The Community for Technology Leaders
Computer Vision, IEEE International Conference on (2011)
Barcelona, Spain
Nov. 6, 2011 to Nov. 13, 2011
ISBN: 978-1-4577-1101-5
TABLE OF CONTENTS
Papers

Corporate sponsors (PDF)

pp. xxxviii

ICCV2011 committees (PDF)

pp. xxx-xxxvii

Oral session 1-1 (PDF)

pp. xxxix

A graph-matching kernel for object categorization (Abstract)

Jean Ponce , École Normale Supérieure de Paris, France
Olivier Duchenne , INRIA, France
Armand Joulin , INRIA, France
pp. 1792-1799

Domain adaptation for object recognition: An unsupervised approach (Abstract)

Rama Chellappa , Center for Automation Research, University of Maryland, College Park, 20742 USA
Ruonan Li , Center for Automation Research, University of Maryland, College Park, 20742 USA
Raghuraman Gopalan , Center for Automation Research, University of Maryland, College Park, 20742 USA
pp. 999-1006

Structured class-labels in random forests for semantic image labelling (Abstract)

P. Kontschieder , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
S. Rota Bulo , Dipt. di Sci. Ambientali, Inf. e Statistica, Univ. Ca' Foscari Venezia, Venezia, Italy
H. Bischof , Inst. for Comput. Graphics & Vision, Graz Univ. of Technol., Graz, Austria
M. Pelillo , Dipt. di Sci. Ambientali, Inf. e Statistica, Univ. Ca' Foscari Venezia, Venezia, Italy
pp. 2190-2197
Papers

Perturb-and-MAP random fields: Using discrete optimization to learn and sample from energy models (Abstract)

George Papandreou , Department of Statistics, University of California, Los Angeles, USA
Alan L. Yuille , Department of Statistics, University of California, Los Angeles, USA
pp. 193-200

Discriminative learning of relaxed hierarchy for large-scale visual recognition (Abstract)

Daphne Koller , Dept. of Computer Science, Stanford University, USA
Tianshi Gao , Dept. of Electrical Engineering, Stanford University, USA
pp. 2072-2079

Decision tree fields (Abstract)

Bangpeng Yao , Stanford University, CA, USA
Pushmeet Kohli , Microsoft Research, Cambridge, UK
Toby Sharp , Microsoft Research, Cambridge, UK
Sebastian Nowozin , Microsoft Research, Cambridge, UK
Carsten Rother , Microsoft Research, Cambridge, UK
Shai Bagon , Weizmann Institute, Israel
pp. 1668-1675

Strong supervision from weak annotation: Interactive training of deformable part models (Abstract)

Pietro Perona , California Institute of Technology, Pasadena, 91125, USA
Serge Belongie , University of California, San Diego, La Jolla, 92093, USA
Steve Branson , University of California, San Diego, La Jolla, 92093, USA
pp. 1832-1839

Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance (Abstract)

Ning Zhang , University of California, Berkeley, USA
Larry S. Davis , University of Maryland, College Park, USA
Trevor Darrell , University of California, Berkeley, USA
Ryan Farrell , University of Maryland, College Park, USA
Om Oza , University of Maryland, College Park, USA
Vlad I. Morariu , University of Maryland, College Park, USA
pp. 161-168

From contours to 3D object detection and pose estimation (Abstract)

Sinisa Todorovic , Oregon State University, Corvallis, 97331, USA
Nadia Payet , Oregon State University, Corvallis, 97331, USA
pp. 983-990

Oral session 2-1 (PDF)

pp. xlii

What an image reveals about material reflectance (Abstract)

Ravi Ramamoorthi , University of California, Berkeley, USA
Manmohan Chandraker , University of California, Berkeley, USA
pp. 1076-1083

Multiplexed illumination for scene recovery in the presence of global illumination (Abstract)

Mohit Gupta , Columbia University, USA
Toshihiro Kobayashi , Canon Inc., Japan
Jinwei Gu , Rochester Institute of Technology, USA
Shree K. Nayar , Columbia University, USA
pp. 691-698

Oral session 2-2 (PDF)

pp. xliii

Data-driven crowd analysis in videos (Abstract)

Mikel Rodriguez , École Normale Supérieure, France
Jean-Yves Audibert , Imagine, LIGM, Universite Paris-Est, France
Josef Sivic , INRIA, France
Ivan Laptev , INRIA, France
pp. 1235-1242

A "string of feature graphs" model for recognition of complex activities in natural videos (Abstract)

B. Song , University of California, Riverside, 92521, USA
U. Gaur , University of California, Riverside, 92521, USA
Y. Zhu , University of California, Riverside, 92521, USA
A. Roy-Chowdhury , University of California, Riverside, 92521, USA
pp. 2595-2602

Learning spatiotemporal graphs of human activities (Abstract)

Sinisa Todorovic , Oregon State University, Corvallis, 97331, USA
William Brendel , Oregon State University, Corvallis, 97331, USA
pp. 778-785

Human action recognition by learning bases of action attributes and parts (Abstract)

Li Fei-Fei , Computer Science Department, Stanford University, CA, USA
Leonidas Guibas , Computer Science Department, Stanford University, CA, USA
Xiaoye Jiang , Institute for Computational & Mathematical Engineering, Stanford University, CA, USA
Aditya Khosla , Computer Science Department, Stanford University, CA, USA
Andy Lai Lin , Electrical Engineering Department, Stanford University, CA, USA
Bangpeng Yao , Computer Science Department, Stanford University, CA, USA
pp. 1331-1338

Oral session 2-3 (PDF)

pp. xliv

Relative attributes (Abstract)

Devi Parikh , Toyota Technological Institute Chicago (TTIC), USA
Kristen Grauman , University of Texas at Austin, USA
pp. 503-510

Describing people: A poselet-based approach to attribute classification (Abstract)

Jitendra Malik , EECS, U.C. Berkeley, CA 94720, USA
Subhransu Maji , EECS, U.C. Berkeley, CA 94720, USA
Lubomir Bourdev , EECS, U.C. Berkeley, CA 94720, USA
pp. 1543-1550

A joint learning framework for attribute models and object descriptions (Abstract)

Vinod Nair , Yahoo! Labs, Bangalore, India
Sundararajan Sellamanickam , Yahoo! Labs, Bangalore, India
Dhruv Mahajan , Yahoo! Labs, Bangalore, India
pp. 1227-1234

Oral session 2-4 (PDF)

pp. xlv

Object detection and segmentation from joint embedding of parts and pixels (Abstract)

Michael Maire , California Institute of Technology - Pasadena, CA 91125, USA
Pietro Perona , California Institute of Technology - Pasadena, CA 91125, USA
Stella X. Yu , Boston College - Chestnut Hill, MA 02467, USA
pp. 2142-2149

Distributed cosegmentation via submodular optimization on anisotropic diffusion (Abstract)

Gunhee Kim , School of Computer Science, Carnegie Mellon University, USA
Takeo Kanade , School of Computer Science, Carnegie Mellon University, USA
Eric P. Xing , School of Computer Science, Carnegie Mellon University, USA
Li Fei-Fei , Computer Science Department, Stanford University, USA
pp. 169-176

Discovering favorite views of popular places with iconoid shift (Abstract)

Tobias Weyand , UMIC Research Centre, RWTH Aachen University, Germany
Bastian Leibe , UMIC Research Centre, RWTH Aachen University, Germany
pp. 1132-1139

Oral session 3-1 (PDF)

pp. xlvi

An adversarial optimization approach to efficient outlier removal (Abstract)

Anders Eriksson , The Australian Centre for Visual Technologies, The University of Adelaide, South Australia, Australia
David Suter , The Australian Centre for Visual Technologies, The University of Adelaide, South Australia, Australia
Jin Yu , The Australian Centre for Visual Technologies, The University of Adelaide, South Australia, Australia
Tat-Jun Chin , The Australian Centre for Visual Technologies, The University of Adelaide, South Australia, Australia
pp. 399-406

Generalized ordering constraints for multilabel optimization (Abstract)

Evgeny Strekalovskiy , TU Munich, Germany
Daniel Cremers , TU Munich, Germany
pp. 2619-2626

Oral session 3-2 (PDF)

pp. xlvii

Generalized subgraph preconditioners for large-scale bundle adjustment (Abstract)

Frank Dellaert , College of Computing, Georgia Institute of Technology, USA
Yong-Dian Jian , College of Computing, Georgia Institute of Technology, USA
Doru C. Balcan , College of Computing, Georgia Institute of Technology, USA
pp. 295-302

RECON: Scale-adaptive robust estimation via Residual Consensus (Abstract)

Rahul Raguram , Department of Computer Science, University of North Carolina at Chapel Hill, USA
Jan-Michael Frahm , Department of Computer Science, University of North Carolina at Chapel Hill, USA
pp. 1299-1306

Realtime multibody visual SLAM with a smoothly moving monocular camera (Abstract)

C. V. Jawahar , International Institute of Information Technology, Hyderabad, India
Abhijit Kundu , International Institute of Information Technology, Hyderabad, India
K Madhava Krishna , International Institute of Information Technology, Hyderabad, India
pp. 2080-2087

A revisit to cost aggregation in stereo matching: How far can we reduce its computational redundancy? (Abstract)

Dongbo Min , Advanced Digital Sciences Center (ADSC), Singapore
Jiangbo Lu , Advanced Digital Sciences Center (ADSC), Singapore
Minh N. Do , University of Illinois at Urbana-Champaign, USA
pp. 1567-1574

Oral session 3-3 (PDF)

pp. xlviii

Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes (Abstract)

Stefan Holzer , Department of Computer Science, CAMP, Technische Universität München (TUM), Germany
Vincent Lepetit , École Polytechnique Fédérale de Lausanne (EPFL), Computer Vision Laboratory, Switzerland
Slobodan Ilic , Department of Computer Science, CAMP, Technische Universität München (TUM), Germany
Stefan Hinterstoisser , Department of Computer Science, CAMP, Technische Universität München (TUM), Germany
Nassir Navab , Department of Computer Science, CAMP, Technische Universität München (TUM), Germany
Cedric Cagniart , Department of Computer Science, CAMP, Technische Universität München (TUM), Germany
Kurt Konolige , WillowGarage, Menlo Park, CA, USA
pp. 858-865

Image based detection of geometric changes in urban environments (Abstract)

Luca Ballan , ETH Zurich, Switzerland
Aparna Taneja , ETH Zurich, Switzerland
Marc Pollefeys , ETH Zurich, Switzerland
pp. 2336-2343

Manhattan scene understanding using monocular, stereo, and 3D features (Abstract)

Ian Reid , Active Vision Laboratory, Oxford University, UK
David Murray , Active Vision Laboratory, Oxford University, UK
Alex Flint , Active Vision Laboratory, Oxford University, UK
pp. 2228-2235

Oral session 3-4 (PDF)

pp. xlix

From learning models of natural image patches to whole image restoration (Abstract)

Daniel Zoran , Interdisciplinary Center for Neural Computation, Hebrew University of Jerusalem, Israel
Yair Weiss , School of Computer Science and Engineering, Hebrew University of Jerusalem, Israel
pp. 479-486

Geometrically consistent stereo seam carving (Abstract)

Tali Basha , Tel Aviv University, 69978, Israel
Yael Moses , The Interdisciplinary Center, Herzliya 46150, Israel
Shai Avidan , Tel Aviv University, 69978, Israel
pp. 1816-1823

Fast template matching in non-linear tone-mapped images (Abstract)

Yacov Hel-Or , IDC Herzelia, Israel
Eyal David , University of Haifa, Israel
Hagit Hel-Or , University of Haifa, Israel
pp. 1355-1362

Coherency Sensitive Hashing (Abstract)

Simon Korman , Dept. of Electrical Engineering, Tel Aviv University, Israel
Shai Avidan , Dept. of Electrical Engineering, Tel Aviv University, Israel
pp. 1607-1614

Tracking by Sampling Trackers (Abstract)

Kyoung Mu Lee , Department of EECS, ASRI, Seoul National University, 151-742, Korea
Junseok Kwon , Department of EECS, ASRI, Seoul National University, 151-742, Korea
pp. 1195-1202

Full DOF tracking of a hand interacting with an object by modeling occlusions and physical constraints (Abstract)

Iason Oikonomidis , Institute of Computer Science - FORTH and Comp. Science Department, Univ. of Crete, Heraklion, Greece
Nikolaos Kyriazis , Institute of Computer Science - FORTH and Comp. Science Department, Univ. of Crete, Heraklion, Greece
Antonis A. Argyros , Institute of Computer Science - FORTH and Comp. Science Department, Univ. of Crete, Heraklion, Greece
pp. 2088-2095

Latent structured models for human pose estimation (Abstract)

Fuxin Li , Georgia Institute of Technology, USA
Cristian Sminchisescu , Faculty of Mathematics and Natural Sciences, University of Bonn, Germany
Catalin Ionescu , Faculty of Mathematics and Natural Sciences, University of Bonn, Germany
pp. 2220-2227

Globally optimal solution to multi-object tracking with merged measurements (Abstract)

Rui Caseiro , Institute of Systems and Robotics, University of Coimbra, Portugal
Jorge Batista , Institute of Systems and Robotics, University of Coimbra, Portugal
Joao F. Henriques , Institute of Systems and Robotics, University of Coimbra, Portugal
pp. 2470-2477

Oral session 4-3 (PDF)

pp. lii

Handling outliers in non-blind image deconvolution (Abstract)

Seungyong Lee , POSTECH, Korea
Jue Wang , Adobe Systems, Korea
Sunghyun Cho , POSTECH, Korea
pp. 495-502

Fast removal of non-uniform camera shake (Abstract)

Stefan Harmeling , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Bernhard Scholkopf , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Christian J. Schuler , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Michael Hirsch , Max Planck Institute for Intelligent Systems, Tübingen, Germany
pp. 463-470

Introducing total curvature for image processing (Abstract)

Daniel Cremers , TU Munich, Germany
Bastian Goldluecke , TU Munich, Germany
pp. 1267-1274

Oral session 4-4 (PDF)

pp. liii

Fourier Active Appearance Models (Abstract)

Sridha Sridharan , Queensland University of Technology, Australia
Rajitha Navarathna , Queensland University of Technology, Australia
Simon Lucey , Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia
pp. 1919-1926

Learning universal multi-view age estimator using video context (Abstract)

Dong Guo , Facebook, Singapore
Shuicheng Yan , Department of Electrical and Computer Engineering, Singapore
Terence Sim , School of Computing, National University of Singapore, Singapore
Zheng Song , Department of Electrical and Computer Engineering, Singapore
Bingbing Ni , Advanced Digital Sciences Center, Singapore
pp. 241-248

