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

Additional reviewers (PDF)

pp. xxxiv,xxxv

Preface (PDF)

pp. xxiv,xxv,xxvi,xxvii,xxviii

Program Committee (PDF)

pp. xxxi-xxxiii
Session 1.1: Object Recognition

Identifying Semantically Equivalent Object Fragments (Abstract)

Boris Epshtein , Weizmann Institute of Science
Shimon Ullman , Weizmann Institute of Science
pp. 2-9

Spatial Priors for Part-Based Recognition Using Statistical Models (Abstract)

David Crandall , Cornell University
Pedro Felzenszwalb , Univerisity of Chicago
Daniel Huttenlocher , Cornell University
pp. 10-17

OBJ CUT (Abstract)

Philip H. S. Torr , Oxford Brookes University
A. Zisserman , University of Oxford
M. Pawan Kumar , Oxford Brookes University
pp. 18-25

Shape Matching and Object Recognition Using Low Distortion Correspondences (Abstract)

Jitendra Malik , University of California at Berkeley
Tamara L. Berg , University of California at Berkeley
Alexander C. Berg , University of California at Berkeley
pp. 26-33

Random Subwindows for Robust Image Classification (Abstract)

Justus Piater , University of Liège
Pierre Geurts , University of Liège
Louis Wehenkel , University of Liège
Raphaël Marée , University of Liège
pp. 34-40
Session 1.2: Video Analysis and Reconstruction

Video Epitomes (Abstract)

Nebojsa Jojic , Microsoft Research
Brendan J. Frey , University of Toronto
Vincent Cheung , University of Toronto
pp. 42-49

Full-Frame Video Stabilization (Abstract)

Heung-Yeung Shum , Microsoft Research Asia
Yasuyuki Matsushita , Microsoft Research Asia
Eyal Ofek , Microsoft Research Asia
Xiaoou Tang , Microsoft Research Asia
pp. 50-57

Dynamosaics: Video Mosaics with Non-Chronological Time (Abstract)

Shmuel Peleg , Hebrew University of Jerusalem
Alex Rav-Acha , Hebrew University of Jerusalem
Yael Pritch , Hebrew University of Jerusalem
Dani Lischinski , Hebrew University of Jerusalem
pp. 58-65

Bayesian Object Detection in Dynamic Scenes (Abstract)

Yaser Sheikh , University of Central Florida
Mubarak Shah , University of Central Florida
pp. 74-79
Poster Session 1

Shock Filters Based on Implicit Cluster Separation (Abstract)

Vinay P. Namboodiri , Indian Institute of Technology - Bombay
Subhasis Chaudhuri , Indian Institute of Technology - Bombay
pp. 82-87

Pixels that Sound (Abstract)

Yoav Y. Schechner , Technion - Israel Institute of Technology
Einat Kidron , Technion - Israel Institute of Technology
Michael Elad , Technion - Israel Institute of Technology
pp. 88-95

A Band-Weighted Landuse Classification Method for Multispectral Images (Abstract)

Gang Wu , Chinese Academy of Sciences
Veronique Prinet , Chinese Academy of Sciences
Chunhong Pan , Chinese Academy of Sciences
Qing Yang , Chinese Academy of Sciences
Songde Ma , Chinese Academy of Sciences
pp. 96-102

Why I Want a Gradient Camera (Abstract)

Amit Agrawal , University of Maryland
Jack Tumblin , Northwestern University
pp. 103-110

Using the KL-Center for Efficient and Accurate Retrieval of Distributions Arising from Texture Images (Abstract)

Murali Rao , University of Florida
Baba C. Vemuri , University of Florida
Eric Spellman , University of Florida
pp. 111-116

Modelling Reflections via Multiperspective Imaging (Abstract)

Leonard McMillan , University of North Carolina
Jingyi Yu , Massachusetts Institute of Technology
pp. 117-124

Dense Photometric Stereo Using Tensorial Belief Propagation (Abstract)

Chi-Keung Tang , Hong Kong University of Science and Technology
Tien-Tsin Wong , Chinese University of Hong Kong
Kam-Lun Tang , Hong Kong University of Science and Technology
pp. 132-139

Dense Photometric Stereo Using a Mirror Sphere and Graph Cut (Abstract)

Tai-Pang Wu , Hong Kong University of Science and Technology
Chi-Keung Tang , Hong Kong University of Science and Technology
pp. 140-147

A Combined Physical and Statistical Approach to Colour Constancy (Abstract)

Steven Hordley , University of East Anglia
Gerald Schaefer , Nottingham Trent University
Graham Finlayson , University of East Anglia
pp. 148-153

