中国科学院自动化研究所   设为首页   加入收藏  联系我们
 
English
网站首页     实验室概况     研究队伍     组织机构     学术交流     科研成果     人才培养     开放课题     创新文化     资源共享     联系我们
    学术讲座

2013-12-17 Exemplar Cut and Object Tracking


模式识别系列讲座

Lecture Series in Pattern Recognition

 

题   目(TITLE):Exemplar Cut and Object Tracking

讲座人(SPEAKER):Prof. Ming-Hsuan Yang(University of California)

主持人(CHAIR):Prof. Stan Z. Li

时    间(TIME):December 17 (Tuesday), 2013, 15:00 PM

地   点(VENUE):No.2Conference Room (3rd floor), Intelligence Building

报告摘要(ABSTRACT):

In this first part of this talk, I will present a hybrid parametric and nonparametric algorithm,exemplarcut, for generating class-specific object segmentation hypotheses. For the parametric part, we train a pylon model on a hierarchical region tree as the energy function for segmentation. For the nonparametric part, we match the input image with eachexemplarby using regions to obtain a score which augments the energy function from the pylon model. Our method thus generates a set of highly plausible segmentation hypotheses by solving a series ofexemplaraugmented graphcuts. Experimental results on the Graz and PASCAL datasets show that the proposed algorithm achieves favorable segmentation performance against the state-of-the-art methods in terms of visual quality and accuracy.

In the second part, I will present arecentbenchmark on online objecttrackingalgorithms (29 methods on 50 sequences). While much progress has been made inrecentyears with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewingrecentadvancesof online objecttracking, we carry out large scale experiments with various evaluation criteria to understand how these algorithms perform. The test image sequences are annotated with different attributes for performance evaluation and analysis. By analyzing quantitative results, we identify effective approaches for robusttrackingand provide potential future research directions in this field.

报告人简介(BIOGRAPHY):

Ming-Hsuan Yang is an associate professor in Electrical Engineering and Computer Science at University of California, Merced. He received the PhD degree in Computer Science from the University of Illinois at Urbana-Champaign in 2000. He has served as an area chair for several conferences including IEEE Conference on Computer Vision and Pattern Recognition, IEEE International Conference on Computer Vision, European Conference on Computer Vision, Asian Conference on Computer, AAAI National Conference on Artificial Intelligence, and IEEE International Conference on Automatic Face and Gesture Recognition. He will serve as a program co-chair for Asian Conference on Computer Vision in 2014. He served as an associate editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence from 2007 to 2011, and currently is as an associate editor of the International Journal of Computer Vision, Image and Vision Computing and Journal of Artificial Intelligence Research. Yang received the Google Faculty Award in 2009, and the Distinguished Early Career Research award from the UC Merced senate in 2011, and the Faculty Early Career Development (CAREER) award from the National Science Foundation in 2012. He is a senior member of the IEEE and the ACM.


 

友情链接
 
中科院自动化研究所 模式识别国家重点实验室 事业单位  京ICP备14019135号-3
NLPR, INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES