dc.contributorUniversidade Estadual Paulista (Unesp)
dc.contributorUniversidade Estadual de Campinas (UNICAMP)
dc.contributorAdvanced Technologies, SAMSUNG Research Institute
dc.date.accessioned2018-12-11T16:55:48Z
dc.date.available2018-12-11T16:55:48Z
dc.date.created2018-12-11T16:55:48Z
dc.date.issued2014-01-01
dc.identifierICMR 2014 - Proceedings of the ACM International Conference on Multimedia Retrieval 2014, p. 345-352.
dc.identifierhttp://hdl.handle.net/11449/171552
dc.identifier10.1145/2578726.2578770
dc.identifier2-s2.0-84899769548
dc.description.abstractThis paper presents a novel unsupervised learning approach that takes into account the intrinsic dataset structure, which is represented in terms of the reciprocal neighborhood references found in different ranked lists. The proposed Reciprocal kNN Distance defines a more effective distance between two images, and is used to improve the effectiveness of image retrieval systems. Several experiments were conducted for different image retrieval tasks involving shape, color, and texture descriptors. The proposed approach is also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate the effectiveness of proposed approach. The Reciprocal kNN Distance yields better results in terms of effectiveness than various state-of-the-art algorithms. Copyright © 2014 ACM.
dc.languageeng
dc.relationICMR 2014 - Proceedings of the ACM International Conference on Multimedia Retrieval 2014
dc.rightsAcesso aberto
dc.sourceScopus
dc.subjectContent-based image retrieval
dc.subjectUnsupervised distance learning
dc.titleUnsupervised distance learning by reciprocal kNN distance for image retrieval
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución