Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Grounding language in perception

Grounding language in perception This paper describes an implemented computer program that recognizes the occurrence of simple spatial motion events in simulated video input. The program receives an animated line-drawing as input and produces as output a semantic representation of the events occurring in that animation. This paper suggests that the notions ofsupport, contact, andattachment are crucial to specifying many simple spatial motion event types and presents a logical notation for describing classes of events that incorporates such notions as primitives. It then suggests that the truth values of such primitives can be recovered from perceptual input by a process of counterfactual simulation, predicting the effect of hypothetical changes to the world on the immediate future. Finally, it suggests that such counterfactual simulation is performed using knowledge of naive physical constraints such assubstantiality, continuity, gravity, andground plane. This paper describes the algorithms that incorporate these ideas in the program and illustrates the operation of the program on sample input. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Artificial Intelligence Review Springer Journals

Grounding language in perception

Siskind, Jeffrey
Artificial Intelligence Review , Volume 8 (6) – Dec 4, 2004
Download PDF
21 pages

Loading next page...
 
/lp/springer-journals/grounding-language-in-perception-uupeINmxNn

References (44)

Publisher
Springer Journals
Copyright
Copyright
Subject
Computer Science; Artificial Intelligence; Computer Science, general
ISSN
0269-2821
eISSN
1573-7462
DOI
10.1007/BF00849726
Publisher site
See Article on Publisher Site

Abstract

This paper describes an implemented computer program that recognizes the occurrence of simple spatial motion events in simulated video input. The program receives an animated line-drawing as input and produces as output a semantic representation of the events occurring in that animation. This paper suggests that the notions ofsupport, contact, andattachment are crucial to specifying many simple spatial motion event types and presents a logical notation for describing classes of events that incorporates such notions as primitives. It then suggests that the truth values of such primitives can be recovered from perceptual input by a process of counterfactual simulation, predicting the effect of hypothetical changes to the world on the immediate future. Finally, it suggests that such counterfactual simulation is performed using knowledge of naive physical constraints such assubstantiality, continuity, gravity, andground plane. This paper describes the algorithms that incorporate these ideas in the program and illustrates the operation of the program on sample input.

Journal

Artificial Intelligence Review – Springer Journals

Published: Dec 4, 2004

There are no references for this article.