ICML Workshop on

                    Machine Learning in Computer Vision

                               July 9, 2002
                            Sydney,  Australia
  In conjunction with ICML-2002The Nineteenth International Conference on
                             Machine Learning
                               (text format)

  ------------------------------------------------------------------------

Workshop description

Learning is one of the current frontiers for computer vision research and
has been receiving increased attention in recent years. Machine learning
technology has strong potential to contribute to:
        - the development of flexible and robust vision algorithms that
will improve the performance of practical vision systems with a higher
level of  competence and greater generality, and
        - the development of architectures that will speed up system
development time and provide better performance.

The goal of improving the performance of computer vision systems has
brought new challenges to the field of machine learning, for example,
learning from structured descriptions, partial information, incremental
learning, focusing attention or learning regions of interests (ROI),
learning with many classes. Solving problems in visual domains will result
in the development of new, more robust machine learning algorithms that
will be able to work in more realistic settings.

>From the standpoint of computer vision systems, machine learning can offer
effective methods for automating the acquisition of visual models, adapting
task parameters and representation, transforming signals to symbols,
building trainable image processing systems, focusing attention on target
object and learning when to apply what algorithm in a vision system.

>From the standpoint of machine learning systems, computer vision can
provide interesting and challenging problems for example: learning models
rather than hand-crafting them, learning to transfer experience gained in
one application domain to another domain, learning from large sets of
images with no annotation, designing evaluation criteria for the quality of
learning processes in computer vision systems.


Workshop schedule


                Time             Activity            Speaker

          9:15 - 9:30am      Welcome and       -
                             registration
                             Paper 1:
                             Recent Progress
                             on RAIL:
                             Automating
                             Clustering and    A. Chen
                             Comparison of     School of Computer
          9:30 - 10:00am     Multiple          Science and
                             Classification    Engineering,
                             Techniques on     University of New
                             High Resolution   South Wales
                             Remotely Sensed
                             Imagery [pdf]

                             Paper 2:
                             Boosted Image
          10:00 - 10:30am    Classification:   N. R. Howe
                             An Empirical
                             Study [pdf]       Smith College

          10:30 - 11:00am    Coffee break      -

                             Paper 3:
                             Signal            B. Lerner
                             Discrimination in Department of
          11:00 - 11:30am    Fluorescence In   Electrical and
                             Situ              Computer
                             Hybridization     Engineering,
                             Images [pdf]      Ben-Gurion
                                               University
                             Paper 4:
                             Combining Wrapper
                             and Filter
                             Approaches for
          11:30 - 12:00pm    Learning Concepts N. Bredeche
                             from Images       LIMSI-University
                             provided by a
                             Mobile Robot
                             [pdf]

          12:00 - 2:00pm     Lunch break       -
                             Paper 5:
                             Automatic Feature
                             Construction and
                             a Simple Rule     G.Gornez
          2:00 - 2:30pm      Induction         ITESM - Campus
                             Algorithm for     Cuernavaca
                             Skin Detection
                             [pdf]

                             Paper 6:
                             A Statistical     Matjaz Bevk
                             Approach To       Faculty of
                             Texture           Computer and
          2:30 - 3:00pm      Description of    Information
                             Medical Images: A Science,
                             Preliminary Study University of
                             [pdf]             Ljubljana


          3:00 - 3:30pm      Paper 7:          -
                             [pdf]
          3:30 - 4:00pm      Coffee break      -
          4:00 - 5:00pm      Panel discussion  -

Organisation

Program co-chair

    Arcot Sowmya
    University of New South Wales
    NSW 2052, AUSTRALIA
    E-mail  sowmya@cse.unsw.edu.au

    Tatjana Zrimec
    University of New South Wales
    NSW 2052, AUSTRALIA
    E-mail   tatjana@cse.unsw.edu.au


Additional information

For additional information, see the web site for the conference:

       http://www.cse.unsw.edu.au/~icml2002