The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (2010)
San Francisco, CA, USA
June 13, 2010 to June 18, 2010
ISBN: 978-1-4244-6984-0
TABLE OF CONTENTS
Papers

Table of contents (PDF)

pp. 1-40

Object-graphs for context-aware category discovery (Abstract)

Yong Jae Lee , University of Texas at Austin
Kristen Grauman , University of Texas at Austin
pp. 1-8

Grouplet: A structured image representation for recognizing human and object interactions (Abstract)

Bangpeng Yao , Computer Science Department, Stanford University, USA
Li Fei-Fei , Computer Science Department, Stanford University, USA
pp. 9-16

Modeling mutual context of object and human pose in human-object interaction activities (Abstract)

Li Fei-Fei , Computer Science Department, Stanford University, USA
Bangpeng Yao , Computer Science Department, Stanford University, USA
pp. 17-24

The chains model for detecting parts by their context (Abstract)

Michael Dinerstein , Weizmann Institute of Science, Rehovot 76100, Israel
Daniel Harari , Weizmann Institute of Science, Rehovot 76100, Israel
Leonid Karlinsky , Weizmann Institute of Science, Rehovot 76100, Israel
Shimon Ullman , Weizmann Institute of Science, Rehovot 76100, Israel
pp. 25-32

Detecting and sketching the common (Abstract)

Meirav Galun , Dept. of Computer Science and Applied Mathematics, The Weizmann Institute of Science, Rehovot 76100, Israel
Shai Bagon , Dept. of Computer Science and Applied Mathematics, The Weizmann Institute of Science, Rehovot 76100, Israel
Michal Irani , Dept. of Computer Science and Applied Mathematics, The Weizmann Institute of Science, Rehovot 76100, Israel
Ori Brostovski , Dept. of Computer Science and Applied Mathematics, The Weizmann Institute of Science, Rehovot 76100, Israel
pp. 33-40

High performance object detection by collaborative learning of Joint Ranking of Granules features (Abstract)

Ram Nevatia , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
Chang Huang , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
pp. 41-48

P-N learning: Bootstrapping binary classifiers by structural constraints (Abstract)

Jiri Matas , Czech Technical University, Prague, Czech Republic
Krystian Mikolajczyk , University of Surrey, Guildford, UK
Zdenek Kalal , University of Surrey, Guildford, UK
pp. 49-56

3D Scene priors for road detection (Abstract)

Antonio M. Lopez , Computer Vision Center and Computer Science Dpt. Univ. Autonoma de Barcelona
Theo Gevers , Faculty of Science, University of Amsterdam
Jose M. Alvarez , Computer Vision Center and Computer Science Dpt. Univ. Autonoma de Barcelona
pp. 57-64

Toward coherent object detection and scene layout understanding (Abstract)

Min Sun , Dept. of Electrical and Computer Engineering, University of Michigan at Ann Arbor, USA
Silvio Savarese , Dept. of Electrical and Computer Engineering, University of Michigan at Ann Arbor, USA
Sid Ying-Ze Bao , Dept. of Electrical and Computer Engineering, University of Michigan at Ann Arbor, USA
pp. 65-72

What is an object? (Abstract)

Bogdan Alexe , Computer Vision Laboratory, ETH Zurich
Thomas Deselaers , Computer Vision Laboratory, ETH Zurich
Vittorio Ferrari , Computer Vision Laboratory, ETH Zurich
pp. 73-80

Cascaded L1-norm Minimization Learning (CLML) classifier for human detection (Abstract)

Jianbin Jiao , Graduate University of Chinese Academy of Sciences, Beijing, China
Qixiang Ye , Graduate University of Chinese Academy of Sciences, Beijing, China
Baochang Zhang , School of Automation Science and Electrical Engineering, Beihang University, Beijing, China
Ran Xu , Graduate University of Chinese Academy of Sciences, Beijing, China
pp. 89-96

Convex shape decomposition (Abstract)

Longin Jan Latecki , Temple University, USA
Wenyu Liu , Huazhong University of Science and Technology, P.R. China
Hairong Liu , Huazhong University of Science and Technology, P.R. China
pp. 97-104

A theory of phase-sensitive rotation invariance with spherical harmonic and moment-based representations (Abstract)

Ramakrishna Kakarala , School of Computer Engineering, Nanyang Technological University
Dansheng Mao , School of Computer Engineering, Nanyang Technological University
pp. 105-112

Multi-class object localization by combining local contextual interactions (Abstract)

Brian McFee , Computer Science and Engineering Department, University of California, San Diego
Carolina Galleguillos , Computer Science and Engineering Department, University of California, San Diego
Gert Lanckriet , Electrical and Computer Engineering Department, University of California, San Diego
Serge Belongie , Computer Science and Engineering Department, University of California, San Diego
pp. 113-120

Automatic discovery of meaningful object parts with latent CRFs (Abstract)

Bernt Schiele , Department of Computer Science, TU Darmstadt
Paul Schnitzspan , Department of Computer Science, TU Darmstadt
Stefan Roth , Department of Computer Science, TU Darmstadt
pp. 121-128

Exploiting hierarchical context on a large database of object categories (Abstract)

Antonio Torralba , Massachusetts Institute of Technology
Joseph J. Lim , Massachusetts Institute of Technology
Myung Jin Choi , Massachusetts Institute of Technology
Alan S. Willsky , Massachusetts Institute of Technology
pp. 129-136

Learning appearance in virtual scenarios for pedestrian detection (Abstract)

Javier Marin , Computer Vision Center and Computer Science Dpt. UAB, 08193 Bellaterra, Barcelona, Spain
Antonio M. Lopez , Computer Vision Center and Computer Science Dpt. UAB, 08193 Bellaterra, Barcelona, Spain
David Geronimo , Computer Vision Center and Computer Science Dpt. UAB, 08193 Bellaterra, Barcelona, Spain
David Vazquez , Computer Vision Center and Computer Science Dpt. UAB, 08193 Bellaterra, Barcelona, Spain
pp. 137-144

Polynomial shape from shading (Abstract)

Ady Ecker , University of Toronto
Allan D. Jepson , University of Toronto
pp. 145-152

Analysis of light transport in scattering media (Abstract)

Ramesh Raskar , MIT Media Lab
Yasushi Yagi , Osaka University
Yasuhiro Mukaigawa , Osaka University
pp. 153-160

A new texture descriptor using multifractal analysis in multi-orientation wavelet pyramid (Abstract)

Xiong Yang , School of Computer Science & Engineering, South China Univ. of Tech., Guangzhou 510006, China
Hui Ji , Department of Mathematics, National University of Singapore, Singapore 117542
Yong Xu , School of Computer Science & Engineering, South China Univ. of Tech., Guangzhou 510006, China
Haibin Ling , Department of Computer and Information Sciences, Temple University, Philadelphia, PA 19122, U.S.A.
pp. 161-168

A content-aware image prior (Abstract)

Richard Szeliski , Microsoft Research
Sing Bing Kang , Microsoft Research
William T. Freeman , Massachusetts Institute of Technology
Taeg Sang Cho , Massachusetts Institute of Technology
Neel Joshi , Microsoft Research
C. Lawrence Zitnick , Microsoft Research
pp. 169-176

Learning from interpolated images using neural networks for digital forensics (Abstract)

Yizhen Huang , Computer Sciences Department, University of Wisconsin-Madison
Na Fan , Department of Electronic Engineering, East China Normal University
pp. 177-182

A probabilistic image jigsaw puzzle solver (Abstract)

Taeg Sang Cho , Massachusetts Institute of Technology
Shai Avidan , Tel-Aviv University, Adobe Systems Inc
William T. Freeman , Massachusetts Institute of Technology
pp. 183-190

Dynamic texture recognition based on distributions of spacetime oriented structure (Abstract)

Konstantinos G. Derpanis , Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada
Richard P. Wildes , Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada
pp. 191-198

Finding dots: Segmentation as popping out regions from boundaries (Abstract)

Elena Bernardis , University of Pennsylvania, Philadelphia, PA 19104
Stella X. Yu , Boston College, Chestnut Hill, MA 02467
pp. 199-206

Estimating optical properties of layered surfaces using the spider model (Abstract)

Katsushi Ikeuchi , Institute of Industrial Science, The University of Tokyo
Rei Kawakami , Institute of Industrial Science, The University of Tokyo
Robby T Tan , Department of Information and Computing Sciences, Utrecht University
Tetsuro Morimoto , Information Technology Research Laboratory, Toppan Printing Co., Ltd
pp. 207-214

Optimal HDR reconstruction with linear digital cameras (Abstract)

Hans-Peter Seidel , MPI Informatik
Hendrik P. A. Lensch , Ulm University
Boris Ajdin , Ulm University
Christian Theobalt , MPI Informatik
Michael Wand , MPI Informatik
Miguel Granados , MPI Informatik
pp. 215-222

Learning to recognize shadows in monochromatic natural images (Abstract)

Jiejie Zhu , University of Central Florida, School of Electrical Engineering and Computer Science, Orlando, FL
Kegan G. G. Samuel , University of Central Florida, School of Electrical Engineering and Computer Science, Orlando, FL
Marshall F. Tappen , University of Central Florida, School of Electrical Engineering and Computer Science, Orlando, FL
Syed Z. Masood , University of Central Florida, School of Electrical Engineering and Computer Science, Orlando, FL
pp. 223-230

Context-constrained hallucination for image super-resolution (Abstract)

Jian Sun , Xi'an Jiaotong University, Xi'an, P. R. China
Jiejie Zhu , EECS, University of Central Florida, Orlando, FL, USA
Marshall F. Tappen , EECS, University of Central Florida, Orlando, FL, USA
pp. 231-238

Exploring features in a Bayesian framework for material recognition (Abstract)

Lavanya Sharan , Disney Research Pittsburgh
Ce Liu , Microsoft Research New England
Ruth Rosenholtz , Massachusetts Institute of Technology
Edward H. Adelson , Massachusetts Institute of Technology
pp. 239-246

Image restoration and disparity estimation from an uncalibrated multi-layered image (Abstract)

Masao Shimizu , Nihon University
Masatoshi Okutomi , Tokyo Institute of Technology
Takahiro Yano , Olympus Corporation
pp. 247-254

Estimation of image bias field with sparsity constraints (Abstract)

Yuanjie Zheng , Penn Image Computing and Science Laboratory (PICSL), University of Pennsylvania School of Medicine, Philadelphia, PA, USA
James C. Gee , Penn Image Computing and Science Laboratory (PICSL), University of Pennsylvania School of Medicine, Philadelphia, PA, USA
pp. 255-262

Performance evaluation of color correction approaches for automatic multi-view image and video stitching (Abstract)

Wei Xu , University of Colorado at Boulder, Boulder, CO 80302-0430 USA
Jane Mulligan , University of Colorado at Boulder, Boulder, CO 80302-0430 USA
pp. 263-270

Surface color estimation based on inter- and intra-pixel relationships in outdoor scenes (Abstract)

Shun Hirose , Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma, Nara, Japan
Jun Takamatsu , Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma, Nara, Japan
Rei Kawakami , University of Tokyo, 4-6-1, Komaba, Meguro-ku, Tokyo, Japan
Kentaro Takemura , Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma, Nara, Japan
Tsuyoshi Suenaga , Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma, Nara, Japan
Tsukasa Ogasawara , Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma, Nara, Japan
pp. 271-278

Estimating demosaicing algorithms using image noise variance (Abstract)

Katsushi Ikeuchi , University of Tokyo, 4-6-1, Komaba, Meguro-ku, Tokyo, Japan
Jun Takamatsu , Nara Institute of Science and Technology, MSR-IJARC fellow 8916-5, Takayama-cho, Ikoma, Nara, Japan
Yasuyuki Matsushita , Microsoft Research Asia, 5F, Beijing Sigma Center, No. 49, Zhichun road, Haidian district, Beijing, China
Tsukasa Ogasawara , Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma, Nara, Japan
pp. 279-286

Object-to-object color transfer: Optimal flows and SMSP transformations (Abstract)

Daniel Freedman , Hewlett-Packard Laboratories, Haifa, Israel
Pavel Kisilev , Hewlett-Packard Laboratories, Haifa, Israel
pp. 287-294

The phase only transform for unsupervised surface defect detection (Abstract)

Dror Aiger , Université Paris-Est, Laboratoire d'Informatique Gaspard-Monge, Equipe A3SI, ESIEE Paris, 2 Boulevard Blaise-Pascal, 93162 Noisy-le-Grand Cedex France
Hugues Talbot , Université Paris-Est, Laboratoire d'Informatique Gaspard-Monge, Equipe A3SI, ESIEE Paris, 2 Boulevard Blaise-Pascal, 93162 Noisy-le-Grand Cedex France
pp. 295-302

Direct image alignment of projector-camera systems with planar surfaces (Abstract)

Masayuki Tanaka , Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo, Japan
Masatoshi Okutomi , Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo, Japan
Samuel Audet , Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo, Japan
pp. 303-310

Spatialized epitome and its applications (Abstract)

Shuicheng Yan , Department of ECE, National University of Singapore
Thomas S. Huang , ECE Department, University of Illinois at Urbana-Champaign
Liyuan Li , Institute for Infocomm Research
Xinqi Chu , Institute for Infocomm Research
Kap Luk Chan , Nanyang Technological University, Singapore
pp. 311-318

Global optimization for estimating a BRDF with multiple specular lobes (Abstract)

Yongduek Seo , Dept. of Media Technology, Sogang University, Seoul, Korea
Sang Wook Lee , Dept. of Media Technology, Sogang University, Seoul, Korea
Chanki Yu , Dept. of Media Technology, Sogang University, Seoul, Korea
pp. 319-326

Robust order-based methods for feature description (Abstract)

Raj Gupta , Department of Computer Science and Engg., Indian Institute of Technology Madras, Chennai India - 600036
Anurag Mittal , Department of Computer Science and Engg., Indian Institute of Technology Madras, Chennai India - 600036
Harshal Patil , Department of Computer Science and Engg., Indian Institute of Technology Madras, Chennai India - 600036
pp. 334-341

Rectilinear parsing of architecture in urban environment (Abstract)

Tian Fang , CSE/HKUST
Honghui Zhang , CSE/HKUST
Peng Zhao , CSE/HKUST
Qinping Zhao , VRLab/BUAA
Jianxiong Xiao , CSAIL/MIT
Long Quan , CSE/HKUST
pp. 342-349

Hybrid multi-view reconstruction by Jump-Diffusion (Abstract)

Florent Lafarge , Imagine group/LIGM, Université Paris Est
Mathieu Bredif , French Mapping Agency
Renaud Keriven , Imagine group/LIGM, Université Paris Est
Vu Hoang Hiep , Imagine group/LIGM, Université Paris Est
pp. 350-357

Building reconstruction using manhattan-world grammars (Abstract)

Carlos A. Vanegas , Purdue University
Bedrich Benes , Purdue University
Daniel G. Aliaga , Purdue University
pp. 358-365

Estimating camera pose from a single urban ground-view omnidirectional image and a 2D building outline map (Abstract)

Liang-Tien Chia , School of Computer Engineering, Nanyang Technological University; Singapore Surrey Space Centre, University of Surrey; Guildford, England
Tat-Jen Cham , School of Computer Engineering, Nanyang Technological University; Singapore Surrey Space Centre, University of Surrey; Guildford, England
Wei-Chian Tan , School of Computer Engineering, Nanyang Technological University; Singapore Surrey Space Centre, University of Surrey; Guildford, England
Minh-Tri Pham , School of Computer Engineering, Nanyang Technological University; Singapore Surrey Space Centre, University of Surrey; Guildford, England
Arridhana Ciptadi , School of Computer Engineering, Nanyang Technological University; Singapore Surrey Space Centre, University of Surrey; Guildford, England
pp. 366-373

Posture invariant surface description and feature extraction (Abstract)

Zouhour Ben Azouz , Institut Supérieur d'Informatique and Ecole Supérieur Privée d'Ingénieurs et de Technologies, Tunis
Stefanie Wuhrer , National Research Council of Canada, Ottawa, Canada
Chang Shu , National Research Council of Canada, Ottawa, Canada
pp. 374-381

Dense non-rigid surface registration using high-order graph matching (Abstract)

Yun Zeng , Stony Brook University
Chaohui Wang , Laboratoire MAS, Ecole Centrale Paris
Nikos Paragios , Laboratoire MAS, Ecole Centrale Paris, France, Equipe GALEN, INRIA Saclay - Ile-de-France
Xianfeng Gu , Computer Science Department, Stony Brook University
Yang Wang , Carnegie Mellon University
Dimitris Samaras , Computer Science Department, Stony Brook University
pp. 382-389

Line matching leveraged by point correspondences (Abstract)

Fuchao Wu , 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
Zhanyi Hu , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China
pp. 390-397

Detecting and parsing architecture at city scale from range data (Abstract)

Ben Taskar , GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA
Philippos Mordohai , Department of Computer Science, Stevens Institute of Technology, Hoboken, NJ, USA
Alexander Toshev , GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA
pp. 398-405

Dynamic and scalable large scale image reconstruction (Abstract)

Timo Pylvanainen , Nokia Research Center
Pascal Fua , CVLab EPFL
Christoph Strecha , CVLab EPFL
pp. 406-413

Learning 3D shape from a single facial image via non-linear manifold embedding and alignment (Abstract)

Xianwang Wang , Center for Visualization & Virtual Environments, University of Kentucky
Ruigang Yang , Center for Visualization & Virtual Environments, University of Kentucky
pp. 414-421

Adaptive pose priors for pictorial structures (Abstract)

Benjamin Sapp , University of Pennsylvania, Philadelphia, PA 19104, USA
Ben Taskar , University of Pennsylvania, Philadelphia, PA 19104, USA
Chris Jordan , University of Pennsylvania, Philadelphia, PA 19104, USA
pp. 422-429

A game-theoretic approach to fine surface registration without initial motion estimation (Abstract)

Emanuele Rodola , Dipartimento di Informatica - Università Ca' Foscari - via Torino, 155 - 30172 Venice Italy
Andrea Torsello , Dipartimento di Informatica - Università Ca' Foscari - via Torino, 155 - 30172 Venice Italy
Andrea Albarelli , Dipartimento di Informatica - Università Ca' Foscari - via Torino, 155 - 30172 Venice Italy
pp. 430-437

Global and local isometry-invariant descriptor for 3D shape comparison and partial matching (Abstract)

Tao Luo , Peking University, Key Laboratory of Machine Perception (MOE)
Xu-Lei Wang , Peking University, Key Laboratory of Machine Perception (MOE)
Huai-Yu Wu , Peking University, Key Laboratory of Machine Perception (MOE)
Hongbin Zha , Peking University, Key Laboratory of Machine Perception (MOE)
Songde Ma , NLPR, CASIA
pp. 438-445

Point-based non-rigid surface registration with accuracy estimation (Abstract)

Wataru Watanabe , Nagoya Institute of Technology, Gokiso, Showa-ku, Nagoya, Aichi, 466-8555 Japan
Hidekata Hontani , Nagoya Institute of Technology, Gokiso, Showa-ku, Nagoya, Aichi, 466-8555 Japan
pp. 446-452

3D Shape correspondence by isometry-driven greedy optimization (Abstract)

Yiicel Yemez , Koç University, Rumelifeneri Yolu, 34450, Sariyer, Istanbul, Turkey
Yusuf Sahillioglu , Koç University, Rumelifeneri Yolu, 34450, Sariyer, Istanbul, Turkey
pp. 453-458

On growth and formlets: Sparse multi-scale coding of planar shape (Abstract)

Timothy D. Oleskiw , York University
James H. Elder , York University
Gabriel Peyre , Université Paris-Dauphine
pp. 459-466

Growing semantically meaningful models for visual SLAM (Abstract)

David Murray , Active Vision Lab, Dept. Engineering Science, University of Oxford, Parks Road, Oxford, UK
Ian Reid , Active Vision Lab, Dept. Engineering Science, University of Oxford, Parks Road, Oxford, UK
Alex Flint , Active Vision Lab, Dept. Engineering Science, University of Oxford, Parks Road, Oxford, UK
Christopher Mei , Mobile Robotics Group, Dept. Engineering Science, University of Oxford, Parks Road, Oxford, UK
pp. 467-474

Diffeomorphic sulcal shape analysis for cortical surface registration (Abstract)

Roger P. Woods , Laboratory of Neuro Imaging, University of California, Los Angeles Los Angeles, California, 90095, USA
Ryan P. Cabeen , Laboratory of Neuro Imaging, University of California, Los Angeles Los Angeles, California, 90095, USA
Shantanu H. Joshi , Laboratory of Neuro Imaging, University of California, Los Angeles Los Angeles, California, 90095, USA
Anand A. Joshi , Laboratory of Neuro Imaging, University of California, Los Angeles Los Angeles, California, 90095, USA
Katherine L. Narr , Laboratory of Neuro Imaging, University of California, Los Angeles Los Angeles, California, 90095, USA
Arthur W. Toga , Laboratory of Neuro Imaging, University of California, Los Angeles Los Angeles, California, 90095, USA
pp. 475-482

A theory of plenoptic multiplexing (Abstract)

Wolfgang Heidrich , The University of British Columbia
Ivo Ihrke , The University of British Columbia
Gordon Wetzstein , The University of British Columbia
pp. 483-490

Non-uniform deblurring for shaken images (Abstract)

Jean Ponce , Ecole Normale Supe´rieure
Josef Sivic , INRIA
Oliver Whyte , INRIA
Andrew Zisserman , Dept. of Engineering Science, University of Oxford
pp. 491-498

Axial light field for curved mirrors: Reflect your perspective, widen your view (Abstract)

Amit Agrawal , Mitsubishi Electric Research Labs (MERL), Cambridge, MA, USA
Yuichi Taguchi , Mitsubishi Electric Research Labs (MERL), Cambridge, MA, USA
Ashok Veeraraghavan , Mitsubishi Electric Research Labs (MERL), Cambridge, MA, USA
Srikumar Ramalingam , Mitsubishi Electric Research Labs (MERL), Cambridge, MA, USA
pp. 499-506

Rectifying rolling shutter video from hand-held devices (Abstract)

Erik Ringaby , Department of Electrical Engineering, Linköping University, Sweden
Per-Erik Forssen , Department of Electrical Engineering, Linköping University, Sweden
pp. 507-514

Correcting over-exposure in photographs (Abstract)

Dong Guo , School of Computing, National University of Singapore, 117417
Shaojie Zhuo , School of Computing, National University of Singapore, 117417
Terence Sim , School of Computing, National University of Singapore, 117417
Yuan Cheng , School of Computing, National University of Singapore, 117417
pp. 515-521

Denoising vs. deblurring: HDR imaging techniques using moving cameras (Abstract)

Xin Chen , ACM
Alok Deshpande , University of Wisconsin, Madison
Li Zhang , University of Wisconsin, Madison
pp. 522-529

Gradient-directed composition of multi-exposure images (Abstract)

Wai-Kuen Cham , Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong
Wei Zhang , Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong
pp. 530-536

Warp propagation for video resizing (Abstract)

Michael Gleicher , Department of Computer Sciences University of Wisconsin-Madison Madison, WI, 53706, USA
Yuzhen Niu , School of Computer Science and Technology Shandong University Jinan, Shandong, 250101, China
Feng Liu , Department of Computer Sciences University of Wisconsin-Madison Madison, WI, 53706, USA
Xueqing Li , School of Computer Science and Technology Shandong University Jinan, Shandong, 250101, China
pp. 537-544

Sensor saturation in Fourier multiplexed imaging (Abstract)

Gordon Wetzstein , The University of British Columbia
Ivo Ihrke , The University of British Columbia
Wolfgang Heidrich , The University of British Columbia
pp. 545-552

Noise-optimal capture for high dynamic range photography (Abstract)

Fredo Durand , Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory
Samuel W. Hasinoff , Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory
William T. Freeman , Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory
pp. 553-560

Using optical defocus to denoise (Abstract)

Sing Bing Kang , Microsoft Research
Zenglu Qin , University of Washington
Qi Shan , University of Washington
Jiaya Jia , The Chinese University of Hong Kong
pp. 561-568

Discontinuous seam-carving for video retargeting (Abstract)

Irfan Essa , Georgia Institute of Technology, Atlanta, GA, USA
Vivek Kwatra , Google Research, Mountain View, CA, USA
Matthias Grundmann , Georgia Institute of Technology, Atlanta, GA, USA
Mei Han , Google Research, Mountain View, CA, USA
pp. 569-576

Hybrid shift map for video retargeting (Abstract)

Yiqun Hu , School of Computer Engineering, Nanyang Technological University, Singapore 639798
Deepu Rajan , School of Computer Engineering, Nanyang Technological University, Singapore 639798
pp. 577-584

Geo-location estimation from two shadow trajectories (Abstract)

Xiaochun Cao , School of Computer Science and Technology, Tianjin University, China
Lin Wu , School of Computer Science and Technology, Tianjin University, China
pp. 585-590

Estimating satellite attitude from pushbroom sensors (Abstract)

Peter Sturm , INRIA Grenoble, 655, avenue de l'Europe 38330 Montbonnot, France
Mathias Ortner , EADS Astrium, 655, avenue de l'Europe 38330 Montbonnot, France
Regis Perrier , INRIA Grenoble, 655, avenue de l'Europe 38330 Montbonnot, France
Elise Arnaud , Université Joseph Fourier, LJK, 655, avenue de l'Europe 38330 Montbonnot, France
pp. 591-598

Optimal coded sampling for temporal super-resolution (Abstract)

Ashok Veeraraghavan , Mitsubishi Electric Research Labs (MERL), Cambridge, MA 02139
Srinivasa G. Narasimhan , Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213
Amit Agrawal , Mitsubishi Electric Research Labs (MERL), Cambridge, MA 02139
Mohit Gupta , Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213
pp. 599-606

Efficient filter flow for space-variant multiframe blind deconvolution (Abstract)

Suvrit Sra , MPI for Biological Cybernetics, Spemannstrae 38, 72076 Tbingen, Germany
Bernhard Scholkopf , MPI for Biological Cybernetics, Spemannstrae 38, 72076 Tbingen, Germany
Stefan Harmeling , MPI for Biological Cybernetics, Spemannstrae 38, 72076 Tbingen, Germany
Michael Hirsch , MPI for Biological Cybernetics, Spemannstrae 38, 72076 Tbingen, Germany
pp. 607-614

Regenerative morphing (Abstract)

Alex Rav-Acha , Weizmann Institute of Science
Steve Seitz , University of Washington
Michal Irani , Weizmann Institute of Science
Eli Shechtman , Adobe Systems
pp. 615-622

Monocular 3D pose estimation and tracking by detection (Abstract)

Bernt Schiele , Department of Computer Science, TU Darmstadt
Mykhaylo Andriluka , Department of Computer Science, TU Darmstadt
Stefan Roth , Department of Computer Science, TU Darmstadt
pp. 623-630

Dynamical binary latent variable models for 3D human pose tracking (Abstract)

Geoffrey E. Hinton , University of Toronto, Toronto, Canada
David J. Fleet , University of Toronto, Toronto, Canada
Leonid Sigal , Disney Research Pittsburgh, USA
Graham W. Taylor , New York University, New York, USA
pp. 631-638

Contour people: A parameterized model of 2D articulated human shape (Abstract)

Michael J. Black , Department of Computer Science, Brown University, Providence, RI 02912, USA
Alexander Weiss , Department of Computer Science, Brown University, Providence, RI 02912, USA
Silvia Zuffi , Department of Computer Science, Brown University, Providence, RI 02912, USA
Oren Freifeld , Division of Applied Mathematics, Brown University, Providence, RI 02912, USA
pp. 639-646

Efficient extraction of human motion volumes by tracking (Abstract)

Li Fei-Fei , Computer Science Department, Stanford University, USA
Juan Carlos Niebles , Princeton University, USA, Universidad del Norte, Colombia
Bohyung Han , Electrical and Computer Engineering, UNIST, Korea
pp. 655-662

Multisensor-fusion for 3D full-body human motion capture (Abstract)

Hans-Peter Seidel , Saarland University & MPI Informatik, Germany
Gerard Pons-Moll , Leibniz Universität Hannover, Germany
Bodo Rosenhahn , Leibniz Universität Hannover, Germany
Meinard Muller , Saarland University & MPI Informatik, Germany
Thomas Helten , Saarland University & MPI Informatik, Germany
Andreas Baak , Saarland University & MPI Informatik, Germany
pp. 663-670

An object-dependent hand pose prior from sparse training data (Abstract)

Luc Van Gool , Computer Vision Laboratory ETH Zurich
Thibaut Weise , LGG EPF Lausanne
Henning Hamer , Computer Vision Laboratory ETH Zurich
Juergen Gall , Computer Vision Laboratory ETH Zurich
pp. 671-678

Vehicle detection and tracking in wide field-of-view aerial video (Abstract)

Feng Han , Sarnoff Corporation
Hui Cheng , Sarnoff Corporation
Jiangjian Xiao , Sarnoff Corporation
Harpreet Sawhney , Sarnoff Corporation
pp. 679-684

Multi-target tracking by on-line learned discriminative appearance models (Abstract)

Ramakant Nevatia , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
Cheng-Hao Kuo , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
Chang Huang , University of Southern California, Institute for Robotics and Intelligent Systems, Los Angeles, CA 90089, USA
pp. 685-692

Tracking with local spatio-temporal motion patterns in extremely crowded scenes (Abstract)

Louis Kratz , Department of Computer Science, Drexel University
Ko Nishino , Department of Computer Science, Drexel University
pp. 693-700

AAM based face tracking with temporal matching and face segmentation (Abstract)

Lin Liang , Microsoft Research Asia, Beijing, China
Yangsheng Wang , Institute of Automation, Chinese Academy of Sciences, Beijing, China
Jian Sun , Microsoft Research Asia, Beijing, China
Mingcai Zhou , Institute of Automation, Chinese Academy of Sciences, Beijing, China
pp. 701-708

Human identity recognition in aerial images (Abstract)

Omar Oreifej , Computer Vision Lab, University of Central Florida, Orlando, FL
Mubarak Shah , Computer Vision Lab, University of Central Florida, Orlando, FL
Ramin Mehran , Computer Vision Lab, University of Central Florida, Orlando, FL
pp. 709-716

Silhouette transformation based on walking speed for gait identification (Abstract)

Yasushi Makihara , Osaka University, 8-1 Mihogaoka, Ibaraki, Osaka, 567-0047, Japan
Akira Tsuji , Osaka University, 8-1 Mihogaoka, Ibaraki, Osaka, 567-0047, Japan
Yasushi Yagi , Osaka University, 8-1 Mihogaoka, Ibaraki, Osaka, 567-0047, Japan
pp. 717-722

PROST: Parallel robust online simple tracking (Abstract)

Amir Saffari , Institute for Computer Graphics and Vision, Graz University of Technology
Thomas Pock , Institute for Computer Graphics and Vision, Graz University of Technology
Christian Leistner , Institute for Computer Graphics and Vision, Graz University of Technology
Horst Bischof , Institute for Computer Graphics and Vision, Graz University of Technology
Jakob Santner , Institute for Computer Graphics and Vision, Graz University of Technology
pp. 723-730

Player localization using multiple static cameras for sports visualization (Abstract)

Matthias Grundmann , Georgia Institute of Technology, Atlanta GA 30332
Irfan Essa , Georgia Institute of Technology, Atlanta GA 30332
Jessica Hodgins , Disney Research, Pittsburgh PA 15213
Kihwan Kim , Georgia Institute of Technology, Atlanta GA 30332
Ram Krishan Kumar , Disney Research, Pittsburgh PA 15213
Raffay Hamid , Disney Research, Pittsburgh PA 15213
pp. 731-738

An online approach: Learning-Semantic-Scene-by-Tracking and Tracking-by-Learning-Semantic-Scene (Abstract)

Huijing Zhao , Key Laboratory of Machine Perception (MoE), Peking University, China
Ryosuke Shibasaki , Center for Spatial Information Science, University of Tokyo, Japan
Hongbin Zha , Key Laboratory of Machine Perception (MoE), Peking University, China
Xiaowei Shao , Center for Spatial Information Science, University of Tokyo, Japan
Jinshi Cui , Key Laboratory of Machine Perception (MoE), Peking University, China
Xuan Song , Key Laboratory of Machine Perception (MoE), Peking University, China
pp. 739-746

Tracking people interacting with objects (Abstract)

Hedvig Kjellstrom , CVAP/CAS, CSC, KTH, 114 22 Stockholm, Sweden
Michael J. Black , Dept. Computer Science, Brown University, Providence, RI 02912, USA
Danica Kragic , CVAP/CAS, CSC, KTH, 114 22 Stockholm, Sweden
pp. 747-754

Real time motion capture using a single time-of-flight camera (Abstract)

Varun Ganapathi , Stanford University, Computer Science Department, Stanford, CA, USA
Christian Plagemann , Stanford University, Computer Science Department, Stanford, CA, USA
Sebastian Thrun , Stanford University, Computer Science Department, Stanford, CA, USA
Daphne Koller , Stanford University, Computer Science Department, Stanford, CA, USA
pp. 755-762

RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images (Abstract)

John Wright , Visual Computing Group, Microsoft Research Asia
Yigang Peng , TNLIST and Dept. of Automation, Tsinghua University
Arvind Ganesh , Dept. of Electrical and Computer Engg., University of Illinois at Urbana-Champaign
Wenli Xu , TNLIST and Dept. of Automation, Tsinghua University
Yi Ma , Dept. of Electrical and Computer Engg., University of Illinois at Urbana-Champaign
pp. 763-770

Efficient computation of robust low-rank matrix approximations in the presence of missing data using the L<inf>1</inf> norm (Abstract)

Anders Eriksson , School of Computer Science, University of Adelaide, Australia
Anton van den Hengel , School of Computer Science, University of Adelaide, Australia
pp. 771-778

On the design of robust classifiers for computer vision (Abstract)

Hamed Masnadi-Shirazi , Department of Electrical and Computer Engineering, University of California, San Diego
Nuno Vasconcelos , Department of Electrical and Computer Engineering, University of California, San Diego
Vijay Mahadevan , Department of Electrical and Computer Engineering, University of California, San Diego
pp. 779-786

Online-batch strongly convex Multi Kernel Learning (Abstract)

Francesco Orabona , Università degli Studi di Milano
Luo Jie , Idiap Research Institute, EPF Lausanne
Barbara Caputo , Idiap Research Institute
pp. 787-794

Efficient joint 2D and 3D palmprint matching with alignment refinement (Abstract)

Guangming Lu , Biocomputing Research Center, Shenzhen Graduate School, Harbin Institute of Technology, Shen Zhen, China
David Zhang , Biometrics Research Center, Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong, China
Jingqi Yan , Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China
Lei Zhang , Biometrics Research Center, Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong, China
Wei Li , Biometrics Research Center, Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong, China
pp. 795-801

Harvesting large-scale weakly-tagged image databases from the web (Abstract)

Jianping Fan , Department of Computer Science, UNC-Charlotte, NC28223, USA
Yuli Gao , Multimedia Interaction and Understanding, HP Labs, Palo Alto, CA94304, USA
Ning Zhou , Department of Computer Science, UNC-Charlotte, NC28223, USA
Yi Shen , Department of Computer Science, UNC-Charlotte, NC28223, USA
pp. 802-809

Visual recognition using mappings that replicate margins (Abstract)

Lior Wolf , The Blavatnik School of Computer Science, Tel-Aviv University
Nathan Manor , The Blavatnik School of Computer Science, Tel-Aviv University
pp. 810-816

An eye for an eye: A single camera gaze-replacement method (Abstract)

Shai Avidan , Department of Electrical Engineering-Systems, Faculty of Engineering, Tel-Aviv University
Lior Wolf , The Blavatnik School of Computer Science, Tel-Aviv University
Ziv Freund , The Blavatnik School of Computer Science, Tel-Aviv University
pp. 817-824

Ink-bleed reduction using functional minimization (Abstract)

Zheng Wu , School of Computing, National University of Singapore
Michael S. Brown , School of Computing, National University of Singapore
Grani A. Hanasusanto , School of Computing, National University of Singapore
pp. 825-832

Action classification on product manifolds (Abstract)

Michael Kirby , Department of Mathematics, Colorado State University, Fort Collins, CO 80523, USA
Yui Man Lui , Department of Computer Science, Colorado State University, Fort Collins, CO 80523, USA
J. Ross Beveridge , Department of Computer Science, Colorado State University, Fort Collins, CO 80523, USA
pp. 833-839

Motion fields to predict play evolution in dynamic sport scenes (Abstract)

Iain Matthews , Disney Research, Pittsburgh, PA, USA
Jessica Hodgins , Disney Research, Pittsburgh, PA, USA
Irfan Essa , Georgia Institute of Technology, Atlanta, GA, USA
Kihwan Kim , Georgia Institute of Technology, Atlanta, GA, USA
Matthias Grundmann , Georgia Institute of Technology, Atlanta, GA, USA
Ariel Shamir , The Interdisciplinary Center, Herzliya, Israel
pp. 840-847

SPEC hashing: Similarity preserving algorithm for entropy-based coding (Abstract)

Jay Yagnik , Google Inc., Mountain View, CA 94043
David A. Ross , Google Inc., Mountain View, CA 94043
Ruei-Sung Lin , Google Inc., Mountain View, CA 94043
pp. 848-854

Shape-based similarity retrieval of Doppler images for clinical decision support (Abstract)

H. Greenspan , IBM Almaden Research Center, 650 Harry Road
T. Syeda-Mahmood , IBM Almaden Research Center, 650 Harry Road
A. Amir , IBM Almaden Research Center, 650 Harry Road
K. Pohl , IBM Almaden Research Center, 650 Harry Road
F. Wang , IBM Almaden Research Center, 650 Harry Road
P. Turaga , University of Maryland, College Park
D. Beymer , IBM Almaden Research Center, 650 Harry Road
pp. 855-862

Real-time vehicle global localisation with a single camera in dense urban areas: Exploitation of coarse 3D city models (Abstract)

Eric Royer , LASMEA-UMR 6602 Université Blaise Pascal/CNRS, 63177 Aubière Cedex, France
Pierre Lothe , CEA LIST, Vision and Content Engineering Lab, Point Courrier 94, Gif-sur-Yvette, 91191 France
Sylvie Naudet-Collette , CEA LIST, Vision and Content Engineering Lab, Point Courrier 94, Gif-sur-Yvette, 91191 France
Michel Dhome , LASMEA-UMR 6602 Université Blaise Pascal/CNRS, 63177 Aubière Cedex, France
Steve Bourgeois , CEA LIST, Vision and Content Engineering Lab, Point Courrier 94, Gif-sur-Yvette, 91191 France
pp. 863-870

