A semantic multimedia analysis approach utilizing a Region Thesaurus and LSA

Spyrou, E; Tolias, G; Mylonas, P; Avrithis, Y

dc.contributor.author	Spyrou, E	en
dc.contributor.author	Tolias, G	en
dc.contributor.author	Mylonas, P	en
dc.contributor.author	Avrithis, Y	en
dc.date.accessioned	2014-03-01T02:45:04Z
dc.date.available	2014-03-01T02:45:04Z
dc.date.issued	2008	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32128
dc.subject	Cluster Algorithm	en
dc.subject	Feature Detection	en
dc.subject	Latent Semantic Analysis	en
dc.subject.other	Key frames	en
dc.subject.other	Latent Semantic Analysis	en
dc.subject.other	Multimedia interactive services	en
dc.subject.other	Clustering algorithms	en
dc.subject.other	Image analysis	en
dc.subject.other	Information theory	en
dc.subject.other	Motion Picture Experts Group standards	en
dc.subject.other	Semantics	en
dc.subject.other	Thesauri	en
dc.subject.other	Multimedia services	en
dc.title	A semantic multimedia analysis approach utilizing a Region Thesaurus and LSA	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/WIAMIS.2008.49	en
heal.identifier.secondary	http://dx.doi.org/10.1109/WIAMIS.2008.49	en
heal.identifier.secondary	4556869	en
heal.publicationDate	2008	en
heal.abstract	This paper presents an approach on high-level feature detection within video documents, using a Region Thesaurus and Latent Semantic Analysis. A video shot is represented by a single keyframe. MPEG-7 features are extracted from coarse regions of it. A clustering algorithm is applied on all extracted regions and a region thesaurus is constructed. Its use is to assist to the mapping of low- to high-level features by a model vector representation. Latent Semantic Analysis is then applied on the model vectors to exploit the latent relations among region types aiming to improve detection performance. The proposed approach is thoroughly examined using TRECVID 2007 development data. ©2008 IEEE.	en
heal.journalName	WIAMIS 2008 - Proceedings of the 9th International Workshop on Image Analysis for Multimedia Interactive Services	en
dc.identifier.doi	10.1109/WIAMIS.2008.49	en
dc.identifier.spage	8	en
dc.identifier.epage	11	en