Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWu, J.en
dc.contributor.authorLi, Y.en
dc.contributor.authorFeng, S.en
dc.contributor.authorShen, H.en
dc.identifier.citationAdvances in Knowledge Discovery and Data Mining: 17th Pacific-Asia Conference, PAKDD 2013, Gold Coast, Australia, April 14-17, 2013, Proceedings, Part II, 2013 / Pei, J., Tseng, V., Cao, L., Motoda, H., Xu, G. (ed./s), vol.7819 LNAI, iss.PART 2, pp.426-436en
dc.description.abstractManifold ranking (MR), as a powerful semi-supervised learning algorithm, plays an important role to deal with the relevance feedback problem in content-based image retrieval (CBIR). However, conventional MR has two main drawbacks: 1) in many cases, it is prone to exploit “unreliable” unlabeled images when deployed in CBIR due to the semantic gap; 2) the performance of MR is quite sensitive to the scale parameter used for calculating the Laplacian matrix. In this work, a self-immunizing MR approach is presented to address the drawbacks. Concretely, we first propose an elastic kNN graph as well as its constructing algorithm to exploit unlabeled images “safely”, and then develop a local scaling solution to calculate the Laplacian matrix adaptively. Extensive experiments on 10,000 Corel images show that the proposed algorithm is more effective than the state-of-the-art approaches.en
dc.description.statementofresponsibilityJun Wu, Yidong Li, Songhe Feng, and Hong Shenen
dc.relation.ispartofseriesLecture Notes in Computer Science; 7819en
dc.rights© Springer-Verlag Berlin Heidelberg 2013en
dc.subjectcontent-based image retrieval; relevance feedback; self-immunizing manifold ranking; elastic kNN graph; local scalingen
dc.titleA self-immunizing manifold ranking for image retrievalen
dc.typeConference paperen
dc.contributor.conference17th Pacific-Asia Conference, PAKDD 2013 (14 Apr 2013 - 17 Apr 2013 : Gold Coast, Australia)en
pubs.library.collectionComputer Science publicationsen
dc.identifier.orcidShen, H. [0000-0002-3663-6591]en
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.

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