From Computational Cognitive Neuroscience to Computer Vision - CCNCV 2007

Description of the workshop

This workshop aims to foster the transfer of knowledge from the area of Computational Cognitive Neuroscience to Computer Vision. The seemingly simplicity of visual perception has periodically attracted machine vision scientists to build biologically inspired algorithms. Although such biologically motivated algorithms have not revolutionized Computer Vision, we believe that several reasons exist that motivate an ongoing exchange. In the recent years there has been much progress in the understanding of brain processes such as visual attention, object recognition, learning of complex feature detectors, decision making and high level cognitive control, to name a few. This work is yet often not suitable for real world applications, but it might lead to new developments, and in the long run, to better algorithms in machine vision.

General topics

We invite contributions from the area of Computational Cognitive Neuroscience that relate to Computer Vision. The contribution should emphasize those properties of neural models that potentially lead to applications in Computer Vision. We do not expect that these applications already exist.

Tentative Schedule

Workshop Session I

Wednesday, 21st March, 10:55-12:30

• 10:55 Welcome and announcements
• 11:00 Introduction
  F. Hamker. Psychologisches Institut II, Westfälische Wilhelms-Universität Münster, Germany
• 11:30 Invited Presentation: On Attention, Saliency, Recognition and Feature Binding
  J. Tsotsos. Dept. of Computer Science & Engineering and Centre for Vision Research, York University, Canada
• 12:30 Lunch

Workshop Session II

Wednesday, 21st March, 13:30-16:00

• 13:30 A top-down attentional system scanning multiple targets with saccades
  J. Fix, N. Rougier, and F. Alexandre. Loria laboratory, France
• 13:55 Attention based on Information Maximization
  N. Bruce, and J. Tsotsos. Dept. of Computer Science & Engineering and Centre for Vision Research, York University, Canada
• 14:20 Spatial attention and its impact on receptive fields: a neurocomputational account
  M. Zirnzak, and F. Hamker. Psychologisches Institut II, Westfälische Wilhelms-Universität Münster, Germany
• 14:45 Fast learning to recognize objects: dynamic fields in label- feature space
  C. Faubel, and G. Schöner. Institut für Neuroinformatik, Ruhr-Universität Bochum, Germany
• 15:10 Natural scene statistics for chromatic and luminance edges
  T. Hansen, and K. Gegenfurtner. Dept. of Psychology, Justus-Liebig-University Gießen, Germany
• 15:35 Neural mechanisms of motion integration and disambiguation: from neuroscience to real-world applications
  C. Beck, P. Bayerl, and H. Neumann. Institute of Neural Information Processing, University of Ulm, Germany
• 16:00 Coffee break

Workshop Session III

Wednesday, 21st March, 16:30-18:45

• 16:30 Poster session
• 17:00 Cortical architectures for early joint coding of 3D dynamic visual parameters: complex feature mapping and distributed representations
  S. Sabatini, M. Chessa, G. Castaldi, F. Solari, and G. Bisio. Dept. of Biophysical and Electronic Engineering, University of Genoa, Italy
• 17:25 Unspecific dopaminergic modulation of learning and working memory in perirhinal cortex
  J. Vitay, and F. Hamker. Psychologisches Institut II, Westfälische Wilhelms-Universität Münster, Germany
• 17:50 The Independent Components of Natural Images are Perceptually Dependent
  Matthias Bethge. MPI for Biological Cybernetics, Tuebingen, Germany
• 18:15 Final discussion
• 18:45 End

Posters

• A neurally inspired model of gaze perception.

  U. Weidenbacher, P. Bayerl, and H. Neumann. Institute of Neural Information Processing, University of Ulm, Germany.

• How does binocular disparity information influence overt attention?

  L. Jansen, S. Onat, and P. König. Institute of Cognitive Science, University Osnabrück, Germany.

• Robust edge detection by a push-pull simple cell model with dominating opponent inhibition.

  T. Hansen, and H. Neumann. Dept. of Psychology, Justus-Liebig- University Gießen, Germany and Institute of Neural Information Processing, University of Ulm, Germany.

• Category systems for the local 2nd order image structure in natural images.

  M. Lillholm, and L. Griffin. University College London, United Kingdom.

• Laser range scans of natural scenes for the evaluation of stereo- matching algorithms.

  J. Steger, R. Märtin, K. Lingemann, A. Nüchter, J. Hertzberg, and P. König. Neurobiopsychology, Institute of Cognitive Science, University Osnabrück, Germany and Knowledge-based Systems, Institute of Computer Science, University Osnabrück, Germany.

• Hebbian Learning of feedforward and feedback connections in dynamic rate coded neurons - A biological motivated model

  J. Wilschut, M. Zirnzak, and F. Hamker. Psychologisches Institut II, Westfälische Wilhelms-Universität Münster, Germany.

Submissions (format, styles, etc.)

Abstracts of max 1 page (preferably PDF) should be submitted to fhamker@uni-muenster.de. The work should be novel but it can be already published. The primary criterion of acceptance is the relevance for the workshop.

Important Dates

Submission of abstracts:		15th January 2007
Notification of acceptance:		2nd February 2007
Camera ready paper:		tbd.
Workshop on CCNCV:		Is planned to take place on Wednesday, March, 21st (a detailed schedule will be available here soon).

Workshop organizers, contact and e-mail for paper submission

Fred Hamker
Psychological Institute II
Otto Creutzfeldt Center for Cognitive and Behavioral Neuroscience
Westf. Wilhelms-Universität Münster
E-mail:fhamker@uni-muenster.de
Web: http://wwwpsy.uni-muenster.de/Psychologie.inst2/AELappe/personen/hamker.html

Julien Vitay
Psychological Institute II
Westf. Wilhelms-Universität Münster
Web: http://julien.vitay.free.fr/