施国琛教授个人简介

Biography of Timothy K. Shih

Dr. Shih is a Professor at the National Central University, Taiwan. He was the Dean of College of Computer Science, Asia University, Taiwan and the Department Chair of the CSIE Department at Tamkang University, Taiwan. Dr. Shih is a Fellow of the Institution of Engineering and Technology (IET). In addition, he is a senior member of ACM and a senior member of IEEE. Dr. Shih also joined the Educational Activities Board of the Computer Society. His current research interests include Multimedia Computing and Distance Learning. Dr. Shih has edited many books and published over 480 papers and book chapters, as well as participated in many international academic activities, including the organization of more than 60 international conferences. He was the founder and co-editor-in-chief of the International Journal of Distance Education Technologies, published by the Idea Group Publishing, USA. Dr. Shih is an associate editor ofthe ACM Transactions on Internet Technology and an associate editor of the IEEE Transactions on Learning Technologies.He was also an associate editor of the IEEE Transactions on Multimedia. Dr. Shih has received many research awards, including research awards from National Science Council of Taiwan, IIAS research award from Germany, HSSS award from Greece, Brandon Hall award from USA, and several best paper awards from international conferences. Dr. Shih has been invited to give more than 30 keynote speeches and plenary talks in international conferences, as well as tutorials in IEEE ICME 2001 and 2006, and ACM Multimedia 2002 and 2007.

施国琛教授讲座大纲

Video Forgery and Motion Editing

The Original Video / The Falsified Video

Video Forgery is a technique for generating fake video by altering, combining, or creating new video contents. We change the behavior of actors in a video. For instance, the outcome of a 100-meter race in the Olympic Game can be falsified. We track objects and segment motions using a modified mean shift mechanism. The resulting video layers can be played in different speeds and at different reference points with respect to the original video. In order to obtain a smooth movement of target objects, a motion interpolation mechanism is proposed based on reference stick figures (i.e., a structure of human skeleton) and video inpainting mechanism. The video inpainting mechanism is performed in a quasi-3D space via guided 3D patch matching. Interpolated target objects and background layers are fused. It is hard to tell whether a falsified video is the original. In addition, in this talk, we demonstrate a new technique to allow users to change the dynamic texture used in a video background for special effect production. For instance, the dynamic texture of fire, smoke, water, cloud, and others can be edited through a series of automatic algorithms. Motion estimations of global and local textures are used. Video blending techniques are used in conjunction with a color balancing technique. The editing procedure will search for suitable patches in irregular shape blocks, to reproduce a realistic dynamic background, such as large waterfall, fire scene, or smoky background. The technique is suitable for making science fiction movies. We demonstrate the original and the falsified videos in our website at Although video falsifying may create a moral problem, our intension is to create special effects in movie industry.

Keywords: Video Forgery, Object Tracking, Motion Estimation, Special Effect Production

李青教授个人简介

/ Qing Li is a Professor at the Department of Computer Science, City University of Hong Kong where he joined as a faculty member since Sept 1998. Meanwhile, he is a Guest Professor at the Zhejiang University and at the Zhongshan (Sun Yat-Sen) University, an Adjunct Professor atthe University of Science and Technology of China, the Huazhong University of Science and Technology, and the State Key Lab of Software Engineering (Wuhan University). He received his B.Eng. from the Hunan University, and M.Sc. and Ph.D. degrees from the University of Southern California (Los Angeles), all in computer science. His research interests include database modeling, Web services, multimedia retrieval and management, and e-learning systems. He has authored more than70 papers in numerous technical journals (incl. ACM and IEEE Transactions), and over 220 papers in major international conferences (incl. VLDB, WWW, ICDE, ACM MM, ICDCS). He is actively involved in the research community by serving as an editor of technical journals, including IEEE Transactions on Knowledge and Data Engineering, ACM Transactions on Internet Technology, and World Wide Web, and as Conference and Program Chair/Co-Chair of numerous major international conferences. He is currently the Chairman of the Hong Kong Web Society, the Deputy Chairman of the WISE Society, a Councilor of the Database Society of Chinese Computer Federation (CCF), and a Steering Committee Member of DASFAA, ICWL, and WAIM. Prof. Li is a Fellow of IET (UK), and a senior member of IEEE (US) and CCF (China).

李青教授讲座大纲

Personalized Resource Search by Tag-based User Profiles and Resource Profiles

Abstract:

With the increase of media-sharing web sites such as YouTube andFlickr, there are more and more shared multimedia resources on the Web. Multimediasearch becomes more important and challenging, as users demand higherretrieval quality. To achieve this goal, multimedia search needs to take users’personalized information into consideration. Collaborative tagging systems allowusers to annotate resources with their own tags, which provide a simple butpowerful way for organizing, retrieving and sharing different types of social media.The user profiles obtained from collaborative tagging systems should be veryuseful for resource retrieval. In this talk, we present a new method to modeluser profiles and resource profiles from wider perspectives and apply them topersonalized resource search in a collaborative tagging environment. We implementa prototype system named as FMRS. Experiments in FMRS show that ourproposed method outperforms baseline methods.