Show simple item record

dc.contributor.authorAssens, 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.accessioned2019-03-12T10:24:15Z
dc.date.issued2019
dc.identifier.citationAssens, M. [et al.]. PathGAN: visual scanpath prediction with generative adversarial networks. A: Workshop on Egocentric Perception, Interaction and Computing. "Computer Vision: ECCV 2018 Workshops, Munich, Germany, September 8-14, 2018: proceedings, part V". Berlín: Springer, 2019, p. 406-422.
dc.identifier.isbn978-3-030-11021-5
dc.identifier.otherhttps://imatge-upc.github.io/pathgan/
dc.identifier.urihttp://hdl.handle.net/2117/130229
dc.description“This is a post-peer-review, pre-copyedit version of an article published in: Computer Vision – ECCV 2018 Workshops. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-030-11021-5_25”.
dc.description.abstractWe introduce PathGAN, a deep neural network for visual scanpath prediction trained on adversarial examples. A visual scanpath is defined as the sequence of fixation points over an image defined by a human observer with its gaze. PathGAN is composed of two parts, the generator and the discriminator. Both parts extract features from images using off-the-shelf networks, and train recurrent layers to generate or discriminate scanpaths accordingly. In scanpath prediction, the stochastic nature of the data makes it very difficult to generate realistic predictions using supervised learning strategies, but we adopt adversarial training as a suitable alternative. Our experiments prove how PathGAN improves the state of the art of visual scanpath prediction on the iSUN and Salient360! datasets.
dc.format.extent17 p.
dc.language.isoeng
dc.publisherSpringer
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshImage processing--Digital techniques
dc.subject.lcshComputer vision
dc.subject.othersaliency
dc.subject.otherscanpath
dc.subject.otheradversarial training
dc.subject.otherGAN
dc.subject.othercGAN
dc.titlePathGAN: visual scanpath prediction with generative adversarial networks
dc.typeConference lecture
dc.subject.lemacXarxes neuronals (Informàtica)
dc.subject.lemacImatges -- Processament -- Tècniques digitals
dc.subject.lemacVisió per ordinador
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi10.1007/978-3-030-11021-5_25
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://link.springer.com/chapter/10.1007%2F978-3-030-11021-5_25
dc.rights.accessRestricted access - publisher's policy
drac.iddocument23845924
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/2PE/ TEC2016-75976-R
dc.date.lift2020-03
upcommons.citation.authorAssens, M.; Giro, X.; McGuinness, K.; O'Connor, N.
upcommons.citation.contributorWorkshop on Egocentric Perception, Interaction and Computing
upcommons.citation.pubplaceBerlín
upcommons.citation.publishedtrue
upcommons.citation.publicationNameComputer Vision: ECCV 2018 Workshops, Munich, Germany, September 8-14, 2018: proceedings, part V
upcommons.citation.startingPage406
upcommons.citation.endingPage422


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder