index - VISINACT - Vision in Action : Efficient strategies for cognitive agents in complex environments Access content directly


As a continuation of the ECCV workshop series on Cognitive Vision (2nd Cognitive Vision Workshop), this workshop aims to bring together researchers from various programs and projects working on novel approaches for cognition in technical systems. The second objective of the workshop is to discuss ways of how to integrate biological and psychological findings from human and insect perception and action generation, their exploration and representation strategies. Recent results in combining biological insights into development of perception and action algorithms promise a large impact on research in several fields. Future algorithms need to work in complex environments with limited processing and sensing capabilities that require intensive studies, more specifically related to:
  • Attention control
  • Collaborative sensing with simple agents
  • Novel sensor systems
  • Multi-modal fusion of sensory perception
  • Modeling and learning of perception and action for development of innate behaviors, and
  • Memory and representations - coupling between visual perception, tasks, knowledge and the visual system.

Call for papers:

The field of computer vision has developed significantly over the past decades and its importance in fields of development of cognitive systems in the areas of robotics and artificial intelligence is growing. The first goal of this workshop is to initiate a close dialog between the communities and allow for long term planning of synergistic effects from the integrated research. The second goal is to model the entire perception-action loop, since in robotics, vision cannot be considered an isolated component and vision research should include consideration of the control of the system.

We invite papers in relation to one or more of the following topics:

  • Attention control - the complexity of the scene requires additional image processing for a light process decision about areas of interest in the sensor data.
  • Collaborative sensing with simple agents - small, lightweight systems do not allow an implementation of large and complex sensing systems. Collaboration between simple systems is a promising way to tackle this problem.
  • Multi-modal fusion of sensory perception - we aim to invite researchers working on fusion of different sensor data representations including physical sensing, resolution, and accuracy.
  • Modeling and learning of perception and action for development of innate behaviors - an example of the emerging research in this area are the established vision-based control approaches in the robotics.
  • Memory and representations - coupling between visual perception, tasks, knowledge and the visual system requires memory and suitable data representations.

Important Dates:

  • Full paper submission: July 20, 2008 Submission only via email to:
  • Format: Maximum 6 pages, ECCV format (
  • Notification of acceptance: August 20, 2008 Papers will be part of centralized workshop proceedings
  • Final manuscript due: August 30, 2008 Strict deadline!

After Workshop Special Issue:

Due to good experiences of previous workshops, we also plan a special issue at a journal and will invite the best papers of the workshops to submit revised versions of their manuscript.

Planned format:

We plan to implement a combination of invited lectures, open submissions, group discussions about recent results in the above cognitive vision fields and a panel discussion to summarize the workshop results.
We plan to use presentations from invited speakers in the field of visual perception, perception in biology and psychology to introduce to different communities the alternative ways of sensor data processing and interpretation that allows for definition of future collaboration between the fields.


Markus Vincze. TU Wien
Danica Kragic, KTH Stockholm danik@nada.kth.se
Darius Burschka, TU Munichburschka@cs.tum.edu
Antonis Argyrosargyros@ics.forth.gr