****************   SECOND (FINAL) NOTICE *************************

                   Call for Participation
                     AAAI Fall Symposium 
                           on

   COMPUTATIONAL MODELS FOR INTEGRATING LANGUAGE AND VISION

                    November 10-12 1995
             Massachusetts Institute of Technology (MIT)
                     Cambridge, MA

This symposium will focus on research issues in developing
computational  models  for  integrating language and vision.  
The intrinsic difficulty of both natural  language  processing 
and computer vision has discouraged researchers 
>from attempting their integration, although in some cases
it may simplify the individual tasks (e.g. collateral-based vision, 
resolving ambiguous sentences through the use of visual information).

Developing a bridge between language and vision is non-trivial,
since the correspondence between words and images is not
one-to-one. Much has been said about the
necessity of linking language and perception for a system
to exhibit intelligent behavior, but there has been relatively
little work on developing computational models for this task.
A natural-language understanding system should be able to
understand and make references to the visual world.  The use of
scene-specific context (obtained from written or spoken text
accompanying a scene) could greatly enhance the performance of
computer vision systems.

Some of the topics to be addressed are: 

o use of collateral text in image and diagram understanding
o generating natural-language descriptions of visual data
  (e.g., event perception in image sequences)
o identifying and extracting visual information from language
o understanding spatial language, spatial reasoning
o knowledge representation for linguistic and visual
  information, hybrid (language and visual) knowledge bases
o use of visual data in disambiguating/understanding text
o content-based retrieval from integrated text/image/video
  databases
o language-based scene modeling
  (e.g., picture or graphics generation)
o cognitive theories connecting language and perception

The symposium will consist of invited talks, panel discussions,
individual presentations and group discussions.  Those 
interested in making a presentation should submit
a technical paper (not to exceed 3,000 words).  Others
interested in participating in the symposium 
should submit either a position
paper or a research abstract.  Email submissions
in postscript format are encouraged, and should be
sent to rohini@cedar.buffalo.edu.  Alternatively, 4
hard copies may be sent to:

        Rohini Srihari
        CEDAR/SUNY at Buffalo
        UB Commons, 520 Lee Entrance Suite 202
        Buffalo, NY  14228-2567
********** Papers should be sent by APRIL 14, 1995. ************

In addition to invited participants, a limited number of other
interested parties will be able to register on a first-come basis.
Registration will be available by August 1, 1995 through AAAI.


Further information

Please address any questions regarding the symposium to
Rohini Srihari (rohini@cedar.buffalo.edu),
Debra Burhans (burhans@cs.buffalo.edu) or Rajiv Chopra
(rchopra@cs.buffalo.edu).

RELEVANT DATES

April 14, 1995          Submissions for the symposium are due
May 19, 1995            Notification of acceptance
September 1, 1995       Working notes for symposium distributed
Nov 10-12, 1995         Symposium held at MIT

Organizing Committee:
Rohini K. Srihari (Chair), CEDAR, SUNY at Buffalo
David Waltz, NEC Research Institute
Thomas M. Strat, SRI International
Candace Sidner, Lotus Development Corporation
Janice Glasgow, Queen's University
Ken Forbus, Northwestern University
Annette Herskovits, Wellesley College
Gordon Novak, University of Texas at Austin
Jeffrey Siskind, University of Toronto


Sponsored by the American Association for Artififical Intelligence
445 Burgess Drive
Menlo Park, CA 94025
(415) 328-3123
fss@aaai.org