6th International Conference on Computer Vision Systems, Vision for Cognitive Systems

Welcome to ICVS 2008

Vision for Cognitive Systems

Keynote Speakers



Invited Talk: Prof. Dr. Heinrich H. Bülthoff, MPI for Biological Cybernetics, Tübingen

Title of the Talk
Going Beyond Vision: Multisensory Integration for Perception and Action

Understanding vision has always been at the centre of research in both cognitive and computational sciences. Experiments on vision, however, have usually been conducted with a strong focus on perception, neglecting the fact that in most natural tasks sensory signals are not ultimately used for perception, but rather for action. The effects of the action are sensed again by the sensory system, so that perception and action are complementary parts of a dynamic control system. Additionally, the human sensory system receives input from multiple senses which have to be integrated in order to solve tasks ranging from standing upright to controlling complex vehicles. In our Cybernetics research group at the Max Planck Institute in Tübingen, we use psychophysical, physiological, modeling, and simulation techniques to study how cues from different sensory modalities are integrated by the brain to perceive, act in, and interact with the real world. In psychophysical studies, we could show that humans integrate multimodal sensory information often but not always in a statistically optimal way, such that cues are weighted according to their reliability. In this talk, I will present results from our studies on multisensory integration of perception and action in both natural and simulated environments in different task contexts - from object recognition, to navigation, to vehicle control.

About the Speaker: 
Heinrich Bülthoff is scientific member of the Max Planck Society and director at the Max Planck Institute for Biological Cybernetics in Tübingen.He is head of the Psychophysics Department in which a group of about 70 biologists, computer scientists, mathematicians, physicists and psychologists work on psychophysical and computational aspects of higher level visual processes in the following areas: object and face recognition, sensory-motor integration, spatial cognition, computer graphics psychophysics, and perception and behavior in virtual environments.
Prof. Bülthoff is involved in many international collaborations on these topics and member of the European research network ECVision, Enactive and Intuition. He is partner in the following projects funded by the European Commission: COGVIS, COMIC, POEMS, PRA, TOUCH-HAPSYS, JAST, CyberWalk, BACS, ImmerSense and Wayfinding.
He holds a Ph.D. degree in the natural sciences from the Eberhard-Karls-Universität in Tübingen. From 1980 to 1988 he worked as a research scientist at the Max Planck Institute for Biological Cybernetics and the Massachusetts Institute of Technology. He was Assistant, Associate and Full Professor of Cognitive Science at Brown University in Providence from 1988-1993 before becoming director at the Max Planck Institute for Biological Cybernetics. Since 1996 he is also Honorary Professor at the Eberhard-Karls-Universität in Tübingen and since 2004 Editor in Chief of the ACM Transactions on Applied Perception. Please have a look at his website for further information.


Invited Talk: Prof. David Hogg, School of Computing University of Leeds, UK

Title of the Talk
Object Detection in Context

A variety of widely differing approaches have been used for understanding and engineering cognitive systems and vision systems in particular. At one extreme, individual competences are acquired by supervised learning proce-dures, typified by current work on object recognition. At the other, situated agents involving many competences are entirely emergent from simulations of natural evolution. Whilst the first approach has enjoyed considerable success in recent years in relation to object detection, problems arise in treating this competence in isolation, par-ticularly in dealing with errors and ambiguities and in overcoming the inherent limitations of a supervised learning regime. The talk will present a partial solution to these problems, through embedding object detection within the wider spatio-temporal context of patterns of activity.

About the Speaker: 
David Hogg has been a Full Professor at the University of Leeds since 1990, where he now heads the Computer Vision group. He was head of the School of Computing from 1996 to 1999, and a Pro-Vice-Chancellor of the University from 2000 to 2004. During 1999-2000 he was a visiting professor at the MIT Media Lab in Cambridge.
He is a member of the EPSRC College, a Fellow of ECCAI, an Associate Editor of IEEE-PAMI, has been on the programme committee for most of the leading international conferences in the field for over ten years and advises many research funding agencies worldwide on a regular basis. His current research is on behaviour recognition, with emphasis on weakly supervised learning and integration with symbolic modes of reasoning. This work has applications in several areas, including security and HCI.
Please have a look at his website for further information.