Call for participation
                IEEE Computer Society Workshop on  
 
                   INTERPRETATION OF VISUAL MOTION
 
               University of California, Santa Barbara
                            June 22, 1998
              just prior to and in conjunction with CVPR
 
             FINAL EXTENDED PAPER DEADLINE:  Feb 27, 1998
 
 
PROGRAM CHAIR:
Aaron Bobick, MIT Media Lab
 
PROGRAM COMMITTEE:
Michael Black, Xerox PARC 
JanOlof Eklundh, KTH, Stockholm 
Irfan Essa, Georgia Tech 
Randall Nelson, U. Rochester 
Tom Olson, Texas Instruments 
 
 
As computer vision moves from the processing of static images to the
consideration of video sequences, the problem of understanding action
is becoming fundamental. Current important applications include
security and surveillance, dynamic situation monitoring
(e.g. refueling a fleet), action verification (e.g. insuring all steps
in an assembly occur), and accessing video databases. With the
explosion of multi-media content being distributed throughout the
world, many new applications are certain to arise in the near future.
 
To date, unfortunately, most image representations and certainly
almost all visual representations of objects have been designed for
static situations.  While we have numerous methods for representing a
particular object (e.g. a given industrial part) we have few visual
representations for "throwing a baseball," "walking around a room," or
"refueling a fleet." Current research on recovering the kinematics of
a human body from static frames presupposes that a sequence of static
poses or "key frames" will be the basis or a prerequisite for
representation of action. But such suppositions are made without much
consideration of the necessary competencies a representation of action
must have.  
 
The goal if this workshop is to have a technical meeting presenting
in visual imagery.  The workshop will consist of one day of technical
presentations, with approximately 4 invited presentations, 16-20
orally presented papers (approximately 25 minutes), and, if interest
and quality warrant, a 1 hour poster session for another 10-15 papers.
 
Topics include but are not limited to: 
 * Representation of time for action understanding 
 * Detecting activities involving multiple interacting agents 
 * Segmentation of video into space-time regions for additional processing 
 * Use of context in understanding action 
 * Qualitative or logical representation of motion 
 * Behavior recognition 
 * Gait detection and identification 
 * Applciations such as sports or surveillance with novel solutions
 
PAPER SUBMISSION:  Four copies of complete manuscript should be received by
Feb 27, 1998  at the following address:
        Aaron Bobick, Program Chair
        MIT Media Lab 
        20 Ames St. 
        Cambrdige, MA 02139
 
Papers  should  include
* A title page containing the names and addresses of the authors
  (including e-mail), an abstract of up to 200 words, and one or more
  categories as listed above or other keywords, 
 
* Paper - limited to 8 double column pages (CVPR Latex or Word style)
  including figures, references, etc. 
 
 
For more information please contact the program chair:
        Aaron Bobick
        MIT Media Laboratory, E15-383
        20 Ames Street
        Cambridge, MA  02139
        Tel:617-253-8307 
        Fax:617-253-8874
        Internet: bobick@media.mit.edu
        WWW: http://www.media.mit.edu/~bobick