The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (2006)
New York, NY
June 17, 2006 to June 22, 2006
ISSN: 1063-6919
ISBN: 0-7695-2597-0
TABLE OF CONTENTS
Introduction

Reviewers (PDF)

pp. xxx-xxxiii

Space-Time Video Montage (Abstract)

Hong-Wen Kang , University of Science and Technology of China, Hefei, China
pp. 1331-1338
Introduction

Program Committee (PDF)

pp. xxix

Reviewers (PDF)

pp. xxx-xxxiii
Oral Session 8: Graphics and Image Synthesis

Clustering Appearance for Scene Analysis (Abstract)

Sanjeev J. Koppal , Carnegie Mellon University, Pittsburgh, USA
Srinivasa G. Narasimhan , Carnegie Mellon University, Pittsburgh, USA
pp. 1323-1330

Space-Time Video Montage (Abstract)

Xue-Quan Chen , University of Science and Technology of China, Hefei, China
Xiaoou Tang , Microsoft Research Asia, Beijing, China
Hong-Wen Kang , University of Science and Technology of China, Hefei, China
Yasuyuki Matsushita , Microsoft Research Asia, Beijing, China
pp. 1331-1338

Fast Compact City Modeling for Navigation Pre-Visualization (Abstract)

Luc Van Gool , Katholieke Universiteit Leuven, Belgium
Nico Cornelis , Katholieke Universiteit Leuven, Belgium
Kurt Cornelis , Katholieke Universiteit Leuven, Belgium
pp. 1339-1344

Single View Reconstruction of Curved Surfaces (Abstract)

Mukta Prasad , University of Oxford, U.K.
Andrew Fitzgibbon , Microsoft Research, Cambridge, U.K.
pp. 1345-1354
Poster Session 7: Recognition

Recognize High Resolution Faces: From Macrocosm to Microcosm (Abstract)

Xiaoou Tang , Microsoft Research Asia Beijing, China
Dahua Lin , Chinese University of Hong Kong
pp. 1355-1362

Local Steerable Phase (LSP) Feature for Face Representation and Recognition (Abstract)

ZHANG Xiaoxun , Beijing Institute of Technology, Beijing 100081, P.R. CHINA
JIA Yunde , Beijing Institute of Technology, Beijing 100081, P.R. CHINA
pp. 1363-1368

Fusion of Summation Invariants in 3D Human Face Recognition (Abstract)

Yu Hen Hu , University of Wisconsin-Madison, WI
Nigel Boston , University of Wisconsin-Madison, WI
Wei-Yang Lin , University of Wisconsin-Madison, WI
Kin-Chung Wong , University of Wisconsin-Madison, WI
pp. 1369-1376

Deformation Modeling for Robust 3D Face Matching (Abstract)

Anil K. Jain , Michigan State University
Xiaoguang Lu , Michigan State University
pp. 1377-1383

Locally Linear Models on Face Appearance Manifolds with Application to Dual-Subspace Based Classification (Abstract)

Dit-Yan Yeung , Hong Kong University of Science and Technology
Wei Fan , Hong Kong University of Science and Technology
pp. 1384-1390

3D Face Recognition Using 3D Alignment for PCA (Abstract)

Tanya Peters , Sandia National Labs Albuquerque, NM
Chris Boehnen , University of Notre Dame
Trina Russ , Sandia National Labs Albuquerque, NM
pp. 1391-1398

3D Facial Expression Recognition Based on Primitive Surface Feature Distribution (Abstract)

Jun Wang , State University of New York at Binghamton, NY, 13902, USA
Xiaozhou Wei , State University of New York at Binghamton, NY, 13902, USA
Yi Sun , State University of New York at Binghamton, NY, 13902, USA
Lijun Yin , State University of New York at Binghamton, NY, 13902, USA
pp. 1399-1406

Face Recognition using 2.5D Shape Information (Abstract)

Edwin R. Hancock , The University of York, UK
William A. P. Smith , The University of York, UK
pp. 1407-1414

Joint Boosting Feature Selection for Robust Face Recognition (Abstract)

Rong Xiao , Microsoft Research Asia, Beijing, 100080, P. R. China
Wujun Li , National Laboratory for Novel Software Technology
Yuandong Tian , Shanghai Jiaotong University, China
Xiaoou Tang , Microsoft Research Asia, Beijing, 100080, P. R. China
pp. 1415-1422

A Generalized EM Approach for 3D Model Based Face Recognition under Occlusions (Abstract)

Luc Van Gool , K.U.Leuven ESAT-PSI, Leuven, Belgium
Rik Fransens , K.U.Leuven ESAT-PSI, Leuven, Belgium
Michael De Smet , K.U.Leuven ESAT-PSI, Leuven, Belgium
pp. 1423-1430

Learning Exemplar-Based Categorization for the Detection of Multi-View Multi-Pose Objects (Abstract)

