Skip to main content

RECONOCIMIENTO VISUAL CON METODOLOGIAS DE APRENDIZAJE DE PRINCIPIO A FIN: MIRANDO LAS PERSONAS Y ENTENDIENDO LAS ESCENAS

TIN2015-66951-C2-2-R

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2015
State Plan 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Management unit Dirección General de Investigación Científica y Técnica
Beneficiary centre FUNDACIO PER A LA UNIVERSITAT OBERTA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

RVOS: end-to-end recurrent network for video object segmentation

  • Ventura Royo, Carles|||0000-0002-3055-339X
  • Bellver, Míriam
  • Girbau Xalabarder, Andreu
  • Salvador Aguilera, Amaia|||0000-0002-9908-1685
  • Marqués Acosta, Fernando|||0000-0001-8311-1168
  • Giró Nieto, Xavier|||0000-0002-9935-5332
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU., This research was supported by the Spanish Ministry ofEconomy and Competitiveness and the European RegionalDevelopment Fund (TIN2015-66951-C2-2-R, TIN2015-65316-P & TEC2016-75976-R), the BSC-CNS SeveroOchoa SEV-2015-0493 and LaCaixa-Severo Ochoa Inter-national Doctoral Fellowship programs, the 2017 SGR 1414and the Industrial Doctorates 2017-DI-064 & 2017-DI-028from the Government of Catalonia, Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

RVOS: end-to-end recurrent network for video object segmentation

  • Ventura Royo, Carles
  • Bellver, Míriam
  • Girbau Xalabarder, Andreu
  • Salvador Aguilera, Amaia
  • Marqués Acosta, Fernando
  • Giró Nieto, Xavier
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU., This research was supported by the Spanish Ministry ofEconomy and Competitiveness and the European RegionalDevelopment Fund (TIN2015-66951-C2-2-R, TIN2015-65316-P & TEC2016-75976-R), the BSC-CNS SeveroOchoa SEV-2015-0493 and LaCaixa-Severo Ochoa Inter-national Doctoral Fellowship programs, the 2017 SGR 1414and the Industrial Doctorates 2017-DI-064 & 2017-DI-028from the Government of Catalonia, Peer Reviewed, Postprint (published version)