Institute of Information Science, Academia Sinica



Press Ctrl+P to print from browser


Toward High-Performance and Intelligent Video Editing: A Learning-Based approach

  • LecturerProf. Chia-Wen Lin (Department of Electrical Engineering, National Tsing Hua University)
    Host: Dr. Mark Hong-Yuan Liao
  • Time2010-01-29 (Fri.) 10:30 – 12:00
  • LocationAuditorium 106 at new IIS Building
Abstract: With the advance of 3C technology, modern people can easily possess their own daily A/V records. However, for a typical user, he or she may know how to record and replay audio-visual data, but usually has difficulty modifying the media contents or improving the media quality with his/her own wish. In this talk, we will show how machine learning techniques can be used to improve the quality of audio-visual data in an automatic way as well as to facilitate the editing of video contents in an intelligent and interactive manner. The talk will present two video editing tools: an eraser (video inpainting) and a magnifier (super-resolution). In addition to introducing state-of-the-art techniques, we will show how to enhance the performance of the two tools using learning techniques. First, we will show how to resolve the most critical spatio-temporal consistency problem in inpainting of video with dynamic-texture using manifold learning. second, we will present a new two-step face hallucination scheme to enhance the visual quality of face super-resolution both subjectively and objectively. In the proposed method, a Bayesian residue compensation is first performed to enhance the quality of a face globally, followed by a manifold-learning-based basis selection step to further refine the quality of facial parts. Bio: Chia-Wen Lin received his Ph.D. degree from the Department of Electrical Engineering, National Tsing Hua University (EE/NTHU), Hsinchu, Taiwan, in January 2000. He has been with EE/NTHU as Associate Professor since August 2007. Prior to joining EE/NTHU, he worked for the Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan from August 2000 to July 2007. He was with the Information and Communications Research Laboratories, Industrial Technology Research Institute (ICL/ITRI), Hsinchu, Taiwan, during 1992-2000, where his final post was Section Manager. His research interests include video networking and video content analysis. Dr. Lin is an Associate Editor of IEEE Transactions on Circuits and Systems for Video Technology and of Journal of Visual Communication and Image Representation. He serves as a Technical Program Chair of IEEE ICME 2010, and was a Special Session Chair of ICME 2009. He was a recipient of the Young Faculty Awards presented by National Chung Cheng University and of the Young Investigator Awards presented by National Science Council, Taiwan, in 2006.