DocumentCode
3426861
Title
Event semantics in two-person interactions
Author
Park, Sangho ; Aggarwal, J.K.
Author_Institution
Electr. & Comput. Eng., Texas Univ., Austin, TX, USA
Volume
4
fYear
2004
fDate
23-26 Aug. 2004
Firstpage
227
Abstract
This work presents a method to represent two-person interactions at a semantic level with a natural language description. A human interaction is composed of two single person actions, which in turn are made up of torso and arm/leg motions. We adopt the verb argument structure in linguistics to represent human action in terms of triplets. Various two-person interactions are represented at a detailed level using multiple triplets aligned along a time line according to the spatial/temporal constraints of the interactions. Our method provides a user-friendly natural-language description of various human interactions, and properly describes positive, neutral, and negative interactions occurring between two persons.
Keywords
natural language interfaces; pattern recognition; semantic networks; event semantics; natural language description; two-person interactions; verb argument structure; Application software; Bayesian methods; Computer interfaces; Humans; Information retrieval; Layout; Leg; Natural languages; Surveillance; Torso;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
ISSN
1051-4651
Print_ISBN
0-7695-2128-2
Type
conf
DOI
10.1109/ICPR.2004.1333745
Filename
1333745
Link To Document