The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (2005)
San Diego, California
June 20, 2005 to June 26, 2005
ISSN: 1063-6919
ISBN: 0-7695-2372-2
TABLE OF CONTENTS
Introduction

Preface (PDF)

pp. xxiv,xxv,xxvi,xxvii,xxviii

Program Committee (PDF)

pp. xxxi-xxxiii
Session 5.1: Tracking

Particle Filtering for Geometric Active Contours with Application to Tracking Moving and Deforming Objects (Abstract)

Namrata Vaswani , Georgia Institute of Technology
Allen Tannenbaum , Georgia Institute of Technology
Anthony Yezzi , Georgia Institute of Technology
Yogesh Rathi , Georgia Institute of Technology
pp. 2-9

Illumination-Invariant Tracking via Graph Cuts (Abstract)

Matthew W. Turek , Rensselaer Polytechnic Institute
Daniel Freedman , Rensselaer Polytechnic Institute
pp. 10-17

Visual Tracking in the Presence of Motion Blur (Abstract)

Roberto Cipolla , University of Cambridge
Paolo Favaro , Siemens Corporate Research
Hailin Jin , Adobe Systems Incorporated
pp. 18-25

Appearance Modeling for Tracking in Multiple Non-Overlapping Cameras (Abstract)

Mubarak Shah , University of Central Florida
Omar Javed , University of Central Florida
Khurram Shafique , University of Central Florida
pp. 26-33

Real-Time Tracking Using Level Sets (Abstract)

W. Clem Karl , Boston University
Yonggang Shi , Boston University
pp. 34-41
Session 5.2: Image Processing and Modeling

Addressing Radiometric Nonidealities: A Unified Framework (Abstract)

Yoav Y. Schechner , Technion - Israel Institute of Technology
Anatoly Litvinov , Technion - Israel Institute of Technology
pp. 52-59

Determining the Radiometric Response Function from a Single Grayscale Image (Abstract)

Lei Zhang , Peking University
Stephen Lin , Microsoft Research Asia
pp. 66-73

A Generative Model of Human Hair for Hair Sketching (Abstract)

Hong Chen , University of California at Los Angeles
Song Chun Zhu , University of California at Los Angeles
pp. 74-81
Poster Session 4

Active Polyhedron: Surface Evolution Theory Applied to Deformable Meshes (Abstract)

Gozde Unal , Siemens Corporate Research
Greg Slabaugh , Siemens Corporate Research
pp. 84-91

Corrected Laplacians: Closer Cuts and Segmentation with Shape Priors (Abstract)

Robert T. Collins , Carnegie Mellon University
David Tolliver , Carnegie Mellon University
Gary L. Miller , Carnegie Mellon University
pp. 92-98

Simultaneous Modeling and Tracking (SMAT) of Feature Sets (Abstract)

N. D. H. Dowson , University of Surrey
R. Bowden , University of Surrey
pp. 99-105

Combining Object and Feature Dynamics in Probabilistic Tracking (Abstract)

Leonid Taycher , Massachusetts Institute of Technology
Trevor Darrell , Massachusetts Institute of Technology
John W. Fisher III , Massachusetts Institute of Technology
pp. 106-113

Localization in Urban Environments: Monocular Vision Compared to a Differential GPS Sensor (Abstract)

Thierry Chateau , LASMEA, UMR6602 CNRS and Blaise Pascal University
Maxime Lhuillier , LASMEA, UMR6602 CNRS and Blaise Pascal University
Eric Royer , LASMEA, UMR6602 CNRS and Blaise Pascal University
Michel Dhome , LASMEA, UMR6602 CNRS and Blaise Pascal University
pp. 114-121

A Direct Method for 3D Factorization of Nonrigid Motion Observed in 2D (Abstract)

Matthew Brand , Mitsubishi Electric Research Labs
pp. 122-128

Full Body Tracking from Multiple Views Using Stochastic Sampling (Abstract)

Roland Kehl , ETH Zuerich
Matthieu Bray , ETH Zuerich and Oxford Brookes University
Luc Van Gool , ETH Zuerich and University of Leuven
pp. 129-136

Automatic 3D to 2D Registration for the Photorealistic Rendering of Urban Scenes (Abstract)

Lingyun Liu , City University of New York
Ioannis Stamos , City University of New York
pp. 137-143

Jensen-Shannon Boosting Learning for Object Recognition (Abstract)

Stan Z. Li , Chinese Academy of Science
Yangsheng Wang , Chinese Academy of Science
Xiangsheng Huang , Chinese Academy of Science
pp. 144-149

WaldBoost — Learning for Time Constrained Sequential Detection (Abstract)

Jiří Matas , Czech Technical University in Prague
Jan Šochman , Czech Technical University in Prague
pp. 150-156

Discriminative Training for Object Recognition Using Image Patches (Abstract)

Hermann Ney , RWTH Aachen University
Daniel Keysers , RWTH Aachen University
Thomas Deselaers , RWTH Aachen University
pp. 157-162

Formulating Semantic Image Annotation as a Supervised Learning Problem (Abstract)

Nuno Vasconcelos , University of California at San Diego
Gustavo Carneiro , University of British Columbia and University of California at San Diego
pp. 163-168

Discriminative Learning of Markov Random Fields for Segmentation of 3D Scan Data (Abstract)

Geremy Heitz , Stanford University
Andrew Ng , Stanford University
Dragomir Anguelov , Stanford University
Daphne Koller , Stanford University
Dinkar Gupta , Stanford University
Ben Taskar , University of California at Berkeley
Vassil Chatalbashev , Stanford University
pp. 169-176

Feature Kernel Functions: Improving SVMs Using High-Level Knowledge (Abstract)

Gerald DeJong , University of Illinois at Urbana-Champaign
Qiang Sun , University of Illinois at Urbana-Champaign
pp. 177-183

Coherent Regions for Concise and Stable Image Description (Abstract)

Jason J. Corso , Johns Hopkins University
Gregory D. Hager , Johns Hopkins University
pp. 184-190

Diagram Structure Recognition by Bayesian Conditional Random Fields (Abstract)

Yuan Qi , Massachusetts Institute of Technology
Thomas P. Minka , Microsoft Research
Martin Szummer , Microsoft Research
pp. 191-196

Fisher+Kernel Criterion for Discriminant Analysis (Abstract)

Chao Zhang , Peking University
Xiaoou Tang , Chinese University of Hong Kong and Microsoft Research Asia
Shu Yang , Peking University
Shuicheng Yan , Chinese University of Hong Kong
Dong Xu , University of Science and Technology of China
pp. 197-202

Concurrent Subspaces Analysis (Abstract)

Shuicheng Yan , Chinese University of Hong Kong
Dong Xu , University of Science and Technology of China and Microsoft Research Asia
Lei Zhang , Microsoft Research Asia
Hong-Jiang Zhang , Microsoft Research Asia
Zhengkai Liu , University of Science and Technology of China
Heung-Yeung Shum , Microsoft Research Asia
pp. 203-208

Face Synthesis and Recognition from a Single Image under Arbitrary Unknown Lighting Using a Spherical Harmonic Basis Morphable Model (Abstract)

Lei Zhang , State University of New York at Stony Brook
Dimitris Samaras , State University of New York at Stony Brook
Sen Wang , State University of New York at Stony Brook
pp. 209-216

A Unified Optimization Based Learning Method for Image Retrieval (Abstract)

Wei-Ying Ma , Microsoft Research Asia
Jingrui He , Tsinghua University
Hong-Jiang Zhang , Microsoft Research Asia
Mingjing Li , Microsoft Research Asia
Changshui Zhang , Tsinghua University
Hanghang Tong , Tsinghua University
pp. 230-235

Robust Object Detection via Soft Cascade (Abstract)

Jonathan Brandt , Adobe Systems Inc.
Lubomir Bourdev , Adobe Systems Inc.
pp. 236-243

Mapping Low-Level Features to High-Level Semantic Concepts in Region-Based Image Retrieval (Abstract)

Wei Jiang , Tsinghua University
Mingjing Li , Microsoft Research Asia
Hongjiang Zhang , Microsoft Research Asia
Kap Luk Chan , Nanyang Technology University
pp. 244-249

Estimating Disparity and Occlusions in Stereo Video Sequences (Abstract)

Oliver Williams , University of Cambridge
Michael Isard , Microsoft Research
John MacCormick , Microsoft Research
pp. 250-257

Representational Oriented Component Analysis (ROCA) for Face Recognition with One Sample Image per Training Class (Abstract)

Fernando De la Torre , Carnegie Mellon University
B. V. K. Vijaya Kumar , Carnegie Mellon University
Ralph Gross , Carnegie Mellon University
Simon Baker , Carnegie Mellon University
pp. 266-273

Linear Combination Representation for Outlier Detection in Motion Tracking (Abstract)

Zhengyou Zhang , Microsoft Research
Charles R. Dyer , University of Wisconsin-Madison
Guodong Guo , University of Wisconsin-Madison
pp. 274-281

Integrated Learning of Saliency, Complex Features, and Object Detectors from Cluttered Scenes (Abstract)

Dashan Gao , University of California at San Diego
Nuno Vasconcelos , University of California at San Diego
pp. 282-287

Parameter Estimation for MRF Stereo (Abstract)

Li Zhang , University of Washington
Steven M. Seitz , University of Washington
pp. 288-295

The Distinctiveness, Detectability, and Robustness of Local Image Features (Abstract)

Allan D. Jepson , University of Toronto
Gustavo Carneiro , University of British Columbia
pp. 296-301

A Semi-Supervised Active Learning Framework for Image Retrieval (Abstract)

Steven C. H. Hoi , Chinese University of Hong Kong
Michael R. Lyu , Chinese University of Hong Kong
pp. 302-309

Optimal Sub-Shape Models by Minimum Description Length (Abstract)

Philipp Peloschek , Vienna Medical University
Georg Langs , Graz University of Technology and Vienna University of Technology
Horst Bischof , Graz University of Technology
pp. 310-315

Object Class Recognition Using Multiple Layer Boosting with Heterogeneous Features (Abstract)

Bing Yu , State University of New York at Stony Brook
Wei Zhang , State University of New York at Stony Brook
Dimitris Samaras , State University of New York at Stony Brook
Gregory J. Zelinsky , State University of New York at Stony Brook
pp. 323-330

Cerebral Vascular Atlas Generation for Anatomical Knowledge Modeling and Segmentation Purpose (Abstract)

J. Baruthio , Strasbourg I University
N. Passat , Strasbourg I University
C. Maillot , Strasbourg I University
C. Ronse , Strasbourg I University
J.-P. Armspach , Strasbourg I University
pp. 331-337

Flattening Curved Documents in Images (Abstract)

David Doermann , University of Maryland at College Park
Jian Liang , University of Maryland at College Park
Daniel DeMenthon , University of Maryland at College Park
pp. 338-345

