Combining Re-ranking And Rank Aggregation Methods For Image Retrieval

dc.creatorGuimaraes Pedronette
dc.creatorDaniel Carlos; Torres
dc.creatorRicardo da S.
dc.date2016
dc.dateagos
dc.date2017-11-13T13:16:18Z
dc.date2017-11-13T13:16:18Z
dc.date.accessioned2018-03-29T05:53:37Z
dc.date.available2018-03-29T05:53:37Z
dc.identifierMultimedia Tools And Applications. Springer, v. 75, p. 9121 - 9144, 2016.
dc.identifier1380-7501
dc.identifier1573-7721
dc.identifierWOS:000382113500016
dc.identifier10.1007/s11042-015-3044-0
dc.identifierhttps://link-springer-com.ez88.periodicos.capes.gov.br/article/10.1007%2Fs11042-015-3044-0
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/327521
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1364546
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionThis paper presents novel approaches for combining re-ranking and rank aggregation methods aiming at improving the effectiveness of Content-Based Image Retrieval (CBIR) systems. Given a query image as input, CBIR systems retrieve the most similar images in a collection by taking into account image visual properties. In this scenario, accurately ranking collection images is of great relevance. Aiming at improving the effectiveness of CBIR systems, re-ranking and rank aggregation algorithms have been proposed. However, different re-ranking and rank aggregation approaches, applied to different image descriptors, may produce different and complementary image rankings. In this paper, we present four novel approaches for combining these rankings aiming at obtaining more effective results. Several experiments were conducted involving shape, color, and texture descriptors. The proposed approaches are also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate that our approaches can improve significantly the effectiveness of image retrieval systems.
dc.description75
dc.description15
dc.description9121
dc.description9144
dc.descriptionSao Paulo Research Foundation - FAPESP [2013/08645-0]
dc.descriptionCNPq [306580/2012-8, 484254/2012-0]
dc.descriptionCAPES
dc.descriptionAMD
dc.descriptionMicrosoft Research
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.languageEnglish
dc.publisherSpringer
dc.publisherDordrecht
dc.relationMultimedia Tools and Applications
dc.rightsfechado
dc.sourceWOS
dc.subjectContent-based Image Retrieval
dc.subjectRe-ranking
dc.subjectRank Aggregation
dc.subjectFusion
dc.titleCombining Re-ranking And Rank Aggregation Methods For Image Retrieval
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución