Main Conference Program

Pocket Guide Available

Please click on this link or the image to download.

2014-08-19 02.08.34 pm

Monday, September 8


0800–0900       Registration (Vestibul K)

0900–0930       Opening & Awards (Kongresssaal)

0930–1030       Oral Session 1A: Tracking and Activity Recognition (Kongresssaal)

Chairs:        Frank Dellaert (Georgia Institute of Technology)
                        Silvio Savarese (Stanford University)

Format (15 min. for presentation + 3 min. for questions)

  1. Visual Tracking by Sampling Tree-Structured Graphical Models, Seunghoon Hong, Bohyung Han, POSTECH
  2. Tracking Interacting Objects Optimally Using Integer Programming, Xinchao Wang, Engin Türetken, EPFL; François Fleuret, EPFL/IDIAP; Pascal Fua, EPFL
  3. Learning Latent Constituents for Recognition of Group Activities in Video, Borislav Antic, Björn Ommer, University of Heidelberg

1030-1115       Coffee Break

1115–1230       Oral Session 1B: Recognition (Kongresssaal)

Chairs:        Hervé Jégou (INRIA)
                        Alex Berg (UNC Chapel Hill)

Format (15 min. for presentation + 3 min. for questions)

  1. Large-Scale Object Classification using Label Relation Graphs, Jia Deng, University of Michigan; Nan Ding; Yangqing Jia; Andrea Frome; Kevin Murphy; Samy Bengio; Yuan Li, Hartmut Neven; Hartwig Adam, Google
  2. 30Hz Object Detection with DPM V5, Mohammad Amin Sadeghi, David Forsyth, UIUC
  3. Knowing a good HOG filter when you see it: Efficient selection of filters for detection, Ejaz Ahmed, University of Maryland at College Park; Gregory Shakhnarovich, TTI Chicago; Subhransu Maji, University of Massachusetts, Amherst
  4. Linking people in videos with “their” names using coreference resolution, Vignesh Ramanathan, Armand Joulin, Percy Liang, Li Fei-Fei, Stanford University

 

1230-1400       Lunch Break

1400-1600        Video spotlight loop (Kongresssaal)

1400-1600       Demos (Panoramasaal- Foyer)

  • Large-Scale Monocular SLAM with Client-Server Architecture, Haomin Liu (Zhejiang University), Guofeng Zhang (Zhejiang University), Hujun Bao (Zhejiang University)
  • Video face enhancer: expression cloning and super-resolution by facial feature tracking, Chen Huang (Tsinghua University), Xiaoqing Ding (Tsinghua University), Chi Fang (Tsinghua University)
  • Self-Learning Camera: Autonomous Adaptation of Object Detectors to Unlabeled Video Streams, Adrien Gaidon, (Xerox Research Centre Europe), Eleonora Vig (Xerox Research Centre Europe)
  • Dense 3D Face Alignment from 2D Video for Analysis and Synthesis, Laszlo A. Jeni (Carnegie Mellon University), Jeffrey F. Cohn (Carnegie Mellon University), Takeo Kanade (Carnegie Mellon University)

1400–1645       Exhibits (Tagungszentrum)

  • Leica
  • Microsoft Research
  • Google
  • Toyota
  • Technicolor
  • Amazon
  • Disney Research
  • Qualcomm
  • Facebook
  • Inilabs
  • Omron
  • Ascending Technologies
  • Pelican Imaging
  • Glamsmile
  • Dacuda
  • Fastvis
  • Ptgrey
  • SCS
  • 4DViews
  • Urbanrobotics
  • Springer

1400–1645       Poster Video Spotlight Loop (Kongresssaal)

1400–1600       Poster Session 1A (Gartensaal: posters 1-24, Panoramasaal: posters 25-52)  

  1. Optimal Essential Matrix Estimation via Inlier-Set Maximization, Jiaolong Yang, BIT and ANU; Hongdong Li, Australian National University; Yunde Iia, BIT
  2. UPnP: An optimal O(n) solution to the absolute pose problem with universal applicability, Laurent Kneip, Australian National University; Hongdong Li, Australian National University; Yongduek Seo, Sogang University
  3. 3D Reconstruction of Dynamic Textures in Crowd Sourced Data, Dinghuang Ji, UNC Chapel Hill; Enrique Dunn, UNC Chapel Hill; Jan-Michael Frahm, UNC Chapel Hill
  4. 3D Interest Point Detection via Discriminative Learning, Leizer Teran, Drexel University; Philippos Mordohai, Stevens Institute of Technology
  5. Pose Locality Constrained Representation for 3D Human Pose Reconstruction, Xiaochuan Fan, Kang Zheng, Youjie Zhou, Song Wang, University of South Carolina
  6. Synchronization of two independently moving cameras without feature correspondences, Tiago Gaspar, IST; Paulo Oliveira, IST; Paolo Favaro, Bern University
  7. Multi-Focus Structured Light for Recovering Scene Shape and Global Illumination, Supreeth Achar, Carnegie Mellon University; Srinivas Narasimhan, CMU
  8. Coplanar Common Points in Non-Centric Cameras, Wei Yang, University of Delaware; Yu Ji, University of Delaware; Jinwei Ye, University of Delaware; S. Susan Young, U.S. Army Research Lab; Jingyi Yu, University of Delaware
  9. SRA: Fast Removal of General Multipath for ToF Sensors,Daniel Freedman, Microsoft Research; Yoni Smolin, Microsoft Research; Eyal Krupko, Microsoft Research; Ido Leichter, Technion; Mirko Schmidt, Microsoft Research
  10. Sub-Pixel Layout for Super-Resolution with Images in the Octic Group, Boxin Shi, MIT Media Lab; Hang Zhao, MIT; Moshe Ben-Ezra, MIT Media Lab; Sai-Kit Yeung, Singapore University of Technology and Design; Christy Cull, MIT Lincoln Lab; R. Hamilton Shepard, MIT; Christopher Barsi, MIT; Ramesh Raskar MIT
  11. Simultaneous Feature and Dictionary Learning for Image Set Based Face Recognition, Jiwen Lu, ADSC; Gang Wang, Nanyang Technological University; Weihong Deng, Beijing Univ. Post. & Telecom; Pierre Moulin, UIUC
  12. Read My Lips: Continuous Signer Independent Weakly Supervised Viseme Recognition, Oscar Koller, RWTH Aachen University; Hermann Ney, RWTH Aachen University; Richard Bowden, University of Surrey UK
  13. Multilinear Wavelets: A Statistical Shape Space for Human Faces, Alan Brunton, Fraunhofer IGD; Timo Bolkart, Saarland University; Stefanie Wuhrer, Saarland University
  14. Distance estimation of an unknown person from a portrait, Xavier Burgos-Artizzu, California Institute of Technology; Matteo Ronchi, California Institute of Technology; Pietro Perona, California Institute of Technology
  15. Probabilistic Temporal Head Pose Estimation Using a Hierarchical Graphical Model, Meltem Demirkus, McGill University; Doina Precup, McGill University; James Clark, McGill University; Tal Arbel, McGill University
  16. Description-Discrimination Collaborative Tracking, Dapeng Chen, Xi’an Jiaotong University; Zejian Yuan, Xi’an Jiaotong University; Gang Hua, Stevens Institute of Technology; Yang Wu, Kyoto University; Nanning Zheng, Xi’an Jiaotong University
  17. Online, Real-Time Tracking using a Category-to-Individual Detector, David Hall, California Institute of Technology; Pietro Perona, California Institute of Technology
  18. Robust Visual Tracking with Double Bounding Box Model, Junseok Kwon, ETH Zurich; Junha Roh, KIST; Kyoung Mu Lee, Seoul National University; Luc Van Gool, Computer Vision Lab, ETH Zurich
  19. Tractable and Reliable Registration of 2D Point Sets, Erik Ask, Lund University; Olof Enqvist, Chalmers University of Technology, Sweden; Linus Svärm, Lund University; Fredrik Kahl, Chalmers University of Technology; Giuseppe Lippolis, Lund University
  20. Graduated Consistency-Regularized Optimization for Multi-Graph Matching, Junchi Yan, Shanghai Jiao Tong University; Yin Li, Georgia Institute of Technolog; Wei Liu, IBM Thomas J. Watson Research; Hongyuan Zha, Georgia Institute of Technology; Xiaokang Yang, Shanghai Jiao Tong University; Stephen Mingyu Chu, IBM Research China
  21. Optical Flow Estimation with Channel Constancy, Laura Sevilla-Lara, University of Massachusetts, Amherst; Deqing Sun, Harvard; Erik Learned-Miller, University of Massachusetts; Michael Black, Max Planck Institute for Intelligent Systems
  22. Non-Local Total Generalized Variation for Optical Flow Estimation, René Ranftl, Graz University of Technology; Kristian Bredies, University of Graz; Thomas Pock, Graz University of Technology
  23. Learning Brightness Transfer Functions for the Joint Recovery of Illumination Changes and Optical Flow, Oliver Demetz, Saarland University; Michael Stoll, University of Stuttgart; Sebastian Volz, University of Stuttgart; Joachim Weickert, Saarland University; Andrés Bruhn, University of Stuttgart
  24. Hipster Wars: Discovering Elements of Fashion Styles, M. Hadi Kiapour, UNC Chapel Hill; Kota Yamaguchi, Stony Brook University; Alexander Berg, UNC Chapel Hill; Tamara Berg, UNC Chapel Hill
  25. From Low-Cost Depth Sensors to CAD: Cross-Domain 3D Shape Retrieval via Regression Tree Fields, Yan Wang, Columbia University; Jie Feng, Columbia University; Zhixiang Wu, Columbia University; Jun Wang, IBM Research Center; Shih-Fu Chang, Columbia University
  26. Fast and Accurate Texture Recognition with Multilayer Convolution and Multifractal Analysis, Hicham Badri, INRIA; Hussein Yahia, INRIA; Khalid Daoudi, INRIA
  27. Learning to Rank 3D Features, Oncel Tuzel, MERL; Ming-Yu Liu, MERL; Yuichi Taguchi, MERL; Arvind Raghunathan, MERL
  28. Salient Color Names for Person Re-Identification, Yang Yang, CBSR; Jimei Yang, University of California at Merced; Junjie Yan, NLPR; Shengcai Liao, Institute of Automation, Chinese Academy of Sciences; Dong Yi, NLPR, CASIA; Stan Z.Li, NLPR Institute of Automation, Chinese Academy of Sciences
  29. Learning Discriminative and Shareable Features for Scene Classification, Zhen Zuo, Nanyang Tech. Univ.; Gang Wang, Nanyang Tech. Univ.; Bing Shuai, Nanyang Tech. Univ.; Lifan Zhao, Nanyang Tech. Univ.; Qingxiong Yang, CityUniversity of Hong Kong; Xudong Jiang, Nanyang Tech. Univ.
  30. Image Retrieval and Ranking via Consistently Reconstructing Multi-Attribute Queries, Xiaochun Cao, SKLOIS, IIIE CAS; Hua Zhang, Tianjin University; Xiaojie Guo, SKLOIS, IIE, CAS; Si Liu, NUS; Xiaowu Chen, Beihang University
  31. Neural Codes for Image Retrieval, Artem Babenko, Yandex; Anton Slesarev, Yandex; Alexandr Chigorin, Yandex; Victor Lempitsky, Skolkovo Institute of Science and Technology  
  32. Architectural Style Classification using Multinomial Latent Logistic Regression, Zhe Xu, University of Technology Sydney; Dacheng Tao, University of Technology Sydney; Ya Zhang, Shanghai Jiao Tong University; Junjie Wu, Beihang University; Ah Chung Tsoi, Macau University of Science and Technology
  33. Instance Segmentation of Indoor Scenes using a Coverage Loss, Nathan Silberman, NYU; David Sontag, NYU; Rob Fergus, NYU
  34. Superpixel Graph Label Transfer with Learned Distance Metric, Stephen Gould, Australian National University; Jiecheng Zhao, ANU; Xuming He, NICTA; Yuhang Zhang, Chalmers University
  35. Precision-Recall-Classification Evaluation Framework: Application to Depth Estimation on Single Images, Guillem Palou Visa, Universitat Politècnica de Catalunya; Philippe Salembier Clairon, Universitat Politècnica de Catalunya
  36. A Multi-Stage Approach to Curve Extraction, Yuliang Guo, Brown University; Naman Kumar, Carnegie Mellon University; Maruthi Narayanan, Brown University; Benjamin Kimia, Brown University
  37. Geometry Driven Semantic Labeling of Indoor Scenes, Salman Khan, UWA; Mohammed Bennamoun, UWA; Ferdous Sohel,UWA; Roberto Togneri, UWA
  38. A Novel Topic-level Random Walk Framework for Scene Image Co-Segmentation, Zehuan Yuan, Nanjing University; Tong Lu, Nanjing University; Shivakumara Palaiahnakote, University of Malaya
  39. Surface Matching and Registration by Landmark Curve-Driven Canonical Quasiconformal Mapping, Wei Zeng, School of Computing and Information; Yi-jun Yang, Shandong University
  40. Motion Words for Videos, Ekaterina Taralova, Carnegie Mellon University; Fernando de la Torre, Carnegie Mellon University; Martial Hebert, Carnegie Mellon University,
  41. Activity Group Localization by Modeling the Relations among Participants, Lei Sun, Tsinghua University; Haizhou Ai, Tsinghua University; Shihong Lao, Omron Social Solutions Co, Ltd.
  42. Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach, Weiyue Wang, Shanghai Jiao Tong University; Weiyao Lin, Shanghai Jiao Tong University; Yuanzhe Chen, Shanghai Jiao Tong University; Jianxin Wu, Nanjing University; Jingdong Wang, Microsoft Research; Bin Sheng, Shanghai Jiao Tong University
  43. Semantic Aware Video Transcription Using Random Forest Classifiers, Chen Sun, University of Southern California; Ram Nevatia, University of Southern California
  44. Ranking Domain-specific Highlights by Analyzing Edited Videos, Min Sun, University of Washington; Ali Farhadi, University of Washington; Steve Seitz, Washington/Google
  45. A Multi-Transformational Model for Background Subtraction with Moving Cameras, Daniya Zamalieva, Ohio State University; Alper Yilmaz, Ohio State University; James W. Davis, Ohio State University

