Mostra el registre d'ítem simple
Structured prediction with output embeddings for semantic image annotation
dc.contributor.author | Quattoni, Ariadna Julieta |
dc.contributor.author | Ramisa Ayats, Arnau |
dc.contributor.author | Madhyastha, Pranava S. |
dc.contributor.author | Simó Serra, Edgar |
dc.contributor.author | Moreno-Noguer, Francesc |
dc.contributor.other | Institut de Robòtica i Informàtica Industrial |
dc.date.accessioned | 2017-05-29T13:43:38Z |
dc.date.available | 2017-05-29T13:43:38Z |
dc.date.issued | 2016 |
dc.identifier.citation | Quattoni, A.J., Ramisa , A., Madhyastha, P.S., Simo, E., Moreno-Noguer, F. Structured prediction with output embeddings for semantic image annotation. A: Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies. "2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference". San Diego, CA: 2016, p. 552-557. |
dc.identifier.isbn | 9781941643914 |
dc.identifier.uri | http://hdl.handle.net/2117/105004 |
dc.description.abstract | We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge. We propose handling this sparsity by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model. |
dc.format.extent | 6 p. |
dc.language.iso | eng |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 Spain |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Automàtica i control |
dc.subject.other | Computational linguistics |
dc.subject.other | Linguistics |
dc.subject.other | Regression analysis |
dc.subject.other | Data sparsity |
dc.subject.other | Embeddings |
dc.subject.other | Feature representation |
dc.subject.other | Loglinear model |
dc.subject.other | Semantic imatge annotations |
dc.subject.other | Structured prediction |
dc.subject.other | computer vision |
dc.subject.other | natural language processing |
dc.title | Structured prediction with output embeddings for semantic image annotation |
dc.type | Conference report |
dc.contributor.group | Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI |
dc.description.peerreviewed | Peer Reviewed |
dc.subject.inspec | Classificació INSPEC::Control theory::Predictive control |
dc.relation.publisherversion | https://aclweb.org/anthology/N/N16/N16-1068.pdf |
dc.rights.access | Open Access |
local.identifier.drac | 19286576 |
dc.description.version | Postprint (author's final draft) |
local.citation.author | Quattoni, A.J.; Ramisa, A.; Madhyastha, P.S.; Simo, E.; Moreno-Noguer, F. |
local.citation.contributor | Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies |
local.citation.pubplace | San Diego, CA |
local.citation.publicationName | 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference |
local.citation.startingPage | 552 |
local.citation.endingPage | 557 |