Vanishing Mask Refinement in Semi-Supervised Video Segmentation

This paper presents a novel architecture, Video Object Segmentation Enhanced with Segment Anything Model, aimed at improving Semi-supervised Video Object Segmentation models by refining each output object mask with fundation models. Video Object Segmentation is a significant focus in the field of co...

Descripción completa

Detalles Bibliográficos
Autores: Pita, Javier, Llerena Caña, Juan Pedro|||0000-0002-3476-6261, Patricio Guisado, Miguel Ángel, Berlanga, Antonio, Usero Aragonés, Luis|||0000-0001-8658-9992
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/64659
Acceso en línea:http://hdl.handle.net/10017/64659
https://dx.doi.org/10.2139/ssrn.4876026
Access Level:acceso abierto
Palabra clave:Video Object Segmentation
Long-Term Videos
Deep Learning
Informática
Computer science
id ES_5b3c5ed450ea4ff74ccf4d6a817169ea
oai_identifier_str oai:ebuah.uah.es:10017/64659
network_acronym_str ES
network_name_str España
repository_id_str
spelling Vanishing Mask Refinement in Semi-Supervised Video SegmentationPita, JavierLlerena Caña, Juan Pedro|||0000-0002-3476-6261Patricio Guisado, Miguel ÁngelBerlanga, AntonioUsero Aragonés, Luis|||0000-0001-8658-9992Video Object SegmentationLong-Term VideosDeep LearningInformáticaComputer scienceThis paper presents a novel architecture, Video Object Segmentation Enhanced with Segment Anything Model, aimed at improving Semi-supervised Video Object Segmentation models by refining each output object mask with fundation models. Video Object Segmentation is a significant focus in the field of computer vision, with object appearance, occlusions, camera movements, or perspective alterations being the main challenge to overcome. This study explores the diverse inputs accepted by Segment Anything Model in order to establish the optimal configuration for our model by intense testing. The results on established video segmentation datasets demonstrate that our proposal enhances the mask outputs of the base model for single object, multi-object, and long video datasets and sets the basis for future exploration by the combination of these two architectures.20242024-06-25journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10017/64659https://dx.doi.org/10.2139/ssrn.4876026reponame:e_Buah Biblioteca Digital Universidad de Alcaláinstname:Universidad de Alcalá (UAH)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:ebuah.uah.es:10017/646592026-06-18T11:13:07Z
dc.title.none.fl_str_mv Vanishing Mask Refinement in Semi-Supervised Video Segmentation
title Vanishing Mask Refinement in Semi-Supervised Video Segmentation
spellingShingle Vanishing Mask Refinement in Semi-Supervised Video Segmentation
Pita, Javier
Video Object Segmentation
Long-Term Videos
Deep Learning
Informática
Computer science
title_short Vanishing Mask Refinement in Semi-Supervised Video Segmentation
title_full Vanishing Mask Refinement in Semi-Supervised Video Segmentation
title_fullStr Vanishing Mask Refinement in Semi-Supervised Video Segmentation
title_full_unstemmed Vanishing Mask Refinement in Semi-Supervised Video Segmentation
title_sort Vanishing Mask Refinement in Semi-Supervised Video Segmentation
dc.creator.none.fl_str_mv Pita, Javier
Llerena Caña, Juan Pedro|||0000-0002-3476-6261
Patricio Guisado, Miguel Ángel
Berlanga, Antonio
Usero Aragonés, Luis|||0000-0001-8658-9992
author Pita, Javier
author_facet Pita, Javier
Llerena Caña, Juan Pedro|||0000-0002-3476-6261
Patricio Guisado, Miguel Ángel
Berlanga, Antonio
Usero Aragonés, Luis|||0000-0001-8658-9992
author_role author
author2 Llerena Caña, Juan Pedro|||0000-0002-3476-6261
Patricio Guisado, Miguel Ángel
Berlanga, Antonio
Usero Aragonés, Luis|||0000-0001-8658-9992
author2_role author
author
author
author
dc.subject.none.fl_str_mv Video Object Segmentation
Long-Term Videos
Deep Learning
Informática
Computer science
topic Video Object Segmentation
Long-Term Videos
Deep Learning
Informática
Computer science
description This paper presents a novel architecture, Video Object Segmentation Enhanced with Segment Anything Model, aimed at improving Semi-supervised Video Object Segmentation models by refining each output object mask with fundation models. Video Object Segmentation is a significant focus in the field of computer vision, with object appearance, occlusions, camera movements, or perspective alterations being the main challenge to overcome. This study explores the diverse inputs accepted by Segment Anything Model in order to establish the optimal configuration for our model by intense testing. The results on established video segmentation datasets demonstrate that our proposal enhances the mask outputs of the base model for single object, multi-object, and long video datasets and sets the basis for future exploration by the combination of these two architectures.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-06-25
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10017/64659
https://dx.doi.org/10.2139/ssrn.4876026
url http://hdl.handle.net/10017/64659
https://dx.doi.org/10.2139/ssrn.4876026
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:e_Buah Biblioteca Digital Universidad de Alcalá
instname:Universidad de Alcalá (UAH)
instname_str Universidad de Alcalá (UAH)
reponame_str e_Buah Biblioteca Digital Universidad de Alcalá
collection e_Buah Biblioteca Digital Universidad de Alcalá
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408783550119936
score 15,812429

Similares en LA Referencia