Show simple item record

dc.contributor.authorHerrera-Palacio, Alba
dc.contributor.authorVentura, Carles
dc.contributor.authorGiró Nieto, Xavier
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2019-11-12T14:10:42Z
dc.date.issued2019
dc.identifier.citationHerrera-Palacio, A.; Ventura, C.; Giro, X. Video object linguistic grounding. A: International Workshop on Multimodal Understanding and Learning for Embodied Applications. "MULEA '19 1st International Workshop on Multimodal Understanding and Learning for Embodied Applications Nice, France: October 25-25, 2019". New York: Association for Computing Machinery (ACM), 2019, p. 49-51.
dc.identifier.isbn978-1-4503-6918-3
dc.identifier.otherhttps://imatge.upc.edu/web/publications/video-object-linguistic-grounding
dc.identifier.urihttp://hdl.handle.net/2117/172234
dc.description.abstractThe goal of this work is segmenting on a video sequence the objects which are mentioned in a linguistic description of the scene. We have adapted an existing deep neural network that achieves state of the art performance in semi-supervised video object segmentation, to add a linguistic branch that would generate an attention map over the video frames, making the segmentation of the objects temporally consistent along the sequence.
dc.format.extent3 p.
dc.language.isoeng
dc.publisherAssociation for Computing Machinery (ACM)
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshLinguistics
dc.subject.lcshImage processing -- Digital techniques
dc.subject.otherVideo object gounding
dc.subject.otherNeural networks
dc.subject.otherLinguistics
dc.titleVideo object linguistic grounding
dc.typeConference lecture
dc.subject.lemacXarxes neuronals (Informàtica) -- Aplicacions
dc.subject.lemacLingüística
dc.subject.lemacImatges -- Processament -- Tècniques digitals
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi10.1145/3347450.3357662
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://dl.acm.org/citation.cfm?id=3357662
dc.rights.accessRestricted access - publisher's policy
local.identifier.drac25894716
dc.description.versionPostprint (published version)
dc.date.lift10000-01-01
local.citation.authorHerrera-Palacio, A.; Ventura, C.; Giro, X.
local.citation.contributorInternational Workshop on Multimodal Understanding and Learning for Embodied Applications
local.citation.pubplaceNew York
local.citation.publicationNameMULEA '19 1st International Workshop on Multimodal Understanding and Learning for Embodied Applications Nice, France: October 25-25, 2019
local.citation.startingPage49
local.citation.endingPage51


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record