2016年1月14日，密苏里大学李竹教授应电子工程与信息科学系和多媒体计算与通信-教育部微软重点实验室的邀请在科大西区科技实验楼1213会议室做题为《Robust Object Re-Identification in Large Repository for Mobile Visual Search （移动视觉搜索中的目标重识别）》的高水平学术前沿讲座。在该讲座中，李竹教授介绍了移动视觉搜索中目标重识别方面的问题以及取得的最新研究成果，并与与会的老师和同学们进行了深入的交流和讨论。

报告人 李竹教授

李竹教授报告现场

　　报告摘要：

　　Mobile visual search has many important applications. A central technical problem to enable these application is the visual object identification against a very large repository. Robust local features are the focus of the recent MPEG standardization effort on Compact Descriptor for Visual Search (CDVS). In this talk, I will review the key technical challenges to the CDVS pipeline, and covering the novel contributions made in the CDVS work on alternative interesting points detection, more efficient interesting points aggregation scheme, indexing / hashing issues for object re-identification against large repository, and retrieval system optimization, as well as the future directions of the research in this area with new depth sensors and video inputs.

　　报告人简介：

　　Zhu Li is an associated professor with the Dept of CSEE, University of Missouri, Kansas City, USA. He received his PhD from Electrical & Computer Engineering from Northwestern University in 2004. He is an Associated Editor for IEEE Trans. On Multimedia (2015~), IEEE Trans. on Circuits & System for Video Technology (2016~). His research interests include audio-visual analytics, machine learning, video adaptation, and source-channel coding.