Mostrar el registro sencillo del ítem
dc.contributor.author | Bolaños, Marc | es_ES |
dc.contributor.author | Peris-Abril, Álvaro | es_ES |
dc.contributor.author | Casacuberta Nolla, Francisco | es_ES |
dc.contributor.author | Soler, Sergi | es_ES |
dc.contributor.author | Radeva, Petia | es_ES |
dc.date.accessioned | 2020-04-29T07:04:13Z | |
dc.date.available | 2020-04-29T07:04:13Z | |
dc.date.issued | 2018-01 | es_ES |
dc.identifier.issn | 1047-3203 | es_ES |
dc.identifier.uri | http://hdl.handle.net/10251/141941 | |
dc.description.abstract | [EN] Egocentric vision consists in acquiring images along the day from a first person point-of-view using wearable cameras. The automatic analysis of this information allows to discover daily patterns for improving the quality of life of the user. A natural topic that arises in egocentric vision is storytelling, that is, how to understand and tell the story relying behind the pictures. In this paper, we tackle storytelling as an egocentric sequences description problem. We propose a novel methodology that exploits information from temporally neighboring events, matching precisely the nature of egocentric sequences. Furthermore, we present a new method for multimodal data fusion consisting on a multi-input attention recurrent network. We also release the EDUB-SegDesc dataset. This is the first dataset for egocentric image sequences description, consisting of 1339 events with 3991 descriptions, from 55¿days acquired by 11 people. Finally, we prove that our proposal outperforms classical attentional encoder-decoder methods for video description. | es_ES |
dc.description.sponsorship | This work was partially founded by TIN2015-66951-C2, SGR 1219, CERCA, Grant 20141510 (Marato TV3), PrometeoII/2014/030 and R-MIPRCV network (TIN2014-54728-REDC). Petia Radeva is partially founded by ICREA Academia'2014. Marc Bolanos is partially founded by an FPU fellowship. We gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan X GPU used for this research. The funders had no role in the study design, data collection, analysis, and preparation of the manuscript. | es_ES |
dc.language | Inglés | es_ES |
dc.publisher | Elsevier | es_ES |
dc.relation.ispartof | Journal of Visual Communication and Image Representation | es_ES |
dc.rights | Reconocimiento - No comercial - Sin obra derivada (by-nc-nd) | es_ES |
dc.subject | Egocentric vision | es_ES |
dc.subject | Video description | es_ES |
dc.subject | Deep learning | es_ES |
dc.subject | Multi-modal learning | es_ES |
dc.subject.classification | LENGUAJES Y SISTEMAS INFORMATICOS | es_ES |
dc.title | Egocentric video description based on temporally-linked sequences | es_ES |
dc.type | Artículo | es_ES |
dc.identifier.doi | 10.1016/j.jvcir.2017.11.022 | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/MINECO//TIN2015-66951-C2/ | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/AGAUR//2014-SGR-1219/ES/Computer Vision at the Universitat de Barcelona | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/MINECO//TIN2014-54728-REDC/ES/RED DE EXCELENCIA MULTIMODAL INTERACTION IN PATTERN RECOGNITION AND COMPUTER VISION/ | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/GVA//PROMETEOII%2F2014%2F030/ES/ Adaptive learning and multimodality in machine translation and text transcription/ | es_ES |
dc.rights.accessRights | Abierto | es_ES |
dc.contributor.affiliation | Universitat Politècnica de València. Departamento de Sistemas Informáticos y Computación - Departament de Sistemes Informàtics i Computació | es_ES |
dc.description.bibliographicCitation | Bolaños, M.; Peris-Abril, Á.; Casacuberta Nolla, F.; Soler, S.; Radeva, P. (2018). Egocentric video description based on temporally-linked sequences. Journal of Visual Communication and Image Representation. 50:205-216. https://doi.org/10.1016/j.jvcir.2017.11.022 | es_ES |
dc.description.accrualMethod | S | es_ES |
dc.relation.publisherversion | https://doi.org/10.1016/j.jvcir.2017.11.022 | es_ES |
dc.description.upvformatpinicio | 205 | es_ES |
dc.description.upvformatpfin | 216 | es_ES |
dc.type.version | info:eu-repo/semantics/publishedVersion | es_ES |
dc.description.volume | 50 | es_ES |
dc.relation.pasarela | S\349208 | es_ES |
dc.contributor.funder | Generalitat Valenciana | es_ES |
dc.contributor.funder | Universitat de Barcelona | es_ES |
dc.contributor.funder | Centres de Recerca de Catalunya | es_ES |
dc.contributor.funder | Ministerio de Economía y Competitividad | es_ES |
dc.contributor.funder | Institució Catalana de Recerca i Estudis Avançats | es_ES |
dc.contributor.funder | Agencia de Gestión de Ayudas Universitarias y de Investigación |