Keynote Speeches

Professor Hyoung Joong Kim
Topic: Data compression by data hiding
Abstract:

Compression is a process to reduce entropy intentionally as low as possible. On the other hand, data hiding is a process to increase entropy unintentionally. Thus, compression and data hiding are opposite by nature. However, in this talk, it will be shown that compression by data hiding is possible. The concept of compression by data hiding is introduced. Several examples are presented to illustrate how to compute the embedding gain. Efficient method for achieving effective embedding gain is provided. For the measurable efficiency, concepts of the net embedding gain, compression gain, payload, and location map size are defined. Data hiding method with/without location map is presented.


Bio: Hyoung Joong Kim received his B.S., M.S., and Ph.D. degrees from Seoul National University, Seoul, Korea, in 1978, 1986, 1989, respectively. He joined the faculty of the Department of Control and Instrumentation Engineering, Kangwon National University, Korea, in 1989. He is currently a Professor of the Graduate School of Information Management and Security, Korea University, Korea since 2006. His research interests include parallel and distributed computing, multimedia computing, and multimedia security. He contributed to MPEG standardization for Digital Item Adaptation, File Format, Symbolic Music Representation, and Multimedia Application Format with more than 10 contributions and same number of patents. In addition, he filed many patents and published more than 30 reviewed papers to international journals including IEEE and ACM, and 2 peer-reviewed book chapters. He served as Guest Editor of the IEEE Transactions on Circuits and Systems for Video Technology, EURASIP Journal of Applied Signal Processing, and Technical Program Chair of many international conferences including International Workshop on Digital Watermarking (IWDW), and so on. He is a Vice Editor-in-Chief of the LNCS Transactions on Data Hiding and Multimedia Security, Associate Editors of well-known international journals, and Editors of many Lecture Notes in Computer Science series. He was the prime investigator of the national projects during 1997-2005 developing interactive and personalized digital television and many government projects. He is a member of ACM, IEEE and a couple of Korean academic societies. He is a President of the Digital Convergence Society. His research topics include content engineering, multimedia security, parallel and distributed systems, soft computing.

Biography:

Hyoung Joong Kim received his B.S., M.S., and Ph.D. degrees from Seoul National University, Seoul, Korea, in 1978, 1986, 1989, respectively. He joined the faculty of the Department of Control and Instrumentation Engineering, Kangwon National University, Korea, in 1989. He is currently a Professor of the Graduate School of Information Management and Security, Korea University, Korea since 2006. His research interests include parallel and distributed computing, multimedia computing, and multimedia security. He contributed to MPEG standardization for Digital Item Adaptation, File Format, Symbolic Music Representation, and Multimedia Application Format with more than 10 contributions and same number of patents. In addition, he filed many patents and published more than 30 reviewed papers to international journals including IEEE and ACM, and 2 peer-reviewed book chapters. He served as Guest Editor of the IEEE Transactions on Circuits and Systems for Video Technology, EURASIP Journal of Applied Signal Processing, and Technical Program Chair of many international conferences including International Workshop on Digital Watermarking (IWDW), and so on. He is a Vice Editor-in-Chief of the LNCS Transactions on Data Hiding and Multimedia Security, Associate Editors of well-known international journals, and Editors of many Lecture Notes in Computer Science series. He was the prime investigator of the national projects during 1997-2005 developing interactive and personalized digital television and many government projects. He is a member of ACM, IEEE and a couple of Korean academic societies. He is a President of the Digital Convergence Society. His research topics include content engineering, multimedia security, parallel and distributed systems, soft computing.

Professor Takashi Matsuyama
Topic: The State of the Art of 3D Video Technologies - Accurate 3D Shape and Motion Reconstruction, High Fidelity Visualization, and Efficient Coding for 3D Video
Abstract:

3D video is not CG animation but new image media recording 3D dynamic visual events in the real world as is; it records time varying 3D object shape with high fidelity surface properties (i.e. color and texture). Its applications cover wide varieties of personal and social human activities: entertainment (e.g. 3D game and 3D TV), education (e.g. 3D animal picture books), sports (e.g. sport performance analysis), medicine (e.g. 3D surgery monitoring), culture (e.g. 3D archive of traditional dances) and so on.

In this talk, we present our newest research attainments on 1. PC cluster system for real-time 3D reconstruction of dynamic object action from multi-view video images, 2. Deformable 3D mesh model and a graph-cut algorithm for the accurate 3D object shape and motion estimation, 3. High fidelity texture mapping algorithm for rendering natural-looking color and texture on the 3D object surface, and 4. Efficient and practical coding method of 3D video. Demonstrations include a real-time interactive 3D video presentation of Japanese traditional dances with a portable 3D pop-up dislpay device.

Biography:

Professor Takashi Matsuyama received B. Eng., M. Eng., and D. Eng. degrees in electrical engineering from Kyoto University, Japan, in 1974, 1976, and 1980, respectively. He is currently a professor of Department of Intelligence Science and Technology, Graduate School of Informatics, and a vice-president of Kyoto University.

His research interests include knowledge-based image understanding, computer vision, 3D video, and human-computer interaction.

His research interests include knowledge-based image understanding, computer vision, 3D video, and human-computer interaction. He wrote about 100 papers and books including two research monographs, A Structural Analysis of Complex Aerial Photographs, PLENUM, 1980 and SIGMA: A Knowledge-Based Aerial Image Understanding System, PLENUM, 1990. He won over ten best paper awards from Japanese and international academic societies including the Marr Prize at ICCV'95. He is on the editorial board of Pattern Recognition Journal.

He has been leading two five years research projects on (1) Development of High Fidelity Digitization Software for Large-Scale and Intangible Cultural Assets and (2) Foundations for Human-centered Communication in the Information Explosion Era. The projects were started from 2004 and 2006, respectively, under the support of the Ministry of Education, Culture, Sports, Science, and Technology.

He was given Fellowships from International Association for Pattern Recognition, Information Processing Society Japan, and Institute for Electronics, Information, and Communication Engineers Japan.

Professor Jianrong Tan
Topic: Multimodal information fusion in the virtual environment and its applications in product design
Abstract:

The integration of virtual reality and computer aided design technologies is a revolution in the history of design. Virtual environment provides more information and feedback to designers than the traditional desktop system can. Examples include immersive and stereoscopic visual information, haptic or tactile feedback, auditory feedback and etc. The multimodal information is in general rather intuitive and inspiring to the designers, resulting in globally enhanced insights, creativity and productivity. Moreover, multimodal virtual reality technology excels at the visualization of complex scene and information, which is particularly difficult in desktop systems.

In this talk, we present our newest research attainments on 1. Online synthesis of multi-channel visual signal; the construction of multimodal virtual environment; 2. Fusion of graphic, image and video signals in augmented reality environment; 3. Synthesis of visual and haptic signals in virtual assembly; 4. Virtual design and simulation in the multimodal virtual environment, including surface deformation based on hand gesture interface, virtual assembly with haptic interaction, virtual maintenance in augmented environment; 5. Demonstrations and Examples.


Biography:

Prof. Jianrong Tan is an academician of Chinese Academy of Engineering. He obtained his master’s degree from Huazhong University of Science and Technology, China and his Ph.D. from Zhejiang University, China, respectively. He is currently a professor of Zhejiang University, the dean of Department of Mechanical Engineering at Zhejiang University and a vice director of state key laboratory of CAD&CG, China.

His research interests mainly include mechanical design theory, digital design and manufacture, virtual reality and its applications in product design, and mass customization design. He received the support of National Outstanding Young Scientists Foundation of NSFC in 1995 and has completed 25 important research projects, published 142 academic papers and 8 research monographs. He Won 2 items of second prizes of National Award for Science and Technology Progress of China in 2004 and 2006, respectively.