The Community for Technology Leaders
Computer Vision, IEEE International Conference on (2003)
Nice, France
Oct. 13, 2003 to Oct. 16, 2003
ISBN: 0-7695-1950-4
TABLE OF CONTENTS
Session 1: Image Segmentation

Learning a Classification Model for Segmentation (Abstract)

Jitendra Malik , University of California at Berkeley
Xiaofeng Ren , University of California at Berkeley
pp. 10

Image Parsing: Unifying Segmentation, Detection, and Recognition (Abstract)

Song-Chun Zhu , University of California, Los Angeles
Zhuowen Tu , University of California, Los Angeles
Xiangrong Chen , University of California, Los Angeles
Alan L. Yuille , University of California, Los Angeles
pp. 18

Computing Geodesics and Minimal Surfaces via Graph Cuts (Abstract)

Yuri Boykov , Siemens Corp. Research
Vladimir Kolmogorov , Cornell University
pp. 26

Epitomic analysis of appearance and shape (Abstract)

Brendan J. Frey , University of Toronto
Nebojsa Jojic , Microsoft Research
Anitha Kannan , University of Toronto
pp. 34
Session 2: Posters

Ranking Prior Likelihood Distributions for Bayesian Shape Localization Framework (Abstract)

Shuicheng Yan , Peking University
Mingjing Li , Microsoft Research Asia
Hongjiang Zhang , Microsoft Research Asia
Qiansheng Cheng , Peking University
pp. 51

Efficient, Robust and Accurate Fitting of a 3D Morphable Model (Abstract)

Thomas Vetter , University of Basel
Sami Romdhani , University of Basel
pp. 59

Statistical Background Subtraction for a Mobile Observer (Abstract)

Jan-Olof Eklundh , Computational Vision and Active Perception Laboratory (CVAP)
Eric Hayman , Computational Vision and Active Perception Laboratory (CVAP)
pp. 67

Joint Region Tracking with Switching Hypothesized Measurements (Abstract)

Yang Wang , Institute for Infocomm Research, Singapore
Kia-Fock Loe , National University of Singapore
Tele Tan , Institute for Infocomm Research, Singapore
pp. 75

The Local Projective Shape of Smooth Surfaces and their Outlines (Abstract)

Svetlana Lazebnik , Beckman Institute, University of Illinois
Jean Ponce , Beckman Institute, University of Illinois
pp. 83

Active Concept Learning for Image Retrieval in Dynamic Databases (Abstract)

Bir Bhanu , University of California, Riverside
Anlei Dong , University of California, Riverside
pp. 90

Video Input Driven Animation (VIDA) (Abstract)

Meng Sun , University of Toronto
Eugene Fiume , University of Toronto
Allan D. Jepson , University of Toronto
pp. 96

Automatic Video Summarization by Graph Modeling (Abstract)

Hong-Jiang Zhang , Microsoft Research Asia
Yu-Fei Ma , Microsoft Research Asia
Chong-Wah Ngo , City University of Hong Kong
pp. 104

A Non-Iterative Greedy Algorithm for Multi-frame Point Correspondence (Abstract)

Mubarak Shah , University of Central Florida, Orlando
Khurram Shafique , University of Central Florida, Orlando
pp. 110

Variational Frameworks for DT-MRI Estimation, Regularization and Visualization (Abstract)

David Tschumperl? , Odyss?e Lab, INRIA Sophia-Antipolis
Rachid Deriche , Odyss?e Lab, INRIA Sophia-Antipolis
pp. 116

Fragmentation in the Vision of Scenes (Abstract)

Jan-Mark Geusebroek , University of Amsterdam
Arnold W. M. Smeulders , University of Amsterdam
pp. 130

Eye Gaze Estimation from a Single Image of One Eye (Abstract)

Jian-Gang Wang , Institute for Infocomm Research
Eric Sung , Nanyang Technological University
Ronda Venkateswarlu , Institute for Infocomm Research
pp. 136

Calibrating pan-tilt cameras in wide-area surveillance networks (Abstract)

James Davis , Honda Research Institute
Xing Chen , NVIDIA Corporation
pp. 144

Calibration of a Hybrid Camera Network (Abstract)

Xilin Chen , Carnegie Mellon University, PA
Alex Waibel , Carnegie Mellon University, PA
Jie Yang , Carnegie Mellon University, PA
pp. 150

Image Registration with Global and Local Luminance Alignment (Abstract)

Chi-Keung Tang , Hong Kong University of Science and Technology
Jiaya Jia , Hong Kong University of Science and Technology
pp. 156

