Robust Object Re-Identification in Large Repository for Mobile Visual Search

题目:Robust Object Re-Identification in Large Repository for Mobile Visual Search

主讲人: Professor Zhu Li

University of Missouri, Kansas City


地点:北京大学 计算机所大楼 106报告厅


Mobile visual search has many important applications in surveillance, security, virtual and augmented reality and e-commerce. A central technical problem to enable these application is the visual object identification against a very large repository. Robust local features that are invariant to the image formation process, good aggregation and compression schemes for the local features that offers indexing efficiency and matching accuracy, 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.


Zhu Li is an associated professor with the Dept of CSEE, University of Missouri, Kansas City, USA, also serving as ad hoc co-chair for the MPEG Point Cloud Compression group. He received his PhD from Electrical & Computer Engineering from Northwestern University in 2004, and was Sr. Staff Researcher/Sr. Manager with Samsung Research America's Multimedia Core Standards Research Lab in Dallas, from 2012-2015, Sr.Staff Researcher with FutureWei(Huawei)'s Media Lab in Bridgewater, NJ, from 2010-2012, Assistant Professor with the Dept of Computing, the Hong Kong Polytechnic University from 2008 to 2010, and a Principal Staff Research Engineer with the Multimedia Research Lab (MRL), Motorola Labs, Schaumburg, Illinois, from 2000 to 2008. His research interests include image/video analysis, compression, and communication and associated optimization and machine learning tools. He has 30+ issued or pending patents, 90+ publications in book chapters, journals, conference proceedings and standards contributions in these areas. He is an IEEE senior member, elected member of the IEEE Multimedia Signal Processing (MMSP) Technical Committee ,2014-17,2017-20, elected Steering Chair (2016-18) of the IEEE Multimedia Communication Technical Committee (MMTC). He is an Associated Editor for IEEE Trans. On Multimedia (2015~), IEEE Trans. on Circuits & System for Video Technology (2016~), Springer Journal on Signal Processing Systems (2015~), co-editor for the Springer-Verlag book on "Intelligent Video Communication: Techniques and Applications". He served on numerous conference and workshop TPCs and was symposium co-chair at IEEE ICC'2010, and on the Best Paper Award Committee for IEEE ICME 2010. He received a Best Paper Award from IEEE Int'l Conf on Multimedia & Expo (ICME) at Toronto, 2006, and a Best Paper Award from IEEE Int'l Conf on Image Processing (ICIP) at San Antonio, 2007.

版权所有 © 2007 北京大学计算机科学技术研究所