Taxonomic classification for web-based videos (Abstract)

Jay Yagnik , Google Inc., Mountain View, CA 94043, USA
Xiaoyun Wu , Google Inc., Mountain View, CA 94043, USA
Yang Song , Google Inc., Mountain View, CA 94043, USA
Ming Zhao , Google Inc., Mountain View, CA 94043, USA
pp. 871-878

YouTubeCat: Learning to categorize wild web videos (Abstract)

Sanjiv Kumar , Google Research, New York, NY 10011, USA
Baoxin Li , Computer Science and Engineering, Arizona State University, Tempe, AZ 85281, USA
Zheshen Wang , Computer Science and Engineering, Arizona State University, Tempe, AZ 85281, USA
Yang Song , Google Research, Mountain View, CA 94043, USA
Ming Zhao , Google Research, Mountain View, CA 94043, USA
pp. 879-886

Covering trees and lower-bounds on quadratic assignment (Abstract)

Alexander Ihler , Dept. of Computer Science, University of California, Irvine, CA 92697
Julian Yarkony , Dept. of Computer Science, University of California, Irvine, CA 92697
Charless Fowlkes , Dept. of Computer Science, University of California, Irvine, CA 92697
pp. 887-894

Efficient piecewise learning for conditional random fields (Abstract)

Chris Russell , Oxford Brookes University, Oxford, UK
Philip H. S. Torr , Oxford Brookes University, Oxford, UK
Karteek Alahari , Oxford Brookes University, Oxford, UK
pp. 895-901

Multimodal semi-supervised learning for image classification (Abstract)

Jakob Verbeek , Laboratoire Jean Kuntzmann
Matthieu Guillaumin , LEAR, INRIA Grenoble
Cordelia Schmid , Laboratoire Jean Kuntzmann
pp. 902-909

What helps where – and why? Semantic relatedness for knowledge transfer (Abstract)

Gyorgy Szarvas , Department of Computer Science, TU Darmstadt
Bernt Schiele , Department of Computer Science, TU Darmstadt
Marcus Rohrbach , Department of Computer Science, TU Darmstadt
Michael Stark , Department of Computer Science, TU Darmstadt
Iryna Gurevych , Department of Computer Science, TU Darmstadt
pp. 910-917

Towards semantic embedding in visual vocabulary (Abstract)

Bineng Zhong , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Wen Gao , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Rongrong Ji , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Xiaoshuai Sun , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Hongxun Yao , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
pp. 918-925

Exploiting Monge structures in optimum subwindow search (Abstract)

Wanquan Liu , Dept. of Computing, Curtin University of Technology, GPO Box U1987, Perth, WA 6845, Australia
Xiaoming Chen , Dept. of Computing, Curtin University of Technology, GPO Box U1987, Perth, WA 6845, Australia
Svetha Venkatesh , Dept. of Computing, Curtin University of Technology, GPO Box U1987, Perth, WA 6845, Australia
Senjian An , Dept. of Computing, Curtin University of Technology, GPO Box U1987, Perth, WA 6845, Australia
Patrick Peursum , Dept. of Computing, Curtin University of Technology, GPO Box U1987, Perth, WA 6845, Australia
pp. 926-933

Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features (Abstract)

Gabriel Takacs , Information Systems Laboratory, Stanford University
Vijay Chandrasekhar , Information Systems Laboratory, Stanford University
Bernd Girod , Information Systems Laboratory, Stanford University
David Chen , Information Systems Laboratory, Stanford University
Radek Grzeszczuk , Nokia Research Center, Palo Alto, CA
Sam Tsai , Information Systems Laboratory, Stanford University
pp. 934-941

Fast polygonal integration and its application in extending haar-like features to improve object detection (Abstract)

Minh-Tri Pham , Surrey Space Centre, University of Surrey, England
Yang Gao , Surrey Space Centre, University of Surrey, England
Tat-Jen Cham , School of Computer Engineering, Nanyang Technological University, Singapore
Viet-Dung D. Hoang , School of Computer Engineering, Nanyang Technological University, Singapore
pp. 942-949

Object detection via boundary structure segmentation (Abstract)

Kostas Daniilidis , GRASP Laboratory, University of Pennsylvania, Philadelphia, PA 19104, USA
Ben Taskar , GRASP Laboratory, University of Pennsylvania, Philadelphia, PA 19104, USA
Alexander Toshev , GRASP Laboratory, University of Pennsylvania, Philadelphia, PA 19104, USA
pp. 950-957

Implicit hierarchical boosting for multi-view object detection (Abstract)

Xavier Perrotton , EADS FRANCE Innovation Works, Suresnes, France
Michel Roux , TELECOM ParisTech, LTCI UMR 5141 CNRS, Paris, France
Marc Sturzel , EADS FRANCE Innovation Works, Suresnes, France
pp. 958-965

Connecting modalities: Semi-supervised segmentation and annotation of images using unaligned text corpora (Abstract)

Richard Socher , Dept. of Computer Science, Stanford University
Li Fei-Fei , Dept. of Computer Science, Stanford University
pp. 966-973

Support vector regression for multi-view gait recognition based on local motion feature selection (Abstract)

Hongdong Li , Research School of Information Sciences and Engineering - Australian National University
Jian Zhang , School of Computer Science and Engineering - University of New South Wales
Qiang Wu , School of Computing and Communications - University of Technology Sydney
Worapan Kusakunniran , School of Computer Science and Engineering - University of New South Wales
pp. 974-981

Integrated pedestrian classification and orientation estimation (Abstract)

Dariu M. Gavrila , Environment Perception, Group Research, Daimler AG, Ulm, Germany
Markus Enzweiler , Image & Pattern Analysis Group, Univ. of Heidelberg, Germany
pp. 982-989

Multi-cue pedestrian classification with partial occlusion handling (Abstract)

Markus Enzweiler , Image & Pattern Analysis Group, Univ. of Heidelberg, Germany
Bernt Schiele , Computer Science Department, TU Darmstadt, Germany
Dariu M. Gavrila , Environment Perception, Group Research, Daimler AG, Ulm, Germany
Angela Eigenstetter , Computer Science Department, TU Darmstadt, Germany
pp. 990-997

Model globally, match locally: Efficient and robust 3D object recognition (Abstract)

Markus Ulrich , MVTec Software GmbH, Neherstraße 1, 81675 Munich, Germany
Bertram Drost , MVTec Software GmbH, Neherstraße 1, 81675 Munich, Germany
Nassir Navab , Department of Computer Science, Technical University of Munich (TUM), Boltzmannstraße 3, 85748 Garching, Germany
Slobodan Ilic , Department of Computer Science, Technical University of Munich (TUM), Boltzmannstraße 3, 85748 Garching, Germany
pp. 998-1005

Visual recognition and detection under bounded computational resources (Abstract)

Ashish Kapoor , University of Texas at Austin, Microsoft Research Redmond
Sudheendra Vijayanarasimhan , University of Texas at Austin, Microsoft Research Redmond
pp. 1006-1013

Talking pictures: Temporal grouping and dialog-supervised person recognition (Abstract)

Benjamin Sapp , University of Pennsylvania
Ben Taskar , University of Pennsylvania
Akash Nagle , University of Pennsylvania
Timothee Cour , INRIA - WILLOW Project
pp. 1014-1021

An efficient divide-and-conquer cascade for nonlinear object detection (Abstract)

Christoph H. Lampert , Max Planck Institute for Biological Cybernetics, Tübingen, Germany
pp. 1022-1029

New features and insights for pedestrian detection (Abstract)

Konrad Schindler , Computer Science Department, TU Darmstadt
Nikodem Majer , Computer Science Department, TU Darmstadt
Stefan Walk , Computer Science Department, TU Darmstadt
Bernt Schiele , Computer Science Department, TU Darmstadt
pp. 1030-1037

Efficient rotation invariant object detection using boosted Random Ferns (Abstract)

Michael Villamizar , Institut de Robòtica i Informàtica Industrial, CSIC-UPC, Llorens i Artigas 4-6, 08028. Barcelona, Spain
Alberto Sanfeliu , Institut de Robòtica i Informàtica Industrial, CSIC-UPC, Llorens i Artigas 4-6, 08028. Barcelona, Spain
Juan Andrade-Cetto , Institut de Robòtica i Informàtica Industrial, CSIC-UPC, Llorens i Artigas 4-6, 08028. Barcelona, Spain
Francesc Moreno-Noguer , Institut de Robòtica i Informàtica Industrial, CSIC-UPC, Llorens i Artigas 4-6, 08028. Barcelona, Spain
pp. 1038-1045

Fast and robust object segmentation with the Integral Linear Classifier (Abstract)

Ricardo Toledo , Computer Vision Center, Dept. Computer Science, Univ. Autònoma de Barcelona
David Aldavert , Computer Vision Center, Dept. Computer Science, Univ. Autònoma de Barcelona
Arnau Ramisa , INRIA-Grenoble, Artificial Intelligence Research Institute (IIIA-CSIC)
Ramon Lopez de Mantaras , Artificial Intelligence Research Institute (IIIA-CSIC), Campus UAB
pp. 1046-1053

Segmenting video into classes of algorithm-suitability (Abstract)

Oisin Mac Aodha , University College London
Marc Pollefeys , ETH Zurich
Gabriel J. Brostow , University College London
pp. 1054-1061

Latent hierarchical structural learning for object detection (Abstract)

Long Zhu , CSAIL, MIT, Cambridge, MA, USA
Yuanhao Chen , Dept. of Stat., UCLA, Los Angeles, CA, USA
A Yuille , Dept. of Stat., UCLA, Los Angeles, CA, USA
W Freeman , CSAIL, MIT, Cambridge, MA, USA
pp. 1062-1069
Papers

Cascaded pose regression (Abstract)

Peter Welinder , California Institute of Technology
Pietro Perona , California Institute of Technology
Piotr Dollar , California Institute of Technology
pp. 1078-1085

Free-shape subwindow search for object localization (Abstract)

Dhaval Salvi , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
Kenton Oliver , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
Jarrell Waggoner , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
Zhiqi Zhang , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
Yu Cao , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
Song Wang , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
pp. 1086-1093

Improving web image search results using query-relative classifiers (Abstract)

Frederic Juried , GREYC, Université de Caen, France
Moray Allan , GREYC, Université de Caen, France
Jakob Verbeek , LEAR team, INRIA Rhône-Alpes, France
Josip Krapac , LEAR team, INRIA Rhône-Alpes, France
pp. 1094-1101

Using cloud shadows to infer scene structure and camera calibration (Abstract)

Robert Pless , Computer Science and Engineering, Washington University in St. Louis, MO, USA
Brian Bies , Computer Science and Engineering, Washington University in St. Louis, MO, USA
Nathan Jacobs , Computer Science and Engineering, Washington University in St. Louis, MO, USA
pp. 1102-1109

Depth from Diffusion (Abstract)

Changyin Zhou , Columbia University
Shree Nayar , Columbia University
Oliver Cossairt , Columbia University
pp. 1110-1117

Self-calibrating photometric stereo (Abstract)

Boxin Shi , Key Lab of Machine Perception (MOE), Peking University
Chao Xu , Key Lab of Machine Perception (MOE), Peking University
Yichen Wei , Microsoft Research Asia
Ping Tan , Department of Electrical & Computer Engineering, National University of Singapore
Yasuyuki Matsushita , Microsoft Research Asia
pp. 1118-1125

Geometric properties of multiple reflections in catadioptric camera with two planar mirrors (Abstract)

Ren Ren , The Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, P.R. China
Hongbin Zha , The Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, P.R. China
Xianghua Ying , The Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, P.R. China
Kun Peng , The Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, P.R. China
pp. 1126-1132

Upsampling range data in dynamic environments (Abstract)

Jongmin Baek , Dept. of Computer Science, Stanford University
Jennifer Dolson , Dept. of Computer Science, Stanford University
Christian Plagemann , Dept. of Computer Science, Stanford University
Sebastian Thrun , Dept. of Computer Science, Stanford University
pp. 1141-1148

Object cut: Complex 3D object reconstruction through line drawing separation (Abstract)

Jianzhuang Liu , Department of Information Engineering, The Chinese University of Hong Kong
Tianfan Xue , Department of Information Engineering, The Chinese University of Hong Kong
Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong
pp. 1149-1156

Consensus photometric stereo (Abstract)

Katsushi Ikeuchi , The University of Tokyo, Tokyo, Japan
Yasuyuki Matsushita , Microsoft Research Asia, Beijing, China
Tomoaki Higo , The University of Tokyo, Tokyo, Japan
pp. 1157-1164

Model evolution: An incremental approach to non-rigid structure from motion (Abstract)

Li Zhang , University of Wisconsin - Madison
Brandon M. Smith , University of Wisconsin - Madison
Shengqi Zhu , University of Wisconsin - Madison
pp. 1165-1172

3D shape scanning with a time-of-flight camera (Abstract)

Christian Theobalt , MPI Informatik
Derek Chan , Stanford University
Sebastian Schuon , Stanford University
Sebastian Thrun , Stanford University
Yan Cui , MPI Informatik
pp. 1173-1180

Refinement of digital elevation models from shadowing cues (Abstract)

William A. P. Smith , Department of Computer Science, University of York, UK
James Hogan , Department of Computer Science, University of York, UK
pp. 1181-1188

Simultaneous pose, correspondence and non-rigid shape (Abstract)

Francesc Moreno-Noguer , Institut de Robòtica i, Informàtica Industrial (CSIC-UPC), Barcelona, Spain
Jordi Sanchez-Riera , Perception Team, INRIA, Grenoble, France
Jonas Ostlund , EPFL - CVLab, Lausanne, Switzerland
Pascal Fua , EPFL - CVLab, Lausanne, Switzerland
pp. 1189-1196

A framework for ultra high resolution 3D imaging (Abstract)

Yu-Wing Tai , Korean Advanced Institute of Science and Technology
Michael S. Brown , National University of Singapore
Moshe Ben-Ezra , Microsoft Research Asia
Zheng Lu , National University of Singapore
pp. 1205-1212

3D reconstruction of glossy surfaces using stereo cameras and projector-display (Abstract)

Gang Xu , Faculty of Information Science and Engineering, Ritsumeikan University, Japan
Masaki Yamazaki , Faculty of Information Science and Engineering, Ritsumeikan University, Japan
pp. 1213-1220

Simultaneous point matching and 3D deformable surface reconstruction (Abstract)

Appu Shaji , Computer Vision Laboratory, EPFL, Lausanne, Switzerland
Lorenzo Torresani , Dartmouth College, Hanover, NH, U.S.A.
Pascal Fua , Computer Vision Laboratory, EPFL, Lausanne, Switzerland
Aydin Varol , Computer Vision Laboratory, EPFL, Lausanne, Switzerland
pp. 1221-1228

Shape and refractive index recovery from single-view polarisation images (Abstract)

Antonio Robles-Kelly , School of Engineering, Australian National University, Canberra ACT 0200, Australia
Edwin Hancock , Department of Computer Science, University of York, Heslington, York, YO10 5DD, UK
Cong Phuoc Huynh , School of Engineering, Australian National University, Canberra ACT 0200, Australia
pp. 1229-1236

High-resolution modeling of moving and deforming objects using sparse geometric and dense photometric measurements (Abstract)

Daniel G. Aliaga , Department of Computer Science, Purdue University
Yi Xu , Department of Computer Science, Purdue University
pp. 1237-1244

Specular surface reconstruction from sparse reflection correspondences (Abstract)

Oncel Tuzel , Mitsubishi Electric Research Labs, Cambridge, MA
Aswin C. Sankaranarayanan , Rice University, Houston, TX
Ashok Veeraraghavan , Mitsubishi Electric Research Labs, Cambridge, MA
Amit Agrawal , Mitsubishi Electric Research Labs, Cambridge, MA
pp. 1245-1252

Single image depth estimation from predicted semantic labels (Abstract)

Daphne Koller , Dept. of Computer Science, Stanford University
Stephen Gould , Dept. of Electrical Engineering, Stanford University
Beyang Liu , Dept. of Computer Science, Stanford University
pp. 1253-1260

Robust piecewise-planar 3D reconstruction and completion from large-scale unstructured point data (Abstract)

Anne-Laure Chauve , IMAGINE, ENPC/CSTB/LIGM, Université Paris-Est, France
Jean-Philippe Pons , IMAGINE, ENPC/CSTB/LIGM, Université Paris-Est, France
Patrick Labatut , IMAGINE, ENPC/CSTB/LIGM, Université Paris-Est, France
pp. 1261-1268

Visual tracking decomposition (Abstract)

Junseok Kwon , Department of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
Kyoung Mu Lee , Department of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
pp. 1269-1276

A globally optimal data-driven approach for image distortion estimation (Abstract)

Yuandong Tian , The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA
Srinivasa G. Narasimhan , The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA
pp. 1277-1284

Tracking the invisible: Learning where the object might be (Abstract)

Philippe Cattin , Medical Image Analysis Center, University of Basel
Luc Van Gool , Computer Vision Laboratory, ETH Zurich
Jiri Matas , Center for Machine Perception, Czech Technical University, Prague
Helmut Grabner , Computer Vision Laboratory, ETH Zurich
pp. 1285-1292

Motion detail preserving optical flow estimation (Abstract)

Jiaya Jia , The Chinese University of Hong Kong
Li Xu , The Chinese University of Hong Kong
Yasuyuki Matsushita , Microsoft Research Asia
pp. 1293-1300

Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes (Abstract)

Shengcai Liao , Center for Biometrics and Security Research & National Laboratory of Pattern, Recognition, Institute of Automation, Chinese Academy of Sciences
Stan Z. Li , Center for Biometrics and Security Research & National Laboratory of Pattern, Recognition, Institute of Automation, Chinese Academy of Sciences
Matti Pietikainen , Machine Vision Group, University of Oulu, Finland
Guoying Zhao , Machine Vision Group, University of Oulu, Finland
Vili Kellokumpu , Machine Vision Group, University of Oulu, Finland
pp. 1301-1306

Real-time tracking of multiple occluding objects using level sets (Abstract)

Ian Reid , Department of Engineering Science, University of Oxford
Charles Bibby , Department of Engineering Science, University of Oxford
pp. 1307-1314

Visual tracking via incremental self-tuning particle filtering on the affine group (Abstract)

Wei Chen , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Tieniu Tan , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Min Li , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Kaiqi Huang , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
pp. 1315-1322

Visual tracking via weakly supervised learning from multiple imperfect oracles (Abstract)

Shaohui Liu , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Xiaotong Yuan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Wen Gao , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Sheng Chen , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Bineng Zhong , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Rongrong Ji , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
Hongxun Yao , Harbin Institute of Technology, Heilongjiang Province, 150001, P. R. China
pp. 1323-1330

Warping background subtraction (Abstract)

Teresa Ko , University of California, Los Angeles, CA 90095
Deborah Estrin , University of California, Los Angeles, CA 90095
Stefano Soatto , University of California, Los Angeles, CA 90095
pp. 1331-1338

Free-form mesh tracking: A patch-based approach (Abstract)

Slobodan Ilic , Department of Computer Science, Technical University of Munich
Edmond Boyer , INRIA Alpes, Grenoble
Cedric Cagniart , Department of Computer Science, Technical University of Munich
pp. 1339-1346

Trajectory matching from unsynchronized videos (Abstract)

Jie Zhou , State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology (TNList), Department of Automation, Tsinghua Univers
Han Hu , State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology (TNList), Department of Automation, Tsinghua Univers
pp. 1347-1354

