The Community for Technology Leaders
2013 IEEE Conference on Computer Vision and Pattern Recognition (1997)
Puerto Rico
June 17, 1997 to June 19, 1997
ISSN: 1063-6919
ISBN: 0-8186-7822-4
TABLE OF CONTENTS

Reviewers (PDF)

pp. xviii
Poster Session 1

An image-based visual-motion-cue for autonomous navigation (Abstract)

S.R. Kundur , Dept. of Electr. Eng., Florida Atlantic Univ., Boca Raton, FL, USA
D. Raviv , Dept. of Electr. Eng., Florida Atlantic Univ., Boca Raton, FL, USA
E. Kent , Dept. of Electr. Eng., Florida Atlantic Univ., Boca Raton, FL, USA
pp. 7

Real-Time Estimation of Human Body Posture from Monocular Thermal Images (Abstract)

Shigeo Morishima , Seikei University
Shoichiro Iwasawa , ATR Media Integration and Communications Research Laboratories
Jun Ohya , ATR Media Integration and Communications Research Laboratories
Kazuyuki Ebihara , ATR Media Integration and Communications Research Laboratories
pp. 15

Matching 3-D arcs (Abstract)

B. Kamgar-Parsi , Adv. Inf. Technol. Branch, Naval Res. Lab., Washington, DC, USA
B. Kamgar-Parsi , Adv. Inf. Technol. Branch, Naval Res. Lab., Washington, DC, USA
pp. 28

Pictorial Recognition Using Affine-Invariant Spectral Signatures (Abstract)

Zhiqian Wang , University of Illinois at Chicago
Jezekiel Ben-Arie , University of Illinois at Chicago
pp. 34

A bootstrapping algorithm for learning linear models of object classes (Abstract)

T. Vetter , Max-Planck-Inst. fur Biol. Kybernetik, Tubingen, Germany
M.J. Jones , Max-Planck-Inst. fur Biol. Kybernetik, Tubingen, Germany
T. Poggio , Max-Planck-Inst. fur Biol. Kybernetik, Tubingen, Germany
pp. 40

Shape from the Light Field Boundary (Abstract)

Kiriakos N. Kutulakos , University of Rochester
pp. 53

Gradient Vector Flow: A New External Force for Snakes (Abstract)

Chenyang Xu , The Johns Hopkins University
Jerry L. Prince , The Johns Hopkins University
pp. 66

Automated Model Acquisition from Range Images with View Planning (Abstract)

Ioannis Stamos , Columbia University
Michael K. Reed , Columbia University
Peter K. Allen , Columbia University
pp. 72

Deterioration detection for digital film restoration (Abstract)

B. Besserer , Lab. d'Inf. et d'Imagerie Ind., La Rochelle Univ., France
F. Helt , Lab. d'Inf. et d'Imagerie Ind., La Rochelle Univ., France
O. Buisson , Lab. d'Inf. et d'Imagerie Ind., La Rochelle Univ., France
S. Boukir , Lab. d'Inf. et d'Imagerie Ind., La Rochelle Univ., France
pp. 78

Fully 3D Active Surface Models with Self--Inflation and Self--Deflation Forces (Abstract)

Zixin Zhang , University of Technology, Sydney
Michael Braun , University of Technology, Sydney
pp. 85

Fast Binary Image Processing Using Binary Decision Diagrams (Abstract)

Luc Robert , INRIA Sophia-Antipolis
Gregoire Malandain , INRIA Sophia-Antipolis
pp. 97

Characterization of errors in compositing panoramic images (Abstract)

Richard Weiss , University of Massachusetts at Amherst
Sing Bing Kang , Digital Equipment Corp.
pp. 103

Determining a Polyhedral Shape Using Interreflections (Abstract)

Noboru Ohnishi , RIKEN BMC
Noboru Sugie , RIKEN BMC
Jun Yang , RIKEN BMC
Dili Zhang , RIKEN BMC
pp. 110

Removing the bias from line detection (Abstract)

C. Steger , Tech. Univ. Munchen, Germany
pp. 116
Session A1: Face Detection and Tracking

Training Support Vector Machines: an Application to Face Detection (Abstract)

