Multimedia Computing Laboratory (MCLab)

Research Center for Information Technology Innovation (CITI), Academia Sinica

Wen-Huang Cheng received the B.S. and M.S. degrees in computer science and information engineering from National Taiwan University, Taipei, Taiwan, in 2002 and 2004, respectively, where he received the Ph.D. degree from the Graduate Institute of Networking and Multimedia in 2008 with highest honors. He is an Assistant Research Fellow of the Research Center for Information Technology Innovation (CITI), Academia Sinica, Taipei, Taiwan, where he is the founding leader of Multimedia Computing Laboratory (MCLab) in CITI: http://mclab.citi.sinica.edu.tw/, and also an Adjunct Assistant Research Fellow of the Institute of Information Science (IIS). Before joining Academia Sinica, he was a principal researcher at the MagicLabs, HTC Corporation, Taoyuan, Taiwan, from 2009 to 2010. His current research interests include multimedia content analysis, computer vision, human computer interaction, and mobile multimedia applications.

He has received numerous research awards, including the Best Reviewer Award by the 2013 Pacific-Rim Conference on Multimedia (PCM), the Excellent Junior Research Investigator Grant by National Science Council in 2012, the Best Poster Paper Award by the 2012 International Conference on 3D Systems and Applications (3DSA). He supervised his postdoctoral fellows to award the Academia Sinica Postdoctoral Fellowship in 2011 and 2013.

In recent years, the proliferation of multimedia contents has lead to the great demand for advanced information technology to improve people's multimedia experience. To effectively respond to such human requests, a premise is that multimedia systems should be "smart" enough to, in a sense, understand the contents, e.g. what a video scene is about, what objects are present, and who is talking, etc. However, it is recognized that there exists a huge gap, namely semantic gap, between the rich meaning and interpretation that humans could read in the contents and the simplicity of low-level features that current algorithms can actually compute. This fact makes most existing multimedia systems being far from satisfactory to meet human needs. The Multimedia Computing Laboratory (MCLab) is then founded in July 2010 in the Research Center for Information Technology Innovation (CITI), Academia Sinica. In responding to the above challenges, its research objective is to develop systematic approaches to enable automatic computation of multimedia semantics, whereby innovative and personalized multimedia applications are created.

whcheng@citi.sinica.edu.tw