報告主題: New Wine in Old Bottles: Re-discover SVD in Visual Signal Processing
報告專家：Weisi Lin （林維斯）
報告時間：2016年3月24日（周四） 下午4時
報告地點：行政樓912
內容介紹😋🌖：
Singular Value Decomposition (SVD) has been known for long in signal representation, processing and understanding. In our recent research projects, we have revisited this topic and further explored its new potentials in image and video manipulations. This talk will start with our findings on singular values and vectors. Then, we are to discuss the applications of SVD toward more effective video compression, visual structure extraction, perceptual visualquality evaluation, scalable signal representation, and noise estimation for images. It is hoped that this talk would trigger more discussion into further research opportunities along this direction, especially to enable a common framework for various visual signal processing tasks (e.g., compression, recognition, search, and so on).
專家介紹🍲：
Weisi Lin obtained his BSc and MSc from Sun YatSen University, Guangzhou, and PhD from King’s College, London University, and is an active researcher in image processing, video compression, quality metrics and perceptual modeling of visual signals, and multimedia communication. He served as the head of the Visual Processing Lab and the Acting Manager of the Media Processing Department in Institute for Infocomm Research (I2R), Singapore. He is currently an Associate Professor, School of Computer Engineering, Nanyang Technological University. He published 150 international journal papers, 220+ conference papers, 2 authored books, 3 edited books, 9 book chapters and 7 patents, and successfully delivered R&D projects with $6m funding as the PI. He has been elected as a Distinguished Lecturer for IEEE Circuits and Systems Society (2016-2017), and Asia-Pacific Signal and Information Processing Association (2012-13), and given keynote/invited/tutorial/panel talks to over 20 international conferences. He is an AE for IEEE Trans. on Image Processing, IEEE Trans. Circuits and Systems for Video Technology, IEEE Signal Processing Letters and Journal of Visual Communication and Image Representation, and a past AE for IEEE Trans. on Multimedia. He has been elected as a Fellow of IEEE and IET. He believes that good theory is practical, and has kept a balance of academic research and industrial deployment (and business development) throughout his working life.