Robert Freund , Massachusetts Institute of Technology
Edgar Osuna , Massachusetts Institute of Technology
Federico Girosi , Massachusetts Institute of Technology
pp. 130

Parametrized structure from motion for 3D adaptive feedback tracking of faces (Abstract)

A. Pentland , Media Lab., MIT, Cambridge, MA, USA
T.S. Jebara , Media Lab., MIT, Cambridge, MA, USA
pp. 144
Session B1: Physics-Based Vision

Reflectance and Texture of Real-World Surfaces Authors: (Abstract)

Bram Van Ginneken , Utrecht University
Jan J. Koenderink , Utrecht University
Kristin J. Dana , Columbia University
Shree K. Nayar , Columbia University
pp. 151

Shape and albedo from multiple images using integrability (Abstract)

A. Yuille , Smith-Kettlewell Eye Res. Inst., San Francisco, CA, USA
D. Snow , Smith-Kettlewell Eye Res. Inst., San Francisco, CA, USA
pp. 158

A Curvature Based Descriptor Invariant to Pose and Albedo Derived from Photometric Data (Abstract)

James P. Williams , The Johns Hopkins University
Lawrence B. Wolff , The Johns Hopkins University
Elli Angelopoulou , The Johns Hopkins University
pp. 165

What is a light source? (Abstract)

Michael S. Langer , NEC Research Institute
Steven W. Zucker , Yale University
pp. 172
Session A2: Object Detection

Object detection with vector quantized binary features (Abstract)

J. Krumm , Intelligent Syst. & Robotics Center, Sandia Nat. Labs., Albuquerque, NM, USA
pp. 179

Object Detection Using Hierarchical MRF and MAP Estimation (Abstract)

Richard J. Qian , University of Illinois at Urbana-Champaign
Thomas S. Huang , University of Illinois at Urbana-Champaign
pp. 186
Session B2: Optic Flow and Structure from Motion

Image velocity estimation from trajectory surface in spatiotemporal space (Abstract)

S. Suzuki , NTT Human Interface Labs., Yokosuka, Japan
T. Horikoshi , NTT Human Interface Labs., Yokosuka, Japan
K. Otsuka , NTT Human Interface Labs., Yokosuka, Japan
pp. 200

Stereo-Motion that Complements Stereo and Motion Analyses (Abstract)

Pui-Kuen Ho , The Chinese University of Hong Kong
Ronald Chung , The Chinese University of Hong Kong
pp. 213
Poster Session 2

Optimal Selection of Camera Parameters for Recovery of Depth from Defocused Images (Abstract)

A. N. Rajagopalan , Indian Institute of Technology
S. Chaudhuri , Indian Institute of Technology
pp. 219

Calibration of a Structured Light System: A Projective Approach (Abstract)

D. Huynh , Signal Processing Research Institute
pp. 225

Self-Maintaining Camera Calibration Over Time (Abstract)

Zhengyou Zhang , ATR Human Information Processing Research Laboratories
Veit Schenk , INRIA
pp. 231

Creating Image-Based VR Using a Self-Calibrating Fisheye Lens (Abstract)

Yalin Xiong , Apple Computer, Inc
Ken Turkowski , Apple Computer, Inc
pp. 237

Feature Tracking from an Image Sequence Using Geometric Invariants (Abstract)

H. T. Tsui , The University of Hong Kong
S. H. Kong , The University of Hong Kong
Z. Y. Zhang , The University of Hong Kong
pp. 244

The confounding of translation and rotation in reconstruction from multiple views (Abstract)

Y. Aloimonos , Comput. Vision Lab., Maryland Univ., College Park, MD, USA
C. Fermuller , Comput. Vision Lab., Maryland Univ., College Park, MD, USA
pp. 250

Tracking non-rigid, moving objects based on color cluster flow (Abstract)

U. Kressel , Res. & Technol., Daimler-Benz AG, Ulm, Germany
B. Heisele , Res. & Technol., Daimler-Benz AG, Ulm, Germany
W. Ritter , Res. & Technol., Daimler-Benz AG, Ulm, Germany
pp. 257

A direct method for stereo correspondence based on singular value decomposition (Abstract)

M. Pilu , Digital Media Dept., Hewlett-Packard Res. Labs., Bristol, UK
pp. 261

Identification of salient contours in cluttered images (Abstract)

Shih-Cheng Yen , Dept. of Bioeng., Pennsylvania Univ., Philadelphia, PA, USA
L.H. Finkel , Dept. of Bioeng., Pennsylvania Univ., Philadelphia, PA, USA
pp. 273

Efficient Regularity-Based Grouping (Abstract)

Jacob Feldman , Rutgers University
pp. 288

Facial Expression Recognition and Its Degree Estimation (Abstract)

Satoshi Kimura , The Kansai Electric Power Co., Inc.
Masahiko Yachida , Osaka University
pp. 295

Extracting Surface Textures and Microstructures from Multiple Aerial Images (Abstract)

Allen R. Hanson , University of Massachusetts
Xiaoguang Wang , University of Massachusetts
pp. 301

Content-based trademark retrieval system using visually salient features (Abstract)

Yong-Sung Kim , Image Eng. Lab., Hanyang Univ., Seoul, South Korea
Whoi-Yul Kim , Image Eng. Lab., Hanyang Univ., Seoul, South Korea
pp. 307

A Computational Approach to Steerable Functions (Abstract)

Yacov Hel-Or , NASA Ames Research Center
Patrick C. Teo , Stanford University
pp. 313

Modelling of single mode distributions of colour data using directional statistics (Abstract)

D.C. Alexander , University College London
B.F. Buxton , University College London
pp. 319
Session A3: Registration and Pose Estimation

Projective registration with difference decomposition (Abstract)

M. Gleicher , Apple Res. Labs., Cupertino, CA, USA
pp. 331

Panoramic mosaics by manifold projection (Abstract)

J. Herman , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
S. Peleg , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
pp. 338

Verifying model-based alignments in the presence of uncertainty (Abstract)

W.E.L. Grimson , Artificial Intelligence Lab., MIT, Cambridge, MA, USA
T.D. Alter , Artificial Intelligence Lab., MIT, Cambridge, MA, USA
pp. 344
Session B3: Image-Level Representations 1

Images as embedding maps and minimal surfaces: movies, color, and volumetric medical images (Abstract)

R. Kimmel , Dept. of Math., California Univ., Berkeley, CA, USA
R. Malladi , Dept. of Math., California Univ., Berkeley, CA, USA
N. Sochen , Dept. of Math., California Univ., Berkeley, CA, USA
pp. 350

Extracting symmetry features from color images (Abstract)

G. Healey , Comput. Vision Lab., California Univ., Irvine, CA, USA
Bea Thai , Comput. Vision Lab., California Univ., Irvine, CA, USA
pp. 356

Corner Detection with Covariance Propagation (Abstract)

Robert M. Haralick , University of Washington
Qiang Ji , University of Washington
pp. 362
Poster Session 3

Name-It: Association of Face and Name in Video (Abstract)

Takeo Kanade , Carnegie Mellon University
Shin'ichi Satoh , Carnegie Mellon University
pp. 368

Deformable Multi Template Matching with Application to Portal Images (Abstract)

Martin Berger , Swiss Federal Institute of Technology, Z?rich, Switzerland
Gaudenz Danuser , Swiss Federal Institute of Technology, Z?rich, Switzerland
pp. 374

Building Reconstruction from Optical and Range Images (Abstract)

Edward Riseman , Computer Vision Laboratory, University of Massachusetts, Amherst
Christopher 0. Jaynes , Computer Vision Laboratory, University of Massachusetts, Amherst
Howard Schultz , Computer Vision Laboratory, University of Massachusetts, Amherst
Allen Hanson , Computer Vision Laboratory, University of Massachusetts, Amherst
pp. 380

Rational Discrete Generalized Cylinders and their Application to Shape Recovery in Medical Images (Abstract)

John K. Johnstone , The University of Alabama at Birmingham
Lawrence B. Wolff , The Johns Hopkins University
James P. Williams , The Johns Hopkins University
pp. 387