Ying Shan , Sarnoff Corporation 201 Washington Road Princeton, NJ
Feng Han , Sarnoff Corporation 201 Washington Road Princeton, NJ
Rakesh Kumar , Sarnoff Corporation 201 Washington Road Princeton, NJ
Harpreet S. Sawhney , Sarnoff Corporation 201 Washington Road Princeton, NJ
pp. 1431-1438

Optimal Pose for Face Recognition (Abstract)

Tsuhan Chen , Carnegie Mellon University Pittsburgh, PA
Xiaoming Liu , General Electric Global Research Center Schenectady, NY
Jens Rittscher , General Electric Global Research Center Schenectady, NY
pp. 1439-1446

A Visual Vocabulary for Flower Classification (Abstract)

Maria-Elena Nilsback , University of Oxford, United Kingdom
Andrew Zisserman , University of Oxford, United Kingdom
pp. 1447-1454

Searching Off-line Arabic Documents (Abstract)

Jim Chan , University of Illinois, Urbana
David Forsyth , University of Illinois, Urbana
Celal Ziftci , University of Illinois, Urbana
pp. 1455-1462

Animals on the Web (Abstract)

Tamara L. Berg , University of California, Berkeley
David A. Forsyth , University of Illinois, Urbana-Champaign
pp. 1463-1470

Aligning ASL for Statistical Translation Using a Discriminative Word Model (Abstract)

David Forsyth , University of Illinois at Urbana-Champai
Ali Farhadi , University of Illinois at Urbana-Champai
pp. 1471-1476

A Graph Based Approach for Naming Faces in News Photos (Abstract)

Derya Ozkan , Bilkent University, Turkey
P? Duygulu , Bilkent University, Turkey
pp. 1477-1482

AnnoSearch: Image Auto-Annotation by Search (Abstract)

Xin-Jing Wang , Microsoft Research Asia, 49 Zhichun Road, Beijing, China
Wei-Ying Ma , Microsoft Research Asia, 49 Zhichun Road, Beijing, China
Feng Jing , Microsoft Research Asia, 49 Zhichun Road, Beijing, China
Lei Zhang , Microsoft Research Asia, 49 Zhichun Road, Beijing, China
pp. 1483-1490

Fast Human Detection Using a Cascade of Histograms of Oriented Gradients (Abstract)

Kwang-Ting Cheng , University of California at Santa Barbara, CA
Mei-Chen Yeh , University of California at Santa Barbara, CA
Qiang Zhu , University of California at Santa Barbara, CA
Shai Avidan , Mitsubishi Electric Research Laboratories 201 Broadway, Cambridge, MA
pp. 1491-1498

Real-time Hand Pose Recognition Using Low-Resolution Depth Images (Abstract)

Zhenyao Mo , University of Southern California
Ulrich Neumann , University of Southern California
pp. 1499-1505

A Detection Technique for Degraded Face Images (Abstract)

Shinji Hayashi , Tokyo Institute of Technology
Osamu Hasegawa , PRESTO, Japan Science and Technology Agency (JST)
pp. 1506-1512

Automatic Cast Listing in Feature-Length Films with Anisotropic Manifold Space (Abstract)

Ognjen Arandjelovic , University of Cambridge, UK
Roberto Cipolla , University of Cambridge, UK
pp. 1513-1520

Person Reidentification Using Spatiotemporal Appearance (Abstract)

Richard Hartley , Australian National University Canberra, Australia
Niloofar Gheissari , National ICT Canberra, Australia
Thomas B. Sebastian , GE Global Research Niskayuna, NY, USA
pp. 1528-1535

Body Localization in Still Images Using Hierarchical Models and Hybrid Search (Abstract)

Yanxi Liu , Carnegie Mellon Univ., PA
Jiayong Zhang , Carnegie Mellon Univ., PA
Robert Collins , Pennsylvania State Univ., PA
Jiebo Luo , Kodak Research Lab, NY
pp. 1536-1543

Probabilistic 3D Polyp Detection in CT Images: The Role of Sample Alignment (Abstract)

Dorin Comaniciu , Siemens Corporate Research,
Luca Bogoni , CAD Solutions, Siemens Medical Solutions
Adrian Barbu , Siemens Corporate Research
Zhuowen Tu , UCLA
Xiang Sean Zhou , CAD Solutions, Siemens Medical Solutions
pp. 1544-1551

Modeling and Classifying Breast Tissue Density in Mammograms (Abstract)

Anna Bosch , University of Girona
Joan Marti , University of Girona
Arnau Oliver , University of Girona
Xavier Munoz , University of Girona
pp. 1552-1558

Image-Based Multiclass Boosting and Echocardiographic View Classification (Abstract)

B. Georgescu , Siemens Corporate Research, Princeton, NJ
S. Kevin Zhou , Siemens Corporate Research, Princeton, NJ
J.H. Park , Siemens Corporate Research, Princeton, NJ
D. Comaniciu , Siemens Corporate Research, Princeton, NJ
J. Otsuki , Siemens Medical Solutions, Mountain View, CA
C. Simopoulos , Siemens Medical Solutions, Mountain View, CA
pp. 1559-1565

