International Conference on Computer Vision - Preliminary program
Sunday January 4
Welcoming remarks (9:30-9:45)
Session 1.1 - Images from Images (9:45-11:25)
- P.J. Narayanan, Peter W. Rander and Takeo Kanade: Constructing Virtual Worlds Using Dense Stereo
- Yakup Genc and Jean Ponce: Parameterized Image Varieties: A Novel Approach to the Analysis and Synthesis of Image Sequences
- Steve M. Seitz and Kiriakos N. Kutulakos: Plenoptic Image Editing
- Geoffrey Cross and Andrew Zisserman: Quadric Surface Reconstruction from Dual-Space Geometry
Coffee break (11:25-11:55)
Session 1.2 - New sensors (11:55 - 12:45)
- Simon Baker and Shree K. Nayar: A Theory of Catadioptric Image Formation
- Jean-Yves Bouguet and Pietro Perona: 3D Photography on Your Desk
Lunch (12:45-2:00)
Session 1.3 - Applications (2:00-3:40)
- Wiro J. Niessen, Koen L. Vincken, Joachim A. Weickert and Max A. Viergever: Three Dimensional MR Brain Segmentation
- Yossi Rubner, Carlo Tomasi and Leonidas J. Guibas: A Metric for
Distributions with Applications to Image Databases
- Tinne Tuytelaars, Luc Van Gool, Marc Proesmans and Theo Moons: A Cascaded Hough Transform as an Aid in Aerial Image Interpretation
- Andres Huertas and Ramakant Nevatia: Detecting Changes in Aerial Views of Man-Made Structures
Coffee break (3:40-4:10)
Session 1.4 - Self-calibration (4:10 - 5:25)
- Tomás Brodsky, Cornelia Fermüller and Yiannis Aloimonos:
Self-Calibration from Image Derivatives
- Marc Pollefeys, Reinhard Koch and Luc Van Gool: Self-Calibration and Metric Reconstruction in Spite of Varying and Unknown Internal Camera Parameters
- Radu Horaud and Gabriella Csurka: Self-Calibration and Euclidean Reconstruction Using Motions of a Stereo Rig
Monday January 5
Session 2.1 - Tracking (9:30-11:10)
- Michael Isard and Andrew Blake: A Mixed-State CONDENSATION Tracker with Automatic Model-Switching
- Douglas DeCarlo and Dimitris Metaxas: Deformable Model-Based Shape and Motion Analysis from Images using Motion Residual Error
- Yaser Yacoob and Michael Black: Parameterized Modeling and Recognition of Activities
- Tony Jebara, Kenneth Russell and Alex Pentland: Mixtures of Eigen Features for Real-Time Structure from Texture
Coffee break (11:10-11:40)
Session 2.2 - Recognition (11:40-12:55)
- Haim Schweitzer: Computing Ritz Approximations of Primary Images
- Margrit Betke and Nicholas C. Makris: Information-Conserving Object Recognition
- Erez Sali and Shimon Ullman: Recognizing Novel 3-D Objects Under New Illumination and Viewing Position Using a Small Number of Examples
Lunch (1:00-2:00)
Session 2.3 - Colour (2:00-3:30)
- Daniel Berwick and Sang Wook Lee: A Chromaticity Space for Specularity-, Illumination Color- and Illumination Pose-Invariant 3-D Object Recognition
- Sashi D. Buluswar and Bruce A. Draper: Color Recognition in Outdoor Images
- G. Sapiro: Color and Illuminant Bilinear Voting
Poster Session 1 - Tracking. low level vision and registration (3:30-6:00)
- Patrick C. Teo and Yacov Hel-Or: Design of Multi-Parameter Steerable Functions Using Cascade Basis Reduction
- Ping Liang: Local Scale Controlled Anisotropic Diffusion with Local Noise Estimate for Image Smoothing and Edge Detection
- A.P. Ashbrook and R.B. Fisher: Segmentation of Range Data into Rigid Subsets Using Surface Patches
- David H. Marimont and Yossi Rubner: A Probabilistic
Framework for Edge Detection and Scale Selection.
- Kaleem Siddiqi, Allen Tannenbaum and Steven W. Zucker: Hyperbolic "Smoothing" of Shapes
- Kaleem Siddiqi, Ali Shokoufandeh, Sven J. Dickinson and Steven W. Zucker: Shock Graphs and Shape Matching
- Cordelia Schmid, Roger Mohr and Christian Bauckhage: Comparing and Evaluating Interest Points
- John Haddon and David Forsyth: Shading Primitives: Finding Folds and Shallow Grooves
- Chu-Song Chen, Yi-Ping Hung and Jen-Bo Cheng: A Fast and Robust Approach for Registration of Partially Overlapping Range Images
- Bernt Schiele and James L. Crowley: Transinformation for Active Object Recognition
- A. Banerjee, P. Burlina and F. Alajaji: Contagion-Based Image Segmentation and Labeling
- G. Simon and M.-O. Berger: A Two-Stage Robust Statistical Method for Temporal Registration from Features of Various Type
- Jan Puzicha and Joachim M. Buhmann: Multiscale Annealing for Real-Time Unsupervised Texture Segmentation
- Paul L. Rosin: Thresholding for Change Detection
- Robert Laganičr: Morphological Corner Detection
- Mark W. Powell, Kevin W. Bowyer, Xiaoyi Jiang and Horst Bunke: Comparing Curved-Surface Range Image Segmenters
- P. Teo, G. Sapiro and B. Wandell: Anatomically Consistent Segmentation of the Human Cortex for Functional MRI Visualization
- Robert Rohling, Andrew Gee and Laurence Berman : Automatic Registration of Ultrasound Images
- R. Malladi and J.A. Sethian: A Real-Time Algorithm for Medical Shape Recovery
- H. Delingette: Initialization of Deformable Models from 3D Data
- G.J. Edwards, C.J. Taylor and T.F. Cootes: Learning to Identify and Track Faces in Image Sequences
- B. Bascle and A. Blake: Separability of Pose and Expression in Facial Tracing and Animation
- Andrew D. Wilson and Aaron F. Bobick: Recognition and Interpretation of Parametric Gesture
- Sumit Basu, Nuria Oliver and Alex Pentland: 3D Modeling of Human Lip Motion
- Tony Heap and David Hogg: Wormholes in Shape Space: Tracking Through Discontinuous Changes in Shape
- J. Fernyhough, A.G. Cohn and D.C. Hogg: Building Qualitative Event Models Automatically from Visual Input
- Q. Cai and J.K. Aggarwal: Automatic Tracking of Human Motion in Indoor Scenes Across Multiple Synchronized Video Streams
- Christian Vogler and Dimitris Metaxas: ASL Recognition Based on a Coupling Between HMMs and 3D Motion Analysis
- Robert Kaucic and Andrew Blake: Accurate, Real-Time, Unadorned Lip Tracking
- Fang Liu and Rosalind W. Picard: Finding Periodicity in Space and Time
- Ben North and Andrew Blake: Using Expectation-Maximisation to Learn a Dynamical Model for a Tracker from Measurement Sequences
- J.P. MacCormick and A. Blake: A Probabilistic Contour Discriminant for Object Localisation
- Isaac Cohen and Isabelle Herlin: Tracking Meteorological Structures Through Curve Matching Using Geodesic Paths
- A. Caunce and C.J. Taylor: 3D Point Distribution Models of the Cortical Sulci
- Gary Jacob, Alison Noble and Andrew Blake: Robust Contour Tracking in Echocardiographic Sequences
- Marie-Pierre Dubuisson-Jolly, Cheng-Chung Liang and Alok Gupta: Optimal Polyline Tracking for Artery Motion Compensation in Coronary Angiography
- Samuel D. Fenster and John R. Kender: Sectored Snakes: Evaluating Learned-Energy Segmentations
- B.C. Vemuri and Y. Guo: Pedal Snakes and Snake Pedals: Geometric Models with Physics-Based Control
- Natan Peterfreund: Robust Tracking with Spatio-Velocity Snakes: Kalman Filtering Approach
- Yu Zhong, Anil K. Jain and Marie-Pierre Dubuisson-Jolly: Object Tracking Using Deformable Templates
- Yaser Yacoob and Larry Davis: Learned Temporal Models of Image Motion
- Thomas O'Donnell, Marie-Pierre Dubuisson-Jolly and Alok Gupta: A Cooperative Framework for Segmentation Using 2D Active Contours and 3D Hybrid Models as Applied to Branching Cylindrical Structures
