Show simple item record

dc.contributor.authorCui, Chaoran
dc.contributor.authorShen, Jialie
dc.contributor.authorChen, Zhumin
dc.contributor.authorWang, Shuaiqiang
dc.contributor.authorMa, Jun
dc.date.accessioned2017-12-11T11:03:16Z
dc.date.available2020-01-26T22:35:17Z
dc.date.issued2018
dc.identifier.citationCui, C., Shen, J., Chen, Z., Wang, S., & Ma, J. (2018). Learning to Rank Images for Complex Queries in Concept-based Search. <i>Neurocomputing</i>, <i>274</i>, 19-28. <a href="https://doi.org/10.1016/j.neucom.2016.05.118" target="_blank">https://doi.org/10.1016/j.neucom.2016.05.118</a>
dc.identifier.otherCONVID_26949709
dc.identifier.otherTUTKAID_73493
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/56233
dc.description.abstractConcept-based image search is an emerging search paradigm that utilizes a set of concepts as intermediate semantic descriptors of images to bridge the semantic gap. Typically, a user query is rather complex and cannot be well described using a single concept. However, it is less effective to tackle such complex queries by simply aggregating the individual search results for the constituent concepts. In this paper, we propose to introduce the learning to rank techniques to concept-based image search for complex queries. With freely available social tagged images, we first build concept detectors by jointly leveraging the heterogeneous visual features. Then, to formulate the image relevance, we explicitly model the individual weight of each constituent concept in a complex query. The dependence among constituent concepts, as well as the relatedness between query and non-query concepts, are also considered through modeling the pairwise concept correlations in a factorization way. Finally, we train our model to directly optimize the image ranking performance for complex queries under a pairwise learning to rank framework. Extensive experiments on two benchmark datasets well verified the promise of our approach.
dc.language.isoeng
dc.publisherElsevier BV
dc.relation.ispartofseriesNeurocomputing
dc.subject.otherconcept-based image search
dc.subject.othercomplex query
dc.subject.otherlearning to rank
dc.subject.otherfactorization machine
dc.titleLearning to Rank Images for Complex Queries in Concept-based Search
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-201711204298
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.date.updated2017-11-20T07:15:12Z
dc.type.coarjournal article
dc.description.reviewstatuspeerReviewed
dc.format.pagerange19-28
dc.relation.issn0925-2312
dc.relation.numberinseries0
dc.relation.volume274
dc.type.versionacceptedVersion
dc.rights.copyright© 2017 Elsevier B.V. This is a final draft version of an article whose final and definitive form has been published by Elsevier. Published in this repository with the kind permission of the publisher.
dc.rights.accesslevelopenAccessfi
dc.subject.ysokuvahaku
dc.subject.ysotiedonhaku
dc.subject.ysokuvat
dc.subject.ysoInternet
jyx.subject.urihttp://www.yso.fi/onto/yso/p26006
jyx.subject.urihttp://www.yso.fi/onto/yso/p2964
jyx.subject.urihttp://www.yso.fi/onto/yso/p1149
jyx.subject.urihttp://www.yso.fi/onto/yso/p20405
dc.relation.doi10.1016/j.neucom.2016.05.118


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record