[UAI] CFP: Machine Learning in Computer Vision -ICML Workshop

From: Tatjana Zrimec (tatjana@cse.unsw.edu.au)
Date: Tue Feb 26 2002 - 09:23:01 PST

  • Next message: SIT'02 Organising Committee: "[UAI] SIT'02 Announcement and Call for Papers"

                                  CALL FOR PAPERS

                                        ICML Workshop

                         Machine Learning in Computer Vision

                           July 9, 2002, Sydney, Australia

               http://www.cse.unsw.edu.au/~icml2002/workshops/MLCV02ws.html
                                           

    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.

    TOPICS

    As learning in vision is a new area of research, there are many unexplored issues
    and potentially many different ways in which learning can be applied to solve
    vision problems. This workshop seeks to provide a broad forum for the
    presentation and discussion of new ideas and contemporary issues. Therefore two
    kinds of papers are invited:
            - "position papers" based on theory or experience
            - deep technical papers of interest to specialists in the area.

    Topics of interest include, but are not limited to:

            * Learning to recognize shapes
            * Supervised learning of visual models
            * Unsupervised learning for structure detection in images
            * Multistrategy and meta learning in vision
            * Learning and refining visual models
            * Multi-level learning and reuse of learned concepts
            * Learning important features for image analysis
            * Relational learning in vision
            * Context in visual learning
            * Mining from large collections of images and videos
            * Interpretation of discovered visual models
            * Image segmentation via learning
            * Probabilistic model estimation and selection
            * Applications such as medical imaging, object recognition, remote sensing,
                    digital maps, document image analysis and recognition, spatial reasoning

    WORKSHOP FORMAT

    The workshop is aimed to be a high communicative meeting place for researchers
    working on similar topics, but from different communities. In order to achieve
    these goals, the workshop will consist of short presentations and longer
    discussions. Each author will be encouraged to read another accepted paper and to
    comment on it after the original talk was given. A panel session at the end of
    the workshop will summarise what has been learned from the workshop and will
    identify future directions.

    Authors are invited to submit original research contributions or experience
    reports. Submitted papers will be reviewed by referees from the Program
    Committee. Accepted papers will be published in the working notes provided by
    ICML-2002.

    IMPORTANT DATES

      Submission deadline: 22 April 2002
      Notification to participants: 10 May 2002
      Camera-ready copies: 31 May 2002
      Workshop date: 9 July 2002

    SUBMISSION INFORMATION

    Papers should be double-spaced and no longer than 12 pages. The preferred method
    of submission is by electronic mail, in PostScript or PDF form. The format of the
    submissions should follow the ICML-2002 recommendations available at
    http://www.cse.unsw.edu.au/~icml2002/format.html. For those using LaTex, a style
    file is available. Submissions should be sent to tatjana@cse.unsw.edu.au by
    April 22, 2002. Subject: MLCV-2002 workshop submission paper.

    ORGANISERS

    PROGRAM CO-CHAIRS

            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
     
    PROGRAM COMMITTEE

            Joachim M. Buhmann, University of Bonn, Germany
            Terry Caelli, The University of Alberta, Alberta, Canada
            Igor Kononenko, University of Ljubljana, Slovenia
            Donato Malerba, University of Bari, Italy
            Ram Nevatia, University of Southern California, USA
            Svetha Venkatesh, Curtin University, Australia
        



    This archive was generated by hypermail 2b29 : Tue Feb 26 2002 - 09:23:59 PST