Robust and efficient parametric face alignment (Abstract)

Maja Pantic , Dept. of Computing, Imperial College London, 180 Queen's Gate, SW7 2AZ, U.K.
Stefanos Zafeiriou , Dept. of Computing, Imperial College London, 180 Queen's Gate, SW7 2AZ, U.K.
Georgios Tzimiropoulos , Dept. of Computing, Imperial College London, 180 Queen's Gate, SW7 2AZ, U.K.
pp. 1847-1854

Poster sessions day 1 (Abstract)

pp. liv

Pushing the limits of digital imaging using structured illumination (Abstract)

Prasanna Rangarajan , Lyle School of Engineering, Southern Methodist University, Dallas, TX 75206, U.S.A
Indranil Sinharoy , Lyle School of Engineering, Southern Methodist University, Dallas, TX 75206, U.S.A
Panos Papamichalis , Lyle School of Engineering, Southern Methodist University, Dallas, TX 75206, U.S.A
Marc P. Christensen , Lyle School of Engineering, Southern Methodist University, Dallas, TX 75206, U.S.A
pp. 1315-1322

Active clustering of document fragments using information derived from both images and catalogs (Abstract)

Lior Wolf , The Blavatnik School of Computer Science, Tel Aviv University, Israel
Roni Shweka , The Friedberg Genizah Project, Jerusalem, Israel
Nachum Dershowitz , The Blavatnik School of Computer Science, Tel Aviv University, Israel
Lior Litwak , The Blavatnik School of Computer Science, Tel Aviv University, Israel
Yaacov Choueka , The Friedberg Genizah Project, Jerusalem, Israel
pp. 1661-1667

Non-stationary correction of optical aberrations (Abstract)

Christian J. Schuler , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Bernhard Scholkopf , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Michael Hirsch , Max Planck Institute for Intelligent Systems, Tübingen, Germany
Stefan Harmeling , Max Planck Institute for Intelligent Systems, Tübingen, Germany
pp. 659-666

Contour Code: Robust and efficient multispectral palmprint encoding for human recognition (Abstract)

Zohaib Khan , School of Computer Science and Software Engineering, The University of Western Australia
Ajmal Mian , School of Computer Science and Software Engineering, The University of Western Australia
Yiqun Hu , School of Computer Science and Software Engineering, The University of Western Australia
pp. 1935-1942

Linear stereo matching (Abstract)

Stefano Mattoccia , University of Bologna, Italy
Rafael Cabeza , Public University of Navarre, Pamplona, Spain
Arantxa Villanueva , Public University of Navarre, Pamplona, Spain
Leonardo De-Maeztu , Public University of Navarre, Pamplona, Spain
pp. 1708-1715

Variational stereo in dynamic illumination (Abstract)

Yohay Swirski , Dept. of Electrical Engineering Technion - Israel Inst. Technology, Haifa 32000, Israel
Yoav Y. Schechner , Dept. of Electrical Engineering Technion - Israel Inst. Technology, Haifa 32000, Israel
Tal Nir , Dept. of Computer Science Technion - Israel Inst. Technology, Haifa 32000, Israel
pp. 1124-1131

Learning nonlinear distance functions using neural network for regression with application to robust human age estimation (Abstract)

Na Fan , Department of Electronic Engineering, East China Normal University, China
pp. 249-254

Revisiting radiometric calibration for color computer vision (Abstract)

Michael S. Brown , National University of Singapore, Singapore
Sabine Susstrunk , National University of Singapore, Singapore
Haiting Lin , National University of Singapore, Singapore
Seon Joo Kim , National University of Singapore, Singapore
pp. 129-136

The medial feature detector: Stable regions from image boundaries (Abstract)

Yannis Avrithis , National Technical University of Athens, Germany
Konstantinos Rapantzikos , National Technical University of Athens, Germany
pp. 1724-1731

A theory of Coprime Blurred Pairs (Abstract)

Jingyi Yu , University of Delaware, Newark, 19716, USA
David Saunders , University of Delaware, Newark, 19716, USA
Zijia Li , Key Laboratory of Mathematics Mechanization, AMSS, Beijing 100190, China
Feng Li , University of Delaware, Newark, 19716, USA
pp. 217-224

Learning to predict the perceived visual quality of photos (Abstract)

Jun Gao , NLPR, Institute of Automation, Chinese Academy of Sciences, China
Ou Wu , NLPR, Institute of Automation, Chinese Academy of Sciences, China
Weiming Hu , NLPR, Institute of Automation, Chinese Academy of Sciences, China
pp. 225-232

Source constrained clustering (Abstract)

Martial Hebert , Carnegie Mellon University, USA
Ekaterina Taralova , Carnegie Mellon University, USA
Fernando De la Torre , Carnegie Mellon University, USA
pp. 1927-1934

Sparse dictionary-based representation and recognition of action attributes (Abstract)

Zhuolin Jiang , Center for Automation Research, UMIACS, University of Maryland, College Park, 20742, USA
Qiang Qiu , Center for Automation Research, UMIACS, University of Maryland, College Park, 20742, USA
Rama Chellappa , Center for Automation Research, UMIACS, University of Maryland, College Park, 20742, USA
pp. 707-714

HMDB: A large video database for human motion recognition (Abstract)

E. Garrote , Massachusetts Institute of Technology, Cambridge, 02139, USA
T. Serre , Brown University, Providence, RI 02906, USA
H. Jhuang , Massachusetts Institute of Technology, Cambridge, 02139, USA
H. Kuehne , Karlsruhe Instit. of Tech., Germany
T. Poggio , Massachusetts Institute of Technology, Cambridge, 02139, USA
pp. 2556-2563

Inferring social relations from visual concepts (Abstract)

Lei Ding , Photogrammetric Computer Vision Lab, The Ohio State University, Columbus, 43210, USA
Alper Yilmaz , Photogrammetric Computer Vision Lab, The Ohio State University, Columbus, 43210, USA
pp. 699-706

A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling (Abstract)

Adrian Hilton , Centre for Vision, Speech and Signal Processing, University of Surrey, UK
Eva Krumhuber , School of Humanities and Social Sciences, Jacobs University, Germany
Darren Cosker , Department of Computer Science, University of Bath, Uk
pp. 2296-2303

Maximizing all margins: Pushing face recognition with Kernel Plurality (Abstract)

Arunava Banerjee , University of Florida, USA
Baba C. Vemuri , University of Florida, USA
Hanspeter Pfister , Harvard University, USA
Ritwik Kumar , IBM Research - Almaden, USA
pp. 2375-2382

Exemplar extraction using spatio-temporal hierarchical agglomerative clustering for face recognition in video (Abstract)

John See , Faculty of Information Technology, Multimedia University, Malaysia
Chikkannan Eswaran , Faculty of Information Technology, Multimedia University, Malaysia
pp. 1481-1486

Exploring regularized feature selection for person specific face verification (Abstract)

Beiji Zou , School of Information Science and Engineering, Central South University, Changsha, Hunan 410083, China
Yixiong Liang , School of Information Science and Engineering, Central South University, Changsha, Hunan 410083, China
Shenghui Liao , School of Information Science and Engineering, Central South University, Changsha, Hunan 410083, China
Lei Wang , School of Information Science and Engineering, Central South University, Changsha, Hunan 410083, China
pp. 1676-1683

A linear subspace learning approach via sparse coding (Abstract)

Qinghua Hu , Harbin Institute of Technology, China
David Zhang , Dept. of Computing, The Hong Kong Polytechnic University, China
Lei Zhang , Dept. of Computing, The Hong Kong Polytechnic University, China
Pengfei Zhu , Dept. of Computing, The Hong Kong Polytechnic University, China
pp. 755-761

DTAM: Dense tracking and mapping in real-time (Abstract)

Andrew J. Davison , Department of Computing, Imperial College London, UK
Steven J. Lovegrove , Department of Computing, Imperial College London, UK
Richard A. Newcombe , Department of Computing, Imperial College London, UK
pp. 2320-2327

Scale space for central catadioptric systems: Towards a generic camera feature extractor (Abstract)

J. J. Guerrero , Departamento de Informática e Ingeniería de Sistemas, Instituto de Investigación en Ingeniería de Aragón, I3A Universidad de Zaragoza, Spain
Luis Puig , Departamento de Informática e Ingeniería de Sistemas, Instituto de Investigación en Ingeniería de Aragón, I3A Universidad de Zaragoza, Spain
pp. 1599-1606

Kernel non-rigid structure from motion (Abstract)

Paulo F. U. Gotardo , Department of Electrical and Computer Engineering, The Ohio State University, Columbus, USA
Aleix M. Martinez , Department of Electrical and Computer Engineering, The Ohio State University, Columbus, USA
pp. 802-809

A dimensionality result for multiple homography matrices (Abstract)

Anton van den Hengel , School of Computer Science, The University of Adelaide, SA 5005, Australia
Wojciech Chojnacki , School of Computer Science, The University of Adelaide, SA 5005, Australia
pp. 2104-2109

Text-based image retrieval using progressive multi-instance learning (Abstract)

Dong Xu , School of Computer Engineering, Nanyang Technological University, Singapore
Ivor Wai-Hung Tsang , School of Computer Engineering, Nanyang Technological University, Singapore
Wen Li , School of Computer Engineering, Nanyang Technological University, Singapore
Lixin Duan , School of Computer Engineering, Nanyang Technological University, Singapore
pp. 2049-2055

Sparse multi-task regression and feature selection to identify brain imaging predictors for memory performance (Abstract)

Shannon Risacher , Computer Science and Engineering, University of Texas at Arlington, USA
Chris Ding , Computer Science and Engineering, University of Texas at Arlington, USA
Hua Wang , Computer Science and Engineering, University of Texas at Arlington, USA
Heng Huang , Computer Science and Engineering, University of Texas at Arlington, USA
Li Shen , Computer Science and Engineering, University of Texas at Arlington, USA
Andrew J Saykin , Computer Science and Engineering, University of Texas at Arlington, USA
Feiping Nie , Computer Science and Engineering, University of Texas at Arlington, USA
pp. 557-562

Content-based photo quality assessment (Abstract)

Xiaogang Wang , Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong
Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Wei Luo , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
pp. 2206-2213

HEAT: Iterative relevance feedback with one million images (Abstract)

Nicolae Suditu , Idiap Research Institute and École Polytechnique, Fédérale de Lausanne (EPFL), Switzerland
Francois Fleuret , Idiap Research Institute and École Polytechnique, Fédérale de Lausanne (EPFL), Switzerland
pp. 2118-2125

Unsupervised learning of a scene-specific coarse gaze estimator (Abstract)

Ben Benfold , Department of Engineering Science, University of Oxford, UK
Ian Reid , Department of Engineering Science, University of Oxford, UK
pp. 2344-2351

Learning to cluster using high order graphical models with latent variables (Abstract)

Nikos Komodakis , University of Crete, Computer Science Department, Greece
pp. 73-80

Diagonal preconditioning for first order primal-dual algorithms in convex optimization (Abstract)

Thomas Pock , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Antonin Chambolle , CMAP & CNRS, École Polytechnique, France
pp. 1762-1769

Tracking multiple people under global appearance constraints (Abstract)

Francois Fleuret , CVLab, EPFL, Lausanne, Switzerland
Horesh Ben Shitrit , CVLab, EPFL, Lausanne, Switzerland
Jerome Berclaz , CVLab, EPFL, Lausanne, Switzerland
Pascal Fua , CVLab, EPFL, Lausanne, Switzerland
pp. 137-144

Treat samples differently: Object tracking with semi-supervised online CovBoost (Abstract)

Shuqiang Jiang , Key Lab of Intell. Info. Process., Inst. of Computi. Tech., CAS, Beijing 100190, China
Guorong Li , Graduate University of Chinese Academy of Sciences(CAS), Beijing 100049, China
Junbiao Pang , Key Lab of Intell. Info. Process., Inst. of Computi. Tech., CAS, Beijing 100190, China
Lei Qin , Key Lab of Intell. Info. Process., Inst. of Computi. Tech., CAS, Beijing 100190, China
Qingming Huang , Graduate University of Chinese Academy of Sciences(CAS), Beijing 100049, China
pp. 627-634

Kinecting the dots: Particle based scene flow from depth sensors (Abstract)

Richard Bowden , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK, GU2 7XH
Simon Hadfield , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK, GU2 7XH
pp. 2290-2295

Graph mode-based contextual kernels for robust SVM tracking (Abstract)

Xi Li , School of Computer Sciences, University of Adelaide, Australia
Chunhua Shen , School of Computer Sciences, University of Adelaide, Australia
Anton van den Hengel , School of Computer Sciences, University of Adelaide, Australia
Hanzi Wang , Center for Pattern Analysis and Machine Intelligence, Xiamen University, China, 361005
Anthony Dick , School of Computer Sciences, University of Adelaide, Australia
pp. 1156-1163

Outdoor human motion capture using inverse kinematics and von mises-fisher sampling (Abstract)

Bodo Rosenhahn , Leibniz University Hannover, Germany
Gerard Pons-Moll , Leibniz University Hannover, Germany
Hans-Peter Seidel , Leibniz University Hannover, Germany
Juergen Gall , BIWI, ETH Zurich, Switzerland
Andreas Baak , Saarland University & MPI Informatik, Germany
Meinard Muller , Saarland University & MPI Informatik, Germany
Laura Leal-Taixe , Saarland University & MPI Informatik, Germany
pp. 1243-1250

Blurred target tracking by Blur-driven Tracker (Abstract)

Feng Li , Department of Computer and Information Sciences, University of Delaware, Newark, 19716, USA
Erkang Cheng , Computer & Information Science Department, Temple University, Philadelphia, PA 19122, USA
Haibin Ling , Computer & Information Science Department, Temple University, Philadelphia, PA 19122, USA
Jingyi Yu , Department of Computer and Information Sciences, University of Delaware, Newark, 19716, USA
Yi Wu , Computer & Information Science Department, Temple University, Philadelphia, PA 19122, USA
pp. 1100-1107

Informative feature selection for object recognition via Sparse PCA (Abstract)

Allen Y. Yang , Department of EECS, University of California, Berkeley, USA
Nikhil Naikal , Department of EECS, University of California, Berkeley, USA
S. Shankar Sastry , Department of EECS, University of California, Berkeley, USA
pp. 818-825

Action recognition using rank-1 approximation of Joint Self-Similarity Volume (Abstract)