 

1600-1645       Coffee Break

1645–1815       Oral Session 1C: Learning and Inference (Kongresssaal)

Chairs:      Jakob Verbeek (INRIA)
                      Christoph Lampert (IST Austria)

Format (15 min. for presentation + 3 min. for questions)

  1. Visualizing and Understanding Convolutional Networks, Matthew Zeiler; Rob Fergus, NYU
  2. Part-based R-CNNs for Fine-grained Category Detection, Ning Zhang, Jeff Donahue, Ross Girshick, Trevor Darrell, UC Berkeley
  3. Coarse-to-Fine Auto-encoder Networks (CFAN) for Real-time Face Alignment, Jie Zhang, Shiguang Shan, Meina Kan, Xilin Chen, Chinese Academy of Science.
  4. From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices, Mehrtash Harandi, Mathieu Salzmann, Richard Hartley, Australian National University
  5. Pose Machines: Articulated Pose Estimation via Inference Machines, Varun Ramakrishna, Daniel Munoz, Martial Hebert, Andrew James Bagnell, Yaser Sheikh, CMU

1815–1945 Welcome Reception (Kongresshaus)

Tuesday, September 9


0800–1830       Registration (Vestibul K)

0830-1115       Demos (Panoramasaal-Foyer)

  • What can you do with a Beam and a reflecting prism?, Aaron Wetzler (Technion), Rom Herskovitz (Technion), Nofar Carmeli (Technion), Ron Kimmel (Technion)
  • Passive Tomography of Turbulence Strength, Marina Alterman (Technion), Yoav Schechner (Technion), Minh Vo (Carnegie Mellon University), Srinivasa Narasimhan (Carnegie Mellon University)
  • Real-time single camera hand gesture recognition system for remote deaf-blind communication, Giuseppe Airò Farulla (Politecnico di Torino, Turin), Andrea Bulgarelli (Politecnico di Torino, Turin), Marco Indaco (Politecnico di Torino, Turin), Stefano Rosa (Politecnico di Sant’Anna), Ludovico Russo (Politecnico di Torino, Italy) and Calogero Oddo (Scuola Superiore Sant’Anna, Pisa, Italy)
  • Will the Pedestrian Cross? Context-Based Pedestrian Path Prediction, N. Schneider (Daimler / University Amsterdam), F. Flohr (Daimler / University Amsterdam), J.F.P. Kooij (Daimler / University Amsterdam) and D. M. Gavrila (Daimler/ University Amsterdam)

0830–1115       Exhibits (Tagungszentrum)

Same as Monday afternoon Exhibits 

0830–1115       Swiss Computer Vision Start-Up Event  (Vestibul K)

0830–1115       Poster Video Spotlight Loop (Kongresssaal)

0830–1115       Poster Session 2A (Gartensaal: posters 1-24, Panoramasaal: posters 25-52)

  1. Piecewise-Planar StereoScan: Structure and Motion from Plane Primitives, Carolina Raposo, Michel Gonalves Antunes, João Barreto, Institute of Systems and Robotics, Universidade de Coimbra
  2. Nonrigid Surface Registration and Completion from RGBD Images, Weipeng Xu, BIT; Mathieu Salzmann, NICTA; Yongtian Wang, BIT; Yue Liu, BIT
  3. Unsupervised Dense Object Discovery, Detection, Tracking and Reconstruction, Lu Ma, The George Washington University; Gabe Sibley, The George Washington University
  4. Know Your Limits: Accuracy of Long Range Stereoscopic Object Measurements in Practice, Peter Pinggera, Daimler AG; David Pfeiffer, Daimler AG; Uwe Franke, Daimler; Rudolf Mester, Goethe Universität Frankfurt am Main
  5. As-Rigid-As-Possible Stereo under Second Order Smoothness Priors, Chi Zhang, Sun Yat-Sen University; Zhiwei Li, Microsoft; Rui Cai, Microsoft Research Asia; Hongyang CHAO, Sun Yat-sen University; Yong Rui, Microsoft
  6. Real-Time Minimization of the Piecewise Smooth Mumford-Shah Functional, Evgeny Strekalovskiy, Technical University Munich; Daniel Cremers, TUM
  7. A MAP-estimation Framework for Blind Deblurring Using High-level Edge Priors, Yipin Zhou, Brown University; Nikos Komodakis, Ecole des Ponts ParisTech
  8. Efficient Color Constancy with Local Surface Reflectance Statistics, Shaobing Gao, Wangwang Han, Kaifu Yang, Chaoyi Li, Yongjie Li, University of Electronic Science & Technology of China
  9. A Contrast Enhancement Framework with JPEG Artifacts Suppression, Yu Li, NUS; Fangfang Guo, NUS; Robby Tan, SIM University; Michael Brown, NUS
  10. Radial Bright Channel Prior for Single Image Vignetting Correction, Hojin Cho, POSTECH; Hyunjoon Lee, POSTECH; Seungyong Lee, POSTECH
  11. Tubular structure filtering by ranking orientation responses of path operators, Odyssée Merveille, ESIEE Paris; Hugues Talbot, Universite Paris Est; Laurent Najman, ESIEE Paris; Nicolas Passat, Université de Reims
  12. Optimization-Based Artifact Correction for Electron Microscopy Image Stacks, Samaneh Azadi, UC Berkeley; Jeremy Maitin-Shepard, UC Berkeley; Pieter Abbeel, UC Berkeley
  13. Metric-Based Pairwise and Multiple Image Registration, Qian Xie, Florida State University; Sebastian Kurtek, Ohio State University; Eric Klassen, Florida State University; Gary Christensen, University of Iowa; Anuj Srivastava, Florida State University
  14. Canonical Correlation Analysis on Riemannian Manifolds and its Applications, Hyunwoo Kim, Nagesh Adluru, Barbara Bendlin, Sterling Johnson, University of Wisconsin Madison; Baba Vemuri, University of Florida; Vikas Singh, University of Wisconsin-Madison
  15. Scalable 6-DOF Localization on Mobile Devices, Sven Middelberg, RWTH Aachen University; Torsten Sattler, ETH Zurich; Ole Untzelmann, Leif Kobbelt, RWTH Aachen University
  16. On Mean Pose and Variability of 3D Deformable Models, Benjamin Allain, Jean-Sébastien Franco, Edmond Boyer, INRIA Grenoble; Tony Tung, Kyoto University
  17. Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians, Bob Collins, Penn State University; Peter Carr, Disney Research
  18. What Do I See? Modeling Human Visual Perception for Multi-person Tracking, Xu Yan, University of Houston; Ioannis Kakadiaris, University of Houston; Shishir Shah, University of Houston
  19. Consistent Re-identification in a Camera Network, Abir Das, UC Riverside; Anirban Chakraborty, UC Riverside; Amit Roy-Chowdhury, UC Riverside
  20. Surface Normal Deconvolution: Photometric Stereo for Optically Thick Translucent Objects, Chika Inoshita, Osaka University; Yasuhiro Mukaigawa, Nara Institute of Science and Technology; Yasuyuki Matsushita, Microsoft Research Asia; Yasushi Yagi, Osaka University
  21. Intrinsic Video, Naejin Kong, Peter Gehler, Michael Black, Max Planck Institute for Intelligent Systems
  22. Robust and Accurate Non-Parametric Estimation of Reflectance using Basis Decomposition and Correction Functions, Tobias Nöll, Johannes Köhler, Didier Stricker, DFKI
  23. Intrinsic Textures for Relightable Free-Viewpoint Video, James Imber, Jean-Yves Guillemaut, Adrian Hilton, University of Surrey
  24. Reasoning About Object Affordances in a Knowledge Base Representation, Yuke Zhu, Alireza Fathi, Li Fei-Fei, Stanford University
  25. Binary Codes Embedding for Fast Image Tagging with Incomplete Labels, Qifan Wang, Bin Shen, Shumiao Wang, Liang Li, Luo Si, Purdue University
  26. Recognizing Products: A Per-Exemplar Multi-Label Image Classification Approach, Marian George, ETH Zurich; Chrisitan Floerkemeir, ETH Zurich
  27. Part-Pair Representation for Part Localization, Jiongxin Liu, Columbia University; Yinxiao Li, Columbia University; Peter Belhumeur, Columbia University
  28. Weakly Supervised Learning of Objects, Attributes and their Associations, Zhiyuan Shi, Yongxin Yang, Timothy Hospedales, Tao Xiang, Queen Mary University of London
  29. Interestingness Prediction by Robust Learning to Rank, Yanwei Fu, Timothy Hospedales, Tao Xiang, Queen Mary University of London; Shaogang Gong, Queen Mary University of London;  Yuan Yao, Peking University, China;
  30. Pairwise Probabilistic Voting: Fast Place Recognition without RANSAC, Edward Johns, Imperial College London; Guang-Zhong Yang, Imperial College London
  31. Robust Instance Recognition in Presence of Occlusion and Clutter, Ujwal Bonde, Vijay Badrinarayanan, Roberto Cipolla, University of Cambridge
  32. Learning 6D Object Pose Estimation using 3D Object Coordinates, Eric Brachmann, Alexander Krull, Frank Michel, Stefan Gumhold, TU Dresden; Jamie Shotton, Microsoft Research; Carsten Rother, TU Dresden
  33. Growing Regression Forests by Classification: Applications to Object Pose Estimation, Kota Hara, University of Maryland; Rama Chellappa, University of Maryland
  34. Stacked Deformable Part Model with Shape Regression for Object Part Localization, Junjie Yan, Lei Zhen, Yang Yang, Stan Z. Li , Institute of Automation Chinese Academy of Science
  35. Transductive Multi-view Embedding forZero-Shot Recognition and Annotation, Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Zhenyong Fu, Shaogang Gong, Queen Mary University of London
  36. Self-Explanatory Sparse Representation for Image Classification, Ba-Di Liu, China University of Petroleum; Yu-Xiong Wang, CMU; Bin Shen, Purdue University; Yu-Jin Zhang, Tsinghua University; Martial Hebert CMU
  37. Efficient k-Support Matrix Pursuit, Hanjiang Lai, Sun Yat-sen University; Yan Pan, Sun Yat-sen University; Canyi Lu, NUS; Yong Tang, South China Normal University; Shuicheng Yan, National University of Singapore
  38. Geodesic Regression on the Grassmannian, Yi Hong, UNC Chapel Hill; Roland Kwitt, University of Salzburg; Nikhil Singh, UNC Chapel Hill; Brad Davis, Kitware; Nuno Vasconcelos, UC San Diego; Marc Niethammer, UNC Chapell Hill
  39. Model Selection by Linear Programming, Joseph Wang, Tolga Bolukbasi, Kirill Trapeznikov, Venkatesh Saligrama, Boston University
  40. Perceptually Inspired Layout-aware Losses for Image Segmentation, Anton Osokin, Moscow State University; Pushmeet Kohli, Microsoft Research UK
  41. Large Margin Local Metric Learning, Julien Bohné, University College London; Yiming Ying, University of Exeter, UK; Stéphane Gentric, Safran Morpho; Massimiliano Pontil, University College London
  42. Movement Pattern Histogram for Action Recognition and Retrieval, Arridhana Ciptadi, Georgia Tech; Matthew S. Godwin, Northeastern University; James Rehg, Georgia Institute of Technology
  43. Pose Filter based Hidden-CRF models for Activity Detection, Prithviraj Banerjee, Ram Nevatia, University of Southern California
  44. Action Recognition Using Super Sparse Coding Vector with Spatio-Temporal Awareness, Xiaodong Yang, City College of New York; Yingli Tian, City College of New York, CUNY
  45. HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition, Hossein Rahmani, Arif Mahmood, Du Huynh, Ajmal Mian, University of Western Australia
  46. Natural action recognition using invariant 3D motion encoding, Simon Hadfield, Karel Lebeda, Richard Bowden, University of Surrey UK
  47. Detecting Social Actions of Fruit Flies, Eyrun Eyjolfsdottir, Steven Branson, Xavier P. Burgos-Artizzau, Eric Hoopfer, Jonathan Schor, David J. Anderson, Pietro Perona, California Institute of Technology