- Bernard Baldwin, Davi Geiger and Robert Hummel: Resolution-Appropriate Shape Representation
Tuesday January 6
Session 3.1 - Multiple views (9:30-11:10)
- Richard I. Hartley: Minimizing Algebraic Error in Geometric Estimation Problems
- O. Faugeras and T. Papadopoulo: A Nonlinear Method for Estimating the Projective Geometry of Three Views
- P.H.S. Torr, Andrew Fitzgibbon and A. Zisserman: Maintaining Multiple Motion Model Hypotheses Through Many Views to Recover Matching and Structure
- Sébastien Roy and Ingemar J. Cox: A Maximum-Flow Formulation of the N-Camera Stereo Correspondence Problem
Coffee break (11:10-11:40)
Session 3.2 - Recovery (11:40-12:55)
- R. Mandelbaum, G. Kamberova and M. Mintz: Stereo Depth Estimation: A Confidence Interval Approach
- Steve Sullivan and Jean Ponce: Automatic Model Construction, Pose Estimation, and Object Recognition from Photographs using Triangular Splines
- Richard Szeliski and Polina Golland: Stereo Matching with Transparency and Matting
Lunch (1:00-2:00)
Poster Session 2 - Multi-view Geometry and Recognition/indexing (2:00-4:30)
- B. Krebs, B. Korn and M. Burkhardt: A Task Driven 3d Object Recognition System using Bayesian Networks
- Mark S. Drew, Jie Wei and Ze-Nian Li: Illumination-Invariant Color Object Recognition via Compressed Chromaticity Histograms of Color-Channel-Normalized Images
- Ronen Basri and Yael Moses: When is it Possible to Identify 3D Objects from Single Images Using Class Constraints?
- Zili Liu and Daniel Kersten: 2D Affine Transformations are Unlikely to Account for Human 3D Object Recognition
- Constantine Papageorgiou, Michael Oren and Tomaso Poggio: A General Framework for Object Detection
- Benoit Huet and Edwin R. Hancock: Relational Histograms for Shape Indexing
- Qing Yang and Song De Ma: Schwarz Representation for Matching and Similarity Analysis
- T. Gevers and A.W.M. Smeulders: Image Indexing using Composite Color and Shape Invariant Features
- Haim Schweitzer: Indexing Images by Trees of Visual Content
- Ali Shokoufandeh, Ivan Marsic and Sven J. Dickinson: View-Based Object Matching
- David W. Jacobs, Daphna Weinshall and Yoram Gdalyahu: Condensing Image Databases when Retrieval is Based on Non-Metric Distances
- Jing Huang, S. Ravi Kumar, Mandar Mitra and Wei-Jing Zhu: Spatial Color Indexing and Applications
- S. Ravela and R. Manmatha: Retrieving Images by Appearance
- Randal C. Nelson and Andrea Selinger: A Cubist Approach to Object Recognition
- Isidore Rigoutsos: Two-Dimensional Affine Invariants that Distribute Uniformly and can be Tuned to any Convex Feature Domain
- A.L. Yuille, D. Snow and M. Nitzberg: Signfinder: Using Color to Detect, Localize and Identify Informational Signs
- George Bebis, Michael Georgiopoulos, Mubarak Shah and Niels da Vitoria Lobo: Using Algebraic Functions of Views for Indexing-Based Object Recognition
- A.N. Rajagopalan, K. Sunil Kumar, Jayashree Karlekar, R. Manivasakan, M. Milind Patil, U.B. Desai, P.G. Poonacha and S. Chaudhuri: Finding Faces in Photographs
- Srinivas Gutta, Jeffrey Huang, Vishal Kakkad and Harry Wechsler: Face Surveillance
- Ali Reza Mirhosseini, Catherine Chen, Tuan Pham and Hong Yan: Human Face Recognition: A Minimal Evidence Approach
- Michael J. Black, David J. Fleet and Yaser Yacoob: A Framework for Modeling Appearance Change in Image Sequences
- Yasushi Sumi, Yoshihiro Kawai, Takashi Yoshimi and Fumiaki Tomita: Recognition of 3D Free-form Objects Using Segment-based Stereo Vision
- Serge Belongie, Chad Carson, Hayit Greenspan and Jitendra Malik: Color- and Texture-based Image Segmentation Using the Expectation-Maximization Algorithm and its Application to Content-Based Image Retrieval
- Michael J. Jones and Tomaso Poggio: Multidimensional Morphable Models
- Cornelia Fermüller and Yiannis Aloimonos: Which Shape from Motion?