Cylindrical rectification to minimize epipolar distortion (Abstract)

I.J. Cox , NEC Res. Inst., Princeton, NJ, USA
S. Roy , NEC Res. Inst., Princeton, NJ, USA
J. Meunier , NEC Res. Inst., Princeton, NJ, USA
pp. 393

Model-based brightness constraints: on direct estimation of structure and motion (Abstract)

G.P. Stein , Artificial Intelligence Lab., MIT, Cambridge, MA, USA3
A. Shashua , Artificial Intelligence Lab., MIT, Cambridge, MA, USA3
pp. 400

A Stratified Approach to Metric Self-Calibration (Abstract)

Marc Pollefeys , K.U.Leuven-MI2
Luc Van Gool , K.U.Leuven-MI2
pp. 407

A Divide-and-conquer Strategy in Shape from Shading Problem (Abstract)

Seong Ik Cho , Keio University, Japan
Hideo Saito , Keio University, Japan
Shinji Ozawa , Keio University, Japan
pp. 413

Using geometric corners to build a 2D mosaic from a set of image (Abstract)

O. Faugeras , INRIA - Sophia-Antipolis
I. Zoghlami , INRIA - Sophia-Antipolis
R. Deriche , INRIA - Sophia-Antipolis
pp. 420

Ego-Motion Estimation Using Optical Flow Fields Observed from Multiple Cameras (Abstract)

An-Ting Tsao , National Taiwan University
Yi-Ping Hung , Academia Sinica
Yong-Sheng Chen , Academia Sinica
Chiou-Shann Fuh , National Taiwan University
pp. 457

Learning Generic Prior Models for Visual Computation (Abstract)

David Mumford , Brown University
Song Chun Zhu , Brown University
pp. 463

Disparity Component Matching for Visual Correspondence (Abstract)

Olga Veksler , Cornell University
Ramin Zabih , Cornell University
Yuri Boykov , Cornell University
pp. 470
Session A4: Applications

Catadioptric Omnidirectional Camera (Abstract)

Shree K. Nayar , Columbia University
pp. 482

A Real-time Computer Vision System for Measuring Traffic Parameters (Abstract)

Benn Coifman , University of California, Berkeley
David Beymer , University of California, Berkeley
Jitendra Mali , University of California, Berkeley
Philip McLauchlan , University of California, Berkeley
pp. 495

Character extraction of license plates from video (Abstract)

Y.-T. Cui , Siemens Corp. Res. Inc., Princeton, NJ, USA
Q. Huang , Siemens Corp. Res. Inc., Princeton, NJ, USA
pp. 502
Session B4: Stereo- and Motion-Based Segmentation

A region-level graph labeling approach to motion-based segmentation (Abstract)

Marc Gelgon , Campus Universitaire de Beaulieu
Patrick Bouthemy , Campus Universitaire de Beaulieu
pp. 514

Empirical Bayesian EM-based Motion Segmentation (Abstract)

Andrew Lippman , MIT Media Laboratory
Nuno Vasconcelos , MIT Media Laboratory
pp. 527
Session A5: Object Recognition

Appearance Matching of Occluded Objects Using Coarse-to-fine Adaptive Masks (Abstract)

Hiroshi Murase , NTT Basic Research Labs Information Sciences Laboratory
Jeff Edwards , NTT Basic Research Labs Information Sciences Laboratory
pp. 533

Dynamic Appearance-Based Recognition (Abstract)

Rajesh P.N. Rao , University of Rochester
pp. 540

3-D to 2-D Recognition with Regions (Abstract)

David W. Jacobs , NEC Research Institute
Ronen Basri , The Weizmann Inst. of Science
pp. 547
Session B5: Learning

Learning bilinear models for two-factor problems in vision. (Abstract)

William T. Freeman , MERL, a Mitsubishi Electric Research Laboratory
pp. 554

Learning Parameterized Models of Image Motion (Abstract)

Michael J. Black , Xerox Palo Alto Research Center
Allan D. Jepson , University of Toronto
Yaser Yacoob , University of Maryland
David J. Fleet , Queen's Univ.
pp. 561
Poster Session 4

