR,University of Heidelberg; Bjorn Ommer 
776 Supervised Assessment of Segmentation Hierarchies Jordi Pont-Tuset*, UPC; Ferran Marques, Universitat PolitËcnica deCatalunya
780 TreeCANN – k-d tree Coherence Approximate Nearest Neighbor algorithm Igor Olonetsky*, Tel Aviv University; Shai Avidan 
785 Jet-Based Local Image Descriptors Anders Boesen Lindbo Larsen*, University of Copenhagen; Sune Darkner,diku.dk; Anders Dahl, dtu.dk; Kim Pedersen, diku.dk
789 Automatic Exposure Correction of Consumer Photographs Lu Yuan*, Microsoft Research Asia; Jian Sun, Microsoft Research Asia
794 Robust Regression Dong Huang*, Carnegie Mellon University; Ricardo  Cabral , Carnegie Mellon University;Fernando De la Torre, Carnegie Mellon University
804 Image Guided Tone Mapping with Locally Nonlinear Model Image Guided ToneMapping with Locally Nonlinear Model Image Guided Tone Mapping with Locally Nonlinear Model  Huxiang Gu*, CASIA; Ying Wang, NLPR; Shiming Xiang, NLPR; Gaofeng MENG,Chinese Academy of Science; Chunhong Pan, NLPR
810 Domain Adaptive Dictionary Learning Qiang Qiu*, Univ. of Maryland College Park; Vishal Patel, UMIACS; PavanTuraga, University of Arizona State; Rama Chellappa, Univ. of Maryland,College Park
811 Latent Hough Transform for Object Detection Nima Razavi*, ETH Zurich; Juergen Gall, ETH Zurich; Pushmeet Kohli; LucVan Gool 
815 Canonical Scene based Contextual Model for Abnormal Object Detection Sangdon Park; Wonsik Kim, Seoul National University; Kyoung Mu Lee*,Seoul National University
816 Robust 3D Action Recognition with Random Occupancy Patterns Jiang Wang*, Northwestern University; Zicheng Liu, MSR; Jan Chorowski,University of Louisville; Zhuoyuan Chen, Northwestern University; Ying Wu,Northwestern University
818 Shapecollage: occlusion-aware, example-based shape interpretation Forrester Cole*, MIT; Phillip Isola, MIT; Edward Adelson, MIT; WilliamFreeman, Massachusetts Institute of Technology ; Fredo Durand, MIT
825 A new image database for Image Quality Assessment Javier Silvestre-Blanes*, UPV; Ian Van Der Linde, ARU; RubÈnPÈrez-LlorÈns, UPV
826 Image Labeling on a Network:\\Using Social-Network Metadata for ImageClassification Julian McAuley*, Stanford; Jure Leskovec, Stanford
832 Spatio-Temporal Phrases for Activity Recognition Yimeng Zhang*, Cornell University; Xiaoming Liu, Ge Global Research;Ming-Ching Chang, Ge Global Research; Weina Ge, Ge Global Research; TsuhanChen, Cornell University
836 Spatial and Angular Variational Super-resolution of 4D Light Fields Sven Wanner, HCI; Bastian Goldluecke*, HCI
841 Blur-Kernel Estimation from Spectral Irregularities Amit Goldstein, Hebrew University of Jerusalem; Raanan Fattal*, HebrewUniversity of Jerusalem
845 A Robust and Efficient Doubly Regularized Metric Learning Approach Meizhu Liu*, Siemens Corporate Research; Baba Vemuri, University ofFlorida
848 Towards a Polynomial Time Algorithm for Triangulation Chris Aholt*, University of Washington; Sameer Agarwal, Google; RekhaThomas, University of Washington
850 Interactive Facial Feature Localization Vuong Le*, University of Illinois; Jonathan Brandt, Adobe Systems;Lubomir Bourdev  Adobe SystemsInc.; Zhe Lin, Adobe; Thomas Huang, UIUC
851 Segmentation Based Particle Filtering for Real-Time 2D Object Tracking Vasileios Belagiannis*, Technische Universität München; Falk Schubert,EADS Innovation Works; Nassir Navab, Technische Universität München; SlobodanIlic, TUM
852 Deconvolving PSFs for A Better Motion Deblurring using Multiple Images Xiang Zhu*, UC Santa Cruz; Filip Sroubek, UTIA, Academy of Sciences ofCR; Peyman Milanfar, UC Santa Cruz
854 A Discriminative Data-dependent Mixture-Model Approach for MultipleInstance Learning in Image Classification Qifan Wang*, Purdue University; Luo Si, Purdue; Dan Zhang, Purdue
855 Multi-Component Models for Object Detection Chunhui Gu*, UC Berkeley; Pablo Arbelaez, UC Berkeley; Yuanqing Lin, NECLaboratories Amertica; Kai Yu, NEC Laboratories Amertica; Jitendra Malik, UCBerkeley
856 Discriminative Decorrelation for Clustering and Classification Bharath Hariharan*, UC Berkeley; Jitendra Malik, UC Berkeley; DevaRamanan 
859 Spatiotemporal Descriptor for Wide-Baseline Stereo Reconstruction ofNon-Rigid and Ambiguous Scenes Eduard Trulls Fortuny*, Institut de RobÚtica (IRI); Alberto Sanfeliu,IRI; Francesc Moreno-Noguer, Institut de RobÚtica i Inform‡tica Industrial(IRI)
866 Recognizing Actions, Poses, and Objects with Relational Phraselets Chaitanya Desai*, University of California Irvine; Deva Ramanan 