- Daniel Morris and Takeo Kanade: A Unified Factorization Algorithm for Points, Line Segments and Planes with Uncertainty Models
- S.J. Maybank and A. Shashua: Ambiguity in Reconstruction from Images of Six Points
- Jorge Batista, Helder Araújo and A.T. Almeida: Iterative Multi-Step Explicit Camera Calibration
- Jun Sato and Roberto Cipolla: Affine Reconstruction of Curved Surfaces from Uncalibrated Views of Apparent Contours
- Taeone Kim, Yongduek Seo and Ki-sang Hong: Physics-based 3D Position Analysis of a Soccer Ball from Monocular Image Sequences
- P.H.S. Torr and A. Zisserman: Robust Computation and Parametrization of Multiple View Relations
- Yoram Leedan and Peter Meer: Estimation with Bilinear Constraints in Computer Vision
- Sven Utcke: Grouping Based on Projective Geometry Constraints and Uncertainty
- L. de Agapito, D.Q. Huynh and M.J. Brooks: Self-calibrating a Stereo Head: An Error Analysis in the Neighbourhood of Degenerate Configurations
- Philip Pritchett and Andrew Zisserman: Wide Baseline Stereo Matching
- Fredrik Kahl and Anders Heyden: Using Conic Correspondence in Two Images to Estimate the Epipolar Geometry
- Qifa Ke, Gang Xu and Song De Ma: Recovering Epipolar Geometry by Reactive Tabu Search
- Zhengyou Zhang: Understanding the Relationship Between the Optimization Criteria in Two-View Motion Analysis
- Long Quan and Zhongdan Lan: Linear 4-Point and N „ 5-Point Pose Determination
- Zhengyou Zhang, Katsunori Isono and Shigeru Akamatsu: Euclidean Structure from Uncalibrated Images Using Fuzzy Domain Knowledge: Application to Facial Images Synthesis
- Sylvain Bougnoux: From Projective to Euclidean Space Under any Practical Situation, a Criticism of Self-Calibration
Session 3.3 - Grouping and representation (4:30-6:00)
- D. Ziou: Passive Depth from Defocus Using a Spatial Domain Approach
- Chhandomay Mandal, Baba C. Vemuri and Hong Qin: Shape Recovery Using Dynamic Subdivision Surfaces
- Radim Sára and Ruzena Bajcsy: Fish-Scales: Representing Fuzzy Manifolds
- Chi-Keung Tang and Gérard Medioni: Integrated Surface, Curve and Junction Inference from Sparse 3-D Data Sets
Wednesday January 7
Session 4.1 - Image description and processing (9:30-11:10)
- Zhibin Lei, Tolga Tasdizen and David B. Cooper: PIMs and Invariant Parts for Shape Recognition
- P.J. Giblin and G. Sapiro: Affine Invariant Medial Axis and Skew Symmetry
- Carlo Tomasi and Roberto Manduchi: Bilateral Filtering for Gray and Color Images
- Song Chun Zhu and David Mumford: GRADE: Gibbs Reaction and Diffusion Equation
Coffee break (11:10-11:40)
Panel - Structure from Motion (11:40-1:00)
This panel was formed based on a provoking paper submitted by Dr. John
Oliensis of NEC. Panelists will be discussing the assertions in that
paper, as well as related issues in structure from motion. The paper
can be found here. The panel will be moderated by Larry Davis, and will
include John Oliensis, Olivier Faugeras, Takeo Kanade and Richard Hartley.
