A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval
Autor(a) principal: | |
---|---|
Data de Publicação: | 2015 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1186/s13640-015-0081-6 http://hdl.handle.net/11449/167952 |
Resumo: | The interaction of users with search services has been recognized as an important mechanism for expressing and handling user information needs. One traditional approach for supporting such interactive search relies on exploiting relevance feedbacks (RF) in the searching process. For large-scale multimedia collections, however, the user efforts required in RF search sessions is considerable. In this paper, we address this issue by proposing a novel semi-supervised approach for implementing RF-based search services. In our approach, supervised learning is performed taking advantage of relevance labels provided by users. Later, an unsupervised learning step is performed with the objective of extracting useful information from the intrinsic dataset structure. Furthermore, our hybrid learning approach considers feedbacks of different users, in collaborative image retrieval (CIR) scenarios. In these scenarios, the relationships among the feedbacks provided by different users are exploited, further reducing the collective efforts. Conducted experiments involving shape, color, and texture datasets demonstrate the effectiveness of the proposed approach. Similar results are also observed in experiments considering multimodal image retrieval tasks. |
id |
UNSP_603aa2ce2af67567d498c78389707fc7 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/167952 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrievalCollaborative image retrievalContent-based image retrievalRecommendationRelevance feedbackSemi-supervised learningThe interaction of users with search services has been recognized as an important mechanism for expressing and handling user information needs. One traditional approach for supporting such interactive search relies on exploiting relevance feedbacks (RF) in the searching process. For large-scale multimedia collections, however, the user efforts required in RF search sessions is considerable. In this paper, we address this issue by proposing a novel semi-supervised approach for implementing RF-based search services. In our approach, supervised learning is performed taking advantage of relevance labels provided by users. Later, an unsupervised learning step is performed with the objective of extracting useful information from the intrinsic dataset structure. Furthermore, our hybrid learning approach considers feedbacks of different users, in collaborative image retrieval (CIR) scenarios. In these scenarios, the relationships among the feedbacks provided by different users are exploited, further reducing the collective efforts. Conducted experiments involving shape, color, and texture datasets demonstrate the effectiveness of the proposed approach. Similar results are also observed in experiments considering multimodal image retrieval tasks.Department of Statistics, Applied Mathematics and Computing - State University of São Paulo (UNESP)Recod Lab - Institute of Computing, University of Campinas (UNICAMP)Department of Exact Sciences, University of Feira de Santana (UEFS), BADepartment of Statistics, Applied Mathematics and Computing - State University of São Paulo (UNESP)Universidade Estadual Paulista (Unesp)Universidade Estadual de Campinas (UNICAMP)Guimarães Pedronette, Daniel Carlos [UNESP]Calumby, Rodrigo T.Torres, Ricardo da S.2018-12-11T16:39:00Z2018-12-11T16:39:00Z2015-12-11info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://dx.doi.org/10.1186/s13640-015-0081-6Eurasip Journal on Image and Video Processing, v. 2015, n. 1, 2015.1687-52811687-5176http://hdl.handle.net/11449/16795210.1186/s13640-015-0081-62-s2.0-849388796192-s2.0-84938879619.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEurasip Journal on Image and Video Processing0,4090,409info:eu-repo/semantics/openAccess2023-11-24T06:16:59Zoai:repositorio.unesp.br:11449/167952Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T18:38:08.657074Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval |
title |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval |
spellingShingle |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval Guimarães Pedronette, Daniel Carlos [UNESP] Collaborative image retrieval Content-based image retrieval Recommendation Relevance feedback Semi-supervised learning |
title_short |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval |
title_full |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval |
title_fullStr |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval |
title_full_unstemmed |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval |
title_sort |
A semi-supervised learning algorithm for relevance feedback and collaborative image retrieval |
author |
Guimarães Pedronette, Daniel Carlos [UNESP] |
author_facet |
Guimarães Pedronette, Daniel Carlos [UNESP] Calumby, Rodrigo T. Torres, Ricardo da S. |
author_role |
author |
author2 |
Calumby, Rodrigo T. Torres, Ricardo da S. |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Universidade Estadual de Campinas (UNICAMP) |
dc.contributor.author.fl_str_mv |
Guimarães Pedronette, Daniel Carlos [UNESP] Calumby, Rodrigo T. Torres, Ricardo da S. |
dc.subject.por.fl_str_mv |
Collaborative image retrieval Content-based image retrieval Recommendation Relevance feedback Semi-supervised learning |
topic |
Collaborative image retrieval Content-based image retrieval Recommendation Relevance feedback Semi-supervised learning |
description |
The interaction of users with search services has been recognized as an important mechanism for expressing and handling user information needs. One traditional approach for supporting such interactive search relies on exploiting relevance feedbacks (RF) in the searching process. For large-scale multimedia collections, however, the user efforts required in RF search sessions is considerable. In this paper, we address this issue by proposing a novel semi-supervised approach for implementing RF-based search services. In our approach, supervised learning is performed taking advantage of relevance labels provided by users. Later, an unsupervised learning step is performed with the objective of extracting useful information from the intrinsic dataset structure. Furthermore, our hybrid learning approach considers feedbacks of different users, in collaborative image retrieval (CIR) scenarios. In these scenarios, the relationships among the feedbacks provided by different users are exploited, further reducing the collective efforts. Conducted experiments involving shape, color, and texture datasets demonstrate the effectiveness of the proposed approach. Similar results are also observed in experiments considering multimodal image retrieval tasks. |
publishDate |
2015 |
dc.date.none.fl_str_mv |
2015-12-11 2018-12-11T16:39:00Z 2018-12-11T16:39:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1186/s13640-015-0081-6 Eurasip Journal on Image and Video Processing, v. 2015, n. 1, 2015. 1687-5281 1687-5176 http://hdl.handle.net/11449/167952 10.1186/s13640-015-0081-6 2-s2.0-84938879619 2-s2.0-84938879619.pdf |
url |
http://dx.doi.org/10.1186/s13640-015-0081-6 http://hdl.handle.net/11449/167952 |
identifier_str_mv |
Eurasip Journal on Image and Video Processing, v. 2015, n. 1, 2015. 1687-5281 1687-5176 10.1186/s13640-015-0081-6 2-s2.0-84938879619 2-s2.0-84938879619.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Eurasip Journal on Image and Video Processing 0,409 0,409 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128956893757440 |