870 No Bias Left Behind: Covariate Shift Adaptation for Discriminative 3DPose Estimation Makoto Yamada*, Tokyo Institute of Technology; Leonid Sigal, DisneyResearch Pittsburgh; Michalis Raptis, Disney Research Pittsburgh
877 Surface Elevation Angle Estimation from Reflectance Monotonicity Boxin Shi*, The University of Tokyo; Ping Tan, National University ofSingapore; Yasu Matsushita; Katsushi Ikeuchi 
880 Generic Cuts: An Efficient Optimal Algorithm for Submodular MRF-MAPProblems with Higher Order Cliques Chetan Arora*, IIT Delhi; Subhashis Banerjee, IIT Delhi; Prem Kalra, IITDelhi; S.N. Maheshwari, IIT Delhi
886 Complex Events Detection using Data-driven Concepts Yang Yang*, UCF
895 Directional Space-Time Oriented Gradients for 3D Pattern Analysis Ehsan Norouznezhad*, NICTA, UQ; Mehrtash Harandi, National ICT Australia(NICTA); Abbas Bigdeli, NICTA, UQ; Mahsa Baktash, NICTA, UQ; Adam Postula,UQ; Brian Lovell, National ICT Australia (NICTA)
900 Learning to Recognize Unsuccessful Activities in Depth Videos Using aTwo-Layer Latent Structural Model Qiang Zhou*, ADSC,Singapore; Gang Wang, Nanyang Technological U
916 Action Recognition Using Subtensor Constraint Qiguang Liu, Tianjin University; Xiaochun Cao* 
920 In Defence of Negative Mining for Annotating Weakly Labeled Data Parthipan Siva*, Queen Mary University of Londo; Tao  Xiang, Queen Mary University ofLondon; Chris Russell, Queen Mary, University of Lond
921 Beyond Spatial Pyramids: A New Feature Extraction Framework with DenseSpatial Sampling for Image Classification Shengye Yan*, Nanyang technological universi; Xinxing Xu, NanyangTechnological University; Dong Xu; Steve Lin 
923 Reading Ancient Coins: Automatically Identifying Denarii using ObverseLegend Seeded Retrieval Ognjen Arandjelovic*, Swansea University
927 Depth and Deblurring from a Spectrally-varying Depth-of-Field Ayan Chakrabarti*, Harvard University; Todd Zickler 
933 Labeling Images by Integrating Sparse Multiple Distance Learning andSemantic Context Modeling Chuanjun Ji*, Fudan University, China; Xiangdong Zhou, Fudan University,China
935 PatchMatchGraph: Building a Graph of Dense Patch Correspondences forLabel Transfer Stephen Gould*, ANU; Yuhang Zhang, ANU
936 Online Video Segmentation by Bayesian Split-Merge Clustering Juho Lee*, POSTECH; Suha Kwak, POSTECH; Bohyung Han, POSTECH; SeungjinChoi, POSTECH
937 Joint Classification-Regression Forests for Spatially StructuredMulti-Object Segmentation Ben Glocker*, Microsoft Research Cambridge; Olivier Pauly, TechnischeUniversitaet Muenchen; Ender Konukoglu, Microsoft Research Cambridge; AntonioCriminisi, Microsoft Research Cambridge
938 Robust and Practical Face Recognition via Structured Sparsity Kui Jia*, Adv. Digital Sciences Center; Tsung-Han  Chan, ADSC, Singapore; Yi Ma 
942 Segmentation over Detection by Coupled Global and Local SparseRepresentations Wei Xia*, NUS; Zheng Song, NUS; Jiashi Feng, NUS; Loong Fah Cheong, NUS;Shuicheng Yan 
944 Subspace Learning in Krein Spaces: Complete Kernel Fisher Discriminantwith Indefinite Kernels Stefanos Zafeiriou*, Imperial College London
947 Online Spatio-Temporal Structural Context Learning for Visual Tracking inUnconstrained Environments Longyin Wen*, CBSR.CASIA; Zhaowei Cai, CBSR.CASIA; Zhen Lei, CBSR.CASIA;Dong Yi, CASIA; Stan Z. Li, CASIA, China
953 Automatic tracking a large number of moving targets in 3D Ye Liu*, Fudan University; Hui Li; Yan Qiu Chen 
959 A Three-Layered Approach to Facade Parsing Andelo Martinovic*, KU Leuven; Markus Mathias, KU Leuven; JulienWeissenberg, ETHZ; Luc Van Gool, KU Leuven
961 A Novel Material-aware Feature Descriptor for Volumetric ImageRegistration in Diffusion Tensor Space Shuai Li*, Beihang University, China; Qinping Zhao, Beihang University;shengfa Wang, Stony Brook University; Tingbo Hou, Stony Brook University;Aimin Hao, Beihang University; Hong Qin, Stony Brook University
962 A Unifying Theory of Active Discovery and Learning Timothy Hospedales*, Queen Mary University, London; Shaogang Gong, QueenMary University, London; Tao Xiang, Queen Mary University of London
971 Moving Object Segmentation Using Motor Signals Jingen Liu*, SRI International Sarnoff
976 Block-sparse RPCA for Consistent Foreground Detection Zhi Gao*, National unviersity of singapo
977 Attribute Learning for Understanding Unstructured Social Activity Yanwei Fu*, EECS, QMUL; Timothy Hospedales, Queen Mary University,London; Tao  Xiang, Queen MaryUniversity of London; Shaogang Gong, Queen Mary University, London
981 Multiple View Object Cosegmentation using Appearance and Stereo Cues Adarsh Kowdle*, Cornell University; Sudipta Sinha; Rick Szeliski 