Rank-R Approximation of Tensors: Using Image-as-Matrix Representation (Abstract)

Narendra Ahuja , University of Illinois at Urbana-Champaign
Hongcheng Wang , University of Illinois at Urbana-Champaign
pp. 346-353

Higher Order Whitening of Natural Images (Abstract)

Joshua Gluckman , Polytechnic University
pp. 354-360

Region Competition via Local Watershed Operators (Abstract)

Ferit Akova , Siemens Corporate Research
Hüseyin Tek , Siemens Corporate Research
Alper Ayvac? , Siemens Corporate Research
pp. 361-368

Contrast Enhancement of Multi-Displays Using Human Contrast Sensitivity (Abstract)

Aditi Majumder , University of California at Irvine
pp. 377-382
Session 6.1: Stereo

Stereo Correspondence by Dynamic Programming on a Tree (Abstract)

Olga Veksler , University of Western Ontario
pp. 384-390

Multi-View Stereo via Volumetric Graph-Cuts (Abstract)

R. Cipolla , University of Cambridge
G. Vogiatzis , University of Cambridge
P. H. S. Torr , Oxford Brookes University
pp. 391-398

Symmetric Stereo Matching for Occlusion Handling (Abstract)

Jian Sun , Microsoft Research Asia
Sing Bing Kang , Microsoft Research
Heung-Yeung Shum , Microsoft Research Asia
Yin Li , Microsoft Research Asia
pp. 399-406

Bi-Layer Segmentation of Binocular Stereo Video (Abstract)

A. Criminisi , Microsoft Research Ltd.
V. Kolmogorov , Microsoft Research Ltd.
C. Rother , Microsoft Research Ltd.
A. Blake , Microsoft Research Ltd.
G. Cross , Microsoft Research Ltd.
pp. 407-414
Session 6.2: Medical Imaging

Imaging the Cardiovascular Pulse (Abstract)

Arcangelo Merla , Università G. DéAnnunzio
Marc Garbey , University of Houston
Ioannis Pavlidis , University of Houston
Nanfei Sun , University of Houston
pp. 416-421

Top-Down and Bottom-Up Strategies in Lesion Detection of Background Diabetic Retinopathy (Abstract)

Xiaohui Zhang , Nanyang Technological University
Opas Chutatape , Nanyang Technological University
pp. 422-428

Database-Guided Segmentation of Anatomical Structures with Complex Appearance (Abstract)

A. Gupta , Siemens Medical Solutions
X. S. Zhou , Siemens Corporate Research
D. Comaniciu , Siemens Corporate Research
B. Georgescu , Siemens Corporate Research
pp. 429-436

Blob Segmentation Using Joint Space-Intensity Likelihood Ratio Test: Application to 3D Tumor Segmentation (Abstract)

Kazunori Okada , Siemens Corporate Research, Inc.
Arun Krishnan , Siemens Medical Solutions USA, Inc.
Umut Akdemir , Siemens Corporate Research, Inc.
pp. 437-444
Session 7.1: Faces

Face Recognition Based on Frontal Views Generated from Non-Frontal Images (Abstract)

Patrick Grother , National Institute of Standards and Technology
P. Jonathon Phillips , National Institute of Standards and Technology
Volker Blanz , Max-Planck-Institut für Informatik
Thomas Vetter , University of Basel
pp. 454-461

Face Verification across Age Progression (Abstract)

Narayanan Ramanathan , University of Maryland at College Park
Rama Chellappa , University of Maryland at College Park
pp. 462-469

A High Resolution Grammatical Model for Face Representation and Sketching (Abstract)

Zijian Xu , University of California at Los Angeles
Song-Chun Zhu , University of California at Los Angeles
Hong Chen , University of California at Los Angeles
pp. 470-477

Hallucinating Faces: TensorPatch Super-Resolution and Coupled Residue Compensation (Abstract)

Wei Liu , Chinese University of Hong Kong
Xiaoou Tang , Chinese University of Hong Kong and Microsoft Research Asia
Dahua Lin , Chinese University of Hong Kong
pp. 478-484
Session 7.2: Motion Segmentation and Tracking

Simultaneous Estimation of Segmentation and Shape (Abstract)

Nils Krahnstoever , General Electric Global Research
Peter H. Tu , General Electric Global Research
Jens Rittscher , General Electric Global Research
pp. 486-493

Ensemble Tracking (Abstract)

Shai Avidan , Mitsubishi Electric Research Labs
pp. 494-501

Multiple Collaborative Kernel Tracking (Abstract)

Ming Yang , Northwestern University
Ying Wu , Northwestern University
Zhimin Fan , Northwestern University
pp. 502-509

A Closed Form Solution to Direct Motion Segmentation (Abstract)

René Vidal , Johns Hopkins University
Dheeraj Singaraju , Johns Hopkins University
pp. 510-515

Optical Flow Estimation and Segmentation of Multiple Moving Dynamic Textures (Abstract)

Avinash Ravichandran , Johns Hopkins University
René Vidal , Johns Hopkins University
pp. 516-521
Poster Session 5

A Bayesian Hierarchical Model for Learning Natural Scene Categories (Abstract)

Pietro Perona , California Institute of Technology
Fei-Fei Li , California Institute of Technology
pp. 524-531

Illumination Normalization for Face Recognition and Uneven Background Correction Using Total Variation Based Image Models (Abstract)