1030-1115        Coffee Break

1115–1230       Oral Session 2A: Structure from Motion and Feature Matching (Kongresssaal)

Chairs:       Jan-Michael Frahm (UNC Chapel Hill)
                       Sameer Agarwal (University of Washington)

Format (15 min. for presentation + 3 min. for questions)

  1. Progressive mode-seeking on graphs for sparse feature matching, Chao Wang, Lei Wang, Lingqiao Liu, University of Wollongong
  2. Globally Optimal Inlier Set Maximization With Unknown Rotation and Focal Length, Jean-Charles Bazin, ETH Zurich; Yongduek Seo, Songang University; Richard Hartley, ANU; Marc Pollefeys, ETH Zurich
  3. Match Selection and Refinement for Highly Accurate Two-View Structure from Motion, Zhe Liu, Pascal Monasse, Renaud Marlet, Ecole des Ponts ParisTech
  4. LSD-SLAM: Large-Scale Direct Monocular SLAM, Jakob Engel, Thomas Schöps, Daniel Cremers, TU Munich
    (These papers will also be presented in Poster Session 2B)

1230–1400       Lunch Break

1400-1600       Demos (Panoramasaal-Foyer)

  • LSD-SLAM: Large-Scale Direct Monocular SLAM, Jakob Engel (Technical University Munich), Thomas Schöps (Technical University Munich), Daniel Cremers (Technical University Munich)
  • 3D Pedestrian Detection via Random Forest, Gabriel Villalonga (Universitat Autònoma de Barcelona), Sebastian Ramos (Computer Vision Center (CVC) and Universitat Autònoma de Barcelona), Germán Ros (Computer Vision Center (CVC) and Universitat Autònoma de Barcelona, David Vázquez, Antonio M. López (Computer Vision Center (CVC) and Universitat Autònoma de Barcelona)
  • The DAVIS Vision Sensor, T. Delbruck (UZH-ETH Zurich), R. Berner (UZH-ETH Zurich), C. Brandli (UZH-ETH Zurich), V. Villenueva (UZH-ETH Zurich), L. Longinotti (UZH-ETH Zurich), S.C. Liu (UZH-ETH Zurich), S.C. Liu (UZH-ETH Zurich)
  • In-air Gestures Around Unmodified Mobile Devices, Jie Song (ETH Zurich), Gábor Sörös (ETH Zurich), Fabrizio Pece (ETH Zurich), Sean R. Fanello (Microsoft Research Cambridge), Shahram Izadi (Microsoft Research Cambridge), Cem Keskin (Microsoft Research Cambridge), Otmar Hilliges (ETH Zurich)
  • GoCARB – A computer vision approach for counting carbohydrates, M. Anthimopoulos (University of Bern), J. Dehais (University of Bern), S. Shevchik (University of Bern), R. Botwey (University of Bern), P. A. Fiave (University of Bern), D. Duke (Roche Diagnostics Operations Inc, A. Greenburg), P. Diem (University of Bern), S. Mougiakakou (University of Bern)

1400–1645       Exhibits (Tagungszentrum)

Same as Monday afternoon Exhibits

1400–1645       Swiss Computer Vision Start-Up Event (Vestibul K)

1400–1645       Poster Video Spotlight Loop (Kongresssaal)

1400–1600       Poster Session 2B (Gartensaal 1-24, Panoramasaal 25-52)

