Keynote Speakers

Prof. Dr. Kevin Bowyer
University of Notre Dame

Title of the talk: "Adventures in 3D Face Recognition."

Abstract:
Face recognition using typical photograph-style images is a much-studied topic. Face recognition based on 3D shape is relatively less studied, but is often claimed to offer advantages. This talk will look at the 2D versus 3D issue, and at the rapid advances in 3D face recognition algorithms over the last five to ten years. Results of a number of large-scale experiments are reviewed, and some current research issues are suggested.

Bio:
Kevin W. Bowyer is the Schubmehl-Prein Professor and Chair of the Department of Computer Science and Engineering at the University of Notre Dame. His research efforts currently focus on biometrics and on data mining. His biometrics work includes efforts in support of the Face Recognition Grand Challenge, Face Recognition Vendor Test, and Iris Challenge Evaluation programs. His paper “A survey of approaches and challenges in 3D and multi-modal 3D+2D face recognition,” published in Computer Vision and Image Understanding, was number one on the CVIU most-downloaded list for two quarters and in the top ten for seven consecutive quarters. His paper “Face Recognition Technology: Security Versus Privacy” published in IEEE Technology and Society, was recognized with a 2005 "Award of Excellence" from the Society for Technical Communication.
Professor Bowyer is the founding General Chair of the IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS)). He is a Fellow of the IEEE, and a Golden Core Member of the IEEE Computer Society. He has served as Editor-in-Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence, and serves or has served on the editorial boards of Computer Vision and Image Understanding, Image and Vision Computing Journal, Machine Vision & Applications, International Journal of Pattern Recognition and Artificial Intelligence, Pattern Recognition, Electronic Letters in Computer Vision and Image Analysis, and the Journal of Privacy Technology.



Prof. Dr. Nadia Magnenat-Thalmann
MIRALab-University of Geneva

Title of the talk: "Communicating with a Virtual Human or a Robot that has Emotions, Memory and Personality"

Abstract:
Multimodal dialogue management capabilities involve and combine input and output from various interaction modalities and technologies, such as speech recognition and synthesis, natural language interpretation and generation, recognition/response of/to human actions, gestures and emotions, and facial expressions. In our talk, we will speak of our research linked to two European Research Projects, the project INTERMEDIA and the project INDIGO. In the European project INTERMEDIA, we are working on the simulation of a virtual human who can talk to us in order to guide us to any place we would like to go. By the means of see-through glasses, the virtual guide will show us the way of how to go to some specific place. The virtual guide will have gestures and will speak.The Virtual guide is able to recognize us and keep memory of our preferences and actions. In our presentation, we will also present some work we have done in the context of the project INDIGO to communicate with a very realistic skin-based face robot. In this project, we are defining memory models, recognition of emotions, and dialogue interaction based on recognition of emotions of the user. In short, when meeting Eva (the name of our Face Robot), she will recognize us, ask some specific questions concerning our habits and will understand our answers and behave accordingly.

Bio:
Prof. Nadia Magnenat-Thalmann has pioneered research into virtual humans over the last 25 years. She obtained several Bachelor's and Master's degrees in various disciplines (Psychology, Biology and Chemistry) and a PhD in Quantum Physics from the University of Geneva. From 1977 to 1989, she was a Professor at the University of Montreal where she founded the research lab MIRALab.
She was elected Woman of the Year by the Grand Montreal Association for her pionnering work on virtual humans and her work was presented at the Modern Art Museum of New York in 1988 . She moved to the University of Geneva in 1989, where she founded the Swiss MIRALab, an internationally interdisciplinary lab composed of about 25 researchers.
She is author and coauthor of more than 200 research papers and a dozen of books in the field of modeling virtual humans, interacting with them and living in augmented life. She has received several scientific and artistic awards for her work, mainly on the Virtual Marylin and the film RENDEZ-VOUS A MONTREAL, but more recently, in 1997, she has been elected to the Swiss Academy of Technical Sciences, and has been nominated as a Swiss personality who has contributed to the advance of science in the 150 years history CD-ROM produced by the Swiss Confederation Parliament.
She has directed and produced several films and real-time mixed reality shows, among the latest are DREAMS OF A MANNEQUIN (2003) , THE AUGMENTED LIFE IN POMPEII (2004) and FASHION IN EQUATIONS (2005). She is editor-in-chief of the Visual Computer Journal published by Springer Verlag and co-Editor-in-chief of Computer Animation and Virtual Worlds published by John Wiley. She has also participated to political events such as the WORLD ECONOMIC FORUM in DAVOS where she was invited to give several talks and seminars.




Prof. Roddy Cowie
Queen's University, Belfast, Northern Ireland

Title of the talk: "Building the databases needed to understand rich, spontaneous human behaviour"

Abstract:
 One of the motives for studying faces and gestures is the role that they play in spontaneous, socially rich interaction between humans. If computers are to interact with humans in that mode (or to analyse what they are doing in it), methods of interpreting the non-verbal signals that they use are critical. It is becoming clear that developing those methods requires databases whose complexity is of a very different order from those that are standard elsewhere. Samples cannot be generated to order, because acting does not reproduce the way features are distributed in spontaneous action. Data collections need to be very large, because there are extensive situational, individual, and cultural differences. It is a very large task to provide annotations that adequately capture the meaning of facial expressions or gestures. These problems are not insoluble, but sustained and well-directed efforts are needed to solve them.

Bio:

Roddy Cowie is Professor of Psychology at Queen’s, Belfast, where he works on human perception and experience. He brings a broad background to the area. He studied philosophy and psychology as an undergraduate, and explored relationships between human and machine vision for his PhD. His publications have addressed visual phenomena that highlight contrasts between people's subjective experience and 'rational' expectations (e.g. ‘impossible objects’ and picture perception); and deafness (with Ellen Douglas-Cowie), considering particularly lipreading, the subjective experience of deafness, the way deafness affects speech, and computational methods of analyzing the speech problems. Since the 1990s, he has focused on the perception of emotion, and he has participated in a series of EC projects on emotion (PHYSTA, ORESTEIA, ERMIS, HUMAINE, and SEMAINE). He co-ordinated the HUMAINE network of excellence, and is president of its successor, the HUMAINE Association.

 

His current work centres on the perception of emotion as it happens in everyday action & interaction. Hence, he is interested in acquiring data that show people in emotionally coloured activities (chatting, persuading, driving); in capturing the nature of the impressions people form when they see and hear emotionally coloured behaviour; in processes that could derive such impressions from data; and in the issues of ethics and language that surround these.