Spatio-temporal shape contexts for human action retrieval

Shao, Ling and Du, Yuanjia (2009) Spatio-temporal shape contexts for human action retrieval. In: IMCE '09 - 1st International Workshop on Interactive Multimedia for Consumer Electronics, 19th - 24th October 2009, Beijing, China.

Full text not available from this repository. (Request a copy)

Abstract

A novel method using the combination of spatio-temporal interest points and spatio-temporal shape contexts for human action description and retrieval is proposed. Both the feature points detection and description are invariant to geometric and photometric changes and intra-class variations. The experimental results show that the proposed descriptor is more effective than brightness gradients based motion descriptors for classifying and retrieving challenging human actions.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Motion descriptor, spatio-temporal shape context, action retrieval
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Paul Burns
Date Deposited:	17 Jun 2015 10:51
Last Modified:	13 Oct 2019 00:25
URI:	http://nrl.northumbria.ac.uk/id/eprint/22987

Downloads