  1. The 3D jigsaw puzzle: mapping large indoor spaces, Ricardo Martin Brualla, University of Washington; Yanling He, University of Washington; Bryan Russell, University of Washington; Steve Seitz, Washington/Google
  2. Pipe-Run Extraction and Reconstruction from Point Clouds, Rongqi Qiu, University of Southern California; Qian-Yi Zhou, Stanford University; Ulrich Neumann, University of Southern California
  3. Image-based 4-d Reconstruction Using 3-d Change Detection, Ali Osman Ulusoy, Brown University; Joseph Mundy, Brown University
  4. VocMatch: Efficient Multiview Correspondence for Structure from Motion, Michal Havlena, ETH Zurich; Konrad Schindler, ETH Zurich
  5. Robust Global Translations with 1DSfM, Kyle Wilson, Cornell University; Noah Snavely, Cornell University
  6. Comparing Salient Object Detection Results without Ground Truth, Long Mai, Portland State University; Feng Liu, Portland State University
  7. RGBD Salient Object Detection: A Benchmark and Algorithms, Houwen Peng, Bing Li, Weihua Xiong, Weiming Hu, Institute of Automation, CAS; Rongrong Ji, Xiamen University
  8. Saliency Detection with Flash and No-flash Image Pairs, Shengfeng He, City University of Hong Kong; Rynson Lau, City University of Hong Kong
  9. Alpha Matting of Motion-Blurred Objects in Bracket Sequence Images, Heesoo Myeong, Seoul National University; Stephen Lin, Microsoft Research Asia; Kyoung Mu Lee, Seoul National University
  10. An Active Patch Model for Real World Texture and Appearance Classification, Junhua Mao, UCLA; Jun Zhu, UCLA; Alan Yuille, UCLA;
  11. Material Classification based on Training Data Synthesized Using a BTF Database, Michael Weinmann, Juergen Gall, Reinhard Klein, University of Bonn
  12. Déjá Vu: Motion Prediction in Static Images, Silvia Pintea, Jan van Gemert, Arnold Smeulders, University of Amsterdam
  13. Transfer Learning Based Visual Tracking with Gaussian Process Regression, Jin Gao, Institute of Automation, CAS; Haibin Ling, Temple University; Weiming Hu, Institute of Automation, CAS; Junliang Xing, NLPR, IACAS
  14. Separable Spatiotemporal Priors for Convex Reconstruction of Time-Varying 3D Point Clouds, Tomas Simon, Carnegie Mellon University; Jack Valmadre, CSIRO; Iain Matthews, Carnegie Mellon University; Yaser Sheikh, Carnegie Mellon University
  15. Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation, Michael Hornacek, TU Vienna; Frederic Besse, University College London; Jan Kautz, University College London; Andrew Fitzgibbon, Microsoft Research; Carsten Rother, TU Dresden
  16. Local Estimation of High Velocity Optical Flow with Correlation Image Sensor, Hidekata Hontani, Nagoya Institute of Technology; Go Oishi, Nagoya Institute of Technology; Tomohiro Kitagawa, Nagoya Institute of Technology
  17. Rank Minimization with Structured Data Patterns, Viktor Larsson, Carl Olsson, Erik Bylow, Fredrik Kahl, Lund University
  18. Duality and the Continuous Graphical Model, Alexander Fix, Cornell University; Sameer Agarwal, Google
  19. Spectral Clustering with a Convex Regularizer on Millions of Images, Maxwell D. Collins, University of Wisconsin-Madison; Ji Liu, University of Rochester; Jia Xu, UW-Madison; Lopamudra Mukherjee, University of Wisconsin Whitewater; Vikas Singh, University of Wisconsin-Madison
  20. Riemannian Sparse Coding of Positive Definite Matrices, Anoop Cherian, INRIA; Suvrit Sra, MPI Tuebingen
  21. Robust Sparse Coding and Compressed Sensing with the Difference Map, Will Landecker, Portland State University; Rick Chartrand, Los Alamos National Laboratory; Simon DeDeo, Indiana University
  22. Object Co-Detection via Efficient Inference in a Fully-Connected CRF, Zeeshan Hayder, ANU-Nicta; Mathieu Salzmann, NICTA; Xuming He, NICTA
  23. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, Kaiming He, Microsoft Research Asia; Xiangyu Zhang, Xi’an Jiaotong University; Shaoqing Ren, USTC; Jian Sun, Microsoft Research China
  24. Context as Supervisory Signal: Discovering Objects with Predictable Context, Carl Doersch, Carnegie Mellon University; Abhinav Gupta, Carnegie Mellon University; Alexei Efros, UC Berkeley
  25. Learning to Hash with Partial Tags: Exploring Correlation Between Tags and Hashing Bits for Large Scale Image Retrieval, Qifan Wang, Purdue University; Luo Si, Purdue University; Zhang Dan, Facebook
  26. Multi-Class Open Set Recognition using Probability of Inclusion, Lalit Jain, University of Colorado Colorado Springs; Walter Scheirer, Harvard University; Terrance Boult, University of Colorado Colorado Springs
  27. Sequential Max-Margin Event Detectors, Dong Huang, Shitong Yao, Yi Wang, Fernando de la Torre, Carnegie Mellon University
  28. Which Looks Like Which: Exploring Inter-Class Relationships in Fine-Grained Visual Categorization, Jian Pu, Chinese Academy Of Sciences; Yu-Gang Jiang, Fudan University; Jun Wang, IBM Research Center; Xiangyang Xue, Fudan University
  29. Object Detection and Viewpoint Estimation with Auto-masking Neural Network, Linjie Yang, CUHK; Jianzhuang Liu, Huawei Technologies Co. Ltd.; Xiaoou Tang, Chinese University of Hong Kong
  30. Statistical and Spatial Consensus Collection for Detector Adaptation, Enver Sangineto, DISI, University of Trento
  31. Deep Learning of Scene-specific Classifier for Pedestrian Detection, Xingyu Zeng, Wanli Ouyang, Meng Wang, Xiaogang Wang, The Chinese University of Hong Kong
  32. A Contour Completion Model for Augmenting Surface Reconstructions, Nathan Silberman, New York University Lior Shapira, Microsoft Research; Ran Gal, Microsoft Research; Pushmeet Kohli, Microsoft Research UK;
  33. Interactive Object Counting, Carlos Arteta, University of Oxford; Victor Lempitsky, Skolkovo Institute of Science and Technology; Alison Noble, Oxford University; Andrew Zisserman, Oxford University
  34. Recognizing City Identity Via Attribute Analysis of Geo-tagged Images, Bolei Zhou, MIT; Liu Liu, MIT; Aude Oliva, MIT; Antonio Torralba, MIT
  35. A Fast and Simple Algorithm for Producing Candidate Regions, Boyan Bonev, UCLA; Alan Yuille, UCLA
  36. Closed-Form Approximate CRF Training for Scalable Image Segmentation, Alexander Kolesnikov, IST Austria; Matthieu Guillaumin, ETH Zurich; Vittorio Ferrari, University of Edinburgh; Christoph Lampert, IST Austria
  37. A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies using a Hybrid Generative-Descriptive Model, Ümit Ruşen Aktaş, Mete Ozay, Aleš Leonardis; Jeremy Wyatt, University of Birmingham
  38. Finding Approximate Convex Shapes in RGBD Images, Hao Jiang, Boston College
  39. ShapeForest: Building constrained Statistical Shape Models with Decision Trees, Sasa Grbic, Siemens; Joshua Swee, Siemens; Razvan Ionasec, Siemens
  40. Optimizing Ranking Measures for Compact Binary Code Learning, Guosheng Lin, The University of Adelaide; Chunhua Shen, University of Adelaide; Jianxin Wu, Nanjing University
  41. Exploiting Low-rank Structure from Latent Domains for Domain Generalization, Zheng Xu, Wen Li, Li Niu, Dong Xu, Nanyang Technological University, Singapore
  42. Sparse Additive Subspace Clustering, Xiao-Tong Yuan, NUIST; Ping Li, Rutgers University
  43. Boosting VLAD with Supervised Dictionary Learning and High-OrderStatistics, Xiaojiang Peng, Southwest Jiaotong University; Limin Wang, The chinese University of Hong Kong; Yu Qiao, Shenzhen Institutes of Advanced Technology, Chinese Academy of Science; Qiang Peng, , Southwest Jiaotong University
  44. Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences, Kuan-Ting Lai, National Taiwan University; Dong Liu, Columbia University; Ming-Syan Chen, Academia Sinica; Shih-Fu Chang, Columbia University
  45. A Hierarchical Representation for Future Action Prediction, Tian Lan, Tsung-Chuan Chen, Silvio Savarese, Stanford University
  46. Continuous Learning of Human Activity Models using Deep Nets, Mahmudul Hasan, UC Riverside; Amit Roy-Chowdhury, UC Riverside
  47. DaMN – Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition, Rui Hou, UCF; Amir Roshan Zamir, UCF; Rahul Sukthankar, Google; Mubarak Shah, UCF
  48. Spatio-Temporal Object Detection Proposals, Dan Oneata, INRIA; Jerome Revaud, INRIA; Jakob Verbeek, INRIA Rhone-Alpes; Cordelia Schmid, INRIA

1600-1645        Coffee Break

1645–1815       Oral Session 2B: Computational Photography and Low-Level Vision (Kongresssaal)

Chairs:      Jason Corso (SUNY Buffalo)
                      Kyros Kutulakos (University of Toronto)

Format (15 min. for presentation + 3 min. for questions)

  1. Depth-of-Field Analysis and Coded Aperture Imaging on XSlit Lens, Jinwei Ye, Yu Ji, Wei Yang, Jingyi Yu, University of Delaware
  2. Refraction Wiggles for Measuring Fluid Depth and Velocity from Video, Tianfan Xue, MIT; Michael Rubinstein, MIT; Neal Wadhwa, MIT; Anat Levin, Weizmann Institute of Science; Fredo Durand, MIT; William T. Freeman, MIT
  3. Blind deblurring using internal patch recurrence, Tomer Michaeli, Michal Irani, Weizmann Institute of Science
  4. Crisp Boundary Detection Using Pointwise Mutual Information, Phillip Isola, Daniel Zoran, Dilip Krishnan, Edward H. Adelson, MIT
  5. Rolling Guidance Filter, Qi Zhang, Xiaoyong Shen, Li Xu, Jiaya Jia, Chinese University of Hong Kong


Wednesday, September 10


0830–1830       Registration (Vestibul K)

0830-1115        Demos (Panoramasaal-Foyer)

  • Collaborative SfM Reconstruction & Accurate, Real-Time Pose Estimation for Mobile Devices, Sven Middelberg (RWTH Aachen University), Ole Untzelmann (RWTH Aachen University), Leif Kobbelt (RWTH Aachen University), Torsten Sattler (ETH Zurich)
  • Live object detection and 6D pose estimation using 3D object coordinates, Eric Brachmann (TU Dresden), Alexander Krull (TU Dresden), Frank Michel (TU Dresden), Stefan Gumhold (TU Dresden), Jamie Shotton (Microsoft Research, Cambridge), and Carsten Rother (TU Dresden)
  • Automatic Geometrical Model Segmentation, Façade-Parsing and LOD3 Model Generation from 3D Point Clouds, William Nguatem (Bundeswehr University Munich), Martin Drauschke (Bundeswehr University Munich), Helmut Mayer (Bundeswehr University Munich)

0830–1115       Exhibits (Tagungszentrum)

Same as Monday afternoon Exhibits

0830–1115       Poster Video Spotlight Loop (Kongresssaal)

0830–1115       Poster Session 3A  (Gartensaal: posters 1-24, Panoramasaal: posters 25-51)

