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
Robot Localization and Navigation

Qualitative Image Based Localization in Indoors Environments (Abstract)

Philip Barber , George Mason University
Liang Zhou , George Mason University
Jana Koseck? , George Mason University
Zoran Duric , George Mason University
pp. 3
Segmentation and Perceptual Organization

Computing Layered Surface Representations: An Algorithm for Detecting and Separating Transparent Overlays (Abstract)

Manish Singh , Rutgers University - New Brunswick
Xiaolei Huang , Rutgers University - New Brunswick
pp. 11

Perception-based 3D Triangle Mesh Segmentation Using Fast Marching Watersheds (Abstract)

M. A. Abidi , University of Tennessee, Knoxville
A. F. Koschan , University of Tennessee, Knoxville
D. L. Page , University of Tennessee, Knoxville
pp. 27

Range Image Segmentation by Surface Extraction Using an Improved Robust Estimator (Abstract)

Paulo F. U. Gotardo , Universidade Federal do Paran?, Brasil
Luciano Silva , Centro Federal de Educa??o Tecnol?gica do Paran?, Brasil
Olga R. P. Bellon , Universidade Federal do Paran?, Brasil
pp. 33

Object-Specific Figure-Ground Segregation (Abstract)

Jianbo Shi , University of Pennsylvania
Stella X. Yu , Carnegie Mellon University
pp. 39

Object Segmentation Using Graph Cuts Based Active Contours (Abstract)

Ning Xu , University of Illinois
Narendra Ahuja , University of Illinois
Ravi Bansal , Columbia University
pp. 46

Learning Affinity Functions for Image Segmentation: Combining Patch-based and Gradient-based Approaches (Abstract)

David Martin , University of California, Berkeley
Charless Fowlkes , University of California, Berkeley
Jitendra Malik , University of California, Berkeley
pp. 54
Video

Background Subtraction based on Cooccurrence of Image Variations (Abstract)

Makito Seki , Mitsubishi Electric Corporation
Hideto Fujiwara , Mitsubishi Electric Corporation
Kazuhiko Sumi , Mitsubishi Electric Corporation
Toshikazu Wada , Wakayama University
pp. 65

Evaluation of Local Models of Dynamic Backgrounds (Abstract)

Scott Siebers , Washington University in St. Louis
Ben Westover , Washington University in St. Louis
John Larson , Washington University in St. Louis
Robert Pless , Washington University in St. Louis
pp. 73

Envolvable Visual Commercial Detector (Abstract)

Nevenka Dimitrova , Philips Research USA
Lalitha Agnihotri , Philips Research USA
Sylvie Jeannin , Philips Research USA
Thomas Mcgee , Philips Research USA
Jan Nesvadba , Philips Research USA
Dave Schaffer , Philips Research USA
pp. 79

Establishment Shot Detection Using Qualitative Motion (Abstract)

Hee Lin Wang , National University of Singapore
Loong Fah Cheong , National University of Singapore
Yong Wang , National University of Singapore
pp. 85
Learning and Statistical Methods II

Multilinear Subspace Analysis of Image Ensembles (Abstract)

Demetri Terzopoulos , University of Toronto; New York University
M. Alex O. Vasilescu , University of Toronto; New York University
pp. 93

Classification Based on Symmetric Maximized Minimal Distance in Subspace (SMMS) (Abstract)

Tsuhan Chen , Carnegie Mellon University
Wende Zhang , Carnegie Mellon University
pp. 100

Constrained Subspace Modelling (Abstract)

Patrick P?rez , Microsoft Research
Jaco Vermaak , Cambridge University Engineering Department
pp. 106

General c-Means Clustering Model and Its Application (Abstract)

Jian Yu , Northern Jiaotong University
pp. 122

Robust Data Clustering (Abstract)

Ana L.N. Fred , Instituto Superior T?cnico
Anil K. Jain , Michigan State University
pp. 128
Vision for Graphics

Editable Dynamic Textures (Abstract)

Gianfranco Doretto , UCLA Computer Science Department
Stefano Soatto , UCLA Computer Science Department
pp. 137

Example-Based Style Synthesis (Abstract)

Daniel Cohen-Or , Tel Aviv University
Hezy Yeshurun , Tel Aviv University
Iddo Drori , Tel Aviv University
pp. 143

Shape-Time Photography (Abstract)

William T. Freeman , Massachusetts Institute of Technology
Hao Zhang , U.C. Berkeley
pp. 151

Face Relighting with Radiance Environment Maps (Abstract)

Zicheng Liu , Microsoft Research
Thomas S. Huang , University of Illinois
Zhen Wen , University of Illinois
pp. 158

Automatic Relighting of Overlapping Textures of a 3D Model (Abstract)

S?bastien Roy , Universit? de Montr?al
Etienne Beauchesne , Universit? de Montr?al
pp. 166
Reflectance Modeling

Low-Dimensional Representations of Shaded Surfaces under Varying Illumination (Abstract)

Peter Nillius , Computational Vision & Active Perception Laboratory (CVAP)
Jan-Olof Eklundh , Computational Vision & Active Perception Laboratory (CVAP)
pp. 185
Oral Session 6A: Calibration and Structure from Motion

Constraint on Five Points in Two Images (Abstract)

Tomas Werner , Czech Technical University; University of Oxford
pp. 203

Learning epipolar geometry from image sequences (Abstract)

Yonatan Wexler , University of Oxford
Andrew Zisserman , University of Oxford
Andrew W. Fitzgibbon , University of Oxford
pp. 209
Oral Session 6B: Tracking II

Learning Object Intrinsic Structure for Robust Visual Tracking (Abstract)

Guangyou Xu , Tsinghua University
Haizhou Ai , Tsinghua University
Qiang Wang , Tsinghua University
pp. 227

Mean-shift Blob Tracking through Scale Space (Abstract)

Robert T. Collins , Carnegie Mellon University
pp. 234

Fusing Online and Offline Information for Stable 3D Tracking in Real-Time (Abstract)

Luca Vacchetti , Swiss Federal Institute of Technology (EPFL)
Vincent Lepetit , Swiss Federal Institute of Technology (EPFL)
Pascal Fua , Swiss Federal Institute of Technology (EPFL)
pp. 241

Appearance Management and Cue Fusion for 3D Model-Based Tracking (Abstract)

N. Krahnstoever , The Pennsylvania State University
R. Sharma , The Pennsylvania State University
pp. 249
Oral Session 7A: Recognition II

A performance evaluation of local descriptors (Abstract)

K. Mikolajczyk , INRIA Rh?ne-Alpes
C. Schmid , INRIA Rh?ne-Alpes
pp. 257

Object Class Recognition by Unsupervised Scale-Invariant Learning (Abstract)

A. Zisserman , University of Oxford
P. Perona , California Institute of Technology
R. Fergus , University of Oxford
pp. 264

3D Object Modeling and Recognition Using Affine-Invariant Patches and Multi-View Spatial Constraints (Abstract)

Cordelia Schmid , INRIA Rh?ne-Alpes
Jean Ponce , University of Illinois at Urbana-Champaign
Fredrick Rothganger , University of Illinois at Urbana-Champaign
Svetlana Lazebnik , University of Illinois at Urbana-Champaign
pp. 272
Oral Session 7B: Multi-body Factorization and Ego-Motion

Optimal Segmentation of Dynamic Scenes from Two Perspective Views (Abstract)

Ren? Vidal , University of California, Berkeley
Shankar Sastry , University of California, Berkeley
pp. 281

Degeneracies, Dependencies and their Implications in Multi-body and Multi-Sequence Factorizations (Abstract)

Michal Irani , The Weizmann Institute of Science
Lihi Zelnik-Manor , The Weizmann Institute of Science
pp. 287

Polydioptric Camera Design and 3D Motion Estimation (Abstract)

Yiannis Aloimonos , University of Maryland
Jan Neumann , University of Maryland
Cornelia Ferm? , University of Maryland
pp. 294
Oral Session 8A: Recognition III