Terrence Chen , University of Illinois at Urbana Champaign
Thomas S. Huang , University of Illinois at Urbana Champaign
Wotao Yin , Columbia University
Xiang Sean Zhou , Siemens Corporate Research
Dorin Comaniciu , Siemens Corporate Research
pp. 532-539

Speckle-Constrained Filtering of Ultrasound Images (Abstract)

Karl Krissian , Harvard Medical School
Ron Kikinis , Harvard Medical School
Carl-Fredrik Westin , Harvard Medical School
pp. 547-552

Learning Spatiotemporal T-Junctions for Occlusion Detection (Abstract)

Andrew Fitzgibbon , University of Oxford
Nicholas Apostoloff , University of Oxford
pp. 553-559

Learning Feature Distance Measures for Image Correspondences (Abstract)

Tat-Jen Cham , Nanyang Technological University and Singapore-MIT Alliance
Xi Chen , Nanyang Technological University
pp. 560-567

Recognizing Facial Expression: Machine Learning and Application to Spontaneous Behavior (Abstract)

Claudia Lainscsek , University of California at San Diego
Mark Frank , Rutgers University
Ian Fasel , University of California at San Diego
Marian Stewart Bartlett , University of California at San Diego
Gwen Littlewort , University of California at San Diego
Javier Movellan , University of California at San Diego
pp. 568-573

On the Small Sample Performance of Boosted Classifiers (Abstract)

Weiliang Li , Lehigh University
Visvanathan Ramesh , Siemens Corporate Research, Inc.
Terrance E. Boult , University of Colorado at Colorado Springs
Ying Zhu , Siemens Corporate Research, Inc.
Xiang Gao , Siemens Corporate Research, Inc.
pp. 574-581

ARTag, a Fiducial Marker System Using Digital Techniques (Abstract)

Mark Fiala , National Research Council of Canada
pp. 590-596

Multi-Output Regularized Projection (Abstract)

Shipeng Yu , University of Munich
Volker Tresp , Siemens AG
Kai Yu , Siemens AG
pp. 597-602

Statistical Cue Integration for Foveated Wide-Field Surveillance (Abstract)

Yuqian Hou , York University
Simon J. D. Prince , York University
Yevgen Olevskiy , York University
James H. Elder , York University
Mikhail Sizintsev , York University
pp. 603-610

Scene-Adapted Structured Light (Abstract)

Luc Van Gool , Katholieke Universiteit Leuven and Swiss Federal Institute of Technology
Thomas P. Koninckx , Katholieke Universiteit Leuven
Pieter Peers , Katholieke Universiteit Leuven
Philip Dutré , Katholieke Universiteit Leuven
pp. 611-618

Beyond Lambert: Reconstructing Specular Surfaces Using Color (Abstract)

Peter N. Belhumeur , Columbia University
David J. Kriegman , University of California at San Diego
Satya P. Mallick , University of California at San Diego
Todd E. Zickler , Harvard University
pp. 619-626

Efficient Image Matching with Distributions of Local Invariant Features (Abstract)

Trevor Darrell , Massachusetts Institute of Technology
Kristen Grauman , Massachusetts Institute of Technology
pp. 627-634

Detecting, Localizing and Recovering Kinematics of Textured Animals (Abstract)

Deva Ramanan , University of California at Berkeley
Kobus Barnard , University of Arizona
D. A. Forsyth , University of California at Berkeley
pp. 635-642

Isophote Properties as Features for Object Detection (Abstract)

Emile Hendriks , Delft University of Technology
Marcel Reinders , Delft University of Technology
Jeroen Lichtenauer , Delft University of Technology
pp. 649-654

Shape Regularized Active Contour Using Iterative Global Search and Local Optimization (Abstract)

Jiebo Luo , Eastman Kodak Company
Tianli Yu , University of Illinois at Urbana-Champaign
Narendra Ahuja , University of Illinois at Urbana-Champaign
pp. 655-662

Integration of Motion Fields through Shape (Abstract)

Hui Ji , University of Maryland at College Park
Cornelia Fermüller , University of Maryland at College Park
pp. 663-669

Learning a Multi-Size Patch-Based Hybrid Kernel Machine Ensemble for Abnormal Region Detection in Colonoscopic Images (Abstract)

S. M. Krishnan , Nanyang Technological University
Peng Li , Nanyang Technological University
Kap Luk Chan , Nanyang Technological University
pp. 670-675

Two-View Multibody Structure-and-Motion with Outliers (Abstract)

David Suter , Monash University
Konrad Schindler , Monash University
pp. 676-683

Probabilistic Modeling-Based Vessel Enhancement in Thoracic CT Scans (Abstract)

Changhua Wu , Illinois Institute of Technology
Gady Agam , Illinois Institute of Technology
pp. 684-689

Level Set Active Contours on Unstructured Point Cloud (Abstract)

Hon Pong Ho , Hong Kong University of Science and Technology
Pengcheng Shi , Hong Kong University of Science and Technology
Yunmei Chen , University of Florida
Huafeng Liu , Hong Kong University of Science and Technology and Zhejiang University
pp. 690-697

Accurate Motion Layer Segmentation and Matting (Abstract)

Mubarak Shah , University of Central Florida
Jiangjian Xiao , University of Central Florida
pp. 698-703

Learning the Semantics of Images by Using Unlabeled Samples (Abstract)

Hangzai Luo , University of North Carolina at Charlotte
Yuli Gao , University of North Carolina at Charlotte
Jianping Fan , University of North Carolina at Charlotte
pp. 704-710

Object Detection Using 2D Spatial Ordering Constraints (Abstract)

