AI Powered Networked Media Exploration
Deep learning based artificial intelligence (AI) have been proven to be very efficient in computer vision tasks, such as detection, tracking, recognition, etc. Recently, we have also observed the interesting trend to apply the AI technologies to networked media applications, ranging from image/video compression, to adaptive real-time streaming, to overlay routing, and even to joint vision tasks and compression.
In this talk, I would like to report the research activities conducted in our lab, including the deep image compression, neural adaptive real-time streaming for cloud gaming, and CodeVision, to demonstrate the efficiency when applying the learning methodologies to the traditional networked media applications.
Zhan Ma received the B.S. and M.S. degrees from Huazhong University of Science and Technology, Wuhan, China, in 2004 and 2006, respectively, and the Ph.D. degree from the Tandon School of Engineering of New York University, New York, NY, USA, in 2011. He is currently on the faculty of Electronic Science and Engineering School, Nanjing University, Nanjing, China. From 2011 to 2014, he was with Samsung Research America, Dallas, TX, USA, and Futurewei Technologies, Inc., Santa Clara, CA, USA, respectively. His current research interests include the video compression, gigapixel streaming, and multispectral signal processing. His researches have been supported by the national natural science foundation (NSFC) of China, National Key Research and Development Program, Jiangsu NSFC, WeChat, Huawei, etc.