Computing Publications

Publications Home » Spatiotemporal saliency for human...

Spatiotemporal saliency for human action recognition

Antonios Oikonomopoulos, Ioannis Patras, Maja Pantic

Conference or Workshop Paper
IEEE Int'l Conf. on Multimedia and Expo 2005
July, 2005
ISBN 0-7803-9332-5

This paper addresses the problem of human action recognition by introducing a sparse representation of image sequences as a collection of spatiotemporal events that are localized at points that are salient both in space and time. We detect the spatiotemporal salient points by measuring changes in the information content of pixel neighborhoods not only in space but also in time. We introduce an appropriate distance metric between two collections of spatiotemporal salient points that is based on the Chamfer distance and an iterative linear time warping technique that deals with time expansion or time compression issues. We propose a classification scheme that is based on Relevance Vector Machines and on the proposed distance measure. We present results on real image sequences from a small database depicting people performing 19 aerobic exercises.

PDF of full publication (1.2 megabytes)
(need help viewing PDF files?)
BibTEX file for the publication
Conditions for downloading publications from this site. built & maintained by Ashok Argent-Katwala.