The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (2003)
Madison, Wisconsin
June 18, 2003 to June 20, 2003
ISSN: 1063-6919
ISBN: 0-7695-1900-8
TABLE OF CONTENTS
Oral Session 1A: Illumination- and Appearance-Based Matching

Illumination Normalization with Time-dependent Intrinsic Images for Video Surveillance (Abstract)

Yasuyuki Matsushita , The University of Tokyo
Ko Nishino , Columbia University
Masao Sakauchi , The University of Tokyo
Katsushi Ikeuchi , The University of Tokyo
pp. 3

Clustering Appearances of Objects Under Varying Illumination Conditions (Abstract)

Ming-Hsuan Yang , Honda Research Institute
David Kriegman , University of California at San Diego
Jongwoo Lim , University of Illinois at Urbana-Champaign
Jeffrey Ho , University of California at San Diego
Kuang-Chih Lee , University of Illinois at Urbana-Champaign
pp. 11

Joint Manifold Distance: a new approach to appearance based clustering (Abstract)

Andrew W. Fitzgibbon , University of Oxford, United Kingdom
Andrew Zisserman , University of Oxford, United Kingdom
pp. 26
Oral Session 1B: Motion and Layers

What Went Where (Abstract)

Sameer Agarwal , University of California, San Diego
Josh Wills , University of California, San Diego
Serge Belongie , University of California, San Diego
pp. 37

Learning Appearance and Transparency Manifolds of Occluded Objects in Layers (Abstract)

Brendan J. Frey , University of Toronto
Nebojsa Jojic , Microsoft Research
Anitha Kannan , University of Toronto
pp. 45
Oral Session 2A: Tracking I

Shape-From-Silhouette of Articulated Objects and its Use for Human Body Kinematics Estimation and Motion Capture (Abstract)

Simon Baker , Carnegie Mellon University
German K.M. Cheung , Carnegie Mellon University
Takeo Kanade , Carnegie Mellon University
pp. 77

Subset Selection for Efficient SVM Tracking (Abstract)

Shai Avidan , MobilEye Vision Technologies
pp. 85
Oral Session 2B: Shape

Statistics of Shape via Principal Geodesic Analysis on Lie Groups (Abstract)

P. Thomas Fletcher , University of North Carolina
Conglin Lu , University of North Carolina
Sarang Joshi , University of North Carolina
pp. 95

Representation and Detection of Deformable Shapes (Abstract)

Pedro F. Felzenszwalb , Massachusetts Institute of Technology
pp. 102

Bayesian Tangent Shape Model: Estimating Shape and Pose Parameters via Bayesian Inference (Abstract)

Hong-Jiang Zhang , Microsoft Research Asia
Lie Gu , CSD, Carnegie Mellon Univ.
Yi Zhou , Microsoft Research Asia SMS, Peking Univ.
pp. 109
Oral Session 3A: Recognition I

Man-Made Structure Detection in Natural Images using a Causal Multiscale Random Field (Abstract)

Sanjiv Kumar , Carnegie Mellon University
Martial Hebert , Carnegie Mellon University
pp. 119

Shape Context and Chamfer Matching in Cluttered Scenes (Abstract)

P. H. S. Torr , Microsoft Research Ltd.
B. Stenger , University of Cambridge
R. Cipolla , University of Cambridge
A. Thayananthan , University of Cambridge
pp. 127

Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA (Abstract)

Jitendra Malik , University of California, Berkeley
Greg Mori , University of California, Berkeley
pp. 134
Oral Session 3B: Segmentation and Medical Image Analysis

A New Graph-Theoretic Approach to Clustering and Segmentation (Abstract)

Massimiliano Pavan , Universit? Ca? Foscari di Venezia
Marcello Pelillo , Universit? Ca? Foscari di Venezia
pp. 145

A 2D Moving Grid Geometric Deformable Model (Abstract)

Chenyang Xu , Siemens Corporate Research
Xiao Han , Johns Hopkins University
Jerry L. Prince , Johns Hopkins University
pp. 153

Simultaneous Estimation of Left Ventricular Motion and Material Properties with Maximum a Posteriori Strategy (Abstract)

Pengcheng Shi , Hong Kong University of Science and Technology
Huafeng Liu , Hong Kong University of Science and Technology
pp. 161
3D Reconstruction I

Multi-view Stereo Beyond Lambert (Abstract)

Hailin Jin , Washington University
Anthony J. Yezzi , Georgia Institute of Technology
Stefano Soatto , University of California, Los Angeles
pp. 171