Performance Modeling and Prediction of Face Recognition Systems (Abstract)

Peng Wang , University of Pennsylvani
Qiang Ji , Rensselaer Polytechnic Institute
pp. 1566-1573

Multiple Face Model of Hybrid Fourier Feature for Large Face Image Set (Abstract)

Seok-Cheol Kee , Samsung Advanced Institute of Technology
Jongha Lee , Samsung Advanced Institute of Technology
Gyutae Park , Samsung Advanced Institute of Technology
Wonjun Hwang , Samsung Advanced Institute of Technology
pp. 1574-1581

Multi-Aspect Detection of Articulated Objects (Abstract)

Bernt Schiele , Darmstadt University of Technology
Bastian Leibe , Darmstadt University of Technology
Edgar Seemann , Darmstadt University of Technology
pp. 1582-1588

Towards Multi-View Object Class Detection (Abstract)

Tinne Tuytelaars , KU Leuven (BE)
Bastian Leibe , ETH Zurich (CH)
Vittorio Ferrar , INRIA Grenoble, France
Luc Van Gool , KU Leuven (BE)
Bernt Schiel , TU Darmstadt (D)
Alexander Thomas , KU Leuven (BE)
pp. 1589-1596

Using Dependent Regions for Object Categorization in a Generative Framework (Abstract)

Li Fei-Fei , Harbin Institute of Technology, China
Gang Wang , University of Illinois Urbana-Champaign
Ye Zhang , University of Illinois Urbana-Champaign
pp. 1597-1604

Using Multiple Segmentations to Discover Objects and their Extent in Image Collections (Abstract)

Alexei A. Efros , Carnegie Mellon University
Andrew Zisserman , University of Oxford, UK
Josef Sivic , University of Oxford, UK
pp. 1605-1614
Poster Session 8: Action Recognition

Joint Recognition of Complex Events and Track Matching (Abstract)

Rahul Bhotika , GE Global Research One Research Circle, NY
Gianfranco Doretto , GE Global Research One Research Circle, NY
John Schmiederer , GE Global Research One Research Circle, NY
Michael T Chan , GE Global Research One Research Circle, NY
Anthony Hoogs , GE Global Research One Research Circle, NY
Amitha Perera , GE Global Research One Research Circle, NY
pp. 1615-1622

Inferring Facial Action Units with Causal Relations (Abstract)

Wenhui Liao , Rensselaer Polytechnic Institute, Troy, NY
Yan Tong , Rensselaer Polytechnic Institute, Troy, NY
Qiang Ji , Rensselaer Polytechnic Institute, Troy, NY
pp. 1623-1630

Learning Temporal Sequence Model from Partially Labeled Data (Abstract)

Aaron Bobick , Georgia Institute Of Technology, Atalanta
Yifan Shi , Georgia Institute Of Technology, Atalanta
Irfan Essa , Georgia Institute Of Technology, Atalanta
pp. 1631-1638

Automatic Discovery of Action Taxonomies from Multiple Views (Abstract)

Remi Ronfard , Project PERCEPTION, INRIA Rhone-Alpes, France
Edmond Boyer , Project PERCEPTION, INRIA Rhone-Alpes, France
Daniel Weinland , Project PERCEPTION, INRIA Rhone-Alpes, France
pp. 1639-1645

Successive Convex Matching for Action Detection (Abstract)

Ze-Nian Li , Simon Fraser University, Burnaby BC, Canada
Hao Jiang , Simon Fraser University, Burnaby BC, Canada
Mark S. Drew , Simon Fraser University, Burnaby BC, Canada
pp. 1646-1653

Unsupervised Discovery of Action Classes (Abstract)

Greg Mori , Simon Fraser University
Mark S. Drew , Simon Fraser University
Ze-Nian Li , Simon Fraser University
Hao Jiang , Simon Fraser University
Yang Wang , Simon Fraser University
pp. 1654-1661

Activity Analysis in Microtubule Videos by Mixture of Hidden Markov Models (Abstract)

Alphan Altinok , University of California Santa Barbara, Santa Barbara
B. S. Manjunath , University of California Santa Barbara, Santa Barbara
Leslie Wilson , University of California Santa Barbara, Santa Barbara
Stuart C. Feinstein , University of California Santa Barbara, Santa Barbara
Austin J. Peck , University of California Santa Barbara, Santa Barbara
Motaz El-Saban , University of California Santa Barbara, Santa Barbara
Kenneth Rose , University of California Santa Barbara, Santa Barbara
pp. 1662-1669

Human Carrying Status in Visual Surveillance (Abstract)

Xindong Wu , University of Vermont
Xuelong Li , Birkbeck, University of London
Stephen J. Maybank , Birkbeck, University of London
Dacheng Tao , Birkbeck, University of London
pp. 1670-1677

AdaBoost.MRF: Boosted Markov Random Forests and Application to Multilevel Activity Recognition (Abstract)

