第六届计算机视觉和模式识别能量优化算法国际研讨会

2007年8月28-30日 (8月26、27日报到，地点：凤凰山庄)

中国莲花山计算机视觉与信息科学研究院(LHI/Ezhou)

参加人员名单 (Participants list)

会议主题

大会主题：探讨计算机视觉和模式识别中的概率推理及能量函数最优化等关键性问题

    计算机视觉和模式识别中的很多问题都可以通过概率推理和优化能量函数来表示。EMMCVPR 2007主要关注与表示、学习和推理有关的主题。主题一：如何以概率推理的方式来表示视觉问题，这些概率推理使用定义在结构关系系统（如图表示以及产生式语法等）上的经典的概率分布。主题二：利用来自于统计，计算机科学以及应用数学等领域的高级技术来发展有效的学习推理算法。主题三：用人工标注的标准数据集作为评判算法的基准，并基于数据集训练学习算法。主题四：高层视觉和人类感知过程的关系，包括在真实场景中的功能语义层次的描述。其它的主题包括图像解译、信息综合、及自底而上的方法和自顶向下的方法这两者之间的平衡等。 

    2007年8月，我们在中国国家自然科学基金和国际模式识别委员会（IAPR）的资助下召开了本次会议。来自美国洛杉矶加州大学、宾夕法尼亚大学、布朗大学、华盛顿大学、费城大学、加拿大西昂特里奥大学、瑞士计算机科学院、德国波恩大学、英国爱丁堡大学、意大利威尼斯大学、韩国Chonnam国立大学、日本千叶大学的国外学者、教授共35人和来自中科院计算所、清华大学、北京大学、北京航空航天大学、北京理工大学、中国传媒大学、复旦大学、浙江大学、武汉大学、华中科技大学等高校院所的国内学者、教授共75人出席了本次会议。本次会议共收到投稿140余篇，录用了口头报告22篇、张贴报告15篇，这些论文的作者均出席了本会。来自美国布朗大学的Michael Black教授、瑞士计算机科学院的Joachim Buhmann教授分别作了题为“Fields of Experts: High-order Markov Random Field Models of Natural Scenes”、“Stochastic Optimization: A Learning Methodology for Vision”的专题特邀报告，给与会者带来了最新的计算机视觉领域的研究成果。

（点右键另存到本机，可查看此图片高清晰版）

来自美国布朗大学的 Michael Black 教授在会上作了题为：
Fields of Experts:High-order Markov Random Field Models Natural Scenes 的专题特邀报告

来自瑞士计算机科学院的 Joachim Buhmann 教授作了题为：
Stochactic Optimization:A learning Methodology for Vision 的专题特邀报告

