【2016学术报告07】 Rate Agnostic Content Identification and De-Duplication in Media Networks
Title: Rate Agnostic Content Identification and De-Duplication in Media Networks
Speaker: Zhu Li, Associate Professor, University of Missouri
Time: 10:30-12:00, 24th, Nov. (Thu.)
Place: 1-312, FIT Building
Organizer: Research Institute of Information Technology (RIIT), Tsinghua University
Zhu Li is now an Associate Professor with the Dept of Computer Science & Electrical Engnieering (CSEE), University of Missouri,Kansas City, and director of the Multimedia Computing & Communication (MC2) Lab. He received his PhD in Electrical & Computer Engineering from Northwestern University, Evanston in 2004. He is the ad-hoc group co-chair for the MPEG Point Cloud Compression group. He was AFRL Faculty Fellow at the US Air Force Academy in Summer 2016, Sr. Staff Researcher/Sr. Manager with Samsung Research America's Multimedia Standards Research Lab in Richardson, TX, 2012-2015, Sr. Staff Researcher/Media Analytics Group Lead with FutureWei (Huawei) Technology's Media Lab in Bridgewater, NJ, 2010~2012, and an 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, from 2000 to 2008.
His research interests include audio-visual analytics and machine learning with its application in large scale video repositories annotation, mining and recommendation, video object identification and event recognition, as well as video adaptation, source-channel coding and distributed optimization issues of the wireless video networks. He has 25 issued or pending patents, 90+ publications in book chapters, journals, conference proceedings and standard contributions in these areas. He is an IEEE senior member, Ad Hoc Co-Chair of the MPEG Point Cloud Compression group, associated editor (2015~) for IEEE Trans.on Multimedia, and associated editor (2016~) for IEEE Trans on Circuits & System for Video Technology, associated editor (2015~) for Journal of Signal Processing Systems (Springer), steering committee member of IEEE ICME, elected member (2014-2017) of the IEEE Multimedia Signal Processing (MMSP) Tech Committee, elected Vice Chair (2008-2010), Standards Liaison (2014-2016) and Steering Committee Chair (2016-) of the IEEE Multimedia Communication Technical Committee (MMTC), member of the Best Paper Award Committee, ICME 2010, co-editor for the Springer-Verlag book on "Intelligent Video Communication: Techniques and Applications", and " Multimedia Analysis, Computing and Communication,". He received the Best Poster Paper Award at IEEE Int'l Conf on Multimedia & Expo (ICME), Toronto, 2006, and the Best Paper (DoCoMo Labs Innovative Paper) Award at IEEE Int'l Conf on Image Processing (ICIP), San Antonio, 2007.
This talk is also a part of the APSIPA DL series: http://www.apsipa.org/edu.htm
The Internet is now dominated by the video traffic, and efforts are underway to re-architect the next gen Internet to better serve the video traffic, moving away from a connectivity centric design, to a content centric design. One central issue for this is a new compact and robust media content identification scheme that can enable efficient content discovery, routing, redundant elimination in the networks, and fast rate agnostic content identification and de-duplication in various network caches. In this talk, I will present an Scaled Eigen Appearance Feature (SEAF) modeling scheme that has been demonstrated to be very effective in playback verification, and a SEAF indexing for approximate nearest frame search, with a highly efficient likelihood prunning scheme, can be highly very efficient in de-duplicating large video segments repository in caches.