The Community for Technology Leaders
Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. (2004)
Washington, D.C., USA
June 27, 2004 to July 2, 2004
ISSN: 1063-6919
ISBN: 0-7695-2158-4
TABLE OF CONTENTS
Poster Session 4: Object Recognition and Sensors

Automatic View Recognition in Echocardiogram Videos Using Parts-Based Representation (Abstract)

Shahram Ebadollahi , Columbia University
Shih-Fu Chang , Columbia University
Henry Wu , Columbia University
pp. 2-9

Elastic-String Models for Representation and Analysis of Planar Shapes (Abstract)

Washington Mio , Florida State University
Anuj Srivastava , Florida State University
pp. 10-15

View Independent Human Body Pose Estimation from a Single Perspective Image (Abstract)

Vasu Parameswaran , University of Marylandn at College Park
Rama Chellappa , University of Marylandn at College Park
pp. 16-22

Distortion Estimation Techniques in Solving Visual CAPTCHAs (Abstract)

Gabriel Moy , Areté Associates
Nathan Jones , Areté Associates
Curt Harkless , Areté Associates
Randall Potter , Areté Associates
pp. 23-28

Is Bottom-Up Attention Useful for Object Recognition? (Abstract)

Ueli Rutishauser , California Institute of Technology
Dirk Walther , California Institute of Technology
Christof Koch , California Institute of Technology
Pietro Perona , California Institute of Technology
pp. 37-44

Cyclic Articulated Human Motion Tracking by Sequential Ancestral Simulation (Abstract)

Cheng Chang , University of Illinois at Chicago
Rashid Ansari , University of Illinois at Chicago
Ashfaq Khokhar , University of Illinois at Chicago
pp. 45-52

Learning Object Detection from a Small Number of Examples: The Importance of Good Features (Abstract)

Kobi Levi , Hebrew University of Jerusalem
Yair Weiss , Hebrew University of Jerusalem
pp. 53-60

Shape Representation and Classification Using the Poisson Equation (Abstract)

Lena Gorelick , Weizmann Institute of Science
Meirav Galun , Weizmann Institute of Science
Eitan Sharon , Brown University
Ronen Basri , Weizmann Institute of Science
Achi Brandt , Weizmann Institute of Science
pp. 61-67

Models of Large Population Recognition Performance (Abstract)

Patrick Grother , National Institute of Standards and Technology
P. Jonathon Phillips , National Institute of Standards and Technology
pp. 68-75

Searching the Web with Mobile Images for Location Recognition (Abstract)

Tom Yeh , Massachusetts Institute of Technology
Konrad Tollmar , Massachusetts Institute of Technology
Trevor Darrell , Massachusetts Institute of Technology
pp. 76-81

Parts-Based 3D Object Classification (Abstract)

Daniel Huber , Carnegie Mellon University
Anuj Kapuria , Carnegie Mellon University
Raghavendra Donamukkala , Carnegie Mellon University
Martial Hebert , Carnegie Mellon University
pp. 82-89

Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting (Abstract)

Yann LeCun , New York University
Fu Jie Huang , New York University
Léon Bottou , NEC Labs America
pp. 97-104

Integrating Multiple Model Views for Object Recognition (Abstract)

Vittorio Ferrari , ETH Zuerich
Tinne Tuytelaars , University of Leuven
Luc Van Gool , ETH Zuerich and University of Leuven
pp. 105-112

Extraction and Integration of Window in a 3D Building Model from Ground View Images (Abstract)

Sung Chun Lee , University of Southern California
Ram Nevatia , University of Southern California
pp. 113-120

Linear Model Hashing and Batch RANSAC for Rapid and Accurate Object Recognition (Abstract)

Y. Shan , Sarnoff Corporation
B. Matei , Sarnoff Corporation
H. S. Sawhney , Sarnoff Corporation
R. Kumar , Sarnoff Corporation
D. Huber , Carnegei Mellon University
M. Hebert , Carnegei Mellon University
pp. 121-128