Rapid selection of reliable templates for visual tracking (Abstract)

Nicolas Alt , Institute for Media Technology
Nassir Navab , Chair for Computer Aided Medical Procedures, Technische Universität München, 80290 München, Germany
Stefan Hinterstoisser , Chair for Computer Aided Medical Procedures, Technische Universität München, 80290 München, Germany
pp. 1355-1362

Generalized simultaneous registration and segmentation (Abstract)

Emre Sargin , Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA 93106-9560
B. S. Manjunath , Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA 93106-9560
Pratim Ghosh , Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA 93106-9560
pp. 1363-1370

A probabilistic framework for joint segmentation and tracking (Abstract)

Johnny Park , Purdue University
Avinash C. Kak , Purdue University
Chad Aeschliman , Purdue University
pp. 1371-1378

Probabilistic 3D occupancy flow with latent silhouette cues (Abstract)

Edmond Boyer , INRIA Rhône-Alpes, France
Jean-Sebastien Franco , LaBRI - INRIA Sud-Ouest, University of Bordeaux, France
Marc Pollefeys , ETH-Zürich, Switzerland UNC-Chapel Hill, U.S.A.
Li Guan , UNC-Chapel Hill, U.S.A.
pp. 1379-1386

Novel observation model for probabilistic object tracking (Abstract)

Qingming Huang , Graduate University of Chinese Academy of Sciences, Beijing, China
Hongxun Yao , School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
Dawei Liang , School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
Wen Gao , National Engineering Laboratory for Video Technology, Peking University, Beijing, China
Shuqiang Jiang , Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
Rongrong Ji , School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
pp. 1387-1394

Online multiple instance learning with no regret (Abstract)

Bao-Liang Lu , Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Mu Li , Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
James T. Kwok , Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong
pp. 1395-1401

Dynamic surface matching by geodesic mapping for 3D animation transfer (Abstract)

Tony Tung , Graduate School of Informatics, Kyoto University, Japan
Takashi Matsuyama , Graduate School of Informatics, Kyoto University, Japan
pp. 1402-1409

Probabilistic temporal inference on reconstructed 3D scenes (Abstract)

Grant Schindler , Georgia Institute of Technology
Frank Dellaert , Georgia Institute of Technology
pp. 1410-1417

Piecewise planar and non-planar stereo for urban scene reconstruction (Abstract)

Jan-Michael Frahm , Department of Computer Science, The University of North Carolina, Chapel Hill, NC, USA
Marc Pollefeys , Department of Computer Science, ETH Zürich, Zürich, Switzerland
David Gallup , Department of Computer Science, The University of North Carolina, Chapel Hill, NC, USA
pp. 1418-1425

Disambiguating visual relations using loop constraints (Abstract)

Manfred Klopschitz , TU Graz, Austria
Christopher Zach , ETH Zürich, Switzerland
Marc Pollefeys , ETH Zürich, Switzerland
pp. 1426-1433

Towards Internet-scale multi-view stereo (Abstract)

Brian Curless , University of Washington
Steven M. Seitz , Google Inc.
Richard Szeliski , Microsoft Research
Yasutaka Furukawa , Google Inc.
pp. 1434-1441

Reconstruction of display and eyes from a single image (Abstract)

Kwan-Yee K. Wong , Department of Computer Science, University of Hong Kong
Dirk Schnieders , Department of Computer Science, University of Hong Kong
Xingdou Fu , Department of Computer Science, University of Hong Kong
pp. 1442-1449

Outlier removal using duality (Abstract)

Anders Eriksson , School of Computer Science, University of Adelaide, Australia
Carl Olsson , Centre for Mathematical Sciences, Lund University, Sweden
Richard Hartley , Australian National University and NICTA, Australia
pp. 1450-1457

A constant-space belief propagation algorithm for stereo matching (Abstract)

Liang Wang , University of Kentucky
Narendra Ahuja , University of Illinois at Urbana Champaign
Qingxiong Yang , University of Illinois at Urbana Champaign
pp. 1458-1465

Evaluation of stereo confidence indoors and outdoors (Abstract)

Philippos Mordohai , Stevens Institute of Technology, Hoboken, New Jersey, USA
Xiaoyan Hu , Stevens Institute of Technology, Hoboken, New Jersey, USA
pp. 1466-1473

Pushing the envelope of modern methods for bundle adjustment (Abstract)

Yekeun Jeong , Robotics and Computer Vision Lab. KAIST
David Nister , Microsoft Research
Richard Szeliski , Microsoft Research
In-So Kweon , Robotics and Computer Vision Lab. KAIST
Drew Steedly , Microsoft Research
pp. 1474-1481

Quasi-dense 3D reconstruction using tensor-based multiview stereo (Abstract)

Tai-Pang Wu , The Hong Kong University of Science and Technology
Chi-Keung Tang , The Hong Kong University of Science and Technology
Jiaya Jia , The Chinese University of Hong Kong
Sai-Kit Yeung , The Hong Kong University of Science and Technology
pp. 1482-1489

Accurate 3D face reconstruction from weakly calibrated wide baseline images with profile contours (Abstract)

Gerard Medioni , Computer Science Department, University of Southern California, 3737 Watt Way, PHE 101, Los Angeles, CA, 90089
Yuping Lin , Computer Science Department, University of Southern California, 3737 Watt Way, PHE 101, Los Angeles, CA, 90089
Jongmoo Choi , Computer Science Department, University of Southern California, 3737 Watt Way, PHE 101, Los Angeles, CA, 90089
pp. 1490-1497

Live dense reconstruction with a single moving camera (Abstract)

Richard A. Newcombe , Department of Computing, Imperial College London, London, UK
Andrew J. Davison , Department of Computing, Imperial College London, London, UK
pp. 1498-1505

Multi-view scene flow estimation: A view centered variational approach (Abstract)

Tali Basha , Tel Aviv University, Tel Aviv 69978, Israel
Nahum Kiryati , Tel Aviv University, Tel Aviv 69978, Israel
Yael Moses , The Interdisciplinary Center, Herzliya 46150, Israel
pp. 1506-1513

Egomotion using assorted features (Abstract)

Vivek Pradeep , University of Southern California, Los Angeles, California, USA
Jongwoo Lim , Honda Research Institute, Mountain View, California, USA
pp. 1514-1521

Monocular SLAM with locally planar landmarks via geometric rao-blackwellized particle filtering on Lie groups (Abstract)

Junghyun Kwon , Department of EECS, ASRI, Seoul National University, Seoul 151-742, Korea
Kyoung Mu Lee , Department of EECS, ASRI, Seoul National University, Seoul 151-742, Korea
pp. 1522-1529

Ray Markov Random Fields for image-based 3D modeling: Model and efficient inference (Abstract)

David B. Cooper , Laboratory for Engineering Man/Machine Systems (LEMS), Division of Engineering, Brown University, Providence, RI 02912
Shubao Liu , Laboratory for Engineering Man/Machine Systems (LEMS), Division of Engineering, Brown University, Providence, RI 02912
pp. 1530-1537

3D curve sketch: Flexible curve-based stereo reconstruction and calibration (Abstract)

Ricardo Fabbri , Brown University, Division of Engineering
Benjamin Kimia , Brown University, Division of Engineering
pp. 1538-1545

Scalable active matching (Abstract)

Andrew J. Davison , Department of Computing, Imperial College London, UK
Ankur Handa , Department of Computing, Imperial College London, UK
Margarita Chli , Department of Computing, Imperial College London, UK
Hauke Strasdat , Department of Computing, Imperial College London, UK
pp. 1546-1553

Triangulation made easy (Abstract)

Peter Lindstrom , Lawrence Livermore National Laboratory
pp. 1554-1561

Simultaneous surveillance camera calibration and foot-head homology estimation from human detections (Abstract)

Branislav Micusik , Safety and Security Department, AIT Austrian Institute of Technology
Tomas Pajdla , Center for Machine Perception, Czech Technical University in Prague
pp. 1562-1569

Surface stereo with soft segmentation (Abstract)

Carsten Rother , Microsoft Research Cambridge, Cambridge, UK
Pushmeet Kohli , Microsoft Research Cambridge, Cambridge, UK
Michael Bleyer , Vienna University of Technology, Vienna, Austria
pp. 1570-1577

Admissible linear map models of linear cameras (Abstract)

Jean Ponce , École Normale Supérieure
Xavier Goaoc , INRIA Nancy Grand Est
Guillaume Batog , Université de Nancy 2
pp. 1578-1585

Exploiting global connectivity constraints for reconstruction of 3D line segments from images (Abstract)

Hans-Peter Seidel , Max-Planck-Institut Informatik, Saarbrücken, Germany
Christian Kurz , Max-Planck-Institut Informatik, Saarbrücken, Germany
Arjun Jain , Max-Planck-Institut Informatik, Saarbrücken, Germany
Thorsten Thormahlen , Max-Planck-Institut Informatik, Saarbrücken, Germany
pp. 1586-1593

Improving the efficiency of hierarchical structure-and-motion (Abstract)

Riccardo Gherardi , Dipartimento di Informática, Università di Verona, Strada Le Grazie 15, 37134 Verona (Italy)
Andrea Fusiello , Dipartimento di Informática, Università di Verona, Strada Le Grazie 15, 37134 Verona (Italy)
Michela Farenzena , Dipartimento di Informática, Università di Verona, Strada Le Grazie 15, 37134 Verona (Italy)
pp. 1594-1600

Multiview constraints in frequency space and camera calibration from unsynchronized images (Abstract)

Jun Sato , Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya 466-8555, Japan
Fumihiko Sakaue , Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya 466-8555, Japan
Hiroki Matsumoto , Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya 466-8555, Japan
pp. 1601-1608

Common visual pattern discovery via spatially coherent correspondences (Abstract)

Shuicheng Yan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Hairong Liu , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
pp. 1609-1616

Unsupervised detection and segmentation of identical objects (Abstract)

Young Min Shin , Department of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
Minsu Cho , Department of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
Kyoung Mu Lee , Department of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
pp. 1617-1624

A novel riemannian framework for shape analysis of 3D objects (Abstract)

Anuj Srivastava , Department of Statistics, Florida State University, Tallahassee, FL
Sebastian Kurtek , Department of Statistics, Florida State University, Tallahassee, FL
Eric Klassen , Department of Mathematics, Florida State University, Tallahassee, FL
Zhaohua Ding , Institute of Imaging Science, Vanderbilt University, Nashville, TN
pp. 1625-1632

Global and efficient self-similarity for object classification and detection (Abstract)

Vittorio Ferrari , Computer Vision Laboratory, ETH Zurich, Zurich, Switzerland
Thomas Deselaers , Computer Vision Laboratory, ETH Zurich, Zurich, Switzerland
pp. 1633-1640

Object matching with a locally affine-invariant constraint (Abstract)

Hongsheng Li , Department of Computer Science and Engineering, Lehigh University, PA 18015
Edward Kim , Department of Computer Science and Engineering, Lehigh University, PA 18015
Xiaolei Huang , Department of Computer Science and Engineering, Lehigh University, PA 18015
Lei He , National Library of Medicine, NIH, Bethesda, MD 20894
pp. 1641-1648

Unsupervised learning of invariant features using video (Abstract)

David Stavens , Stanford Artificial Intelligence Laboratory, Computer Science Department, Stanford, CA 94305-9010
Sebastian Thrun , Stanford Artificial Intelligence Laboratory, Computer Science Department, Stanford, CA 94305-9010
pp. 1649-1656

Scale-hierarchical 3D object recognition in cluttered scenes (Abstract)

Ko Nishino , Department of Computer Science, Drexel University
Prabin Bariya , Department of Computer Science, Drexel University
pp. 1657-1664

Linked edges as stable region boundaries (Abstract)

Horst Bischof , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Hayko Riemenschneider , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Michael Donoser , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
pp. 1665-1672

Many-to-one contour matching for describing and discriminating object shape (Abstract)

Praveen Srinivasan , GRASP Laboratory, University of Pennsylvania, 3330 Walnut St., Philadelphia, PA - 19104
Jianbo Shi , GRASP Laboratory, University of Pennsylvania, 3330 Walnut St., Philadelphia, PA - 19104
Qihui Zhu , GRASP Laboratory, University of Pennsylvania, 3330 Walnut St., Philadelphia, PA - 19104
pp. 1673-1680

3D model based vehicle classification in aerial imagery (Abstract)

Hui Cheng , Sarnoff Corporation 201 Washington Road, Princeton, NJ 08543, USA
Harpreet Sawhney , Sarnoff Corporation 201 Washington Road, Princeton, NJ 08543, USA
Saad M. Khan , Sarnoff Corporation 201 Washington Road, Princeton, NJ 08543, USA
Dennis Matthies , Sarnoff Corporation 201 Washington Road, Princeton, NJ 08543, USA
pp. 1681-1687

Multi-view object class detection with a 3D geometric model (Abstract)

Joerg Liebelt , IW-SI, EADS Innovation Works, D-81663 Munich, Germany
Cordelia Schmid , LEAR, INRIA Grenoble, F-38330 Montbonnot, France
pp. 1688-1695

Fast directional chamfer matching (Abstract)

Ashok Veeraraghavan , Mitsubishi Electric Research Labs
Rama Chellappa , University of Maryland College Park
Oncel Tuzel , Mitsubishi Electric Research Labs
Ming-Yu Liu , University of Maryland College Park
pp. 1696-1703

Scale-invariant heat kernel signatures for non-rigid shape recognition (Abstract)

Iasonas Kokkinos , Laboratoire de Mathématiques Appliquées aux Systèmes, École Centrale de Paris, France, Equipe GALEN, INRIA Saclay - ÃŽle-de-France, Orsay, France
Michael M. Bronstein , Department of Computer Science, Technion - Israel Institute of Technology, Haifa 32000, Israel
pp. 1704-1711

Object recognition as ranking holistic figure-ground hypotheses (Abstract)

Cristian Sminchisescu , Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn
Fuxin Li , Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn
Joao Carreira , Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn
pp. 1712-1719

Finding nemo: Deformable object class modelling using curve matching (Abstract)

Andrew Zisserman , University of Oxford
Andrew Fitzgibbon , Microsoft Research, Cambridge
Luc Van Gool , ETH Zürich
Mukta Prasad , ETH Zürich
pp. 1720-1727

Automatic attribution of ancient Roman imperial coins (Abstract)

Ognjen Arandjelovic , Trinity College, University of Cambridge, Cambridge, CB2 1TQ, United Kingdom
pp. 1728-1734

Multiple object detection by sequential monte carlo and Hierarchical Detection Network (Abstract)

Dorin Comaniciu , Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540, USA
Jingdan Zhang , Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540, USA
Michal Sofka , Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540, USA
S. Kevin Zhou , Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540, USA
pp. 1735-1742

Putting local features on a manifold (Abstract)

Marwan Torki , Department of Computer Science, Rutgers University, New Brunswick, NJ, USA
Ahmed Elgammal , Department of Computer Science, Rutgers University, New Brunswick, NJ, USA
pp. 1743-1750

A generative perspective on MRFs in low-level vision (Abstract)

Stefan Roth , Department of Computer Science, TU Darmstadt
Uwe Schmidt , Department of Computer Science, TU Darmstadt
Qi Gao , Department of Computer Science, TU Darmstadt
pp. 1751-1758

Manifold blurring mean shift algorithms for manifold denoising (Abstract)

Miguel A. Carreira-Perpinan , Electrical Engineering and Computer Science, University of California, Merced
Weiran Wang , Electrical Engineering and Computer Science, University of California, Merced
pp. 1759-1766

Increasing depth resolution of electron microscopy of neural circuits using sparse tomographic reconstruction (Abstract)

Alex. V. Genkin , HHMI, Ashburn, VA
Shan Xu , HHMI, Ashburn, VA
Richard Fetter , HHMI, Ashburn, VA
Graham Knott , EPFL, Lausanne
Lou Scheffer , HHMI, Ashburn, VA
Harald Hess , HHMI, Ashburn, VA
Ashok Veeraraghavan , MERL, Cambridge MA
Shiv Vitaladevuni , HHMI, Ashburn, VA
Dmitri Chklovskii , HHMI, Ashburn, VA
Marco Cantoni , EPFL, Lausanne
pp. 1767-1774

SVM for edge-preserving filtering (Abstract)

Shengnan Wang , University of Illinois at Urbana Champaign
Qingxiong Yang , University of Illinois at Urbana Champaign
Narendra Ahuja , University of Illinois at Urbana Champaign
pp. 1775-1782

Robust video denoising using low rank matrix completion (Abstract)

Zuowei Shen , Department of Mathematics, National University of Singapore, Singapore 117542
Hui Ji , Department of Mathematics, National University of Singapore, Singapore 117542
Yuhong Xu , Center for Wavelets, Approx. and Info. Proc., National University of Singapore, Singapore 117542
Chaoqiang Liu , Center for Wavelets, Approx. and Info. Proc., National University of Singapore, Singapore 117542
pp. 1791-1798

Personalization of image enhancement (Abstract)

Sing Bing Kang , Microsoft Research, Redmond, WA, USA
Dani Lischinski , The Hebrew University of Jerusalem, Israel
Ashish Kapoor , Microsoft Research, Redmond, WA, USA
pp. 1799-1806

Adaptive linear predictors for real-time tracking (Abstract)

Nassir Navab , Department of Computer Science, Technical University of Munich (TUM) Boltzmannstrasse 3, 85748 Garching, Germany
Slobodan Ilic , Department of Computer Science, Technical University of Munich (TUM) Boltzmannstrasse 3, 85748 Garching, Germany
Stefan Holzer , Department of Computer Science, Technical University of Munich (TUM) Boltzmannstrasse 3, 85748 Garching, Germany
pp. 1807-1814

Multilinear pose and body shape estimation of dressed subjects from image sets (Abstract)

Thorsten Thormahlen , Max-Planck-Institut Informatik (MPII)* Saarland University, Leibniz University Hannover Weta Digital
Bodo Rosenhahn , Max-Planck-Institut Informatik (MPII)* Saarland University, Leibniz University Hannover Weta Digital
Hans-Peter Seidel , Max-Planck-Institut Informatik (MPII)* Saarland University, Leibniz University Hannover Weta Digital
Hanno Ackermann , Max-Planck-Institut Informatik (MPII)* Saarland University, Leibniz University Hannover Weta Digital
Nils Hasler , Max-Planck-Institut Informatik (MPII)* Saarland University, Leibniz University Hannover Weta Digital
pp. 1823-1830

Linear view synthesis using a dimensionality gap light field prior (Abstract)

Anat Levin , Weizmann Institute of Science MIT CSAIL
Fredo Durand , Weizmann Institute of Science MIT CSAIL
pp. 1831-1838

Multi-target tracking of time-varying spatial patterns (Abstract)

Yanxi Liu , Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA 16802, USA
Jingchen Liu , Department of Computer Science and Engineering, The Pennsylvania State University, University Park, PA 16802, USA
pp. 1839-1846

Abrupt motion tracking via adaptive stochastic approximation Monte Carlo sampling (Abstract)

Xiuzhuang Zhou , Computer Science School, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China
Yao Lu , Computer Science School, Beijing Institute of Technology, Beijing Laboratory of Intelligent Information Technology, Beijing, China
pp. 1847-1854

Boosting for transfer learning with multiple sources (Abstract)

Gianfranco Doretto , Visualization and Computer Vision Lab, GE Global Research, Niskayuna, NY 12309
Yi Yao , Visualization and Computer Vision Lab, GE Global Research, Niskayuna, NY 12309
pp. 1855-1862

