Video event detection and summarization using audio, visual and text saliency

Evangelopoulos, G; Zlatintsi, A; Skoumas, G; Rapantzikos, K; Potamianos, A; Maragos, P; Avrithis, Y

dc.contributor.author	Evangelopoulos, G	en
dc.contributor.author	Zlatintsi, A	en
dc.contributor.author	Skoumas, G	en
dc.contributor.author	Rapantzikos, K	en
dc.contributor.author	Potamianos, A	en
dc.contributor.author	Maragos, P	en
dc.contributor.author	Avrithis, Y	en
dc.date.accessioned	2014-03-01T02:46:34Z
dc.date.available	2014-03-01T02:46:34Z
dc.date.issued	2009	en
dc.identifier.issn	15206149	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32724
dc.subject	Audio	en
dc.subject	Movie summarization	en
dc.subject	Multimodal saliency	en
dc.subject	Text processing	en
dc.subject	Video	en
dc.subject	Video abstraction	en
dc.subject.other	Audio	en
dc.subject.other	Movie summarization	en
dc.subject.other	Multimodal saliency	en
dc.subject.other	Video	en
dc.subject.other	Video abstraction	en
dc.subject.other	Abstracting	en
dc.subject.other	Acoustics	en
dc.subject.other	Embedded systems	en
dc.subject.other	Mathematical operators	en
dc.subject.other	Motion pictures	en
dc.subject.other	Signal processing	en
dc.subject.other	Text processing	en
dc.subject.other	Video recording	en
dc.subject.other	Word processing	en
dc.subject.other	Signal detection	en
dc.title	Video event detection and summarization using audio, visual and text saliency	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICASSP.2009.4960393	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICASSP.2009.4960393	en
heal.identifier.secondary	4960393	en
heal.publicationDate	2009	en
heal.abstract	Detection of perceptually important video events is formulated here on the basis of saliency models for the audio, visual and textual information conveyed in a video stream. Audio saliency is assessed by cues that quantify multifrequency waveform modulations, extracted through nonlinear operators and energy tracking. Visual saliency is measured through a spatiotemporal attention model driven by intensity, color and motion. Text saliency is extracted from part-of-speech tagging on the subtitles information available with most movie distributions. The various modality curves are integrated in a single attention curve, where the presence of an event may be signified in one or multiple domains. This multimodal saliency curve is the basis of a bottom-up video summarization algorithm, that refines results from unimodal or audiovisual-based skimming. The algorithm performs favorably for video summarization in terms of informativeness and enjoyability. ©2009 IEEE.	en
heal.journalName	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings	en
dc.identifier.doi	10.1109/ICASSP.2009.4960393	en
dc.identifier.spage	3553	en
dc.identifier.epage	3556	en