Show simple item record

dc.contributor.authorAssens Reina, Marc
dc.contributor.authorGiró Nieto, Xavier
dc.contributor.authorMcGuinness, Kevin
dc.contributor.authorO'Connor, Noel
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2018-07-16T08:16:15Z
dc.date.available2022-06-01T00:36:08Z
dc.date.issued2018-06-23
dc.identifier.citationAssens, M., Giro, X., McGuinness, K., O'Connor, N. Scanpath and saliency prediction on 360 degree images. "Signal processing: image communication", 23 Juny 2018, vol. 69, p. 8-14.
dc.identifier.issn0923-5965
dc.identifier.otherhttps://imatge.upc.edu/web/publications/scanpath-and-saliency-prediction-360-degree-images
dc.identifier.urihttp://hdl.handle.net/2117/119346
dc.description.abstractWe introduce deep neural networks for scanpath and saliency prediction trained on 360-degree images. The scanpath prediction model called SaltiNet is based on a temporal-aware novel representation of saliency information named the saliency volume. The first part of the network consists of a model trained to generate saliency volumes, whose parameters are fit by back-propagation using a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes. Sampling strategies over these volumes are used to generate scanpaths over the 360-degree images. Our experiments show the advantages of using saliency volumes, and how they can be used for related tasks. We also show how a similar architecture achieves state-of-the-art performance for the related task of saliency map prediction. Our source code and trained models available at https://github.com/massens/saliency-360salient-2017.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
dc.subject.lcshImage processing--Digital techniques
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshArtificial intelligence
dc.subject.lcshThree-dimensional imaging
dc.subject.lcshMachine learning
dc.subject.otherdeep learning
dc.subject.othermachine learning
dc.subject.othersaliency
dc.subject.otherscanpath
dc.subject.othervisual attention
dc.titleScanpath and saliency prediction on 360 degree images
dc.typeArticle
dc.subject.lemacImatges -- Processament -- Tècniques digitals
dc.subject.lemacXarxes neuronals (Informàtica)
dc.subject.lemacIntel·ligència artificial
dc.subject.lemacImatges tridimensionals
dc.subject.lemacAprenentatge automàtic
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi10.1016/j.image.2018.06.006
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://www.sciencedirect.com/science/article/pii/S0923596518306209
dc.rights.accessOpen Access
local.identifier.drac23234728
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/2PE/TEC2016-75976-R
local.citation.authorAssens, M.; Giro, X.; McGuinness, K.; O'Connor, N.
local.citation.publicationNameSignal processing: image communication
local.citation.volume69
local.citation.startingPage8
local.citation.endingPage14


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record