Segmentation of a Piece-Wise Planar Scene from Perspective Images (Abstract)

Yi Ma , University of Illinois at Urbana-Champaign
Shankar Rao , University of Illinois at Urbana-Champaign
Andrew Wagner , University of Illinois at Urbana-Champaign
Allen Y. Yang , University of Illinois at Urbana-Champaign
pp. 154-161

Coupled PDEs for Non-Rigid Registration and Segmentation (Abstract)

Gozde Unal , Siemens Corporate Research
Greg Slabaugh , Siemens Corporate Research
pp. 168-175

Efficient Mean-Shift Tracking via a New Similarity Measure (Abstract)

Ramani Duraiswami , University of Maryland at College Park
Larry Davis , University of Maryland at College Park
Changjiang Yang , University of Maryland at College Park
pp. 176-183

A SIFT Descriptor with Global Context (Abstract)

Hongli Deng , Oregon State University
Linda Shapiro , University of Washington
Eric N. Mortensen , Oregon State University
pp. 184-190

An Axiomatic Approach to Corner Detection (Abstract)

B. S. Manjunath , University of California at Santa Barbara
M. Zuliani , University of California at Santa Barbara
C. S. Kenney , University of California at Santa Barbara
pp. 191-197

3D Reconstruction by Fitting Low-Rank Matrices with Missing Data (Abstract)

Daniel Martinec , Czech Technical University in Prague
Tomáš Pajdla , Czech Technical University in Prague
pp. 198-205

Multi-View Geometry for General Camera Models (Abstract)

Peter Sturm , INRIA Rhône-Alpes, GRAVIR-CNRS
pp. 206-212

A Rational Function Lens Distortion Model for General Cameras (Abstract)

Andrew W. Fitzgibbon , University of Oxford
David Claus , University of Oxford
pp. 213-219

Matching with PROSAC — Progressive Sample Consensus (Abstract)

Ondřej Chum , Czech Technical University in Prague
Jiří Matas , Czech Technical University in Prague
pp. 220-226

Kernel-Based Bayesian Filtering for Object Tracking (Abstract)

Dorin Comaniciu , Siemens Corporate Research
Ying Zhu , Siemens Corporate Research
Bohyung Han , University of Maryland at College Park
Larry Davis , University of Maryland at College Park
pp. 227-234

Appearance-Guided Particle Filtering for Articulated Hand Tracking (Abstract)

Chu-Song Chen , Academia Sinica
Yi-Ping Hung , Academia Sinica and National Taiwan University
Wen-Yan Chang , Academia Sinica and National Taiwan University
pp. 235-242

Dynamic Environment Exploration Using a Virtual White Cane (Abstract)

D. Yuan , University of California at Santa Cruz
R. Manduchi , University of California at Santa Cruz
pp. 243-249

Background Recognition in Dynamic Scenes with Motion Constraints (Abstract)

L. Van Gool , K.U. Leuven and ETH
K. E. Ozden , K.U. Leuven
pp. 250-255

Multiscale Segmentation by Combining Motion and Intensity Cues (Abstract)

Meirav Galun , Weizmann Institute of Science
Alexander Apartsin , Weizmann Institute of Science
Ronen Basri , Weizmann Institute of Science
pp. 256-263

A Dynamic Conditional Random Field Model for Object Segmentation in Image Sequences (Abstract)

Qiang Ji , Rensselaer Polytechnic Institute
Yang Wang , Rensselaer Polytechnic Institute
pp. 264-270

Strike a Pose: Tracking People by Finding Stylized Poses (Abstract)

D. A. Forsyth , University of California at Berkeley
Deva Ramanan , University of California at Berkeley
Andrew Zisserman , University of Oxford
pp. 271-278

Ordinal Palmprint Represention for Personal Identification (Abstract)

Stan Z. Li , Chinese Academy of Sciences
Yunhong Wang , Chinese Academy of Sciences and Beihang University
Zhenan Sun , Chinese Academy of Sciences
Tieniu Tan , Chinese Academy of Sciences
pp. 279-284

Active Contours Using a Constraint-Based Implicit Representation (Abstract)

Weiming Liu , Brigham Young University
Bryan S. Morse , Brigham Young University
Terry S. Yoo , National Library of Medicine
Kalpathi Subramanian , University of North Carolina at Charlotte
pp. 285-292

Affine Object Tracking with Kernel-Based Spatial-Color Representation (Abstract)

Haihong Zhang , Institute of Infocomm Research and National University of Singapore
Zhiyong Huang , National University of Singapore
Liyuan Li , Institute of Infocomm Research
Weimin Huang , Institute of Infocomm Research
pp. 293-300

A Caratheodory-Fejer Approach to Dynamic Appearance Modeling (Abstract)

Octavia I. Camps , Pennsylvania State University
Hwasup Lim , Pennsylvania State University
Mario Sznaier , Pennsylvania State University
pp. 301-307

3D Articulated Motion Estimation from Images (Abstract)

Xiaoyun Zhang , Shanghai Jiaotong University
Yuncai Liu , Shanghai Jiaotong University
pp. 308-314

Motion Segmentation of Multiple Translating Objects Using Line Correspondences (Abstract)

Jianhua Wang , Shanghai Jiao Tong University
Jing Zhang , Shanghai Jiao Tong University
Fanhuai Shi , Shanghai Jiao Tong University
Yuncai Liu , Shanghai Jiao Tong University
pp. 315-320

The Radial Trifocal Tensor: A Tool for Calibrating the Radial Distortion of Wide-Angle Cameras (Abstract)

SriRam Thirthala , University of North Carolina at Chapel Hill
Marc Pollefeys , University of North Carolina at Chapel Hill
pp. 321-328

Wide-Baseline Stereo Matching with Line Segments (Abstract)

Herbert Bay , ETH Zuerich
Vittorio Ferrari , ETH Zuerich
Luc Van Gool , ETH Zuerich and University of Leuven
pp. 329-336

3D Geometric and Optical Modeling of Warped Document Images from Scanners (Abstract)

Zheng Zhang , National University of Singapore
Tao Xia , National University of Singapore
Chew Lim Tan , National University of Singapore
Li Zhang , National University of Singapore
pp. 337-342

Interactive Shape from Shading (Abstract)

Heung-Yeung Shum , Microsoft Research Asia
Gang Zeng , Hong Kong University of Science and Technology
Long Quan , Hong Kong University of Science and Technology
Yasuyuki Matsushita , Microsoft Research Asia
pp. 343-350

Geo-Consistency for Wide Multi-Camera Stereo (Abstract)

Sébastien Roy , Université de Montréal
Marc-Antoine Drouin , Université de Montréal
Martin Trudeau , Université de Montréal
pp. 351-358

Robust Boosting for Learning from Few Examples (Abstract)

Ian Martin , Massachusetts Institute of Technology
Lior Wolf , Massachusetts Institute of Technology
pp. 359-364

Boosting Saliency in Color Image Features (Abstract)

Th. Gevers , University of Amsterdam
J. van de Weijer , University of Amsterdam
pp. 365-372

Learn Discriminant Features for Multi-View Face and Eye Detection (Abstract)

Peng Wang , Rensselaer Polytechnic Institute
Qiang Ji , Rensselaer Polytechnic Institute
pp. 373-379

A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition (Abstract)

R. Fergus , University of Oxford
A. Zisserman , University of Oxford
P. Perona , California Institute of Technology
pp. 380-387
Session 2.1: Tracking Humans

Discriminative Density Propagation for 3D Human Motion Estimation (Abstract)

Zhiguo Li , Rutgers University
Dimitris Metaxas , Rutgers University
Atul Kanaujia , Rutgers University
Cristian Sminchisescu , University of Toronto
pp. 390-397

Space-Time Behavior Based Correlation (Abstract)

Eli Shechtman , Weizmann Institute of Science
Michal Irani , Weizmann Institute of Science
pp. 405-412

Hybrid Joint-Separable Multibody Tracking (Abstract)

Roberto Manduchi , University of California at Santa Cruz
Oswald Lanz , ITC-irst
pp. 413-420

Modeling and Learning Contact Dynamics in Human Motion (Abstract)

Alessandro Bissacco , University of California at Los Angeles
pp. 421-428
Session 2.2: Image Analysis and Segmentation

Level Set Evolution without Re-Initialization: A New Variational Formulation (Abstract)

Chenyang Xu , Siemens Corporate Research
Chunming Li , University of Connecticut
Changfeng Gui , University of Connecticut
Martin D. Fox , University of Connecticut
pp. 430-436

Bayesian Image Segmentation Using Wavelet-Based Priors (Abstract)

Mário A. T. Figueiredo , Instituto de Telecomunicações and Instituto Superior Técnico
pp. 437-443

Segmentation Induced by Scale Invariance (Abstract)

Stella X. Yu , University of California at Berkeley
pp. 444-451

A New Active Contour Method Based on Elastic Interaction (Abstract)

Yang Xiang , Hong Kong University of Science and Technology
Albert C.S. Chung , Hong Kong University of Science and Technology
Jian Ye , Hong Kong University of Science and Technology
pp. 452-457

Robust Centerline Extraction Framework Using Level Sets (Abstract)

M. Sabry Hassouna , University of Louisville
Aly A. Farag , University of Louisville
pp. 458-465
Poster Session 2

Feature-Level Fusion in Personal Identification (Abstract)

Yongsheng Gao , Griffith University
Michael Maggs , Griffith University
pp. 468-473

A Two-Stage Level Set Evolution Scheme for Man-Made Objects Detection in Aerial Images (Abstract)

Zhihong Mao , Shanghai Jiao Tong University
Xin Yang , Shanghai Jiao Tong University
Guo Cao , Shanghai Jiao Tong University
pp. 474-479

Pruning Training Sets for Learning of Object Categories (Abstract)

Yaser Abu-Mostafa , California Institute of Technology
Anelia Angelova , California Institute of Technology
Pietro Perona , California Institute of Technology
pp. 494-501

Pose-Robust Face Recognition Using Geometry Assisted Probabilistic Modeling (Abstract)

Tsuhan Chen , Carnegie Mellon University
Xiaoming Liu , General Electric Global Research Center
pp. 502-509

Multi-Image Matching Using Multi-Scale Oriented Patches (Abstract)

Richard Szeliski , Microsoft Research
Matthew Brown , University of British Columbia
Simon Winder , Microsoft Research
pp. 510-517

Tangent-Corrected Embedding (Abstract)

Dale Schuurmans , University of Alberta
Ali Ghodsi , University of Waterloo
Jiayuan Huang , University of Waterloo
Finnegan Southey , University of Alberta
pp. 518-525

Discriminant Analysis with Tensor Representation (Abstract)

Xiaoou Tang , Chinese University of Hong Kong and Microsoft Research Asia
Dong Xu , University of Science and Technology of China
Shuicheng Yan , Chinese University of Hong Kong
Qiang Yang , Hong Kong University of Science and Technology
Hong-Jiang Zhang , Microsoft Research Asia
Lei Zhang , Microsoft Research Asia
pp. 526-532

Infomax Boosting (Abstract)

Siwei Lyu , Dartmouth College
pp. 533-538

Learning a Similarity Metric Discriminatively, with Application to Face Verification (Abstract)

Raia Hadsell , New York University
Sumit Chopra , New York University
Yann LeCun , New York University
pp. 539-546

Multilinear Independent Components Analysis (Abstract)

M. Alex O. Vasilescu , University of Toronto and New York University
Demetri Terzopoulos , New York University and University of Toronto
pp. 547-553

Nonlinear Face Recognition Based on Maximum Average Margin Criterion (Abstract)

Wen Gao , Harbin Institute of Technology and Chinese Academy of Science
Xilin Chen , Harbin Institute of Technology and Chinese Academy of Science
Baochang Zhang , Harbin Institute of Technology
Shiguang Shan , Chinese Academy of Science
pp. 554-559

Selection and Fusion of Color Models for Feature Detection (Abstract)

H. Stokman , University of Amsterdam
Th. Gevers , University of Amsterdam
pp. 560-565

Multiple Object Tracking with Kernel Particle Filter (Abstract)

Rashid Ansari , University of Illinois at Chicago
Cheng Chang , University of Illinois at Chicago
Ashfaq Khokhar , University of Illinois at Chicago
pp. 566-573

Subspace Analysis Using Random Mixture Models (Abstract)

Xiaogang Wang , Massachusetts Institute of Technology
Xiaoou Tang , Chinese University of Hong Kong and Microsoft Research Asia
pp. 574-580

Face Recognition with Image Sets Using Manifold Density Divergence (Abstract)

John Fisher , Massachusetts Institute of Technology
Trevor Darrell , Massachusetts Institute of Technology
Roberto Cipolla , University of Cambridge
Ognjen Arandjelović , University of Cambridge
Gregory Shakhnarovich , Massachusetts Institute of Technology
pp. 581-588

Digital Tapestry (Abstract)

Carsten Rother , Microsoft Research
Sanjiv Kumar , Carnegie Mellon University
Vladimir Kolmogorov , Microsoft Research
Andrew Blake , Microsoft Research
pp. 589-596

Computer Vision for Music Identification (Abstract)

Yan Ke , Carnegie Mellon University
Derek Hoiem , Carnegie Mellon University
Rahul Sukthankar , Carnegie Mellon University and Intel Research Pittsburgh
pp. 597-604

Multitarget Tracking with Split and Merged Measurements (Abstract)

Tucker Balch , Georgia Institute of Technology
Frank Dellaert , Georgia Institute of Technology
Zia Khan , Georgia Institute of Technology
pp. 605-610

Semi-Supervised Adapted HMMs for Unusual Event Detection (Abstract)

Iain McCowan , IDIAP Research Institute
Daniel Gatica-Perez , IDIAP Research Institute
Dong Zhang , IDIAP Research Institute and Swiss Federal Institute of Technology
Samy Bengio , IDIAP Research Institute and Swiss Federal Institute of Technology
pp. 611-618

Mixture Trees for Modeling and Fast Conditional Sampling with Applications in Vision and Graphics (Abstract)

Sang Min Oh , Georgia Institute of Technology
Frank Dellaert , Georgia Institute of Technology
Vivek Kwatra , Georgia Institute of Technology
pp. 619-624

A Cross-Validatory Statistical Approach to Scale Selection for Image Denoising by Nonlinear Diffusion (Abstract)

Petros Maragos , National Technical University of Athens
George Papandreou , National Technical University of Athens
pp. 625-630

A Principled Approach to Detecting Surprising Events in Video (Abstract)

Laurent Itti , University of Southern California
Pierre Baldi , University of California at Irvine
pp. 631-637

Restoration and Recognition in a Loop (Abstract)

Mithun Das Gupta , University of Illinois at Urbana-Champaign
Thomas S. Huang , University of Illinois at Urbana-Champaign
Shyamsundar Rajaram , University of Illinois at Urbana-Champaign
Nemanja Petrovic , Siemens Corporate Research
pp. 638-644

Coupled Kernel-Based Subspace Learning (Abstract)

Benyu Zhang , Microsoft Research Asia
Shuicheng Yan , Chinese University of Hong Kong
HongJiang Zhang , Microsoft Research Asia
Dong Xu , University of Science and Technology of China
Lei Zhang , Microsoft Research Asia
pp. 645-650

An On-Line Learning Mechanism for Unsupervised Classification and Topology Representation (Abstract)

Shen Furao , Tokyo Institute of Technology
Osamu Hasegawa , Tokyo Institute of Technology
pp. 651-656

Semi-Supervised Cross Feature Learning for Semantic Concept Detection in Videos (Abstract)

Milind Naphade , IBM TJ Watson Research Center
Rong Yan , Carnegie Mellon University
pp. 657-663

A Discriminative Framework for Modelling Object Classes (Abstract)

Alex Holub , California Institute of Technology
Pietro Perona , California Institute of Technology
pp. 664-671

Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement (Abstract)

Evgeniy Bart , Weizmann Institute of Science
Shimon Ullman , Weizmann Institute of Science
pp. 672-679

Robust Face Detection with Multi-Class Boosting (Abstract)

Tyng-Luh Liu , Academia Sinica
Yen-Yu Lin , Academia Sinica
pp. 680-687

A Two Level Approach for Scene Recognition (Abstract)

Le Lu , Johns Hopkins University
Kentaro Toyama , Microsoft Research
Gregory D. Hager , Johns Hopkins University
pp. 688-695

Online Detection and Classification of Moving Objects Using Progressively Improving Detectors (Abstract)

Mubarak Shah , University of Central Florida
Omar Javed , University of Central Florida
Saad Ali , University of Central Florida
pp. 696-701

Object Class Recognition by Boosting a Part-Based Model (Abstract)

Tomer Hertz , Hebrew University of Jerusalem
Daphna Weinshall , Hebrew University of Jerusalem
Aharon Bar-Hillel , Hebrew University of Jerusalem
pp. 702-709

Hierarchical Part-Based Visual Object Categorization (Abstract)

Bill Triggs , LEAR, GRAVIR-INRIA
Guillaume Bouchard , LEAR, GRAVIR-INRIA
pp. 710-715

Learning with Constrained and Unlabelled Data (Abstract)

Anil K. Jain , Michigan State University
Tilman Lange , ETH Zurich
Joachim M. Buhmann , ETH Zurich
Martin H.C. Law , Michigan State University
pp. 731-738

Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization (Abstract)

Jiaya Jia , Chinese University of Hong Kong
Yu-Wing Tai , Hong Kong University of Science and Technology
Chi-Keung Tang , Hong Kong University of Science and Technology
pp. 747-754

Interactive Graph Cut Based Segmentation with Shape Priors (Abstract)

Daniel Freedman , Rensselaer Polytechnic Institute
Tao Zhang , Rensselaer Polytechnic Institute
pp. 755-762