Chuan Sun , Division of Computer Science, University of Central Florida, USA
Imran Junejo , Department of Computer Science, University of Sharjah, United Arab Emirates
Hassan Foroosh , Division of Computer Science, University of Central Florida, USA
pp. 1007-1012

The truth about cats and dogs (Abstract)

Andrew Zisserman , Department of Engineering Science, University of Oxford, United Kingdom
Andrea Vedaldi , Department of Engineering Science, University of Oxford, United Kingdom
C. V. Jawahar , Center for Visual Information Technology, International Institute of Information Technology, Hyderabad 500032, India
Omkar M Parkhi , Center for Visual Information Technology, International Institute of Information Technology, Hyderabad 500032, India
pp. 1427-1434

The NBNN kernel (Abstract)

K. Saenko , UC Berkeley EECS & ICSI, US
M. Fritz , MPI Informatics, Saarbrücken, Germany
T. Darrell , UC Berkeley EECS & ICSI, US
T. Tuytelaars , K.U.Leuven, ESAT - PSI, IBBT, Belgium
pp. 1824-1831

A new distance for scale-invariant 3D shape recognition and registration (Abstract)

Oliver J. Woodford , Cambridge Research Laboratory, Toshiba Research Europe Ltd, UK
Minh-Tri Pham , Cambridge Research Laboratory, Toshiba Research Europe Ltd, UK
Atsuto Maki , Cambridge Research Laboratory, Toshiba Research Europe Ltd, UK
Roberto Cipolla , Department of Engineering, University of Cambridge, UK
Bjorn Stenger , Cambridge Research Laboratory, Toshiba Research Europe Ltd, UK
Frank Perbet , Cambridge Research Laboratory, Toshiba Research Europe Ltd, UK
pp. 145-152

Salient Object Detection using concavity context (Abstract)

Hong Lu , School of Computer Science, Fudan University, Shanghai, China
Wei Zhang , School of Computer Science, Fudan University, Shanghai, China
Xiangyang Xue , School of Computer Science, Fudan University, Shanghai, China
Yao Lu , School of Computer Science, Fudan University, Shanghai, China
pp. 233-240

Spatial pyramid co-occurrence for image classification (Abstract)

Yi Yang , Electrical Engineering & Computer Science, University of California at Merced, USA
Shawn Newsam , Electrical Engineering & Computer Science, University of California at Merced, USA
pp. 1465-1472

Actively selecting annotations among objects and attributes (Abstract)

Kristen Grauman , University of Texas at Austin, USA
Sudheendra Vijayanarasimhan , University of Texas at Austin, USA
Adriana Kovashka , University of Texas at Austin, USA
pp. 1403-1410

Scene recognition and weakly supervised object localization with deformable part-based models (Abstract)

Megha Pandey , Dept. of Computer Science, University of North Carolina at Chapel Hill, USA
Svetlana Lazebnik , Dept. of Computer Science, University of North Carolina at Chapel Hill, USA
pp. 1307-1314

Multi-label visual classification with label exclusive context (Abstract)

Qiang Chen , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Xiangyu Chen , NUS Graduate School for Integrative Sciences and Engineering, Singapore
Shuicheng Yan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Xiao-Tong Yuan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Tat-Seng Chua , NUS Graduate School for Integrative Sciences and Engineering, Singapore
pp. 834-841

CARD: Compact And Real-time Descriptors (Abstract)

Yuichi Yoshida , Denso IT Laboratory, Inc., Japan
Mitsuru Ambai , Denso IT Laboratory, Inc., Japan
pp. 97-104

BiCoS: A Bi-level co-segmentation method for image classification (Abstract)

Yuning Chai , Electrical Engineering Dept., ETH Zurich, Switzerland
Victor Lempitsky , Dept. of Engineering Science, University of Oxford, UK
Andrew Zisserman , Dept. of Engineering Science, University of Oxford, UK
pp. 2579-2586

Convex multi-region probabilistic segmentation with shape prior in the isometric log-ratio transformation space (Abstract)

Ghassan Hamarneh , Medical Image Analysis Lab, Simon Fraser University, 8888 University Drive, Burnaby, BC, Canada, V5A 1S6
Chris McIntosh , Medical Image Analysis Lab, Simon Fraser University, 8888 University Drive, Burnaby, BC, Canada, V5A 1S6
Shawn Andrews , Medical Image Analysis Lab, Simon Fraser University, 8888 University Drive, Burnaby, BC, Canada, V5A 1S6
pp. 2096-2103

A general preconditioning scheme for difference measures in deformable registration (Abstract)

Darko Zikic , Computer Aided Medical Procedures (CAMP), Technische Universität München, Germany
Nassir Navab , Computer Aided Medical Procedures (CAMP), Technische Universität München, Germany
Ali Kamen , Siemens Corporate Research (SCR), Princeton, USA
Maximilian Baust , Computer Aided Medical Procedures (CAMP), Technische Universität München, Germany
pp. 49-56

A 3D Laplacian-driven parametric deformable model (Abstract)

Edward Kim , Department of Computer Science and Engineering, Lehigh University, USA
Shaoting Zhang , Department of Computer Science, Rutgers University, Piscataway, USA
Xiaolei Huang , Department of Computer Science and Engineering, Lehigh University, USA
Tian Shen , Department of Computer Science and Engineering, Lehigh University, USA
Junzhou Huang , Department of Computer Science and Engineering, University of Texas at Arlington, USA
Hongsheng Li , Department of Computer Science and Engineering, Lehigh University, USA
pp. 279-286

Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions (Abstract)

Thomas Brox , Computer Vision Group, University of Freiburg, Germany
Peter Ochs , Computer Vision Group, University of Freiburg, Germany
pp. 1583-1590

Spatio-temporal clustering of probabilistic region trajectories (Abstract)

Roberto Cipolla , Department of Engineering, University of Cambridge, United Kingdom
Fabio Galasso , Department of Engineering, University of Cambridge, United Kingdom
Kunio Nobori , Advanced Technology Research Laboratory, Panasonic Corporation, Japan
Masahiro Iwasaki , Advanced Technology Research Laboratory, Panasonic Corporation, Japan
pp. 1738-1745

Generalized background subtraction based on hybrid inference by belief propagation and Bayesian filtering (Abstract)

Suha Kwak , Department of Computer Science and Engineering, POSTECH, Korea
Bohyung Han , Department of Computer Science and Engineering, POSTECH, Korea
Taegyu Lim , Department of Computer Science and Engineering, POSTECH, Korea
Joon Hee Han , Department of Computer Science and Engineering, POSTECH, Korea
Woonhyun Nam , Department of Computer Science and Engineering, POSTECH, Korea
pp. 2174-2181

Video from a single coded exposure photograph using a learned over-complete dictionary (Abstract)

Mohit Gupta , Columbia University, USA
Tomoo Mitsunaga , Sony Corporation, USA
Yasunobu Hitomi , Sony Corporation, USA
Jinwei Gu , Rochester Institute of Technology, USA
Shree K. Nayar , Columbia University, USA
pp. 287-294

Unwrapping low-rank textures on generalized cylindrical surfaces (Abstract)

Yi Ma , Visual computing Group, Microsoft Research Asia, China
Xiao Liang , Visual computing Group, Microsoft Research Asia, China
Zhengdong Zhang , Visual computing Group, Microsoft Research Asia, China
pp. 1347-1354

Unstructured light scanning to overcome interreflections (Abstract)

Nicolas Martin , Université de Montréal, Canada
Vincent Couture , Université de Montréal, Canada
Sebastien Roy , Université de Montréal, Canada
pp. 1895-1902

On the repeatability of the local reference frame for partial shape matching (Abstract)

Luigi Di Stefano , CVLab - DEIS, University of Bologna, Viale Risorgimento, 2 - 40135, Italy
Alioscia Petrelli , CVLab - DEIS, University of Bologna, Viale Risorgimento, 2 - 40135, Italy
pp. 2244-2251

Geometrically consistent elastic matching of 3D shapes: A linear programming solution (Abstract)

Ulrich Schlickewei , Technische Universität München, Germany
Thomas Windheuser , Technische Universität München, Germany
Daniel Cremers , Technische Universität München, Germany
Frank R. Schmidt , University of Western Ontario, Canada
pp. 2134-2141

Correspondence free registration through a point-to-model distance minimization (Abstract)

Mohammad Rouhani , Computer Vision Center, Edifici O, Campus UAB, 08193 Bellaterra, Barcelona, Spain
Angel D. Sappa , Computer Vision Center, Edifici O, Campus UAB, 08193 Bellaterra, Barcelona, Spain
pp. 2150-2157

Multi-class semi-supervised SVMs with Positiveness Exclusive Regularization (Abstract)

Hai Jin , Huazhong University of Science and Technology, Wuhan, China
Xiaotong Yuan , National University of Singapore, Singapore
Shuicheng Yan , National University of Singapore, Singapore
Xiaobai Liu , Huazhong University of Science and Technology, Wuhan, China
pp. 1435-1442

Centralized sparse representation for image restoration (Abstract)

Lei Zhang , Dept. of Computing, The Hong Kong Polytechnic Univ., China
Weisheng Dong , Sch. of Elec. Engineering, Xidian University, China
Guangming Shi , Sch. of Elec. Engineering, Xidian University, China
pp. 1259-1266

Positive definite dictionary learning for region covariances (Abstract)

Ravishankar Sivalingam , Department of Computer Science & Engineering, University of Minnesota, Minneapolis, USA
Vassilios Morellas , Department of Computer Science & Engineering, University of Minnesota, Minneapolis, USA
Nikolaos Papanikolopoulos , Department of Computer Science & Engineering, University of Minnesota, Minneapolis, USA
Daniel Boley , Department of Computer Science & Engineering, University of Minnesota, Minneapolis, USA
pp. 1013-1019

Learning cross-modality similarity for multinomial data (Abstract)

Mathieu Salzmann , TTI-Chicago, USA
Yangqing Jia , UC Berkeley EECS, USA
Trevor Darrell , UC Berkeley EECS, USA
pp. 2407-2414

Random ensemble metrics for object recognition (Abstract)

Susumu Kubota , Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan
Satoshi Ito , Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan
Tatsuo Kozakaya , Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan
pp. 1959-1966

Diffusion runs low on persistence fast (Abstract)

Chao Chen , IST Austria, Klosterneuburg & PRIP, Vienna Univ. Techn., Austria
Herbert Edelsbrunner , IST Austria, Klosterneuburg, Austria
pp. 423-430

Illumination demultiplexing from a single image (Abstract)

Matthew Turk , UC Santa Barbara, CA, USA
Daniel Vaquero , UC Santa Barbara, CA, USA
Christine Chen , ETH Zürich, Switzerland
pp. 17-24

ORB: An efficient alternative to SIFT or SURF (Abstract)

Gary Bradski , Willow Garage, Menlo Park, California, USA
Kurt Konolige , Willow Garage, Menlo Park, California, USA
Vincent Rabaud , Willow Garage, Menlo Park, California, USA
Ethan Rublee , Willow Garage, Menlo Park, California, USA
pp. 2564-2571

Temporally coded flash illumination for motion deblurring (Abstract)

Scott McCloskey , Honeywell ACS Labs, 1985 Douglas Drive North, Minneapolis, MN, USA
pp. 683-690

Poster sessions day 2 (Abstract)

pp. lv

Active scene recognition with vision and language (Abstract)

Yiannis Aloimonos , Computer Vision Lab, University of Maryland, College Park, 20742, USA
Yezhou Yang , Computer Vision Lab, University of Maryland, College Park, 20742, USA
Ching Lik Teo , Computer Vision Lab, University of Maryland, College Park, 20742, USA
Cornelia Fermuller , Computer Vision Lab, University of Maryland, College Park, 20742, USA
Xiaodong Yu , Computer Vision Lab, University of Maryland, College Park, 20742, USA
pp. 810-817

Handling label noise in video classification via multiple instance learning (Abstract)

John Zhang , Columbia University, New York, 10027, USA
Yang Song , Google Inc., Mountain View, CA 94043, USA
Thomas Leung , Google Inc., Mountain View, CA 94043, USA
pp. 2056-2063

Unsupervised learning of event AND-OR grammar and semantics from video (Abstract)

Mingtao Pei , Lab of Intelligent Info. Tech., Beijing Institute of Technology, China
Song-Chun Zhu , Department of Statistics, University of California, Los Angeles, USA
Zhangzhang Si , Department of Statistics, University of California, Los Angeles, USA
Benjamin Yao , Department of Statistics, University of California, Los Angeles, USA
pp. 41-48

Detailed reconstruction of 3D plant root shape (Abstract)

Ying Zheng , Dept. of Computer Science, Duke Univ., USA
Steve Gu , Dept. of Computer Science, Duke Univ., USA
Carlo Tomasi , Dept. of Computer Science, Duke Univ., USA
Philip Benfey , Dept. of Biology, Duke Univ., USA
Herbert Edelsbrunner , IST Austria
pp. 2026-2033

Dynamic fluid surface acquisition using a camera array (Abstract)

Yu Ji , University of Delaware, Newark, 19716 USA
Feng Li , University of Delaware, Newark, 19716 USA
Yuanyuan Ding , University of Delaware, Newark, 19716 USA
Jingyi Yu , University of Delaware, Newark, 19716 USA
pp. 2478-2485

Spatiotemporal oriented energies for spacetime stereo (Abstract)

Richard P. Wildes , Department of Computer Science and Engineering, York University, Toronto, ON, Canada
Mikhail Sizintsev , Department of Computer Science and Engineering, York University, Toronto, ON, Canada
pp. 1140-1147

Image representation by active curves (Abstract)

Song-Chun Zhu , Department of Statistics, UCLA, USA
Wenze Hu , Department of Statistics, UCLA, USA
Ying Nian Wu , Department of Statistics, UCLA, USA
pp. 1808-1815

Diffuse reflectance imaging with astronomical applications (Abstract)

Anat Levin , Weizmann Institute, Germany
William T. Freeman , MIT CSAIL, USA
Samuel W. Hasinoff , TTIC, USA
Philip R. Goode , Big Bear Solar Observatory, USA
pp. 185-192

Video Primal Sketch: A generic middle-level representation of video (Abstract)

Zhi Han , Institute for Information and System Sciences, Xi'an Jiaotong University, China
Zongben Xu , Institute for Information and System Sciences, Xi'an Jiaotong University, China
Song-Chun Zhu , Department of Statistics, University of California, LA, USA
pp. 1283-1290

Gradient-based learning of higher-order image features (Abstract)

Roland Memisevic , Department of Computer Science, University of Frankfurt, Germany
pp. 1591-1598

Action recognition in videos acquired by a moving camera using motion decomposition of Lagrangian particle trajectories (Abstract)