Highlight Removal by Illumination-Constrained Inpainting (Abstract)

Ping Tan , Microsoft Research, Asia
Heung-Yeung Shum , Microsoft Research, Asia
Long Quan , Hong Kong University of Science and Technology
Stephen Lin , Microsoft Research, Asia
pp. 164

Surface Reflectance Modeling of Real Objects with Interreflections (Abstract)

Takashi Machida , Osaka University
Haruo Takemura , Osaka University
Naokazu Yokoya , Nara Institute of Science and Technology
pp. 170

Variable Bandwidth QMDPE and Its Application in Robust Optical Flow Estimation (Abstract)

David Suter , Monash University, Australia
Hanzi Wang , Monash University, Australia
pp. 178

Surface Reconstruction from Feature Based Stereo (Abstract)

Camillo J. Taylor , University of Pennsylvania, Philadelphia
pp. 184

Gaze Manipulation for One-to-one Teleconferencing (Abstract)

A. Criminisi , Microsoft Research Ltd, Cambridge, UK
J. Shotton , Microsoft Research Ltd, Cambridge, UK
A. Blake , Microsoft Research Ltd, Cambridge, UK
P.H.S. Torr , Microsoft Research Ltd, Cambridge, UK
pp. 191

Multiple-View Structure and Motion From Line Correspondences (Abstract)

Adrien Bartoli , INRIA Rh?ne-Alpes
Peter Sturm , INRIA Rh?ne-Alpes
pp. 207

Modeling Textured Motion : Particle, Wave and Sketch (Abstract)

Song-Chun Zhu , University of California, Los Angeles
Yizhou Wang , University of California, Los Angeles
pp. 213

Circular Motion Geometry by Minimal 2 Points in 4 Images (Abstract)

Guang Jiang , The Chinese University of Hong Kong; Xidian Univeristy
Hung-tat Tsui , The Chinese University of Hong Kong
Long Quan , Kong University of Science and Technology
pp. 221

A Cylindrical Surface Model to Rectify the Bound Document Image (Abstract)

Xiaoqing Ding , Tsinghua University
Changsong Liu , Tsinghua University
Huaigu Cao , Tsinghua University
pp. 228

Edit Distance From Graph Spectra (Abstract)

A. Robles-Kelly , The University of York
E. R. Hancock , The University of York
pp. 234

Minimum Risk Distance Measure for Object Recognition (Abstract)

Martial Hebert , Carnegie Mellon University
Shyjan Mahamud , Carnegie Mellon University
pp. 242

Recognition with Local Features: the Kernel Recipe (Abstract)

Barbara Caputo , CVAP, NADA, KTH
Christian Wallraven , MPI for Biological Cybernetics
Arnulf Graf , MPI for Biological Cybernetics
pp. 257

Images as Bags of Pixels (Abstract)

Tony Jebara , Columbia University, NY
pp. 265

Object Recognition with Informative Features and Linear Classi?cation (Abstract)

Michel Vidal-Naquet , The Weizmann Institute of Science
Shimon Ullman , The Weizmann Institute of Science
pp. 281

Meshfree Particle Method (Abstract)

Pengcheng Shi , Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
Huafeng Liu , Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
pp. 289

Minimally-Supervised Classification using Multiple Observation Sets (Abstract)

Chris Stauffer , Massachusetts Institute of Technology
pp. 297

Learning How to Inpaint from Global Image Statistics (Abstract)

Yair Weiss , The Hebrew University of Jerusalem
Assaf Zomet , The Hebrew University of Jerusalem
Anat Levin , The Hebrew University of Jerusalem
pp. 305

Multiclass Spectral Clustering (Abstract)

Jianbo Shi , University of Pennsylvania
Stella X. Yu , Carnegie Mellon University
pp. 313

Graph Partition by Swendsen-Wang Cuts (Abstract)

Song-Chun Zhu , University of California, Los Angeles
Adrian Barbu , University of California, Los Angeles
pp. 320
Session 3: Tracking

Obstacle Detection Using Projective Invariant and Vanishing Lines (Abstract)

Kazunori Onoguchi , Toshiba Corporation
Kenji Furukawa , Toshiba Corporation
Ryuzo Okada , Toshiba Corporation
Yasuhiro Taniguchi , Toshiba Corporation
pp. 330

Using Temporal Coherence to Build Models of Animals (Abstract)

Deva Ramanan , University of California, Berkeley
D. A. Forsyth , University of California, Berkeley
pp. 338

On-Line Selection of Discriminative Tracking Features (Abstract)

Robert T. Collins , Carnegie Mellon University
Yanxi Liu , Carnegie Mellon University
pp. 346