Hung H. Bui , Artificial Intelligence Center, SRI International, Menlo Park, CA
Tran The Truyen , Curtin University of Technology
Dinh Q. Phung , Curtin University of Technology
Svetha Venkatesh , Curtin University of Technology
pp. 1686-1693

Parameterized Duration Mmodeling for Switching Linear Dynamic Systems (Abstract)

Sang Min Oh , Georgia Institute of Technology
Frank Dellaert , Georgia Institute of Technology
James M. Rehg , Georgia Institute of Technology
pp. 1694-1700

Recognition of Composite Human Activities through Context-Free Grammar Based Representation (Abstract)

J. K. Aggarwal , University of Texas at Austin
M. S. Ryoo , University of Texas at Austin
pp. 1709-1718
Oral Session 9: Learning

Correlated Label Propagation with Application to Multi-label Learning (Abstract)

Rong Jin , Michigan State University
Rahul Sukthankar , 3Robotics Institute, Carnegie Mellon
Feng Kang , Michigan State University
pp. 1719-1726

Pursuing Informative Projection on Grassmann Manifold (Abstract)

Xiaoou Tang , Microsoft Research Asia Beijing, China
Dahua Lin , Chinese University of Hong Kong
Shuicheng Yan , Chinese University of Hong Kong
pp. 1727-1734

Dimensionality Reduction by Learning an Invariant Mapping (Abstract)

Sumit Chopra , New York University
Yann LeCun , New York University
Raia Hadsell , New York University
pp. 1735-1742
Oral Session 10: Matching and Registration

Local Features, All Grown Up (Abstract)

pp. 1753-1760

BoostMotion: Boosting a Discriminative Similarity Function for Motion Estimation (Abstract)

Jie Shao , University of Maryland, College Park, MD
Dorin Comaniciu , Siemens Corporate Research, Princeton NJ
Shaohua Kevin Zhou , Siemens Corporate Research, Princeton NJ
Bogdan Georgescu , Siemens Corporate Research, Princeton NJ
pp. 1761-1768

New Method of Probability Density Estimation with Application to Mutual Information Based Image Registration (Abstract)

Ajit Rajwade , University of Florida, USA
Anand Rangarajan , University of Florida, USA
Arunava Banerjee , University of Florida, USA
pp. 1769-1776

Nonparametric Priors on the Space of Joint Intensity Distributions for Non-Rigid Multi-Modal Image Registration (Abstract)

Daniel Cremers , University of Bonn, Germany
Christoph Guetter , Siemens Corporate Research, Princeton, NJ
Chenyang Xu , Siemens Corporate Research, Princeton, NJ
pp. 1777-1783
Poster Session 9: Low Level and Photometric Analysis

Visible Surface Reconstruction from Normals with Discontinuity Consideration (Abstract)

Tai-Pang Wu , Hong Kong University of Science and Technology
Chi-Keung Tang , Hong Kong University of Science and Technology
pp. 1793-1800

Combining Cues: Shape from Shading and Texture (Abstract)

Ryan White , University of California, Berkeley
David A. Forsyth , University of Illinois, Urbana Champaign
pp. 1809-1816

A New Formulation for Shape from Shading for Non-Lambertian Surfaces (Abstract)

Aly A. Farag , University of Louisville, Louisville, KY
Abdelrehim H. Ahmed , University of Louisville, Louisville, KY
pp. 1817-1824

Mesostructure from Specularity (Abstract)

Hans-Peter Seidel , MPI Informatik
Michael Goesele , University of Washington
Tongbo Chen , MPI Informatik
pp. 1825-1832

Shape from Shading: Recognizing the Mountains through a Global View (Abstract)

Qihui Zhu , University of Pennsylvania, Philadelphia, PA
Jianbo Shi , University of Pennsylvania, Philadelphia, PA
pp. 1839-1846

Reconstruction in the Round Using Photometric Normals and Silhouettes. (Abstract)

Roberto Cipolla , University of Cambridge, Cambridge, CB2 1PZ, UK
George Vogiatzis , University of Cambridge, Cambridge, CB2 1PZ, UK
Carlos Hernandez , University of Cambridge, Cambridge, CB2 1PZ, UK
pp. 1847-1854

Separation of Highlight Reflections on Textured Surfaces (Abstract)

Ping Tan , Hong Kong University of Science and Technology
Stephen Lin , Microsoft Research Asia
Long Quan , Hong Kong University of Science and Technology
pp. 1855-1860

Instant 3Descatter (Abstract)

Yoav Y. Schechner , Technion - Israel Inst. Technology
Tali Treibitz , Technion - Israel Inst. Technology
pp. 1861-1868

Specular Flow and the Recovery of Surface Structure (Abstract)

Stefan Roth , Brown University, Providence, RI, USA
Michael J. Black , Brown University, Providence, RI, USA
pp. 1869-1876

A Design Principle for Coarse-to-Fine Classification (Abstract)