Shandong Wu , Computer Vision Lab, University of Central Florida, USA
Omar Oreifej , Computer Vision Lab, University of Central Florida, USA
Mubarak Shah , Computer Vision Lab, University of Central Florida, USA
pp. 1419-1426

A chains model for localizing participants of group activities in videos (Abstract)

Mohamed R. Amer , Oregon State University, USA
Sinisa Todorovic , Oregon State University, USA
pp. 786-793

Parsing video events with goal inference and intent prediction (Abstract)

Song-Chun Zhu , Department of Statistics, University of California, Los Angeles, USA
Yunde Jia , Lab of Intelligent Info. Technology, Beijing Institute of Technology, China
Mingtao Pei , Lab of Intelligent Info. Technology, Beijing Institute of Technology, China
pp. 487-494

iGroup: Weakly supervised image and video grouping (Abstract)

Andrew Gilbert , University of Surrey, Guildford, UK
Richard Bowden , University of Surrey, Guildford, UK
pp. 2166-2173

A selective spatio-temporal interest point detector for human action recognition in complex scenes (Abstract)

F. Xavier Roca , Computer Vision Center, Universitat Autònoma de Barcelona, Catalonia (Spain)
Thomas B. Moeslund , Computer Vision and Media Technology Laboratory, Aalborg Universtity, Denmark
Jordi Gonzalez , Computer Vision Center, Universitat Autònoma de Barcelona, Catalonia (Spain)
Bhaskar Chakraborty , Computer Vision Center, Universitat Autònoma de Barcelona, Catalonia (Spain)
Michael B. Holte , Computer Vision and Media Technology Laboratory, Aalborg Universtity, Denmark
pp. 1776-1783

Optimal landmark detection using shape models and branch and bound (Abstract)

Thomas Vetter , University of Basel, Switzerland
Brian Amberg , University of Basel, Switzerland
pp. 455-462

Face recognition based on non-corresponding region matching (Abstract)

Xilin Chen , Key Lab of Intelligent Information Processing of CAS, Institute of Computing Technology, CAS, Beijing 100190, China
Wen Gao , Institute of Digital Media, Peking University, Beijing, 100871, China
Annan Li , Key Lab of Intelligent Information Processing of CAS, Institute of Computing Technology, CAS, Beijing 100190, China
Shiguang Shan , Key Lab of Intelligent Information Processing of CAS, Institute of Computing Technology, CAS, Beijing 100190, China
pp. 1060-1067

Pose, illumination and expression invariant pairwise face-similarity measure via Doppelgänger list comparison (Abstract)

Florian Schroff , Department of Computer Science and Engineering, University of California, San Diego, USA
Tali Treibitz , Department of Computer Science and Engineering, University of California, San Diego, USA
Serge Belongie , Department of Computer Science and Engineering, University of California, San Diego, USA
David Kriegman , Department of Computer Science and Engineering, University of California, San Diego, USA
pp. 2494-2501

Face recognition via local sparse coding (Abstract)

Ilias Theodorakopoulos , Department of Physics, University of Patras, 26500, Greece
Spiros Fotopoulos , Department of Physics, University of Patras, 26500, Greece
Ioannis Rigas , Department of Physics, University of Patras, 26500, Greece
George Economou , Department of Physics, University of Patras, 26500, Greece
pp. 1647-1652

Double window optimisation for constant time visual SLAM (Abstract)

Andrew J. Davison , Department of Computing, Imperial College London, UK
J.M.M. Montiel , Instituto de Investigacion en Ingeniera de Aragon (I3A), Universidad de Zaragoza, Spain
Hauke Strasdat , Department of Computing, Imperial College London, UK
Kurt Konolige , Willow Garage Inc, Menlo Park, USA
pp. 2352-2359

Optimal estimation of vanishing points in a Manhattan world (Abstract)

Stergios I. Roumeliotis , University of Minnesota, Minneapolis, 55414, USA
Faraz M. Mirzaei , University of Minnesota, Minneapolis, 55414, USA
pp. 2454-2461

A robust pipeline for rapid feature-based pre-alignment of dense range scans (Abstract)

Alberto Signoroni , University of Brescia, Information Engineering Dept., via Branze, 38, I25123, ITALY
Riccardo Leonardi , University of Brescia, Information Engineering Dept., via Branze, 38, I25123, ITALY
Francesco Bonarrigo , University of Brescia, Information Engineering Dept., via Branze, 38, I25123, ITALY
pp. 2260-2267

Simultaneous localization, mapping and deblurring (Abstract)

Junghyun Kwon , Department of EECS, ASRI, Seoul National University, 151-742, Korea
Kyoung Mu Lee , Department of EECS, ASRI, Seoul National University, 151-742, Korea
Hee Seok Lee , Department of EECS, ASRI, Seoul National University, 151-742, Korea
pp. 1203-1210

The generalized trace-norm and its application to structure-from-motion problems (Abstract)

Christopher Zach , Computer Vision and Geometry Group, Eidgenössische Technische Hochschule Zürich, Switzerland
Roland Angst , Computer Vision and Geometry Group, Eidgenössische Technische Hochschule Zürich, Switzerland
Marc Pollefeys , Computer Vision and Geometry Group, Eidgenössische Technische Hochschule Zürich, Switzerland
pp. 2502-2509

Learning component-level sparse representation using histogram information for image classification (Abstract)

Chen-Kuo Chiang , National Tsing Hua University, Hsinchu, 300, Taiwan
Shang-Hong Lai , National Tsing Hua University, Hsinchu, 300, Taiwan
Chih-Hsueh Duan , National Tsing Hua University, Hsinchu, 300, Taiwan
Shih-Fu Chang , Columbia University, New York, 10027, USA
pp. 1519-1526

From images to scenes: Compressing an image cluster into a single scene model for place recognition (Abstract)

Guang-Zhong Yang , The Hamlyn Centre, Imperial College London, UK
Edward Johns , The Hamlyn Centre, Imperial College London, UK
pp. 874-881

Dyadic transfer learning for cross-domain image classification (Abstract)

Heng Huang , Department of Computer Science and Engineering, University of Texas at Arlington, 76019, USA
Chris Ding , Department of Computer Science and Engineering, University of Texas at Arlington, 76019, USA
Feiping Nie , Department of Computer Science and Engineering, University of Texas at Arlington, 76019, USA
Hua Wang , Department of Computer Science and Engineering, University of Texas at Arlington, 76019, USA
pp. 551-556

Contextual weighting for vocabulary tree based image retrieval (Abstract)

Ming Yang , NEC Laboratories America, Inc., Cupertino, CA 95014, USA
Kai Yu , NEC Laboratories America, Inc., Cupertino, CA 95014, USA
Tony X. Han , Dept. of ECE, Univ. of Missouri, Columbia, 65211, USA
Shenghuo Zhu , NEC Laboratories America, Inc., Cupertino, CA 95014, USA
Xiaoyu Wang , Dept. of ECE, Univ. of Missouri, Columbia, 65211, USA
Timothee Cour , NEC Laboratories America, Inc., Cupertino, CA 95014, USA
pp. 209-216

Efficient regression of general-activity human poses from depth images (Abstract)

Ross Girshick , Microsoft Research Cambridge, USA
Antonio Criminisi , Microsoft Research Cambridge, USA
Jamie Shotton , Microsoft Research Cambridge, USA
Andrew Fitzgibbon , Microsoft Research Cambridge, USA
Pushmeet Kohli , Microsoft Research Cambridge, USA
pp. 415-422

3D scene flow estimation with a rigid motion prior (Abstract)

Konrad Schindler , Photogrammetry and Remote Sensing, ETH Zürich, Switzerland
Stefan Roth , Department of Computer Science, TU Darmstadt, Germany
Christoph Vogel , Photogrammetry and Remote Sensing, ETH Zürich, Switzerland
pp. 1291-1298

Superpixel tracking (Abstract)

Ming-Hsuan Yang , Electrical Engineering and Computer Science, University of California at Merced, United States
Huchuan Lu , School of Information and Communication Engineering, Dalian University of Technology, China
Shu Wang , School of Information and Communication Engineering, Dalian University of Technology, China
Fan Yang , School of Information and Communication Engineering, Dalian University of Technology, China
pp. 1323-1330

Basis constrained 3D scene flow on a dynamic proxy (Abstract)

Martin Jagersand , University of Alberta, Canada
Dana Cobzas , University of Alberta, Canada
Neil Birkbeck , University of Alberta, Canada
pp. 1967-1974

Similarity invariant classification of events by KL divergence minimization (Abstract)

Mubarak Shah , University of Central Florida, USA
Salman Khokhar , University of Central Florida, USA
Imran Saleemi , University of Central Florida, USA
pp. 1903-1910

Learning occlusion with likelihoods for visual tracking (Abstract)

Woonhyun Nam , Department of Computer Science and Engineering, POSTECH, Korea
Bohyung Han , Department of Computer Science and Engineering, POSTECH, Korea
Suha Kwak , Department of Computer Science and Engineering, POSTECH, Korea
Joon Hee Han , Department of Computer Science and Engineering, POSTECH, Korea
pp. 1551-1558

Blurring-invariant Riemannian metrics for comparing signals and images (Abstract)

Eric Klassen , Florida State University, USA
Zhengwu Zhang , Florida State University, USA
Anuj Srivastava , Florida State University, USA
Rama Chellappa , University of Maryland, USA
Pavan Turaga , University of Maryland, USA
pp. 1770-1775

Simultaneous correspondence and non-rigid 3D reconstruction of the coronary tree from single X-ray images (Abstract)

Adriana Romero , Centre de Visió per Computador, UAB, Barcelona, Spain
Eduard Serradell , Institut de Robòtica i Informàtica Industrial, CSIC-UPC, Barcelona, Spain
Carlo Gatta , Centre de Visió per Computador, UAB, Barcelona, Spain
Ruben Leta , Hospital de la Santa Creu i Sant Pau, Barcelona, Spain
Francesc Moreno-Noguer , Hospital de la Santa Creu i Sant Pau, Barcelona, Spain
pp. 850-857

Incremental on-line semi-supervised learning for segmenting the left ventricle of the heart from ultrasound data (Abstract)

Jacinto C. Nascimento , Instituto de Sistemas e Robótica, Instituto Superior Técnico, Portugal
Gustavo Carneiro , Australian Centre for Visual Technologies, The University of Adelaide, Australia
pp. 1700-1707

Multi-observation visual recognition via joint dynamic sparse representation (Abstract)

Yanning Zhang , School of Computer Science, Northwestern Polytechnical University, Xi'an China
Thomas S. Huang , Beckman Institute, University of Illinois at Urbana-Champaign, USA
Haichao Zhang , School of Computer Science, Northwestern Polytechnical University, Xi'an China
Nasser M. Nasrabadi , U.S. Army Research Laboratory, 2800 Powder Mill Road, Adelphi, MD USA
pp. 595-602

Articulated part-based model for joint object detection and pose estimation (Abstract)

Silvio Savarese , Dept. of Electrical and Computer Engineering, University of Michigan at Ann Arbor, USA
Min Sun , Dept. of Electrical and Computer Engineering, University of Michigan at Ann Arbor, USA
pp. 723-730

Weakly supervised semantic segmentation with a multi-image model (Abstract)

Alexander Vezhnevets , ETH Zurich, 8092, Switzerland
Vittorio Ferrari , ETH Zurich, 8092, Switzerland
Joachim M. Buhmann , ETH Zurich, 8092, Switzerland
pp. 643-650

Segmentation as selective search for object recognition (Abstract)

Arnold W. M. Smeulders , University of Amsterdam, The Netherlands
Koen E. A. van de Sande , University of Amsterdam, The Netherlands
Jasper R. R. Uijlings , University of Trento, Italy
Theo Gevers , University of Amsterdam, The Netherlands
pp. 1879-1886

Extracting foreground masks towards object recognition (Abstract)

Amir Rosenfeld , School of Computer Science and Engineering, Hebrew university of Jerusalem, Israel 91904
Daphna Weinshall , School of Computer Science and Engineering, Hebrew university of Jerusalem, Israel 91904
pp. 1371-1378

Ensemble of exemplar-SVMs for object detection and beyond (Abstract)

Abhinav Gupta , Carnegie Mellon University, USA
Tomasz Malisiewicz , Carnegie Mellon University, USA
Alexei A. Efros , Carnegie Mellon University, USA
pp. 89-96

Viewpoint-aware object detection and pose estimation (Abstract)

Meirav Galun , Department of Computer Science and Applied Mathematics, The Weizmann Institute of Science, ISRAEL
Daniel Glasner , Department of Computer Science and Applied Mathematics, The Weizmann Institute of Science, ISRAEL
Sharon Alpert , Department of Computer Science and Applied Mathematics, The Weizmann Institute of Science, ISRAEL
Ronen Basri , Department of Computer Science and Applied Mathematics, The Weizmann Institute of Science, ISRAEL
Gregory Shakhnarovich , Toyota Technological Institute at Chicago, USA
pp. 1275-1282

Extracting adaptive contextual cues from unlabeled regions (Abstract)

Congcong Li , Cornell University, USA
Devi Parikh , Toyota Technological Institute Chicago, USA
Tsuhan Chen , Cornell University, USA
pp. 511-518

Efficient learning of sparse, distributed, convolutional feature representations for object recognition (Abstract)

Dae Yon Jung , Dept. of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, 48109, USA
Alfred O. Hero , Dept. of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, 48109, USA
Honglak Lee , Dept. of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, 48109, USA
Kihyuk Sohn , Dept. of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, 48109, USA
pp. 2643-2650

Silhouette-based object phenotype recognition using 3D shape priors (Abstract)

Roberto Cipolla , Department of Engineering, University of Cambridge, UK
Yu Chen , Department of Engineering, University of Cambridge, UK
Tae-Kyun Kim , Department of Electrical Engineering, Imperial College, London, UK
pp. 25-32

Video parsing for abnormality detection (Abstract)

Borislav Antic , Interdisciplinary Center for Scientific Computing, University of Heidelberg, Germany
Bjorn Ommer , Interdisciplinary Center for Scientific Computing, University of Heidelberg, Germany
pp. 2415-2422

Efficient parallel message computation for MAP inference (Abstract)

Aristeidis Sotiras , Center for Visual Computing, Ecole Centrale de Paris, Châtenay-Malabry, France
Nikos Paragios , Center for Visual Computing, Ecole Centrale de Paris, Châtenay-Malabry, France
Stavros Alchatzidis , Center for Visual Computing, Ecole Centrale de Paris, Châtenay-Malabry, France
pp. 1379-1386

Recursive MDL via graph cuts: Application to segmentation (Abstract)

Olga Veksler , Department of Computer Science University of Western Ontario, Canada
Lena Gorelick , Department of Computer Science University of Western Ontario, Canada
Andrew Delong , Department of Computer Science University of Western Ontario, Canada
Yuri Boykov , Department of Computer Science University of Western Ontario, Canada
pp. 890-897

Efficient Orthogonal Matching Pursuit using sparse random projections for scene and video classification (Abstract)

Rohit Prasad , Raytheon BBN Technologies, 10 Moulton Street, Cambridge, MA 02138, USA
Shiv N. Vitaladevuni , Raytheon BBN Technologies, 10 Moulton Street, Cambridge, MA 02138, USA
Pradeep Natarajan , Raytheon BBN Technologies, 10 Moulton Street, Cambridge, MA 02138, USA
Prem Natarajan , Raytheon BBN Technologies, 10 Moulton Street, Cambridge, MA 02138, USA
pp. 2312-2319

Building large urban environments from unstructured point data (Abstract)

Florent Lafarge , INRIA Sophia Antipolis, France
Clement Mallet , Université Paris Est, IGN, France
pp. 1068-1075

Local Intensity Order Pattern for feature description (Abstract)

Fuchao Wu , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China
Zhenhua Wang , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China
Bin Fan , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China
pp. 603-610

Minimum near-convex decomposition for robust shape representation (Abstract)

Zhou Ren , Nanyang Technological University, Singapore
Junsong Yuan , Nanyang Technological University, Singapore
Chunyuan Li , Huazhong Univ. of Sci. & Tech., China
Wenyu Liu , Huazhong Univ. of Sci. & Tech., China
pp. 303-310

StereoCut: Consistent interactive object selection in stereo image pairs (Abstract)

Scott Cohen , Adobe Systems, USA
Brian L. Price , Adobe Systems, USA
pp. 1148-1155

Are spatial and global constraints really necessary for segmentation? (Abstract)

Kevin Smith , Computer Vision Laboratory, EPFL, Lausanne, Siwtzerland
Xavier Boix , BIWI, ETH Zurich, Switzerland
Pascal Fua , Computer Vision Laboratory, EPFL, Lausanne, Siwtzerland
Aurelien Lucchi , Computer Vision Laboratory, EPFL, Lausanne, Siwtzerland
Yunpeng Li , Computer Vision Laboratory, EPFL, Lausanne, Siwtzerland
pp. 9-16

Segmentation from a box (Abstract)

Marie-Pierre Jolly , Siemens Corporate Research-Image Analytics and Informatics, 755 College Rd., Princeton NJ, USA
Aaron Seitz , University of California Riverside-Department of Psychology, 900 University Ave., USA
Leo Grady , Siemens Corporate Research-Image Analytics and Informatics, 755 College Rd., Princeton NJ, USA
pp. 367-374

Multi-task low-rank affinity pursuit for image segmentation (Abstract)

Jingdong Wang , Microsoft Research Asia, China
Shuicheng Yan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Bin Cheng , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Zhongyang Huang , Panasonic Singapore Laboratories, Singapore
Guangcan Liu , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
pp. 2439-2446

Structure-sensitive superpixels via geodesic distance (Abstract)

Rui Gan , Key Laboratory on Machine Perception, Peking University, China
Gang Zeng , Key Laboratory on Machine Perception, Peking University, China
Peng Wang , Key Laboratory on Machine Perception, Peking University, China
Hongbin Zha , Key Laboratory on Machine Perception, Peking University, China
Jingdong Wang , Microsoft Research Asia, China
pp. 447-454

Point-based calibration using a parametric representation of the general imaging model (Abstract)

Joao Queiro , Department of Mathematics, University of Coimbra, 3001-454, Portugal
Helder Araujo , Institute for Systems and Robotics, Department of Electrical and Computer Engineering-Polo 2, University of Coimbra, 3030-290, Portugal
Pedro Miraldo , Institute for Systems and Robotics, Department of Electrical and Computer Engineering-Polo 2, University of Coimbra, 3030-290, Portugal
pp. 2304-2311

Refractive shape from light field distortion (Abstract)

Ramesh Raskar , MIT Media Lab, USA
Wolfgang Heidrich , University of British Columbia, USA
David Roodnick , University of British Columbia, USA
Gordon Wetzstein , University of British Columbia, USA
pp. 1180-1186

Self-calibrating depth from refraction (Abstract)

Miaomiao Liu , Department of Computer Science, The University of Hong Kong, Hong Kong
Zhihu Chen , Department of Computer Science, The University of Hong Kong, Hong Kong
Kwan-Yee K. Wong , Department of Computer Science, The University of Hong Kong, Hong Kong
Xiaolong Zhu , Department of Computer Science, The University of Hong Kong, Hong Kong
Yasuyuki Matsushita , Microsoft Research Asia, Beijing, China
pp. 635-642

Latent Low-Rank Representation for subspace segmentation and feature extraction (Abstract)

Guangcan Liu , Electrical and Computer Engineering, National University of Singapore, Singapore
Shuicheng Yan , Electrical and Computer Engineering, National University of Singapore, Singapore
pp. 1615-1622

Correlative multi-label multi-instance image annotation (Abstract)

Bin Wu , School of Computer Science, Fudan University, Shanghai, China
Jie Zhang , School of Computer Science, Fudan University, Shanghai, China
Xiangyang Xue , School of Computer Science, Fudan University, Shanghai, China
Yao Lu , School of Computer Science, Fudan University, Shanghai, China
Wei Zhang , School of Computer Science, Fudan University, Shanghai, China
Jianping Fan , Department of Computer Science, UNC-Charlotte, NC28223, USA
pp. 651-658

Learning equivariant structured output SVM regressors (Abstract)

Andrea Vedaldi , Department of Engineering Science, University of Oxford, UK
Matthew Blaschko , Department of Engineering Science, University of Oxford, UK
Andrew Zisserman , Department of Engineering Science, University of Oxford, UK
pp. 959-966

Learning a mixture of sparse distance metrics for classification and dimensionality reduction (Abstract)

Zhuowen Tu , Lab of Neuro Imaging and Department of Computer Science, UCLA, USA
Quannan Li , Lab of Neuro Imaging and Department of Computer Science, UCLA, USA
Yi Hong , Lab of Neuro Imaging and Department of Computer Science, UCLA, USA
Jiayan Jiang , Lab of Neuro Imaging and Department of Computer Science, UCLA, USA
pp. 906-913

Learning specific-class segmentation from diverse data (Abstract)

Haithem Turki , Computer Science Department, Stanford University, USA
M. Pawan Kumar , Computer Science Department, Stanford University, USA
Daphne Koller , Computer Science Department, Stanford University, USA
Dan Preston , Computer Science Department, Stanford University, USA
pp. 1800-1807

Tasting families of features for image classification (Abstract)

Charles Dubout , Idiap Research Institute, Switzerland
Francois Fleuret , Idiap Research Institute, Switzerland
pp. 929-936

Low order dynamics embedding for high dimensional time series (Abstract)

Fei Xiong , Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Mario Sznaier , Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Octavia I. Camps , Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
pp. 2368-2374

A nonparametric Riemannian framework on tensor field with application to foreground segmentation (Abstract)

Rui Caseiro , Institute for Systems and Robotics - University of Coimbra, Portugal
Jorge Batista , Institute for Systems and Robotics - University of Coimbra, Portugal
Pedro Martins , Institute for Systems and Robotics - University of Coimbra, Portugal
Joao F. Henriques , Institute for Systems and Robotics - University of Coimbra, Portugal
pp. 1-8
Papers

Panoramic stereo video textures (Abstract)

Sebastien Roy , Université de Montréal, Canada
Vincent Couture , Université de Montréal, Canada
Michael S. Langer , McGill University, Canada
pp. 1251-1258

Scale and object aware image retargeting for thumbnail browsing (Abstract)

Jin Sun , Center for Data Analytics & Biomedical Informatics, Dept. of Computer & Information Sciences, Temple University, Philadelphia, 19122, USA
Haibin Ling , Center for Data Analytics & Biomedical Informatics, Dept. of Computer & Information Sciences, Temple University, Philadelphia, 19122, USA
pp. 1511-1518

Probabilistic 3D object recognition with both positive and negative evidences (Abstract)

Sukhan Lee , Intelligent System Research Institute, SungKyunKwan University, Suwon, Korea
Zhaojin Lu , Intelligent System Research Institute, SungKyunKwan University, Suwon, Korea
Hyunwoo Kim , Multimedia Research Team, Daum Communication Corp., Korea
pp. 2360-2367

Poster sessions day 3 (Abstract)

pp. lvi

Automatic salient object extraction with contextual cue (Abstract)

Le Wang , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, China
Gang Hua , Department of Computer Science, Stevens Institute of Technology, USA
Nanning Zheng , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, China
Jianru Xue , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, China
pp. 105-112

Predicting occupation via human clothing and contexts (Abstract)

Meng Wang , School of Computing, National University of Singapore, Singapore
Shuicheng Yan , Department of Electrical and Computer Engineering, Singapore
Zheng Song , Department of Electrical and Computer Engineering, Singapore
Xian-sheng Hua , Microsoft Research Asia, China
pp. 1084-1091

An automatic assembly and completion framework for fragmented skulls (Abstract)

Li Wei , Department of Automation, Xiamen University, China
Zhao Yin , Department of Automation, Xiamen University, China
Mary Manhein , Dept. Electrical & Computer Engineering, Center for Computation and Technology, Louisiana State University, USA
Xin Li , Department of Geography & Anthropology, LSU FACES Laboratory, Louisiana State University, USA
pp. 2532-2539

Stereo reconstruction using high order likelihood (Abstract)

Ho Yub Jung , Department of EECS, ASRI, Seoul National University, 151-742, Korea
Sang Uk Lee , Department of EECS, ASRI, Seoul National University, 151-742, Korea
Kyoung Mu Lee , Department of EECS, ASRI, Seoul National University, 151-742, Korea
pp. 1211-1218

2D-3D fusion for layer decomposition of urban facades (Abstract)

Qian Zheng , SIAT, China
Daniel Cohen-Or , Tel Aviv Univ., China
Yangyan Li , SIAT, China
Baoquan Chen , SIAT, China
Niloy J. Mitra , UCL, China
Andrei Sharf , Ben-Gurion Univ., China
pp. 882-889

Simultaneous multi-body stereo and segmentation (Abstract)

Guofeng Zhang , State Key Lab of CAD&CG, Zhejiang University, China
Hujun Bao , State Key Lab of CAD&CG, Zhejiang University, China
Jiaya Jia , The Chinese University of Hong Kong, China
pp. 826-833

Center-surround divergence of feature statistics for salient object detection (Abstract)

Simone Frintrop , Rheinische Friedrich-Wilhelms Universität Bonn, Institute of Computer Science III, Römerstr. 164, 53117, Germany
Dominik A. Klein , Rheinische Friedrich-Wilhelms Universität Bonn, Institute of Computer Science III, Römerstr. 164, 53117, Germany
pp. 2214-2219

What characterizes a shadow boundary under the sun and sky? (Abstract)

Lance Williams , Multimedia Lab, Nokia Research Center, USA
Gang Hua , Computer Science Dept., Stevens Institute of Technology, USA
Xiang Huang , EECS Dept., Northwestern University, USA
Jack Tumblin , EECS Dept., Northwestern University, USA
pp. 898-905

Semantic contours from inverse detectors (Abstract)

Bharath Hariharan , EECS, U.C. Berkeley, CA 94720, USA
Lubomir Bourdev , EECS, U.C. Berkeley, CA 94720, USA
Pablo Arbelaez , EECS, U.C. Berkeley, CA 94720, USA
Jitendra Malik , EECS, U.C. Berkeley, CA 94720, USA
Subhransu Maji , EECS, U.C. Berkeley, CA 94720, USA
pp. 991-998

High quality image reconstruction from RAW and JPEG image pair (Abstract)

Lu Yuan , Microsoft Research Asia, China
Jian Sun , Microsoft Research Asia, China
pp. 2158-2165

Automatic construction of an action video shot database using web videos (Abstract)

Keiji Yanai , Department of Informatics, The University of Electro-Communications, Tokyo, 1-5-1 Chogugaoka, Chofu-shi 182-8585 Japan
Do Hang Nga , Department of Informatics, The University of Electro-Communications, Tokyo, 1-5-1 Chogugaoka, Chofu-shi 182-8585 Japan
pp. 527-534

Feature seeding for action recognition (Abstract)

Rahul Sukthankar , The Robotics Institute, Carnegie Mellon University, USA
Pyry Matikainen , The Robotics Institute, Carnegie Mellon University, USA
Martial Hebert , The Robotics Institute, Carnegie Mellon University, USA
pp. 1716-1723

Spectral learning of latent semantics for action recognition (Abstract)

Horace H.S. Ip , Department of Computer Science, City University of Hong Kong, Hong Kong
Yuxin Peng , Institute of Computer Science and Technology, Peking University, Beijing 100871, China
Zhiwu Lu , Institute of Computer Science and Technology, Peking University, Beijing 100871, China
pp. 1503-1510

Learning parameterized histogram kernels on the simplex manifold for image and action classification (Abstract)

Stan Sclaroff , Computer Science Dept., Boston University, USA
Vitaly Ablavsky , CVLab, EPFL, Switzerland
pp. 1473-1480

Probabilistic group-level motion analysis and scenario recognition (Abstract)

Nils Krahnstoever , GE Global Research Center, One Research Circle, Niskayuna, NY, USA
Ming-Ching Chang , GE Global Research Center, One Research Circle, Niskayuna, NY, USA
Weina Ge , GE Global Research Center, One Research Circle, Niskayuna, NY, USA
pp. 747-754

Digital anti-aging in face images (Abstract)

Guodong Guo , Dept. of CSEE, West Virginia University, USA
pp. 2510-2515

Recognising spontaneous facial micro-expressions (Abstract)

Matti Pietikainen , Machine Vision Group, Department of Computer Science and Engineering, University of Oulu, PO Box 4500, 90014, Finland
Guoying Zhao , Machine Vision Group, Department of Computer Science and Engineering, University of Oulu, PO Box 4500, 90014, Finland
Xiaobai Li , Machine Vision Group, Department of Computer Science and Engineering, University of Oulu, PO Box 4500, 90014, Finland
Tomas Pfister , Machine Vision Group, Department of Computer Science and Engineering, University of Oulu, PO Box 4500, 90014, Finland
pp. 1449-1456

Inferring human gaze from appearance via adaptive linear regression (Abstract)

