Movie summarization based on audiovisual saliency detection

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

dc.contributor.author	Evangelopoulos, G	en
dc.contributor.author	Rapantzikos, K	en
dc.contributor.author	Potamianos, A	en
dc.contributor.author	Maragos, P	en
dc.contributor.author	Zlatintsi, A	en
dc.contributor.author	Avrithis, Y	en
dc.date.accessioned	2014-03-01T02:45:39Z
dc.date.available	2014-03-01T02:45:39Z
dc.date.issued	2008	en
dc.identifier.issn	15224880	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32315
dc.subject	Audio processing	en
dc.subject	Audiovisual saliency	en
dc.subject	Movie summarization	en
dc.subject	Video processing	en
dc.subject.other	Attention model	en
dc.subject.other	Attention modeling	en
dc.subject.other	Audio and video	en
dc.subject.other	Audio processing	en
dc.subject.other	Audiovisual saliency	en
dc.subject.other	Geometrical features	en
dc.subject.other	Informativeness	en
dc.subject.other	Level Set	en
dc.subject.other	Local extremum	en
dc.subject.other	Movie summarization	en
dc.subject.other	Multi-frequency bands	en
dc.subject.other	Nonlinear operator	en
dc.subject.other	Saliency detection	en
dc.subject.other	Sharp transition	en
dc.subject.other	Signal modulations	en
dc.subject.other	Video processing	en
dc.subject.other	Visual saliency	en
dc.subject.other	Frequency bands	en
dc.subject.other	Graph theory	en
dc.subject.other	Image processing	en
dc.subject.other	Imaging systems	en
dc.subject.other	Mathematical operators	en
dc.subject.other	Video signal processing	en
dc.subject.other	Motion pictures	en
dc.title	Movie summarization based on audiovisual saliency detection	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2008.4712308	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2008.4712308	en
heal.identifier.secondary	4712308	en
heal.publicationDate	2008	en
heal.abstract	Based on perceptual and computational attention modeling studies, we formulate measures of saliency for an audiovisual stream. Audio saliency is captured by signal modulations and related multi-frequency band features, extracted through nonlinear operators and energy tracking. Visual saliency is measured by means of a spatiotemporal attention model driven by various feature cues (intensity, color, motion). Audio and video curves are integrated in a single attention curve, where events may be enhanced, suppressed or vanished. The presence of salient events is signified on this audiovisual curve by geometrical features such as local extrema, sharp transition points and level sets. An audiovisual saliency-based movie summarization algorithm is proposed and evaluated. The algorithm is shown to perform very well in terms of summary informativeness and enjoyability for movie clips of various genres. © 2008 IEEE.	en
heal.journalName	Proceedings - International Conference on Image Processing, ICIP	en
dc.identifier.doi	10.1109/ICIP.2008.4712308	en
dc.identifier.spage	2528	en
dc.identifier.epage	2531	en