WORKSHOP ON LEARNING IN COMPUTER VISION 
 
                 in conjunction with ECCV '98
                        June 6, 1998
                     Freiburg, Germany
 
 
Description
-----------
 
In recent years rising computer performance has made it 
possible to exploit complex statistical models and to learn 
and estimate their parameters from an increasing amount of data. 
Therefore the issues of computational and statistical learning 
theory and Bayesian inference become more and more relevant for 
computer vision applications. Especially the related topics of 
generalization and choice of model complexity are of central 
importance in computer vision. Furthermore, the question of 
needed accuracy for optimization and parameter estimation 
turns out to be a closely related topic.
 
The application of methods from statistical learning theory and 
neurally inspired approaches in computer vision are rather diverse 
and learning in computer vision is by no means a homogeneous field. 
But the necessity becomes more and more evident to take a more 
fundamental point of view and to clarify the multiple implications 
that the recent achievements of statistical learning theory have on 
computer vision problems. Statistical learning theory might have 
significant influence on many applications ranging from classification 
and statistical object recognition, grouping and segmentation to 
statistical field models and optimization. We are convinced that 
focussing on these joint aspects may yield a major contribution 
to the understanding and improvement of the diverse range of 
learning applications in computer vision. A workshop on learning 
in computer vision may greatly contribute to these goals.
 
Workshop Issues
---------------
 
The workshop will focus on the latest developments of learning 
in computer vision and will try to clarify to what extent statistical 
learning theory and Bayesian inference support computer vision 
applications. The workshop will present high quality oral 
contributions on any aspects of learning in computer vision, 
including but not restricted to the following topics:
 
* Supervised Learning and its application to classification, 
  support vector networks and model learning
* Unsupervised Learning for structure detection in images
* Robustness of Computer Vision algorithms and generalization
* Probabilistic model estimation and selection, 
  e.g. Bayesian inference for vision
 
Attendance and Workshop Format
------------------------------
 
The workshop will consist of invited keynote talks and regular 
talks in one track. For submissions please send an extended 
abstract of 1-2 pages by March 31, 1998 to
 
  Workshop Learning in Computer Vision 
  c/o Prof. Joachim Buhmann 
  Institut fuer Informatik 
  Roemerstrasse 164  
  D-53117 Bonn 
  Germany 
 
In case of more submissions than available time slots a selection 
will be made based on a peer review of the submissions by the 
program committee.
 
Venue
-----
 
The workshop will be held in Freiburg, Germany on June 6, 1998 
in conjunction with the European Conference on 
Computer Vision (ECCV '98). 
 
Program Committee
-----------------
 
* Joachim M. Buhmann, Chair (University of Bonn, Germany)
* Andrew Blake (University of Oxford, UK)
* Jitendra Malik (UC Berkeley, USA)
* Tomaso Poggio (MIT, USA)
* Daphna Weinshall (Hebrew University, Israel)
 
Local Organization: Andreas Polzer, Jan Puzicha (University of Bonn)
 
To obtain further information please contact:
 
   WWW:    http://www-dbv.cs.uni-bonn.de/learning.html
   e-mail: jan@cs.uni-bonn.de