Computer Vision - ECCV 2008

1. Front Matter

   PDF

2. Matching

   1. 3D Non-rigid Surface Matching and Registration Based on Holomorphic Differentials

      • Wei Zeng, Yun Zeng, Yang Wang, Xiaotian Yin, Xianfeng Gu, Dimitris Samaras

      Pages 1-14

   2. Learning Two-View Stereo Matching

      • Jianxiong Xiao, Jingni Chen, Dit-Yan Yeung, Long Quan

      Pages 15-27

   3. SIFT Flow: Dense Correspondence across Different Scenes

      • Ce Liu, Jenny Yuen, Antonio Torralba, Josef Sivic, William T. Freeman

      Pages 28-42

3. Learning+Features

   1. Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation

      • Julien Mairal, Marius Leordeanu, Francis Bach, Martial Hebert, Jean Ponce

      Pages 43-56

   2. Non-local Regularization of Inverse Problems

      • Gabriel Peyré, Sébastien Bougleux, Laurent Cohen

      Pages 57-68

   3. Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks

      • Amr Ahmed, Kai Yu, Wei Xu, Yihong Gong, Eric Xing

      Pages 69-82

   4. Learning Optical Flow

      • Deqing Sun, Stefan Roth, J. P. Lewis, Michael J. Black

      Pages 83-97

4. Poster Session III

   1. Optimizing Binary MRFs with Higher Order Cliques

      • Asem M. Ali, Aly A. Farag, Georgy L. Gimel’farb

      Pages 98-111

   2. Multi-camera Tracking and Atypical Motion Detection with Behavioral Maps

      • Jérôme Berclaz, François Fleuret, Pascal Fua

      Pages 112-125

   3. Automatic Image Colorization Via Multimodal Predictions

      • Guillaume Charpiat, Matthias Hofmann, Bernhard Schölkopf

      Pages 126-139

   4. CSDD Features: Center-Surround Distribution Distance for Feature Extraction and Matching

      • Robert T. Collins, Weina Ge

      Pages 140-153

   5. Detecting Carried Objects in Short Video Sequences

      • Dima Damen, David Hogg

      Pages 154-167

   6. Constrained Maximum Likelihood Learning of Bayesian Networks for Facial Action Recognition

      • Cassio P. de Campos, Yan Tong, Qiang Ji

      Pages 168-181

   7. Robust Scale Estimation from Ensemble Inlier Sets for Random Sample Consensus Methods

      • Lixin Fan, Timo Pylvänäinen

      Pages 182-195

   8. Efficient Camera Smoothing in Sequential Structure-from-Motion Using Approximate Cross-Validation

      • Michela Farenzena, Adrien Bartoli, Youcef Mezouar

      Pages 196-209

   9. Semi-automatic Motion Segmentation with Motion Layer Mosaics

      • Matthieu Fradet, Patrick Pérez, Philippe Robert

      Pages 210-223

   10. Unified Frequency Domain Analysis of Lightfield Cameras

       • Todor Georgiev, Chintan Intwala, Sevkit Babakan, Andrew Lumsdaine

       Pages 224-237

   11. Segmenting Fiber Bundles in Diffusion Tensor Images

       • Alvina Goh, René Vidal

       Pages 238-250

   12. View Point Tracking of Rigid Objects Based on Shape Sub-manifolds

       • Christian Gosch, Ketut Fundana, Anders Heyden, Christoph Schnörr

       Pages 251-263

Welcome to the 2008EuropeanConference onComputer Vision. These proce- ings are the result of a great deal of hard work by many people. To produce them, a total of 871 papers were reviewed. Forty were selected for oral pres- tation and 203 were selected for poster presentation, yielding acceptance rates of 4.6% for oral, 23.3% for poster, and 27.9% in total. Weappliedthreeprinciples.First,sincewehadastronggroupofAreaChairs, the ?nal decisions to accept or reject a paper rested with the Area Chair, who wouldbeinformedbyreviewsandcouldactonlyinconsensuswithanotherArea Chair. Second, we felt that authors were entitled to a summary that explained how the Area Chair reached a decision for a paper. Third, we were very careful to avoid con?icts of interest. Each paper was assigned to an Area Chair by the Program Chairs, and each Area Chair received a pool of about 25 papers. The Area Chairs then identi?ed and rankedappropriatereviewersfor eachpaper in their pool, and a constrained optimizationallocated three reviewers to each paper. We are very proud that every paper received at least three reviews. At this point, authors were able to respond to reviews. The Area Chairs then needed to reach a decision. We used a series of procedures to ensure careful review and to avoid con?icts of interest. ProgramChairs did not submit papers. The Area Chairs were divided into three groups so that no Area Chair in the group was in con?ict with any paper assigned to any Area Chair in the group.

• Unity
• action recognition
• aerial imagery
• classification
• edge detection
• filtering
• motion capture
• multi body tracking
• multi-modal sensors
• photography
• segmentation
• statistics
• surface reconstruction
• unsupervised learning
• visually impaired

• Computer Science Department, University of Illinois at Urbana Champaign, Urbana, USA

  David Forsyth

• Department of Computing, Oxford Brookes University, Wheatley, Oxford, UK

  Philip Torr

• Department of Engineering Science, University of Oxford, Oxford, UK

  Andrew Zisserman

Policies and ethics