Yoichi Sato , Institute of Industrial Science, the University of Tokyo, Japan
Takahiro Okabe , Institute of Industrial Science, the University of Tokyo, Japan
Feng Lu , Institute of Industrial Science, the University of Tokyo, Japan
Yusuke Sugano , Institute of Industrial Science, the University of Tokyo, Japan
pp. 153-160

Sparse representation or collaborative representation: Which helps face recognition? (Abstract)

Xiangchu Feng , Dept. of Applied Mathematics, Xidian University, Xi'an, China
Lei Zhang , Dept. of Computing, The Hong Kong Polytechnic University, China
Meng Yang , Dept. of Computing, The Hong Kong Polytechnic University, China
pp. 471-478

Sparse representation or collaborative representation: Which helps face recognition? (Abstract)

Lei Zhang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Meng Yang , Dept. of Comput., Hong Kong Polytech. Univ., Hong Kong, China
Xiangchu Feng , Dept. of Appl. Math., Xidian Univ., Xi'an, China
pp. 471-478
Papers

Pose estimation from reflections for specular surface recovery (Abstract)

Zhihu Chen , The University of Hong Kong, Hong Kong
Miaomiao Liu , The University of Hong Kong, Hong Kong
Kwan-Yee K. Wong , The University of Hong Kong, Hong Kong
Zhenwen Dai , Frankfurt Institute for Advanced Studies, Germany
pp. 579-586

Scan rectification for structured light range sensors with rolling shutters (Abstract)

Per-Erik Forssen , Department of Electrical Engineering, Linköping University, Sweden
Erik Ringaby , Department of Electrical Engineering, Linköping University, Sweden
pp. 1575-1582

Decoupling photometry and geometry in dense variational camera calibration (Abstract)

Kalin Kolev , TU Munich, Germany
Mathieu Aubry , TU Munich, Germany
Bastian Goldluecke , TU Munich, Germany
Daniel Cremers , TU Munich, Germany
pp. 1411-1418

Variational recursive joint estimation of dense scene structure and camera motion from monocular high speed traffic sequences (Abstract)

Jorg H. Kappes , HCI and IPA, Heidelberg University, Speyerer Str. 6, 69115, Germany
Frank Lenzen , HCI and IPA, Heidelberg University, Speyerer Str. 6, 69115, Germany
Florian Becker , HCI and IPA, Heidelberg University, Speyerer Str. 6, 69115, Germany
Christoph Schnorr , HCI and IPA, Heidelberg University, Speyerer Str. 6, 69115, Germany
pp. 1692-1699

Automated articulated structure and 3D shape recovery from point correspondences (Abstract)

Lourdes Agapito , Queen Mary University of London, Mile End Road - E1 4NS, United Kingdom
Chris Russell , Queen Mary University of London, Mile End Road - E1 4NS, United Kingdom
Joao Fayad , Queen Mary University of London, Mile End Road - E1 4NS, United Kingdom
pp. 431-438

Parallelizable inpainting and refinement of diffeomorphisms using Beltrami holomorphic flow (Abstract)

Tony F. Chan , Hong Kong University of Science and Technology, Office of the President, HKUST,, Clear Water Bay, Kowloon, Hong Kong
Lok Ming Lui , The Chinese University of Hong Kong, Department of Mathematics, Room 207, Lady Shaw Building, CUHK, Shatin, Hong Kong
Tsz Wai Wong , University of California, Los Angeles Department of Mathematics, 520 Portola Plaza, Math Science Building 6363, UCLA, 90095, USA
Xianfeng Gu , State University of New York at Stony Brook, Department of Computer Science, Room 2425, Computer Science Building, State University of New York at Stony Brook, 11794-4400, USA
pp. 2383-2390

Markov Random Field-based fitting of a subdivision-based geometric atlas (Abstract)

Nikos Paragios , Computational Biomedicine Lab, University of Houston, TX, USA
James P. Carson , Pacific Northwest National Laboratory, Richland, WA, USA
Uday Kurkure , Computational Biomedicine Lab, University of Houston, TX, USA
Tao Ju , Washington University in St. Louis, MO, USA
Yen H. Le , Computational Biomedicine Lab, University of Houston, TX, USA
Ioannis A. Kakadiaris , Computational Biomedicine Lab, University of Houston, TX, USA
pp. 2540-2547

Modeling temporal coherence for optical flow (Abstract)

Andres Bruhn , Vision and Image Processing Group, Saarland University, Germany
Sebastian Volz , Vision and Image Processing Group, Saarland University, Germany
Levi Valgaerts , Vision and Image Processing Group, Saarland University, Germany
Henning Zimmer , Mathematical Image Analysis Group, Saarland University, Germany
pp. 1116-1123

Accurate 3D pose estimation from a single depth image (Abstract)

Liu Ren , Bosch Research, USA
Mao Ye , University of Kentucky, USA
Xianwang Wang , HP Labs, Palo Alto, USA
Ruigang Yang , University of Kentucky, USA
Marc Pollefeys , ETH Zürich, Germany
pp. 731-738

Dynamic subspace-based coordinated multicamera tracking (Abstract)

Mustafa Ayazoglu , Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Caglayan Dicle , Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Binlong Li , Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Octavia I. Camps , Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
Mario Sznaier , Dept. of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
pp. 2462-2469

A data-driven approach for real-time full body pose reconstruction from a depth camera (Abstract)

Hans-Peter Seidel , Saarland University & MPI Informatik, Saarbrücken, Germany
Gaurav Bharaj , Saarland University & MPI Informatik, Saarbrücken, Germany
Meinard Muller , Saarland University & MPI Informatik, Saarbrücken, Germany
Andreas Baak , Saarland University & MPI Informatik, Saarbrücken, Germany
Christian Theobalt , Saarland University & MPI Informatik, Saarbrücken, Germany
pp. 1092-1099

Optical flow estimation using learned sparse model (Abstract)

Kui Jia , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong
Xiaogang Wang , Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong
pp. 2391-2398

Struck: Structured output tracking with kernels (Abstract)

Philip H. S. Torr , Oxford Brookes University, UK
Sam Hare , Oxford Brookes University, UK
Amir Saffari , Oxford Brookes University, UK
pp. 263-270

Delta-Dual Hierarchical Dirichlet Processes: A pragmatic abnormal behaviour detector (Abstract)

Tom S.F. Haines , School of Electrical Engineering and Computer Science, Queen Mary, University of London, UK
Tao Xiang , School of Electrical Engineering and Computer Science, Queen Mary, University of London, UK
pp. 2198-2205

Modeling image similarity by Gaussian mixture models and the Signature Quadratic Form Distance (Abstract)

Thomas Seidl , Data Management and Data Exploration Group, RWTH Aachen University, Germany
Christian Beecks , Data Management and Data Exploration Group, RWTH Aachen University, Germany
Steffen Kirchhoff , Data Management and Data Exploration Group, RWTH Aachen University, Germany
Anca Maria Ivanescu , Data Management and Data Exploration Group, RWTH Aachen University, Germany
pp. 1754-1761

Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet Divergence (Abstract)

Suvrit Sra , MPI for Intelligent Systems, Tübingen, Germany
Arindam Banerjee , Dept. of CS & Engg., University of Minnesota, USA
Nikolaos Papanikolopoulos , Dept. of CS & Engg., University of Minnesota, USA
Anoop Cherian , Dept. of CS & Engg., University of Minnesota, USA
pp. 2399-2406

Scalable object-class retrieval with approximate and top-k ranking (Abstract)

Chen Fang , Computer Science Department, Dartmouth College, Hanover, NH 03755, U.S.A.
Lorenzo Torresani , Computer Science Department, Dartmouth College, Hanover, NH 03755, U.S.A.
Mohammad Rastegari , Computer Science Department, Dartmouth College, Hanover, NH 03755, U.S.A.
pp. 2659-2666

Complementary hashing for approximate nearest neighbor search (Abstract)

Hao Xu , MOE-MS KeyLab of MCC, University of Science and Technology of China, China
Nenghai Yu , MOE-MS KeyLab of MCC, University of Science and Technology of China, China
Jingdong Wang , Microsoft Research Asia, China
Gang Zeng , Key Laboratory of Machine Perception, Peking University, China
Shipeng Li , Microsoft Research Asia, China
Zhu Li , Core Networks Research, Huawei Technology, USA
pp. 1631-1638

Visual word disambiguation by semantic contexts (Abstract)

Frederic Jurie , GREYC, University of Caen, France
Yu Su , GREYC, University of Caen, France
pp. 311-318

Understanding scenes on many levels (Abstract)

Svetlana Lazebnik , Dept. of Computer Science, University of North Carolina, Chapel Hill, 27599, USA
Joseph Tighe , Dept. of Computer Science, University of North Carolina, Chapel Hill, 27599, USA
pp. 335-342

Multiclass transfer learning from unconstrained priors (Abstract)

Tatiana Tommasi , Idiap Research Institute, CH-1920 Martigny, Switzerland
Barbara Caputo , Idiap Research Institute, CH-1920 Martigny, Switzerland
Luo Jie , Idiap Research Institute, CH-1920 Martigny, Switzerland
pp. 1863-1870

Learning a category independent object detection cascade (Abstract)

Esa Rahtu , Machine Vision Group, University of Oulu, Finland
Matthew Blaschko , Visual Geometry Group, University of Oxford, UK
Juho Kannala , Machine Vision Group, University of Oulu, Finland
pp. 1052-1059

In defense of soft-assignment coding (Abstract)

Lei Wang , School of Engineering, Australian National University, ACT 0200, Australia
Lingqiao Liu , School of Engineering, Australian National University, ACT 0200, Australia
Xinwang Liu , School of Engineering, Australian National University, ACT 0200, Australia
pp. 2486-2493

Assessing the aesthetic quality of photographs using generic image descriptors (Abstract)

Florent Perronnin , Textual and Visual Pattern Analysis (TVPA), Xerox Research Centre Europe (XRCE), France
Luca Marchesotti , Textual and Visual Pattern Analysis (TVPA), Xerox Research Centre Europe (XRCE), France
Gabriela Csurka , Textual and Visual Pattern Analysis (TVPA), Xerox Research Centre Europe (XRCE), France
Diane Larlus , Textual and Visual Pattern Analysis (TVPA), Xerox Research Centre Europe (XRCE), France
pp. 1784-1791

Evaluation of image features using a photorealistic virtual world (Abstract)

Antonio Torralba , MIT Computer Science and Artificial Intelligence Laboratory, USA
Biliana Kaneva , MIT Computer Science and Artificial Intelligence Laboratory, USA
William T. Freeman , MIT Computer Science and Artificial Intelligence Laboratory, USA
pp. 2282-2289

Modeling spatial layout with fisher vectors for image categorization (Abstract)

Jakob Verbeek , LEAR team, INRIA Grenoble Rhône-Alpes, France
Frederic Jurie , LEAR team, INRIA Grenoble Rhône-Alpes, France
Josip Krapac , LEAR team, INRIA Grenoble Rhône-Alpes, France
pp. 1487-1494

Annotator rationales for visual recognition (Abstract)

Kristen Grauman , Dept. of Computer Science, University of Texas at Austin, USA
Jeff Donahue , Dept. of Computer Science, University of Texas at Austin, USA
pp. 1395-1402

Fusing visual and range imaging for object class recognition (Abstract)

Dan Levi , General Motors Advanced Technical Center, Hamada 7, Herzliya, Israel
Dmitri Hanukaev , The center for neural computation, Hebrew university of Jerusalem, Israel 91904
Aharon Bar-Hillel , General Motors Advanced Technical Center, Hamada 7, Herzliya, Israel
pp. 65-72

Conditional Random Fields for multi-camera object detection (Abstract)

Pascal Fua , EPFL, Lausanne (Switzerland)
Horesh Ben Shitrit , EPFL, Lausanne (Switzerland)
Gemma Roig , ETHZ, Zurich (Switzerland)
Xavier Boix , ETHZ, Zurich (Switzerland)
pp. 563-570

Tight convex relaxations for vector-valued labeling problems (Abstract)

Daniel Cremers , TU Munich, Germany
Bastian Goldluecke , TU Munich, Germany
Evgeny Strekalovskiy , TU Munich, Germany
pp. 2328-2335

Generalized roof duality for pseudo-boolean optimization (Abstract)

Petter Strandmark , Centre for Mathematical Sciences, Lund University, Sweden
Fredrik Kahl , Centre for Mathematical Sciences, Lund University, Sweden
pp. 255-262

A graph cut algorithm for higher-order Markov Random Fields (Abstract)

Alexander Fix , Cornell University, USA
Ramin Zabih , Cornell University, USA
Aritanan Gruber , Rutgers University, USA
Endre Boros , Rutgers University, USA
pp. 1020-1027

Stereo time-of-flight (Abstract)

Diana Mateus , Computer Aided Medical Procedures (CAMP), Technische Universität München (TUM), Germany
Nassir Navab , Computer Aided Medical Procedures (CAMP), Technische Universität München (TUM), Germany
Victor Castaneda , Computer Aided Medical Procedures (CAMP), Technische Universität München (TUM), Germany
pp. 1684-1691

Dense one-shot 3D reconstruction by detecting continuous regions with parallel line projection (Abstract)

Hiroshi Kawasaki , Kagoshima University, Japan
Ryo Furukawa , Hiroshima City University, Japan
Ryusuke Sagawa , AIST, Tsukuba, Japan
Shota Kiyota , Kagoshima University, Japan
pp. 1911-1918

Shared shape spaces (Abstract)

Ian Reid , University of Oxford, UK
Victor Adrian Prisacariu , University of Oxford, UK
pp. 2587-2594

Image segmentation by figure-ground composition into maximal cliques (Abstract)

Cristian Sminchisescu , Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn, Germany
Joao Carreira , Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn, Germany
Adrian Ion , Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn, Germany
pp. 2110-2117

A convex framework for image segmentation with moment constraints (Abstract)

Daniel Cremers , TU Munich, Germany
Maria Klodt , TU Munich, Germany
pp. 2236-2243

Active geodesics: Region-based active contour segmentation with a global edge-based constraint (Abstract)

Anthony Yezzi , Georgia Institute of Technology, Atlanta, USA
Vikram Appia , Georgia Institute of Technology, Atlanta, USA
pp. 1975-1980

Probabilistic image segmentation with closedness constraints (Abstract)

Bjoern Andres , HCI, University of Heidelberg, Speyerer Str. 6, 69115, Germany
Ullrich Kothe , HCI, University of Heidelberg, Speyerer Str. 6, 69115, Germany
Thorsten Beier , HCI, University of Heidelberg, Speyerer Str. 6, 69115, Germany
Jorg H. Kappes , HCI, University of Heidelberg, Speyerer Str. 6, 69115, Germany
Fred A. Hamprecht , HCI, University of Heidelberg, Speyerer Str. 6, 69115, Germany
pp. 2611-2618