Yakup Genc , Siemens Corporate Research
Takeo Kanade , Carnegie Mellon University
Yan Li , Carnegie Mellon University
Yanghai Tsin , Siemens Corporate Research
pp. 711-718

Using the Inner-Distance for Classification of Articulated Shapes (Abstract)

Haibin Ling , University of Maryland at College Park
David W. Jacobs , University of Maryland at College Park
pp. 719-726

Classification of Contour Shapes Using Class Segment Sets (Abstract)

Kang B. Sun , University of Illinois at Chicago
Boaz J. Super , University of Illinois at Chicago
pp. 727-733

Part-Based Statistical Models for Object Classification and Detection (Abstract)

Elliot Joel Bernstein , University of Chicago
Yali Amit , University of Chicago
pp. 734-740

A Bayesian Mixture Model for Multi-View Face Alignment (Abstract)

Harry Shum , Microsoft Research Asia
Wei Zhang , Tsinghua University
Xiaoou Tang , Microsoft Research Asia
Yi Zhou , Microsoft Research Asia
pp. 741-746

Learning to Estimate Human Pose with Data Driven Belief Propagation (Abstract)

Ying Wu , Northwestern University
Ming-Hsuan Yang , Honda Research Institute
Gang Hua , Northwestern University
pp. 747-754

Joint Nonparametric Alignment for Analyzing Spatial Gene Expression Patterns in Drosophila Imaginal Discs (Abstract)

Ann Hammonds , University of California at Berkeley
Cyrus L. Harmon , University of California at Berkeley
Parvez Ahammad , University of California at Berkeley
S. Shankar Sastry , University of California at Berkeley
Gerald M. Rubin , Howard Hughes Medical Institute and University of California at Berkeley
pp. 755-760

Vehicle Fingerprinting for Reacquisition and Tracking in Videos (Abstract)

Harpreet Sawhney , Sarnoff Corporation
Yanlin Guo , Sarnoff Corporation
Ying Shan , Sarnoff Corporation
Rakesh Kumar , Sarnoff Corporation
Steve Hsu , Sarnoff Corporation
pp. 761-768

Fast Spatial Pattern Discovery Integrating Boosting with Constellations of Contextual Descriptors (Abstract)

Petia Radeva , Universitat Autonoma de Barcelona
Nicu Sebe , University of Amsterdam
Jaume Amores , Universitat Autonoma de Barcelona
pp. 769-774

Randomized Trees for Real-Time Keypoint Recognition (Abstract)

Pascal Fua , École Polytechnique Fédérale de Lausanne
Vincent Lepetit , École Polytechnique Fédérale de Lausanne
Pascal Lagger , École Polytechnique Fédérale de Lausanne
pp. 775-781

Skeletal Parameter Estimation from Optical Motion Capture Data (Abstract)

Adam G. Kirk , University of California at Berkeley
David A. Forsyth , University of California at Berkeley
James F. O?Brien , University of California at Berkeley
pp. 782-788

A Minimal Solution for Relative Pose with Unknown Focal Length (Abstract)

Fredrik Kahl , University of California at San Diego
Henrik Stewénius , Lund University
David Nistér , University of Kentucky
Frederik Schaffalitzky , University of Oxford
pp. 789-794

Combining Variable Selection with Dimensionality Reduction (Abstract)

Stan Bileschi , Massachusetts Institute of Technology
Lior Wolf , Massachusetts Institute of Technology
pp. 801-806

A Factorization-Based Approach to Articulated Motion Recovery (Abstract)

Jingyu Yan , University of North Carolina at Chapel Hill
Marc Pollefeys , University of North Carolina at Chapel Hill
pp. 815-821
Session 8.1: Learning

Graph Embedding: A General Framework for Dimensionality Reduction (Abstract)

Shuicheng Yan , Chinese University of Hong Kong
Hong-Jiang Zhang , Microsoft Research Asia
Benyu Zhang , Microsoft Research Asia
Dong Xu , University of Science and Technology of China
pp. 830-837

Beyond Pairwise Clustering (Abstract)

Lihi Zelnik-Manor , California Institute of Technology
Jongwoo Lim , University of California at San Diego
Pietro Perona , California Institute of Technology
Serge Belongie , University of California at San Diego
Sameer Agarwal , University of California at San Diego
David Kriegman , University of California at San Diego
pp. 838-845

Local Discriminant Embedding and Its Variants (Abstract)

Tyng-Luh Liu , Academia Sinica
Hwann-Tzong Chen , Academia Sinica
Huang-Wei Chang , Academia Sinica
pp. 846-853

Unsupervised Learning in Radiology Using Novel Latent Variable Models (Abstract)

Sanjay Prabhu , Bristol Royal Infirmary
Paul Goddard , Bristol Royal Infirmary
Luke Carrivick , University of Bristol
Jonathan Rossiter , University of Bristol and RIKEN
pp. 854-859

Fields of Experts: A Framework for Learning Image Priors (Abstract)

Stefan Roth , Brown University
Michael J. Black , Brown University
pp. 860-867
Session 8.2: 3D Reconstruction

Shape from Shading: A Well-Posed Problem? (Abstract)

O. Faugeras , INRIA
E. Prados , University of California at Los Angeles
pp. 870-877

Complex 3D Shape Recovery Using a Dual-Space Approach (Abstract)

Chen Liang , University of Hong Kong
Kwan-Yee K. Wong , University of Hong Kong
pp. 878-884

Bayesian 3D Modeling from Images Using Multiple Depth Maps (Abstract)

Peter Sturm , INRIA Rhône-Alpes, GRAVIR-CNRS
Pau Gargallo , INRIA Rhône-Alpes, GRAVIR-CNRS
pp. 885-891

Visibility Constrained Surface Evolution (Abstract)

Anders Heyden , Malmö University
Fredrik Kahl , University of California at San Diego
Jan Erik Solem , Malmö University
pp. 892-899
Poster Session 6

Asymmetrical Occlusion Handling Using Graph Cut for Multi-View Stereo (Abstract)

Yichen Wei , Hong Kong University of Science and Technology
Long Quan , Hong Kong University of Science and Technology
pp. 902-909

Camera Calibration and Light Source Estimation from Images with Shadows (Abstract)

Xiaochun Cao , University of Central Florida
Mubarak Shah , University of Central Florida
pp. 918-923

Locally Adaptive Support-Weight Approach for Visual Correspondence Search (Abstract)

Kuk-Jin Yoon , Korea Advanced Institute of Science and Technology
In-So Kweon , Korea Advanced Institute of Science and Technology
pp. 924-931

Monocular 3-D Tracking of the Golf Swing (Abstract)

Pascal Fua , EPFL
David J. Fleet , University of Toronto
pp. 932-938

Energy Minimization via Graph Cuts: Settling What is Possible (Abstract)

Daniel Freedman , Rensselaer Polytechnic Institute
Petros Drineas , Rensselaer Polytechnic Institute
pp. 939-946

Theoretical Analysis on Reconstruction-Based Super-Resolution for an Arbitrary PSF (Abstract)

Masatoshi Okutomi , Tokyo Institute of Technology
Masayuki Tanaka , Tokyo Institute of Technology
pp. 947-954

Learning and Detecting Activities from Movement Trajectories Using the Hierarchical Hidden Markov Models (Abstract)

Hung Bui , SRI International
Dinh Q. Phung , Curtin University of Technology
Nam T. Nguyen , Curtin University of Technology
Svetha Venkatesh , Curtin University of Technology
pp. 955-960

Nonparametric Subspace Analysis for Face Recognition (Abstract)

Zhifeng Li , Chinese University of Hong Kong
Wei Liu , Chinese University of Hong Kong
Xiaoou Tang , Chinese University of Hong Kong and Microsoft Research Asia
Dahua Lin , Chinese University of Hong Kong
pp. 961-966

Audio-Visual Affect Recognition through Multi-Stream Fused HMM for HCI (Abstract)

Zhenqiu Zhang , University of Illinois at Urbana-Champaign
Brian Pianfetti , University of Illinois at Urbana-Champaign
Thomas S. Huang , University of Illinois at Urbana-Champaign
Jilin Tu , University of Illinois at Urbana-Champaign
Stephen Levinson , University of Illinois at Urbana-Champaign
Ming Liu , University of Illinois at Urbana-Champaign
Zhihong Zeng , University of Illinois at Urbana-Champaign
Tong Zhang , University of Illinois at Urbana-Champaign
pp. 967-972

Finding Glass (Abstract)

Jean Ponce , University of Illinois at Urbana-Champaign
Kenton McHenry , University of Illinois at Urbana-Champaign
David Forsyth , University of Illinois at Urbana-Champaign
pp. 973-979

Robust Instantaneous Rigid Motion Estimation (Abstract)

Karl Pauwels , K.U.Leuven
Marc M. Van Hulle , K.U. Leuven
pp. 980-985

Object Recognition with Features Inspired by Visual Cortex (Abstract)

Lior Wolf , Massachusetts Institute of Technology
Thomas Serre , Massachusetts Institute of Technology
Tomaso Poggio , Massachusetts Institute of Technology
pp. 994-1000

Applying Neighborhood Consistency for Fast Clustering and Kernel Density Estimation (Abstract)

Ming Tang , Chinese Academy of Sciences
James T. Kwok , University of Science and Technology - Kowloon
Kai Zhang , University of Science and Technology - Kowloon
pp. 1001-1007

Unstructured Point Cloud Matching within Graph-Theoretic and Thermodynamic Frameworks (Abstract)

A. Jagannathan , Northeastern University
E. L. Miller , Northeastern University
pp. 1008-1015

Optimal Point Correspondence through the Use of Rank Constraints (Abstract)

Ricardo Oliveira , Instituto Superior Técnico
João Xavier , Instituto Superior Técnico
João Costeira , Instituto Superior Técnico
pp. 1016-1021

Multimodal Face Recognition: Combination of Geometry with Physiological Information (Abstract)

G. Toderici , University of Houston
G. Passalis , University of Houston
N. Murtuza , University of Houston
T. Theoharis , University of Houston
I. Konstantinidis , University of Houston
I. A. Kakadiaris , University of Houston
pp. 1022-1029

Online Selecting Discriminative Tracking Features Using Particle Filter (Abstract)

Wen Gao , Harbin Institute of Technology and Chinese Academy of Sciences
Jianyu Wang , Harbin Institute of Technology
Xilin Chen , Harbin Institute of Technology and Chinese Academy of Sciences
pp. 1037-1042

Tracking Multiple Objects through Occlusions (Abstract)

Yan Huang , Georgia Institute of Technology
Irfan Essa , Georgia Institute of Technology
pp. 1051-1058

Tracking Non-Stationary Appearances and Dynamic Feature Selection (Abstract)

Ming Yang , Northwestern University
Ying Wu , Northwestern University
pp. 1059-1066

