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.accessioned2018-03-07T10:35:12Z
dc.date.available2018-03-07T10:35:12Z
dc.date.issued2018
dc.identifier.citationAssens, M., Giro, X., McGuinness, K., O'Connor, N. SaltiNet: scan-path prediction on 360 degree images using saliency volumes. A: International Workshop on Egocentric Perception, Interaction and Computing. "2017 IEEE International Conference on Computer Vision Workshops (ICCVW)". IEEE Press, 23/01/2018, p. 2331-2338.
dc.identifier.isbn978-1-5386-1034-3
dc.identifier.otherhttps://arxiv.org/abs/1707.03123
dc.identifier.urihttp://hdl.handle.net/2117/114891
dc.description.abstractWe introduce SaltiNet, a deep neural network for scan-path prediction trained on 360-degree images. The model 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 computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency volumes. Sampling strategies over these volumes are used to generate scan-paths over the 360-degree images. Our experiments show the advantages of using saliency volumes, and how they can be used for related tasks. Our source code and trained models available at https://github.com/massens/saliency-360salient-2017.
dc.format.extent8 p.
dc.language.isoeng
dc.publisherIEEE Press
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Representació del coneixement
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.lcshArtificial vision
dc.subject.lcshArtificial intelligence
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshComputer vision
dc.subject.othersaliency prediction
dc.subject.otherscanpath
dc.subject.othereye gaze
dc.subject.othercomputer vision
dc.subject.otherdeep learning
dc.subject.otherconvolutional neural networks
dc.titleSaltiNet: scan-path prediction on 360 degree images using saliency volumes
dc.typeConference lecture
dc.subject.lemacImatges -- Processament -- Tècniques digitals
dc.subject.lemacVisió artificial (Robòtica)
dc.subject.lemacVisió per ordinador
dc.subject.lemacIntel·ligència artificial
dc.subject.lemacXarxes neuronals (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi10.1109/ICCVW.2017.275
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://ieeexplore.ieee.org/document/8265485/
dc.rights.accessOpen Access
local.identifier.drac21999164
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO//TEC2013-43935-R/ES/PROCESADO DE INFORMACION HETEROGENEA Y SEÑALES EN GRAFOS PARA BIG DATA. APLICACION EN CRIBADO DE ALTO RENDIMIENTO, TELEDETECCION, MULTIMEDIA Y HCI./
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/PE2016-2020/TEC2016-75976-R
local.citation.authorAssens, M.; Giro, X.; McGuinness, K.; O'Connor, N.
local.citation.contributorInternational Workshop on Egocentric Perception, Interaction and Computing
local.citation.publicationName2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
local.citation.startingPage2331
local.citation.endingPage2338


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record