Your browser does not support JavaScript!
資訊系統與應用研究所
[May-16] The MPEG Experience: Standardization and Research

Seminar of Institute of Information Systems and Applications

Speaker :

Prof. Wen-Hsiao Peng
CS Department, National Chiao Tung University

Topic :

The MPEG Experience: Standardization and Research

Date :

13:30-15:00 Wednesday 16-May-2018

Place :

台達館R105Delta Building R105

Host :

Prof. YI-SHIN CHEN

 

Abstract

In this seminar, I shall talk about my personal experience with the Moving Pictures Experts Group (MPEG) standardization process and my recent research on deep video/image compression. The MPEG has been the main driving force behind the continuously evolved MPEG families of video standards, with MPEG-H (a.k.a. HEVC/H.265) being the latest out of a joint effort with ITU-T. Its almost 30 years of history since 1988 speaks for its proven working model for transforming academic research into industry products with worldwide impacts. Being involved in the development of three major MPEG standards over the last 10 years, I would like to share how my research group managed to survive in the highly competitive and industry-oriented standardization process. It is my hope that our lessons learned could further young dream seekers to be courageous in taking up their challenges. The second part of this talk shall shed lights on emerging deep video/image compression technologies, including applying reinforcement learning to video encoder control and autoencoder-based deep image compression.

Bio

Dr. Wen-Hsiao Peng (SM’13) received the B.S., M.S., and Ph.D. degrees from National Chiao Tung University (NCTU), Hsinchu, Taiwan, in 1997, 1999, and 2005, respectively, all in electronics engineering.

He was with the Intel Microprocessor Research Laboratory, USA from 2000 to 2001, where he was involved in the development of ISO/IEC MPEG-4 fine granularity scalability. Since 2003, he has actively participated in the ISO/IEC and ITU-T video coding standardization process and contributed to the development of SVC, HEVC and SCC standards. He is currently a Professor with the Computer Science Department, NCTU, and was a Visiting Scholar with the IBM Thomas J. Watson Research Center, USA, from 2015 to 2016. He has authored over 60 journal/conference papers and over 60 ISO/IEC and ITU-T standards contributions. His research group at NCTU was one of the few university teams around the world that participated in the Call-for-Proposals on HEVC and its Screen Content Coding extensions. His current research interests include cross-domain/task adaptation using deep learning, meta-learning, reinforcement learning for video encoder control, deep video/image compression, multimedia analytics, and computer vision.

Dr. Peng is a Member of the VSPC and MSA Technical Committees of the IEEE CAS Society. He was Technical Program Co-chair for 2011 IEEE VCIP, 2017 IEEE ISPACS and 2018 APSIPA ASC, Area Chair for IEEE ICME and VCIP, Review Committee Member for IEEE ISCAS, and organized several special sessions in these and other conferences. He served as Lead Guest Editor/Guest Editor/Senior Editorial Board Member for IEEE JETCAS. More recently, he was elected Distinguished Lecturer of APSIPA.

 

All faculties and students are welcome to join.

瀏覽數