  1. Physically Grounded Spatio-Temporal Object Affordances, Hema S. Koppula, Cornell University; Saxena Ashutosh, Cornell University
  2. Schwarps: Locally Projective Image Warps Based on 2D Schwarzian Derivatives, Rahat Khan, Daniel Pizarro-Perez, Adrien Bartoli, Université d’Auvergne
  3. gDLS: A Scalable Solution to the Generalized Pose and Scale Problem, Chris Sweeney, Victor Fragoso, Tobias Hollerer, Matthew Turk, UC Santa Barbara USA
  4. Generalized Connectivity Constraints for Spatio-temporal Multi-View 3D Reconstruction, Martin Ralf Oswald, Jan Stühmer, Daniel Cremers, TU München;
  5. Passive Tomography of Turbulence Strength, Marina Alterman, Institute of Technology Israel; Yoav Schechner, Technion Israel; Minh Vo, CMU; Srinivas Narasimhan, CMU
  6. A Non-local Method for Robust Noisy Image Completion, Wei Li, Zhejiang University; Lei Zhao, Zhejiang University; Duanqing Xu, Zhejiang University; Dongming Lu, Zhejiang University
  7. Improved Motion Invariant Deblurring through Motion Estimation, Scott McCloskey, Honeywell
  8. Consistent Matting for Light Field Image, Donghyeon Cho, KAIST; Sunyeong Kim, KAIST; Yu-Wing Tai, KAIST
  9. Consensus of Regression for Occlusion-Robust Facial Feature Localization, Xiang Yu, Rutgers University; Zhe Lin, Adobe Research; Jonathan Brandt, Adobe Research; Dimitris Metaxas, Rutgers University
  10. Learning the Face Prior for Bayesian Face Recognition, Chaochao Lu, Xiaoou Tang, The Chinese University of Hong Kong
  11. Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity, Laszlo Jeni, Carnegie Mellon University; András Lőrincz; Zoltán Szabó, University College London; Jeffrey Cohn, University of Pittsburgh; Takeo Kanade, Carnegie Mellon University
  12. Feature Disentangling Machine – A Novel Approach of Feature Selection and Disentangling in Facial Expression Analysis, Ping Liu, University ofSouth Carolina; Joey Tianyi Zhou, Nanyang Technological University; Ivor Wai-Hung Tsang, University of Technology, Australia; Zibo Meng, Shizhong Han, Yan Tong, University of South Carolina;
  13. Joint Unsupervised Face Alignment and Behaviour Analysis, Lazaros Zafeiriou, Epameinondas Antonakos, Stefanos Zafeiriou, Maja Pantic, Imperial College London
  14. Learning a Deep Convolutional Network for Image Super-Resolution, Chao Dong, The Chinese University of Hong Kong; Chen-Change Loy, The Chinese University of Hong Kong; Kaiming He, Microsoft Research; Xiaoou Tang, The Chinese University of Hong Kong
  15. Discriminative Indexing for Probabilistic Image Patch Priors, Yan Wang, Columbia University; Sunghyun Cho, Adobe; Jue Wang, Adobe Research; Shih-Fu Chang, Columbia University
  16. Modeling Video Dynamics with Deep Dynencoder, Xing Yan, Chinese Academy of Sciences; Hong Chang, Chinese Academy of Sciences; Shiguang Shan, Chinese Academy of Sciences; Xilin Chen, Chinese Academy of Sciences
  17. Good Image Priors for Non-blind Deconvolution: Generic vs Specific, Libin Sun, Brown University; Sunghyun Cho, Adobe; Jue Wang, Adobe Research; James Hays, Brown University
  18. Image Deconvolution Ringing Artifact Detection and Removal via PSF Frequency Analysis, Ali Mosleh, Ecole Polytechnique Montréal; J.M. Pierre Langlois, Ecole Polytechnique Montréal; Paul Green, Algolux
  19. View-Consistent 3D Scene Flow Estimation over Multiple Frames, Christoph Vogel, ETH Zurich; Stefan Roth, TU Darmstadt; Konrad Schindler, ETH Zurich
  20. Hand Waving Away Scale, Christopher Ham, University of Queensland; Simon Lucey, Carnegie Mellon University; Surya Singh, University of Queensland
  21. A Non-Linear Filter for Gyroscope-Based Video Stabilization, Steven Bell, Stanford University; Alejandro Troccoli, NVIDIA; Kari Pulli, NVIDIA
  22. Multi-Modal and Multi-Spectral Registration for Natural Images, Xiaoyong Shen, Li Xu, Qi Zhang, Jiaya Jia, Chinese University of Hong Kong
  23. Using Isometry to Classify Correct/Incorrect 3D-2D Correspondences Toby Collins, ALCoV, ISIT; Adrien Bartoli, Universite d’Auvergne
  24. Bilateral Functions for Global Motion Modeling, Daniel Lin, ADSC; Ming-Ming Cheng, University of Oxford; Jiangbo Lu, ADSC Singapore; Hongsheng Yang, UNC Chapel Hill; Do Minh, University of Illinois at Urbana-Champaign; Philip Torr, University of Oxford
  25. VCDB: A Large-Scale Database for Partial Copy Detection in Videos, Yu-Gang Jiang, Yudong Jiang, Jiajun Wang, Fudan University;
  26. Single-Image Super-Resolution: A Benchmark, Chih-Yuan Yang, University of California at Merced; Chao Ma, Shanghai Jiao Tong University; Ming-Hsuan Yang, UC Merced
  27. Well Begun is Half Done: Generating High-Quality Seeds for Automatic Image Dataset Construction from Web, Yan Xia, USTC; Xudong Cao, MSRA; Fang Wen, MSRA; Jian Sun, Microsoft Research China
  28. Zero-Shot Learning via Visual Abstraction, Stanislaw Antol, Virginia Tech; Larry Zitnick, Microsoft Research Redmond; Devi Parikh, Virginia Tech
  29. Discovering Groups of People in Images, Wongun Choi, NEC Labs; YuWei Chao, University of Michigan; Caroline Pantofaru, Google; Silvio Savarese, Stanford University
  30. Untangling Object-View Manifold for Multiview Recognition and Pose Estimation, Amr Bakry, Rutgers University; Ahmed Elgammal, Rutgers University
  31. Parameterizing Object Detectors in the Continuous Pose Space, Kun He, Boston University; Leonid Sigal, Disney Research; Stan Sclaroff, Boston University
  32. Jointly Optimizing 3D Model Fitting and Fine-Grained Classification, Yenliang Lin, NTU; Vlad Morariu, University of Maryland; Winston Hsu, National Taiwan University; Larry Davis, University of Maryland USA
  33. Pipelining Localized Semantic Features for Fine-Grained Action Recognition, Yang Zhou, UTSA; Bingbing Ni, ADSC Singapore; Shuicheng Yan, National University of Singapore; Pierre Moulin, UIUC; Qi Tian, UTSA
  34. Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees, Weilin Huang, Chinese Academy of Sciences; Yu Qiao, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Xiaoou Tang, CUHK
  35. Deep Features for Text Spotting, Max Jaderberg, University of Oxford; Andrea Vedaldi, Oxford; Andrew Zisserman, Oxford
  36. Improving Image-Sentence Embeddings Using Large Weakly Annotated Photo Collections, Yunchao Gong, UNC Chapel Hill; Liwei Wang, UIUC; Micah Hodosh, UIUC; Julia Hockenmaier, UIUC; Svetlana Lazebnik, UIUC
  37. Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features, Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van den Hengel, The University of Adelaide
  38. Selecting Influential Examples: Active Learning with Expected Model Output Changes, Alexander Freytag, FSU Jena; Erik Rodner, Computer Vision Group, University of Jena; Joachim Denzler, FSU Jena
  39. Efficient Sparsity Estimation via Marginal-Lasso Coding, Tzu-Yi Hung, Nanyang Technological Univ.; Jiwen Lu, ADSC; Yap-Peng Tan, NTU, Singapore; Shenghua Gao, Shanghai Tech University
  40. Continuous Conditional Neural Fields for Structured Regression, Tadas Baltrusaitis, University of Cambridge; Peter Robinson, University of Cambridge; Louis-Philippe Morency, University of Southern California
  41. Learning to Rank using High-Order Information, Puneet Kumar Dokania, Ecole Centrale de Paris and INRIA Saclay; Aseem Behl, IIIT, Hyderabad; C.V. Jawahar, IIIT Hyderabad; M. Pawan Kumar, Ecole Centrale Paris INRIA Saclay
  42. Support Vector Guided Dictionary Learning, Sijia Cai, Tianjin University; Wangmeng Zuo, Harbin Institute of Technology; Lei Zhang, The Hong Kong Polytechnic University; Xiangchu Feng, Xidian University; Ping Wang, Tianjin University
  43. Video Object Discovery and Co-segmentation with Extremely Weak Supervision, Le Wang, Xi’an Jiaotong University; Gang Hua, Stevens Institute of Technology; Rahul Sukthankar, Google; Jianru Xue, Xi’an Jiaotong University; Nanning Zheng, Xi’an Jiaotong University
  44. Supervoxel-Consistent Foreground Propagation in Video, Suyog Jain, University of Texas at Austin; Kristen Grauman, University of Texas at Austin
  45. Clustering with Hypergraphs: The Case for Large Hyperedges, Pulak Purkait, The University of Adelaide; Tat-Jun Chin, University of Adelaide; Hanno Ackermann, Leibniz University Hannover; David Suter, The University of Adelaide
  46. Person Re-Identification by Video Ranking, Taiqing Wang, Tsinghua University; Shaogang Gong, Queen Mary University of London; Xiatian Zhu, Queen Mary University of London; Shengjin Wang, Tsinghua University

1045-1115        Coffee break

1115–1230       Oral Session 3A: Vision (Kongresssaal)

Chairs:        Peter Gehler (Max Planck Institute Tuebingen)
                        Jamie Shotton (Microsoft)

Format (15 min. for presentation + 3 min. for questions)

  1. Bayesian Nonparametric Intrinsic Image Decomposition, Jason Chang, Randi Cabezas, John Fisher, MIT
  2. Face detection without bells and whistles, Markus Mathias, KULeuven; Rodrigo Benenson, MPI-Saarbruecken, Marco Pedersoli, KULeuven; Luc Van Gool, KULeuven/ETH Zurich
  3. On image contours of projective shapes, Jean Ponce, ENS/INRIA, Martial Hebert, CMU
  4. Programmable Automotive Headlights, Robert Tamburo, Eriko Nurvitadhi, Abhishek Chugh, Mei Chen, Anthony Rowe, Takeo Kanade, Srinivasa Narasimhan, CMU

1230-1400       Lunch Break

1400-1600       Demos (Panoramasaal-Foyer)

  • Real-Time Minimization of the Piecewise Smooth Mumford-Shah Functional, Evgeny Strekalovskiy (Technical University Munich), Daniel Cremers (Technical University Munich)
  • Slot Car Racer, T. Delbruck (UZH-ETH Zurich), R. Berner (UZH-ETH Zurich), C. Brandli (UZH-ETH Zurich), V. Villenueva (UZH-ETH Zurich), L. Longinotti (UZH-ETH Zurich), S.C. Liu (UZH-ETH Zurich)
  • Fast Large-Scale Convolutional Object Detection, Judy Hoffman (UC Berkley), Sergio Guadaramma (UC Berkley), Jonathan Long (UC Berkley), Jeff Donahue (UC Berkley), Eric Tzeng (UC Berkley), Ross Girshick (UC Berkley), Kate Saenko (UC Berkley), Trevor Darrell (UC Berkley)
  • SVO: Fast Semi-Direct Monocular Visual Odometry, C. Forster (University of Zurich), M. Pizzoli (University of Zurich), D. Scaramuzza (University of Zurich)

 

1400–1645       Exhibits (Tagungszentrum)

Same as Monday afternoon Exhibits

1400–1645       Poster Video Spotlight Loop (Kongresssaal)

1400–1645       Poster Session 3B (Gartensaal:  posters 1-24, Panoramasaal: posters 25-52)