982 Extracting 3D Scene-consistent Object Proposals and Depth from StereoImages Michael Bleyer, Vienna Univerity of Technology; Christoph Rhemann*,Vienna University of Technolog; Carsten Rother 
995 Efficient Closed-Form Solution to Generalized Boundary Detection Marius Leordeanu*, IMAR; Rahul Sukthankar, Google Research and CMU;Cristian Sminchisescu, University of Bonn
999 Recognizing Materials by Transfering Appearance from Virtual to RealExamples Mario Fritz*, MPI Informatik; Wenbin Li, MPI Informatics
1000 Local Log-Euclidean Covariance Matrix (L$^{2}$ECM) for ImageRepresentation and Its Applications Peihua Li*, Heilongjiang University; Qilong Wang 
1001 Scene Recognition on the Semantic Manifold Roland Kwitt*, Kitware Inc.; Nuno Vasconcelos, University of Californiaat San Diego; Nikhil Rasiwasia, Yahoo Research
1006 Repairing Sparse Low-Rank Texture Xiao Liang*, Tsinghua University; Xiang Ren, Microsoft Research Asia;Zhengdong Zhang, Microsoft Research Asia; Yi Ma 
1010 Statistical Inference of Motion in the Invisible Haroon Idrees*, UCF; Imran Saleemi, UCF; Mubarak Shah, UCF
1024 Using linking features in learning non-parametric part models Leonid Karlinsky*, Weizmann Institute of Science; Shimon Ullman, WeizmannInstitute of Science
1030 Unsupervised Temporal Commonality Discovery Wen-Sheng Chu*, Carnegie Mellon University; Feng Zhou, Carnegie MellonUniversity; Fernando De la Torre, Carnegie Mellon University
1032 Finding People Using Scale, Rotation and Articulation Invariant Matching Hao Jiang*, Boston College
1033 A Generative Model for Simultaneous Estimation of Human Body Shape andPixel-level Segmentation Ingmar Rauschert*, Penn State; Robert Collins, Penn State
1034 Camera Pose Estimation Using First-Order Curve Differential Geometry Ricardo Fabbri*, Brown University; Benjamin Kimia, Brown University
1035 Patch Complexity, Finite Pixel Correlations and Optimal Denoising Anat Levin*, Weizmann Institute; Boaz Nadler, Weizmann Inst; FredoDurand, MIT; William Freeman, Massachusetts Institute of Technology 
1038 Measuring Image Distances via Embedding in a Semantic Manifold Chen Fang, Dartmouth College; Lorenzo Torresani*, Dartmouth
1041 Efficient Point-to-Subspace Query in L1 with Application to Robust FaceRecognition Ju Sun*, Columbia University; Yuqian Zhang; John Wright, ColumbiaUniversity
1043 Unsupervised and Supervised Visual Codes with Restricted BoltzmannMachines Hanlin Goh*, UniversitÈ Pierre et Marie Curie; Nicolas Thome, UniversitÈPierre et Marie Curie; Matthieu Cord, UniversitÈ Pierre et Marie Curie;Joo-Hwee Lim, Institute for Infocomm Research
1049 Towards Optimal Non-rigid Surface Tracking Martin Klaudiny*, University of Surrey; Adrian Hilton, University ofSurrey
1050 Beyond Feature Points: Structured Prediction for Monocular Non-rigid 3DReconstruction Mathieu Salzmann*, NICTA; Raquel Urtasun, TTIC
1051 Filter-based Mean-Field Inference for Random Fields with Higher OrderTerms and Product Label-Spaces Jonathan Warrell*, Oxford Brookes University; Phil Torr; Vibhav Vineet,Oxford Brookes University
1052 A new biologically inspired color- and shape-based image descriptor Jun Zhang, Brown University; Youssef Barhomi, Brown University; ThomasSerre*, Brown University
1057 Going With the Flow: Pedestrian Efficiency in Crowded Scenes Louis Kratz*, Drexel University; Ko Nishino, Drexel University
1061 Learning Spatially-Smooth Mappings in Non-Rigid Structure from Motion Onur Hamsici, Qualcomm; Paulo Gotardo*, The Ohio State University; AleixMartinez, The Ohio State University
1068 Reconstructing 3D Human Pose from 2D Image Landmarks. Varun Ramakrishna*, Carnegie Mellon University; Takeo Kanade ; YaserSheikh, CMU
1071 Good Regions to Deblur Zhe Hu*, UC Merced; Ming-Hsuan Yang, University of California at Merced
1073 Active Frame Selection for Label Propagation in Videos Sudheendra Vijayanarasimhan; Kristen Grauman* 
1075 Non-causal Temporal Prior for Video Deblocking Deqing Sun*, Brown University; Ce Liu, Microsoft Research New England
1077 Mediating Trajectory and Detection Graphs for Tracking through PersistentOcclusions  Katerina Fragkiadaki*, University of Pennsylvania; Weiyu Zhang,University of Pennsylvania
1078 Finding Correspondence from Multiple Images via Sparse and Low-rankDecomposition Zinan Zeng*, Nanyang Technological Uni; Tsung-Han  Chan, ADSC, Singapore; Kui Jia, Adv.Digital Sciences Center; Dong Xu 
1079 Indoor Segmentation and Support Inference from RGBD Images Nathan Silberman*, NYU; Rob Fergus; Derek Hoiem (Non-AC), UIUC;Pushmeet Kohli 
1081 Taking Mobile Multi-Object Tracking to the Next Level: People, UnknownObjects, and Carried Items Dennis Mitzel*, RWTH Aachen University; Bastian Leibe, RWTH AachenUniversity