Multilabel Random Walker Image Segmentation Using Prior Models (Abstract)

Leo Grady , Siemens Corporate Research
pp. 763-770
Session 3.1: Structure from Motion

Two-View Geometry Estimation Unaffected by a Dominant Plane (Abstract)

Tomáš Werner , Czech Technical University in Prague
Jiří Matas , Czech Technical University in Prague
Ondřej Chum , Czech Technical University in Prague
pp. 772-779

On the Absolute Quadratic Complex and Its Application to Autocalibration (Abstract)

K. McHenry , University of Illinois at Urbana-Champaign
J. Ponce , University of Illinois at Urbana-Champaign
T. Papadopoulo , INRIA Sophia-Antipolis
B. Triggs , INRIA Rhône-Alpes
M. Teillaud , INRIA Sophia-Antipolis
pp. 780-787

Reflections on the Generalized Bas-Relief Ambiguity (Abstract)

David J. Kriegman , University of California at San Diego
Manmohan Krishna Chandraker , University of California at San Diego
Fredrik Kahl , University of California at San Diego
pp. 788-795

Radon-Based Structure from Motion without Correspondences (Abstract)

Shankar Sastry , University of California at Berkeley
Christopher Geyer , University of California at Berkeley
Kostas Daniilidis , University of Pennsylvania
Ameesh Makadia , University of Pennsylvania
pp. 796-803
Session 3.2: Applications and Real Time Vision

MER-DIMES: A Planetary Landing Application of Computer Vision (Abstract)

Larry Matthies , California Institute of Technology
Andrew Johnson , California Institute of Technology
Yang Cheng , California Institute of Technology
pp. 806-813

A Projector-Camera System with Real-Time Photometric Adaptation for Dynamic Environments (Abstract)

Michael D. Grossberg , City University of New York
Kensaku Fujii , NTT Corporation
Shree K. Nayar , Columbia University
pp. 814-821

Real-Time Non-Rigid Surface Detection (Abstract)

Julien Pilet , ?cole Polytechnique F?d?rale de Lausanne
Pascal Fua , ?cole Polytechnique F?d?rale de Lausanne
Vincent Lepetit , ?cole Polytechnique F?d?rale de Lausanne
pp. 822-828

Integral Histogram: A Fast Way To Extract Histograms in Cartesian Spaces (Abstract)

Fatih Porikli , Mitsubishi Electric Research Laboratories
pp. 829-836
Session 4.1: Video Recognition and Analysis

Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model (Abstract)

Svetha Venkatesh , Curtin University of Technology
Thi V. Duong , Curtin University of Technology
Hung H. Bui , SRI International
Dinh Q. Phung , Curtin University of Technology
pp. 838-845

Probabilistic Kernels for the Classification of Auto-Regressive Visual Processes (Abstract)

Antoni B. Chan , University of California at San Diego
Nuno Vasconcelos , University of California at San Diego
pp. 846-851

Online Learning of Probabilistic Appearance Manifolds for Video-Based Recognition and Tracking (Abstract)

Kuang-Chih Lee , University of Illinois at Urbana-Champaign
David Kriegman , University of California at San Diego
pp. 852-859

Learning Appearance Manifolds from Video (Abstract)

Ali Rahimi , Massachusetts Institute of Technology
Trevor Darrell , Massachusetts Institute of Technology
Ben Recht , Massachusetts Institute of Technology
pp. 868-875
Session 4.2: Object Recognition

Pedestrian Detection in Crowded Scenes (Abstract)

Bernt Schiele , Technical University of Darmstadt
Edgar Seemann , Technical University of Darmstadt
Bastian Leibe , Technical University of Darmstadt
pp. 878-885

Histograms of Oriented Gradients for Human Detection (Abstract)

Bill Triggs , INRIA Rhône-Alps
Navneet Dalal , INRIA Rhône-Alps
pp. 886-893

MosaicShape: Stochastic Region Grouping with Shape Prior (Abstract)

Margrit Betke , Boston University
Erdan Gu , University of Pennsylvania
Jingbin Wang , Boston University
pp. 902-908

Indexing with Unknown Illumination and Pose (Abstract)

Ronen Basri , Weizmann Institute of Science
Ira Kemelmacher , Weizmann Institute of Science
pp. 909-916
Poster Session 3

Eye Gaze Tracking under Natural Head Movements (Abstract)

Zhiwei Zhu , Rensselaer Polytechnic Institute
Qiang Ji , Rensselaer Polytechnic Institute
pp. 918-923

Near Real-Time Reliable Stereo Matching Using Programmable Graphics Hardware (Abstract)

Minglun Gong , Laurentian University
Yee-Hong Yang , University of Alberta
pp. 924-931

Real-Time Tracking with Multiple Cues by Set Theoretic Random Search (Abstract)

Cheng Chang , University of Illinois at Chicago
Rashid Ansari , University of Illinois at Chicago
pp. 932-938

Decentralized Multiple Target Tracking Using Netted Collaborative Autonomous Trackers (Abstract)

Ying Wu , Northwestern University
Ting Yu , Northwestern University
pp. 939-946

Evaluating Image Retrieval (Abstract)

Kobus Barnard , University of Arizona
Nikhil V. Shirahatti , University of Arizona
pp. 955-961

Using Particles to Track Varying Numbers of Interacting People (Abstract)

Kevin Smith , IDIAP Research Institute
Daniel Gatica-Perez , IDIAP Research Institute
Jean-Marc Odobez , IDIAP Research Institute
pp. 962-969

Real-Time Multiple Objects Tracking with Occlusion Handling in Dynamic Scenes (Abstract)

Jing Li , Northwestern Polytechnical University
Stan Z. Li , Chinese Academy of Sciences
Quan Pan , Northwestern Polytechnical University
Tao Yang , Northwestern Polytechnical University
pp. 970-975

Real-Time Wide Area Multi-Camera Stereo Tracking (Abstract)

Tao Zhao , Sarnoff Corporation
Harpreet Sawhney , Sarnoff Corporation
Manoj Aggarwal , Sarnoff Corporation
Rakesh Kumar , Sarnoff Corporation
pp. 976-983

Actions Sketch: A Novel Action Representation (Abstract)

Mubarak Shah , University of Central Florida
Alper Yilmaz , University of Central Florida
pp. 984-989

A Unified Framework for Tracking through Occlusions and across Sensor Gaps (Abstract)

Anthony Hoogs , General Electric Global Research
Robert Kaucic , General Electric Global Research
Glen Brooksby , General Electric Global Research
John Kaufhold , General Electric Global Research
A. G. Amitha Perera , General Electric Global Research
pp. 990-997

Conformal Deskewing of Non-Planar Documents (Abstract)

Michael S. Brown , California State University at Monterey Bay
pp. 998-1004

A Nonlinear Approach for Face Sketch Synthesis and Recognition (Abstract)

Hanqing Lu , Chinese Academy of Science
Songde Ma , Chinese Academy of Science
Xiaoou Tang , Chinese University of Hong Kong and Microsoft Research Asia
Qingshan Liu , Chinese University of Hong Kong and Chinese Academy of Science
Hongliang Jin , Chinese University of Hong Kong and Chinese Academy of Science
pp. 1005-1010

Semi-Supervised Learning Based Object Detection in Aerial Imagery (Abstract)

Zhongfei (Mark) Zhang , State University of New York at Binghamton
Jian Yao , State University of New York at Binghamton
pp. 1011-1016

Image Denoising Using Non-Negative Sparse Coding Shrinkage Algorithm (Abstract)

Deshuang Huang , Chinese Academy of Sciences
Li Shang , Chinese Academy of Sciences
pp. 1017-1022

A Statistical Field Model for Pedestrian Detection (Abstract)

Gang Hua , Northwestern University
Ting Yu , Northwestern University
Ying Wu , Northwestern University
pp. 1023-1030

Detection and Explanation of Anomalous Activities: Representing Activities as Bags of Event n-Grams (Abstract)

Charles Isbell , Georgia Institute of Technology
Graham Coleman , Georgia Institute of Technology
Samir Batta , Georgia Institute of Technology
Amos Johnson , Georgia Institute of Technology
Raffay Hamid , Georgia Institute of Technology
Aaron Bobick , Georgia Institute of Technology
pp. 1031-1038

Tracking Multiple Mouse Contours (without Too Many Samples) (Abstract)

Serge Belongie , University of California at San Diego
Kristin Branson , University of California at San Diego
pp. 1039-1046

A Slit Scanning Depth of Route Panorama from Stationary Blur (Abstract)

Min Shi , Indiana University Purdue University Indianapolis
Jiang Yu Zheng , Indiana University Purdue University Indianapolis
pp. 1047-1054

Correspondence Expansion for Wide Baseline Stereo (Abstract)

Parris K. Egbert , Brigham Young University
Kevin L. Steele , Brigham Young University
pp. 1055-1062

Feature Uncertainty Arising from Covariant Image Noise (Abstract)