Estimating the photorealism of images: Distinguishing paintings from photographs (Abstract)

Florin Cutzu , Indiana University
Alex Leykin , Indiana University
Riad Hammoud , Indiana University
pp. 305

A Sparse Texture Representation Using Affine-Invariant Regions (Abstract)

Svetlana Lazebnik , University of Illinois, Urbana
Jean Ponce , University of Illinois, Urbana
Cordelia Schmid , Inria Rh?ne-Alpes
pp. 319
Oral Session 8B: Video

Video Content Annotation Using Visual Analysis and a Large Semantic Knowledgebase (Abstract)

Gees Stein , GE Global Research
Jens Rittscher , GE Global Research
Anthony Hoogs , GE Global Research
John Schmiederer , GE Global Research
pp. 327

Video Segmentation Based on Graphical Models (Abstract)

Yang Wang , Institute for Infocomm Research
Kia-Fock Loe , National University of Singapore
Tele Tan , Institute for Infocomm Research
pp. 335

Scene Detection In Hollywood Movies and TV Shows (Abstract)

Zeeshan Rasheed , University of Central Florida
Mubarak Shah , University of Central Florida
pp. 343
3D Reconstruction III

Dynamic Depth Recovery from Unsynchronized Video Streams (Abstract)

Hai Tao , University of California, Santa Cruz
Chunxiao Zhou , University of California, Santa Cruz
pp. 351

Spacetime Stereo: A Unifying Framework for Depth from Triangulation (Abstract)

James Davis , Honda Research Institute
Ravi Ramamoorthi , Columbia University
Szymon Rusinkiewicz , Princeton University
pp. 359

Spacetime Stereo: Shape Recovery for Dynamic Scenes (Abstract)

Brian Curless , University of Washington, Seattle
Steven M. Seitz , University of Washington, Seattle
Li Zhang , University of Washington, Seattle
pp. 367

Properties and Applications of Shape Recipes (Abstract)

William T. Freeman , MIT Artificial Intelligence Laboratory
Antonio Torralba , MIT Artificial Intelligence Laboratory
pp. 383

ROD-TV: Reconstruction on Demand by Tensor Voting (Abstract)

Chi-Keung Tang , Hong Kong University of Science and Technology
Wai-Shun Tong , Hong Kong University of Science and Technology
pp. 391
Recognition III

Shape-based Recognition Of Wiry Objects (Abstract)

Owen Carmichael , Carnegie Mellon University
Martial Hebert , Carnegie Mellon University
pp. 401

Analyzing Appearance and Contour Based Methods for Object Categorization (Abstract)

Bastian Leibe , ETH Zurich, Switzerland
Bernt Schiele , ETH Zurich, Switzerland
pp. 409

Enhancing DPF for Near-replica Image Recognition (Abstract)

Yan Meng , University of California, Santa Barbara
Edward Chang , University of California, Santa Barbara
Beitao Li , University of California, Santa Barbara
pp. 416

Simultaneous Pose and Correspondence Determination using Line Features (Abstract)

Daniel DeMenthon , University of Maryland Institute for Advanced Computer Studies
Hanan Samet , University of Maryland
Philip David , University of Maryland; Army Research Laboratory
Ramani Duraiswami , University of Maryland Institute for Advanced Computer Studies
pp. 424

Estimating 3D Hand Pose from a Cluttered Image (Abstract)

Vassilis Athitsos , Boston University
Stan Sclaroff , Boston University
pp. 432
Tracking III

Using Multiple Cues for Hand Tracking and Model Refinement (Abstract)

Dimitris Samaras , S.U.N.Y. Stony Brook
John Oliensis , Stevens Institute of Technology
Shan Lu , Rutgers University
Dimitris Metaxas , Rutgers University
pp. 443

Eye Gaze Tracking Using an Active Stereo Head (Abstract)

David Beymer , IBM Almaden Research Center
Myron Flickner , IBM Almaden Research Center
pp. 451

Multi-modal image registration by minimizing Kullback-Leibler distance between expected and observed joint class histograms (Abstract)

