Computer Vision -- ACCV 2009

1. Front Matter

   PDF

2. Oral Session 1: Multiple View and Stereo

   1. Multiple View Reconstruction of a Quadric of Revolution from Its Occluding Contours

      • Pierre Gurdjos, Vincent Charvillat, Géraldine Morin, Jérôme Guénard

      Pages 1-12

   2. Robust Focal Length Estimation by Voting in Multi-view Scene Reconstruction

      • Martin Bujnak, Zuzana Kukelova, Tomas Pajdla

      Pages 13-24

   3. Support Aggregation via Non-linear Diffusion with Disparity-Dependent Support-Weights for Stereo Matching

      • Kuk-Jin Yoon, Yekeun Jeong, In So Kweon

      Pages 25-36

3. Oral Session 2: Face and Pose Analysis

   1. Manifold Estimation in View-Based Feature Space for Face Synthesis across Poses

      • Xinyu Huang, Jizhou Gao, Sen-ching S. Cheung, Ruigang Yang

      Pages 37-47

   2. Estimating Human Pose from Occluded Images

      • Jia-Bin Huang, Ming-Hsuan Yang

      Pages 48-60

   3. Head Pose Estimation Based on Manifold Embedding and Distance Metric Learning

      • Xiangyang Liu, Hongtao Lu, Daqiang Zhang

      Pages 61-70

   4. 3D Reconstruction of Human Motion and Skeleton from Uncalibrated Monocular Video

      • Yen-Lin Chen, Jinxiang Chai

      Pages 71-82

4. Oral Session 3: Motion Analysis and Tracking

   1. Mean-Shift Object Tracking with a Novel Back-Projection Calculation Method

      • LingFeng Wang, HuaiYu Wu, ChunHong Pan

      Pages 83-92

   2. A Shape Derivative Based Approach for Crowd Flow Segmentation

      • Si Wu, Zhiwen Yu, Hau-San Wong

      Pages 93-102

   3. Learning Group Activity in Soccer Videos from Local Motion

      • Yu Kong, Weiming Hu, Xiaoqin Zhang, Hanzi Wang, Yunde Jia

      Pages 103-112

   4. Combining Discriminative and Descriptive Models for Tracking

      • Jing Zhang, Duowen Chen, Ming Tang

      Pages 113-122

5. Oral Session 4: Segmentation

   1. From Ramp Discontinuities to Segmentation Tree

      • Emre Akbas, Narendra Ahuja

      Pages 123-134

   2. Natural Image Segmentation with Adaptive Texture and Boundary Encoding

      • Shankar R. Rao, Hossein Mobahi, Allen Y. Yang, S. Shankar Sastry, Yi Ma

      Pages 135-146

   3. Gradient Vector Flow over Manifold for Active Contours

      • Shaopei Lu, Yuanquan Wang

      Pages 147-156

   4. 3D Motion Segmentation Using Intensity Trajectory

      • Hua Yang, Greg Welch, Jan-Michael Frahm, Marc Pollefeys

      Pages 157-168

6. Oral Session 5: Feature Extraction and Object Detection

   1. Vehicle Headlights Detection Using Markov Random Fields

      • Wei Zhang, Q. M. Jonathan Wu, Guanghui Wang

      Pages 169-179

   2. A Novel Visual Organization Based on Topological Perception

      • Yongzhen Huang, Kaiqi Huang, Tieniu Tan, Dacheng Tao

      Pages 180-189

   3. Multilevel Algebraic Invariants Extraction by Incremental Fitting Scheme

      • Bo Zheng, Jun Takamatsu, Katsushi Ikeuchi

      Pages 190-200

   4. Towards Robust Object Detection: Integrated Background Modeling Based on Spatio-temporal Features

      • Tatsuya Tanaka, Atsushi Shimada, Rin-ichiro Taniguchi, Takayoshi Yamashita, Daisaku Arita

      Pages 201-212

It gives us greatpleasureto presentthe proceedings of the 9th Asian Conference on Computer Vision (ACCV 2009), held in Xi’an, China, in September 2009. This was the ?rst ACCV conference to take place in mainland China. We received a total of 670 full submissions, which is a new record in the ACCV series. Overall, 35 papers were selected for oral presentation and 131 as posters, yielding acceptance rates of 5.2% for oral, 19.6% for poster, and 24.8% in total. In the paper reviewing, we continued the tradition of previous ACCVsbyconductingthe processinadouble-blindmanner.Eachofthe33Area Chairs received a pool of about 20 papers and nominated a number of potential reviewers for each paper. Then, Program Committee Chairs allocated at least three reviewers to each paper, taking into consideration any con?icts of interest and the balance of loads. Once the reviews were ?nished, the Area Chairs made summaryreportsforthepapersintheirpools,basedonthereviewers’comments and on their own assessments of the papers.

• 3D vision
• SVM
• active contour models
• algorithms
• biometrics
• statistical methods
• watermarking

• Department of Machine Intelligence, Peking University, Beijing, China

  Hongbin Zha

• Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan

  Rin-ichiro Taniguchi

• Birkbeck College, Department of Computer Science, University of London, London, UK

  Stephen Maybank

Policies and ethics