Welcome to the proceedings of the 8th European Conference on Computer - sion! Following a very successful ECCV 2002, the response to our call for papers was almost equally strong – 555 papers were submitted. We accepted 41 papers for oral and 149 papers for poster presentation. Several innovations were introduced into the review process. First, the n- ber of program committee members was increased to reduce their review load. We managed to assign to program committee members no more than 12 papers. Second, we adopted a paper ranking system. Program committee members were asked to rank all the papers assigned to them, even those that were reviewed by additional reviewers. Third, we allowed authors to respond to the reviews consolidated in a discussion involving the area chair and the reviewers. Fourth, thereports,thereviews,andtheresponsesweremadeavailabletotheauthorsas well as to the program committee members. Our aim was to provide the authors with maximal feedback and to let the program committee members know how authors reacted to their reviews and how their reviews were or were not re?ected in the ?nal decision. Finally, we reduced the length of reviewed papers from 15 to 12 pages. ThepreparationofECCV2004wentsmoothlythankstothee?ortsofthe- ganizing committee, the area chairs, the program committee, and the reviewers. We are indebted to Anders Heyden, Mads Nielsen, and Henrik J. Nielsen for passing on ECCV traditions and to Dominique Asselineau from ENST/TSI who kindly provided his GestRFIA conference software. We thank Jan-Olof Eklundh and Andrew Zisserman for encouraging us to organize ECCV 2004 in Prague.
Author(s): Julien Bect, Laure Blanc-Féraud, Gilles Aubert, Antonin Chambolle (auth.), Tomás Pajdla, Jiří Matas (eds.)
Series: Lecture Notes in Computer Science 3024
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2004
Language: English
Pages: 624
Tags: Image Processing and Computer Vision; Pattern Recognition; Computer Graphics; Artificial Intelligence (incl. Robotics)
Front Matter....Pages -
A l 1 -Unified Variational Framework for Image Restoration....Pages 1-13
Support Blob Machines....Pages 14-24
High Accuracy Optical Flow Estimation Based on a Theory for Warping....Pages 25-36
Model-Based Approach to Tomographic Reconstruction Including Projection Deblurring. Sensitivity of Parameter Model to Noise on Data....Pages 37-49
Unlevel-Sets: Geometry and Prior-Based Segmentation....Pages 50-61
Learning and Bayesian Shape Extraction for Object Recognition....Pages 62-73
Multiphase Dynamic Labeling for Variational Recognition-Driven Image Segmentation....Pages 74-86
Integral Invariant Signatures....Pages 87-99
Detecting Keypoints with Stable Position, Orientation, and Scale under Illumination Changes....Pages 100-113
Spectral Simplification of Graphs....Pages 114-126
Inferring White Matter Geometry from Diffusion Tensor MRI: Application to Connectivity Mapping....Pages 127-140
Unifying Approaches and Removing Unrealistic Assumptions in Shape from Shading: Mathematics Can Help....Pages 141-154
Morphological Operations on Matrix-Valued Images....Pages 155-167
Constraints on Coplanar Moving Points....Pages 168-179
A PDE Solution of Brownian Warping....Pages 180-191
Stereovision-Based Head Tracking Using Color and Ellipse Fitting in a Particle Filter....Pages 192-204
Parallel Variational Motion Estimation by Domain Decomposition and Cluster Computing....Pages 205-216
Whitening for Photometric Comparison of Smooth Surfaces under Varying Illumination....Pages 217-228
Structure from Motion of Parallel Lines....Pages 229-240
A Bayesian Framework for Multi-cue 3D Object Tracking....Pages 241-252
On the Significance of Real-World Conditions for Material Classification....Pages 253-266
Toward Accurate Segmentation of the LV Myocardium and Chamber for Volumes Estimation in Gated SPECT Sequences....Pages 267-278
An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets....Pages 279-290
Human Pose Estimation Using Learnt Probabilistic Region Similarities and Partial Configurations....Pages 291-303
Tensor Field Segmentation Using Region Based Active Contour Model....Pages 304-315
Groupwise Diffeomorphic Non-rigid Registration for Automatic Model Building....Pages 316-327
Separating Transparent Layers through Layer Information Exchange....Pages 328-341
Multiple Classifier System Approach to Model Pruning in Object Recognition....Pages 342-353
Coaxial Omnidirectional Stereopsis....Pages 354-365
Classifying Materials from Their Reflectance Properties....Pages 366-376
Seamless Image Stitching in the Gradient Domain....Pages 377-389
Spectral Clustering for Robust Motion Segmentation....Pages 390-401
Learning Outdoor Color Classification from Just One Training Image....Pages 402-413
A Polynomial-Time Metric for Attributed Trees....Pages 414-427
Probabilistic Multi-view Correspondence in a Distributed Setting with No Central Server....Pages 428-441
Monocular 3D Reconstruction of Human Motion in Long Action Sequences....Pages 442-455
Fusion of Infrared and Visible Images for Face Recognition....Pages 456-468
Reliable Fiducial Detection in Natural Scenes....Pages 469-480
Light Field Appearance Manifolds....Pages 481-493
Galilean Differential Geometry of Moving Images....Pages 494-506
Tracking People with a Sparse Network of Bearing Sensors....Pages 507-518
Transformation-Invariant Embedding for Image Analysis....Pages 519-530
The Least-Squares Error for Structure from Infinitesimal Motion....Pages 531-545
Stereo Based 3D Tracking and Scene Learning, Employing Particle Filtering within EM....Pages 546-559
The Isophotic Metric and Its Application to Feature Sensitive Morphology on Surfaces....Pages 560-572
A Closed-Form Solution to Non-rigid Shape and Motion Recovery....Pages 573-587
Stereo Using Monocular Cues within the Tensor Voting Framework....Pages 588-601
Shape and View Independent Reflectance Map from Multiple Views....Pages 602-615
Back Matter....Pages -
