National Cheng Kung University,       Tainan, Taiwan


Tutorial 1
Progress toward Three-dimensional Television
Speaker: Yo-Sung Ho, GIST Korea
Duration: 3 hours
Abstract Download

Tutorial 2
Digital Data Forensics
Speaker: Yun Qing Shi, New Jersey Institute of Technology, USA
Duration: 3 hours
Abstract Download

Tutorial 3
Best Practices and Methodologies of European Living Labs (Tentative)
Speaker: Esteve Almirall, UPC, Technical University of Catalonia
Duration: 3 hours
Abstract Download

Tutorial 4
Video Near-Duplicate Detection and its Application to Video Mining
Speaker: Shin'ichi Satoh, NII Japan
Duration: 3 hours
Abstract Download


Prof. Yo-Sung Ho


Gwangju Institute of Science and Technology (GIST)

Tutorial Title: Progress toward Three-dimensional Television


In recent years, various multimedia services have become available and the demand for three-dimensional television (3DTV) is growing rapidly. Since 3DTV is considered as the next generation broadcasting service that can deliver real and immersive experiences by supporting user-friendly interactions, a number of advanced three-dimensional video technologies have been studied. Among them, multi-view video coding (MVC) is the key technology for various applications including free-viewpoint video (FVV), free-viewpoint television (FVT), 3DTV, immersive teleconference, and surveillance systems. In this tutorial lecture, we are going to cover the current state-of-the-art technologies for 3DTV. After defining the basic requirements for realistic broadcasting services, we will cover various multi-modal immersive media processing technologies. We also compare two different approaches for 3DTV, depth-based and multi-view camera systems, and discuss a hybrid camera system implementation combining both approaches.


Dr. Yo-Sung Ho received the B.S. and M.S. degrees in electronic engineering from Seoul National University, Seoul, Korea, in 1981 and 1983, respectively, and the Ph.D. degree in electrical and computer engineering from the University of California, Santa Barbara, in 1990. He joined ETRI (Electronics and Telecommunications Research Institute), Daejon, Korea, in 1983. From 1990 to 1993, he was with North America Philips Laboratories, Briarcliff Manor, New York, where he was involved in development of the Advanced Digital High-Definition Television (AD-HDTV) system. In 1993, he rejoined the technical staff of ETRI and was involved in development of the Korean DBS Digital Television and High-Definition Television systems. Since 1995, he has been with Gwangju Institute of Science and Technology (GIST), where he is currently Professor of Information and Communications Department. Since August 2003, he has been Director of Realistic Broadcasting Research Center at GIST in Korea. From September 2005, he has been a visiting scholar at University of Washington, Seattle, USA. He gave several tutorial lectures at various international conferences, including the IEEE Region 10 Conferences (TenCon) in 1999 and 2000, and the Pacific-Rim Conference on Multimedia (PCM) in 2006. He is presently serving as an Associate Editor of both IEEE Transactions on Circuits and Systems Video Technology (T-CSVT) and IEEE Transactions on Multimedia (T-MM). His research interests include digital image and video coding, advanced source coding techniques, three-dimensional image modeling and representation, and three-dimensional television.

Prof.Yun Qing Shi


New Jersey Institute of Technology, NJ, USA


Tutorial Title: Digital Data Forensics


In our digital age, digital media have been being massively produced, easily manipulated, and swiftly transmitted to almost anywhere in the world at anytime. While the great convenience has been appreciated, information assurance has become an urgent and critical issue faced by the digital world. The data hiding, cryptography, and combination of both have been shown not sufficient in many applications. Digital data forensics, which gathers evidence of data composition, origin, and history, is hence called for. Although this new research field is still in its infancy stage, it has started to attract increasing attention from the multimedia-security research community.

        In this tutorial, firstly, blind and passive image tampering detection is addressed. After pointing out the urgency of this task, the state-of-the-art technologies are presented. The existing problems and future research subjects are discussed. Secondly, a related area of forensics, steganalysis, is introduced and its newest status in research is presented. The relationship between image tampering detection and steganalysis is then analyzed. Finally, the issue of detection of JPEG compression history for bmp images is addressed.  It is shown that a generalized Benford law, also known as the first digit law, can play an important role in this forensics task. For example, it can be effectively used for detection of double JPEG or MPEG compression.