A Sparse Probabilistic Learning Algorithm for Real-Time Tracking (Abstract)

Andrew Blake , Microsoft Research Ltd.
Oliver Williams , University of Cambridge
Roberto Cipolla , University of Cambridge
pp. 353
Session 4: Clustering and Feature Selection

Dominant Sets and Hierarchical Clustering (Abstract)

Massimiliano Pavan , Universit? Ca' Foscari di Venezia
Marcello Pelillo , Universit? Ca' Foscari di Venezia
pp. 362

Learning a Locality Preserving Subspace for Visual Recognition (Abstract)

Shuicheng Yan , Peking University, China
Hong-Jiang Zhang , Microsoft Research Asia
Yuxiao Hu , Microsoft Research Asia
Xiaofei He , University of Chicago
pp. 385
Session 5: Features and Tracking

A Model-Based Approach for Automated Feature Extraction in Fundus Images (Abstract)

Opas Chutatape , Nanyang Technological University
Huiqi Li , National University of Singapore
pp. 394

Information Theoretic Focal Length Selection for Real-Time Active 3-D Object Tracking (Abstract)

M. Zobel , University of Erlangen-Nuremberg
H. Niemann , University of Erlangen-Nuremberg
J. Denzler , University of Erlangen-Nuremberg
pp. 400
Session 6: Posters

Mean Shift Based Clustering in High Dimensions: A Texture Classification Example (Abstract)

Peter Meer , Rutgers University, Piscataway, NJ
Ilan Shimshoni , Technion - Israel Institute of Technology
Bogdan Georgescu , Rutgers University, Piscataway, NJ
pp. 456

Improved Fast Gauss Transform and Efficient Kernel Density Estimation (Abstract)

Changjiang Yang , University of Maryland, College Park
Nail A. Gumerov , University of Maryland, College Park
Larry Davis , University of Maryland, College Park
Ramani Duraiswami , University of Maryland, College Park
pp. 464

Unsupervised Image Translation (Abstract)

R?mer Rosales , University of Toronto, Canada
Brendan Frey , University of Toronto, Canada
Kannan Achan , University of Toronto, Canada
pp. 472

On Exploiting Occlusions in Multiple-view Geometry (Abstract)

Paolo Favaro , Washington University, St. Louis, MO; UCLA
Yi Ma , Beckman Institute
pp. 479

Machine Learning and Multiscale Methods in the Identification of Bivalve Larvae (Abstract)

Sanjay Tiwari , Woods Hole Oceanographic Institution
Scott Gallager , Woods Hole Oceanographic Institution
pp. 494

A Segmentation Algorithm for Contrast-Enhanced Images (Abstract)

Junhwan Kim , Cornell University
Ramin Zabih , Cornell University
pp. 502

Reinforcement Learning for Combining Relevance Feedback Techniques (Abstract)

Kuang-Cheng Chang , National Chi-Nan University, Taiwan
Anlei Dong , University of California, Riverside
Bir Bhanu , University of California, Riverside
Peng-Yeng Yin , National Chi-Nan University, Taiwan
pp. 510

Automatically Labeling Video Data Using Multi-class Active Learning (Abstract)

Jie Yang , Carnegie Mellon University
Alexander Hauptmann , Carnegie Mellon University
Rong Yan , Carnegie Mellon University
pp. 516

An automatic drowning detection surveillance system for challenging outdoor pool environments (Abstract)

How-Lung Eng , Institute for Infocomm Research
Kar-Ann Toh , Institute for Infocomm Research
Junxian Wang , Institute for Infocomm Research
Alvin H. Kam , Institute for Infocomm Research
Wei-Yun Yau , Institute for Infocomm Research
pp. 532

Cumulative Residual Entropy, A New Measure of Information & its Application to Image Alignment (Abstract)

M. Rao , University of Florida
F. Wang , University of Florida
Y. Chen , University of Florida
B. C. Vemuri , University of Florida
pp. 548

Determining Reflectance and Light Position from a Single Image Without Distant Illumination Assumption (Abstract)

Katsushi Ikeuchi , The University of Tokyo
Ko Nishino , Columbia University
Kenji Hara , Fukuoka Industrial Technology Center
pp. 560

Phenomenological Eigenfunctions for Image Irradiance (Abstract)

Jan-Olof Eklundh , Royal Institute of Technology (KTH)
Peter Nillius , Royal Institute of Technology (KTH)
pp. 568

Dealing with Textureless Regions and Specular Highlights-A Progressive Space Carving Scheme Using a Novel Photo-consistency Measure (Abstract)

Greg Welch , University of North Carolina at Chapel Hill
Marc Pollefeys , University of North Carolina at Chapel Hill
Ruigang Yang , University of North Carolina at Chapel Hill
pp. 576

Outlier Correction in Image Sequences for the Affine Camera (Abstract)

R. Hartley , The Australian National University
A. Heyden , Malm? University
D. Q. Huynh , The University of Western Australia
pp. 585

Voxel Carving for Specular Surfaces (Abstract)

Peter Sturm , MOVI - GRAVIR - INRIA, Grenoble, France
Thomas Bonfort , MOVI - GRAVIR - INRIA, Grenoble, France
pp. 591

Two-Frame Wide Baseline Matching (Abstract)

Jiangjian Xiao , University of Central Florida, Orlando
Mubarak Shah , University of Central Florida, Orlando
pp. 603

Fast Stereo Matching Using Reliability-Based Dynamic Programming and Consistency Constraints (Abstract)

Yee-Hong Yang , Univ. of Alberta, Edmonton, Canada
Minglun Gong , Univ. of Alberta, Edmonton, Canada
pp. 610

Shape and Motion under Varying Illumination: Unifying Structure from Motion, Photometric Stereo, and Multi-view Stereo (Abstract)

Li Zhang , University of Washington, Seattle, WA
Brian Curless , University of Washington, Seattle, WA
Aaron Hertzmann , University of Toronto, Toronto, ON
Steven M. Seitz , University of Washington, Seattle, WA
pp. 618

Unsupervised Improvement of Visual Detectors using Co-Training (Abstract)

Paul Viola , Microsoft Research
Yoav Freund , Columbia University
Anat Levin , The Hebrew University
pp. 626

Selection of Scale-Invariant Parts for Object Class Recognition (Abstract)

C. Schmid , INRIA Rh?ne-Alpes
Gy. Dork? , INRIA Rh?ne-Alpes
pp. 634

Inferring 3D Structure with a Statistical Image-Based Shape Model (Abstract)

Kristen Grauman , Massachusetts Institute of Technology
Gregory Shakhnarovich , Massachusetts Institute of Technology
Trevor Darrell , Massachusetts Institute of Technology
pp. 641

Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition (Abstract)

Svetlana Lazebnik , University of Illinois, Urbana
Cordelia Schmid , Inria Rh?ne-Alpes
Jean Ponce , University of Illinois, Urbana
pp. 649

Shape Representation via Harmonic Embedding (Abstract)

Sanjoy K. Mitter , Massachusetts Institute of Technology, Cambridge
Alessandro Duci , University of California at Los Angeles
Stefano Soatto , University of California at Los Angeles
Anthony J. Yezzi , Georgia Institute of Technology, Atlanta
pp. 656

Learning Pedestrian Models for Silhouette Refinement (Abstract)

K. Tieu , Massachusettes Institute of Technology
G. Dalley , Massachusettes Institute of Technology
L. Lee , Massachusettes Institute of Technology
pp. 663

A Bayesian Network Framework for Relational Shape Matching (Abstract)

James Coughlan , Smith-Kettlewell Institute
Anand Rangarajan , University of Florida, Gainesville
pp. 671

Unified Subspace Analysis for Face Recognition (Abstract)

Xiaogang Wang , The Chinese University of Hong Kong
Xiaoou Tang , The Chinese University of Hong Kong
pp. 679

Face Sketch Synthesis and Recognition (Abstract)

Xiaogang Wang , The Chinese University of Hong Kong
Xiaoou Tang , The Chinese University of Hong Kong
pp. 687

Dynamic Stroke Information Analysis for Video-Based Handwritten Chinese Character Recognition (Abstract)

Xiaoou Tang , The Chinese University of Hong Kong
Feng Lin , The Chinese University of Hong Kong
pp. 695

Surface Classification Using Conformal Structures (Abstract)

Shing-Tung Yau , Harvard University
Xianfeng Gu , University of Florida, Gainesville
pp. 701

Boosting Chain Learning for Object Detection (Abstract)

Hong-Jiang Zhang , Microsoft Research Asia
Long Zhu , Microsoft Research Asia
Rong Xiao , Microsoft Research Asia
pp. 709

Texture Segmentation by Multiscale Aggregation of Filter Responses and Shape Elements (Abstract)

Ronen Basri , The Weizmann Inst. of Science
Achi Brandt , The Weizmann Inst. of Science
Eitan Sharon , The Weizmann Inst. of Science
Meirav Galun , The Weizmann Inst. of Science
pp. 716
98 ms
(Ver )