Integration of visual and shape attributes for object action complexes
2008 (English)In: Computer Vision Systems, Proceedings / [ed] Gasteratos, A; Vincze, M; Tsotsos, JK, 2008, Vol. 5008, 13-22 p.Conference paper (Refereed)
Our work is oriented towards the idea of developing cognitive capabilities in artificial systems through Object Action Complexes (OACs) . The theory comes up with the claim that objects and actions are inseparably intertwined. Categories of objects are not built by visual appearance only, as very common in computer vision, but by the actions an agent can perform and by attributes perceivable. The core of the OAC concept is constituting objects from a set of attributes, which can be manifold in type (e.g. color, shape, mass, material), to actions. This twofold of attributes and actions provides the base for categories. The work presented here is embedded in the development of an extensible system for providing and evolving attributes,, beginning with attributes extractable from visual data.
Place, publisher, year, edition, pages
2008. Vol. 5008, 13-22 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 5008
cognitive vision, object action complexes, object attribution
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-38418DOI: 10.1007/978-3-540-79547-6_2ISI: 000255865700002ScopusID: 2-s2.0-44649119245ISBN: 978-3-540-79546-9OAI: oai:DiVA.org:kth-38418DiVA: diva2:437954
6th International Conference on Computer Vision Systems, ICVS 2008; Santorini; 12 May 2008 through 15 May 2008
QC 201108312011-08-312011-08-252016-05-23Bibliographically approved