A Model for Dynamic Shape and Its Applications (Abstract)

Che-Bin Liu , University of Illinois at Urbana-Champaign
Narendra Ahuja , University of Illinois at Urbana-Champaign
pp. 129-134

Jitter Camera: High Resolution Video from a Low Resolution Detector (Abstract)

Moshe Ben-Ezra , Columbia University
Assaf Zomet , Columbia University
Shree K. Nayar , Columbia University
pp. 135-142

High-Zoom Video Hallucination by Exploiting Spatio-Temporal Regularities (Abstract)

Göksel Dedeoğlu , Carnegie Mellon University
Takeo Kanade , Carnegie Mellon University
Jonas August , Carnegie Mellon University
pp. 151-158

Eye Typing off the Shelf (Abstract)

Dan Witzner Hansen , IT University Copenhagen
Arthur Pece , University Copenhagen
pp. 159-164

A Flexible Projector-Camera System for Multi-Planar Displays (Abstract)

Mark Ashdown , University of Cambridge Computer Lab
Matthew Flagg , Georgia Institute of Technology
Rahul Sukthankar , Intel Research Pittsburgh and Carnegie Mellon University
James M. Rehg , Georgia Institute of Technology
pp. 165-172

Probability Models for High Dynamic Range Imaging (Abstract)

Chris Pal , Microsoft Research
Rick Szeliski , Microsoft Research
Matthew Uyttendaele , Microsoft Research
Nebojsa Jojic , Microsoft Research
pp. 173-180

Improving Object Classification in Far-Field Video (Abstract)

Biswajit Bose , Massachusetts Institute of Technology
Eric Grimson , Massachusetts Institute of Technology
pp. 181-188

Uncontrolled Modulation Imaging (Abstract)

Yoav Y. Schechner , Technion - Israel Institute Technology
Shree K. Nayar , Columbia University
pp. 197-204

Bridging the Gaps between Cameras (Abstract)

Dimitrios Makris , Kingston University
Tim Ellis , Kingston University
James Black , Kingston University
pp. 205-210

Calibrating an Air-Ground Control System from Motion Correspondences (Abstract)

Rahul Rao , University of Pennsylvania
Camillo J. Taylor , University of Pennsylvania
Vijay Kumar , University of Pennsylvania
pp. 218-225

Recovering Shape and Reflectance Model of Non-Lambertian Objects from Multiple Views (Abstract)

Tianli Yu , University of Illinois at Urbana-Champaign
Ning Xu , University of Illinois at Urbana-Champaign
Narendra Ahuja , University of Illinois at Urbana-Champaign
pp. 226-233

Computing Depth under Ambient Illumination Using Multi-Shuttered Light (Abstract)

Hector Gonzalez-Banos , Honda Research Institute
James Davis , Honda Research Institute
pp. 234-241
Session 4A: Statistical Methods - 2

Point Matching as a Classification Problem for Fast and Robust Object Pose Estimation (Abstract)

Vincent Lepetit , Swiss Federal Institute of Technology
Julien Pilet , Swiss Federal Institute of Technology
Pascal Fua , Swiss Federal Institute of Technology
pp. 244-250

Feature Selection for Classifying High-Dimensional Numerical Data (Abstract)

Yimin Wu , State University of New York at Buffalo
Aidong Zhang , State University of New York at Buffalo
pp. 251-258

Random Sampling LDA for Face Recognition (Abstract)

Xiaogang Wang , Chinese University of Hong Kong
Xiaoou Tang , Chinese University of Hong Kong
pp. 259-265
Session 4B: Learning

BoostMap: A Method for Efficient Approximate Similarity Rankings (Abstract)

Vassilis Athitsos , Boston University
Jonathan Alon , Boston University
Stan Sclaroff , Boston University
George Kollios , Boston University
pp. 268-275

Automatic Cascade Training with Perturbation Bias (Abstract)

Jie Sun , Georgia Institute of Technology
James M. Rehg , Georgia Institute of Technology
Aaron Bobick , Georgia Institute of Technology
pp. 276-283

A Discriminative Learning Framework with Pairwise Constraints for Video Object Classification (Abstract)

Rong Yan , Carnegie Mellon University
Jian Zhang , Carnegie Mellon University
Jie Yang , Carnegie Mellon University
Alexander Hauptmann , Carnegie Mellon University
pp. 284-291
Session 5A: Motion - 1

High-Speed Videography Using a Dense Camera Array (Abstract)

Bennett Wilburn , Stanford University
Neel Joshi , Stanford University
Vaibhav Vaish , Stanford University
Marc Levoy , Stanford University
Mark Horowitz , Stanford University
pp. 294-301

Motion-Based Background Subtraction Using Adaptive Kernel Density Estimation (Abstract)

Anurag Mittal , Siemens Corporate Research
Nikos Paragios , C.E.R.T.I.S. Ecole Nationale de Ponts et Chaussees
pp. 302-309

Motion Segmentation with Missing Data Using PowerFactorization and GPCA (Abstract)

René Vidal , Johns Hopkins University and National ICT Australia
Richard Hartley , Australian National University and National ICT Australia
pp. 310-316
Session 5B: Object Recognition

Recovering Human Body Configurations: Combining Segmentation and Recognition (Abstract)

Greg Mori , University of California at Berkeley
Xiaofeng Ren , University of California at Berkeley
Alexei A. Efros , University of Oxford
Jitendra Malik , University of California at Berkeley
pp. 326-333

Proposal Maps Driven MCMC for Estimating Human Body Pose in Static Images (Abstract)

Mun Wai Lee , University of Southern California
Isaac Cohen , University of Southern California
pp. 334-341

Representation and Matching of Articulated Shapes (Abstract)

Jiayong Zhang , Carnegie Mellon University
Robert Collins , Carnegie Mellon University
Yanxi Liu , Carnegie Mellon University
pp. 342-349

2D-Shape Analysis Using Conformal Mapping (Abstract)

E. Sharon , Brown University
D. Mumford , Brown University
pp. 350-357
Session 6A: Applications I

Faster Graph-Theoretic Image Processing via Small-World and Quadtree Topologies (Abstract)

Leo Grady , Siemens Corporate Research
Eric L. Schwartz , Boston University
pp. 360-365

Detecting and Reading Text in Natural Scenes (Abstract)

Xiangrong Chen , University of California at Los Angeles
Alan L. Yuille , University of California at Los Angeles
pp. 366-373

Bayesian Face Recognition Using Support Vector Machine and Face Clustering (Abstract)

Zhifeng Li , Chinese University of Hong Kong
Xiaoou Tang , Chinese University of Hong Kong
pp. 374-380

How Features of the Human Face Affect Recognition: A Statistical Comparison of Three Face Recognition Algorithms (Abstract)

G. Givens , Colorado State University
J. R. Beveridge , Colorado State University
B. A. Draper , Colorado State University
P. Grother , NIST
pp. 381-388
Session 6B: Detection Tracking - 2

Novel Region-Based Modeling for Human Detection within Highly Dynamic Aquatic Environment (Abstract)

How-Lung Eng , 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. 390-397

Tracking Multiple Humans in Crowded Environment (Abstract)

Tao Zhao , Sarnoff Corporation
Ram Nevatia , University of Southern California
pp. 406-413

Efficient Model-Based Linear Head Motion Recovery from Movies (Abstract)

Jian Yao , Chinese University of Hong Kong,
Wai-Kuen Cham , Chinese University of Hong Kong
pp. 414-421
Poster Session 5: Statistical Methods

Multiobjective Data Clustering (Abstract)

Martin H. C. Law , Michigan State University
Alexander P. Topchy , Michigan State University
Anil K. Jain , Michigan State University
pp. 424-430

An Invariant, Closed-Form Solution for Matching Sets of 3D Lines (Abstract)

Behzad Kamgar-Parsi , Office of Naval Research
Behrooz Kamgar-Parsi , Naval Research Laboratory
pp. 431-436

Spatially Coherent Clustering Using Graph Cuts (Abstract)

Ramin Zabih , Cornell University
Vladimir Kolmogorov , Microsoft Research
pp. 437-444

A Probabilistic Framework for Combining Tracking Algorithms (Abstract)

Ido Leichter , Technion - Israel Institute of Technology
Michael Lindenbaum , Technion - Israel Institute of Technology
Ehud Rivlin , Technion - Israel Institute of Technology
pp. 445-451

Local Smoothing for Manifold Learning (Abstract)

JinHyeong Park , Pennsylvania State University
Zhenyue Zhang , Zhejiang University
Hongyuan Zha , Pennsylvania State University
Rangachar Kasturi , University of South Florida
pp. 452-459

Grouping with Bias Revisited (Abstract)

Richard Nock , DSI/University Antilles-Guyane
Frank Nielsen , Sony CS Labs Inc.
pp. 460-465

Graphical Models for Graph Matching (Abstract)

Tibério S. Caetano , University of Alberta and Universidade Federal do Rio Grande do Sul
Terry Caelli , University of Alberta
Dante A. C. Barone , Universidade Federal do Rio Grande do Sul
pp. 466-473

Linear Projection Methods in Face Recognition under Unconstrained Illuminations: A Comparative Study (Abstract)

Qi Li , University of Delaware
Jieping Ye , University of Minnesota
Chandra Kambhamettu , University of Delaware
pp. 474-481

Object-Based Image Retrieval Using the Statistical Structure of Images (Abstract)

Derek Hoiem , Carnegie Mellon University
Rahul Sukthankar , Carnegie Mellon University and Intel Research Pittsburgh
Henry Schneiderman , Carnegie Mellon University
Larry Huston , Intel Research Pittsburgh
pp. 490-497

Generalized Quotient Image (Abstract)

Haitao Wang , Chinese Academy of Sciences
Stan Z. Li , Microsoft Research Asia
Yangsheng Wang , Chinese Academy of Sciences
pp. 498-505

PCA-SIFT: A More Distinctive Representation for Local Image Descriptors (Abstract)

Yan Ke , Carnegie Mellon University
Rahul Sukthankar , Carnegie Mellon University and Intel Research Pittsburgh
pp. 506-513

Biventricular Myocardial Kinematics Based on Tagged MRI from Anatomical NURBS Models (Abstract)

N. J. Tustison , Washington University in St. Louis
D. Abendschein , Washington University in St. Louis
A. A. Amini , Washington University in St. Louis
pp. 514-519

Probabilistic Expression Analysis on Manifolds (Abstract)

Ya Chang , University of California at Santa Barbara
Changbo Hu , University of California at Santa Barbara
Matthew Turk , University of California at Santa Barbara
pp. 520-527

Invariant Operators, Small Samples, and the Bias-Variance Dilemma (Abstract)

X. Shi , University of California at Santa Cruz
R. Manduchi , University of California at Santa Cruz
pp. 528-534

Real-Time Combined 2D+3D Active Appearance Models (Abstract)

Jing Xiao , Carnegie Mellon University
Simon Baker , Carnegie Mellon University
Iain Matthews , Carnegie Mellon University
Takeo Kanade , Carnegie Mellon University
pp. 535-542

On the Distribution of Saliency (Abstract)

Alexander Berengolts , Technion - Israel Institute of Technology
Michael Lindenbaum , Technion - Israel Institute of Technology
pp. 543-549

Approximation of Canonical Sets and Their Applications to 2D View Simplification (Abstract)

