Improving the search accuracy of the VLAD through weighted aggregation of local descriptors

Cited 7 time in webofscience Cited 0 time in scopus
  • Hit : 358
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKim, Tak-Eunko
dc.contributor.authorKim, Myoung Hoko
dc.date.accessioned2015-11-13T06:42:46Z-
dc.date.available2015-11-13T06:42:46Z-
dc.date.created2015-07-03-
dc.date.created2015-07-03-
dc.date.issued2015-08-
dc.identifier.citationJOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v.31, pp.237 - 252-
dc.identifier.issn1047-3203-
dc.identifier.urihttp://hdl.handle.net/10203/200447-
dc.description.abstractWe present a novel compact image descriptor, called the Weighted VLAD (wVLAD), which extends the original vector of locally aggregated descriptors (VLAD). The main idea is that the relative importance of local descriptors can be quite different among the local descriptors of an image, depending on the positions from which the descriptors are extracted. Thus, we propose an approach where we assign a weight to each local descriptor of an image, and then compute weighted aggregations of local descriptors. The weights of local descriptors are measured by performing saliency analysis together with an appropriate calibration function. We show, through experiments on publicly available datasets, that our proposed method works better than other existing methods in most image datasets. (C) 2015 Elsevier Inc. All rights reserved.-
dc.languageEnglish-
dc.publisherACADEMIC PRESS INC ELSEVIER SCIENCE-
dc.subjectIMAGE CLASSIFICATION-
dc.subjectSCALE-
dc.subjectFEATURES-
dc.subjectIDF-
dc.titleImproving the search accuracy of the VLAD through weighted aggregation of local descriptors-
dc.typeArticle-
dc.identifier.wosid000359181600022-
dc.identifier.scopusid2-s2.0-84937215571-
dc.type.rimsART-
dc.citation.volume31-
dc.citation.beginningpage237-
dc.citation.endingpage252-
dc.citation.publicationnameJOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION-
dc.identifier.doi10.1016/j.jvcir.2015.07.005-
dc.contributor.localauthorKim, Myoung Ho-
dc.contributor.nonIdAuthorKim, Tak-Eun-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorCompact image descriptor-
dc.subject.keywordAuthorWeighting scheme-
dc.subject.keywordAuthorWeighted VLAD-
dc.subject.keywordAuthorSaliency analysis-
dc.subject.keywordAuthorContent-based image retrieval-
dc.subject.keywordAuthorImportance of local descriptors-
dc.subject.keywordAuthorCalibration of saliency values-
dc.subject.keywordAuthorSearch accuracy-
dc.subject.keywordPlusIMAGE CLASSIFICATION-
dc.subject.keywordPlusSCALE-
dc.subject.keywordPlusFEATURES-
dc.subject.keywordPlusIDF-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 7 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0