Donald Geman , Johns Hopkins University
Sachin Gangaputra , Johns Hopkins University
pp. 1877-1884

A Multi-Channel Algorithm for Edge Detection Under Varying Lighting (Abstract)

Michael Jenkin , York University, Canada
Yves Lesperance , York University, Canada
Wei Xu , University of Colorado at Boulder
pp. 1885-1892

Bottom-Up & Top-down Object Detection using Primal Sketch Features and Graphical Models (Abstract)

Petros Maragos , National Technical University of Athens
Iasonas Kokkinos , National Technical University of Athens
pp. 1893-1900

The Bottleneck Geodesic: Computing Pixel Affinity (Abstract)

Ido Omer , Hebrew University of Jerusalem, Israel
Michael Werman , Hebrew University of Jerusalem, Israel
pp. 1901-1907

Motion Patterns: High-Level Representation of Natural Video Sequences (Abstract)

Te-Won Lee , University of California, San Diego
Duangmanee Putthividhya , University of California, San Diego
pp. 1908-1915

A Framework for Feature Selection for Background Subtraction (Abstract)

Ahmed Elgammal , Rutgers University
Anurag Mittal , Siemens Corporate Research, Princeton, NJ
Toufiq Parag , Rutgers University
pp. 1916-1923

Image Denoising with Shrinkage and Redundant Representations (Abstract)

Boaz Matalon , Technion - Israel Institute of Technology
Michael Zibulevsky , Technion - Israel Institute of Technology
Michael Elad , Technion - Israel Institute of Technology
pp. 1924-1931

A Projective Invariant for Textures (Abstract)

Yong Xu , South China University of Technology
Hui Ji , University of Maryland, College Park
Cornelia Fermuller , University of Maryland, College Park
pp. 1932-1939

A Shape Representation for Planar Curves by Shape Signature Harmonic Embedding (PDF)

Neil A. Clark , SRS-4702, USDA Forest Service Blacksburg, VA
Philip A. Araman , SRS-4702, USDA Forest Service Blacksburg, VA
A. Lynn Abbott , Virginia Tech, Blacksburg, VA
Sang-Mook Lee , Virginia Tech, Blacksburg, VA
pp. 1940-1947

Perceptually-Inspired and Edge-Directed Color Image Super-Resolution (Abstract)

Wai-Shun Tong , Hong Kong University of Science and Technology
Chi-Keung Tang , Hong Kong University of Science and Technology
Yu-Wing Tai , Hong Kong University of Science and Technology
pp. 1948-1955

Image Pre-Conditioning for Out-of-Focus Projector Blur (Abstract)

Michael S. Brown , Nanyang Technological University, Singapore
Peng Song , Nanyang Technological University, Singapore
Tat-Jen Cham , Nanyang Technological University, Singapore
pp. 1956-1963

Supervised Learning of Edges and Object Boundaries (Abstract)

Serge Belongie , University of California, San Diego
Zhuowen Tu , UCLA
Piotr Dollar , University of California, San Diego
pp. 1964-1971

Multiscale Nonlinear Diffusion and Shock Filter for Ultrasound Image Enhancement (Abstract)

Liang Mong Koh , Nanyang Technological University, Singapore
Fan Zhang , Nanyang Technological University, Singapore
Lichen Zhang , Nanyang Technological University, Singapore
Yongmin Kim , University of Washington, Seattle
Yang Mo Yoo , University of Washington, Seattle
pp. 1972-1977

CSIFT: A SIFT Descriptor with Color Invariant Characteristics (Abstract)

Aly A. Farag , University of Louisville, Louisville, KY
Alaa E. Abdel-Hakim , University of Louisville, Louisville, KY
pp. 1978-1983

Blind Haze Separation (Abstract)

Sarit Shwartz , Technion - Israel Inst. Technology
Yoav Y. Schechner , Technion - Israel Inst. Technology
Einav Namer , Technion - Israel Inst. Technology
pp. 1984-1991

Color Subspaces as Photometric Invariants (Abstract)

Satya P. Mallick , University of California, San Diego
Todd Zickler , Harvard University
Peter N. Belhumeur , Columbia University
David J. Kriegman , University of California, San Diego
pp. 2000-2010
Poster Session 10: Recognition

A Generative-Discriminative Hybrid Method for Multi-View Object Detection (Abstract)

Dong-Qing Zhang , Columbia University, New York, NY
Shih-Fu Chang , Columbia University, New York, NY
pp. 2017-2024

Shape Topics: A Compact Representation and New Algorithms for 3D Partial Shape Retrieval (Abstract)

Yi Liu , Peking University
Hongbin Zha , Peking University
Hong Qin , State University of New York at Stony Brook
pp. 2025-2032

Discriminative Object Class Models of Appearance and Shape by Correlatons (Abstract)

J. Winn , Microsoft Research Ltd., Cambridge, CB3 0FB, United Kingdom
A. Criminisi , Microsoft Research Ltd., Cambridge, CB3 0FB, United Kingdom
S. Savarese , University of Illinois at Urbana-Champaign
pp. 2033-2040

Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation (Abstract)

Leonid Sigal , Brown University, Providence, RI
Michael J. Black , Brown University, Providence, RI
pp. 2041-2048

An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed (Abstract)

Vidhya Navalpakkam , University of Southern California
Laurent Itti , University of Southern California
pp. 2049-2056

Region-based Image Annotation using Asymmetrical Support Vector Machine-based Multiple-Instance Learning (Abstract)

Jing Hua , Wayne State University
Ming Dong , Wayne State University
Changbo Yang , Wayne State University
pp. 2057-2063

Learning Object Shape: From Drawings to Images (Abstract)

Daphne Koller , Stanford University
Geremy Heitz , Stanford University
Gal Elidan , Stanford University
pp. 2064-2071

Learning Distance Metrics with Contextual Constraints for Image Retrieval (Abstract)

Wei-Ying Ma , Microsoft Research Asia, Beijing, P.R. China
Michael R. Lyu , Chinese University of Hong Kong, Hong Kong
Wei Liu , Chinese University of Hong Kong, Hong Kong
Steven C. H. Hoi , Chinese University of Hong Kong, Hong Kong
pp. 2072-2078

Satellite Features for the Classification of Visually Similar Classes (Abstract)

Boris Epshtein , Weizmann Institute of Science, Israel
Shimon Ullman , Weizmann Institute of Science, Israel
pp. 2079-2086

Affine Invariance Revisited (Abstract)

Evgeni Begelfor , Hebrew University of Jerusalem
Michael Werman , Hebrew University of Jerusalem
pp. 2087-2094

Incorporating the Boltzmann Prior in Object Detection Using SVM (Abstract)

Margarita Osadchy , University of Haifa
Daniel Keren , University of Haifa
pp. 2095-2101

Using Language to Drive the Perceptual Grouping of Local Image Features (Abstract)

Sven Dickinson , University of Toronto
Sven Wachsmuth , Bielefeld University
Michael Jamieson , University of Toronto
Suzanne Stevenson , University of Toronto
pp. 2102-2109

A Simple Bayesian Framework for Content-Based Image Retrieval (Abstract)

Katherine A. Heller , University College London
Zoubin Ghahramani , Cambridge University, UK
pp. 2110-2117

Spatial Weighting for Bag-of-Features (Abstract)

Cordelia Schmid , INRIA Rhone-Alpes, LEAR - GRAVIR, France
Marcin Marsza?ek , INRIA Rhone-Alpes, LEAR - GRAVIR, France
pp. 2118-2125

SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition (Abstract)

Jitendra Malik , Univ. of California, Berkeley
Hao Zhang , Univ. of California, Berkeley
Alexander C. Berg , Univ. of California, Berkeley
Michael Maire , Univ. of California, Berkeley
pp. 2126-2136
Oral Selssion 11: Recognition

Putting Objects in Perspective (Abstract)

Derek Hoiem , Carnegie Mellon University, Robotics Institute
Alexei A. Efros , Carnegie Mellon University, Robotics Institute
Martial Hebert , Carnegie Mellon University, Robotics Institute
pp. 2137-2144

Context and Hierarchy in a Probabilistic Image Model (Abstract)

Stuart Geman , Brown University
Ya Jin , Brown University
pp. 2145-2152

Perception Strategies in Hierarchical Vision Systems (Abstract)

Stan Bileschi , Massachusetts Institute of Technology
Ethan Meyers , Massachusetts Institute of Technology
Lior Wolf , Massachusetts Institute of Technology
pp. 2153-2160

Scalable Recognition with a Vocabulary Tree (Abstract)

David Nister , University of Kentucky
Henrik Stewenius , University of Kentucky
pp. 2161-2168

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories (Abstract)

Svetlana Lazebnik , University of Illinois
Cordelia Schmid , INRIA Rhone-Alpes Montbonnot, France
Jean Ponce , Ecole Normale Sup?erieure Paris, France
pp. 2169-2178
Oral Session 12: Tracking and Video Analysis

Tunable Kernels for Tracking (Abstract)

Visvanathan Ramesh , Siemens Corporate Research, NJ
Vasu Parameswaran , Siemens Corporate Research, NJ
Imad Zoghlami , Siemens Corporate Research, NJ
pp. 2179-2186

Multi-Target Tracking - Linking Identities using Bayesian Network Inference (Abstract)

Peter Nillius , Institute of Computer Science - FORTH, Greece
Josephine Sullivan , Royal Institute of Technology (KTH), Sweden
Stefan Carlsson , Royal Institute of Technology (KTH), Sweden
pp. 2187-2194

Multi-Camera Scene Flow by Tracking 3-D Points and Surfels (Abstract)

