【字色： 红 蓝 褐 绿 黑 紫 粉红 深蓝】
【字体:8 7 6 5 4 3 2 1】
题目： Tensor Analysis for Groupwise Correspondence in Computer Vision
报告人： 凌海滨 博士（Temple University）
时间： 2016年3月17日（星期四），下午15:00 – 16:00
邀请人： 王瀚漓 教授
Haibin Ling received the B.S. degree in mathematics and the MS degree in computer science from Peking University, China, in 1997 and 2000, respectively, and the PhD degree from the University of Maryland, College Park, in Computer Science in 2006. From 2000 to 2001, he was an assistant researcher at Microsoft Research Asia. From 2006 to 2007, he worked as a postdoctoral scientist at the University of California Los Angeles. After that, he joined Siemens Corporate Research as a research scientist. Currently, he is with Temple University as an Associate Professor and meanwhile visiting South China University of Technology as a Chair Professor. In addition, Dr. Ling is the Chief Scientist and a co-founder of HiScene Information Technologies. Dr. Ling’s research interests include computer vision, medical image analysis, human computer interaction, and machine learning. He received the Best Student Paper Award at the ACM Symposium on User Interface Software and Technology (UIST) in 2003, and the NSF CAREER Award in 2014. He is an editorial board member of the Pattern Recognition Journal, and has served as Area Chairs for CVPR 2014 and CVPR 2016.
Visual matching is a fundamental problem in computer vision (CV) and intensive research efforts have been devoted to building correspondence between a pair of visual objects. By contrast, finding correspondence among an ensemble of objects remains challenging. In this talk we will present a new unified framework for this problem and its applications. Specifically, we establish a close correlation between the classical multi-dimensional assignment (MDA) problem and low-rank tensor approximation. Such correlation paves a way of using high-order tensor analysis for groupwise visual matching that assumes an MDA formulation. Along the way, we developed a series of power-iteration algorithms and applied them to multi-target tracking, deformable trackinga and multi-graph matching.