3D Shape from Anisotropic Diffusion (Abstract)

P. Favaro , Washington University
S. Osher , UCLA
L. Vese , UCLA
S. Soatto , UCLA
pp. 179

A Bayesian Approach to Image-Based Visual Hull Reconstruction (Abstract)

Gregory Shakhnarovich , Massachusetts Institute of Technology
Trevor Darrell , Massachusetts Institute of Technology
Kristen Grauman , Massachusetts Institute of Technology
pp. 187

High-Accuracy Stereo Depth Maps Using Structured Light (Abstract)

Richard Szeliski , Microsoft Research
Daniel Scharstein , Middlebury College
pp. 195

Video-Rate Stereo Depth Measurement on Programmable Hardware (Abstract)

Ahmad Darabiha , University of Toronto
Jonathan Rose , University of Toronto
W. James MacLean , University of Toronto
pp. 203

Multi-Resolution Real-Time Stereo on Commodity Graphics Hardware (Abstract)

Marc Pollefeys , University of North Carolina at Chapel Hill
Ruigang Yang , University of North Carolina at Chapel Hill
pp. 211
Recognition I

Object Recognition Based on Photometric Alignment Using RANSAC (Abstract)

Takahiro OKABE , University of Tokyo
Yoichi SATO , University of Tokyo
pp. 221

Optimal Linear Representations of Images for Object Recognition (Abstract)

Anuj Srivastava , Florida State University
Kyle Gallivan , Florida State University
Xiuwen Liu , Florida State University
pp. 229

Probabilistic Spatial Context Models for Scene Content Understanding (Abstract)

Weiyu Zhu , Univ. of Illinois
Jiebo Luo , Eastman Kodak Company
Amit Singhal , Eastman Kodak Company
pp. 235

Learning a discriminative classifier using shape context distances (Abstract)

Hao Zhang , University of California at Berkeley
Jitendra Malik , University of California at Berkeley
pp. 242

The Optimal Distance Measure for Object Detection (Abstract)

Martial Hebert , Carnegie Mellon University
Shyjan Mahamud , Carnegie Mellon University
pp. 248
Tracking I

Automated multi-camera planar tracking correspondence modeling (Abstract)

Kinh Tieu , Massachusetts Institute of Technology
Chris Stauffer , Massachusetts Institute of Technology
pp. 259

Continuous Tracking Within and Across Camera Streams (Abstract)

Isaac Cohen , University of Southern California
Gerard Medioni , University of Southern California
Jinman Kang , University of Southern California
pp. 267

Resolution vs. tracking error: zoom as a gain controller (Abstract)

D. W. Murray , University of Oxford
B. J. Tordoff , University of Oxford
pp. 273

Robust Data Association For Online Applications (Abstract)

Ali Shahrokni , Swiss Federal Institute of Technology (EPFL)
Vincent Lepetit , Swiss Federal Institute of Technology (EPFL)
Pascal Fua , Swiss Federal Institute of Technology (EPFL)
pp. 281

Deformable Object Tracking Using the Boundary Element Method (Abstract)

Bradley J. Nelson , Swiss Federal Institute of Technology (ETH)
Michael A. Greminger , University of Minnesota
pp. 289

Switching Observation Models for Contour Tracking in Clutter (Abstract)

Ting Yu , Northwestern University
Gang Hua , Northwestern University
Ying Wu , Northwestern University
pp. 295
Face Detection and Recognition

Face Authentication using the Trace Transform (Abstract)

Maria Petrou , University of Surrey; CERTH
Alexander Kadyrov , University of Surrey
Werasak Kurutach , Mahanakorn University of Technology
Sanun Srisuk , Mahanakorn University of Technology; University of Surrey
pp. 305

Video-Based Face Recognition Using Probabilistic Appearance Manifolds (Abstract)

Jeffrey Ho , University of California, San Diego
Kuang-Chih Lee , University of Illinois, Urbana-Champaign
David Kriegman , University of California, San Diego
Ming-Hsuan Yang , Honda Research Institute
pp. 313

Face Alignment Using Statistical Models and Wavelet Features (Abstract)

Dale Schuurmans , University of Waterloo
Feng Jiao , University of Waterloo
Heung-Yeung Shum , Microsoft Research Asia
Stan Li , Microsoft Research Asia
pp. 321

Deformable Pedal Curves with Application to Face Contour Extraction (Abstract)

Jianbo Su , Shanghai Jiaotong University
Fuzhen Huang , Shanghai Jiaotong University
pp. 328

Face Recognition in Hyperspectral Images (Abstract)

Manish Prasad , University of California, Irvine
Bruce J. Tromberg , University of California, Irvine
Glenn E. Healey , University of California, Irvine
Zhihong Pan , University of California, Irvine
pp. 334

Video-Based Face Recognition Using Adaptive Hidden Markov Models (Abstract)

Xiaoming Liu , Carnegie Mellon University
Tsuhan Chen , Carnegie Mellon University
pp. 340

A Novel Convergence Scheme for Active Appearance Models (Abstract)

Monson H. Hayes , Georgia Institute of Technology
Aziz Umit Batur , Georgia Institute of Technology
pp. 359
Motion

Error Analysis of 3-D Motion Estimation Algorithms in the Differential Case (Abstract)

Tao Xiang , University of London
Loong-Fah Cheong , National University of Singapore
pp. 369

Discovering Clusters in Motion Time-Series Data (Abstract)

George Kollios , Boston University
Vladimir Pavlovic , Rutgers University
Stan Sclaroff , Boston University
Jonathan Alon , Boston University
pp. 375

Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach (Abstract)

Mircea Nicolescu , University of Southern California
G?rard Medioni , University of Southern California
pp. 382

Homotopy-Based Computation of Defocus Blur and Affine Transform (Abstract)

F. Desch?nes , Universit? de Sherbrooke
D. Ziou , Universit? de Sherbrooke
pp. 398

Object Segmentation in Videos from Moving Camera with MRFs on Color and Motion Features (Abstract)

Andrea Prati , University of Modena and Reggio Emilia
Rita Cucchiara , University of Modena and Reggio Emilia
Roberto Vezzani , University of Modena and Reggio Emilia
pp. 405
Learning and Statistical Methods I

S-AdaBoost and Pattern Detection in Complex Environment (Abstract)

Kia-Fock Loe , National University of Singapore
Jimmy Liu Jiang , National University of Singapore
pp. 413

A Novel Support Vector Classifier with Better Rejection Performance (Abstract)

David Casasent , Carnegie Mellon University
Chao Yuan , Carnegie Mellon University
pp. 419

An Efficient Approach to Learning Inhomogeneous Gibbs Model (Abstract)

Heung-Yeung Shum , Microsoft Research Asia
Ziqiang Liu , Microsoft Research Asia
Hong Chen , Microsoft Research Asia
pp. 425

Adaptation For Multiple Cue Integration (Abstract)

Zhaohui Sun , Eastman Kodak Company
pp. 440
Medical Image Analysis

Flux Driven Fly Throughs (Abstract)

Sylvain Bouix , McGill University
Kaleem Siddiqi , McGill University
Allen Tannenbaum , Georgia Institute of Technology
pp. 449

Pose reconstruction with an uncalibrated Computed Tomography imaging device (Abstract)

M. de Mathelin , Strasbourg I University
C. Doignon , Strasbourg I University
B. Maurin , Strasbourg I University
A. Gangi , University Hospital of Strasbourg
pp. 455

Simultaneous Smoothing and Estimation of the Tensor Field from Diffusion Tens or MRI (Abstract)

T. Mareci , University of Florida
B. C. Vemuri , University of Florida
Y. Chen , University of Florida
Z. Wang , University of Florida
pp. 461

Tensor-based Brain Surface Modeling and Analysis (Abstract)

Moo K. Chung , University of Wisconsin-Madison
Keith J. Worsley , McGill University
Alan C. Evans , McGill University
Steve Robbins , McGill University
pp. 467
Calibration and Structure from Motion

Motion From 3D Line Correspondences: Linear and Non-Linear Solutions (Abstract)

Richard I. Hartley , Australian National University
Fredrik Kahl , Lund University, Sweden
Adrien Bartoli , INRIA Rh?ne-Alpes, France
pp. 477

Estimation of omnidirectional camera model from epipolar geometry (Abstract)

Tom? Pajdla , Czech Technical University in Prague
Branislav Micus? , Czech Technical University in Prague
pp. 485

Line Reconstruction from Many Perspective Images by Factorization (Abstract)

Daniel Martinec , Czech Technical University in Prague
Tom? Pajdla , Czech Technical University in Prague
pp. 497

Linear Auto-Calibration for Ground Plane Motion (Abstract)

Andrew Zisserman , University of Oxford
Ian Reid , University of Oxford
Joss Knight , University of Oxford
pp. 503

A Critical Configuration for Reconstruction from Rectilinear Motion (Abstract)

