BMVA
British Machine Vision Association and Society for Pattern Recognition
Call for Participation
Visual Recognition
www.bmva.ac.uk/meetings
One Day BMVA symposium in London, UK March 1st, 2006
Chairs: Jiri (George) Matas (Czech Technical University Prague &
University of Surrey) and Krystian Mikolajczyk (TU Darmstadt & University
of Surrey)
Visual recognition is a fundamental problem in computer vision. Recently,
noticeable progress has been achieved in some rather restricted areas, e.g.
in robust recognition of rigid, locally planar objects with distinctively
textured surfaces. However, most visual recognition problems appear to be
much more challenging and significant progress is yet to be made. Such
problems include object class recognition (categorisation) recognition of
non-compact or wire-like objects, recognition of natural objects like
trees, non-rigid object recognition and other. Consequently, some visual
recognition methods are reaching a mature state where industrial
application is possible and focus shifts to efficiency and robustness and
yet other areas are in stage of problem formulation and first ad hoc
attempts.
We solicit contributions covering work related to any aspect of visual
recognition.
Presentations will cover, but are not limited to, the following topics:
Object Recognition
Categorisation (object class recognition)
Object recognition in video sequences, interplay between recognition and
tracking
Texture recognition
Shape-based recognition
Indexing techniques for large scale visual recognition
Object-level image retrieval
Methods for establishing correspondences
Learning for visual recognition
Perceptual grouping and segmentation for object recognition
Natural image statistics for visual recognition
Covariant region detectors (interest points, distinguished regions)
Non-rigid matching
Multi-view matching techniques
Multi-view object representation
Appearance-based recognition techniques
Performance evaluation of visual recognition methods
Applications of object recognition techniques
Please submit an extended summary of about one A4-sized page (no longer
than two pages) in length (PDF preferred). Send contributions by email
attachment (1Mb max please!) to J. Matas (<[log in to unmask]>) by 6th
Jan 2006.
|