研讨会会场的气氛热烈而融洽，专家、学者展开了热烈的讨论。

口头宣读论文：

1. Improved Object Tracking Using an Adaptive Colour Model
--- Zezhi Chen and Andrew M. Wallace
2. Compositional Object Recognition, Segmentation, and Tracking in Video
--- Bjorn Ommer and Joachim M. Buhmann
3. Bayesian Order-Adaptive Clustering for Video Segmentation
--- Peter Orbanz, Samuel Braendle, & Joachim Buhmann
4. Dynamic Feature Cascade for Multiple Object Tracking with Trackability Analysis
--- Zheng Li, Haifeng Gong, Song-Chun Zhu, and Nong Sang
5. Bottom-Up Recognition and Parsing of the Human Body
--- Praveen Srinivasan and Jianbo Shi
6. Introduction to a Large-Scale General Purpose Ground Truth Database: Methodology, Annotation Tool and Benchmarks
--- Benjamin Yao, Michael Yang, and Song-Chun Zhu
7. An Automatic Portrait System based on And-Or Graph Representation
--- Feng Min, Jin-Li Sun, Song-Chun Zhu, and Nong Sang
8. Object Category Recognition Using Generative Template Boosting
--- Woody Peng, Liang Lin, Jake Porway, Nong Sang, and Song-Chun Zhu
9. Bayesian Inference for Layer Representation with Mixed Markov Random Field
--- Ru-Xin Gao, Tian-Fu Wu, Song-Chun Zhu, and Nong Sang
10. Continuous Global Optimization in Multiview 3D Reconstruction
--- Kalin Kolev, Maria Klodt, Thomas Brox, Selim Esedoglu, and Daniel Cremers
11. A New Bayesian Method for Range Image Segmentation
--- Smaine Mazouzi and Mohamed Batouche
12. Szemeredi' s Regularity Lemma and its Applications to Pairwise Clustering and Segmentation
--- Anna Sperotto & Marcello Pelillo，Samuel Rota Bulo.
13. Exact Solution of Permuted Submodular MinSum Problems
--- Dmitrij Schlesinger
14. Efficient Shape Matching Via Graph Cuts
--- Frank R. Schmidt, Eno Toppe, Daniel Cremers and Yuri Boykov
15. Simulating Classic Mosaics with Graph Cuts
--- Yu Liu, Olga Veksler and Olivier Juan
16. A Pupil Localization Algorithm based on Adapative Gabor Filtering and Negative Radial Symmetry
--- Fei Xiong, Yi Zhang, and Guilin Zhang
17. Decomposing Document Images by Heuristic Search
--- Dashan Gao and Yizhou Wang
18. An a contrario approach for parameters estimation of a motion-blurred image
--- Feng Xue, Quansheng Liu, and Jacques Forment
19. Discrete Skeleton Evolution
--- Xiang Bai and Longin Jan Latecki
20. Shape Classification Based on Skeleton Path Similarity
--- Xingwei Yang, Xiang Bai, Deguang Yu, & Longin Jan Latecki
21. Removing Shape-Preserving Transformations in Square Root Elastic (SRT) Framework for Shape Analysis of Curves
--- Shantanu H. Joshi, Eric Klassen, Anuj Srivastava, and Ian Jermyn
22. Shape Analysis of Open Curves with Applications to Study of Fiber Tracks in DT-MRI Data
--- Niokolay Balov, Anuj Srivastava, Chunming Li, and Zhaohua Ding 

张贴论文：

1. An Effective Multi-level Algorithm Based on Simulated Annealing for Bisecting Graph
--- Lingyu Sun, Ming Leng
2. Dichromatic reflection separation from a single image
--- Yun-Chung Chung, Shyang-Lih Chang, Shen Cherng, and Sei-Wang Chen
3. CIDER: Corrected Inverse-Denoising Filter for Image Restoration
--- You-Wei Wen, Michael Ng, Wai-ki Ching
4. Corrupted Region Restoration using Second Order Tensors and Segmentation
--- Jonghyun Park, Nguyen Trung Kien
5. 3D Computation of Gray Level Co-occurrence in Hyperspectral Image Cubes
--- Fuan Tsai, Chun-Kai Chang, Jian-Yeo Rau, Tang-Huang Lin, Gin-Ron Liu
6. Skew Detection Algorithm for Form Document Based on Elongate Feature
--- Feng-ying Xie, Zhi-guo Jiang, Lei Wang
7. Active Appearance Models Fitting with Occlusion
--- Xin Yu, Jinwen Tian, Jian Liu
8. Vehicle Tracking Based on Image Alignment in Aerial Videos
--- Hong Zhang, Fei Yuan
9. Probabilistic Fiber Tracking using Particle Filtering and Von Mises-Fisher Sampling
--- Fan Zhang, Casey Goodlett, Edwin Hancock, Guido Gerig
10. Marked Point Process for Vascular Tree Extraction on Angiogram
--- Kaiqiong Sun, Nong Sang, Tianxu Zhang
11. A Boosting Discriminative Model for Moving Cast Shadow Detection
--- Yufei Zha, Ying Chu, Duyan Bi
12. Combining Both Irises for Personal Authentication
--- Xiangqian Wu, David Zhang, Kuanquan Wang, Ning Qi
13. An Energy Minimisation Approach to Attributed Graph Regularisation
--- Zhouyu Fu, Antonio Robles-Kelly
14. Surface Reconstruction from LiDAR Data with Extended Snake Theory
--- Yi-Hsing Tseng, Kai-Pei Tang, Fu-Chen Chou

会议时间、地点：

       会议时间：2007年8月28－8月30日（3天）26、27报道

       地点：凤凰山庄

         公共交通：从北京乘Z37次列车到达武汉武昌火车站，然后到傅家坡车站（可在火车站乘TAXI到约5到10元）乘长途

         汽车（10分钟一班）到达鄂州中心汽车站，然后乘TAXI（约10元）到达凤凰山庄。