Looking for trouble: using causal semantics to direct focus of attention

Lawrence A Birnbaum*, Matthew Brand, Paul Cooper

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

24 Citations (Scopus)

Abstract

Vision should provide an explanation of the scene in terms of a causal semantics - what affects what, and why. An important part of the causal explanation of static scenes is what supports what, or, counterfacturally: Why aren't things moving? We use simple naive physical knowledge as the basis of a vertically integrated vision system that explains arbitrarily complex stacked block structures. The semantics provides a basis for controlling the application of visual attention, and forms a framework for the explanation that is generated. We show how the program sequentially explores scenes of complex blocks structures, identifies functional substructures such as arches and cantilevers, and develops an explanation of why the whole construction stands and the role of each block in its stability.

Original languageEnglish (US)
Title of host publication1993 IEEE 4th International Conference on Computer Vision
PublisherPubl by IEEE
Pages49-56
Number of pages8
ISBN (Print)0818638729
StatePublished - Jan 1 1993
Event1993 IEEE 4th International Conference on Computer Vision - Berlin, Ger
Duration: May 11 1993May 14 1993

Publication series

Name1993 IEEE 4th International Conference on Computer Vision

Other

Other1993 IEEE 4th International Conference on Computer Vision
CityBerlin, Ger
Period5/11/935/14/93

Fingerprint

Semantics
Arches

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Birnbaum, L. A., Brand, M., & Cooper, P. (1993). Looking for trouble: using causal semantics to direct focus of attention. In 1993 IEEE 4th International Conference on Computer Vision (pp. 49-56). (1993 IEEE 4th International Conference on Computer Vision). Publ by IEEE.
Birnbaum, Lawrence A ; Brand, Matthew ; Cooper, Paul. / Looking for trouble : using causal semantics to direct focus of attention. 1993 IEEE 4th International Conference on Computer Vision. Publ by IEEE, 1993. pp. 49-56 (1993 IEEE 4th International Conference on Computer Vision).
@inproceedings{0b2d19ea3ca245be8c7fa4baddba2617,
title = "Looking for trouble: using causal semantics to direct focus of attention",
abstract = "Vision should provide an explanation of the scene in terms of a causal semantics - what affects what, and why. An important part of the causal explanation of static scenes is what supports what, or, counterfacturally: Why aren't things moving? We use simple naive physical knowledge as the basis of a vertically integrated vision system that explains arbitrarily complex stacked block structures. The semantics provides a basis for controlling the application of visual attention, and forms a framework for the explanation that is generated. We show how the program sequentially explores scenes of complex blocks structures, identifies functional substructures such as arches and cantilevers, and develops an explanation of why the whole construction stands and the role of each block in its stability.",
author = "Birnbaum, {Lawrence A} and Matthew Brand and Paul Cooper",
year = "1993",
month = "1",
day = "1",
language = "English (US)",
isbn = "0818638729",
series = "1993 IEEE 4th International Conference on Computer Vision",
publisher = "Publ by IEEE",
pages = "49--56",
booktitle = "1993 IEEE 4th International Conference on Computer Vision",

}

Birnbaum, LA, Brand, M & Cooper, P 1993, Looking for trouble: using causal semantics to direct focus of attention. in 1993 IEEE 4th International Conference on Computer Vision. 1993 IEEE 4th International Conference on Computer Vision, Publ by IEEE, pp. 49-56, 1993 IEEE 4th International Conference on Computer Vision, Berlin, Ger, 5/11/93.

Looking for trouble : using causal semantics to direct focus of attention. / Birnbaum, Lawrence A; Brand, Matthew; Cooper, Paul.

1993 IEEE 4th International Conference on Computer Vision. Publ by IEEE, 1993. p. 49-56 (1993 IEEE 4th International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Looking for trouble

T2 - using causal semantics to direct focus of attention

AU - Birnbaum, Lawrence A

AU - Brand, Matthew

AU - Cooper, Paul

PY - 1993/1/1

Y1 - 1993/1/1

N2 - Vision should provide an explanation of the scene in terms of a causal semantics - what affects what, and why. An important part of the causal explanation of static scenes is what supports what, or, counterfacturally: Why aren't things moving? We use simple naive physical knowledge as the basis of a vertically integrated vision system that explains arbitrarily complex stacked block structures. The semantics provides a basis for controlling the application of visual attention, and forms a framework for the explanation that is generated. We show how the program sequentially explores scenes of complex blocks structures, identifies functional substructures such as arches and cantilevers, and develops an explanation of why the whole construction stands and the role of each block in its stability.

AB - Vision should provide an explanation of the scene in terms of a causal semantics - what affects what, and why. An important part of the causal explanation of static scenes is what supports what, or, counterfacturally: Why aren't things moving? We use simple naive physical knowledge as the basis of a vertically integrated vision system that explains arbitrarily complex stacked block structures. The semantics provides a basis for controlling the application of visual attention, and forms a framework for the explanation that is generated. We show how the program sequentially explores scenes of complex blocks structures, identifies functional substructures such as arches and cantilevers, and develops an explanation of why the whole construction stands and the role of each block in its stability.

UR - http://www.scopus.com/inward/record.url?scp=0027242756&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027242756&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027242756

SN - 0818638729

T3 - 1993 IEEE 4th International Conference on Computer Vision

SP - 49

EP - 56

BT - 1993 IEEE 4th International Conference on Computer Vision

PB - Publ by IEEE

ER -

Birnbaum LA, Brand M, Cooper P. Looking for trouble: using causal semantics to direct focus of attention. In 1993 IEEE 4th International Conference on Computer Vision. Publ by IEEE. 1993. p. 49-56. (1993 IEEE 4th International Conference on Computer Vision).