Energy minimization for linear envelope MRFs (Abstract)

M. Pawan Kumar , Computer Science Department, Stanford University, USA
Pushmeet Kohli , Microsoft Research, Cambridge, UK
pp. 1863-1870

Unified graph matching in Euclidean spaces (Abstract)

Tiberio S. Caetano , NICTA/ANU Canberra, ACT 0200
Julian J. McAuley , NICTA/ANU, Canberra, ACT 0200
Teofilo de Campos , University of Surrey, Guildford, GU2 7XH, UK
pp. 1871-1878

On-line semi-supervised multiple-instance boosting (Abstract)

Christian Leistner , Institute for Computer Graphics and Vision, TU Graz
Bernhard Zeisl , Institute for Computer Graphics and Vision, TU Graz
Horst Bischof , Institute for Computer Graphics and Vision, TU Graz
Amir Saffari , Institute for Computer Graphics and Vision, TU Graz
pp. 1879

Robust RVM regression using sparse outlier model (Abstract)

Kaushik Mitra , Department of Electrical and Computer Engineering and Center for Automation Research, UMIACS, University of Maryland, College Park, MD
Rama Chellappa , Department of Electrical and Computer Engineering and Center for Automation Research, UMIACS, University of Maryland, College Park, MD
Ashok Veeraraghavan , Mitshubishi Electric Research Laboratories, Cambridge, MA
pp. 1887-1894

Parametric dimensionality reduction by unsupervised regression (Abstract)

Zhengdong Lu , CS, University of Texas, Austin
Miguel A. Carreira-Perpinan , EECS, University of California, Merced
pp. 1895-1902

Spherical embeddings for non-Euclidean dissimilarities (Abstract)

Richard C. Wilson , Department of Computer Science, University of York, UK
Elzbieta Pekalska , School of Computer Science, University of Manchester, United Kingdom
Robert P. W. Duin , Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Netherlands
Edwin R. Hancock , Department of Computer Science, University of York, UK
pp. 1903-1910

Moving vistas: Exploiting motion for describing scenes (Abstract)

Nitesh Shroff , Department of Electrical and Computer Engineering, Center for Automation Research, UMIACS, University of Maryland, College Park, MD 20742
Rama Chellappa , Department of Electrical and Computer Engineering, Center for Automation Research, UMIACS, University of Maryland, College Park, MD 20742
Pavan Turaga , Department of Electrical and Computer Engineering, Center for Automation Research, UMIACS, University of Maryland, College Park, MD 20742
pp. 1911-1918

Part and appearance sharing: Recursive Compositional Models for multi-view (Abstract)

Long Zhu , CSAIL, MIT, Cambridge, MA, USA
Yuanhao Chen , Dept. of Stat., UCLA, Los Angeles, CA, USA
A Torralba , CSAIL, MIT, Cambridge, MA, USA
W Freeman , CSAIL, MIT, Cambridge, MA, USA
A Yuille , Dept. of Stat., UCLA, Los Angeles, CA, USA
pp. 1919-1926
Papers

Improving state-of-the-art OCR through high-precision document-specific modeling (Abstract)

Gary Huang , Department of Computer Science University of Massachusetts Amherst
Erik Learned-Miller , Department of Computer Science University of Massachusetts Amherst
Carl Doersch , Department of Computer Science, Carnegie Mellon University
Andrew Kae , Department of Computer Science University of Massachusetts Amherst
pp. 1935-1942

Discriminative clustering for image co-segmentation (Abstract)

Jean Ponce , Ecole Normale Supérieure, 45 rue d'Ulm, 75005 Paris, France
Armand Joulin , INRIA, 23 avenue d'Italie, 75214 Paris, France
Francis Bach , INRIA, 23 avenue d'Italie, 75214 Paris, France
pp. 1943-1950

What's going on? Discovering spatio-temporal dependencies in dynamic scenes (Abstract)

Michael D. Breitenstein , Computer Vision Laboratory, ETH Zurich
Vittorio Ferrari , Computer Vision Laboratory, ETH Zurich
Daniel Kuettel , Computer Vision Laboratory, ETH Zurich
Luc Van Gool , Computer Vision Laboratory, ETH Zurich
pp. 1951-1958

Visual event recognition in videos by learning from web data (Abstract)

Dong Xu , School of Computer Engineering, Nanyang Technological University
Ivor W. Tsang , School of Computer Engineering, Nanyang Technological University
Lixin Duan , School of Computer Engineering, Nanyang Technological University
Jiebo Luo , Kodak Research Labs, Eastman Kodak Company, Rochester, NY, USA
pp. 1959-1966

Temporal causality for the analysis of visual events (Abstract)

Sangmin Oh , Kitware, Inc.
James M. Rehg , Health Systems Institute and RIM@GT School of Interactive Computing, Georgia Institute of Technology
Ping Wang , Health Systems Institute and RIM@GT School of Interactive Computing, Georgia Institute of Technology
Gregory D. Abowd , Health Systems Institute and RIM@GT School of Interactive Computing, Georgia Institute of Technology
Karthir Prabhakar , Health Systems Institute and RIM@GT School of Interactive Computing, Georgia Institute of Technology
pp. 1967-1974

Anomaly detection in crowded scenes (Abstract)

Weixin Li , Department of Electrical and Computer Engineering, University of California, San Diego
Viral Bhalodia , Department of Electrical and Computer Engineering, University of California, San Diego
Nuno Vasconcelos , Department of Electrical and Computer Engineering, University of California, San Diego
Vijay Mahadevan , Department of Electrical and Computer Engineering, University of California, San Diego
pp. 1975-1981

Illumination compensation based change detection using order consistency (Abstract)

Visvanathan Ramesh , Real Time Vision and Industrial Imaging, Siemens Corporate Research, Siemens Corporation, Princeton, NJ 08540
Maneesh Singh , Real Time Vision and Industrial Imaging, Siemens Corporate Research, Siemens Corporation, Princeton, NJ 08540
Vasu Parameswaran , Real Time Vision and Industrial Imaging, Siemens Corporate Research, Siemens Corporation, Princeton, NJ 08540
pp. 1982-1989

Efficient action spotting based on a spacetime oriented structure representation (Abstract)

Konstantinos G. Derpanis , Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada
Richard P. Wildes , Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada
Mikhail Sizintsev , Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada
Kevin Cannons , Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada
pp. 1990-1997

Cross-dataset action detection (Abstract)

Liangliang Cao , Beckman Institute, Department of ECE, UIUC
Thomas S. Huang , Beckman Institute, Department of ECE, UIUC
Zicheng Liu , Microsoft Research, Redmond, WA, USA
pp. 1998-2005

Learning 3D action models from a few 2D videos for view invariant action recognition (Abstract)

Pradeep Natarajan , Raytheon BBN Technologies, Cambridge, MA
Ram Nevatia , University of Southern California, Los Angeles, CA
Vivek Kumar Singh , University of Southern California, Los Angeles, CA
pp. 20006-2013

Exploiting simple hierarchies for unsupervised human behavior analysis (Abstract)

Helmut Grabner , Computer Vision Laboratory ETH Zurich
Fabian Nater , Computer Vision Laboratory ETH Zurich
Luc Van Gool , Computer Vision Laboratory ETH Zurich
pp. 2014-2021

Clustering dynamic textures with the hierarchical EM algorithm (Abstract)

Antoni B. Chan , Dept. of Computer Science, City University of Hong Kong
Gert. R. G. Lanckriet , Dept. of Electrical and Computer Engineering, University of California, San Diego
Emanuele Coviello , Dept. of Electrical and Computer Engineering, University of California, San Diego
pp. 2022-2029

Recognizing human actions from still images with latent poses (Abstract)

Weilong Yang , School of Computing Science, Simon Fraser University, Burnaby, BC, Canada
Yang Wang , School of Computing Science, Simon Fraser University, Burnaby, BC, Canada
Greg Mori , School of Computing Science, Simon Fraser University, Burnaby, BC, Canada
pp. 2030-2037

Group motion segmentation using a Spatio-Temporal Driving Force Model (Abstract)

Rama Chellappa , Department of Electrical and Computer Engineering, and Center for Automation Research, UMIACS, University of Maryland, College Park, MD 20742
Ruonan Li , Department of Electrical and Computer Engineering, and Center for Automation Research, UMIACS, University of Maryland, College Park, MD 20742
pp. 2038-2045

Learning a hierarchy of discriminative space-time neighborhood features for human action recognition (Abstract)

Adriana Kovashka , Department of Computer Science, University of Texas at Austin
Kristen Grauman , Department of Computer Science, University of Texas at Austin
pp. 2046-2053

Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes (Abstract)

Brian E. Moore , Department of Mathematics University of Central Florida
Mubarak Shah , Computer Vision Lab, University of Central Florida
Shandong Wu , Computer Vision Lab, University of Central Florida
pp. 2054-2060

A Hough transform-based voting framework for action recognition (Abstract)

Angela Yao , ETH Zurich, Switzerland
Juergen Gall , ETH Zurich, Switzerland
Luc Van Gool , ETH Zurich, Switzerland
pp. 2061-2068

Scene understanding by statistical modeling of motion patterns (Abstract)

Mubarak Shah , Computer Vision Lab, University of Central Florida
Imran Saleemi , Computer Vision Lab, University of Central Florida
Lance Hartung , Computer Sciences Department, University of Wisconsin-Madison
pp. 2069-2076

Spike train driven dynamical models for human actions (Abstract)

Stefano Soatto , Computer Science Department, University of California, Los Angeles, CA 90095
Michalis Raptis , Computer Science Department, University of California, Los Angeles, CA 90095
Kamil Wnuk , Computer Science Department, University of California, Los Angeles, CA 90095
pp. 2077-2084

Parallel and distributed graph cuts by dual decomposition (Abstract)

Fredrik Kahl , Centre for Mathematical Sciences, Lund University, Sweden
Petter Strandmark , Centre for Mathematical Sciences, Lund University, Sweden
pp. 2085-2092

Object separation in x-ray image sets (Abstract)

Gal Chechik , Qylur Security Systems, Inc., Palo Alto, CA 94305
Geremy Heitz , Qylur Security Systems, Inc., Palo Alto, CA 94305
pp. 2093-2100

Learning full pairwise affinities for spectral segmentation (Abstract)

Tae Hoon Kim , Sang Uk Lee Dept. of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
Kyoung Mu Lee , Sang Uk Lee Dept. of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
pp. 2101-2108

Isoperimetric cut on a directed graph (Abstract)

Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong
Ming Liu , Department of Information Engineering, The Chinese University of Hong Kong
Jianzhuang Liu , Department of Information Engineering, The Chinese University of Hong Kong
Mo Chen , Department of Information Engineering, The Chinese University of Hong Kong
pp. 2109-2116

“Lattice Cut” - Constructing superpixels using layer constraints (Abstract)

Jonathan Warrell , Oxford Brookes University, Oxford, OX33 1HX, UK
Simon J. D. Prince , University College London, Gower Street, WC1E 6BT, UK
Alastair P. Moore , University College London, Gower Street, WC1E 6BT, UK
pp. 2117-2124

A diffusion approach to seeded image segmentation (Abstract)

Jianfei Cai , Nanyang Technological University, Singapore
Jianmin Zheng , Nanyang Technological University, Singapore
Juyong Zhang , Nanyang Technological University, Singapore
pp. 2125-2132

Discrete minimum ratio curves and surfaces (Abstract)

Philip H. S. Torr , Oxford Brookes University, Oxford, UK
Fred Nicolls , University of Cape Town Cape Town, South Africa
pp. 2133-2140

Efficient hierarchical graph-based video segmentation (Abstract)

Vivek Kwatra , Google Research, Mountain View, CA, USA
Irfan Essa , Georgia Institute of Technology, Atlanta, GA, USA
Matthias Grundmann , Georgia Institute of Technology, Atlanta, GA, USA
Mei Han , Google Research, Mountain View, CA, USA
pp. 2141-2148

A spatially varying PSF-based prior for alpha matting (Abstract)

Carsten Rother , Microsoft Research Cambridge, Cambridge, UK
Christoph Rhemann , Vienna University of Technology, Vienna, Austria
Pushmeet Kohli , Microsoft Research Cambridge, Cambridge, UK
Margrit Gelautz , Vienna University of Technology, Vienna, Austria
pp. 2149-2156

Simultaneous foreground, background, and alpha estimation for image matting (Abstract)

Brian L. Price , Brigham Young University
Bryan S. Morse , Brigham Young University
Scott Cohen , Adobe Systems
pp. 2157-2164

Fast matting using large kernel matting Laplacian matrices (Abstract)

Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong
Kaiming He , Department of Information Engineering, The Chinese University of Hong Kong
Jian Sun , Microsoft Research Asia
pp. 2165-2172

Fast approximate energy minimization with label costs (Abstract)

Hossam N. Isack , Department of Computer Science, University of Western Ontario
Yuri Boykov , Department of Computer Science, University of Western Ontario
Andrew Delong , Department of Computer Science, University of Western Ontario
Anton Osokin , Department of Computational Mathematics and Cybernetics, Moscow State University
pp. 2173-2180

Parallel graph-cuts by adaptive bottom-up merging (Abstract)

Jian Sun , Microsoft Research Asia
Jiangyu Liu , University of Science and Technology of China
pp. 2181-2188

Transductive segmentation of live video with non-stationary background (Abstract)

Xueying Qin , Department of Computer Science, Shandong University
Qunsheng Peng , State Key Lab. of CAD&CG, Zhejiang University
Fan Zhong , State Key Lab. of CAD&CG, Zhejiang University
pp. 2189-2196

Morphological snakes (Abstract)

Pablo Marquez-Neila , Dep. Inteligencia Artificial, Facultad Informática, Universidad Politécnica de Madrid
Luis Alvarez , Dep. Informática y Sistemas, Universidad de las Palmas de Gran, Canaria
Pedro Henriquez , Dep. Informática y Sistemas, Universidad de las Palmas de Gran, Canaria
Luis Baumela , Dep. Inteligencia Artificial, Facultad Informática, Universidad Politécnica de Madrid
pp. 2197-2202

Co-clustering of image segments using convex optimization applied to EM neuronal reconstruction (Abstract)

Shiv N. Vitaladevuni , Janelia Farm Research Campus, Howard Hughes Medical Institute
Ronen Basri , Dept. of Computer Science and Applied Math, Weizmann Institute of Science
pp. 2203-2210

Multi-domain, higher order level set scheme for 3D image segmentation on the GPU (Abstract)

Qin Zhang , Computational Visualization Center The University of Texas at Austin, USA
Ojaswa Sharma , DTU Informatics The Technical University of Denmark, Denmark
Chandrajit Bajaj , Computational Visualization Center The University of Texas at Austin, USA
Franccois Anton , DTU Informatics The Technical University of Denmark, Denmark
pp. 2211-2216

A study on continuous max-flow and min-cut approaches (Abstract)

Xue-Cheng Tai , Department of Mathematics, University of Bergen, University of Bergen, Johaness Brunsgate 12, Bergen 5007, Norway
Egil Bae , Department of Mathematics, University of Bergen, University of Bergen, Johaness Brunsgate 12, Bergen 5007, Norway
Jing Yuan , Computer Science Department, University of Western Ontario, Middlesex College 240, University of Western Ontario, London, ON, Canada, N6A 5B7
pp. 2217-2224

Object recognition by discriminative combinations of line segments and ellipses (Abstract)

Deepu Rajan , School of Computer Engineering, Nanyang Technological University, Singapore
Susanto Rahardja , Institute for Infocomm Research, Singapore
Maylor Karhang Leung , School of Computer Engineering, Nanyang Technological University, Singapore
Alex Yong-Sang Chia , Institute for Infocomm Research, Singapore
pp. 2225-2232

On detection of multiple object instances using hough transforms (Abstract)

Victor Lempitsky , University of Oxford
Olga Barinova , Moscow State University
Pushmeet Kohli , Microsoft Research Cambridge
pp. 2233-2240

Cascade object detection with deformable part models (Abstract)

Ross B. Girshick , University of Chicago
David McAllester , TTI at Chicago
Pedro F. Felzenszwalb , University of Chicago
pp. 2241-2248

Food recognition using statistics of pairwise local features (Abstract)

Shulin Yang , Univ. of Washington, Seattle, WA, USA
Mei Chen , Intel Labs. Pittsburgh, Pittsburgh, PA, USA
D Pomerleau , Intel Labs. Pittsburgh, Pittsburgh, PA, USA
R Sukthankar , Intel Labs. Pittsburgh, Pittsburgh, PA, USA
pp. 2249-2256
Papers

The multiscale competitive code via sparse representation for palmprint verification (Abstract)

Zhenhua Guo , Hong Kong Polytechnic University, Kowloon, Hong Kong
David Zhang , Hong Kong Polytechnic University, Kowloon, Hong Kong
Wangmeng Zuo , Harbin Institute of Technology, Harbin, 150001, China
Zhouchen Lin , Microsoft Research Asia, Beijing, 100190, China
pp. 2265-2272

Learning a probabilistic model mixing 3D and 2D primitives for view invariant object recognition (Abstract)

Wenze Hu , Department of Statistics, University of California, Los Angeles (UCLA), USA
Song-Chun Zhu , Department of Statistics, University of California, Los Angeles (UCLA), USA
pp. 2273-2280

Dense interest points (Abstract)

Tinne Tuytelaars , K.U. Leuven, ESAT - PSI
pp. 2281-2288

Two perceptually motivated strategies for shape classification (Abstract)

Brent C. Munsell , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
Jarrell W. Waggoner , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
Andrew Temlyakov , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
Song Wang , Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
pp. 2289-2296

Large-scale image categorization with explicit data embedding (Abstract)

Jorge Senchez , Research Centre Europe (XRCE)
Yan Liu Xerox , Research Centre Europe (XRCE)
Florent Perronnin , Research Centre Europe (XRCE)
pp. 2297-2304

Probabilistic models for supervised dictionary learning (Abstract)

Bao-Liang Lu , Department of Computer Science and Engineering, Shanghai Jiao Tong University, China
Lei Zhang , Microsoft Research Asia
Zhiwei Li , MOE-MS Key Lab for Intelligent Computing and Intelligent Systems, Shanghai Jiao Tong University, China
Xiao-Chen Lian , Department of Computer Science and Engineering, Shanghai Jiao Tong University, China
Changhu Wang , Microsoft Research Asia
pp. 2305-2312

Use bin-ratio information for category and scene classification (Abstract)

Nianhua Xie , National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China
Haibin Ling , Dept. of Computer and Information Science, Temple University, Philadelphia, USA
Xiaoqin Zhang , National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China
Weiming Hu , National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China
pp. 2313-2319

Learning weights for codebook in image classification and retrieval (Abstract)

Hongping Cai , National University of Defense Technology, China
Fei Yan , University of Surrey, UK
Krystian Mikolajczyk , University of Surrey, UK
pp. 2320-2327

The role of features, algorithms and data in visual recognition (Abstract)

C. Lawrence Zitnick , Microsoft Research, Redmond
Devi Parikh , Toyota Technological Institute, Chicago (TTIC)
pp. 2328-2335

Global Gaussian approach for scene categorization using information geometry (Abstract)

Hideki Nakayama , Grad. School of Information Science and Technology, The University of Tokyo
Tatsuya Harada , Grad. School of Information Science and Technology, The University of Tokyo
Yasuo Kuniyoshi , Grad. School of Information Science and Technology, The University of Tokyo
pp. 2336-2343

