Show simple item record

dc.contributor.authorLinardos, Panagiotis
dc.contributor.authorMohedano, Eva
dc.contributor.authorNieto, Juan Jose
dc.contributor.authorO'Connor, Noel
dc.contributor.authorGiró Nieto, Xavier
dc.contributor.authorMcGuinness, Kevin
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2020-03-06T13:47:42Z
dc.date.issued2019
dc.identifier.citationLinardos, P. [et al.]. Simple vs complex temporal recurrences for video saliency prediction. A: British Machine Vision Conference. "Proceedings of the 30th British Machine Vision Conference". 2019, p. 1-12.
dc.identifier.urihttp://hdl.handle.net/2117/179382
dc.description.abstractThis paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain. The first modification is the addition of a ConvLSTM within the architecture, while the second is a conceptually simple exponential moving average of an internal convolutional state. We use weights pre-trained on the SALICON dataset and fine-tune our model on DHF1K. Our results show that both modifications achieve state-of-the-art results and produce similar saliency maps.
dc.format.extent12 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshComputer vision
dc.subject.lcshDeep learning
dc.subject.otherVideo
dc.subject.otherSaliency
dc.subject.otherComputer vision
dc.subject.otherDeep learning
dc.titleSimple vs complex temporal recurrences for video saliency prediction
dc.typeConference lecture
dc.subject.lemacXarxes neuronals (Informàtica)
dc.subject.lemacVisió per ordinador
dc.subject.lemacAprenentatge profund
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://bmvc2019.org/wp-content/uploads/papers/0952-paper.pdf
dc.rights.accessRestricted access - publisher's policy
local.identifier.drac25837903
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/2PE/TEC2016-75976-R
dc.date.lift10000-01-01
local.citation.authorLinardos, P.; Mohedano, E.; Nieto, J.; O'Connor, N.; Giro, X.; McGuinness, K.
local.citation.contributorBritish Machine Vision Conference
local.citation.publicationNameProceedings of the 30th British Machine Vision Conference
local.citation.startingPage1
local.citation.endingPage12


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record