Mostrar el registro sencillo del ítem

dc.contributor.authorFernandez-Beltran, Ruben
dc.contributor.authorPla, Filiberto
dc.date.accessioned2018-07-05T15:40:53Z
dc.date.available2018-07-05T15:40:53Z
dc.date.issued2018
dc.identifier.citationFERNANDEZ-BELTRAN, Ruben; PLA, Filiberto. Sparse multi-modal probabilistic latent semantic analysis for single-image super-resolution. Signal Processing, 2018, vol. 152, p. 227-237ca_CA
dc.identifier.issn0165-1684
dc.identifier.urihttp://hdl.handle.net/10234/175491
dc.description.abstractThis paper presents a novel single-image super-resolution (SR) approach based on latent topics in order to take advantage of the semantics pervading the topic space when super-resolving images. Image semantics has shown to be useful to relieve the ill-posed nature of the SR problem, however the most accepted clustering-based approach used to define semantic concepts limits the capability of representing complex visual relationships. The proposed approach provides a new probabilistic perspective where the SR process is performed according to the semantics encapsulated by a new topic model, the Sparse Multimodal probabilistic Latent Semantic Analysis (sMpLSA). Firstly, the sMpLSA model is formulated. Subsequently, a new SR framework based on sMpLSA is defined. Finally, an experimental comparison is conducted using seven learningbased SR methods over three different image datasets. Experiments reveal the potential of latent topics in SR by reporting that the proposed approach is able to provide a competitive performance.ca_CA
dc.format.extent30 p.ca_CA
dc.format.mimetypeapplication/pdfca_CA
dc.language.isoengca_CA
dc.publisherElsevierca_CA
dc.relation.isPartOfSignal Processing, 2018, vol. 152, p. 227-237ca_CA
dc.rights.urihttp://rightsstatements.org/vocab/CNE/1.0/*
dc.subjectSuper-Resolutionca_CA
dc.subjectLatent Topicsca_CA
dc.subjectprobabilistic latent semantic analysisca_CA
dc.subjectimage learningca_CA
dc.subjectimage quality assessmentca_CA
dc.titleSparse Multi-modal probabilistic Latent Semantic Analysis for Single-Image Super-Resolutionca_CA
dc.typeinfo:eu-repo/semantics/articleca_CA
dc.identifier.doihttps://doi.org/10.1016/j.sigpro.2018.05.026
dc.relation.projectIDThis work was supported by the Spanish Ministry of Economy under the projects ESP2013-48458-C4-3-P and ESP2016-79503-C2-2-P, by Generalitat Valenciana through the PROMETEO-II/2014/062 project and the APOSTD/2017/007 contract, and by Universitat Jaume I under the P11B2014-09 project.ca_CA
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessca_CA
dc.relation.publisherVersionhttps://www.sciencedirect.com/science/article/pii/S0165168418301944ca_CA
dc.type.versioninfo:eu-repo/semantics/submittedVersionca_CA


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

  • INIT_Articles [745]
  • LSI_Articles [361]
    Articles de publicacions periòdiques escrits per professors del Departament de Llenguatges i Sistemes Informàtics

Mostrar el registro sencillo del ítem