Asymmetric region-to-image matching for comparing images with generic object categories (Abstract)

Jaechul Kim , University of Texas at Austin
Kristen Grauman , University of Texas at Austin
pp. 2344-2351

Attribute-centric recognition for cross-category generalization (Abstract)

Ali Farhadi , University of Illinois at Urbana Champaign
Ian Endres , University of Illinois at Urbana Champaign
Derek Hoiem , University of Illinois at Urbana Champaign
pp. 2352-2359

Person re-identification by symmetry-driven accumulation of local features (Abstract)

A. Perina , Dipartimento di Informatica, University of Verona, Italy
V. Murino , Dipartimento di Informatica, University of Verona, Italy
M. Cristani , Dipartimento di Informatica, University of Verona, Italy
M. Farenzena , Dipartimento di Informatica, University of Verona, Italy
L. Bazzani , Dipartimento di Informatica, University of Verona, Italy
pp. 2360-2367

Measuring visual saliency by Site Entropy Rate (Abstract)

Qingming Huang , National Engineering Lab for Video Technology
Wen Gao , National Engineering Lab for Video Technology
Yizhou Wang , National Engineering Lab for Video Technology
Wei Wang , National Engineering Lab for Video Technology
pp. 2368-2375

Context-aware saliency detection (Abstract)

Stas Goferman , Technion
Ayellet Tal , Technion
pp. 2376-2383

Minimum length in the tangent bundle as a model for curve completion (Abstract)

Ohad Ben-Shahar , Computer Science Department, Ben-Gurion University, Beer Sheva, Israel
Guy Ben-Yosef , Computer Science Department, Ben-Gurion University, Beer Sheva, Israel
pp. 2384-2391

Removing rolling shutter wobble (Abstract)

Sing Bing Kang , Microsoft Corporation, One Microsoft Way, Redmond WA 98052
Richard Szeliski , Microsoft Corporation, One Microsoft Way, Redmond WA 98052
Eric Bennett , Microsoft Corporation, One Microsoft Way, Redmond WA 98052
Simon Baker , Microsoft Corporation, One Microsoft Way, Redmond WA 98052
pp. 2392-2399

Super resolution using edge prior and single image detail synthesis (Abstract)

Shuaicheng Liu , National University of Singapore
Michael S. Brown , National University of Singapore
Stephen Lin , Microsoft Research Asia
Yu-Wing Tai , Korean Advanced Institute of Science and Technology
pp. 2400-2407

Coded exposure imaging for projective motion deblurring (Abstract)

Stephen Lin , Microsoft Research Asia
Sung Yong Shin , Korea Advanced Institute of Science and Technology
Yu-Wing Tai , Korea Advanced Institute of Science and Technology
Naejin Kong , Korea Advanced Institute of Science and Technology
pp. 2408-2415

DARTs: Efficient scale-space extraction of DAISY keypoints (Abstract)

David Marimon , Telefonica Research and Development, Barcelona, Spain
Arturo Bonnin , Telefonica Research and Development, Barcelona, Spain
Tomasz Adamek , Telefonica Research and Development, Barcelona, Spain
Roger Gimeno , Telefonica Research and Development, Barcelona, Spain
pp. 2416-2423

Generating sharp panoramas from motion-blurred videos (Abstract)

Daniel P. Huttenlocher , Cornell University, Ithaca, NY 14853, USA
Yunpeng Li , Cornell University, Ithaca, NY 14853, USA
Sing Bing Kang , Microsoft Research, Redmond, WA 98052, USA
Steve M. Seitz , University of Washington, Seattle, WA 98195, USA
Neel Joshi , Microsoft Research, Redmond, WA 98052, USA
pp. 2424-2431

Secrets of optical flow estimation and their principles (Abstract)

Stefan Roth , TU Darmstadt
Michael J. Black , Brown University
Deqing Sun , Brown University
pp. 2432-2439

Robust flash deblurring (Abstract)

Dong Guo , School of Computing, National University of Singapore, 117417
Shaojie Zhuo , School of Computing, National University of Singapore, 117417
Terence Sim , School of Computing, National University of Singapore, 117417
pp. 2440-2447

Recovering fluid-type motions using Navier-Stokes potential flow (Abstract)

Philippe Guyenne , Department of Mathematical Sciences, University of Delaware, Newark, DE19716, USA
Jingyi Yu , Department of Computer and Information Sciences, University of Delaware, Newark, DE19716, USA
Feng Li , Department of Computer and Information Sciences, University of Delaware, Newark, DE19716, USA
Liwei Xu , Department of Mathematical Sciences, University of Delaware, Newark, DE19716, USA
pp. 2448-2455

Sparsity model for robust optical flow estimation at motion discontinuities (Abstract)

Ying Wu , Northwestern University, 2145 Sheridan Road, Evanston, IL 60208
Xiaohui Shen , Northwestern University, 2145 Sheridan Road, Evanston, IL 60208
pp. 2456-2463

Motion estimation with non-local total variation regularization (Abstract)

Manuel Werlberger , Institute for Computer Graphics and Vision
Thomas Pock , Institute for Computer Graphics and Vision
Horst Bischof , Institute for Computer Graphics and Vision
pp. 2464-2471

Robust classification of objects, faces, and flowers using natural image statistics (Abstract)

Garrison Cottrell , Department of Computer Science and Engineering, University of California, San Diego
Christopher Kanan , Department of Computer Science and Engineering, University of California, San Diego
pp. 2472-2479

Fast image alignment in the Fourier domain (Abstract)

Simon Lucey , Commonwealth Science and Industrial Research Organisation, (CSIRO), Australia
Ahmed Bilal Ashraf , Carnegie Mellon University
Tsuhan Chen , Cornell University
pp. 2480-2487

Boundary Learning by Optimization with Topological Constraints (Abstract)

Wickliffe C. Abraham , Dept. of Psychology and Brain Health and Repair Research Center, Univ. of Otago, Dunedin, New Zealand
Richard Schalek , Department of Molecular and Cellular Biology, Center for Brain Science, Harvard University, Cambridge, MA, USA
Ken J. Hayworth , Department of Molecular and Cellular Biology, Center for Brain Science, Harvard University, Cambridge, MA, USA
Narayanan Kasthuri , Department of Molecular and Cellular Biology, Center for Brain Science, Harvard University, Cambridge, MA, USA
Jeff W. Lichtman , Department of Molecular and Cellular Biology, Center for Brain Science, Harvard University, Cambridge, MA, USA
Moritz N. Helmstaedter , Department of Biomedical Optics, Max Planck Institute for Medical Research, Heidelberg, Germany
Kristen M. Harris , Center for Learning and Memory, Department of Neurobiology, University of Texas at Austin, TX, USA
Kevin L. Briggman , Department of Biomedical Optics, Max Planck Institute for Medical Research, Heidelberg, Germany
John M. Mendenhall , Center for Learning and Memory, Department of Neurobiology, University of Texas at Austin, TX, USA
Benjamin Bollmann , Brain & Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA
Mark Richardson , Brain & Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA
Winfried Denk , Department of Biomedical Optics, Max Planck Institute for Medical Research, Heidelberg, Germany
Daniel R. Berger , Brain & Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA
Juan Carlos Tapia , Department of Molecular and Cellular Biology, Center for Brain Science, Harvard University, Cambridge, MA, USA
H. Sebastian Seung , Brain & Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA
Viren Jain , Brain & Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA
Jared B. Bowden , Center for Learning and Memory, Department of Neurobiology, University of Texas at Austin, TX, USA
pp. 2488-2495

Beyond trees: MRF inference via outer-planar decomposition (Abstract)

A. C. Gallagher , Eastman Kodak Company
Tsuhan Chen , Cornell University
Dhruv Batra , Carnegie Mellon Univerity
pp. 2496-2503

Optical flow estimation with adaptive convolution kernel prior on discrete framework (Abstract)

Dongjin Kwon , School of EECS, Seoul Nat'l Univ., Seoul, 151-742, Korea
Kyong Joon Lee , School of EECS, Seoul Nat'l Univ., Seoul, 151-742, Korea
Sang Uk Lee , School of EECS, Seoul Nat'l Univ., Seoul, 151-742, Korea
Il Dong Yun , School of EIE, Hankuk Univ. of F. S., Yongin, 449-791, Korea
pp. 2504-2511

Analyzing spatially-varying blur (Abstract)

William T. Freeman , CTL, Adobe Systems Inc., Cambridge, MA 02142, USA
Todd Zickler , SEAS, Harvard University, Cambridge, MA 02138, USA
Ayan Chakrabarti , SEAS, Harvard University, Cambridge, MA 02138, USA
pp. 2512-2519

Highly accurate boundary detection and grouping (Abstract)

Iasonas Kokkinos , Laboratoire MAS, Ecole Centrale de Paris, INRIA Saclay, GALEN Group
pp. 2520-2527

Deconvolutional networks (Abstract)

Rob Fergus , Dept. of Computer Science, Courant Institute, New York University
Matthew D. Zeiler , Dept. of Computer Science, Courant Institute, New York University
Graham W. Taylor , Dept. of Computer Science, Courant Institute, New York University
Dilip Krishnan , Dept. of Computer Science, Courant Institute, New York University
pp. 2528-2535

Diffusion filtering without parameter tuning: Models and inference tools (Abstract)

Kai Krajsek , ICG-3, Forschungszentrum Ju¨lich, Germany
Hanno Scharr , ICG-3, Forschungszentrum Ju¨lich, Germany
pp. 2536-2543

Visual object tracking using adaptive correlation filters (Abstract)

Bruce A. Draper , Colorado State University Fort Collins, CO 80521, USA
David S. Bolme , Colorado State University Fort Collins, CO 80521, USA
J. Ross Beveridge , Colorado State University Fort Collins, CO 80521, USA
Yui Man Lui , Colorado State University Fort Collins, CO 80521, USA
pp. 2544-2550

Modeling pixel means and covariances using factorized third-order boltzmann machines (Abstract)

Geoffrey E. Hinton , Department of Computer Science - University of Toronto, 10 King's College Road, Toronto, Canada
Marc'Aurelio Ranzato , Department of Computer Science - University of Toronto, 10 King's College Road, Toronto, Canada
pp. 2551-2558

Learning mid-level features for recognition (Abstract)

Francis Bach , INRIA
Yann LeCun , Courant Institute, New York University
Jean Ponce , Ecole Normale Supérieure
pp. 2559-2566

Face recognition based on image sets (Abstract)

Hakan Cevikalp , Eskisehir Osmangazi University, Meselik Kampusu, 26480, Eskisehir, Turkey
Bill Triggs , Laboratoire Jean Kuntzmann, B.P. 53, 38041 Grenoble Cedex 9, France
pp. 2567-2573

Unsupervised discovery of facial events (Abstract)

Feng Zhou , Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
Fernando De la Torre , Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
Jeffrey F. Cohn , University of Pittsburgh, Department of Psychology, Pittsburgh, Pennsylvania 15260
pp. 2574-2581

3D morphable model construction for robust ear and face recognition (Abstract)

John D. Bustard , ISIS, School of Electronics and Computer Science, University of Southampton, Southampton, U.K.
Mark S. Nixon , ISIS, School of Electronics and Computer Science, University of Southampton, Southampton, U.K.
pp. 2582-2589

Bimodal gender recognition from face and fingerprint (Abstract)

Xiong Li , Shanghai Jiao Tong University, Shanghai, 200240, China
Yuncai Liu , Shanghai Jiao Tong University, Shanghai, 200240, China
Yun Fu , Department of CSE, University at Buffalo (SUNY), NY 14260, USA
Xu Zhao , Shanghai Jiao Tong University, Shanghai, 200240, China
pp. 2590-2597

Towards general motion-based face recognition (Abstract)

Ning Ye , School of Computing, National University of Singapore, Singapore 117417
Terence Sim , School of Computing, National University of Singapore, Singapore 117417
pp. 2598-2605

Morphable Reflectance Fields for enhancing face recognition (Abstract)

Tim K. Marks , Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
Ritwik Kumar , School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA
Michael Jones , Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
pp. 2606-2613

Removal of 3D facial expressions: A learning-based approach (Abstract)

Song Han , Department of Computer Science, Zhejiang University, China
Gang Pan , Department of Computer Science, Zhejiang University, China
Zhaohui Wu , Department of Computer Science, Zhejiang University, China
Yuting Zhang , Department of Computer Science, Zhejiang University, China
pp. 2614-2621

Multi-task warped Gaussian process for personalized age estimation (Abstract)

Yu Zhang , Department of Computer Science and Engineering, Hong Kong University of Science and Technology
Dit-Yan Yeung , Department of Computer Science and Engineering, Hong Kong University of Science and Technology
pp. 2622-2629

Learning shift-invariant sparse representation of actions (Abstract)

Hui Ji , Department of Mathematics, National University of Singapore
Cornelia Fermuller , Computer Vision Lab University of Maryland, College Park, MD 20742
Yiannis Aloimonos , Computer Vision Lab University of Maryland, College Park, MD 20742
Yi Li , Computer Vision Lab University of Maryland, College Park, MD 20742
pp. 2630-2637

Exploring facial expressions with compositional features (Abstract)

Qingshan Liu , Computer Science Department, Rutgers University 110 Frelinghuysen Road, Piscataway, NJ 08854, USA
Dimitris N. Metaxas , Computer Science Department, Rutgers University 110 Frelinghuysen Road, Piscataway, NJ 08854, USA
Peng Yang , Computer Science Department, Rutgers University 110 Frelinghuysen Road, Piscataway, NJ 08854, USA
pp. 2638-2644

An extension of multifactor analysis for face recognition based on submanifold learning (Abstract)

Marios Savvides , Electrical and Computer Engineering Department, Carnegie Mellon University, Pittsburgh PA 15213, USA
Sung Won Park , Electrical and Computer Engineering Department, Carnegie Mellon University, Pittsburgh PA 15213, USA
pp. 2645-2652

Making specific features less discriminative to improve point-based 3D object recognition (Abstract)

Alvaro Collet , Robotics Institute, Carnegie Mellon University, USA
Martial Hebert , Robotics Institute, Carnegie Mellon University, USA
Edward Hsiao , Robotics Institute, Carnegie Mellon University, USA
pp. 2653-2660

Cost-sensitive subspace learning for face recognition (Abstract)

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. 2661-2666

Calibration-free gaze sensing using saliency maps (Abstract)

Yoichi Sato , The University of Tokyo Tokyo, Japan, 153-8505
Yasuyuki Matsushita , Microsoft Research Asia, Beijing, P. R. China, 100080
Yusuke Sugano , The University of Tokyo Tokyo, Japan, 153-8505
pp. 2667-2674

A novel Markov random field based deformable model for face recognition (Abstract)

Albert C.S. Chung , Lo Kwee-Seong Medical Image Analysis Laboratory, Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong
Shu Liao , Lo Kwee-Seong Medical Image Analysis Laboratory, Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong
pp. 2675-2682

Pose-robust albedo estimation from a single image (Abstract)

Soma Biswas , Department of Electrical and Computer Engineering and CfAR, University of Maryland, College Park
Rama Chellappa , Department of Electrical and Computer Engineering and CfAR, University of Maryland, College Park
pp. 2683-2690

Discriminative K-SVD for dictionary learning in face recognition (Abstract)

Baoxin Li , Computer Science and Engineering, Arizona State University, Tempe, AZ
Qiang Zhang , Computer Science and Engineering, Arizona State University, Tempe, AZ
pp. 2691-2698

Adaptive generic learning for face recognition from a single sample per person (Abstract)

Xilin Chen , Digital Media Research Center, Institute of Computing Technology, CAS, China
Yu Su , School of Computer Science and Technology, Harbin Institute of Technology, China
Shiguang Shan , Digital Media Research Center, Institute of Computing Technology, CAS, China
Wen Gao , School of Computer Science and Technology, Harbin Institute of Technology, China
pp. 2699-2706

Face recognition with learning-based descriptor (Abstract)

Xiaoou Tang , The Chinese University of Hong Kong
Qi Yin , ITCS, Tsinghua University
Jian Sun , Microsoft Research Asia
Zhimin Cao , The Chinese University of Hong Kong
pp. 2707-2714

Automatic point-based facial trait judgments evaluation (Abstract)

David Masip , Computer Vision Center, Edifici O, Campus UAB, Spain
Alexander Todorov , Department of Psychology, Princeton University, Princeton, New Jersey, USA 08540
Mario Rojas Q. , Computer Vision Center, Edifici O, Campus UAB, Spain
Jordi Vitria , Computer Vision Center, Edifici O, Campus UAB, Spain
pp. 2715-2720

Bidirectional relighting for 3D-aided 2D face recognition (Abstract)

S. Zafeiriou , Department of Electrical and Electronic Engineering, Imperial College London, UK
G. Passalis , Computational Biomedicine Lab, Dept. of CS, ECE, Biomedical Engineering, Univ. of Houston, Houston, TX, USA
T. Theoharis , Computational Biomedicine Lab, Dept. of CS, ECE, Biomedical Engineering, Univ. of Houston, Houston, TX, USA
G. Tzimiropoulos , Department of Electrical and Electronic Engineering, Imperial College London, UK
I. A. Kakadiaris , Computational Biomedicine Lab, Dept. of CS, ECE, Biomedical Engineering, Univ. of Houston, Houston, TX, USA
M. Petrou , ITI-CERTH, Greece
G. Toderici , Computational Biomedicine Lab, Dept. of CS, ECE, Biomedical Engineering, Univ. of Houston, Houston, TX, USA
pp. 2721-2728

Facial point detection using boosted regression and graph models (Abstract)

Michel Valstar , Department of Computing Imperial College London
Brais Martinez , ICT Department, Universitat Pompeu Fabra
Maja Pantic , Imperial College London, Department of Computing, Twente University, EEMCS
Xavier Binefa , ICT Department, Universitat Pompeu Fabra
pp. 2729-2736

Action unit detection with segment-based SVMs (Abstract)

Minh Hoai Nguyen , The Robotics Institute, Carnegie Mellon University
Tomas Simon , The Robotics Institute, Carnegie Mellon University
Fernando De La Torre , The Robotics Institute, Carnegie Mellon University
Jeffrey F. Cohn , The Robotics Institute, Carnegie Mellon University
pp. 2737-2744

Gesture recognition by learning local motion signatures (Abstract)

Mohamed Becha Kaaniche , INRIA Sophia Antipolis - Mediterranean Research Center - PULSAR Project, 2004 route des Lucioles B.P 93, 06902 Sophia Antipolis Cedex, France
Francois Bremond , INRIA Sophia Antipolis - Mediterranean Research Center - PULSAR Project, 2004 route des Lucioles B.P 93, 06902 Sophia Antipolis Cedex, France
pp. 2745-2752

Rapid face recognition using hashing (Abstract)

Hanxi Li , Australian National University, and NICTA, Canberra, Australia
Chunhua Shen , NICTA, and Australian National University, Canberra, Australia
Qinfeng Shi , Australian National University, and NICTA, Canberra, Australia
pp. 2753-2760

Non-rigid structure from locally-rigid motion (Abstract)

Allan D. Jepson , Department of Computer Science University of Toronto
Kiriakos N. Kutulakos , Department of Computer Science University of Toronto
Jonathan Taylor , Department of Computer Science University of Toronto
pp. 2761-2768

Bundled depth-map merging for multi-view stereo (Abstract)

