Using region semantics and visual context for scene classification

Spyrou, E; Mylonas, P; Avrithis, Y

dc.contributor.author	Spyrou, E	en
dc.contributor.author	Mylonas, P	en
dc.contributor.author	Avrithis, Y	en
dc.date.accessioned	2014-03-01T02:51:31Z
dc.date.available	2014-03-01T02:51:31Z
dc.date.issued	2008	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/35527
dc.subject	Indexing Terms	en
dc.subject	Knowledge Modeling	en
dc.subject	Scene Classification	en
dc.subject	Semantic Relations	en
dc.title	Using region semantics and visual context for scene classification	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2008.4711689	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2008.4711689	en
heal.publicationDate	2008	en
heal.abstract	In this paper we focus on scene classification and detection of high-level concepts within multimedia documents, by in- troducing an intermediate contextual approach as a means of exploiting the visual context of images. More specifically, we introduce and model a novel relational knowledge representa- tion, founded on topological and semantic relations between the concepts of an image. We further develop	en
heal.journalName	Image Processing, IEEE International Conference	en
dc.identifier.doi	10.1109/ICIP.2008.4711689	en