1085 Towards Optimal Design of Time and Color Multiplexing Codes Tsung-Han  Chan*, ADSC,Singapore; Kui Jia, Adv. Digital Sciences Center; Eliot Wycoff, ADSC,Singapore; Chong-Yung Chi, National Tsing Hua University; Yi Ma 
1086 Text Image Deblurring Using Text-specific Properties Hojin Cho, POSTECH; Jue Wang, Adobe Systems; Seungyong Lee*, POSTECH
1087 Sequential Spectral Learning to Hash with Multiple Representations SAEHOON KIM*, POSTECH; YOONSEOP KANG, POSTECH; Seungjin Choi, POSTECH
1089 Efficient Exact Inference for 3D Indoor Scene Understanding Alexander Schwing*, ETH Zurich; Raquel Urtasun, TTIC
1103 Multidimensional Spectral Hashing Yair Weiss; Rob Fergus*; Antonio Torralba, MIT
1106 Dynamic Context for Tracking Behind Occlusions Fei Xiong, Northeastern University; Octavia Camps*, NortheasternUniversity; Mario Sznaier, Northeastern University
1108 Seam Segment Carving: Irregular Shape Image Retargeting Shaoyu Qi*, University of Florida; Jeffrey Ho, University of Florida
1110 Reflectance and Natural Illumination from a Single Image Stephen Lombardi*, Drexel University; Ko Nishino, Drexel University
1111 Recognizing Complex Events using Large Margin Joint Low-Level Event Model Hamid Izadinia*, University of Central Florida
1113 Categorizing Turn-Taking Interactions Karthir Prabhakar*, Georgia Tech; James Rehg 
1117 To Track or To Detect? An Ensemble Framework for Optimal Selection XU YAN*, University of Houston; Xuqing Wu; Ioannis A Kakadiaris,University of Houston; Shishir Shah, University of Houston
1119 Local Expert Forest of Score Fusion for Video Event Classification Jingchen Liu, Pennsylvania State Univ.; Scott McCloskey*, Honeywell
1126 View-Invariant Action Recognition using Latent Kernelized Structural SVM Xinxiao Wu*, Beijing Institute ofTechnology; Yunde Jia, Beijing Inst. ofTech.
1131 Learning Hybrid Part Filters for Scene Recognition Yingbin Zheng, Fudan University; Yu-Gang Jiang*, Fudan University;Xiangyang Xue, Fudan University
1133 Trajectory-Based Modeling of Human Actions with Motion Reference Points Yu-Gang Jiang*, Fudan University; Qi Dai, Fudan University; XiangyangXue, Fudan University; Wei Liu, Columbia University; Chong-Wah Ngo, CityUniversity of Hong Kong
1138 Visual Dictionary Learning for Joint Object Categorization andSegmentation Rene Vidal*, Johns Hopkins University; Aastha Jain, Johns HopkinsUniversity
1142 Stixels motion estimation without optical flow computation Bertan G¸nyel*, KU Leuven; Rodrigo Benenson, KU Leuven; Radu Timofte, KULeuven; Luc Van Gool, KU Leuven
1148 Parametric Manifold of an Object under Different Viewing Directions Xiaozheng Zhang*, National ICT Australia; Yongsheng Gao, GriffithUniversity; Terry Caelli, National ICT Australia
1155 Video Matting Using Multi-Frame Nonlocal Matting Laplacain Inchang Choi*, KAIST; Yu-Wing Tai, KAIST; Minhaeng Lee, KAIST
1159 Automatic localization of balloon markers and guidewire in rotationalfluoroscopy with application to 3D stent reconstruction Yu Wang*, Siemens Corporate Research; Terrence Chen, Siemens CorporateResearch; Peng Wang; Christopher Rohkohl; Dorin Comaniciu 
1161 In Defence of RANSAC for Outlier Rejection in Deformable Registration Quoc Huy Tran, The University of Adelaide; Tat-Jun Chin*, The Universityof Adelaide; Gustavo Carneiro, The University of Adelaide; Michael S. Brown,; David Suter, The University of Adelaide
1162 Dating Historical Color Images Frank Palermo*, Carnegie Mellon University; Alyosha Efros, CMU
1164 Estimation of Intrinsic Image Sequences from Image+Depth Video Kyong Joon Lee*, Seoul NationalUniversity; Qi Zhao, University of California – Santa Cruz; Xin Tong,Microsoft Research Asia; Minmin Gong, Microsoft Research Asia; Shahram Izadi,Microsoft Research Cambridge; Sang Uk Lee, Seoul National University; PingTan; Steve Lin   
1168 What Makes a Good Detector? — Structured Priors for Learning From FewExamples Tianshi Gao*, Stanford University; Michael Stark; Daphne Koller,Stanford University
1170 Temporally Consistent 3D Scene Flow Estimation for Multi-View Data Jaesik Park*, KAIST; Tae Hyun Oh, KAIST; Jiyoung Jung, KAIST; Yu-WingTai, KAIST; In So Kweon, KAIST
1171 Diagnosing Error in Object Detectors Derek Hoiem*, University of Illinois; Yodsawalai Chodpathumwan,University of Illinois; Qieyun Dai, University of Illinois
1176 Two-view Underwater Structure and Motion for Cameras under FlatRefractive Interfaces Lai Kang*, University of Alberta; National University of DefenseTechnology; Lingda Wu; Yee-Hong Yang 
1178 Rainbow Flash Camera: Depth Edge Extraction Using Complementary Colors Yuichi Taguchi*, MERL
