Brief Bio:
Peter Robinson is Reader in Computer Technology and Deputy Head of Department at the University of Cambridge Computer Laboratory in England, where he leads the Rainbow Group working on computer graphics, interaction and electronic CAD. He is also a Fellow, Praelector and Director of Studies in Computer Science at Gonville & Caius College where he previously studied for a first degree in Mathematics and a PhD in Computer Science under Neil Wiseman.

Dr Robinson's research interests are in the general area of applied computer science. The main focus for this is human-computer interaction, where he has been leading work for some years on the use of video and paper as part of the user interface. He also works on electronic design automation and, in particular, on support for self-timed circuits.

He lectures in the Computer Science Tripos and Diploma in Computer Science on Discrete Mathematics and VLSI Design, with occasional lectures on Electronic CAD, Computer Graphics and Java.

He is a Chartered Engineer and a Fellow of the British Computer Society.


Abstract:
The increasing power and falling cost of computers, combined with improvements in digital projectors and cameras, are making the use of video interaction in human-computer interfaces more popular. This talk will present two recent video interface projects at the University of Cambridge.

People manage large amounts of information on a physical desk, using the space to arrange different documents to facilitate their work. The 'desk top' on a computer screen only offers a poor approximation. The Escritoire is a desk-based interface for a personal workstation that uses two overlapping projectors to create a foveal display: a large display surface with a central, high resolution region to allow detailed work. Multiple pen input devices are calibrated to the display to allow input with both hands. A server holds the documents and programs while multiple clients connect to collaborate on them. [Work by Mark Ashdown]

Facial displays are an important channel for the expression of emotions, and are often thought of as projections of a person's mental state. Computer systems generally ignore this information. Mind-reading interfaces infer users' mental states from facial expressions, giving them a degree of emotional intelligence. Video processing is used to track two dozen features on the user's face. These are then interpreted as basic action units, which are interpreted using statistical techniques as one of six basic emotions or 18 more complex cognitive emotions. [Work by Rana el Kaliouby]

Brief Bio:
Ken Perlin is a professor in the Media Research Laboratory, within the Department of Computer Science at New York University. He directed the NYU Center for Advanced Technology from 1994-2004. His research interests include graphics, animation, and multimedia. In January 2004 he was the featured artist at the Whitney Museum of American Art. In 2002 he received the NYC Mayor's award for excellence in Science and Technology and the Sokol award for outstanding Science faculty at NYU. In 1997 he won an Academy Award for Technical Achievement from the Academy of Motion Picture Arts and Sciences for his noise and turbulence procedural texturing techniques, which are widely used in feature films and television. In 1991 he received a Presidential Young Investigator Award from the National Science Foundation.

Dr. Perlin received his Ph.D. in Computer Science from New York University in 1986, and a B.A. in theoretical mathematics from Harvard University in 1979. He was Head of Software Development at R/GREENBERG Associates in New York, NY from 1984 through 1987. Prior to that, from 1979 to 1984, he was the System Architect for computer generated animation at Mathematical Applications Group, Inc., Elmsford, NY, where the first feature film he worked on was TRON. He has served on the Board of Directors of the New York chapter of ACM/SIGGRAPH, and currently serves on the Board of Directors of the New York Software Industry Association.


Abstract:
Thanks to Moore's Law and GPU technology, real time graphics is advancing by leaps and bounds. Much of this advance is being driven by games. But perhaps interactive graphics can move beyond game play. Perhaps an interactive character can make you cry, or otherwise move you deeply, in the way you can be moved by characters in a novel or film. This could effect a revolution in how society perceives and uses interactive graphics. In this talk I will show some of the steps along the way to this revolution.

Brief Bio:
Dr Andre Gagalowicz is a research director at INRIA, FRANCE. He was the creator of the first laboratory involved in image analysis/synthesis collaboration techniques in 1984. He graduated from Ecole Superieure d'Electricite in 1971 (engineer in Electrical Engineering), obtained his PHD in Automatic Control from the University of Paris XI, Orsay, in 1973, and his state doctorate in Mathematics (doctorat d'Etat es Sciences) from the University of Paris VI (1983). He is fluent in english, german, russian and polish and got a bachelor degree in chinese from the University of Paris IX, INALOCO in 1983. His research interests are in 3D approaches for computer vision, computer graphics, and their cooperation and also in digital image processing and pattern recognition. He received the prizes of the best scientific communication and the best technical slide at the Eurographics'85 conference. He was awarded the second prize of the Seymour Cray competition in 1991 and one of his papers was selected by Computers and Graphics journal as one of the three best publications of this journal over the last ten years. He took part to the redaction of eight books and wrote around two hundreds publications. He was the founder and the last chairman of the MIRAGES international conference. The last version of the MIRAGES conference took place at INRIA, FRANCE between the 3rd and 5th of March 2005. This conference is exclusively dedicated to computer vision/computer graphics collaboration techniques.


Abstract:
I will first explain what is 3D rotoscopy and its role in post-production applications. Then I will present the computer vision/computer graphics strategy used to perform this task. I will first briefly present the case of rigid objects where the strategy appears clearly. I will then proceed to the case of articulated objects and especially to the case of a full human body tracking (when garments are rather tight). I will present some results related to the tracking of professional golfers. Finally, I will give some results of face tracking which is a case of deformable objects. I will conclude with a presentation of other possible applications of the research done at the MIRAGES laboratory at INRIA Rocquencourt.