Ho-Ming Chan , Dept. of Comput. Sci., Hong Kong Univ. of Sci. & Technol., China
A.C.S. Chung , Dept. of Comput. Sci., Hong Kong Univ. of Sci. & Technol., China
pp. II-570
Tracking III

Finding and Tracking People from the Bottom Up (Abstract)

Deva Ramanan , University of California, Berkeley
D. A. Forsyth , University of California, Berkeley
pp. 467

Markerless Kinematic Model and Motion Capture from Volume Sequences (Abstract)

Chi-Wei Chu , University of Southern California
Odest Chadwicke Jenkins , University of Southern California
Maja J Mataric , University of Southern California
pp. 475

Implicit Meshes for Modeling and Reconstruction (Abstract)

Pascal Fua , EPFL, Switzerland
Slobodan Ilic , EPFL, Switzerland
pp. 483
Fingerprint Recognition

A Novel Model for Orientation Field of Fingerprints (Abstract)

Jie Zhou , Tsinghua University
Jinwei Gu , Tsinghua University
pp. 493

On The Fundamental Performance For Fingerprint Matching (Abstract)

Xuejun Tan , University of California, Riverside
Bir Bhanu , University of California, Riverside
pp. 499

Robust Crease Detection in Fingerprint Images (Abstract)

Chenyu Wu , Tsinghua University
Zhao-qi Bian , Tsinghua University
Gang Rong , Tsinghua University
Jie Zhou , Tsinghua University
pp. 505
Documents, Text and Projectors

Shadow Elimination and Occluder Light Suppression for Multi-Projector Displays (Abstract)

Tat-Jen Cham , Nanyang Technological University
Rahul Sukthankar , Intel Research Pittsburgh; Carnegie Mellon University
Gita Sukthankar , Carnegie Mellon University
James M. Rehg , Georgia Institute of Technology
pp. 513

Word Image Matching Using Dynamic Time Warping (Abstract)

Toni M. Rath , University of Massachusetts
R. Manmatha , University of Massachusetts
pp. 521

Document Image Enhancement Using Directional Wavelet (Abstract)

Lida Li , National University of Singapore
Tao Xia , National University of Singapore
Chew Lim Tan , National University of Singapore
Qian Wang , National University of Singapore
pp. 534
Registration and Alignment

Implicit similarity: a new approach to multi-sensor image registration (Abstract)

Yosi Keller , Technion Institute of Technology
Amir averbuch , Tel-Aviv University
pp. 543

Practical Super-Resolution from Dynamic Video Sequences (Abstract)

Zhongding Jiang , Zhejiang University, China
Hujun Bao , Zhejiang University, China
Tien-Tsin Wong , The Chinese University of Hong Kong, China
pp. 549

Automated Feature-Based Range Registration of Urban Scenes of Large Scale (Abstract)

Marius Leordeanu , Hunter College, City University of New York
Ioannis Stamos , Hunter College, City University of New York
pp. 555

Constructing 3D City Models by Merging Ground-Based and Airborne Views (Abstract)

Christian Frueh , University of California, Berkeley
Avideh Zakhor , University of California, Berkeley
pp. 562

Multi-modal image registration by minimizing Kullback-Leibler distance between expected and observed joint class histograms (Abstract)

Alexander Norbash , Harvard Medical School, Boston, MA
William M. Wells III , Harvard Medical School, Boston, MA; Massachusetts Institute of Technology, Cambridge, MA
Simon C.H. Yu , Prince of Wales Hospital, Hong Kong
Albert C.S. Chung , Hong Kong University of Science and Technology, Hong Kong
Ho-Ming Chan , Hong Kong University of Science and Technology, Hong Kong
pp. 570
Sensing

Using Many Cameras as One (Abstract)

Robert Pless , Washington University in St. Louis
pp. 587

A Perspective on Distortions (Abstract)

Shree K. Nayar , Columbia University
Michael D. Grossberg , Columbia University
Rahul Swaminathan , Columbia University
pp. 594

What is the Space of Camera Response Functions? (Abstract)