Dr. Yun Qing Shi has joined the Department of Electrical and Computer Engineering at the New Jersey Institute of Technology (NJIT), Newark, NJ since 1987, and is currently a professor there. He obtained his B.S. degree and M.S. degree from the Shanghai Jiao Tong University, Shanghai, China; his M.S. and Ph.D. degrees from the University of Pittsburgh, PA, USA. His research interests include motion analysis, video compression and transmission, multimedia data hiding and security (robust watermarking, fragile- and semi-fragile lossless data hiding, authentication, steganalysis, and data forensics), applications of digital image processing, computer vision and pattern recognition to industrial automation and biomedical engineering, theory of multidimensional systems and signal processing. Some of his research projects have been supported by several federal and New Jersey State funding agencies.

He is an author/coauthor of 200 papers in his research areas, a book on Image and Video Compression, three book chapters on Image Data Hiding, and one book chapter on Digital Image Processing. He holds three US patents and has 24 US patents pending (among which 20 have been licensed to another party by NJIT). He is the chairman of Signal Processing Chapter of IEEE North Jersey Section, the founding editor-in-chief of LNCS Transactions on Data Hiding and Multimedia Security (Springer), an editorial board member of Journal on Multidimensional Systems and Signal Processing (Springer), a member of IEEE Circuits and Systems Society (CASS)’s Technical Committee of Visual Signal Processing and Communications, Technical Committee of Multimedia Systems and Applications, and Technical Committee of Life Science, Systems and Applications, a member of IEEE Signal Processing Society’s Technical Committee of Multimedia Signal Processing, a fellow of IEEE.

He was an Associate Editor of IEEE Transactions on Signal Processing, IEEE Transactions on Circuits and Systems Part II, an editorial board member of International Journal of Image and Graphics (World Scientific), the guest editor of special issue on Image Data Hiding for International Journal of Image and Graphics, the guest editor of special issue on Multimedia Signal Processing for Journal of VLSI Signal Processing Systems, the guest editor of special issue on Image Sequence Processing for International Journal of Imaging Systems and Technology, a formal reviewer of the Mathematical Reviews, a contributing author in the area of Signal and Image Processing for the Comprehensive Dictionary of Electrical Engineering (CRC), an IEEE CASS Distinguished Lecturer, a co-general chair of IEEE 2002 International Workshop on Multimedia Signal Processing (MMSP02), a co-technical chair of MMSP05, a co-chair of Technical Program Committee of International Workshop on Digital Watermarking 2006 (IWDW06) and IWDW07, the chair of Technical Program Committee of IEEE International Conference on Multimedia and Expo 2007 (ICME07).


        Recently, Dr. Shi has provided four tutorials in the following IEEE conferences:ces:

a.       Y. Q. Shi, tutorial, “Lossless data hiding,” IEEE International Symposium on Circuits and Systems (ISCAS), Bangkok, Thailand, May 2003.

b.       Y. Q. Shi, tutorial, “Steganography and steganalysis,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France, May 2006.

c.       Y. Q. Shi, tutorial, “Steganography and steganalysis,” IEEE International Conference on Multimedia and Expo (ICME), Toronto, Canada, July 2006.

Y. Q. Shi, tutorial, “Digital image forensics,” IEEE International Conference on Image Processing, San Antonio, Texas, USA, September 2007.

Prof. Esteve Almirall


Coordinator of Catalan Network of Living Lab UPC, Technical University of Catalonia

Tutorial Title: Best Practices and Methodologies of European Living Labs (Tentative)



Opening the Innovation Process: Open Innovation, User Innovation and Living Labs
Knowledge today is more widespread than ever and the large increase of the space of technological solutions fostered innovation to unexpected levels. To the point that if productivity was on the spot as the key competitive factor some years ago, now is becoming a commodity while the capacity of innovation is increasingly being portray as the scare resource that could advance both companies and countries.
In this new world, where a problem has no longer a single solution but many and where technologies co-evolve with societies the role of users is increasingly important. Moreover, technology has put in the hands of users many instruments to imagine, share, build and deploy ideas and participate in the innovation process.
Innovation is clearly evolving opening to new actors while blurring the boundaries of companies. Living Labs are organizations that aim to include the contribution of users and their imagination in the innovation process. Now, the European Network of Living Labs (ENoLL) counts with 160 members willing to explore the contributions of user-driven innovation together with its managerial and policy implications.

Best Practices and Methodologies of European Living Labs
The European Network of Living Labs (ENoLL) is a bottom up grown organization coming from the European Living Labs, the E.U., national and regional governments, academia and leading companies + SMEs, providing networking and a global context to Living Lab organizations.
A Living Lab is about experimentation and co-creation with real users in real life environments, where users together with researchers, firms and public institutions look together for new solutions, new products, new services or new business models.
But also Living Labs are about societal involvement, about promoting innovation in a societal basis, involving academia, SMEs, public institutions and large companies in an Open Innovation process that because happens in real environments has an immediate impact. This is how Living Labs aim to contribute to a new Innovation System where users and citizens become active actors and not only passive receivers.

This talk will explore a collection of the Best Practices and Methodologies currently used in the ENoLL.



Esteve Almirall has an MCIS and MSc in Artificial Intelligence, together with a DEA in AI (UPC) and a DEA in Management Sciences (ESADE). Currently he is working in his Ph.Ds. in IA and in Business Sciences. Most of his career has been devoted to Information Technologies, especially in consulting, banking and finances where he worked for more than 20 years in executive and board level positions in IS, Organization and Marketing. Moreover, Esteve holds an MBA, a PDD from IESE and a Diploma in Marketing from UC Berkeley.

Esteve Almirall has also worked as a researcher in Computer Science (UPC) and in Business (IESE and Esade) while being active in consulting. Moreover he participated in a number of research projects around Innovation, Collaborative Environments, Social Networking and Recommender Systems, European Projects such as COL-LABS, Laboranova, VEP, ... and national or regional projects, being active in a number of innovation user driven initiatives such as the Catalan and European Network of Living Labs. He also published a fair number of articles in academic and non-academic journals and conferences, directed research projects and Master Thesis and is regularly appointed as speaker. Currently he serves as associated professor at UPC (Computer Science) and Esade (Business Administration- Innovation & IT Management, part time) at Master, Executive and BS levels. His interests focus on Open Innovation, Innovation Dynamics and AI tools that could foster innovation in collaborative systems.

Shin'ichi Satoh

National Institute of Informatics


Tutorial Title: Video Near-Duplicate Detection and its Application to Video Mining



Advances in broadband networks, storage devices, and digital video broadcasting have led to a growing demand for large-scale video databases and intelligent access methods.  Video semantic analysis is indispensable to enable such databases and access.  However, despite the efforts of many researchers on high-level feature extraction, such as for TRECVID tasks, video semantic analysis has insufficient performance for this purpose.


Near-duplicate shot detection has recently attracted the attention of researchers as a complement to video semantic analysis. Near-duplicate shot detection or video near-duplicate detection detects shot pairs from video archives or video streams that can be regarded as the "same" video content.  We call such shot pairs video near duplicates.  Typically, video near duplicates are obtained from the same video material, from shots of the same scene, or from shots of the same object.  Video near-duplicate detection does not require semantic analysis (e.g., it does not need to extract information identifying the object shown, what the scenery is, etc.). However, it may still be able to extract some hints that would be useful to estimate semantic relations between shots, without analyzing the semantic content of each shot.


This tutorial discusses several aspects of video near-duplicate detection, including the taxonomy of video near duplicates in video streams and video archives, examples of detection methods, and promising applications of video near-duplicate detection, especially video mining.



Professor Shin'ichi Satoh received his BE degree in Electronics Engineering in 1987, his ME and PhD degrees in Information Engineering in 1989 and 1992 at the University of Tokyo.  He joined National Center for Science Information Systems (NACSIS) in 1992.  He is a full professor at National Institute of Informatics (NII) since 2004. He was a visiting scientist at the Robotics Institute, Carnegie Mellon University, from 1995 to 1997.


His research interests include image processing, video content analysis and multimedia database.  Currently he is leading the video processing project at NII.


He has served on several international conference technical program committees.  He served as a program co-chair for Pacific-Rim Conference on Multimedia in 2004 (PCM2004), and as a program co-chair for Multimedia Modeling Conference in 2008 (MMM2008).




  • descriptiondescription
  • descriptiondescription
  • descriptiondescription
  • descriptiondescription