Multi-Image Focus of Attention for Rapid Site Model Construction (Abstract)

Robert T. Collins , The Robotics Institute, Carnegie Mellon University,
pp. 575

Lip reading from scale-space measurements (Abstract)

J. Andrew Bangham , University of East Anglia,
Stephen Cox , University of East Anglia,
Richard Harvey , University of East Anglia,
Iain Matthews , University of East Anglia,
pp. 582

Detection and Description of Buildings from Multiple Aerial Images (Abstract)

Ram Nevatia , University of Southern California
Sanjay Noronha , University of Southern California
pp. 588

Analysis of Gesture and Action in Technical Talks for Video Indexing (Abstract)

Don Kimber , Xerox Palo Alto Research Center
Shanon X. Ju , Univ. of Toronto
Michael J. Black , Xerox Palo Alto Research Center
Scott Minneman , Xerox Palo Alto Research Center
pp. 595

Lens distortion calibration using point correspondences (Abstract)

G.P. Stein , Artificial Intelligence Lab., MIT, Cambridge, MA, USA
pp. 602

Autocalibration and the absolute quadric (Abstract)

B. Triggs , Inst. Nat. de Recherche en Inf. et Autom., Montbonnot St. Martin, France
pp. 609

Representation Of Objects In A Volumetric Frequency Domain With Application To Face Recognition (Abstract)

Dibyendu Nandy , University of Illinois at Chicago
Jezekiel Ben-Arie , University of Illinois at Chicago
pp. 615

Area and Length Minimizing Flows for Shape Segmentation (Abstract)

Steven W. Zucker , Yale University
Yves Bérubé Lauzière , McGill University
Kaleem Siddiqi , Yale University
Allen Tannenbaum , University of Minnesota
pp. 621

Efficient Approximation of Range Images Through Data-Dependent Adaptive Triangulations (Abstract)

Miguel Angel Garcia , Polytechnic University of Catalonia
Angel Domingo Sappa , Polytechnic University of Catalonia
Luis Basañez , Polytechnic University of Catalonia
pp. 628

A Minimum-Variance Adaptive Surface Mesh (Abstract)

Edwin R Hancock , University of York
Richard C Wilson , University of York
pp. 634

3D Reconstruction of the Human Jaw from A Sequence of Images (Abstract)

S. Roberts , University of Louisville
S. Ahmed , University of Louisville
E. Hemayed , University of Louisville
S. Yamany , University of Louisville
A. Farag , University of Louisville
M. Ahmed , University of Louisville
pp. 646

A general filter for measurements with any probability distribution (Abstract)

Y. Rosenberg , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
M. Werman , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
pp. 654

Fast 3D Stabilization and Mosaic Construction (Abstract)

Rama Chellappa , University of Maryland
Carlos Morimoto , University of Maryland
pp. 660

Automatic line matching across views (Abstract)

A. Zisserman , Dept. of Eng. Sci., Oxford Univ., UK
C. Schmid , Dept. of Eng. Sci., Oxford Univ., UK
pp. 666

Independent 3D Motion Detection Based on Depth Elimination in Normal Flow Fields (Abstract)

Antonis A. Argyros , Foundation for Research and Technology
Stelios C. Orphanoudakis , Foundation for Research and Technology
pp. 672

Body plans (Abstract)

M.M. Fleck , Dept. of Comput. Sci., California Univ., Berkeley, CA, USA
D.A. Forsyth , Dept. of Comput. Sci., California Univ., Berkeley, CA, USA
pp. 678

Recognizing Objects by Matching Oriented Points (Abstract)

Andrew Edie Johnson , Carnegie Mellon University
Martial Hebert , Carnegie Mellon University
pp. 684
Session A6: Tracking

Vision for a smart kiosk (Abstract)

M. Loughlin , Cambridge Res. Lab., Digital Equipment Corp., Cambridge, MA, USA
J.M. Rehg , Cambridge Res. Lab., Digital Equipment Corp., Cambridge, MA, USA
K. Waters , Cambridge Res. Lab., Digital Equipment Corp., Cambridge, MA, USA
pp. 690

