標題圖片 標題圖片 標題圖片 標題圖片
:::

專題演講










Wing-Kin (Ken) Ma Associate Professor (IEEE Fellow)
Chinese University of Hong Kong


Title: 
Hyperspectral Unmixing: Insights and Beyond

Abstract: 
Hyperspectral unmixing (HU) is one of the most prominent research topics in hyperspectral imaging in remote sensing. HU aims at identifying the underlying materials and their corresponding compositions in the scene, using the high spectral degrees of freedom of hyperspectral images. Early HU research is based on smart intuitions from remote sensing, and recent involvements from other fields—such as signal processing, optimization and machine learning—have substantially enriched HU techniques. In this talk we will look at what are the key insights of HU from a signal processing perspective, how such insights lead to a unique branch of theory and methods for structured matrix factorization, and why HU has strong connections to problems from other areas such as machine learning, data analytics, computer vision and biomedical imaging. If time permits, we will also have a quick tour on hyperspectral super-resolution, an emerging and fundamentally intriguing topic in which HU also plays a role.

Speaker Biography:
Wing-Kin (Ken) Ma is an Associate Professor with the Department of Electronic Engineering, The Chinese University of Hong Kong. His research interests are in signal processing, optimization and communications, with recent activities focused on structured matrix factorization and applications, and MIMO transceiver designs and interference management. Dr. Ma is active in the Signal Processing Society. He served as editors of several journals, e.g., Senior Area Editor of IEEE Transactions on Signal Processing, Lead Guest Editor of a special issue in IEEE Signal Processing Magazine, to name a few. He was a member of the Signal Processing Theory and Methods (SPTM) Technical Committee, and he is currently a member of the Signal Processing for Communications and Networking (SPCOM) Technical Committee. He received Research Excellence Award 2013–2014 by CUHK, the 2015 IEEE Signal Processing Magazine Best Paper Award, and the 2016 IEEE Signal Processing Letters Best Paper Award. His students received ICASSP Best Student Paper Awards in 2011 and 2014. He is an IEEE Fellow. He is currently an IEEE SPS Distinguished Lecturer.


Chia-Wen Lin Professor (IEEE Fellow)

National Tsing Hua University, Taiwan


Title: 
Stereo Video Retargeting: Bringing the Theater Experience into Our Home

Abstract:
The popularity of stereo images/videos and various VR/AR display devices poses the need of resizing stereo image/video pairs. Nevertheless, traditional resizing methods like uniform scaling and cropping usually lead to annoying shape and depth distortions such as depth change and window violation. Although content-aware retargeting schemers can address such problems, existing content-aware methods often incur conflicts among the requirements on shape, depth, and temporal coherency preservation, thereby failing to meet one or more of these requirements. This can significantly degrade the quality of experience when watching at 3D movie at home. In this talk, we will introduce our recent results on how to simultaneously avoid shape and depth distortions as well as maintain the temporal coherency of shape and depth while resizing a stereo image/video to a desired size. Different from the existing methods, our method effectively avoids the conflicts among depth, shape and temporal-coherency requirements by relaxing the resizing constraints on those regions in a 3D scene that cannot be perceived by human eyes to maintain the temporal coherency of the remaining regions. Based on this new finding, our method employs depth information to derive effective temporal-coherency constraints so as to offer visually pleasing results and achieves significantly better retargeting performance than existing methods, making it possible to bring the theater experience into our home.

Speaker Biography:
Prof. Chia-Wen Lin received his PhD degree in Electrical Engineering from National Tsing Hua University (NTHU), Hsinchu, Taiwan in 2000. He is currently a Professor with the Department of Electrical Engineering, National Tsing Hua University, Taiwan. He is Deputy Director of the AI Research Center of NTHU. His research interests include image/video processing and video networking.
Dr. Lin is an IEEE Fellow. He is a Distinguished Lecturer of IEEE Circuits and System Society during 2018-2019. He has served as Associate Editor of IEEE Transactions on Image Processing, IEEE Transactions on Multimedia, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Multimedia, and Journal of Visual Communication and Image Representation. He also served as a Steering Committee member of the IEEE Transactions on Multimedia during 2013-2015. He was Chair of the Multimedia Systems and Applications Technical Committee of the IEEE CASS. He served as Technical Program Co-Chair of the IEEE ICME in 2010 and will be the Conference Chair of IEEE VCIP 2018 in Taichung and TPC Chair of IEEE ICIP 2019 in Taipei. His papers won the Best Paper Award of IEEE VCIP 2015, and the Young Investigator Award of SPIE VCIP 2005.