Spatiotemporal Features for Action Recognition and Salient Event Detection

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	2014-03-01T01:37:06Z
dc.date.available	2014-03-01T01:37:06Z
dc.date.issued	2011	en
dc.identifier.issn	1866-9956	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/21448
dc.subject	Action recognition	en
dc.subject	Salient event detection	en
dc.subject	Spatiotemporal visual saliency	en
dc.subject	Volumetric representation	en
dc.subject.other	Action recognition	en
dc.subject.other	Computational model	en
dc.subject.other	Constrained minimization	en
dc.subject.other	Data sets	en
dc.subject.other	Event detection	en
dc.subject.other	Event detection in video	en
dc.subject.other	Gestalt law	en
dc.subject.other	Human vision	en
dc.subject.other	Human visual	en
dc.subject.other	Multiple resolutions	en
dc.subject.other	Novel methods	en
dc.subject.other	Salient event detection	en
dc.subject.other	Spatio temporal features	en
dc.subject.other	Spatiotemporal regions	en
dc.subject.other	Temporal segments	en
dc.subject.other	Video sequences	en
dc.subject.other	Visual feature	en
dc.subject.other	Visual saliency	en
dc.subject.other	Volumetric representation	en
dc.subject.other	Competition	en
dc.subject.other	Object recognition	en
dc.subject.other	Video recording	en
dc.subject.other	Visualization	en
dc.subject.other	Feature extraction	en
dc.title	Spatiotemporal Features for Action Recognition and Salient Event Detection	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/s12559-011-9097-0	en
heal.identifier.secondary	http://dx.doi.org/10.1007/s12559-011-9097-0	en
heal.language	English	en
heal.publicationDate	2011	en
heal.abstract	Although the mechanisms of human visual understanding remain partially unclear, computational models inspired by existing knowledge on human vision have emerged and applied to several fields. In this paper, we propose a novel method to compute visual saliency from video sequences by counting in the actual spatiotemporal nature of the video. The visual input is represented by a volume in space-time and decomposed into a set of feature volumes in multiple resolutions. Feature competition is used to produce a saliency distribution of the input implemented by constrained minimization. The proposed constraints are inspired by and associated with the Gestalt laws. There are a number of contributions in this approach, namely extending existing visual feature models to a volumetric representation, allowing competition across features, scales and voxels, and formulating constraints in accordance with perceptual principles. The resulting saliency volume is used to detect prominent spatiotemporal regions and consequently applied to action recognition and perceptually salient event detection in video sequences. Comparisons against established methods on public datasets are given and reveal the potential of the proposed model. The experiments include three action recognition scenarios and salient temporal segment detection in a movie database annotated by humans. © 2011 Springer Science+Business Media, LLC.	en
heal.publisher	SPRINGER	en
heal.journalName	Cognitive Computation	en
dc.identifier.doi	10.1007/s12559-011-9097-0	en
dc.identifier.isi	ISI:000292777700014	en
dc.identifier.volume	3	en
dc.identifier.issue	1	en
dc.identifier.spage	167	en
dc.identifier.epage	184	en