Shree K. Nayar , Columbia University
Michael D. Grossberg , Columbia University
pp. 602
Activity Recognition

View Invariants for Human Action Recognition (Abstract)

Rama Chellappa , University of Maryland
Vasu Parameswaran , University of Maryland
pp. 613

Recognising and Monitoring High-Level Behaviours in Complex Spatial Environments (Abstract)

Geoff West , Curtin University of Technology
Nam T. Nguyen , Curtin University of Technology
Svetha Venkatesh , Curtin University of Technology
Hung H. Bui , Curtin University of Technology
pp. 620

Expectation Grammars: Leveraging High-Level Expectations for Activity Recognition (Abstract)

Irfan Essa , Georgia Institute of Technology
David Minnen , Georgia Institute of Technology
Thad Starner , Georgia Institute of Technology
pp. 626

Activity Recognition Using the Dynamics of the Configuration of Interacting Objects (Abstract)

Amit Roy Chowdhury , University of Maryland
Rama Chellappa , University of Maryland
Namrata Vaswani , University of Maryland
pp. 633
Image and Video Retrieval

Nearest Neighbor Search for Relevance Feedback (Abstract)

B.S. Manjunath , University of California, Santa Barbara
Jelena Te?sic , University of California, Santa Barbara
pp. 643

3D Model Retrieval With Morphing-Based Geometric and Topological Feature Maps (Abstract)

Indriyati Atmosukarto , National University of Singapore
Meng Yu , National University of Singapore
Rong Xu , National University of Singapore
Zhiyong Huang , National University of Singapore
Wee Kheng Leow , National University of Singapore
pp. 656

A New Semi-Supervised EM Algorithm for Image Retrieval (Abstract)

Anlei Dong , University of California, Riverside
Bir Bhanu , University of California, Riverside
pp. 662

Enhancing Image and Video Retrieval: Learning via Equivalence Constraints (Abstract)

Tomer Hertz , The Hebrew University of Jerusalem, Jerusalem
Aharon Bar-Hillel , The Hebrew University of Jerusalem, Jerusalem
Daphna Weinshall , The Hebrew University of Jerusalem, Jerusalem
Noam Shental , The Hebrew University of Jerusalem, Jerusalem
pp. 668

The Effects of Segmentation and Feature Choice in a Translation Model of Object Recognition (Abstract)

Pinar Duygulu , Technical University, Turkey
David Forsyth , University of California, Berkeley
Raghavendra Guru , University of Arizona
Prasad Gabbur , University of Arizona
Kobus Barnard , University of Arizona
pp. 675
Texture

Texture Classification: Are Filter Banks Necessary? (Abstract)

Andrew Zisserman , University of Oxford
Manik Varma , University of Oxford
pp. 691

Active Unsupervised Texture Segmentation on a Diffusion Based Feature Space (Abstract)

Rachid Deriche , INRIA Sophia-Antipolis
Thomas Brox , Saarland University
Mika? Rousson , INRIA Sophia-Antipolis
pp. 699
Image Restoration and Inpainting

Simultaneous Structure and Texture Image Inpainting (Abstract)

S. Osher , University Pompeu Fabra, University of Minnesota, UCLA
L. Vese , University Pompeu Fabra, University of Minnesota, UCLA
M. Bertalmio , University Pompeu Fabra, University of Minnesota, UCLA
G. Sapiro , University Pompeu Fabra, University of Minnesota, UCLA
pp. 707

Object Removal by Exemplar-Based Inpainting (Abstract)

A. Criminisi , Microsoft Research Ltd.
K. Toyama , Microsoft Corporation
P. P?rez , Microsoft Research Ltd.
pp. 721

Image Hallucination with Primal Sketch Priors (Abstract)

Hai Tao , Univ. of California, SC
Nan-Ning Zheng , Xi?an Jiaotong University
Heung-Yeung Shum , Microsoft Research Asia
Jian Sun , Xi?an Jiaotong University
pp. 729

Author's Index (PDF)

pp. 737
89 ms
(Ver )