Matthieu Guilbert , INRIA Rhone-Alpes, Cedex, France
Diana Mateus , INRIA Rhone-Alpes, Cedex, France
Frederic Devernay , INRIA Rhone-Alpes, Cedex, France
pp. 2203-2212
Poster Session 11: Stereo and 3D Reconstruction

3D Building Detection and Modeling from Aerial LIDAR Data (Abstract)

Stephen Hsu , Canesta, Inc.
Rakesh Kumar , Sarnoff Corporation
Vivek Verma , Sarnoff Corporation
pp. 2213-2220

Three-Dimensional Volume Reconstruction Based on Trajectory Fusion from Confocal Laser Scanning Microscope Images (Abstract)

Sang-Chul Lee , University of Illinois at Urbana-Champaign
Peter Bajcsy , University of Illinois at Urbana-Champaign
pp. 2221-2228

Landmark-Based Geodesic Computation for Heuristically Driven Path Planning (Abstract)

Gabriel Peyre , CMAP, UMR CNRS 7641, France
Laurent D. Cohen , CEREMADE, UMR CNRS 7534, Paris, France
pp. 2229-2236

Surface Reconstruction of Bone from X-ray Images and Point Distribution Model Incorporating a Novel Method for 2D-3D Correspondence (Abstract)

Guoyan Zheng , University of Bern, CH-3014, Bern, Switzerland
Lutz-Peter Nolte , University of Bern, CH-3014, Bern, Switzerland
pp. 2237-2244

Element-Free Elastic Models for Volume Fitting and Capture (Abstract)

Andrzej Szymczak , Georgia Institute of Technology
Jaeil Choi , Georgia Institute of Technology
Greg Turk , Georgia Institute of Technology
Irfan Essa , Georgia Institute of Technology
pp. 2245-2252

Structure and View Estimation for Tomographic Reconstruction: A Bayesian Approach (Abstract)

Serge J. Belongie , University of California, San Diego
Sameer Agarwal , University of California, San Diego
Clinton S. Potter , Scripps Research Institute, La Jolla.
Bridget Carragher , Scripps Research Institute, La Jolla
Satya P. Mallick , University of California, San Diego
David J. Kriegman , University of California, San Diego
pp. 2253-2260

SDG Cut: 3D Reconstruction of Non-lambertian Objects Using Graph Cuts on Surface Distance Grid (Abstract)

Narendra Ahuja , Univ. of Illinois at Urbana-Champaign
Wei-Chao Chen , Nvidia Corporation
Tianli Yu , Univ. of Illinois at Urbana-Champaign
pp. 2269-2276

3-D Shape Reconstruction of Retinal Fundus (Abstract)

Tae Eun Choe , University of Southern California
Isaac Cohen , University of Southern California
Gerard Medioni , University of Southern California
pp. 2277-2284

Shape from Dynamic Texture for Planes (Abstract)

Mubarak Shah , University of Central Florida
Niels Haering , Object Video Reston, VA
Yaser Sheikh , University of Central Florida
pp. 2285-2292

Edge Suppression by Gradient Field Transformation Using Cross-Projection Tensors (Abstract)

Amit Agrawal , University of Maryland
Rama Chellappa , University of Maryland
Ramesh Raskar , Mitsubishi Electric Research Labs Cambridge, MA
pp. 2301-2308

Vertical Parallax from Moving Shadows (Abstract)

Yaron Caspi , Weizmann Institute of Science, Israel
Michael Werman , Hebrew University of Jerusalem, Israel
pp. 2309-2315

A Refractive Camera for Acquiring Stereo and Super-resolution Images (Abstract)

Narendra Ahuja , University of Illinois at Urbana-Champaign
Chunyu Gao , University of Illinois at Urbana-Champaign
pp. 2316-2323

A Planar Light Probe (Abstract)

Neil G. Alldrin , University of California, San Diego
David J. Kriegman , University of California, San Diego
pp. 2324-2330

Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures (Abstract)

Richard Szeliski , Microsoft Research, Redmond, WA
Marc Levoy , Stanford University, CA
C. L. Zitnick , Microsoft Research, Redmond, WA
Vaibhav Vaish , Stanford University, CA
Sing Bing Kang , Microsoft Research, Redmond, WA
pp. 2331-2338

The Panum Proxy Algorithm for Dense Stereo Matching over a Volume of Interest (Abstract)

A. Agarwal , Microsoft Research Ltd., Cambridge, UK
A. Blake , Microsoft Research Ltd., Cambridge, UK
pp. 2339-2346

Stereo Matching with Color-Weighted Correlation, Hierachical Belief Propagation and Occlusion Handling (Abstract)

Q?ngxiong Yang , University of Kentucky
Ruigang Yang , University of Kentucky
Liang Wang , University of Kentucky
David Nister , University of Kentucky
Henrik Stewenius , University of Kentucky
pp. 2347-2354

Surface Geometric Constraints for Stereo in Belief Propagation (Abstract)

Steven W. Zucker , Yale University
Gang Li , Yale University
pp. 2355-2362

Binocular Stereo Dense Matching in the Presence of Specular Reflections (Abstract)