Real-time closed-world tracking (Abstract)

A.F. Bobick , Media Lab., MIT, Cambridge, MA, USA
J.W. Davis , Media Lab., MIT, Cambridge, MA, USA
S.S. Intille , Media Lab., MIT, Cambridge, MA, USA
pp. 697

Object tracking using affine structure for point correspondences (Abstract)

P. Jain , Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., New Delhi, India
L. Kumar , Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., New Delhi, India
G. Singh Manku , Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., New Delhi, India
S. Banerjee , Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., New Delhi, India
A. Aggarwal , Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., New Delhi, India
pp. 704
Session B6: Image-Level Representations 2

Orientation diffusions (Abstract)

P. Perona , California Inst. of Technol., Pasadena, CA, USA
pp. 710

Efficient Guaranteed Search for Gray-level Patterns (Abstract)

William Rucklidge , Xerox Palo Alto Research Center
pp. 717

Adaptive B-Splines and Boundary Estimation (Abstract)

Jose M. N. Leitao Instituto de , Telecomunicacoes and DEEC Instituto Superior Tecnico
Mario A. T. Figueiredo , Telecomunicacoes and DEEC Instituto Superior Tecnico
Anil K. Jain , Michigan State University
pp. 724
Session A7: Segmentation

Normalized Cuts and Image Segmentation (Abstract)

Jianbo Shi , U.C. Berkeley
Jitendra Malik , U.C. Berkeley
pp. 731

Scale-Space Vector Fields for Feature Analysis (Abstract)

Andrew D.J. Cross , University of York
Edwin R. Hancock , University of York
pp. 738

Edge Flow: A Framework of Boundary Detection and Image Segmentation (Abstract)

B. S. Manjunath , University of California, Santa Barbara, CA, USA
W. Y. Ma , University of California, Santa Barbara, CA, USA
pp. 744

Robust analysis of feature spaces: color image segmentation (Abstract)

D. Comaniciu , Dept. of Electr. & Comput. Eng., Rutgers Univ., Piscataway, NJ, USA
P. Meer , Dept. of Electr. & Comput. Eng., Rutgers Univ., Piscataway, NJ, USA
pp. 750
Session B7: Video and Image Database Indexing

FOCUS: Searching for Multi-colored Objects in a Diverse Image Database (Abstract)

Madirakshi Das , University of Massachusetts
Edward M. Riseman , University of Massachusetts
Bruce A. Draper , Colorado State University
pp. 756

Image Indexing Using Color Correlograms (Abstract)

Mandar Mitra , Cornell University
Ramin Zabih , Cornell University
Jing Huang , Cornell University
Wei-Jing Zhu , Cornell University
S. Ravi Kumar , Cornell University
pp. 762

Object-Based Video Indexing for Virtual Studio Productions (Abstract)

Peter J.L. Van Beek , University of Rochester
A.Murat Tekalp , University of Rochester
Bilge Gunsel , University of Rochester
pp. 769
Poster Session 5

Interaction with On-Screen Objects using Visual Gesture Recognition (Abstract)

John Kender , Columbia University
Rick Kjeldsen , IBM T.J. Watson Research Center
pp. 788

Using Local 3D Structure for Segmentation of Bone from Computer Tomography Images (Abstract)

Hans Knutsson , Linkoping University
Abhir Bhalerao , Harvard Medical School
Ron Kikinis , Harvard Medical School
Carl-Fredrik Westin , Harvard Medical School
pp. 794

Depth from Scattering (Abstract)

Fabio Cozman , Carnegie Mellon University
Eric Krotkov , Carnegie Mellon University
pp. 801

On Perpendicular Texture: Why do we see more flowers in the distance? (Abstract)

Jitendra Malik , University of California at Berkeley
Thomas Leung , University of California at Berkeley
pp. 807

Are Textureless Scenes Recoverable? (Abstract)

Hari Sundaram , Columbia University
Shree K. Nayar , Columbia University
pp. 814

Local Blur Estimation and Super-Resolution (Abstract)

Ming-Chao Chiang , Columbia University
Terrance E. Boult , Lehigh University
pp. 821