On Modelling Nonlinear Shape-and-Texture Appearance Manifolds (Abstract)

Trevor Darrell , Massachusetts Institute of Technology
C. Mario Christoudias , Massachusetts Institute of Technology
pp. 1067-1074

A Dense Stereo Matching Using Two-Pass Dynamic Programming with Generalized Ground Control Points (Abstract)

Kyoung Mu Lee , Seoul National University
Jae Chul Kim , Electronics and Telecommunications Research Institute
Byoung Tae Choi , Electronics and Telecommunications Research Institute
Sang Uk Lee , Seoul National University
pp. 1075-1082

A Framework of 2D Fisher Discriminant Analysis: Application to Face Recognition with Small Number of Training Samples (Abstract)

Hui Kong , Nanyang Technological University
Eam Khwang Teoh , Nanyang Technological University
Jian-Gang Wang , Institute for Infocomm Research
Lei Wang , Nanyang Technological University
Ronda Venkateswarlu , Institute for Infocomm Research
pp. 1083-1088

MRF Augmented Particle Filter Tracker (Abstract)

Loong-Fah Cheong , National University of Singapore
Hee Lin Wang , National University of Singapore
pp. 1097-1103

Analytically Solving Radial Distortion Parameters (Abstract)

Tobias Hanning , University of Passau
Simone Graf , University of Passau
pp. 1104-1109

Articulated Structure from Motion by Factorization (Abstract)

P. Tresadern , University of Oxford
I. Reid , University of Oxford
pp. 1110-1115

Polarization Multiplexing for Bidirectional Imaging (Abstract)

Kristin J. Dana , Rutgers University
Dongsheng Wang , Rutgers University
Oana G. Cula , Rutgers University
Dinesh K. Pai , Rutgers University
pp. 1116-1123

Spectral Segmentation with Multiscale Graph Decomposition (Abstract)

Jianbo Shi , University of Pennsylvania
Florence Bénézit , Ecole Polytechnique
Timothée Cour , University of Pennsylvania
pp. 1124-1131

Quantitative Evaluation of a Novel Image Segmentation Algorithm (Abstract)

Francisco J. Estrada , University of Toronto
Allan D. Jepson , University of Toronto
pp. 1132-1139

Range Data Registration Using Photometric Features (Abstract)

Joon Kyu Seo , Sogang University
Sang Wook Lee , Sogang University
Gregory C. Sharp , Massachusetts General Hospital
pp. 1140-1145

Using Coupled Subspace Models for Recovery of Reflectance Spectra from Airborne Images (Abstract)

Kartik Chandra , University of California at Irvine
Glenn Healey , University of California at Irvine
pp. 1146-1151

Vehicle Segmentation and Tracking from a Low-Angle Off-Axis Camera (Abstract)

Stanley T. Birchfield , Clemson University
Shrinivas J. Pundlik , Clemson University
Neeraj K. Kanhere , Clemson University
pp. 1152-1157

Spatiograms versus Histograms for Region-Based Tracking (Abstract)

Stanley T. Birchfield , Clemson University
Sriram Rangarajan , Clemson University
pp. 1158-1163

Level Set Based Shape Prior Segmentation (Abstract)

Wei Zhu , New York University
Tony Chan , University of California at Los Angeles
pp. 1164-1170

A Weighted Nearest Mean Classifier for Sparse Subspaces (Abstract)

David M. J. Tax , Delft University of Technology
Cor J. Veenman , Delft University of Technology
pp. 1171-1176
VPCVPR

Tracking Multiple Colored Blobs with a Moving Camera (PDF)

Manolis I. A. Lourakis , Foundation for Research and Technology - Hellas
Antonis A. Argyros , Foundation for Research and Technology - Hellas
pp. 1178

Automatic Thermal Monitoring System (ATHEMOS) for Deception Detection (PDF)

I. Pavlidis , University of Houston
M. G. Frank , Rutgers University
P. Buddharaju , University of Houston
J. Dowdall , University of Houston
D. Shastri , University of Houston
P. Tsiamyrtzis , University of Houston
pp. 1179

Efficient Real-Time Algorithms for Eye State and Head Pose Tracking in Advanced Driver Support Systems (PDF)

Phillip Malawey , Delphi Electronics and Safety
Andrew Wilhelm , Delphi Electronics and Safety
Riad I. Hammond , Delphi Electronics and Safety
Gerald J. Witt , Delphi Electronics and Safety
pp. 1181

Tracking Multiple Objects through Occlusions (PDF)

Irfan Essa , Georgia Institute of Technology
Yan Huang , Georgia Institute of Technology
pp. 1182

8D-THERMO CAM: Combination of Geometry with Physiological Information for Face Recognition (PDF)

G. Toderici , University of Houston
T. Theoharis , University of Houston
G. Passalis , University of Houston
I. Konstantinidis , University of Houston
I. A. Kakadiaris , University of Houston
N. Murtuza , University of Houston
pp. 1183

Computer Vision for Music Identification: Video Demonstration (PDF)

Rahul Sukthankar , Intel Research Pittsburgh and Carnegie Mellon University
Yan Ke , Carnegie Mellon University
Derek Hoiem , Carnegie Mellon University
pp. 1184

Skeletal Parameter Estimation from Optical Motion Capture Data (PDF)

Adam G. Kirk , University of California at Berkeley
David A. Forsyth , University of California at Berkeley
James F. O'Brien , University of California at Berkeley
pp. 1185

Bi-Layer Segmentation of Binocular Stereo Video (PDF)

