Show simple item record

dc.contributor.authorArmağan, Anılen_US
dc.contributor.authorPopescu, A.en_US
dc.contributor.authorDuygulu, Pınaren_US
dc.coverage.spatialBarcelona, Spainen_US
dc.date.accessioned2016-02-08T12:09:27Z
dc.date.available2016-02-08T12:09:27Z
dc.date.issued2013en_US
dc.identifier.issn1613-0073
dc.identifier.urihttp://hdl.handle.net/11693/28043
dc.descriptionDate of Conference: October 18-19, 2013.en_US
dc.descriptionConference name: MediaEval 2013 Multimedia Benchmark Workshopen_US
dc.description.abstractThe Mediaeval 2013 Retrieving Diverse Social Image Task addresses the challenge of improving both relevance and diversity of photos in a retrieval task on Flickr. We propose a clustering based technique that exploits both textual and visual information. We introduce a k-Nearest Neighbor (k-NN) inspired re-ranking algorithm that is applied before clustering to clean the dataset. After the clustering step, we exploit social cues to rank clusters by social relevance. From those ranked clusters images are retrieved according to their distance to cluster centroids.en_US
dc.language.isoEnglishen_US
dc.source.titleCEUR Workshop Proceedingsen_US
dc.subjectCluster centroidsen_US
dc.subjectK-nearest neighborsen_US
dc.subjectRe-rankingen_US
dc.subjectSocial cuesen_US
dc.subjectSocial imagesen_US
dc.subjectVisual informationen_US
dc.subjectNearest neighbor searchen_US
dc.titleMUCKE participation at retrieving diverse social images task of MediaEval 2013en_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.volumeNumber1043en_US
dc.publisherCEUR-WSen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record