Object recognition using invariant profiles (Abstract)

D. Slater , Dept. of Electr. & Comput. Eng., California Univ., Irvine, CA, USA
G. Healey , Dept. of Electr. & Comput. Eng., California Univ., Irvine, CA, USA
pp. 827

Edge Localization in Surface Reconstruction Using Optimal Estimation Theory (Abstract)

F.P. Ferrie , McGill University
Shailendra Mathur , SOFTIMAGE/Microsoft Corporation
pp. 833

Shocks from images: propagation of orientation elements (Abstract)

P.A. Stoll , Div. of Eng., Brown Univ., Providence, RI, USA
B.B. Kimia , Div. of Eng., Brown Univ., Providence, RI, USA
H. Tek , Div. of Eng., Brown Univ., Providence, RI, USA
pp. 839

Surface Shape from Warping (Abstract)

Tony Zhang , The Smith-Kettlewell Eye Research Institute
Alan Yuille , The Smith-Kettlewell Eye Research Institute
Mario Ferraro , The Smith-Kettlewell Eye Research Institute
pp. 846

On Occluding Contour Artifacts in Stereo Vision (Abstract)

Ruzena Bajcsy , University of Pennsylvania
Radim Sara , University of Pennsylvania
pp. 852

Efficient Stereo with Multiple Windowing (Abstract)

Vito Roberto , University of Udine
Emanuele Trucco , Heriot-Watt University
Andrea Fusiello , University of Udine
pp. 858

Multi-Scale Classification of 3-D Objects (Abstract)

Dongmei Zhang , Carnegie Mellon University
Martial Hebert , Carnegie Mellon University
pp. 864

Hierarchical Recognition of Articulated Objects from Single Perspective Views (Abstract)

Stefan Lanser , Technische Universitat Munchen
Christoph Zierl , Technische Universitat Munchen
Alexa Hauck , Technische Universitat Munchen
pp. 870

Object Recognition Using Appearance-Based Parts and Relations (Abstract)

Octavia I. Camps , The Pennsylvania State University
Chien-Yuan Huang , The Pennsylvania State University
Tapas Kanungo , Caere Corporation
pp. 877

Experimental Performance Evaluation of Feature Grouping Modules (Abstract)

Sudeep Sarkar , University of South Florida
Sudhir Borra , University of South Florida
pp. 891
Session A8: Applications: Terrain Modeling
Session B8: Non-Rigid Motion and Image Sequences

Temporal Multi-scale Models for Flow and Acceleration (Abstract)

Yaser Yacoob , University of Maryland
Larry Davis , University of Maryland
pp. 921

Analyzing Articulated Motion Using Expectation-Maximization (Abstract)

Henry A. Rowley , Carnegie Mellon University
James M. Rehg , Digital Equipment Corporation
pp. 935
Poster Session 6

Model-based multi-objective analysis of ultrasound image sequences in prenatal diagnosis (Abstract)

H.I. Bozma , Dept. of Electr. & Electron. Eng., Bogazici Univ., Istanbul, Turkey
E. Kemik , Dept. of Electr. & Electron. Eng., Bogazici Univ., Istanbul, Turkey
pp. 942

Temporal Classification of Natural Gesture and Application to Video Coding (Abstract)

Aaron F. Bobick , MIT Media Laboratory
Andrew D. Wilson , MIT Media Laboratory
Justine Cassell , MIT Media Laboratory
pp. 948

Controlling view-based algorithms using approximate world models and action information (Abstract)

C.S. Pinhanez , Media Lab., MIT, Cambridge, MA, USA
A.F. Bobick , Media Lab., MIT, Cambridge, MA, USA
pp. 955

Robust Occluding Contour Detection Using the Hausdorff Distance (Abstract)

Xilin Yi , The Pennsylvania State University
Octavia I. Camps , The Pennsylvania State University
pp. 962

Physically based fluid flow recovery from image sequences (Abstract)

Michael J. Amabile , David Sarnoff Research Center, Inc.
Tzong-Shyng Leu , David Sarnoff Research Center, Inc.
Richard P. Wildes , David Sarnoff Research Center, Inc.
Ann-Marie Lanzillotto , David Sarnoff Research Center, Inc.
pp. 969