Face reconstruction in the wild (Abstract)

Steven M. Seitz , University of Washington and Google Inc., USA
Ira Kemelmacher-Shlizerman , University of Washington, USA
pp. 1746-1753

Multiview 3D warps (Abstract)

Adrien Bartoli , ALCoV - ISIT, Université Clermont 1, Italy
Alessio Del Bue , Istituto Italiano di Tecnologia (IIT), Italy
pp. 675-682

Optimal object matching via convexification and composition (Abstract)

Junzhou Huang , Department of Computer Science & Engineering, University of Texas at Arlington, USA
Shaoting Zhang , Department of Computer Science, Rutgers University, USA
Hongsheng Li , Department of Computer Science & Engineering, Lehigh University, USA
Xiaolei Huang , Department of Computer Science & Engineering, Lehigh University, USA
pp. 33-40

Viewpoint invariant 3D landmark model inference from monocular 2D images using higher-order priors (Abstract)

Yun Zeng , Department of Computer Science, Stony Brook University, NY, USA
Loic Simon , Center for Visual Computing, Ecole Centrale Paris, Châtenay-Malabry, France
Nikos Paragios , Center for Visual Computing, Ecole Centrale Paris, Châtenay-Malabry, France
Ioannis Kakadiaris , Computational Biomedicine Lab, University of Houston, TX, USA
Dimitris Samaras , Department of Computer Science, Stony Brook University, NY, USA
Chaohui Wang , Center for Visual Computing, Ecole Centrale Paris, Châtenay-Malabry, France
pp. 319-326

Isotonic CCA for sequence alignment and activity recognition (Abstract)

Vladimir Pavlovic , Rutgers, The state university of New Jersey, Piscataway, USA
Shahriar Shariat , Rutgers, The state university of New Jersey, Piscataway, USA
pp. 2572-2578

The power of comparative reasoning (Abstract)

David A. Ross , Google Inc, USA
Ruei-sung Lin , Google Inc, USA
Jay Yagnik , Google Inc, USA
Dennis Strelow , Google Inc, USA
pp. 2431-2438

Adaptive deconvolutional networks for mid and high level feature learning (Abstract)

Rob Fergus , Dept. of Computer Science, Courant Institute, New York University, USA
Matthew D. Zeiler , Dept. of Computer Science, Courant Institute, New York University, USA
Graham W. Taylor , Dept. of Computer Science, Courant Institute, New York University, USA
pp. 2018-2025

Multiclass recognition and part localization with humans in the loop (Abstract)

Catherine Wah , Department of Computer Science and Engineering, University of California, San Diego, USA
Steve Branson , Department of Computer Science and Engineering, University of California, San Diego, USA
Serge Belongie , Department of Electrical Engineering, California Institute of Technology, USA
Pietro Perona , Department of Electrical Engineering, California Institute of Technology, USA
pp. 2524-2531

Unsupervised and semi-supervised learning via l<inf>1</inf>-norm graph (Abstract)

Heng Huang , Department of Computer Science and Engineering, University of Texas, Arlington, 76019, USA
Feiping Nie , Department of Computer Science and Engineering, University of Texas, Arlington, 76019, USA
Chris Ding , Department of Computer Science and Engineering, University of Texas, Arlington, 76019, USA
Hua Wang , Department of Computer Science and Engineering, University of Texas, Arlington, 76019, USA
pp. 2268-2273

Building a better probabilistic model of images by factorization (Abstract)

Benjamin J. Culpepper , UC Berkeley, CA, USA
Jascha Sohl-Dickstein , UC Berkeley, CA, USA
Bruno A. Olshausen , UC Berkeley, CA, USA
pp. 2011-2017

Dynamic Manifold Warping for view invariant action recognition (Abstract)

Gerard Medioni , Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, 90089, USA
Dian Gong , Institute for Robotics and Intelligent Systems, University of Southern California, Los Angeles, 90089, USA
pp. 571-578

Dynamic texture classification using dynamic fractal analysis (Abstract)

Haibin Ling , Department of Computer and Information Sciences, Temple University, Philadelphia, 19122, U.S.A.
Hui Ji , Department of Mathematics, National University of Singapore, Singapore 117542
Yuhui Quan , School of Computer Science & Engineering, South China Univ. of Tech., Guangzhou 510006, China
Yong Xu , School of Computer Science & Engineering, South China Univ. of Tech., Guangzhou 510006, China
pp. 1219-1226

Simplification of 3D morphable models (Abstract)

Ankur Patel , Department of Computer Science, The University of York, USA
William A. P. Smith , Department of Computer Science, The University of York, USA
pp. 271-278

Multi-view repetitive structure detection (Abstract)

Nianjuan Jiang , National University of Singapore, Singapore
Ping Tan , National University of Singapore, Singapore
Loong-Fah Cheong , National University of Singapore, Singapore
pp. 535-542

Multi-hypothesis motion planning for visual object tracking (Abstract)

Jianbo Shi , GRASP Lab, University of Pennsylvania, USA
Maxim Likhachev , Robotics Institute, Carnegie Mellon University, USA
Jack Sim , GRASP Lab, University of Pennsylvania, USA
Haifeng Gong , GRASP Lab, University of Pennsylvania, USA
pp. 619-626

Poster sessions day 4 (Abstract)

pp. lvii

Home 3D body scans from noisy image and range data (Abstract)

Alexander Weiss , Dept. of Computer Science, Brown University, Providence, RI, USA
Michael J. Black , Perceiving Systems Dept., Max Planck Institute for Intelligent Systems, Tübingen, Germany
David Hirshberg , Perceiving Systems Dept., Max Planck Institute for Intelligent Systems, Tübingen, Germany
pp. 1951-1958

High quality depth map upsampling for 3D-TOF cameras (Abstract)

Jaesik Park , Korea Advanced Institute of Science and Technology (KAIST), Korea
Yu-Wing Tai , Korea Advanced Institute of Science and Technology (KAIST), Korea
Hyeongwoo Kim , Korea Advanced Institute of Science and Technology (KAIST), Korea
Inso Kweon , Korea Advanced Institute of Science and Technology (KAIST), Korea
Michael S. Brown , National University of Singapore (NUS), Singapore
pp. 1623-1630

Material-specific user colour profiles from imaging spectroscopy data (Abstract)

Cong Phuoc Huynh , NICTA y, Locked Bag 8001, Canberra ACT 2601, Australia
Lin Gu , School of Engineering, Australian National University, Canberra ACT 0200, Australia
Antonio Robles-Kelly , NICTA y, Locked Bag 8001, Canberra ACT 2601, Australia
Jun Zhou , School of Engineering, Australian National University, Canberra ACT 0200, Australia
pp. 1987-1994

Dense disparity maps from sparse disparity measurements (Abstract)

Simon Hawe , Department of Electrical Engineering and Information Technology, Technische Universität München, Arcisstraße 21, 80290, Germany
Klaus Diepold , Department of Electrical Engineering and Information Technology, Technische Universität München, Arcisstraße 21, 80290, Germany
Martin Kleinsteuber , Department of Electrical Engineering and Information Technology, Technische Universität München, Arcisstraße 21, 80290, Germany
pp. 2126-2133

Aerial 3D reconstruction with line-constrained dynamic programming (Abstract)

Huei-Hung Liao , Univ of Southern California, USA
Gerard Medioni , Univ of Southern California, USA
Yuping Lin , Univ of Southern California, USA
pp. 1855-1862

Fusing generic objectness and visual saliency for salient object detection (Abstract)

Tyng-Luh Liu , Institute of Information Science, Academia Sinica, Taiwan
Shang-Hong Lai , Department of Computer Science, National Tsing Hua University, Taiwan
Kai-Yueh Chang , Institute of Information Science, Academia Sinica, Taiwan
Hwann-Tzong Chen , Department of Computer Science, National Tsing Hua University, Taiwan
pp. 914-921

Cluster-based color space optimizations (Abstract)

Cheryl Lau , University of British Columbia, Canada
Rafal Mantiuk , Bangor University, UK
Wolfgang Heidrich , University of British Columbia, Canada
pp. 1172-1179

Towards accurate and efficient representation of image irradiance of convex-Lambertian objects under unknown near lighting (Abstract)

Shireen Y. Elhabian , University of Louisville, CVIP Lab, KY, USA
Aly A. Farag , University of Louisville, CVIP Lab, KY, USA
Ham Rara , University of Louisville, CVIP Lab, KY, USA
pp. 1732-1737

Color photometric stereo for multicolored surfaces (Abstract)

Bjorn Stenger , Toshiba Research Europe, UK
Robert Anderson , University of Cambridge, UK
Roberto Cipolla , University of Cambridge, UK
pp. 2182-2189

BRISK: Binary Robust invariant scalable keypoints (Abstract)

Stefan Leutenegger , Autonomous Systems Lab, ETH Zürich, Switzerland
Roland Y. Siegwart , Autonomous Systems Lab, ETH Zürich, Switzerland
Margarita Chli , Autonomous Systems Lab, ETH Zürich, Switzerland
pp. 2548-2555

Salient object detection by composition (Abstract)

Jian Sun , Microsoft Research Asia, China
Chao Zhang , Key Laboratory of Machine Perception (MOE), Peking University, China
Yichen Wei , Microsoft Research Asia, China
Jie Feng , Key Laboratory of Machine Perception (MOE), Peking University, China
Litian Tao , Microsoft Search Technology Center Asia, China
pp. 1028-1035

Action recognition in cluttered dynamic scenes using Pose-Specific Part Models (Abstract)

Ram Nevatia , University of Southern California, Los Angeles, USA
Vivek Kumar Singh , University of Southern California, Los Angeles, USA
pp. 113-120

Human activity prediction: Early recognition of ongoing activities from streaming videos (Abstract)

M. S. Ryoo , Electronics and Telecommunications Research Institute, Daejeon, Korea
pp. 1036-1043

Discriminative figure-centric models for joint action localization and recognition (Abstract)

Greg Mori , School of Computing Science, Simon Fraser University, Canada
Tian Lan , School of Computing Science, Simon Fraser University, Canada
Yang Wang , Dept. of Computer Science, UIUC, USA
pp. 2003-2010

Understanding egocentric activities (Abstract)

Ali Farhadi , Computer Science Department, University of Illinois at Urbana-Champaign, USA
Alireza Fathi , College of Computing, Georgia Institute of Technology, USA
James M. Rehg , College of Computing, Georgia Institute of Technology, USA
pp. 407-414

Unsupervised metric learning for face identification in TV video (Abstract)

Cordelia Schmid , LEAR, INRIA Grenoble Laboratoire Jean Kuntzmann, France
Jakob Verbeek , LEAR, INRIA Grenoble Laboratoire Jean Kuntzmann, France
Ramazan Gokberk Cinbis , LEAR, INRIA Grenoble Laboratoire Jean Kuntzmann, France
pp. 1559-1566

Fully automatic pose-invariant face recognition via 3D pose normalization (Abstract)

Kinh H. Tieu , Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
Tim K. Marks , Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
Akshay Asthana , Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
MV Rohith , Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
Michael J. Jones , Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
pp. 937-944

Shape-constrained Gaussian process regression for facial-point-based head-pose normalization (Abstract)

Ognjen Rudovic , Comp. Dept, Imperial College London, UK
Maja Pantic , Comp. Dept, Imperial College London, UK
pp. 1495-1502

Discriminative multi-manifold analysis for face recognition from a single training sample per person (Abstract)

Gang Wang , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
Yap-Peng Tan , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
Jiwen Lu , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
pp. 1943-1950

Fisher Discrimination Dictionary Learning for sparse representation (Abstract)

David Zhang , Dept. of Computing, The Hong Kong Polytechnic University, China
Lei Zhang , Dept. of Computing, The Hong Kong Polytechnic University, China
Xiangchu Feng , Dept. of Applied Mathematics, Xidian University, Xi'an, China
Meng Yang , Dept. of Computing, The Hong Kong Polytechnic University, China
pp. 543-550

Robust topological features for deformation invariant image matching (Abstract)

Ram Vasudevan , Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA
Ruzena Bajcsy , Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA
Ron Alterovitz , Department of Computer Science, University of North Carolina, Chapel Hill, USA
Edgar Lobaton , Department of Computer Science, University of North Carolina, Chapel Hill, USA
pp. 2516-2523

Optimizing polynomial solvers for minimal geometry problems (Abstract)

Kostas Daniilidis , University of Pennsylvania, Philadelphia, USA
Oleg Naroditsky , University of Pennsylvania, Philadelphia, USA
pp. 975-982

3D reconstruction of a smooth articulated trajectory from a monocular image sequence (Abstract)

Yaser Sheikh , Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA, 15213, USA
Hyun Soo Park , Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA, 15213, USA
pp. 201-208

Multiview structure from motion in trajectory space (Abstract)

Mohammad Haris Baig , LUMS School of Science and Engineering, Lahore, Pakistan
Aamer Zaheer , LUMS School of Science and Engineering, Lahore, Pakistan
Ijaz Akhter , LUMS School of Science and Engineering, Lahore, Pakistan
Shabbir Marzban , LUMS School of Science and Engineering, Lahore, Pakistan
Sohaib Khan , LUMS School of Science and Engineering, Lahore, Pakistan
pp. 2447-2453

Exploiting the Manhattan-world assumption for extrinsic self-calibration of multi-modal sensor networks (Abstract)

Joachim Denzler , Computer Vision, Friedrich Schiller University of Jena, Ernst-Abbe-Platz 2, 07743, Germany
Marcel Bruckner , Computer Vision, Friedrich Schiller University of Jena, Ernst-Abbe-Platz 2, 07743, Germany
pp. 945-950

A geometric solver for calibrated stereo egomotion (Abstract)

Jan-Michael Frahm , University of North Carolina at Chapel Hill, USA
Enrique Dunn , University of North Carolina at Chapel Hill, USA
Brian Clipp , Applied Research Associates, USA
pp. 1187-1194

Semi-supervised learning and optimization for hypergraph matching (Abstract)

Cristian Sminchisescu , Institute of Mathematics of the Romanian Academy, Romania
Andrei Zanfir , Institute of Mathematics of the Romanian Academy, Romania
Marius Leordeanu , Institute of Mathematics of the Romanian Academy, Romania
pp. 2274-2281

An adaptive coupled-layer visual model for robust visual tracking (Abstract)