Chandra Kambhamettu , University of Delaware
Wei Zhou , University of Delaware
pp. 2363-2370

Stereo Matching with Symmetric Cost Functions (Abstract)

In So Kweon , KAIST, Korea
Kuk-Jin Yoon , KAIST, Korea
pp. 2371-2377

Region-Tree Based Stereo Using Dynamic Programming Optimization (Abstract)

Cheng Lei , University of Alberta, Canada
Yee-Hong Yang , University of Alberta, Canada
Jason Selzer , University of Alberta, Canada
pp. 2378-2385

Stereo Vision in Structured Environments by Consistent Semi-Global Matching (Abstract)

Heiko Hirschmuller , German Aerospace Center (DLR), 82230 Wessling, Germany
pp. 2386-2393

Combined Depth and Outlier Estimation in Multi-View Stereo (Abstract)

Rik Fransens , K.U.Leuven-ESAT-Psi, Belgium
Christoph Strecha , K.U.Leuven-ESAT-Psi, Belgium
Luc Van Gool , K.U.Leuven-ESAT-Psi, Belgium
pp. 2394-2401

Multi-View Stereo Revisited (Abstract)

Michael Goesele , University of Washington
Steven M. Seitz , University of Washington
Brian Curless , University of Washington
pp. 2402-2409

A Dynamic Bayesian Network Model for Autonomous 3D Reconstruction from a Single Indoor Image (Abstract)

Erick Delage , Stanford University
Andrew Y. Ng , Stanford University
Honglak Lee , Stanford University
pp. 2418-2428
Poster Session 12: Matching and Registration

Simultaneous Registration and Modeling of Deformable Shapes (Abstract)

Dorin Comaniciu , Siemens Corporate Research, NJ
Jing Xiao , Epson Palo Alto Lab, CA
Xiang Zhou , Siemens Corporate Research, NJ
Takeo Kanade , Robotics Institute, CMU, PA
Bogdan Georgescu , Siemens Corporate Research, NJ
pp. 2429-2436

Real-time Image-Based Guidance Method for Lung-Cancer Assessment (Abstract)

Lav Rai , Penn State University
William E. Higgins , Penn State University
Scott A. Merritt , Penn State University
pp. 2437-2444

Object Pose Detection in Range Scan Data (Abstract)

Dragomir Anguelov , Stanford University
Daphne Koller , Stanford University
Jim Rodgers , Stanford University
Hoi-Cheung Pang , Stanford University
pp. 2445-2452

3D Surface Matching and Recognition Using Conformal Geometry (Abstract)

Sen Wang , State University of New York at Stony Brook
Dimitris Samaras , State University of New York at Stony Brook
Miao Jin , State University of New York at Stony Brook
Yang Wang , State University of New York at Stony Brook
Xianfeng Gu , State University of New York at Stony Brook
pp. 2453-2460

Wire Structure Pattern Extraction and Tracking From X-Ray Images of Composite Mechanisms (Abstract)

J. Fadili , GREYC IMAGE (CNRS UMR 6072), Cedex, France
D. Tschumperle , GREYC IMAGE (CNRS UMR 6072), Cedex, France
pp. 2461-2466

Scale-Driven Iterative Optimization for Brain Extraction and Registration (Abstract)

Thomas S. Huang , University of Illinois at Urbana Champaign, USA
Terrence Chen , University of Illinois at Urbana Champaign, USA
pp. 2467-2474

Coupled Bayesian Framework for Dual Energy Image Registration (Abstract)

Tong Fang , Siemens Corporate Research, USA
Yunqiang Chen , Siemens Corporate Research, USA
Hao Wu , University of Maryland, USA
pp. 2475-2482

Robust AAM Fitting by Fusion of Images and Disparity Data (Abstract)

Jing Xiao , Epson Palo Alto Laboratory, USA
Joerg Liebelt , Universitaet Karlsruhe (TH), Germany
Jie Yang , Carnegie Mellon University, USA
pp. 2483-2490

Piecewise Image Registration in the Presence of Multiple Large Motions (Abstract)

Ke Colin Zheng , University of Washington, USA
Brian Curless , University of Washington, USA
Maneesh Agrawala , University of California, Berkeley, USA
Pravin Bhat , University of Washington, USA
Aseem Agarwala , University of Washington, USA
Noah Snavely , University of Washington, USA
Michael F. Cohen , Microsoft Research, USA
pp. 2491-2497

Seamless Image Stitching of Scenes with Large Motions and Exposure Differences (Abstract)

Richard Szeliski , Microsoft Research, USA
Ashley Eden , U.C. Berkeley, USA
Matthew Uyttendaele , Microsoft Research, USA
pp. 2498-2505

Image Matching Using Photometric Information (Abstract)

Ilan Shimshoni , Haifa University, Israel
Michael Kolomenkin , Technion, Israel
pp. 2506-2514
Author Index

Author Index (PDF)

pp. 2515
92 ms
(Ver )