Yurong Chen , Intel Labs China, Haidian, Beijing, 100190
Yimin Zhang , Intel Labs China, Haidian, Beijing, 100190
Eric Li , Intel Labs China, Haidian, Beijing, 100190
Jianguo Li , Intel Labs China, Haidian, Beijing, 100190
Lin Xu , Intel Labs China, Haidian, Beijing, 100190
pp. 2769-2776

Multi-view structure computation without explicitly estimating motion (Abstract)

Hongdong Li , NICTA and Australian National University Canberra, ACT 2600, Australia
pp. 2777-2784

ABSORB: Atlas building by Self-Organized Registration and Bundling (Abstract)

Dinggang Shen , Department of Radiology and BRIC
Guorong Wu , Department of Radiology and BRIC
Hongjun Jia , Department of Radiology and BRIC
Qian Wang , Department of Radiology and BRIC
pp. 2785-2790

Stratified learning of local anatomical context for lung nodules in CT images (Abstract)

Arun Krishnan , CAD and Knowledge Solutions, Siemens Medical Solutions, Malvern, PA 19355 USA
Dijia Wu , CAD and Knowledge Solutions, Siemens Medical Solutions, Malvern, PA 19355 USA
Le Lu , CAD and Knowledge Solutions, Siemens Medical Solutions, Malvern, PA 19355 USA
Yoshihisa Shinagawa , CAD and Knowledge Solutions, Siemens Medical Solutions, Malvern, PA 19355 USA
Marcos Salganicoff , CAD and Knowledge Solutions, Siemens Medical Solutions, Malvern, PA 19355 USA
Kim Boyer , ECSE Department, Rensselaer Polytechnic Institute, Troy, NY 12180 USA
Jinbo Bi , CAD and Knowledge Solutions, Siemens Medical Solutions, Malvern, PA 19355 USA
pp. 2791-2798

Delineating trees in noisy 2D images and 3D image-stacks (Abstract)

Pascal Fua , CVLab, EPFL, CH-1015 Lausanne, Switzerland
Engin Turetken , CVLab, EPFL, CH-1015 Lausanne, Switzerland
Franccois Fleuret , IDIAP Research Institute, Rue Marconi 19, Martigny, Switzerland
German Gonzalez , CVLab, EPFL, CH-1015 Lausanne, Switzerland
pp. 2799-2806

Sign ambiguity resolution for phase demodulation in interferometry with application to prelens tear film analysis (Abstract)

Kim L. Boyer , Rensselaer Polytechnic Institute 110 8th Street, Troy 12180, USA
Dijia Wu , Rensselaer Polytechnic Institute 110 8th Street, Troy 12180, USA
pp. 2807-2814

Multiple dynamic models for tracking the left ventricle of the heart from ultrasound data using particle filters and deep learning architectures (Abstract)

Gustavo Carneiro , Instituto de Sistemas e Robótica Instituto Superior Técnico, Lisbon, Portugal
Jacinto C. Nascimento , Instituto de Sistemas e Robótica Instituto Superior Técnico, Lisbon, Portugal
pp. 2815-2822

Multilinear feature extraction and classification of multi-focal images, with applications in nematode taxonomy (Abstract)

Amit K. Roy-Chowdhury , Department of Electrical Engineering, University of California, Riverside
Min Liu , Department of Electrical Engineering, University of California, Riverside
pp. 2823-2830

Search strategies for multiple landmark detection by submodular maximization (Abstract)

Dorin Comaniciu , Siemens Corporation, Corporate Research, Princeton, NJ, USA, Siemens AG, Sector Healthcare, Computed Tomography, Forchheim, Germany
Dominik Bernhardt , Siemens Corporation, Corporate Research, Princeton, NJ, USA, Siemens AG, Sector Healthcare, Computed Tomography, Forchheim, Germany
David Liu , Siemens Corporation, Corporate Research, Princeton, NJ, USA, Siemens AG, Sector Healthcare, Computed Tomography, Forchheim, Germany
Kevin S. Zhou , Siemens Corporation, Corporate Research, Princeton, NJ, USA, Siemens AG, Sector Healthcare, Computed Tomography, Forchheim, Germany
pp. 2831-2838

Compression of surface registrations using Beltrami coefficients (Abstract)

Tony Chan , Hong Kong University of Science and Technology, Hong Kong
Tsz Wai Wong , Department of Mathematics, UCLA, Los Angeles, CA, USA
Paul Thompson , Laboratory of Neuro Imaging, UCLA School of Medicine, Los Angeles, CA, USA
Xianfeng Gu , Department of Computer Science, SUNY Stony Brook, Stony Brook, NY, USA
Lok Ming Lui , Department of Mathematics, Harvard University, Cambridge, MA, USA
Shing-Tung Yau , Department of Mathematics, Harvard University, Cambridge, MA, USA
pp. 2839-2846

Natural gradients for deformable registration (Abstract)

Ali Kamen , Siemens Corporate Research (SCR), Princeton, NJ, USA
Nassir Navab , Computer Aided Medical Procedures (CAMP), Technische Universita¨t Mu¨nchen, Germany
Darko Zikic , Computer Aided Medical Procedures (CAMP), Technische Universita¨t Mu¨nchen, Germany
pp. 2847-2854

Curious snakes: A minimum latency solution to the cluttered background problem in active contours (Abstract)

Ganesh Sundaramoorthi , University of California, Los Angeles
Anthony J. Yezzi , Georgia Institute of Technology
Stefano Soatto , University of California, Los Angeles
pp. 2855-2862

Anatomical parts-based regression using non-negative matrix factorization (Abstract)

Scott Grafton , Department of Psychology, University of California Santa Barbara
Swapna Joshi , Department of Electrical and Computer Engineering, University of California Santa Barbara
S. Karthikeyan , Department of Electrical and Computer Engineering, University of California Santa Barbara
Kent A. Kiehl , Department Psychology, University of New Mexico
B. S. Manjunath , Department of Electrical and Computer Engineering, University of California Santa Barbara
pp. 2863-2870

Metric-induced optimal embedding for intrinsic 3D shape analysis (Abstract)

Roger Woods , Dept. of Neurology, UCLA School of Medicine, Los Angeles, CA, USA
Arthur W. Toga , Lab. of Neuro Imaging, Dept. of Neurology, UCLA School of Medicine, Los Angeles, CA, USA
Tony F. Chan , Department of Mathematics, University of California, Los Angeles, CA, USA
Kevin Scheibel , Dept. of Neurology, UCLA School of Medicine, Los Angeles, CA, USA
Scott Fears , Dept. of Neurology, UCLA School of Medicine, Los Angeles, CA, USA
Yonggang Shi , Lab. of Neuro Imaging, Dept. of Neurology, UCLA School of Medicine, Los Angeles, CA, USA
Rongjie Lai , Department of Mathematics, University of California, Los Angeles, CA, USA
pp. 2871-2878

Simultaneous searching of globally optimal interacting surfaces with shape priors (Abstract)

Qi Song , Department of Electrical and Computer Engineering The University of Iowa, Iowa City, IA 52242, USA
Yunlong Liu , Department of Electrical and Computer Engineering The University of Iowa, Iowa City, IA 52242, USA
Mona Garvin , Department of Electrical and Computer Engineering The University of Iowa, Iowa City, IA 52242, USA
Xiaodong Wu , Department of Electrical and Computer Engineering The University of Iowa, Iowa City, IA 52242, USA
Milan Sonka , Department of Electrical and Computer Engineering The University of Iowa, Iowa City, IA 52242, USA
pp. 2879-2886

Group MRF for fMRI activation detection (Abstract)

Ghassan Hamarneh , Simon Fraser University, 8888 University Drive, Burnaby, BC V5A 1S6
Rafeef Abugharbieh , The University of British Columbia, 2329 West Mall, Vancouver, BC V6T 1Z4
Bernard Ng , The University of British Columbia, 2329 West Mall, Vancouver, BC V6T 1Z4
pp. 2887-2894

Localizing non-overlapping surveillance cameras under the L-Infinity norm (Abstract)

Branislav Micusik , Safety and Security Department, AIT Austrian Institute of Technology
Roman Pflugfelder , Safety and Security Department, AIT Austrian Institute of Technology
pp. 2895-2901

Neuron geometry extraction by perceptual grouping in ssTEM images (Abstract)

Joachim M. Buhmann , Department of Computer Science, ETH Zurich, 8092 Zurich, Switzerland
Verena Kaynig , Department of Computer Science, ETH Zurich, 8092 Zurich, Switzerland
Thomas Fuchs , Department of Computer Science, ETH Zurich, 8092 Zurich, Switzerland
pp. 2902-2909

An automatic unsupervised classification of MR images in Alzheimer's disease (Abstract)

Xiaojing Long , Virginia Tech, Blacksburg, VA 24061
Chris Wyatt , Virginia Tech, Blacksburg, VA 24061
pp. 2910-2917

Masked FFT registration (Abstract)

Dirk Padfield , GE Global Research, One Research Circle, Niskayuna, NY 12309
pp. 2918-2925

Lymph node detection in 3-D chest CT using a spatial prior probability (Abstract)

Martin Huber , Siemens Corporate Technology, Erlangen, Germany
Dorin Comaniciu , Siemens Corporate Research, Princeton, NJ, USA
S. Kevin Zhou , Siemens Corporate Research, Princeton, NJ, USA
Johannes Feulner , Pattern Recognition Lab, University of Erlangen-Nuremberg, Germany
Alexander Cavallaro , Radiology Institute, University Hospital Erlangen, Germany
Joachim Hornegger , Pattern Recognition Lab, University of Erlangen-Nuremberg, Germany
pp. 2926-2932

Image atlas construction via intrinsic averaging on the manifold of images (Abstract)

Jeffrey Ho , Department of Computer and Information Sciences and Engineering, University of Florida
Baba C. Vemuri , Department of Computer and Information Sciences and Engineering, University of Florida
Yuchen Xie , Department of Computer and Information Sciences and Engineering, University of Florida
pp. 2933-2939

Heterogeneous Conditional Random Field: Realizing joint detection and segmentation of cell regions in microscopic images (Abstract)

Jiyan Pan , Robotics Institute, Carnegie Mellon University, USA
Mei Chen , Intel Labs Pittsburgh, USA
Takeo Kanade , Robotics Institute, Carnegie Mellon University, USA
pp. 2940-2947

Model-based respiratory motion compensation for image-guided cardiac interventions (Abstract)

Rui Liao , Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540, USA
Joachim Hornegger , Pattern Recognition Lab, University of Erlangen-Nuremberg, Erlangen, Germany
Hari Sundar , Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540, USA
Matthias Schneider , Pattern Recognition Lab, University of Erlangen-Nuremberg, Erlangen, Germany
Chenyang Xu , Siemens Corporate Research, 755 College Road East, Princeton, NJ 08540, USA
pp. 2948-2954

Proximate sensing: Inferring what-is-where from georeferenced photo collections (Abstract)

Shawn Newsam , Electrical Engineering & Computer Science, University of California at Merced
Daniel Leung , Electrical Engineering & Computer Science, University of California at Merced
pp. 2955-2962

Detecting text in natural scenes with stroke width transform (Abstract)

Eyal Ofek , Microsoft Corporation
Boris Epshtein , Microsoft Corporation
Yonatan Wexler , Microsoft Corporation
pp. 2963-2970

Reading between the lines: Object localization using implicit cues from image tags (Abstract)

Kristen Grauman , Department of Computer Science, University of Texas at Austin
Sung Ju Hwang , Department of Computer Science, University of Texas at Austin
pp. 2971-2978

Beyond active noun tagging: Modeling contextual interactions for multi-class active learning (Abstract)

Abhinav Gupta , Robotics Institute, Carnegie Mellon University
Behjat Siddiquie , Department of Computer Science, University of Maryland, College Park
pp. 2979-2986

ARISTA - image search to annotation on billions of web photos (Abstract)

Wei-Ying Ma , Microsoft Research Asia, 49 Zhichun Road, Beijing, China
Lei Zhang , Microsoft Research Asia, 49 Zhichun Road, Beijing, China
Yi Li , Microsoft Corporation, One Microsoft Way, Redmond, U.S.A.
Ming Liu , Microsoft Corporation, One Microsoft Way, Redmond, U.S.A.
Xin-Jing Wang , Microsoft Research Asia, 49 Zhichun Road, Beijing, China
pp. 2987-2994

Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback (Abstract)

Nikolaos Papanikolopoulos , University of Minnesota, Twin Cities
Fatih Porikli , Mitsubishi Electric Research, Laboratories
Ajay J. Joshi , University of Minnesota, Twin Cities
pp. 2995-3002

Efficient histogram-based sliding window (Abstract)

Litian Tao , Beihang University
Yichen Wei , Microsoft Research Asia
pp. 3003-3010

Pareto-optimal dictionaries for signatures (Abstract)

Michael Calonder , EPFL, Lausanne, Switzerland
Vincent Lepetit , EPFL, Lausanne, Switzerland
Pascal Fua , EPFL, Lausanne, Switzerland
pp. 3011-3018

Region moments: Fast invariant descriptors for detecting small image structures (Abstract)

Gianfranco Doretto , Visualization and Computer Vision Lab, GE Global Research, Niskayuna, NY 12309
Yi Yao , Visualization and Computer Vision Lab, GE Global Research, Niskayuna, NY 12309
pp. 3019-3026

Optimizing one-shot recognition with micro-set learning (Abstract)

Rahul Sukthankar , Intel Labs Pittsburgh, Carnegie Mellon
Marshall F. Tappen , University of Central, Florida
Christoph H. Lampert , Max Planck Institute for Biological Cybernetics
Kevin D. Tang , Cornell University
pp. 3027-3034

Far-sighted active learning on a budget for image and video recognition (Abstract)

Kristen Grauman , University of Texas at Austin
Sudheendra Vijayanarasimhan , University of Texas at Austin
Prateek Jain , University of Texas at Austin
pp. 3035-3042

A square-root sampling approach to fast histogram-based search (Abstract)

Hwann-Tzong Chen , National Tsing Hua University, Taiwan
Huang-Wei Chang , Stanford University
pp. 3043-3049

Fast pattern matching using orthogonal Haar transform (Abstract)

Wanli Ouyang , The Chinese University of Hong Kong, The Chinese University of Hong Kong, Shatin N.T., HongKong
Wai-Kuen Cham , The Chinese University of Hong Kong, The Chinese University of Hong Kong, Shatin N.T., HongKong
Renqi Zhang , The Chinese University of Hong Kong, The Chinese University of Hong Kong, Shatin N.T., HongKong
pp. 3050-3057

One-shot multi-set non-rigid feature-spatial matching (Abstract)

Marwan Torki , Department of Computer Science, Rutgers University, New Brunswick, NJ, USA
Ahmed Elgammal , Department of Computer Science, Rutgers University, New Brunswick, NJ, USA
pp. 3058-3065

Relaxing the 3L algorithm for an accurate implicit polynomial fitting (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. 3066-3072

Online visual vocabulary pruning using pairwise constraints (Abstract)

Anil K. Jain , Dept. Computer Science and Engineering, Michigan St. Univ., East Lansing, MI-48824
Pavan K. Mallapragada , Dept. Computer Science and Engineering, Michigan St. Univ., East Lansing, MI-48824
Rong Jin , Dept. Computer Science and Engineering, Michigan St. Univ., East Lansing, MI-48824
pp. 3073-3080

Safety in numbers: Learning categories from few examples with multi model knowledge transfer (Abstract)

Francesco Orabona , DSI, Universita' degli Studi di Milano, Milan IT
Tatiana Tommasi , Idiap Research Institute, Martigny CH
Barbara Caputo , Idiap Research Institute, Martigny CH
pp. 3081-3088

Rapid and accurate developmental stage recognition of C. elegans from high-throughput image data (Abstract)

Huey-Ling Kao , Center for Genomics and Systems Biology and Department of Biology, New York University, New York, NY, USA
Brandon Lees , Center for Genomics and Systems Biology and Department of Biology, New York University, New York, NY, USA
Amelia G. White , Center for Genomics and Systems Biology and Department of Biology, New York University, New York, NY, USA
Eduardo Sontag , BioMaPS Institute, Rutgers University, Piscataway, NJ, USA
Kristin C. Gunsalus , Center for Genomics and Systems Biology and Department of Biology, New York University, New York, NY, USA
Patricia G. Cipriani , Center for Genomics and Systems Biology and Department of Biology, New York University, New York, NY, USA
Davi Geiger , Department of Computer Science, New York University, New York, NY, USA
Fabio Piano , Center for Genomics and Systems Biology and Department of Biology, New York University, New York, NY, USA
pp. 3089-3096

Tiered scene labeling with dynamic programming (Abstract)

Pedro F. Felzenszwalb , University of Chicago
Olga Veksler , University of Western Ontario
pp. 3097-3104

Segmentation of building facades using procedural shape priors (Abstract)

Panagiotis Koutsourakis , Laboratoire MAS, Ecole Centrale Paris
Olivier Teboul , Laboratoire MAS, Ecole Centrale Paris
Loic Simon , Laboratoire MAS, Ecole Centrale Paris
Nikos Paragios , Laboratoire MAS, Ecole Centrale Paris
pp. 3105-3112

Layered object detection for multi-class segmentation (Abstract)

Charless Fowlkes , Dept. of Computer Science, University of California, Irvine
Deva Ramanan , Dept. of Computer Science, University of California, Irvine
Sam Hallman , Dept. of Computer Science, University of California, Irvine
Yi Yang , Dept. of Computer Science, University of California, Irvine
pp. 3113-3120

Rectification of figures and photos in document images using bounding box interface (Abstract)

Hyung Il Koo , Department of EECS, INMC, Seoul National University, Seoul, 151-742, Korea
Nam Ik Cho , Department of EECS, INMC, Seoul National University, Seoul, 151-742, Korea
pp. 3121-3128

Geodesic star convexity for interactive image segmentation (Abstract)

Varun Gulshan , Dept. of Engineering Science, University of Oxford, UK
Andrew Blake , Microsoft Research Ltd. Cambridge, UK
Andrew Zisserman , Dept. of Engineering Science, University of Oxford, UK
Antonio Criminisi , Microsoft Research Ltd. Cambridge, UK
Carsten Rother , Microsoft Research Ltd. Cambridge, UK
pp. 3129-3136

Figure-ground segmentation improves handled object recognition in egocentric video (Abstract)

Xiaofeng Ren , Intel Labs Seattle, 1100 NE 45th Street, Seattle, WA 98105
Chunhui Gu , University of California at Berkeley, Berkeley, CA 94720
pp. 3137-3144

Learning kernels for variants of normalized cuts: Convex relaxations and applications (Abstract)

Chris Hinrichs , Univ. of Wisconsin-Madison
Vikas Singh , Univ. of Wisconsin-Madison
Lopamudra Mukherjee , Univ. of Wisconsin-Whitewater
Jiming Peng , Univ. of Illinois at Urbana Champaign
pp. 3145-3152

Globally optimal pixel labeling algorithms for tree metrics (Abstract)

Pedro F. Felzenszwalb , University of Chicago
Eva Tardos , Cornell University
Gyula Pap , Cornell University
Ramin Zabih , Cornell University
pp. 3153-3160

Geodesic graph cut for interactive image segmentation (Abstract)

Bryan Morse , Brigham Young University
Brian L. Price , Brigham Young University
Scott Cohen , Adobe Systems
pp. 3161-3168

iCoseg: Interactive co-segmentation with intelligent scribble guidance (Abstract)

Devi Parikh , Toyota Technological Institute at Chicago (TTIC)
Jiebo Luo , Eastman Kodak Company
Dhruv Batra , Carnegie Mellon Univerity
Adarsh Kowdle , Cornell University
Tsuhan Chen , Cornell University
pp. 3169-3176

