学术报告
学术报告 您现在所在位置:首页 > 学术报告
High-Order Graphs in Computer Vision: A Pseudo-Bound Optimization Approach
文章来源:[]  作者:[]  时间:[2017-04-18]  阅读:1574 次
报告题目:High-Order Graphs in Computer Vision: A Pseudo-Bound Optimization Approach
报告人:Prof. Ismail Ayed 加拿大魁北克大学
邀请人:袁景 教授
报告时间:4月25日 (周二)14:30
报告地点:信远楼II206数统院报告厅
报告人简介:Ismail Ben Ayed received the PhD degree (with the highest honor) in computer vision from the INRS, University of Quebec, Montreal, QC, in 2007. He is currently Associate Professor at the ETS, University of Quebec, where he holds an institutional research chair on artificial intelligence in medical imaging. Before joining the ETS, he worked for 8 years as a scientist at GE Healthcare, London, ON, where he conducted research in medical image analysis. He also holds an adjunct professor appointment at Western University (since 2012). Ismail’s interests are in optimization, computer vision, machine learning and their potential applications in medical image analysis. He co-authored a book and over seventy peer-reviewed publications, mostly published in the top venues in these subject areas. During his experience with GE, he received the GE innovation award (2010) and filed seven US patents. Dr. Ben Ayed serves regularly as program committee member for the flagship conferences of the field, and as regular reviewer for the top journals. He received the outstanding reviewer award for CVPR in 2015.
报告摘要:Recently, optimization of high-order and non-submodular discrete functions has drawn tremendous research interests. Such hard-to-optimize functions arise naturally in a breadth of computer vision and machine learning problems, e.g., clustering, semantic segmentation, surface registration, classification, image deconvolution, curvature regularization, among many others. In this talk, I will discuss some recent developments in this direction, focusing on a general and powerful pseudo-bound optimization framework. I will discuss the key technical aspects of this framework using various examples and illustrations, and show how it improves the state-of-the-art in difficult vision/learning problems, including constrained graph clustering as well as a variety of semantic image segmentation examples. 
Some publications related to the talk:
• M. Tang et al.: Normalized Cut meets MRFs, ECCV 2016
• Ben Ayed et al.: Distribution Matching with the Bhattacharyya Similarity: A Bound Optimization Framework. IEEE Trans. on Pattern Anal. Mach. Intell., 2015
• M. Tang et al.: Pseudo-bound Optimization for Binary Energies, ECCV 2014
• Ben Ayed et al.: Auxiliary Cuts for General Classes of Higher Order Functionals, CVPR 2013
• M. Tang et al.: Secrets of GrabCut and Kernel K-Means, ICCV 2015
[打印 关闭    
 上一篇: 五运六气理论中气象因素的统计分析
 下一篇: 无线网络优化与资源调度