Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/73428
Type: Artigo
Title: Unsupervised manifold learning using reciprocal kNN graphs in image re-ranking and rank aggregation tasks
Author: Pedronette, Daniel Carlos Guimarães
Penatti, Otávio A. B.
Torres, Ricardo da S.
Abstract: In this paper, we present an unsupervised distance learning approach for improving the effectiveness of image retrieval tasks. We propose a Reciprocal kNN Graph algorithm that considers the relationships among ranked lists in the context of a k-reciprocal neighborhood. The similarity is propagated among neighbors considering the geometry of the dataset manifold. The proposed method can be used both for re-ranking and rank aggregation tasks. Unlike traditional diffusion process methods, which require matrix multiplication operations, our algorithm takes only a subset of ranked lists as input, presenting linear complexity in terms of computational and storage requirements. We conducted a large evaluation protocol involving shape, color, and texture descriptors, various datasets, and comparisons with other post-processing approaches. The re-ranking and rank aggregation algorithms yield better results in terms of effectiveness performance than various state-of-the-art algorithms recently proposed in the literature, achieving bull's eye and MAP scores of 100% on the well-known MPEG-7 shape dataset (C) 2013 Elsevier B.V. All rights reserved.
In this paper, we present an unsupervised distance learning approach for improving the effectiveness of image retrieval tasks. We propose a Reciprocal kNN Graph algorithm that considers the relationships among ranked lists in the context of a k-reciprocal
Subject: Re-ranqueamento
Ensino à distância
Recuperação de imagens baseada em conteúdo
Country: Países Baixos
Editor: Elsevier
Citation: Image And Vision Computing. Elsevier Science Bv, v. 32, n. 2, n. 120, n. 130, 2014.
Rights: Fechado
Identifier DOI: 10.1016/j.imavis.2013.12.009
Address: https://www.sciencedirect.com/science/article/pii/S0262885613001819
Date Issue: 2014
Appears in Collections:IC - Artigos e Outros Documentos
FT - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
000332905300003.pdf1.43 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.