Keynotes
More information will be posted here as it becomes available.
Cars that Drive Themselves
Tuesday Morning, June 24
Sebastian Thrun
This talk will introduce the audience of the ICME into the fascinating world of robotics cars. Most of us use cars in our daily lives; yet cars are inefficient, unsafe, and environmentally wasteful. Robotic technology promises to overcome some of these shortcomings, by making cars safer; drivers more productive; and also by reducing the burden to the environment by enabling new models of car sharing. Thrun will present Stanford's research on the basic artificial intelligence behind this new emerging technology. In particular, he will report from two recent autonomous car competitions, organized by DARPA, and dubbed "Grand Challenge" and "Urban Challenge." Machine perception, computer vision, machine learning, and probabilistic computation all play major roles in the design of these systems. Thrun will shed light onto the inner workings of these robots, and discuss the impact of self-driving cars on society once the technology is sufficiently matured.
Sebastian Thrun is a Professor of Computer Science and Electrical Engineering at Stanford University, where he directs the Stanford Artificial Intelligence Laboratory. Thrun's research focuses on Artificial Intelligence and Robotics. Thrun is probably best known for his victory in the DARPA Grand Challenge, and his second place finish in the DARPA Urban Challenge - both robotic competition organized by the US Government to foster the field of autonomous robotics. Thrun has published 11 books, over 300 technical papers, and has won numerous awards, including most recently the Science Prize of the City of Braunschweig, Germany. Thrun is an elected member of the National Academy of Engineering (USA) and of the Leopoldina in Germany.
Learning-Based Methods for Multimedia
Wednesday Morning, June 25
Tsuhan Chen
Traditionally, multimedia content retrieval has been mostly based on low-level processing techniques. In the past decade, however, it has grown to become an area where a variety of learning-based tools are used to solve high-level semantic problems. These tools conventionally were studied exclusively in the machine learning community. In this talk, we will use one application to illustrate this trend in multimedia content retrieval: object discovery, i.e., extracting the "object of interest" from a set of images or videos in a completely unsupervised manner. Based on feature extraction and statistical modeling, our approach to object discovery applies to both still images and motion video. For video, the spatial-temporal framework incorporates both appearance modeling and motion modeling, so that motion ambiguities can be resolved by appearance, and appearance ambiguities can be resolved by motion. In addition, based on machine learning methods, we will show how to extract hierarchical relationships among objects from image/video data without any manual labeling.
Tsuhan Chen has been with the Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, Pennsylvania, since October 1997, where he is currently Professor and Associate Department Head. From August 1993 to October 1997, he worked at AT&T Bell Laboratories, Holmdel, New Jersey. He received the M.S. and Ph.D. degrees in electrical engineering from the California Institute of Technology, Pasadena, California, in 1990 and 1993, respectively. He received the B.S. degree in electrical engineering from the National Taiwan University in 1987.
Tsuhan served as the Editor-in-Chief for IEEE Transactions on Multimedia in 2002-2004. He also served in the Editorial Board of IEEE Signal Processing Magazine and as Associate Editor for IEEE Trans. on Circuits and Systems for Video Technology, IEEE Trans. on Image Processing, IEEE Trans. on Signal Processing, and IEEE Trans. on Multimedia. He co-edited a book titled Multimedia Systems, Standards, and Networks.
Tsuhan received the Charles Wilts Prize at the California Institute of Technology in 1993. He was a recipient of the National Science Foundation CAREER Award, from 2000 to 2003. He received the Benjamin Richard Teare Teaching Award at the Carnegie Mellon University in 2006. He is elected to the Board of Governors, IEEE Signal Processing Society, 2007-2009. He is a member of the Phi Tau Phi Scholastic Honor Society. He is Fellow of IEEE, and a Distinguished Lecturer of the Signal Processing Society.
Social-Mobile Networks
Thursday Morning, June 26
Frank H.P. Fitzek
Social networking is one of the hot topics in the Internet community. People are subscribed to Facebook, myspace and others to communicate or to get in contact with other people. Being connected to those platforms using mobile phones is already possible now. But this talk should highlight social-mobile networks, which are social networks with a much shorter life span created for that special moment, whereas the known social networks are focused on long term relationship.
Social-mobile networks are formed to get a quick understanding of the environment and the people in my proximity. To create that kind of knowledge mobile devices will use the short range technologies such as WLAN or Bluetooth instead of cellular technologies. The later one may be used to establish a long term relationship later on, but the short range technology is the key to create contextual information about my proximity. Social-mobile networks will come along with new business models and service ideas, both introduced in the talk.
Frank H. P. Fitzek is an Associate Professor in the Department of Communication Technology, University of Aalborg, Denmark heading the Future Vision and Mobile Device group. He received his diploma (Dipl.-Ing.) degree in electrical engineering from the University of Technology - Rheinisch-Westfälische Technische Hochschule (RWTH) - Aachen, Germany, in 1997 and his Ph.D. (Dr.-Ing.) in Electrical Engineering from the Technical University Berlin, Germany in 2002 for quality of service support in wireless CDMA networks. As a visiting student at the Arizona State University he conducted research in the field of video services over wireless networks. He co-founded the start-up company acticom GmbH in Berlin in 1999. In 2002 he was Adjunct Professor at the University of Ferrara, Italy giving lectures on wireless communications and conducting research on multi-hop networks. In 2005 he won the YRP award for the work on MIMO MDC and received the Young Elite Researcher Award of Denmark. Due to his outstanding skills and devotion he was selected to receive the Nokia Champion award in 2007 and 2008. His current research interests are in the areas of wireless and mobile communication networks, mobile phone programming, cross layer as well as energy efficient protocol design and cooperative networking.