Richard Hartley , Australia National University
Fredrik Kahl , Lund University, Sweden
pp. 511

The Viewing Graph (Abstract)

Noam Levi , The Hebrew University of Jerusalem
Michael Werman , The Hebrew University of Jerusalem
pp. 518
Oral Session 4A: 3D Reconstruction

Structure From Motion for Scenes Without Features (Abstract)

Anthony J. Yezzi , Georgia Institute of Technology, Atlanta
Stefano Soatto , University of California, Los Angeles
pp. 525

Shape and Materials by Example: A Photometric Stereo Approach (Abstract)

Steven M. Seitz , University of Washington, Seattle
Aaron Hertzmann , University of Toronto
pp. 533

Surface Reconstruction via Helmholtz Reciprocity with a Single Image Pair (Abstract)

Peter Tu , GE Global Research Center
Paulo R. S. Mendon? , GE Global Research Center
pp. 541

Toward a Stratification of Helmholtz Stereopsis (Abstract)

David J. Kriegman , University of California, San Diego
Todd E. Zickler , Yale University
Peter N. Belhumeur , Columbia University
pp. 548
Oral Session 4B: Face and Gesture

Improving Continuous Gesture Recognition with Spoken Prosody (Abstract)

Mohammed Yeasin , Pennsylvania State University
Sanshzar Kettebekov , Pennsylvania State University
Rajeev Sharma , Pennsylvania State University
pp. 565

Learning Dynamics for Exemplar-based Gesture Recognition (Abstract)

Yaser Yacoob , University of Maryland
Larry S. Davis , University of Maryland
Vinay Shet , University of Maryland
Ahmed Elgammal , Rutgers University
pp. 571

Independent Component Analysis in a Facial Local Residue Space (Abstract)

Tae-Kyun Kim , Samsung Advanced Institute of Technology, Korea; University of Surrey, U.K.
Seok-Cheol Kee , Samsung Advanced Institute of Technology, Korea
Hyunwoo Kim , Samsung Advanced Institute of Technology, Korea
Wonjun Hwang , Samsung Advanced Institute of Technology, Korea
Josef Kittler , University of Surrey, U.K.
pp. 579

Kullback-Leibler Boosting (Abstract)

Hueng-Yeung Shum , Microsoft Research Asia
Ce Liu , Microsoft Research Asia
pp. 587

Learning Bayesian Network Classifiers for Facial Expression Recognition using both Labeled and Unlabeled Data (Abstract)

Thomas S. Huang , University of Illinois at Urbana-Champaign
Fabio G. Cozman , Universidade de S?o Paulo
Ira Cohen , University of Illinois at Urbana-Champaign
Marcelo C. Cirelo , Universidade de S?o Paulo
Nicu Sebe , Leiden University
pp. 595
Oral Session 5A: Learning and Statistical Methods

Nonparametric Belief Propagation (Abstract)

Alan S. Willsky , Massachusetts Institute of Technology
Erik B. Sudderth , Massachusetts Institute of Technology
William T. Freeman , Massachusetts Institute of Technology
Alexander T. Ihler , Massachusetts Institute of Technology
pp. 605

Generalized Principal Component Analysis (GPCA) (Abstract)

Ren? Vidal , University of California, Berkeley
Yi Ma , University of Illinois, Urbana
Shankar Sastry , University of California, Berkeley
pp. 621

Bootstrapping SVM Active Learning by Incorporating Unlabelled Images for Image Retrieval (Abstract)

Kap Luk Chan , Nanyang Technological University
Zhihua Zhang , Nanyang Technological University
Lei Wang , Nanyang Technological University
pp. 629

Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation (Abstract)

Amnon Shashua , Hebrew University of Jerusalem
Lior Wolf , Hebrew University of Jerusalem
pp. 635
Oral Session 5B: Illumination and Image Restoration

Image Repairing: Robust Image Synthesis by Adaptive ND Tensor Voting (Abstract)

Jiaya Jia , Hong Kong University of Science and Technology
Chi-Keung Tang , Hong Kong University of Science and Technology
pp. 643

Motion Deblurring Using Hybrid Imaging (Abstract)

Shree K. Nayar , Columbia University
Moshe Ben-Ezra , Columbia University
pp. 657

Shedding Light on the Weather (Abstract)

Srinivasa G. Narasimhan , Columbia University
Shree K. Nayar , Columbia University
pp. 665

Illumination Chromaticity Estimation using Inverse-Intensity Chromaticity Space (Abstract)

Katsushi Ikeuchi , The University of Tokyo
Robby T. Tan , The University of Tokyo
Ko Nishino , Columbia University
pp. 673
3D Reconstruction II

A Hybrid Approach for Computing Visual Hulls of Complex Objects (Abstract)

Edmond Boyer , GRAVIR-INRIA Rh?ne-Alpes
Jean-S?bastien Franco , GRAVIR-INRIA Rh?ne-Alpes
pp. 695

Computation of the shock scaffold for unorganized point clouds in 3D (Abstract)

F.F. Leymarie , Div. of Eng., Brown Univ., Providence, RI, USA
B.B. Kimia , Div. of Eng., Brown Univ., Providence, RI, USA
pp. 0
3D Reconstruction II

Surfaces with Occlusions from Layered Stereo (Abstract)

Carlo Tomasi , Duke University
Michael H. Lin , Stanford University
pp. 710

Wide-baseline Multiple-view Correspondences (Abstract)

Vittorio Ferrari , ETH Zuerich, Switzerland
Tinne Tuytelaars , University of Leuven, Belgium
Luc Van Gool , ETH Zuerich, Switzerland; University of Leuven, Belgium
pp. 718
Recognition II

Local Appearance-Based Models using High-Order Statistics of Image Features (Abstract)

David Guillamet , Universitat Aut?noma de Barcelona
Baback Moghaddam , Mitsubishi Electric
Jordi Vitri? , Universitat Aut?noma de Barcelona
pp. 729

Multi-scale Phase-based Local Features (Abstract)

Allan D. Jepson , University of Toronto
Gustavo Carneiro , University of Toronto
pp. 736

A Road Sign Recognition System Based on Dynamic Visual Model (Abstract)

C. S. Fuh , National Taiwan University, Taipei
C. Y. Fang , National Taiwan Normal University, Taipei
P. S. Yen , National Taiwan Normal University, Taipei
S. W. Chen , National Taiwan Normal University, Taipei
pp. 750

Occupant Classification System for Automotive Airbag Suppression (Abstract)

Michael E. Farmer , Eaton Corporation
Anil K. Jain , Michigan State University
pp. 756
Tracking II

Variational Inference for Visual Tracking (Abstract)

Jaco Vermaak , Cambridge University
Neil D. Lawrence , University of Sheffield
Patrick P?rez , Microsoft Research
pp. 773

Probabilistic Tracking in Joint Feature-Spatial Spaces (Abstract)

Ahmed Elgammal , Rutgers University
Ramani Duraiswami , University of Maryland
Larry S. Davis , University of Maryland
pp. 781

Tracking Appearances with Occlusions (Abstract)

Ying Wu , Northwestern University
Gang Hua , Northwestern University
Ting Yu , Northwestern University
pp. 789

Feature Selection for Reliable Tracking using Template Matching (Abstract)

Toshimitsu Kaneko , Toshiba Corporation
Osamu Hori , Toshiba Corporation
pp. 796

Adaptive View-Based Appearance Models (Abstract)

Ali Rahimi , MIT Artificial Intelligence Laboratory
Trevor Darrell , MIT Artificial Intelligence Laboratory
Louis-Philippe Morency , MIT Artificial Intelligence Laboratory
pp. 803
Shape

Directional Histogram Model for Three-Dimensional Shape Similarity (Abstract)

Sing Bing Kang , Microsoft Research
Robin Sun , Zhejiang University
Heung-Yeung Shum , Microsoft Research Asia
Xinguo Liu , Microsoft Research Asia
pp. 813

Curvature Correction of the Hamilton-Jacobi Skeleton (Abstract)

Andrea Torsello , University of York
Edwin R. Hancock , University of York
pp. 828

Flux Invariants for Shape (Abstract)

James N. Damon , University of North Carolina, Chapel Hill
Kaleem Siddiqi , McGill University
Pavel Dimitrov , McGill University
pp. 835

3D Surface Modeling from Range Curves (Abstract)

Dragan Tubic , University Laval
Denis Laurendeau , University Laval
Patrick H?bert , University Laval
pp. 842

Many-to-Many Graph Matching via Metric Embedding (Abstract)

Sven Dickinson , University of Toronto
Yakov Keselman , DePaul University
M. Fatih Demirci , Drexel University
Ali Shokoufandeh , Drexel University
pp. 850

3D Modeling Using a Statistical Sensor Model and Stochastic Search (Abstract)

Martial Hebert , Carnegie Mellon University
Daniel F. Huber , Carnegie Mellon University
pp. 858

Author's Index (PDF)

pp. 867
93 ms
(Ver )