Ridge's corner detection and correspondence (Abstract)

M. Werman , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
Y. Gdalyahn , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
F. Shilat , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
pp. 976

Motion estimation using ordinal measures (Abstract)

A. Gupta , Columbia Univ., New York, NY, USA
D.N. Bhat , Columbia Univ., New York, NY, USA
S.K. Nayar , Columbia Univ., New York, NY, USA
pp. 982

Optic flow calculation using robust statistics (Abstract)

D. Suter , Dept. of Electr. & Comput. Syst. Eng., Monash Univ., Clayton, Vic., Australia
A. Bab-Hadiashar , Dept. of Electr. & Comput. Syst. Eng., Monash Univ., Clayton, Vic., Australia
pp. 988

Coupled hidden Markov models for complex action recognition (Abstract)

A. Pentland , Media Lab., MIT, Cambridge, MA, USA
N. Oliver , Media Lab., MIT, Cambridge, MA, USA
M. Brand , Media Lab., MIT, Cambridge, MA, USA
pp. 994

Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces (Abstract)

David G. Lowe , University of British Columbia
Jeffrey S. Beis , University of British Columbia
pp. 1000

Configuration based scene classification and image indexing (Abstract)

E. Grimson , Artificial Intelligence Lab., MIT, Cambridge, MA, USA
P. Lipson , Artificial Intelligence Lab., MIT, Cambridge, MA, USA
P. Sinha , Artificial Intelligence Lab., MIT, Cambridge, MA, USA
pp. 1007

A Bayesian Segmentation Framework for Textured Visual Images (Abstract)

J. K. Aggarwal , The University of Texas at Austin
Shishir Shah , The University of Texas at Austin
pp. 1014

Prediction Intervals for Surface Growing Range Segmentation (Abstract)

James V. Miller , Rensselaer Polytechnic Institute
Charles V. Stewart , Rensselaer Polytechnic Institute
pp. 1027

Novel view synthesis in tensor space (Abstract)

S. Avidan , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
A. Shashua , Inst. of Comput. Sci., Hebrew Univ., Jerusalem, Israel
pp. 1034

Image Based View Synthesis of Articulated Agents (Abstract)

Martin Jagersand , University of Rochester
pp. 1047

A class of probabilistic shape models (Abstract)

A.J. Abrantes , INESC, Lisbon, Portugal
J.S. Marques , INESC, Lisbon, Portugal
pp. 1054
Session A9: Shape

The Bas-Relief Ambiguity (Abstract)

Alan L. Yuille , Smith-Kettlewell Eye Research Institute
David J. Kriegman , Yale University
Peter N. Belhumeur , Yale University
pp. 1060

Photorealistic Scene Reconstruction by Voxel Coloring (Abstract)

Charles R. Dyer , University of Wisconsin
Steven M. Seitz , University of Wisconsin
pp. 1067

Hyper-patches for 3D model acquisition and tracking (Abstract)

C.S. Wiles , Kansai Res. Labs., Toshiba Corp., Kobe, Japan
N. Matsuda , Kansai Res. Labs., Toshiba Corp., Kobe, Japan
A. Maki , Kansai Res. Labs., Toshiba Corp., Kobe, Japan
M. Watanabe , Kansai Res. Labs., Toshiba Corp., Kobe, Japan
pp. 1074

Using Differential Constraints to Reconstruct Complex Surfaces from Stereo (Abstract)

Richard Lengagne , INRIA-Rocquencourt
Pascal Fua , EPFL Ecublens
Olivier Monga , INRIA-Rocquencourt
pp. 1081
Session B9: Stereo and Calibration

Error Analysis of a Real-Time Stereo System (Abstract)

Yalin Xiong , Apple Computer, Inc
Larry Matthies , Apple Computer, Inc
pp. 1087

Stereo Coupled Active Contours (Abstract)

Roberto Cipolla , University of Cambridge
Tat-Jen Cham , University of Cambridge
pp. 1094

Author Index (PDF)

pp. 1113
85 ms
(Ver )