1180 Fast approximations to structured sparse coding and applications toobject classification Arthur Szlam*, City college of new york; Karol Gregor, Howard HughesMedical Institute; Yann LeCun, New York University
1181 A Naturalistic Open Source Movie for Optical Flow Evaluation Daniel Butler*, University of Washington; Jonas Wulff, Max PlanckInstitute for Intelligent Systems; Garrett Stanley, Department of BiomedicalEngineering, Georgia Institute of Technology; Michael Black, Max PlanckInstitute for Intelligent Systems
1186 A Convolutional Treelets Binary Feature Approach to Fast KeypointRecognition Chenxia Wu*, Zhejiang University; Jianke Zhu, Zhejiang University; DengCai, Zhejiang University; Chun Chen 
1195 Online Moving Camera Background Subtraction Ali Elqursh*, Rutgers University; Ahmed Elgammal, Rutgers University
1202 Bayesian Blind Deconvolution with General Sparse Image Priors S. Derin Babacan*, University of Illinois at Urbana-Champaign; RafaelMolina, Universidad de Granada; Minh Do, University of Illinois atUrbana-Champaign; Aggelos Katsaggelos, Northwestern University
1203 Shape From Fluorescence Tali Treibitz*, UCSD; Zack Murez, UCSD; David Kriegman 
1207 A probabilistic derivative measure based on the distribution of intensitydifference Youngbae Hwang*, KETI
1208 Enhancing Descriptor Approaches by a Template Structure for FaceRecognition Liang Chen*, Uni. of N. British Columbia; Ling Yan 
1209 3D^2PM – 3D Deformable Part Models Bojan Pepik*, Max Planck Informatics; Michael Stark; Peter Gehler;Bernt Schiele 
1213 Latent Pyramidal Regions for Recognizing Scenes Fereshteh Sadeghi*, University of Central Florida; Marshall Tappen, UCF
1215 Super-Resolution-based inpainting Olivier LE MEUR*, University of Rennes 1; Christine GUILLEMOT, INRIA
1219 Guaranteed Ellipse Fitting with the Sampson Distance Zygmunt Szpak*, University of Adelaide; Wojciech Chojnacki, TheUniversity of Adelaide; Anton van den hengel, University of Adelaide
1220 Fast Planar Correlation Clustering for Image Segmentation Julian Yarkony, UC Irvine; Alexander Ihler, UC Irvine; Charless Fowlkes*,UC Irvine
1225 Coregistration: Simultaneous Alignment and Modeling of Articulated 3DShape David Hirshberg, MPI for Intelligent Systems; Matthew Loper, MPI forIntelligent Systems; Eric Rachlin*, MPI for Intelligent Systems; MichaelBlack, Max Planck Institute for Intelligent Systems
1228 Pairwise Rotation Invariant Co-occurrence Local Binary Pattern Xianbiao Qi*, BUPT; Rong Xiao, microsoft; Lei Zhang, MSRA; Jun Guo, BUPT
1234 Improving NCC-based Direct Visual Tracking Glauco Scandaroli*, INRIA – Sophia Antipolis; Rogerio Richa, JohnsHopkins University; Maxime Meilland 
1238 Efficient Similarity Derived From Kernel-based Transition Probability Takumi Kobayashi*, National Institute of AIST; Nobuyuki Otsu 
1239 Simultaneous Compaction and Factorization of Sparse Image Motion Matrices Susanna Ricco*, Duke University; Carlo Tomasi 
1243 Efficient Optimization For Low-Rank Integrated Bilinear Classifiers Takumi Kobayashi*, National Institute of AIST; Nobuyuki Otsu 
1249 Per-patch Descriptor Selection using Surface and Scene Properties Ivo Everts*, UvA; Jan van Gemert, UvA; Theo Gevers, UvA
1258 PlantID: A Computer Vision System for Automatic Plant SpeciesIdentification Neeraj Kumar*, University of Washington; David Jacobs; Peter Belhumeur,Columbia University; Arijit Biswas, University of Maryland; Joao Soares,University of Maryland
1261 A Convex Discrete-Continuous Approach for Markov Random Fields Christopher Zach*, Microsoft Research; Pushmeet Kohli 
1265 Augmented Attribute Representations Viktoriia Sharmanska*, IST Austria; Novi Quadrianto, University ofCambridge; Christoph Lampert, IST Austria
1273 A Locally Linear Regression Model for Boundary Preserving Regularizationin Stereo Matching Shengqi Zhu*, Univ of Wisconsin – Madison; Li Zhang, Univ. of Wisconsin -Madison; Hailin Jin 
1274 Exploring the Spatial Hierarchy of Mixture Models for Human PoseEstimation Yuandong Tian*, Carnegie Mellon University; C. Lawrence Zitnick,Microsoft Research; Srinivasa Narasimhan, Carnegie Mellon University
1279 People Orientation Recognition by Mixtures of Wrapped Distributions onRandom Trees Davide Baltieri, University of Modena and Reggio Emilia; RobertoVezzani*, University of Modena and Reggio Emilia; Rita Cucchiara, Universityof Modena and Reggio Emilia
1280 A Novel Fast Method for $L_\infty$ Problems in Multiview Geometry Zhijun Dai*, Intelligence Engineering Labor; Yihong Wu; HonganWang 
1283 Low-Rank  Sparse Learning  for Robust Visual Tracking  Tianzhu Zhang*, ADSC; Bernard Ghanem; Narendra Ahuja, University ofIllinois, Urbana Champaign
1286 Robust and Efficient Subspace Segmentation via Least Squares Regression Can-Yi Lu*, USTC; lin zhu; deshuang huang 
1287 Visibility Probability Structure from SfM Dataset and Applications Siddharth Choudhary*, IIIT Hyderabad; P J Narayanan 
1288 Hybrid Classifiers for Object Classification with a Rich Background Margarita Osadchy*, University of Haifa; Daniel Keren, University ofHaifa; Bella Specktor, University of Haifa
1289 A Generative Model for Online Depth Fusion Oliver Woodford*, Toshiba Research Europe Ltd; George Vogiatzis, AstonUniversity
1290 Mixed-Resolution Patch-Matching Harshit Sureka*, IIIT-Hyderabad; P J Narayanan 
1294 Depth Recovery Using an Adaptive Color-Guided Auto-Regressive Model Jingyu Yang*, Tianjin University; Xinchen Ye, Tianjin University; Kun Li,Tianjin University; Chunping Hou, Tianjin University
1298 Real-Time Camera Tracking: When is High Frame-Rate Best? Ankur Handa, Imperial College London; Richard Newcombe, Imperial CollegeLondon; Adrien Angeli; Andrew Davison*, Imperial College London
1299 Motion Interchange Patterns for Action Recognition in UnconstrainedVideos Orit Kliper-Gross, Weizmann Institute of Science; Yaron Gurovich,Tel-Aviv University; Tal Hassner*, The Open University of Israel; Lior Wolf,Tel-Aviv University
1302 Exploiting Sparse Representations for Robust Analysis of Noisy ComplexVideo Scenes Gloria Zen*, University of Trento; Elisa Ricci, University of Perugia;Nicu Sebe, University of Trento
1308 An Automatic Pose Invariant FRAD Approach Eslam Mostafa*, University of Louisville; Asem Ali; Aly Farag 
1322 A non-parametric hierarchical model to discover behavior dynamics fromtracks Dariu Gavrila*, University of Amsterdam; Julian Kooij; GwennEnglebienne 
1328 Generalized Roof Duality for Multi-Label Optimization: Optimal LowerBounds and Persistency Thomas Windheuser*, Technische Universität München; Hiroshi Ishikawa;Daniel Cremers 
1330 Semantic Segmentation with Second-Order Pooling Joao Carreira*, University of Coimbra; Rui Caseiro, Institute SystemsRobotics; Jorge Batista, Institute Systems Robotics – University Coimbra -Portugal; Cristian Sminchisescu, University of Bonn
1331 Separability Oriented Preprocessing for Illumination-invariant FaceRecognition Hu Han*, Michigan State University; Shiguang Shan, ICT, CAS; Xilin Chen,ICT, CAS; Shihong Lao, Omron Company; Wen Gao, Peking University
1335 Minimal Correlation Ensemble Noga Levy*, Tel Aviv University; Lior Wolf, Tel-Aviv University
1340 Elastic Shape Matching of Parameterized Surfaces Using Square Root NormalFields Ian Jermyn; Sebastian Kurtek*; Eric Klassen, Florida StateUniversity; Anuj Srivastava, Florida State University
1357 Contextual Object Detection using Set-based Classification Ramazan Gokberk CINBIS*, INRIA Grenoble; Stan Sclaroff, Boston University
1358 A Bayesian Approach to Alignment-based Image Hallucination Marshall Tappen*, UCF; Ce Liu, Microsoft Research New England
1360 KAZE Features Pablo Fern·ndez Alcantarilla*, UniversitÈ d’Auvergne; Adrien Bartoli,ISIT; Andrew Davison, Imperial College London
1369 Saliency Modeling from Image Histograms Shijian Lu*, I2R, A*STAR; Joo-Hwee Lim, Institute for Infocomm Research
1373 N-tuple Color Segmentation for Multi-View Silhouette Extraction Abdelaziz Djelouah*, Inria; technicolor; edmond boyer, INRIA;Jean-Sebastien Franco, INRIA; Patrick Perez, technicolor; FranÁois Le Clerc,Technicolor
1378 Local Label Descriptor for Example based Semantic Image Labeling Yiqing Yang*, Univ of Wisconsin – Madison; Zhouyuan Li, Univ of Wisconsin- Madison; Li Zhang, Univ. of Wisconsin – Madison; Christopher Murphy, Univof Wisconsin – Madison; Jim Hoeve, Univ of Wisconsin – Madison; HongruiJiang 
1383 Photo-Sequensing  Tali Basha*, Tel Aviv University; Shai Avidan; Yael Moses, IDC
1385 Age Invariant Face Verification with Relative Craniofacial Growth Model Tao Wu*, University of Maryland; Rama Chellappa, Univ. of Maryland,College Park
1399 Sparse Embedding: A framework for Sparsity Promoting DimensionalityReduction Hien Nguyen*, University of Maryland; Vishal Patel, UMIACS; NasserNasrabadi, Army Research Laboratory; Rama Chellappa, Univ. of Maryland,College Park
1403 Inferring gene interaction networks from ISH images via kernelizedgraphical models  Kriti Puniyani*, Carnegie Mellon University; Eric Xing 
1407 Random Forest for Image Annotation Hao Fu*, University of Nottingham; Qian Zhang, University of Nottingham;Guoping Qiu, University of Nottingham
1422 Continuous Markov Random Fields for Robust Stereo Estimation Koichiro Yamaguchi, TTI Chicago; Tamir Hazan, TTI Chicago; DavidMcAllester, TTI Chicago; Raquel Urtasun*, TTIC
1423 Loss-Specific Training of Non-Parametric Image Restoration Models: A NewState of the Art Jeremy Jancsary*, OFAI; Sebastian Nowozin, Microsoft Research; CarstenRother 
1427 A Probabilistic Approach to Robust Matrix Factorization Naiyan Wang*, HKUST; Tiansheng Yao; Jingdong Wang, Microsoft ResearchAsia; Dit-Yan Yeung 
1428 Continuous Regression for Non-Rigid Image Alignment Enrique Sanchez Lozano*, Gradiant; Fernando De la Torre, Carnegie MellonUniversity; Daniel Gonzalez Jimenez, Gradiant
1429 Fourier Kernel Learning Eduard-Gabriel Bazavan*, IMAR; Fuxin Li, Georgia Inst. of Tech.; CristianSminchisescu, University of Bonn
1430 Simultaneous Tracking of Multiple People and their Parts Hamid Izadinia*, University of Central Florida
1435 Information Theoretic Learning for Pixel-based Visual Agents Marco Maggini*, University of Siena; Stefano Melacci, University ofSiena; Marco Gori, University of Siena; Marco Lippi, University of Siena
1436 Large Scale Visual Geo-Localization of Images in Mountainous Terrain Georges Baatz*, ETHZ; Olivier Saurer, ETHZ; Kevin Koeser, ETHZ; MarcPollefeys 
1439 A theoretical analysis of camera response functions in image deblurring Xiaogang Chen*, Shanghai Jiaotong University; Jingyi Yu; Jie Yang;Feng Li, University of Delaware
1448 Fast Parameter Sensitivity Analysis of PDE-based Image Processing Methods Torben Pätz*, Jacobs University Bremen; Tobias Preusser, JacobsUniversity Bremen
1454 The Lazy Flipper: Efficient Depth-limited Exhaustive Search in DiscreteGraphical Models Bjoern Andres*, Harvard University; Jˆrg Kappes, Heidelberg University;Thorsten Beier, University of Heidelberg; Ullrich Koethe, University ofHeidelberg, Germany; Fred Hamprecht, University of Heidelberg, Germany
1459 Road Scene Segmentation from a Single Image Jose  Alvarez*, ComputerVision Center; Theo Gevers, UvA; Yann LeCun, New York University; AntonioLopez, Computer Vision Center
1465 Mixture Component Identification and Learning for Visual Recognition Omid Aghazadeh*, CVAP, KTH; Hossein Azizpour, CVAP, KTH; Josephine Sullivan; Stefan Carlsson, CVAP,KTH
1467 Predictable and Discriminative Binary Codes  Mohammad Rastegari*, Dartmouth college; Ali Farhadi; DavidForsyth 
1473 Scene semantics from long-term observation of people Vincent Delaitre; David Fouhey, Carnegie Mellon University; IvanLaptev*; Josef Sivic, INRIA / Ecole Normale Superieure; Abhinav Gupta;Alyosha Efros, CMU
1476 Local Higher-order Statistics (LHS) for Texture Categorization and FacialAnalysis Gaurav Sharma, Unicaen; Sibt ul Hussain*, UniversitÈ de Caen; FredericJurie, University of Caen
1482 Motion-Aware Structured Light Using Spatio-Temporal Decodable Patterns Yuichi Taguchi*, MERL; Amit Agrawal, MERL; Oncel Tuzel, MERL
1501 Face Association across Unconstrained Video Frames Using ConditionalRandom Fields Ming Du*, University of Maryland; Rama Chellappa, Univ. of Maryland,College Park
1503 Non-Rigid Shape Registration: A Single Linear Least Squares Framework Mohammad Rouhani*, CVC; Angel Sappa, Computer Vision Center
1509 Image Retrieval with Structured Object Queries Using Latent Ranking SVM Tian Lan*, Simon Fraser University; Weilong Yang, Simon FraserUniversity; Yang Wang, UIUC; Greg Mori 
1512 Similarity Constrained Latent Support Vector Machine: An Application toWeakly Supervised Action Classification Nataliya Shapovalova*, SFU; Arash Vahdat, SFU; Kevin Cannons, SFU; TianLan, SFU; Greg Mori 
1521 Refractive Calibration of Underwater Cameras Anne Sedlazeck*, Kiel University; Reinhard Koch 
1526 Detection of Independently Moving Objects in Non-planar Scenes viaMulti-Frame Monocular Epipolar Constraint Vladimir Reilly*, University of Central Florida; Soumyabrata Dey,University of Central Florida; Mubarak Shah, UCF
1532  SEEDS: Superpixels Extractedvia Energy-Driven Sampling Michael Van den Bergh*, ETH Zurich; Gemma Roig Noguera, ETH; Xavier Boix,ETH; Luc Van Gool 
1535 Shape from Angle Regularity Aamer Zaheer, LUMS School of Science and Engineering; Maheen Rashid, LUMSSchool of Science and Engineering; Sohaib Khan*, LUMS School of Science andEng
1543 Streaming Hierarchical Video Segmentation Chenliang Xu, SUNY at Buffalo; Caiming Xiong, SUNY at Buffalo; JasonCorso*, SUNY at Buffalo
1553 Co-inference for Multi-modal Scene Analysis Daniel Munoz*, Carnegie Mellon University; James Bagnell; MartialHebert 
1560 A Unified View on Deformable Shape Factorizations Roland Angst*, ETH Zurich; Marc Pollefeys 
1566 Large-lexicon attribute-consistent text recognition in natural images Tatiana Novikova, Moscow State University; Olga Barinova*, Moscow StateUniversity; Pushmeet Kohli; Victor Lempitsky 
1567 Team Activity Recognition in Sports Cem Direkoglu*, Dublin City University; Noel O’Connor, Dublin CityUniversity
1568 Dictionary-based Face Recognition from Video Yi-Chen Chen*, UMIACS; Vishal Patel, UMIACS; Jonathon Phillips; RamaChellappa, Univ. of Maryland, College Park
1573 Efficient Learning of Camera Transitions for Person Re-Identification Martin Hirzer*, Graz University of Technology; Peter Roth, GrazUniversity of Technology; Horst Bischof 
1588 Saliency-Based Space-Variant Descriptor Sampling for Action Recognition Eleonora Vig*, Rowland Institute at Harvard; Michael Dorr, Schepens EyeResearch Institute, Harvard Medical School; David Cox, Rowland Institute atHarvard
1589 Finding the exact rotation between two images independently of thetranslation Laurent Kneip*, ETH Zurich; Roland Siegwart, ETH Zurich; MarcPollefeys 
1597 Contraction Moves for Geometric Model Fitting Oliver Woodford*, Toshiba Research Europe; Minh-Tri Pham, ToshibaResearch Europe; Atsuto Maki, Toshiba Research Europe; Riccardo Gherardi,Toshiba Research Europe; Frank Perbet, Toshiba Research Europe; BjornStenger, Toshiba Research Europe
1609 Dynamic Probabilistic CCA for Analysis of Affective Behaviour Mihalis Nicolaou*, Imperial College London; Vladimir Pavlovic, RutgersUniversity; Maja Pantic, Imperial College London
1615 Connecting Missing Links: Object Discovery from Sparse Observations Hongwen Kang*, Carnegie Mellon University; Martial Hebert; Takeo Kanade 
1616 General and Nested Wiberg Minimization: L_2 and Maximum Likelihood Dennis Strelow*, Google
1619 Motion Capture of Hands in Action using Discriminative Salient Points Luca Ballan*, ETH Zurich; Aparna Taneja, ETH Zurich; Juergen Gall, ETHZurich; Luc Van Gool; Marc Pollefeys 
1625 A new set of quartic trivariate polynomial equations for stratifiedcamera self-calibration under zero-skew and constant parameters assumptions Adlane Habed*, University of Bourgogne; Kassem Al Ismaeil, University ofLuxembourg; David Fofi, University of Bourgogne
1637 A minimal solution for camera calibration using independent pairwisecorrespondences Francisco Vasconcelos*, ISR – Coimbra; Jo„o Pedro Barreto, ISR; edmondboyer, INRIA
1656 Robust and Accurate Shape Model Fitting using Random Forest RegressionVoting Tim Cootes*, The University of Manchester; Mircea Ionita, The Universityof Manchester; Claudia Lindner, The University of Manchester; Patrick Sauer,The University of Manchester
1664 Disentangling factors of variation for facial expression recognition Salah Rifai*, Universite de Montreal; Yoshua Bengio, U. Montreal; AaronCourville, U. Montreal; Pascal Vincent, UniversitÈ de MontrÈal; Mehdi Mirza,U. Montreal
1675 Recording and playback of camera shake:   benchmarking blind deconvolutionwith a real-world database Rolf Koehler*, MPI for Intelligent Systems; Michael Hirsch, MPI forIntelligent Systems; Stefan Harmeling, MPI for Intelligent Systems; BettyMohler; Bernhard Schˆlkopf, MPI for Intelligent Systems
1677 Joint Image Classification and Annotation via Biased Random Walk onTri-Relationship Graph Xiao Cai*, UTA; Feiping Nie, UTA; Heng Huang, University of Texas atArlington
1682 Real–Time Human Pose Tracking using Range Cameras Varun Ganapathi*, Google; Christian Plagemann, Google Research; DaphneKoller, Stanford University; Sebastian Thrun, Google
1687 Spring Lattice Counting Grids  Alessandro Perina*, Microsoft Research; Nebojsa Jojic, Microsoft Research
1688 Efficient Recursive Algorithms for Computing the Mean Diffusion Tensorand Applications to DTI Segmentation Hesamoddin Salehian, University of Florida; Guang Cheng, University ofFlorida; Baba Vemuri*, University of Florida
1691 Semi-Nonnegative Matrix Factorization for Motion Segmentation withMissing Data Quanyi Mo*, Colorado State University; Bruce Draper, Colorado StateUniversity
1699 Learning-Based Symmetry Detection in Natural Images Stavros Tsogkas*, Ecole Centrale de Paris; Iasonas Kokkinos, EcoleCentrale Paris/INRIA
1707 Beyond the line of sight: labeling the underlying surfaces Ruiqi Guo*, UIUC; Derek Hoiem, University of Illinois
1711 Hand Pose Estimation and Hand Shape Classification using Multi–layeredRandomized Decision Forests Cem Keskin*, Bo?aziÁi University; Yunus Emre Kara; Furkan K?raÁ; LaleAkarun 
1712 Nonmetric Priors for Continuous Multilabel Optimization Evgeny Strekalovskiy*, Technical University Munich; Claudia Nieuwenhuis,TU München; Daniel Cremers 

你可能感兴趣的:(计算机视觉,list,microsoft,image,classification,descriptor,object)