ECCV 2010 Workshop on
'Vision for Cognitive Tasks'


Friday September 10, 2010
home
Call for papers
Planed format
Program
Invited speakers
Organizers
Committee
Contact

Markus Vincze
Technische Universitšt Wien
vincze[-at-]acin.tuwien.ac.at

Danica Kragic
KTH - Royal Institute of Technology.
danik[-at-]nada.kth.se

Ales Leonardis
University of Ljublana
ales.leonardis[-at-]fri.uni-lj.si

 

Objectives:

We are on the verge of a new era when technical systems expand from typical industrial applications with pre-programmed, hard-wired behaviors into everyday life situations where they have to deal with complex and unpredictable events. Many practical applications such as mobility, manipulation and interaction require a large number of vision-based cognitive tasks such as human tracking, activity interpretation, object tracking, recognition and classification. In the relation to robotic and cognitive systems, vision however faces a number of new challenges going beyond present-day approaches benchmarked on databases.

Hence, the main objective of the workshop is to initiate a close dialog between the communities and allow for long term planning of synergistic effects from the integrated research. It will be beneficial for participants to learn about the potential of vision techniques in the wide area of possible applications in these fields. In addition, in many cases, methods available in the computer vision community are not fully exploited in the robotics and cognitive systems communities.

The target audience are computer vision researchers willing to have a look into the challenges of application areas such as robotics and cognitive systems as well as researchers from these fields interested to become acquainted with state of the art vision methods. While researchers in computer vision mainly work on image and video databases, robot researchers predominantly work with single-coloured objects. It would be great to start bridging this rather large gap by bringing these communities closely together at the level of present day experience. Knowing about tasks makes it possible to obtain more robust perception while state of the art vision methods will push systems to new applications.