  1. ROCHADE: Robust Checkerboard Advanced Detection for Camera Calibration, Simon Placht, Metrilus GmbH; Peter Fürsattel, Universität Erlangen-Nürnberg; Etienne Assoumou Mengue, Pattern Recognition Lab; Hannes Hofmann, Metrilus GmbH; Christian Schaller, Metrilus GmbH; Michael Balda, Metrilus GmbH; Elli Angelopoulou, University of Erlangen
  2. Correcting for Duplicate Scene Structure in Sparse 3D Reconstruction, Jared Heinly, UNC Chapel Hill; Enrique Dunn, UNC Chapel Hill; Jan-Michael Frahm, UNC Chapel Hill
  3. Total Moving Face Reconstruction, Supasorn Suwajanakorn, University of Washington; Ira Kemelmacher, University of Washington; Steve Seitz, Washington/Google
  4. Automatic Single-View Calibration and Rectification from Parallel Planar Curves, Eduardo Corral-Soto, York University; James Elder, York University
  5. On Sampling Focal Length Values to Solve the Absolute Pose Problem, Torsten Sattler, ETH Zurich; Chris Sweeney, UC Santa Barbara; Marc Pollefeys, ETH Zurich
  6. Video Registration to SfM Models, Till Kroeger, ETH Zurich; Luc Van Gool, Computer Vision Lab, ETH Zurich
  7. Soft Cost Aggregation with Multi-Resolution Fusion, Tan Xiao, UNSW; Sun Changming, CSIRO; Wang Dadong, CSIRO; Guo Yi, CSIRO; Pham Tuan, University of Aizu
  8. Inverse Kernels for Fast Spatial Deconvolution, Li Xu, Chinese University of Hong Kong; Xin Tao, CUHK; Jiaya Jia, CUHK
  9. Deep Network Cascade for Image Super-resolution, Zhen Cui, ICT, CAS; Hong Chang, ICT, CAS; Shiguang Shan, ICT, CAS; Bineng Zhong, Huaqiao University; Xilin Chen, ICT, CAS
  10. Spectral Edge Image Fusion: Theory and Applications, David Connah, University of Bradford; Mark Drew, Simon Fraser University; Graham Finlayson, University of East Anglia
  11. Spatio-Chromatic Opponent Features, Ioannis Alexiou, Imperial College London; Anil A. Bharath, Imperial College London
  12. Modeling Perceptual Color Differences by Local Metric Learning, Michaël Perrot, Amaury Habrard, Damien Muselet, Marc Sebban, Université Jean Monnet
  13. Online Graph-Based Tracking, Hyeonseob Nam, POSTECH; Seunghoon Hong, POSTECH; Bohyung Han, POSTECH
  14. Fast Visual Tracking via Dense Spatio-Temporal Context Learning, Kaihua Zhang, NUIST; Lei Zhang, The Hong Kong Polytechnic; Qingshan Liu, NUIST; David Zhang, Hong Kong Polytechnic; Ming-Hsuan Yang, UC Merced
  15. Extended Lucas-Kanade Tracking, Shaul Oron, Tel-Aviv University; Aharon Bar-Hillel, Microsoft; Shai Avidan, Tel-Aviv University
  16. Appearances can be deceiving: Learning visual tracking from few trajectory annotations, Santiago Manen, ETH Zurich; Junseok Kwon, ETH Zurich; Matthieu Guillaumin, ETH Zurich; Luc Van Gool, Computer Vision Lab, ETH Zurich
  17. Generalized Background Subtraction using Superpixels with Label Integrated Motion Estimation, Jongwoo Lim, Hanyang University; Bohyung Han, POSTECH
  18. Spectra Estimation of Fluorescent and Reflective Scenes by Using Ordinary Illuminants, Yinqiang Zheng, National Institute of Informatics; Imari Sato, National Institute of Informatics; Yoichi Sato, University of Tokyo
  19. Interreflection Removal Using Fluorescence, Ying Fu, The University of Tokyo; Antony Lam, National Institute of Informatics; Yasuyuki Matsushita, Microsoft Research Asia; Imari Sato, National Institute of Informatics; Yoichi Sato, University of Tokyo
  20. Intrinsic Face Image Decomposition with Human Face Priors, Chen Li, Zhejiang University; Kun Zhou, Zhejiang University; Stephen Lin, Microsoft Research Asia
  21. Recovering Scene Geometry under Wavy Fluid via Distortion and Defocus Analysis, Mingjie Zhang, Tsinghua University; Xing Lin, Tsinghua University; Mohit Gupta, Columbia University; Jinli Suo, Tsinghua University; Qionghai Dai, Tsinghua University
  22. Human Detection using Learned Part Alphabet and Pose Dictionary, Cong Yao, Huazhong University of Science and Technology; Xiang Bai, Huazhong University of Science and Technology; Wenyu Liu, HUST; Longin Jan Latecki, Temple University
  23. SPADE: Scalar Product Accelerator by Integer Decomposition for Object Detection, Mitsuru Ambai, Denso IT Laboratory, Inc.; Ikuro Sato, Denso IT Laboratory, Inc.
  24. Detecting Snap Points in Egocentric Video with a Web Photo Prior, Bo Xiong, University of Texas at Austin; Kristen Grauman, University of Texas at Austin
  25. Towards Unified Object Detection and Semantic Segmentation, Jian Dong, National University of Singapore; Qiang Chen, IBM; Shuicheng Yan, National University of Singapore; Alan Yuille, UCLA
  26. Foreground Consistent Human Pose Estimation using Branch and Bound, Jens Puwein, ETH Zurich; Luca Ballan, ETH Zurich; Remo Ziegler, Vizrt; Marc Pollefeys, ETH Zurich
  27. Human Pose Estimation with Fields of Parts, Martin Kiefel, Max Planck Institute for Intelligent Systems; Peter Gehler, Max Planck Institute for Intelligent Systems
  28. Unsupervised Video Adaptation for Parsing Human Motion, Haoquan Shen, Zhejiang University; Shoou-I Yu, Carnegie Mellon University; Yi Yang, University of Queensland; Deyu Meng, Xi’an Jiaotong University; Alex Hauptmann, Carnegie Mellon University
  29. Training object class detectors from eye tracking data, Dim Papadopoulos, University of Edinburgh; Alasdair D. Clarke, University of Edinburgh; Frank Keller, University of Edinburgh; Vittorio Ferrari, University of Edinburgh
  30. Depth Based Object Detection from Partial Pose Estimation of Symmetric Objects, Ehud Barnea, Ben-Gurion University, Israel; Ohad Ben-Shahar, Ben-Gurion University, Israel
  31. Edge Boxes: Locating Object Proposals from Edges, Larry Zitnick, Microsoft Research Redmond; Piotr Dollár, Miscrosoft Research Redmond
  32. Training Deformable Object Models for Human Detection based on Alignment and Clustering, Benjamin Drayer, University of Freiburg; Thomas Brox, University of Freiburg
  33. Predicting Actions from Static Scenes, Tuan-Hung Vu, WILLOW; Catherine Olsson, MIT CSAIL, NYU CNS; Ivan Laptev, INRIA Paris; Aude Oliva, MIT; Josef Sivic, INRIA
  34. Exploiting Privileged Information from Web Data for Image Cagegorization, Wen Li, Li Niu, Dong Xu, Nanyang Technological University
  35. Multi-modal Unsupervised Feature Learning for RGB-D Scene Labeling, Anran Wang, Nanyang Technological University; Jiwen Lu, ADSC; Gang Wang, Nanyang Technological University; Jianfei Cai, Nanyang Technological University; Tat-Jen Cham, Nanyang Technological University
  36. Discriminatively Trained Dense Surface Normal Estimation, Lubor Ladický, ETH Zurich; Bernhard Zeisl, ETH Zurich; Marc Pollefeys, ETH Zurich
  37. Numerical Inversion of SRNFs for Efficient Elastic Shape Analysis of Star-Shaped Objects, Qian Xie, Florida State University; Ian Jermyn, INRIA; Sebastian Kurtek, Ohio State University; Anuj Srivastava, Florida State University
  38. Non-Associative Higher-Order Markov Networks for Point Cloud Classification, Mohammad Najafi, NICTA – ANU; Sarah Taghavi Namin, NICTA – ANU; Mathieu Salzmann, NICTA; Lars Petersson, NICTA
  39. Learning Where To Classify In Multi-View Semantic Segmentation, Hayko Riemenschneider, Computer Vision Lab, ETH Zurich; Andras Bodis-Szomoru, Computer Vision Lab, ETH Zurich; Julien Weissenberg, Computer Vision Lab, ETH Zurich; Luc Van Gool, Computer Vision Lab, ETH Zurich
  40. Stixmantics: A Medium-Level Model for Real-Time Semantic Scene Understanding, Timo Scharwächter, Daimler AG; Markus Enzweiler, Daimler AG; Uwe Franke, Daimler AG; Stefan Roth, TU Darmstadt
  41. Sparse Dictionaries for Semantic Segmentation, Lingling Tao, Johns Hopkins University; Fatih Porikli, NICTA and ANU; Rene Vidal, Johns Hopkins University
  42. Video Action Detection with Relational Dynamic-Poselets, Limin Wang, CUHK; Yu Qiao, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Xiaoou Tang, Chinese University of Hong Kong
  43. Action Recognition with Stacked Fisher Vectors, Xiaojiang Peng, Southwest Jiaotong University; Changging Zou, Hengyang Normal University; Yu Qiao, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Qiang Peng, Southwest Jiaotong University
  44. A Discriminative Model with Multiple Temporal Scales for Action Prediction, Yu Kong, Northeastern University; Dmitry Kit, Northeastern University; Yun Fu, Northeastern University
  45. Seeing is Worse than Believing: Reading People’s Minds Better than Computer-Vision Methods Recognize Actions, Andrei Barbu, MIT; Daniel Barrett, Purdue University; Wei Chen, SUNY Buffalo; Narayanaswamy Siddharth, Purdue University; Caiming Xiong, SUNY at Buffalo; Jason Corso, University of Michigan; Christiane D. Fellbaum, Princeton University; Catherina Hanson, Rutgers University; Stephen José Hanson, Rutgers University; Sébastien Hélie, Purdue University; Evguenia Malaia, University of Texas at Arlington; Barak A. Pearlmutter, National University of Ireland Maynooth; Jeffrey Mark Siskind, Purdue University; Thomas Michael Talavage, Purdue University; Ronnie B. Wilbur, Purdue University
  46. Weakly Supervised Action Labeling in Videos Under Ordering Constraints, Piotr Bojanowski, INRIA; Remi Lajugie, INRIA; Francis Bach, ENS Paris; Ivan Laptev, INRIA Paris; Jean Ponce, ENS Paris; Cordelia Schmid, INRIA; Josef Sivic, INRIA
  47. Active Random Forests: An application to Autonomous Unfolding of Clothes, Andreas Doumanoglou, Imperial College London; Tae-Kyun Kim, Imperial College London; Xiaowei Zhao, Imperial College London; Sotiris Malassiotis, CERTH
  48. Model-Free Segmentation and Grasp Selection of Unknown Stacked Objects, Umar Asif, The University of Western Australia; Mohammed Bennamoun, The University of Western Australia; Ferdous Sohel, The University of Western Australia

1600–1645       Coffee break

1645–1815       Oral Session 3B: Segmentation and Saliency (Kongresssaal)

Chairs:       Thomas Brox (University of Freiburg)
                       Carsten Rother (TU Dresden)

Format (15 min. for presentation + 3 min. for questions)

  1. Convexity Shape Prior for Segmentation, Lena Gorelick, Olga Veksler, Yuri Boykov, University of Western Ontario; Claudia Nieuwenhuis, UC Berkeley
  2. Pseudo-Bound Optimization for Binary Energies, Meng Tang, Ismail Ben Ayed, Yuri Boykov, University of Western Ontario
  3. A Closer Look at Context: From Coxels to the Contextual Emergence of Object Saliency, Rotem Mairon, Ohad Ben-Shahar, Ben Gurion University
  4. Geodesic Object Proposals, Philipp Krähenbühl, Stanford University, Vladlen Koltun, Adobe
  5. Microsoft COCO: Common Objects in Context, Tsung-Yi Lin, Cornell Tech; Michael Maire, Caltech; Serge Belongie, Cornell Tech; James Hays, Brown University; Pietro Perona, Caltech; Deva Ramanan, UC Irvine; Piotr Dollár, Microsoft Research; Larry Zitnick, Microsoft Research

 

1900–2300       Conference Dinner  (ETH Polyterrasse)


Options for transportation from Kongresshaus to ETH Polyterasse:

Walk (some guides will be available)

 map_dinner

Public Transportation / Tram

map_dinner_vbz

  • Tram 9 from Burkliplatz to ETH/Unispital (dir. Hirzenbach)
  • Tram 5 from Burkliplatz to Platte (dir. Kirche Fluntern)
  • Tram 6 from Stockerstrasse to ETH/Unispital (dir. Zoo)
  • Tram 7 from Stockerstrasse to Central (dir. Bahnhof Stettbach), followed by Polybahn (funicular up to Polyterrasse, operates until 19:15)
  • Tram 4/15 from Bellevue to Central (dir. Bahnhof Altstetten), followed by Polybahn 

Thursday, September 11


0800-1730       Registration (Vestibul K)

0830-1115       Demos (Panoramasaal-Foyer)

  • 3D modeling on a mobile phone, Petri Tanskanen (ETH Zurich), Kalin Kolev (ETH Zurich), Amael Delaunoy (ETH Zurich), Marc Pollefeys (ETH Zurich)
  • Real-Time Scalable Edge-Based Object Detector (a light weight method on Android), Dima Damen (University of Bristol), Yannan Cui (University of Bristol), Ping Wang (University of Bristol), Teesid Leelasawassuk (University of Bristol) and Walterio Mayol-Cuevas (University of Bristol)
  • Mimic-Me: Affect-Sensitive Game with Humanoid Robot, Jie Shen (Imperial College London), Shiyang Cheng (Imperial College London), and Maja Pantic (Imperial College London)
  • The Chameleon Tracker in 3D, David Joseph Tan (TU München), Nassir Navab (TU München), Slobodan Ilic (Siemens CT)

 

0830–1115      Exhibits (Tagungszentrum)

Same as Monday afternoon Exhibits

0830–1115       Poster Video Spotlight Loop (Kongresssaal)

0830–1115       Poster Session 4A   (Gartensaal: posters 1-24, Panoramasaal: posters 25-51)

  1. Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation, Koichiro Yamaguchi, TTI Chicago; David McAllester, TTI-Chicago; Raquel Urtasun, University of Toronto
  2. Robust Bundle Adjustment Revisited, Christopher Zach, Toshiba Research Europe
  3. Accurate intrinsic calibration of depth camera with cuboids, Bingwen Jin, Zhejiang University; Hao Lei, Zhejiang University; Weidong Geng, Zhejiang University
  4. Statistical pose averaging with non-isotropic and incomplete relative measurements, Roberto Tron, University of Pennsylvania; Kostas Daniilidis, University of Pennsylvania
  5. A Pot of Gold: Rainbows as a Calibration Cue, Scott Workman, University of Kentucky; Radu Mihail, University of Kentucky; Nathan Jacobs, University of Kentucky
  6. Let There Be Color! – Large-Scale Texturing of 3D Reconstructions, Michael Waechter, TU Darmstadt; Nils Moehrle, TU Darmstadt; Michael Goesele, TU Darmstadt
  7. All-In-Focus Synthetic Aperture Imaging, Tao Yang, Northwestern Polytechnical University; Yanning Zhang, Northwestern Polytechnical University; Jingyi Yu, University of Delaware; Jing Li, Xidian University; Wenguang Ma, Northwestern Polytechnical University; Xiaomin Tong, Northwestern Polytechnical University; Rui Yu, University College London; Lingyan Ran, Northwestern Polytechnical University
  8. Photo Uncrop, Qi Shan, University of Washington; Brian Curless, University of Washington; Yasutaka Furukawa, Washington University; Carlos Hernandez, Google; Steve Seitz, Washington/Google
  9. Solving Square Jigsaw Puzzles with Loop Constraints, Kilho Son, Brown University; James Hays, Brown University; David Cooper, Brown University
  10. Geometric Calibration of Micro-Lens-Based Light-Field Cameras, Yunsu Bok, KAIST; Hae-Gon Jeon, KAIST; In So Kweon, KAIST
  11. Spatio-temporal Matching for Human Detection in Video, Feng Zhou, Carnegie Mellon University; Fernando de la Torre, Carnegie Mellon University
  12. Collaborative Facial Landmark Localization for Transferring Annotations Across Datasets, Brandon Smith, University of Wisconsin – Madison; Li Zhang, University of Wisconsin-Madison
  13. Facial Landmark Detection by Deep Multi-task Learning, Zhanpeng Zhang, The Chinese University of Hong Kong; Ping Luo, The Chinese University of Hong Kong; Chen-Change Loy, The Chinese University of Hong Kong; Xiaoou Tang, The Chinese University of Hong Kong
  14. Joint Cascade Face Detection and Alignment, Dong Chen, USTC; Shaoqing Ren, USTC; Yichen Wei, Microsoft Research Asia; Xudong Cao, MSRA; Jian Sun, Microsoft Research China
  15. Weighted Block-Sparse Low Rank Representation for Face Clustering in Videos, Shijie Xiao, NTU; Mingkui Tan, University of Adelaide; Dong Xu, Nanyang Technological University
  16. Crowd Tracking with Dynamic Evolution of Group Structures, Feng Zhu, USTC; Xiaogang Wang, Chinese University of Hong Kong; Nenghai Yu, University of Science and Technology of China
  17. Tracking using Multilevel Quantizations, Zhibin Hong, University of Technology, Sydney; Chaohui Wang, Max Planck Institute for Intelligent Systems; Xue Mei, TEMA TTC; Danil Prokhorov, TEMA TTC; Dacheng Tao, University of Technology, Sydney
  18. Occlusion and Motion Reasoning for Long-term Tracking, Yang Hua, INRIA; Karteek Alahari, INRIA; Cordelia Schmid, INRIA
  19. MEEM: Robust Tracking via Multiple Experts using Entropy Minimization, Jianming Zhang, Boston University; Shugao Ma, Boston University; Stan Sclaroff, Boston University
  20. Robust Motion Segmentation with Unknown Correspondences, Pan Ji, Australian National University; Hongdong Li, Australian National University; Mathieu Salzmann, NICTA; Yuchao Dai, Australian National University
  21. Monocular Multiview Object Tracking with 3D Aspect Parts, Yu Xiang, University of Michigan; Changkyu Song, University of Michigan; Roozbeh Mottaghi, Stanford University; Silvio Savarese, Stanford University
  22. Modeling Blurred Video with Layers, Jonas Wulff, Max Planck Institute for Intelligent Systems; Michael Black, Max Planck Institute for Intelligent Systems
  23. Efficient Image and Video Co-localization with Frank-Wolfe Algorithm, Armand Joulin, Stanford University; Kevin Tang, Stanford University; Fei-Fei Li, Stanford University
  24. Non-parametric Higher-order Random Fields for Image Segmentation, Pablo Márquez-Neila, Universidad Politecnica de Madrid; Pushmeet Kohli, Microsoft Research UK; Carsten Rother, TU Dresden; Luis Baumela, Universidad Politecnica de Madrid
  25. Co-Sparse Textural Similarity for Interactive Segmentation, Claudia Nieuwenhuis, UC Berkeley; Simon Hawe, TU Munich; Martin Kleinsteueber, TU Munich; Daniel Cremers, TU Munich; 
  26. A Convergent Incoherent Dictionary Learning Algorithm for Sparse Coding, Chenlong Bao, National University of Singapore; Yuhui Quan, National University of Singapore; Hui Ji, National University of Singapore;
  27. Free-Shape Polygonal Object Localization, Xiaolu Sun, EPFL; Mario Christoudias, EPFL; Pascal Fua, EPFL
  28. Interactively Guiding Semi-Supervised Clustering via Attribute-based Explanations, Shrenik Lad, Virginia Tech; Devi Parikh, Virginia Tech
  29. Attributes make sense on segmented objects, Zhenyang Li, University of Amsterdam; Efstratios Gavves, University of Amsterdam; Thomas Mensink, University of Amsterdam; Cees Snoek, University of Amsterdam
  30. Towards Transparent Systems: Semantic Characterization of Failure Modes, Aayush Bansal, Carnegie Mellon University; Ali Farhadi, University of Washington; Devi Parikh, Virginia Tech
  31. Orientation covariant aggregation of local descriptors with embeddings, Giorgos Tolias, INRIA; Teddy Furon, INRIA; Hervé Jégou, INRIA Rennes
  32. Similarity-invariant Sketch-based Image Retrieval in Large Databases, Sarthak Parui, IIT Madras; Anurag Mittal, IIT Madras
  33. Discovering Object Classes from Activities, Abhilash Srikantha, University of Bonn; Juergen Gall, University of Bonn
  34. Weakly Supervised Object Localization with Latent Category Learning, Chong Wang, NLPR, CASIA; Weiqiang Ren, CASIA, CRIPAC; Kaiqi Huang, National Laboratory of Pattern Recognition; Tieniu Tan, NLPR China
  35. Food-101 – Mining Discriminative Components with Random Forests, Lukas Bossard, ETH Zurich; Matthieu Guillaumin, ETH Zurich; Luc Van Gool, Computer Vision Lab, ETH Zurich
  36. Latent-Class Hough Forests for 3D Object Detection and Pose Estimation, Alykhan Tejani, Imperial College London; Tang Tang, Imperial College London; Rigas Kouskouridas, Imperial College London; Tae-Kyun Kim, Imperial College London
  37. FPM: Fine pose Part-based Model with 3D CAD models, Joseph Lim, MIT; Aditya Khosla, MIT; Antonio Torralba, MIT
  38. Learning High-level Judgments of Urban Perception, Vicente Ordonez, UNC Chapel Hill; Tamara Berg, UNC Chapel Hill
  39. CollageParsing: Nonparametric scene parsing by adaptive overlapping windows, Frederick Tung, University of British Columbia; Jim Little, University of British Columbia
  40. Discovering Video Clusters from Visual Features and Noisy Tags, Arash Vahdat, Simon Fraser University; Guang-Tong Zhou, Simon Fraser University; Greg Mori, Simon Fraser University
  41. Category-specific video summarization, Danila Potapov, INRIA; Matthijs Douze, INRIA; Zaid Harchaoui, INRIA; Cordelia Schmid, INRIA
  42. Assessing the Quality of Actions, Hamed Pirsiavash, MIT; Carl Vondrick, MIT; Antonio Torralba, MIT
  43. HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos, Mohamed Amer, Oregon State University; Peng Lei, Oregon State University; Sinisa Todorovic, Oregon State University
  44. Part Bricolage: Flow-assisted Part-based Graphs for Detecting Activities in Videos, Sukrit Shankar, University of Cambridge; Vijay Badrinarayanan, University of Cambridge; Roberto Cipolla, University of Cambridge
  45. GIS-assisted Object Detection and geospatial localization, Shervin Ardeshir, University of Central Florida; Amir Roshan Zamir, CRCV at UCF; Alejandro Torroella, UCF; Mubarak Shah, University of Central Florida
  46. Context-based Pedestrian Path Prediction, Julian Francisco Kooij, University of Amsterdam; Nicolas Schneider, Daimler AG; Fabian Flohr, Daimler AG; Dariu Gavrila, University of Amsterdam

 

1030–1115       Coffee Break

1115–1230       Oral session 4A: Context and 3D Scenes (Kongresssaal)

Chairs:       Lourdes Agapito (University College London)
                       Hongdong Li (Australian National University)

Format (15 min. for presentation + 3 min. for questions)

  1. Sliding Shapes for 3D Object Detection in Depth Images, Shuran Song, Jianxiong Xiao, Princeton University
  2. Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model, Bo Li, BIT/UCLA; Tianfu Wu, UCLA; Song-Chun Zhu, UCLA
  3. PanoContext: A Whole-room 3D Context Model for Panoramic Scene Understanding, Yinda Zhang, Shuran Song, Ping Tan, Jianxiong Xiao, Princeton University
  4. Unfolding an Indoor Origami World, David Ford Fouhey, Abhinav Gupta, Martial Hebert, CMU

1230–1400       Lunch break

1400–1645       Poster Video Spotlight Loop (Kongresssaal)

1400–1645       Poster Session 4B  (Gartensaal: posters 1-24, Panoramasaal: posters 25-52)

  1. Joint Semantic Segmentation and 3D Reconstruction from Monocular Video, Abhijit Kundu, Georgia Institute of Technology; Yin Li, Georgia Institute of Technology; Frank Dellaert, Georgia Institute of Technology; Fuxin Li, Georgia Institute of Technology; James Rehg, Georgia Institute of Technology
  2. A New Variational Framework for Multiview Surface Reconstruction, Ben Semerjian, Urban Robotics
  3. Multi-Body Depth-Map Fusion with Non-Intersection Constraints, Bastien Jacquet, ETH Zurich; Christian Häne, ETH Zürich; Roland Angst, Stanford University; Marc Pollefeys, ETH Zurich
  4. Shape from Light Field meets Robust PCA, Stefan Heber, TU Graz; Thomas Pock, TU Graz
  5. Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval, Bor-Chun Chen, Academia Sinica, Taiwan; Chu-Song Chen, Academia Sinica; Winston Hsu, National Taiwan University
  6. Reverse Training: An efficient Approach for Image Set Classification, Munawar Hayat, UWA; Mohammed Bennamoun, University of Western Australia; Senjian An, University of Western Australia
  7. Real-Time Exemplar-Based Face Sketch Synthesis, Yibing Song, City University of Hong Kong; Linchao Bao, City University of Hong Kong; Qingxiong Yang, City University of Hong Kong; Ming-Hsuan Yang, UC Merced
  8. Domain-adaptive Discriminative One-shot Learning of Gestures, Tomas Pfister, University of Oxford; James Charles, University of Leeds; Andrew Zisserman, University of Oxford
  9. Person Re-Identification using Kernel-based Metric Learning Methods, Fei Xiong, Northeastern University; Mengran Gou, Northeastern University; Octavia Camps, Northeastern University; Mario Sznaier, Northeastern University
  10. Saliency in crowd, Ming Jiang, NUS; Juan Xu, NUS; Qi Zhao, NUS
  11. Webpage Saliency, Chengyao Shen, National University of Singapore; Qi Zhao, NUS
  12. Deblurring Face Images with Exemplars, Jinshan Pan, DLUT; Zhe Hu, UC Merced; Zhixun Su, Dalian University of Technology; Ming-Hsuan Yang, UC Merced
  13. Sparse Spatio-spectral Representation for Hyperspectral Image Super-Resolution, Naveed Akhtar, The University of Western Australia; Faisal Shafait, The University of Western Australia; Ajmal Mian, UWA
  14. Hybrid Image Deblurring by Fusing Edge and Power Spectrum Information, Tao Yue, Tsinghua University; Sunghyun Cho, Adobe; Jue Wang, Adobe Research; Qionghai Dai, Tsinghua University
  15. Affine Subspace Representation for Feature Description, Zhenhua Wang, NLPR, CASIA; Bin Fan, NLPR, CASIA; Fuchao Wu, NLPR, CASIA
  16. A Generative Model for the Joint Registration of Multiple Point Sets, Georgios Evangelidis, INRIA; Dionyssos Kounades- Bastian, INRIA; Radu Horaud, INRIA; Emmanouil Psarakis, University of Patras
  17. Change Detection in the Presence of Motion Blur and Rolling Shutter Effect, Vijay Rengarajan Angarai Pichaikuppan, IIT Madras; Rajagopalan Ambasamudram Narayanan, IIT Madras; Aravind Rangarajan, IIT Madras
  18. An Analysis of Errors in Graph-based Keypoint Matching and Proposed Solutions, Toby Collins, ALCoV, ISIT; Pablo Mesejo, University of Clermont; Adrien Bartoli, Universite d’Auvergne
  19. OpenDR: An Approximate Differentiable Renderer Matthew Loper, Max Planck Institute for Intelligent Systems; Michael Black, Max Planck Institute for Intelligent Systems
  20. A Superior Tracking Approach: Building a strong Tracker through Fusion, Christian Bailer, DFKI; Alain Pagani, DFKI; Didier Stricker, DFKI
  21. Training-Based Spectral Reconstruction from a Single RGB Image, Rang Nguyen, NUS (Singapore); Dilip Prasad, NUS; Michael Brown, NUS
  22. On Shape and Material Recovery from Motion, Manmohan Chandraker, NEC Labs America
  23. Intrinsic Image Decomposition using Structure-Texture Separation and Surface Normals, Junho Jeon, POSTECH; Sunghyun Cho, Adobe Research; Xin Tong, Microsoft Asia; Seungyong Lee, POSTECH
  24. Multi-level Adaptive Active Learning for Scene Classification, Xin Li, Yuhong Guo, Temple University
  25. Graph Cuts for Supervised Binary Coding, Tiezheng Ge, USTC; Kaiming He, Microsoft Research Asia; Jian Sun, Microsoft Research
  26. Planar Structure Matching Under Projective Uncertainty for Geolocation, Ang Li, University of Maryland; Vlad Morariu, University of Maryland; Larry S. Davis, University of Maryland
  27. Active Deformable Part Models Inference, Menglong Zhu, University of Pennsylvania; Nikolay Atanasov, University of Pennsylvania; George Pappas, University of Pennsylvania; Kostas Daniilidis, University of Pennsylvania
  28. Simultaneous Detection and Segmentation, Bharath Hariharan, UC Berkeley; Pablo Arbeláez, UC Berkeley; Ross Girshick, UC Berkeley; Jitendra Malik, UC Berkeley
  29. Learning Graphs to Model Visual Objects Across Different Depictive Styles, Qi Wu, University of Bath; Hongping Cai, University of Bath; Peter Hall, University of Bath
  30. Analyzing The Performance of Multi Layer Neural Networks for Object Recognition, Pulkit Agrawal, UC Berkeley; Ross Girshick, UC Berkeley; Jitendra Malik, UC Berkeley
  31. Learning Rich Features from RGB-D Images for Object Detection andSegmentation, Saurabh Gupta, UC Berkeley; Ross Girshick, UC Berkeley; Pablo Arbelaez, UC Berkeley; Jitendra Malik, UC Berkeley
  32. Scene Classification via Hypergraph-based Semantic Attributes Subnetworks Identification, Sun-Wook Choi, Inha University; Chong Ho Lee, Inha University; In Kyu Park, Inha University
  33. OTC: A Novel Local Descriptor for Scene Classification, Ran Margolin, Technion; Lihi Zelnik-Manor, Technion; Ayellet Tal, Technion
  34. Multi-scale Orderless Pooling of Deep Convolutional Activation Features, Yunchao Gong, UNC Chapel Hill; Liwei Wang, UIUC; Ruiqi Guo, UIUC; Svetlana Lazebnik, UIUC
  35. Expanding the Family of Grassmannian Kernels: An Embedding Perspective, Mehrtash Harandi, ANU/NICTA; Mathieu Salzmann, NICTA/ANU; Sadeep Jayasumana, ANU/NICTA; Richard Hartley, ANU/NICTA; Hongdong Li, ANU
  36. Image Tag Completion by Noisy Matrix Recovery, Zheyun Feng, Michigan State University; Songhe Feng, Beijing Jiaotong University; Rong Jin, Michigan State University; Anil K. Jain, Michigan State University
  37. ConceptMap: Mining noisy web data for concept learning, Eren Golge, Bilkent University; Pinar Duygulu, Bilkent University
  38. Shrinkage Expansion Adaptive Metric Learning, Qilong Wang, Heilongjiang University; Wangmeng Zuo, Harbin Institute of Technology; Lei Zhang, The Hong Kong Polytechnic University; Peihua Li, Dalian University of Technology
  39. Salient Montages from Unconstrained Videos, Min Sun, University of Washington; Ali Farhadi, University of Washington; Ben Taskar, University of Washington; Steve Seitz, Washington/Google
  40. Action-Reaction: Forecasting the Dynamics of Human Interaction, De-An Huang, Carnegie Mellon University; Kris Kitani, Carnegie Mellon University
  41. Creating Summaries from User Videos, Michael Gygli, ETH Zurich; Helmut Grabner, ETH Zurich; Hayko Riemenschneider, Computer Vision Lab, ETH Zurich; Luc Van Gool, Computer Vision Lab, ETH Zurich
  42. Spatiotemporal Background Subtraction Using Minimum Spanning Tree and Optical Flow, Mingliang Chen, City University of Hong Kong; Qingxiong Yang, City University of Hong Kong; Qing Li, City University of Hong Kong; Gang Wang, Nanyang Technological University; Ming-Hsuan Yang, UC Merced
  43. Robust Foreground Detection Using Smoothness and Arbitrariness Constraints, Xiaojie Guo, SKLOIS, IIE CAS; Xinggang Wang, Huazhong University of Science and Technology; Liang Yang, SKLOIS, IIE, CAS; Xiaochun Cao, SKLOIS, IIIE, CAS; Yi Ma, ShanghaiTech University
  44. Video Object Co-Segmentation by Regulated Maximum Weight Cliques, Dong Zhang, UCF; Omar Javed, SRI International; Mubarak Shah, University of Central Florida

1600–1645       Coffee break

1645–1800       Oral Session 4B: Motion and 3D Scene Analysis (Kongresssaal)

Chairs:      Shai Avidan (Tel-Aviv University)
                      Raquel Urtasun (University of Toronto)

Format (15 min. for presentation + 3 min. for questions)

  1. Dense Semi-Rigid Scene Flow Estimation from RGBD images, Julian Quiroga, INRIA; Thomas Brox, Uni Freiburg; Frédéric Devernay, James Crowley, INRIA
  2. Video Pop-up: Monocular 3D Reconstruction of Dynamic Scenes, Chris Russell, Rui Yu, Lourdes Agapito, UC London
  3. Joint Object Class Sequencing and Trajectory Triangulation (JOST), Enliang Zheng, Ke Wang, Enrique Dunn, Jan-Michael Frahm, UNC-Chapel Hill
  4. Scene Chronology, Kevin Matzen, Noah Snavely, Cornell University

 

1800-1815       Closing