R. Matt Steele , University of Kentucky
Christopher Jaynes , University of Kentucky
pp. 1063-1070

Fast Illumination-Invariant Background Subtraction Using Two Views: Error Analysis, Sensor Placement and Applications (Abstract)

Larry S. Davis , University of Maryland at College Park
Nikos Paragios , Ecole Nationale des Ponts et Chaussees
Ser-Nam Lim , University of Maryland at College Park
Anurag Mittal , Siemens Corporate Research
pp. 1071-1078

Colour Constancy Using the Chromagenic Constraint (Abstract)

S. D. Hordley , University of East Anglia
P. Morovic , University of East Anglia
G. D. Finlayson , University of East Anglia
pp. 1079-1086

Detecting Doctored Images Using Camera Response Normality and Consistency (Abstract)

Xiaoou Tang , Microsoft Research Asia
Heung-Yeung Shum , Microsoft Research Asia
Zhouchen Lint , Microsoft Research Asia
Rongrong Wang , Fudan University
pp. 1087-1092

Towards Complete Generic Camera Calibration (Abstract)

Suresh K. Lodha , University of California at Santa Cruz
Srikumar Ramalingam , University of California at Santa Cruz
Peter Sturm , INRIA Rh?ne-Alpes, GRAVIR-CNRS
pp. 1093-1098

Guided Sampling via Weak Motion Models and Outlier Sample Generation for Epipolar Geometry Estimation (Abstract)

Ilan Shimshoni , Technion - Israel Institute of Technology
Liran Goshen , Technion - Israel Institute of Technology
pp. 1105-1112

The Modified pbM-Estimator Method and a Runtime Analysis Technique for the RANSAC Family (Abstract)

Stas Rozenfeld , Technion - Israel Institute of Technology
Ilan Shimshoni , Technion - Israel Institute of Technology
pp. 1113-1120

A Sparse Support Vector Machine Approach to Region-Based Image Categorization (Abstract)

James Z. Wang , Pennsylvania State University
Jinbo Bi , Siemens Medical Solutions, Inc.
Yixin Chen , University of New Orleans
pp. 1121-1128

On the Localization of Straight Lines in 3D Space from Single 2D Images (Abstract)

Vincenzo Caglioti , Politecnico di Milano
Simone Gasparini , Politecnico di Milano
pp. 1129-1134

Implicit Surfaces Make for Better Silhouettes (Abstract)

Mathieu Salzmann , Ecole Polytechnique F?d?rale de Lausanne
Slobodan Ilic , Ecole Polytechnique F?d?rale de Lausanne
Pascal Fua , Ecole Polytechnique F?d?rale de Lausanne
pp. 1135-1141

Unsupervised Learning of Object Features from Video Sequences (Abstract)

Marius Leordeanu , Carnegi Mellon University
Robert Collins , Carnegi Mellon University
pp. 1142-1149

A Hybrid Graphical Model for Robust Feature Extraction from Video (Abstract)

Wojciech Zajdel , University of Amsterdam
A. Taylan Cemgil , University of Amsterdam
Ben J. A. Kröse , University of Amsterdam
pp. 1158-1165

Hybrid Models for Human Motion Recognition (Abstract)

Claudio Fanti , California Institute of Technology
Lihi Zelnik-Manor , California Institute of Technology
Pietro Perona , California Institute of Technology
pp. 1166-1173

Robust and Efficient Foreground Analysis for Real-Time Video Surveillance (Abstract)

Max Lu , IBM T.J. Watson Research Center
Arun Hampapur , IBM T.J. Watson Research Center
Ying-Li Tian , IBM T.J. Watson Research Center
pp. 1182-1187

A Direct Method for Modeling Non-Rigid Motion with Thin Plate Spline (Abstract)

Jongwoo Lim , University of Illinois at Urbana Champaign
Ming-Hsuan Yang , Honda Research Institute
pp. 1196-1202

Cloth Representation by Shape from Shading with Shading Primitives (Abstract)

Song-Chun Zhu , University of California at Los Angeles
Feng Han , University of California at Los Angeles
pp. 1203-1210

Machine Learning for Clinical Diagnosis from Functional Magnetic Resonance Imaging (Abstract)

Nora Volkow , Brookhaven National Laboratory
Dardo Tomasi , Brookhaven National Laboratory
Dimitris Samaras , State University of New York at Stony Brook
Rita Goldstein , Brookhaven National Laboratory
Lei Zhang , State University of New York at Stony Brook
pp. 1211-1217
Author Index

Author Index (PDF)

pp. 1219-1223
97 ms
(Ver )