Variational segmentation of elongated volumetric structures (Abstract)

Christian Reinbacher , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Christian Bauer , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Horst Bischof , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Thomas Pock , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
pp. 3177-3184

Collect-cut: Segmentation with top-down cues discovered in multi-object images (Abstract)

Kristen Grauman , University of Texas at Austin
Yong Jae Lee , University of Texas at Austin
pp. 3185-3192

Authority-shift clustering: Hierarchical clustering by authority seeking on graphs (Abstract)

Kyoung MuLee , Department of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
Minsu Cho , Department of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
pp. 3193-3200

Nonparametric higher-order learning for interactive segmentation (Abstract)

Kyoung Mu Lee , Dept. of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
Sang Uk Lee , Dept. of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
Tae Hoon Kim , Dept. of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea
pp. 3201-3208

GPCA with denoising: A moments-based convex approach (Abstract)

Necmiye Ozay , ECE Department, Northeastern University, Boston, MA 02115
Octavia Camps , ECE Department, Northeastern University, Boston, MA 02115
Constantino Lagoa , Department of EE, Penn State University, University Park, PA 16802
Mario Sznaier , ECE Department, Northeastern University, Boston, MA 02115
pp. 3209-3216

Efficiently selecting regions for scene understanding (Abstract)

Daphne Koller , Computer Science Department, Stanford University
M. Pawan Kumar , Computer Science Department, Stanford University
pp. 3217-3224

Finding image distributions on active curves (Abstract)

Ismail Ben Ayed , GE Healthcare, London, ON, Canada
Mohamed Ben Salah , Institut National de la Recherche Scientifique, INRS-EMT, Montreal, QC, Canada
Amar Mitiche , Institut National de la Recherche Scientifique, INRS-EMT, Montreal, QC, Canada
Shuo Li , GE Healthcare, London, ON, Canada
pp. 3225-3232

A shape-driven MRF model for the segmentation of organs in medical images (Abstract)

D. R. Chittajallu , Computational Biomedicine Lab, Depts. of Computer Science, Elec. & Comp. Engineering, and Biomedical Engineering, Univ. of Houston, Houston, TX, USA
S. K. Shah , Computational Biomedicine Lab, Depts. of Computer Science, Elec. & Comp. Engineering, and Biomedical Engineering, Univ. of Houston, Houston, TX, USA
I. A. Kakadiaris , Computational Biomedicine Lab, Depts. of Computer Science, Elec. & Comp. Engineering, and Biomedical Engineering, Univ. of Houston, Houston, TX, USA
pp. 3233-3240

Constrained parametric min-cuts for automatic object segmentation (Abstract)

Cristian Sminchisescu , Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn
Joao Carreira , Computer Vision and Machine Learning Group, Institute for Numerical Simulation, Faculty of Mathematics and Natural Sciences, University of Bonn
pp. 3241-3248

Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning (Abstract)

Joachim M. Buhmann , ETH Zurich 8092 Zurich, Switzerland
Alexander Vezhnevets , ETH Zurich 8092 Zurich, Switzerland
pp. 3249-3256

Fast global optimization of curvature (Abstract)

Noha Youssry El-Zehiry , Siemens Corporate Research, Princeton, NJ
Leo Grady , Siemens Corporate Research, Princeton, NJ
pp. 3257-3264

Label propagation in video sequences (Abstract)

Roberto Cipolla , University of Cambridge, UK
Fabio Galasso , University of Cambridge, UK
Vijay Badrinarayanan , University of Cambridge, UK
pp. 3265-3272

Vessel scale-selection using MRF optimization (Abstract)

Ghassan Hamarneh , Medical Image Analysis Lab, Simon Fraser University, BC, Canada
Hengameh Mirzaalian , Medical Image Analysis Lab, Simon Fraser University, BC, Canada
pp. 3273-3279

Harmony potentials for joint classification and segmentation (Abstract)

Joost van de Weijer , Centre de Visi´o per Computador
Xavier Boix , Centre de Visi´o per Computador
Jordi Gonzalez , Centre de Visi´o per Computador
Joan Serrat , Centre de Visi´o per Computador
Josep M. Gonfaus , Centre de Visi´o per Computador
Andrew D. Bagdanov , Centre de Visi´o per Computador
pp. 3280-3287

Graph cut segmentation with a global constraint: Recovering region distribution via a bound of the Bhattacharyya measure (Abstract)

Ian Ross , University of Western Ontario, London, ON, Canada
Ismail Ben Ayed , GE Healthcare, London, ON, Canada
Kumaradevan Punithakumar , GE Healthcare, London, ON, Canada
Hua-mei Chen , University of Western Ontario, London, ON, Canada
Shuo Li , GE Healthcare, London, ON, Canada
pp. 3288-3295

Interest seam image (Abstract)

Xiao Zhang , Tsinghua University
Gang Hua , Nokia Research
Lei Zhang , Microsoft Corporation
Heung-Yeung Shum , Microsoft Corporation
pp. 3296-3303

Aggregating local descriptors into a compact image representation (Abstract)

Herve Jegou , INRIA Rennes
Cordelia Schmid , INRIA Grenoble
Matthijs Douze , INRIA Grenoble
Patrick Perez , Technicolor
pp. 3304-3311

Automatic image annotation using group sparsity (Abstract)

Dimitris N. Metaxas , Department of Computer Science, Rutgers University, Piscataway, NJ, 08854
Yang Yu , Department of Computer Science, Rutgers University, Piscataway, NJ, 08854
Hongsheng Li , Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA, 18015
Shaoting Zhang , Department of Computer Science, Rutgers University, Piscataway, NJ, 08854
Junzhou Huang , Department of Computer Science, Rutgers University, Piscataway, NJ, 08854
Yuchi Huang , Department of Computer Science, Rutgers University, Piscataway, NJ, 08854
pp. 3312-3319

Nonparametric Label-to-Region by search (Abstract)

Hai Jin , Huazhong University of Science and Technology, China
Zhongyang Huango , Panasonic Singapore Laboratories Pte Ltd, Singapore
Jinhui Tang , National University of Singapore, Singapore
Shuicheng Yan , National University of Singapore, Singapore
Xiaobai Liu , Huazhong University of Science and Technology, China
Jiebo Luo , Kodak Research Laboratories, Eastman Kodak Company, Rochester, USA
pp. 3320-3327

CRAM: Compact representation of actions in movies (Abstract)

Mikel Rodriguez , Computer Vision Lab, University of Central Florida. Orlando, FL
pp. 3328-3335

Building and using a semantivisual image hierarchy (Abstract)

Li-Jia Li , Computer Science Department, Stanford University, Stanford, CA 94305
Yongwhan Lim , Computer Science Department, Stanford University, Stanford, CA 94305
Chong Wang , Computer Science Department, Princeton University, Princeton, NJ 08540
David M. Blei , Computer Science Department, Princeton University, Princeton, NJ 08540
Li Fei-Fei , Computer Science Department, Stanford University, Stanford, CA 94305
pp. 3336-3343

Weakly-supervised hashing in kernel space (Abstract)

Jialie Shen , Singapore Management University
Yadong Mu , National University of Singapore
Shuicheng Yan , National University of Singapore
pp. 3344-3351

Spatial-bag-of-features (Abstract)

Lei Zhang , Microsoft Research Asia, Beijing, China
Changhu Wang , Microsoft Research Asia, Beijing, China
Yang Cao , MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems, Shanghai Jiao Tong University
Zhiwei Li , Microsoft Research Asia, Beijing, China
Liqing Zhang , MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems, Shanghai Jiao Tong University
pp. 3352-3359

Locality-constrained Linear Coding for image classification (Abstract)

Jinjun Wang , Akiira Media System, Palo Alto, California
Kai Yu , NEC Laboratories America, Inc., Cupertino, California
Fengjun Lv , NEC Laboratories America, Inc., Cupertino, California
Yihong Gong , Akiira Media System, Palo Alto, California
Thomas Huang , Beckman Institute, University of Illinois at Urbana-Champaign
Jianchao Yang , Beckman Institute, University of Illinois at Urbana-Champaign
pp. 3360-3367

Semantic context modeling with maximal margin Conditional Random Fields for automatic image annotation (Abstract)

Zuotao Liu , Fudan Unviersity Shanghai, China
Yu Xiang , Fudan Unviersity Shanghai, China
Chong-Wah Ngo , City University, HongKong, China
Xiangdong Zhou , Fudan Unviersity Shanghai, China
Tat-Seng Chua , National University, Singapore
pp. 3368-3375

Image retrieval via probabilistic hypergraph ranking (Abstract)

Dimitris N. Metaxas , Rutgers University 617 Bowser Road, Piscataway, NJ 08854
Shaoting Zhang , Rutgers University 617 Bowser Road, Piscataway, NJ 08854
Yuchi Huang , Rutgers University 617 Bowser Road, Piscataway, NJ 08854
Qingshan Liu , Rutgers University 617 Bowser Road, Piscataway, NJ 08854
pp. 3376-3383

Large-scale image retrieval with compressed Fisher vectors (Abstract)

Yan Liu , Xerox Research Centre Europe (XRCE)
Herve Poirier , Xerox Research Centre Europe (XRCE)
Florent Perronnin , Xerox Research Centre Europe (XRCE)
Jorge Sanchez , Xerox Research Centre Europe (XRCE)
pp. 3384-3391

Optimizing kd-trees for scalable visual descriptor indexing (Abstract)

Hongbin Zha , Key Laboratory of Machine Perception, Peking University
Xian-Sheng Hua , Microsoft Research Asia
Jingdong Wang , Microsoft Research Asia
You Jia , Key Laboratory of Machine Perception, Peking University
Gang Zeng , Key Laboratory of Machine Perception, Peking University
pp. 3392-3399

Content-aware Ranking for visual search (Abstract)

Bo Gengti , Key Laboratory of Machine Perception ( Ministry of Education ), Peking University, Beijing, 100871
Linjun Yang , Microsoft Research Asia, Beijing, 100190
Chao Xu , Key Laboratory of Machine Perception ( Ministry of Education ), Peking University, Beijing, 100871
Xian-Sheng Hua , Microsoft Research Asia, Beijing, 100190
pp. 3400-3407

Topic regression multi-modal Latent Dirichlet Allocation for image annotation (Abstract)

Srikantan S. Nagarajan , UCSF, 513 Parnassus Avenue, San Francisco, CA 94143
Duangmanee Putthividhy , UCSD, 9500 Gilman Drive, La Jolla, CA 92307
Hagai T. Attias , Golden Metallic, Inc., P. O. Box 475608, San Francisco, CA 91147
pp. 3408-3415

Unsupervised discovery of co-occurrence in sparse high dimensional data (Abstract)

Ondrej Chum , CMP, Dept. of Cybernetics, Faculty of Elec. Eng., Czech Technical University in Prague
Jiri Matas , CMP, Dept. of Cybernetics, Faculty of Elec. Eng., Czech Technical University in Prague
pp. 3416-3423

Semi-supervised hashing for scalable image retrieval (Abstract)

Jun Wang , Columbia University New York, NY, 10027
Sanjiv Kumar , Google Research, New York, NY, 10011
Shih-Fu Chang , Columbia University New York, NY, 10027
pp. 3424-3431

Image webs: Computing and exploiting connectivity in image collections (Abstract)

Natasha Gelfand , Nokia Research - Palo Alto, CA
Maks Ovsjanikov , Stanford University
Kyle Heath , Stanford University
Mridul Aanjaneya , Stanford University
Leonidas J. Guibas , Stanford University
pp. 3432-3439

Tag-based web photo retrieval improved by batch mode re-tagging (Abstract)

Jiebo Luo , Kodak Research Laboratories, Eastiman Kodak Company, Rochester, USA
Dong Xu , School of Computer Engineering, Nanyang Technologicial University, Singapore
Ivor W. Tsang , School of Computer Engineering, Nanyang Technologicial University, Singapore
Lin Chen , School of Computer Engineering, Nanyang Technologicial University, Singapore
pp. 3440-3446

Finding meaning on YouTube: Tag recommendation and category discovery (Abstract)

George Toderici , Google Inc., 1600 Amphitheatre Parkway, Mountain View, California 94043
Jay Yagnik , Google Inc., 1600 Amphitheatre Parkway, Mountain View, California 94043
Luciano Sbaiz , Google Inc., 1600 Amphitheatre Parkway, Mountain View, California 94043
Hrishikesh Aradhye , Google Inc., 1600 Amphitheatre Parkway, Mountain View, California 94043
Marius Pasca , Google Inc., 1600 Amphitheatre Parkway, Mountain View, California 94043
pp. 3447-3454

Discovering scene categories by information projection and cluster sampling (Abstract)

Dengxin Dai , Lotus Hill Res. Inst. (LHI), Ezhou, China
Tianfu Wu , Dept. of Stat., Univ. of California, Los Angeles (UCLA), Los Angeles, CA, USA
Song-Chun Zhu , Dept. of Stat., Univ. of California, Los Angeles (UCLA), Los Angeles, CA, USA
pp. 3455-3462
Papers

Scalable face image retrieval with identity-based quantization and multi-reference re-ranking (Abstract)

Qifa Ke , Microsoft Research Silicon Valley Lab
Heung-Yeung Shum , Microsoft Corporation
Zhong Wu , Tsinghua Univ., Ctr Adv Study
Jian Sun , Microsoft Research Asia Lab
pp. 3469-3476

Compact projection: Simple and efficient near neighbor search with practical memory requirements (Abstract)

Linjun Yang , Microsoft Research Asia
Yi Ma , Microsoft Research Asia
Kerui Min , School of Computer Science, Fudan University
Xian-Sheng Hua , Microsoft Research Asia
John Wright , Microsoft Research Asia
Lei Wu , Microsoft Research Asia
pp. 3477-3484

SUN database: Large-scale scene recognition from abbey to zoo (Abstract)

Aude Oliva , Massachusetts Institute of Technology
Krista A. Ehinger , Massachusetts Institute of Technology
Antonio Torralba , Massachusetts Institute of Technology
James Hays , Brown University
Jianxiong Xiao , Massachusetts Institute of Technology
pp. 3485-3492

Visual classification with multi-task joint sparse representation (Abstract)

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
pp. 3493-3500

Classification and clustering via dictionary learning with structured incoherence and shared features (Abstract)

Ignacio Ramirez , Electrical and Computer Engineering, University of Minnesota
Pablo Sprechmann , Electrical and Computer Engineering, University of Minnesota
Guillermo Sapiro , Electrical and Computer Engineering, University of Minnesota
pp. 3501-3508

The automatic design of feature spaces for local image descriptors using an ensemble of non-linear feature extractors (Abstract)

Gustavo Carneiro , Instituto de Sistemas e Robótica, Instituto Superior Técnico, Lisbon, Portugal
pp. 3509-3516

Supervised translation-invariant sparse coding (Abstract)

Kai Yu , NEC Laboratories America, Inc., Cupertino, California
Thomas Huang , Beckman Institute, University of Illinois at Urbana-Champaign
Jianchao Yang , Beckman Institute, University of Illinois at Urbana-Champaign
pp. 3517-3524

Comparative object similarity for improved recognition with few or no examples (Abstract)

David Forsyth , Dept. of Computer Science University of Illinois Urbana-Champaign (UIUC)
Gang Wang , Dept. of Electrical and Computer Engineering University of Illinois Urbana-Champaign (UIUC)
Derek Hoiem , Dept. of Computer Science University of Illinois Urbana-Champaign (UIUC)
pp. 3525-3532

Bayes optimal kernel discriminant analysis (Abstract)

Aleix M. Martinez , Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH 43210, USA
Di You , Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH 43210, USA
pp. 3533-3538

Efficient additive kernels via explicit feature maps (Abstract)

Andrew Zisserman , Dept. of Engineering Science, University of Oxford, UK
Andrea Vedaldi , Dept. of Engineering Science, University of Oxford, UK
pp. 3539-3546

Data driven mean-shift belief propagation for non-gaussian MRFs (Abstract)

Somesh Kashyap , Department of Electrical Engineering The Pennsylvania State University
Yanxi Liu , Department of Computer Science and Engineering The Pennsylvania State University
Minwoo Park , Department of Computer Science and Engineering The Pennsylvania State University
Robert T Collins , Department of Computer Science and Engineering The Pennsylvania State University
pp. 3547-3554

Local features are not lonely – Laplacian sparse coding for image classification (Abstract)

Ivor Wai-Hung Tsang , School of Computer Engineering, Nanyang Technological University, Singapore
Peilin Zhao , School of Computer Engineering, Nanyang Technological University, Singapore
Liang-Tien Chia , School of Computer Engineering, Nanyang Technological University, Singapore
Shenghua Gao , School of Computer Engineering, Nanyang Technological University, Singapore
pp. 3555-3561

Factorization towards a classifier (Abstract)

Tian-Tsong Ng , Computer Vision and Image Understanding Department, Institute for Infocomm Research, Singapore
Shuicheng Yan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Qiang Chen , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
pp. 3562-3569

Online multi-class LPBoost (Abstract)

Amir Saffari , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Thomas Pock , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Horst Bischof , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Martin Godec , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
Christian Leistner , Institute for Computer Graphics and Vision, Graz University of Technology, Austria
pp. 3570-3577

Sparse representation using nonnegative curds and whey (Abstract)

Shuicheng Yan , Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Fei Wu , College of Computer Science and Technology, Zhejiang University, China
Yueting Zhuang , College of Computer Science and Technology, Zhejiang University, China
Yanan Liu , College of Computer Science and Technology, Zhejiang University, China
Zhihua Zhang , College of Computer Science and Technology, Zhejiang University, China
pp. 3578-3585

Multi-structure model selection via kernel optimisation (Abstract)

Tat-Jun Chin , School of Computer Science, The University of Adelaide, South Australia
Hanzi Wang , School of Computer Science, The University of Adelaide, South Australia
David Suter , School of Computer Science, The University of Adelaide, South Australia
pp. 3586-3593

Data fusion through cross-modality metric learning using similarity-sensitive hashing (Abstract)

Alexander M. Bronstein , Department of Computer Science, Technion - Israel Institute of Technology, Haifa 32000, Israel
Nikos Paragios , Laboratoire de Mathématiques Appliquées aux Systèmes, École Centrale de Paris, France
Michael M. Bronstein , Department of Computer Science, Technion - Israel Institute of Technology, Haifa 32000, Israel
Fabrice Michel , Laboratoire de Mathématiques Appliquées aux Systèmes, École Centrale de Paris, France
pp. 3594-3601

Pareto discriminant analysis (Abstract)

Fernando de la Torre , The Robotics Institute, Carnegie Mellon University
Karim T. Abou-Moustafa , Centre of Intelligent Machines, McGill University
Frank P. Ferrie , Centre of Intelligent Machines, McGill University
pp. 3602-3609

Fast sparse representation with prototypes (Abstract)

Jia-Bin Huang , University of California at Merced
Ming-Hsuan Yang , University of California at Merced
pp. 3618-3625

l<inf>p</inf> norm multiple kernel Fisher discriminant analysis for object and image categorisation (Abstract)

Josef Kittler , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, GU2 7XH, UK
Fei Yan , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, GU2 7XH, UK
Hongping Cai , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, GU2 7XH, UK
Krystian Mikolajczyk , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, GU2 7XH, UK
Mark Barnard , Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, GU2 7XH, UK
pp. 3626-3632

Author Index (PDF)

pp. 1-120
92 ms
(Ver )