Lunch (1:00-2:00)
Poster Session 3 - Stereo, Robot vision, Shape, Mosaics (2:00 - 4:30)
- Paolo Remagnino, Tieniu Tan and Keith Baker: Agent Orientated Annotation in Model Based Visual Surveillance
- Ronen Basri, Ehud Rivlin and Ilan Shimshoni: Visual Homing: Surfing on the Epipoles
- Eiji Uchibe, Minoru Asada and Koh Hosoda: State Space Construction for Behavior Acquisition in Multi Agent Environments with Vision and Action
- Garbis Salgian and Dana H. Ballard: Visual Routines for Autonomous Driving
- Keisuke Kinoshita and Michael Lindenbaum: Robotic Control with Partial Visual Information
- M. Yeasin and S. Chaudhuri: Automatic Generation of Robot Program Code: Learning from Perceptual Data
- Kishore Bubna and Charles V. Stewart: Model Selection and Surface Merging in Reconstruction Algorithms
- Nicola J. Ferrier: Achieving a Fitts Law Relationship for Visual Guided Reaching
- Colin Davidson and Andrew Blake: Error-Tolerant Visual Planning of Planar Grasp
- Mark D. Wheeler, Yoichi Sato and Katsushi Ikeuchi: Consensus Surfaces for Modeling 3D Objects from Multiple Range Images
- Zoran Duric, Ehud Rivlin and Azriel Rosenfeld: Understanding Object Motion
of Tools and Vehicles
- E. Mémin and P. Pérez: A Multigrid Approach for Hierarchical Motion Estimation
- Fredrik Kahl and Kalle Ĺström: Motion Estimation in Image Sequences Using the Deformation of Apparent Contours
- Benny Rousso, Shmuel Peleg, Ilan Finci and Alex Rav-Acha: Universal Mosaicing using Pipe Projection
- Heung-Yeung Shum and Richard Szeliski: Construction and Refinement of Panoramic Mosaics with Global and Local Alignment
- Michal Irani and P. Anandan: Robust Multi-Sensor Image Alignment
- César Silva and José Santos-Victor: Egomotion Estimation Using Log-Polar Images
- Alan L. Yuille, P-Y. Burgi, N.M. Grzywacz: Visual Motion Estimation and Prediction: A Probabilistic Network Model for Temporal Coherence
- Sándor Fejes and Larry S. Davis: What Can Projections of Flow Fields Tell Us About Visual Motion
- Alessandro Verri and Emanuele Trucco: Finding the Epipole from Uncalibrated Optical Flow
- Yu-Te Wu, Takeo Kanade, Jeffrey Cohn and Ching-Chung Li: Optical Flow Estimation Using Wavelet Motion Model
- Joshua Gluckman and Shree K. Nayar: Ego-Motion and Omnidirectional Cameras
- Hans-Hellmut Nagel and Michael Haag: Bias-Corrected Optical Flow Estimation for Road Vehicle Tracking
- Manolis I.A. Lourakis, Antonis A. Argyros and Stelios C. Orphanoudakis: Independent 3D Motion Detection Using Residual Parallax Normal Flow Fields
- Jong Seung Park and Joon Hee Han: A Curvature-Based Approach to Contour Motion Estimation
- R.D. Henkel: Fast Stereovision with Subpixel-Precision
- Y.F. Wang and Ping Liang: 3D Shape and Motion Analysis from Image Blur and Smear: A Unified Approach
- Guo-Qing Wei and Gerd Hirzinger: Intensity and Feature Based Stereo Matching by Disparity Parametrization
- Zhengyou Zhang: Modeling Geometric Structure and Illumination Variation of a Scene from Real Images
- A.N. Rajagopalan and S. Chaudhuri: Optimal Recovery of Depth from Defocused Images Using an MRF Model
- Atsuto Maki, Mutsumi Watanabe and Charles Wiles: Geotensity: Combining Motion and Lighting for 3D Surface Reconstruction
- Yoav Y. Schechner, Nahum Kiryati and Ronen Basri: Separation of Transparent Layers Using Focus
- Blanca Garcia and Pere Brunet: 3D Reconstruction with Projective Octrees and Epipolar Geometry
- Stan Birchfield and Carlo Tomasi: Depth Discontinuities by Pixel-to-Pixel Stereo
- Marc Proesmans, Luc Van Gool and Filip Defoort: Active Extraction of Dynamic 3D with Surface Texture
- Sameer A. Nene and Shree K. Nayar: Stereo Using Mirrors
- Jonathan C. Carr, W. Richard Fright, Andrew H. Gee, Richard W. Prager and Kevin J. Dalton: 3D Shape Reconstruction Using Volume Intersection Techniques
- Jiang Yu Zheng and Akio Murata: Acquiring 3D Object Models from Specular Motion Using Circular Lights Illumination
- Ikushi Yoda and Katsuhiko Sakaue: Utilization of Stereo Disparity and Optical Flow Information for Human Interaction
- Rupert W. Curwen, Charles V. Stewart and Joseph L. Mundy: Plane Projective Symmetry as a Measure of Saliency
- Sibel Tari and Jayant Shah: Local Symmetries of Shapes in Arbitrary Dimension
- Tyng-Luh Liu, Davi Geiger and Robert Kohn: Shape Similarity via Symmetry Axis and Vice-Versa
Session 4.2 - Flow and tracking (4:30-5:55)
- Nikolaos Paragios and Rachid Deriche: A PDE-Based Level-Set Approach for Detection and Tracking of Moving Objects
- Stan Sclaroff and John Isidoro: Active Blobs
- Jianbo Shi and Jitendra Malik: Motion Segmentation and Tracking Using Normalized Cuts
Press This to go to conference page