Trip Denton , Drexel University
Jeff Abrahamson , Drexel University
Ali Shokoufandeh , Drexel University
pp. 550-557

Learning Classifiers from Imbalanced Data Based on Biased Minimax Probability Machine (Abstract)

Kaizhu Huang , Chinese University of Hong Kong
Haiqin Yang , Chinese University of Hong Kong
Irwin King , Chinese University of Hong Kong
Michael R. Lyu , Chinese University of Hong Kong
pp. 558-563

Dual-Space Linear Discriminant Analysis for Face Recognition (Abstract)

Xiaogang Wang , Chinese University of Hong Kong
Xiaoou Tang , Chinese University of Hong Kong
pp. 564-569

Learning Distance Functions for Image Retrieval (Abstract)

Tomer Hertz , Hebrew University of Jerusalem
Aharon Bar-Hillel , Hebrew University of Jerusalem
Daphna Weinshall , Hebrew University of Jerusalem
pp. 570-577

Cue Integration through Discriminative Accumulation (Abstract)

M.E. Nilsback , Computational Vision and Active Perception Laboratory
B. Caputo , Computational Vision and Active Perception Laboratory
pp. 578-585

Orthogonal Complement Component Analysis for Positive Samples in SVM Based Relevance Feedback Image Retrieval (Abstract)

Dacheng Tao , Chinese University of Hong Kong
Xiaoou Tang , Chinese University of Hong Kong
pp. 586-591

Robust Subspace Clustering by Combined Use of kNND Metric and SVD Algorithm (Abstract)

Qifa Ke , Carnegie Mellon University
Takeo Kanade , Carnegie Mellon University
pp. 592-599

Direct Super-Resolution and Registration Using Raw CFA Images (Abstract)

Tomomasa Gotoh , Tokyo Institute of Technology
Masatoshi Okutomi , Tokyo Institute of Technology
pp. 600-607

Variational Mixture Smoothing for Non-Linear Dynamical Systems (Abstract)

Cristian Sminchisescu , University of Toronto
Allan Jepson , University of Toronto
pp. 608-615

Self-Normalized Linear Tests (Abstract)

Sachin Gangaputra , Johns Hopkins University
Donald Geman , Johns Hopkins University
pp. 616-622

Bayesian Fusion of Camera Metadata Cues in Semantic Scene Classification (Abstract)

Matthew Boutell , University of Rochester
Jiebo Luo , Eastman Kodak Company
pp. 623-630

Minimum Effective Dimension for Mixtures of Subspaces: A Robust GPCA Algorithm and Its Applications (Abstract)

Kun Huang , University of Illinois at Urbana-Champaign
Yi Ma , University of Illinois at Urbana-Champaign
René Vidal , Johns Hopkins University
pp. 631-638

Random Sampling Based SVM for Relevance Feedback Image Retrieval (Abstract)

Dacheng Tao , Chinese University of Hong Kong
Xiaoou Tang , Chinese University of Hong Kong
pp. 647-652

Reconstructing Open Surfaces from Unorganized Data Points (Abstract)

Jan Erik Solem , Malm? University
Anders Heyden , Malm? University
pp. 653-660

Inference of Multiple Subspaces from High-Dimensional Data and Application to Multibody Grouping (Abstract)

Zhimin Fan , Tsinghua University
Jie Zhou , Tsinghua University
Ying Wu , Northwestern University
pp. 661-666

Efficient Graphical Models for Processing Images (Abstract)

Marshall F. Tappen , Massachusetts Institute of Technology
Bryan C. Russell , Massachusetts Institute of Technology
William T. Freeman , Massachusetts Institute of Technology
pp. 673-680

A Fast Multigrid Implicit Algorithm for the Evolution of Geodesic Active Contours (Abstract)

George Papandreou , National Technical University of Athens
Petros Maragos , National Technical University of Athens
pp. 689-694

Multiscale Conditional Random Fields for Image Labeling (Abstract)

Xuming He , University of Toronto
Richard S. Zemel , University of Toronto
Miguel Á. Carreira-Perpiñán , University of Toronto
pp. 695-702
Poster Session 6: Surveillance and Recognition

Studies on Silhouette Quality and Gait Recognition (Abstract)

Zongyi Liu , University of South Florida
Laura Malave , University of South Florida
Sudeep Sarkar , University of South Florida
pp. 704-711

Diffeomorphic Matching of Distributions: A New Approach for Unlabelled Point-Sets and Sub-Manifolds Matching (Abstract)

Joan Glaunes , LAGA, Université Paris 13
Alain Trouvé , CMLA, ENS de Cachan
Laurent Younes , CIS, Johns Hopkins University
pp. 712-718

Face Localization via Hierarchical CONDENSATION with Fisher Boosting Feature Selection (Abstract)

Jilin Tu , University of Illinois at Urbana-Champaign
Zhenqiu Zhang , University of Illinois at Urbana-Champaign
Zhihong Zeng , University of Illinois at Urbana-Champaign
Thomas Huang , University of Illinois at Urbana-Champaign
pp. 719-724

Shaping Receptive Fields for Affine Invariance (Abstract)

S. Ravela , Massachusetts Institute of Technology
pp. 725-730

Multigrid and Multi-Level Swendsen-Wang Cuts for Hierarchic Graph Partition (Abstract)

Adrian Barbu , University of California at Los Angeles
Song-Chun Zhu , University of California at Los Angeles
pp. 731-738

A Graphical Model Framework for Coupling MRFs and Deformable Models (Abstract)

Rui Huang , Rutgers University
Vladimir Pavlovic , Rutgers University
Dimitris N. Metaxas , Rutgers University
pp. 739-746

Flexible Spatial Models for Grouping Local Image Features (Abstract)

Gustavo Carneiro , University of Toronto
Allan D. Jepson , University of Toronto
pp. 747-754

Asymmetrically Boosted HMM for Speech Reading (Abstract)

Pei Yin , Georgia Institute of Technology
Irfan Essa , Georgia Institute of Technology
James M. Rehg , Georgia Institute of Technology
pp. 755-761

Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection (Abstract)

Antonio Torralba , Massachusetts Institute of Technology
Kevin P. Murphy , Massachusetts Institute of Technology
William T. Freeman , Massachusetts Institute of Technology
pp. 762-769

Scalable Discriminant Feature Selection for Image Retrieval and Recognition (Abstract)

Nuno Vasconcelos , University of California at San Diego
Manuela Vasconcelos , Harvard University
pp. 770-775

What Image Information Is Important in Silhouette-Based Gait Recognition? (Abstract)

G.V. Veres , University of Southampton
L. Gordon , University of Southampton
J.N. Carter , University of Southampton
M.S. Nixon , University of Southampton
pp. 776-782

Modelling the Effects of Walking Speed on Appearance-Based Gait Recognition (Abstract)

Rawesak Tanawongsuwan , Georgia Institute of Technology
Aaron Bobick , Georgia Institute of Technology
pp. 783-790

Efficient Search of Faces from Complex Line Drawings (Abstract)

Jianzhuang Liu , Chinese University of Hong Kong
Xiaoou Tang , Chinese University of Hong Kong
pp. 791-796

A Discriminative Feature Space for Detecting and Recognizing Faces (Abstract)

Abdenour Hadid , Infotech Oulu and University of Oulu
Matti Pietikäinen , Infotech Oulu and University of Oulu
Timo Ahonen , Infotech Oulu and University of Oulu
pp. 797-804

Probabilistic Identity Characterization for Face Recognition (Abstract)

Shaohua Kevin Zhou , University of Maryland at College Park
Rama Chellappa , University of Maryland at College Park
pp. 805-812

Effect of Colorspace Transformation, the Illuminance Component, and Color Modeling on Skin Detection (Abstract)

Sriram Jayaram , University of North Carolina at Charlotte
Stephen Schmugge , University of North Carolina at Charlotte
Min C. Shin , University of North Carolina at Charlotte
Leonid V. Tsap , Lawrence Livermore National Laboratory
pp. 813-818

Detecting Unusual Activity in Video (Abstract)

Hua Zhong , Carnegie Mellon University
Jianbo Shi , University of Pennsylvania
Mirkó Visontai , University of Pennsylvania
pp. 819-826

A Cognitive Vision System for Action Recognition in Office Environments (Abstract)

C. Bauckhage , Bielefeld University
M. Hanheide , Bielefeld University
S. Wrede , Bielefeld University
G. Sagerer , Bielefeld University
pp. 827-833

"Corefaces" - Robust Shift Invariant PCA Based Correlation Filter for Illumination Tolerant Face Recognition (Abstract)

Marios Savvides , Carnegie Mellon University
B.V.K. Vijaya Kumar , Carnegie Mellon University
P.K. Khosla , Carnegie Mellon University
pp. 834-841

Statistical Feature Fusion for Gait-Based Human Recognition (Abstract)

Ju Han , University of California at Riverside
Bir Bhanu , University of California at Riverside
pp. 842-847

Names and Faces in the News (Abstract)

Tamara L. Berg , University of California at Berkeley
Alexander C. Berg , University of California at Berkeley
Jaety Edwards , University of California at Berkeley
Michael Maire , University of California at Berkeley
Ryan White , University of California at Berkeley
Yee-Whye Teh , University of California at Berkeley
Erik Learned-Miller , University of California at Berkeley
D. A. Forsyth , University of California at Berkeley
pp. 848-854

A GMM Parts Based Face Representation for Improved Verification through Relevance Adaptation (Abstract)

Simon Lucey , Carnegie Mellon University
Tsuhan Chen , Carnegie Mellon University
pp. 855-861

Propagation Networks for Recognition of Partially Ordered Sequential Action (Abstract)

Yifan Shi , Georgia Institute of Technology
Yan Huang , Georgia Institute of Technology
David Minnen , Georgia Institute of Technology
Aaron Bobick , Georgia Institute of Technology
Irfan Essa , Georgia Institute of Technology
pp. 862-869

Facial Event Classification with Task Oriented Dynamic Bayesian Network (Abstract)

Haisong Gu , University of Nevada Reno
Qiang Ji , Rensselaer Polytechnic Institute
pp. 870-875

Probabilistic Data Association Methods in Visual Tracking of Groups (Abstract)

G. Gennari , University of Padova
G. D. Hager , Johns Hopkins University
pp. 876-881

3D Human Pose from Silhouettes by Relevance Vector Regression (Abstract)

Ankur Agarwal , GRAVIR-INRIA-CNRS
Bill Triggs , GRAVIR-INRIA-CNRS
pp. 882-888

Local Facial Asymmetry for Expression Classification (Abstract)

Sinjini Mitra , Carnegie Mellon University
Yanxi Liu , Carnegie Mellon University
pp. 889-894

Frame Synchronization and Multi-Level Subspace Analysis for Video Based Face Recognition (Abstract)

Xiaoou Tang , Chinese University of Hong Kong
Zhifeng Li , Chinese University of Hong Kong
pp. 902-907

Alignment of continuous video onto 3D point clouds (Abstract)

W. Zhao , Sarnoff Corp., Princeton, NJ, USA
D. Nister , Sarnoff Corp., Princeton, NJ, USA
S. Hsu , Sarnoff Corp., Princeton, NJ, USA
pp. 0
Poster Session 6: Surveillance and Recognition

Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects (Abstract)

Fred Rothganger , University of Illinois at Urbana-Champaign
Svetlana Lazebnik , University of Illinois at Urbana-Champaign
Cordelia Schmid , INRIA Rhône-Alpes
Jean Ponce , University of Illinois at Urbana-Champaign
pp. 914-921

From Facial Expression to Level of Interest: A Spatio-Temporal Approach (Abstract)

M. Yeasin , State University New York Institute of Technology
B. Bullot , Pennsylvania State University
R. Sharma , Pennsylvania State University
pp. 922-927

Integrating and Employing Multiple Levels of Zoom for Activity Recognition (Abstract)

Paul Smith , University of Central Florida
Mubarak Shah , University of Central Florida
Niels da Vitoria Lobo , University of Central Florida
pp. 928-935
Session 7A: Low Level Vision - 2

Radiometric Calibration from a Single Image (Abstract)

Stephen Lin , Microsoft Research Asia
Jinwei Gu , Tsinghua University
Shuntaro Yamazaki , University of Tokyo
Heung-Yeung Shum , Microsoft Research Asia
pp. 938-945

Color Lines: Image Specific Color Representation (Abstract)

Ido Omer , Hebrew University of Jerusalem
Michael Werman , Hebrew University of Jerusalem
pp. 946-953

Learning to Segment Images Using Region-Based Perceptual Features (Abstract)

John Kaufhold , General Electric Global Research Center
Anthony Hoogs , General Electric Global Research Center
pp. 954-961
Session 7B: Motion - 2

Alignment of Continuous Video onto 3D Point Clouds (Abstract)

W. Zhao , Sarnoff Corporation
D. Nister , Sarnoff Corporation
S. Hsu , Sarnoff Corporation
pp. 964-971

Motion Layer Extraction in the Presence of Occlusion Using Graph Cut (Abstract)

Jiangjian Xiao , University of Central Florida
Mubarak Shah , University of Central Florida
pp. 972-979

A Rao-Blackwellized Particle Filter for EigenTracking (Abstract)

Zia Khan , Georgia Institute of Technology
Tucker Balch , Georgia Institute of Technology
Frank Dellaert , Georgia Institute of Technology
pp. 980-986
Session 8A: Retrieval/Annotation

Unsupervised Learning of Image Manifolds by Semidefinite Programming (Abstract)

Kilian Q. Weinberger , University of Pennsylvania
Lawrence K. Saul , University of Pennsylvania
pp. 988-995

Hidden Semantic Concept Discovery in Region Based Image Retrieval (Abstract)

Ruofei Zhang , State University of New York at Binghamton
Zhongfei (Mark) Zhang , State University of New York at Binghamton
pp. 996-1001

Multiple Bernoulli Relevance Models for Image and Video Annotation (Abstract)

S. L. Feng , University of Massachusetts at Amherst
R. Manmatha , University of Massachusetts at Amherst
V. Lavrenko , University of Massachusetts at Amherst
pp. 1002-1009
Session 8B: Applications - 2

Thermal Face Recognition in an Operational Scenario (Abstract)

Diego A. Socolinsky , Equinox Corporation
Andrea Selinger , Equinox Corporation
pp. 1012-1019

Audio-Visual Based Emotion Recognition — A New Approach (Abstract)

Mingli Song , Zhejiang University
Jiajun Bu , Zhejiang University
Chun Chen , Zhejiang University
Nan Li , Zhejiang University
pp. 1020-1025

Value Directed Learning of Gestures and Facial Displays (Abstract)

Jesse Hoey , University of British Columbia
James J. Little , University of British Columbia
pp. 1026-1033

Accurate Face Models from Uncalibrated and Ill-Lit Video Sequences (Abstract)

M. Dimitrijevic , Swiss Federal Institute of Technology
S. Ilic , Swiss Federal Institute of Technology
P. Fua , Swiss Federal Institute of Technology
pp. 1034-1041
Author Index

Author Index (PDF)

pp. 1043-1049
95 ms
(Ver 3.3 (11022016))