Luka Cehovin , Faculty of Computer and Information Science, University of Ljubljana, Trzaska 25, Slovenia
Matej Kristan , Faculty of Computer and Information Science, University of Ljubljana, Trzaska 25, Slovenia
Ales Leonardis , Faculty of Computer and Information Science, University of Ljubljana, Trzaska 25, Slovenia
pp. 1363-1370

Hough-based tracking of non-rigid objects (Abstract)

Horst Bischof , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Peter M. Roth , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Martin Godec , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
pp. 81-88

Linear time offline tracking and lower envelope algorithms (Abstract)

Steve Gu , Computer Science, Duke University, USA
Carlo Tomasi , Computer Science, Duke University, USA
Ying Zheng , Computer Science, Duke University, USA
pp. 1840-1846

N-best maximal decoders for part models (Abstract)

Deva Ramanan , UC Irvine, USA
Dennis Park , UC Irvine, USA
pp. 2627-2634

Fast articulated motion tracking using a sums of Gaussians body model (Abstract)

Christian Theobalt , MPI Informatik, Germany
Nils Hasler , MPI Informatik, Germany
Carsten Stoll , MPI Informatik, Germany
Hans-Peter Seidel , MPI Informatik, Germany
Juergen Gall , ETH Zurich, Switzerland
pp. 951-958

Robust unsupervised motion pattern inference from video and applications (Abstract)

Gerard Medioni , University of Southern California, Los Angeles, 90089, USA
Xuemei Zhao , University of Southern California, Los Angeles, 90089, USA
pp. 715-722

Smooth object retrieval using a bag of boundaries (Abstract)

Relja Arandjelovic , Department of Engineering Science, University of Oxford, UK
Andrew Zisserman , Department of Engineering Science, University of Oxford, UK
pp. 375-382

Fast image-based localization using direct 2D-to-3D matching (Abstract)

Bastian Leibe , RWTH Aachen University, Germany
Torsten Sattler , RWTH Aachen University, Germany
Leif Kobbelt , RWTH Aachen University, Germany
pp. 667-674

Large-scale image annotation using visual synset (Abstract)

Henry A. Rowley , Google Research, Mountain View, CA, USA
Yushi Jing , Google Research, Mountain View, CA, USA
Sergey Ioffe , Google Research, Mountain View, CA, USA
David Tsai , Computational Perception Lab, School of Interactive Computing, Georgia Institute of Technology, Atlanta, USA
James M. Rehg , Computational Perception Lab, School of Interactive Computing, Georgia Institute of Technology, Atlanta, USA
Yi Liu , Google Research, Mountain View, CA, USA
pp. 611-618

Edge foci interest points (Abstract)

Krishnan Ramnath , Microsoft Research, Redmond, WA, USA
C. Lawrence Zitnick , Microsoft Research, Redmond, WA, USA
pp. 359-366

Weakly supervised object detector learning with model drift detection (Abstract)

Tao Xiang , School of Electronic Engineering and Computer Science, Queen Mary University of London, E1 4NS, UK
Parthipan Siva , School of Electronic Engineering and Computer Science, Queen Mary University of London, E1 4NS, UK
pp. 343-350

End-to-end scene text recognition (Abstract)

Boris Babenko , Department of Computer Science and Engineering, University of California, San Diego, USA
Serge Belongie , Department of Computer Science and Engineering, University of California, San Diego, USA
Kai Wang , Department of Computer Science and Engineering, University of California, San Diego, USA
pp. 1457-1464

Regression from local features for viewpoint and pose estimation (Abstract)

Ahmed Elgammal , Department of Computer Science, Rutgers University, New Brunswick, NJ, USA
Marwan Torki , Department of Computer Science, Rutgers University, New Brunswick, NJ, USA
pp. 2603-2610

Recognizing jumbled images: The role of local and global information in image classification (Abstract)

Devi Parikh , Toyota Technological Institute, Chicago (TTIC), USA
pp. 519-526

Robust object pose estimation via statistical manifold modeling (Abstract)

Alfred Hero , Department of EECS, University of Michigan, Ann Arbor, USA
Silvio Savarese , Department of EECS, University of Michigan, Ann Arbor, USA
Liang Mei , Department of EECS, University of Michigan, Ann Arbor, USA
Jingen Liu , Department of EECS, University of Michigan, Ann Arbor, USA
pp. 967-974

Compact correlation coding for visual object categorization (Abstract)

Shin'ichi Satoh , National Institute of Informatics, Tokyo, Japan
Nobuyuki Morioka , The University of New South Wales & NICTA, Sydney, Australia
pp. 1639-1646

Discovering object instances from scenes of Daily Living (Abstract)

Martial Hebert , School of Computer Science, Carnegie Mellon University, USA
Hongwen Kang , School of Computer Science, Carnegie Mellon University, USA
Takeo Kanade , School of Computer Science, Carnegie Mellon University, USA
pp. 762-769

Density-aware person detection and tracking in crowds (Abstract)

Josef Sivic , INRIA, France
Ivan Laptev , INRIA, France
Jean-Yves Audibert , Imagine, LIGM, Universite Paris-Est, France
Mikel Rodriguez , École Normale Supérieure, France
pp. 2423-2430

Source camera identification using Auto-White Balance approximation (Abstract)

Zhonghai Deng , Univ.of Alabama, Tuscaloosa, USA
Jingyuan Zhang , Univ. of Alabama, Tuscaloosa, USA
Arjan Gijsenij , Univ. of Amsterdam, Netherlands
pp. 57-64

Tabula rasa: Model transfer for object category detection (Abstract)

Andrew Zisserman , Department of Engineering Science, University of Oxford, UK
Yusuf Aytar , Department of Engineering Science, University of Oxford, UK
pp. 2252-2259

Ask the locals: Multi-way local pooling for image recognition (Abstract)

Francis Bach , INRIA, France
Y-Lan Boureau , INRIA, France
Yann LeCun , Courant Institute, New York University, USA
Jean Ponce , Ecole Normale Supérieure, France
Nicolas Le Roux , INRIA, France
pp. 2651-2658

Superpixels via pseudo-Boolean optimization (Abstract)

Stewart Burn , CSIRO, Australia
John Mashford , CSIRO, Australia
Yuhang Zhang , The Australian National University, Australia
Richard Hartley , The Australian National University, Australia
pp. 1387-1394

Who Blocks Who: Simultaneous clothing segmentation for grouping images (Abstract)

Haizhou Ai , Computer Science and Technology Department, Tsinghua University, Beijing, China
Nan Wang , Computer Science and Technology Department, Tsinghua University, Beijing, China
pp. 1535-1542

Level-set person segmentation and tracking with multi-region appearance models and top-down shape information (Abstract)

Konstantinos Rematas , UMIC Research Centre, RWTH Aachen University, Germany
Esther Horbert , UMIC Research Centre, RWTH Aachen University, Germany
Bastian Leibe , UMIC Research Centre, RWTH Aachen University, Germany
pp. 1871-1878

Key-segments for video object segmentation (Abstract)

Kristen Grauman , University of Texas at Austin, USA
Jaechul Kim , University of Texas at Austin, USA
Yong Jae Lee , University of Texas at Austin, USA
pp. 1995-2002

Localized principal component analysis based curve evolution: A divide and conquer approach (Abstract)

Tracy Faber , Emory University, Atlanta, GA, USA
Balaji Ganapathy , Georgia Institute of Technology, Atlanta, USA
Vikram Appia , Georgia Institute of Technology, Atlanta, USA
Anthony Yezzi , Georgia Institute of Technology, Atlanta, USA
pp. 1981-1986

Automated corpus callosum extraction via Laplace-Beltrami nodal parcellation and intrinsic geodesic curvature flows on surfaces (Abstract)

Yonggang Shi , Department of Neurology, University of California, Los Angeles, USA
Rongjie Lai , Department of Mathematics, University of Southerm California, USA
Nancy Sicotte , Cedar Sinai Medical Center, Los Angeles, U. S. A.
Arthur W. Toga , Department of Neurology, University of California, Los Angeles, USA
pp. 2034-2040

Segmentation fusion for connectomics (Abstract)

Amelio Vazquez-Reina , School of Engineering and Applied Sciences, Harvard University, MA (USA)
Jeff Lichtman , Center for Brain Science, Harvard University, MA (USA)
Daniel Huang , School of Engineering and Applied Sciences, Harvard University, MA (USA)
Eric Miller , Department of Computer Science, Tufts University, MA (USA)
Hanspeter Pfister , School of Engineering and Applied Sciences, Harvard University, MA (USA)
Michael Gelbart , Graduate Program in Biophysics, Harvard University, MA (USA)
pp. 177-184

Single-shot high dynamic range imaging with conventional camera hardware (Abstract)

Keigo Hirakawa , Intelligent Signal Systems Laboratory, University of Dayton, 300 College Park, OH 45469, USA
Paul M. Simon , Intelligent Signal Systems Laboratory, University of Dayton, 300 College Park, OH 45469, USA
pp. 1339-1346

Imaging via three-dimensional compressive sampling (3DCS) (Abstract)

Xianbiao Shu , University of Illinois at Champaign-Urbana, 405 N. Mathews Avenue, 61801 USA
Narendra Ahuja , University of Illinois at Champaign-Urbana, 405 N. Mathews Avenue, 61801 USA
pp. 439-446

Locally rigid globally non-rigid surface registration (Abstract)

Jun Takamatsu , Graduate School of Information Science, Nara Institute of Science and Technology, Japan
Bo Zheng , Institute of Industrial Science, The University of Tokyo, Japan
Ko Nishino , Department of Computer Science, Drexel University, USA
Kent Fujiwara , Institute of Industrial Science, The University of Tokyo, Japan
Katsushi Ikeuchi , Institute of Industrial Science, The University of Tokyo, Japan
pp. 1527-1534

Multiscale, curvature-based shape representation for surfaces (Abstract)

Ruirui Jiang , Computer Science Department, Stony Brook University, USA
Xianfeng Gu , Computer Science Department, Stony Brook University, USA
pp. 1887-1894

Robust consistent correspondence between 3D non-rigid shapes based on "Dual Shape-DNA" (Abstract)

Hongbin Zha , Peking University, China
Huai-Yu Wu , Peking University & NLPR, CASIA, China
pp. 587-594

Discriminative high order SVD: Adaptive tensor subspace selection for image classification, clustering, and retrieval (Abstract)

Heng Huang , The University of Texas at Arlington, 701 S Nedderman Drive, USA
Dijun Luo , The University of Texas at Arlington, 701 S Nedderman Drive, USA
Chris Ding , The University of Texas at Arlington, 701 S Nedderman Drive, USA
pp. 1443-1448

Dynamic and hierarchical multi-structure geometric model fitting (Abstract)

Tat-Jun Chin , The Australian Centre for Visual Technologies, School of Computer Science, The University of Adelaide, South Australia
David Suter , The Australian Centre for Visual Technologies, School of Computer Science, The University of Adelaide, South Australia
Hoi Sim Wong , The Australian Centre for Visual Technologies, School of Computer Science, The University of Adelaide, South Australia
Jin Yu , The Australian Centre for Visual Technologies, School of Computer Science, The University of Adelaide, South Australia
pp. 1044-1051

Linear dependency modeling for feature fusion (Abstract)

Andy J H Ma , Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong
Pong C Yuen , Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong
pp. 2041-2048

Unsupervised metric learning by Self-Smoothing Operator (Abstract)

Zhuowen Tu , UCLA and Microsoft Research Asia, China
Bo Wang , University of Toronto, Canada
Jiayan Jiang , UCLA, USA
pp. 794-801

Slow feature analysis and decorrelation filtering for separating correlated sources (Abstract)

Ha Quang Minh , Istituto Italiano di Tecnologia (IIT), Via Morego 30, Genoa, 16163, Italy
Laurenz Wiskott , Ruhr-Universität Bochum, D-44780, Germany
pp. 866-873

Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation (Abstract)

Charless C. Fowlkes , Bren School of Information and Computer Sciences, University of California, Irvine, 92697, USA
Max Welling , Bren School of Information and Computer Sciences, University of California, Irvine, 92697, USA
Andrew Gelfand , Bren School of Information and Computer Sciences, University of California, Irvine, 92697, USA
Yutian Chen , Bren School of Information and Computer Sciences, University of California, Irvine, 92697, USA
pp. 2635-2642

Means in spaces of tree-like shapes (Abstract)

Mads Nielsen , Department of Computer Science, University of Copenhagen, Universitetsparken 1, DK-2100, Denmark
Soren Hauberg , Department of Computer Science, University of Copenhagen, Universitetsparken 1, DK-2100, Denmark
Francois Lauze , Department of Computer Science, University of Copenhagen, Universitetsparken 1, DK-2100, Denmark
Aasa Feragen , Department of Computer Science, University of Copenhagen, Universitetsparken 1, DK-2100, Denmark
pp. 736-746

Sorted Random Projections for robust texture classification (Abstract)

Paul Fieguth , System Design Engineering Dept., University of Waterloo, Ontario, Canada N2L 3G1
Li Liu , National University of Defense Technology, Changsha, Hunan, China 410043
Hongbin Zha , Machine Intelligence Dept., Peking University, Beijing, China 100871
Gangyao Kuang , National University of Defense Technology, Changsha, Hunan, China 410043
pp. 391-398

Object recoloring based on intrinsic image estimation (Abstract)

Joost van de Weijer , Centre de Visio per Computador, Computer Science Department, Universitat Autonoma de Barcelona, Edifci O, Campus UAB (Bellaterra), C.P.08193, Spain
Shida Beigpour , Centre de Visio per Computador, Computer Science Department, Universitat Autonoma de Barcelona, Edifci O, Campus UAB (Bellaterra), C.P.08193, Spain
pp. 327-334

Shading-based dynamic shape refinement from multi-view video under general illumination (Abstract)

Yebin Liu , MPI Informatik, Germany
Kiran Varanasi , MPI Informatik, Germany
Christian Theobalt , MPI Informatik, Germany
Chenglei Wu , MPI Informatik, Germany
Hans-Peter Seidel , MPI Informatik, Germany
pp. 1108-1115

A Direct Least-Squares (DLS) method for PnP (Abstract)

Joel A. Hesch , University of Minnesota, Minneapolis, 55455, USA
Stergios I. Roumeliotis , University of Minnesota, Minneapolis, 55455, USA
pp. 383-390

Speeded-up, relaxed spatial matching (Abstract)

Giorgos Tolias , National Technical University of Athens, Greece
Yannis Avrithis , National Technical University of Athens, Greece
pp. 1653-1660
108 ms
(Ver 3.3 (11022016))