Spatiotemporal saliency for event detection and representation in the 3D wavelet domain: Potential in human action recognition

Rapantzikos, K; Avrithis, Y; Kollias, S

dc.contributor.author	Rapantzikos, K	en
dc.contributor.author	Avrithis, Y	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T02:44:57Z
dc.date.available	2014-03-01T02:44:57Z
dc.date.issued	2007	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32052
dc.subject	3D wavelet transform	en
dc.subject	Action recognition	en
dc.subject	Spatiotemporal saliency	en
dc.subject.other	Computational complexity	en
dc.subject.other	Computer vision	en
dc.subject.other	Database systems	en
dc.subject.other	Discrete wavelet transforms	en
dc.subject.other	Three dimensional	en
dc.subject.other	3D wavelet transform	en
dc.subject.other	Action recognition	en
dc.subject.other	Event detection	en
dc.subject.other	Spatiotemporal saliency	en
dc.subject.other	Image recognition	en
dc.title	Spatiotemporal saliency for event detection and representation in the 3D wavelet domain: Potential in human action recognition	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1282280.1282326	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1282280.1282326	en
heal.publicationDate	2007	en
heal.abstract	Event detection and recognition is still one of the most active fields in computer vision, since the complexity of the dynamic events and the need for computational efficient solutions pose several difficulties. This paper addresses detection and representation of spatiotemporal salient regions using the 3D Discrete Wavelet Transform (DWT). We propose a framework to measure saliency based on the orientation selective bands of the 3D DWT and represent events using simple features of salient regions. We apply this method to human action recognition, test it on a large public video database consisting of six human actions and compare the results against an established method in the literature. Qualitative and quantitative evaluation indicates the potential of the proposed method to localize and represent human actions. Copyright 2007 ACM.	en
heal.journalName	Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007	en
dc.identifier.doi	10.1145/1282280.1282326	en
dc.identifier.spage	294	en
dc.identifier.epage	301	en