A. Criminisi , Microsoft Research Ltd.
A. Blake , Microsoft Research Ltd.
G. Cross , Microsoft Research Ltd.
C. Rother , Microsoft Research Ltd.
V. Kolmogorov , Microsoft Research Ltd.
pp. 1186

Hand Tracking with Flocks of Features (PDF)

Matthew Turk , University of California at Santa Barbara
Mathias Kölsch , Naval Postgraduate School
pp. 1187

Object Detection Using 2D Spatial Ordering Constraints (PDF)

Yanghai Tsin , Siemens Corporate Research
Takeo Kanade , Carnegie Mellon University
Yakup Genc , Siemens Corporate Research
Yan Li , Carnegie Mellon University
pp. 1188

Online Modeling and Tracking of Pose-Varying Faces in Video (PDF)

Tsuhan Chen , Carnegie Mellon University
Xiaoming Liu , General Electric Global Research Center
pp. 1189

Camera Matchmoving in Unprepared, Unknown Environments (PDF)

Manolis I. A. Lourakis , Foundation for Research and Technology - Hellas
Antonis A. Argyros , Foundation for Research and Technology - Hellas
pp. 1190

Interactive Pinpoint Image Object Removal (PDF)

Richard Nock , UAG France
Frank Nielsen , Sony Computer Science Laboratories, Inc.
pp. 1191

Interactive Montages of Sprites for Indexing and Summarizing Security Video (PDF)

Nebojsa Jojic , Microsoft Research
Chris Pal , University of Massachusetts at Amherst
pp. 1192

Geodesic Computation for Adaptive Remeshing (PDF)

Gabriel Peyré , École Polytechnique
Laurent Cohen , Universite Paris Dauphine
pp. 1193

Tracking People and Recognizing Their Activities (PDF)

Deva Ramanan , University of California at Berkeley
David Forsyth , University of California at Berkeley and University of Illinois at Urbana-Champaign
Andrew Zisserman , Oxford University
pp. 1194

Facial Muscle Activations from Motion Capture (PDF)

Ron Fedkiw , Stanford University
Eftychios Sifakis , Stanford University
pp. 1195

Synchronization and Calibration of a Camera Network for 3D Event Reconstruction from Live Video (PDF)

Marc Pollefeys , University of North Carolina at Chapel Hill
Sudipta N. Sinha , University of North Carolina at Chapel Hill
pp. 1196

A Markov Random Field Approach for Dense Photometric Stereo (PDF)

Tien-Tsin Wong , Chinese University of Hong Kong
Chi-Keung Tang , Hong Kong University of Science and Technology
Kam-Lun Tang , Hong Kong University of Science and Technology
pp. 1197

Calibration of Pan-Tilt-Zoom (PTZ) Cameras and Omni-Directional Cameras (PDF)

Sudipta N. Sinha , University of North Carolina at Chapel Hill
Marc Pollefeys , University of North Carolina at Chapel Hill
SriRam Thirthala , University of North Carolina at Chapel Hill
pp. 1198

Monocular 3D Tracking of the Golf Swing (PDF)

David J. Fleet , University of Toronto
Pascal Fua , EPFL
pp. 1199

Face Modeling and Analysis in Stony Brook University (PDF)

Lei Zhang , State University of New York at Stony Brook
Sen Wang , State University of New York at Stony Brook
Yang Wang , State University of New York at Stony Brook
Dimitris Samaras , State University of New York at Stony Brook
Mohit Gupta , State University of New York at Stony Brook
pp. 1200

Videoshop: A New Framework for Spatio-Temporal Video Editing in Gradient Domain (PDF)

Narendra Ahuja , University of Illinois at Urbana-Champaign
Ning Xu , University of Illinois at Urbana-Champaign
Ramesh Raskar , Mitsubishi Electric Research Laboratories
Hongcheng Wang , University of Illinois at Urbana-Champaign
pp. 1201

A Flow-Based Approach to Vehicle Detection and Background Mosaicking in Airborne Video (PDF)

Hulya Yalcin , Carnegi Mellon University
Michael J. Black , Brown University
Martial Hebert , Carnegi Mellon University
Robert Collins , Penn State University
pp. 1202

A Factorization-Based Approach to Articulated Motion Recovery (PDF)

Jingyu Yan , University of North Carolina at Chapel Hill
Marc Pollefeys , University of North Carolina at Chapel Hill
pp. 1203
Demos

Driver State Monitor from DELPHI (PDF)

E. Yoder , Delphi Electronics & Safety
G. Witt , Delphi Electronics & Safety
N. Edenborough , Delphi Electronics & Safety
M. Smith , Delphi Electronics & Safety
A. Wilhelm , Delphi Electronics & Safety
G. Scharenbroch , Delphi Electronics & Safety
P. Malawey , Delphi Electronics & Safety
H. Zhang , Delphi Electronics & Safety
A. Harbach , Delphi Electronics & Safety
S. Skiver , Delphi Electronics & Safety
B. Kisačanin , Delphi Electronics & Safety
T. Newman , Delphi Electronics & Safety
A. Ingold , Delphi Electronics & Safety
R. Hammoud , Delphi Electronics & Safety
pp. 1206-1207

ALIP: The Automatic Linguistic Indexing of Pictures System (PDF)

James Z. Wang , Pennsylvania State University
Jia Li , Pennsylvania State University
pp. 1208-1209
Author Index

Author Index (PDF)

pp. 1211-1216
106 ms
(Ver 3.1 (10032016))