Video summarisation by deep visual and categorical diversity

Autores
Atencio, Pedro; Sanchez Torres, German; Branch, John; Delrieux, Claudio Augusto
Año de publicación
2019
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The authors propose a video-summarisation method based on visual and categorical diversities using pre-trained deep visual and categorical models. Their method extracts visual and categorical features from a pre-trained deep convolutional network (DCN) and a pre-trained word-embedding matrix. Using visual and categorical information they obtain a video diversity estimation, which is used as an importance score to select segments from the input video that best describes it. Their method also allows performing queries during the search process, in this way personalising the resulting video summaries according to the particular intended purposes. The performance of the method is evaluated using different pre-trained DCN models in order to select the architecture with the best throughput. They then compare it with other state-of-the-art proposals in video summarisation using a data-driven approach with the public dataset SumMe, which contains annotated videos with per-fragment importance. The results show that their method outperforms other proposals in most of the examples. As an additional advantage, their method requires a simple and direct implementation that does not require a training stage.
Fil: Atencio, Pedro. Instituto Tecnológico Metropolitano.; Colombia
Fil: Sanchez Torres, German. Universidad del Magdalena; Colombia
Fil: Branch, John. Universidad Nacional de Colombia. Sede Medellin. Facultad de Minas; Colombia
Fil: Delrieux, Claudio Augusto. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina
Materia
VIDEO SUMMARIZATION METHOD
TRANSFER LEARNING
DCN
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/107468
Acceder
id CONICETDig_f823a3138f33d992f3e7b1bb2c84fc9e
oai_identifier_str oai:ri.conicet.gov.ar:11336/107468
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Video summarisation by deep visual and categorical diversityAtencio, PedroSanchez Torres, GermanBranch, JohnDelrieux, Claudio AugustoVIDEO SUMMARIZATION METHODTRANSFER LEARNINGDCNhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1The authors propose a video-summarisation method based on visual and categorical diversities using pre-trained deep visual and categorical models. Their method extracts visual and categorical features from a pre-trained deep convolutional network (DCN) and a pre-trained word-embedding matrix. Using visual and categorical information they obtain a video diversity estimation, which is used as an importance score to select segments from the input video that best describes it. Their method also allows performing queries during the search process, in this way personalising the resulting video summaries according to the particular intended purposes. The performance of the method is evaluated using different pre-trained DCN models in order to select the architecture with the best throughput. They then compare it with other state-of-the-art proposals in video summarisation using a data-driven approach with the public dataset SumMe, which contains annotated videos with per-fragment importance. The results show that their method outperforms other proposals in most of the examples. As an additional advantage, their method requires a simple and direct implementation that does not require a training stage.Fil: Atencio, Pedro. Instituto Tecnológico Metropolitano.; ColombiaFil: Sanchez Torres, German. Universidad del Magdalena; ColombiaFil: Branch, John. Universidad Nacional de Colombia. Sede Medellin. Facultad de Minas; ColombiaFil: Delrieux, Claudio Augusto. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; ArgentinaInstitution of Engineering and Technology2019-05-13info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/107468Atencio, Pedro; Sanchez Torres, German; Branch, John; Delrieux, Claudio Augusto; Video summarisation by deep visual and categorical diversity; Institution of Engineering and Technology; Iet Computer Vision; 13; 6; 13-5-2019; 569-5771751-96321751-9640CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2018.5436info:eu-repo/semantics/altIdentifier/doi/ 10.1049/iet-cvi.2018.5436info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T09:44:27Zoai:ri.conicet.gov.ar:11336/107468instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 09:44:28.184CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Video summarisation by deep visual and categorical diversity
title Video summarisation by deep visual and categorical diversity
spellingShingle Video summarisation by deep visual and categorical diversity
Atencio, Pedro
VIDEO SUMMARIZATION METHOD
TRANSFER LEARNING
DCN
title_short Video summarisation by deep visual and categorical diversity
title_full Video summarisation by deep visual and categorical diversity
title_fullStr Video summarisation by deep visual and categorical diversity
title_full_unstemmed Video summarisation by deep visual and categorical diversity
title_sort Video summarisation by deep visual and categorical diversity
dc.creator.none.fl_str_mv Atencio, Pedro
Sanchez Torres, German
Branch, John
Delrieux, Claudio Augusto
author Atencio, Pedro
author_facet Atencio, Pedro
Sanchez Torres, German
Branch, John
Delrieux, Claudio Augusto
author_role author
author2 Sanchez Torres, German
Branch, John
Delrieux, Claudio Augusto
author2_role author
author
author
dc.subject.none.fl_str_mv VIDEO SUMMARIZATION METHOD
TRANSFER LEARNING
DCN
topic VIDEO SUMMARIZATION METHOD
TRANSFER LEARNING
DCN
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv The authors propose a video-summarisation method based on visual and categorical diversities using pre-trained deep visual and categorical models. Their method extracts visual and categorical features from a pre-trained deep convolutional network (DCN) and a pre-trained word-embedding matrix. Using visual and categorical information they obtain a video diversity estimation, which is used as an importance score to select segments from the input video that best describes it. Their method also allows performing queries during the search process, in this way personalising the resulting video summaries according to the particular intended purposes. The performance of the method is evaluated using different pre-trained DCN models in order to select the architecture with the best throughput. They then compare it with other state-of-the-art proposals in video summarisation using a data-driven approach with the public dataset SumMe, which contains annotated videos with per-fragment importance. The results show that their method outperforms other proposals in most of the examples. As an additional advantage, their method requires a simple and direct implementation that does not require a training stage.
Fil: Atencio, Pedro. Instituto Tecnológico Metropolitano.; Colombia
Fil: Sanchez Torres, German. Universidad del Magdalena; Colombia
Fil: Branch, John. Universidad Nacional de Colombia. Sede Medellin. Facultad de Minas; Colombia
Fil: Delrieux, Claudio Augusto. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca; Argentina
description The authors propose a video-summarisation method based on visual and categorical diversities using pre-trained deep visual and categorical models. Their method extracts visual and categorical features from a pre-trained deep convolutional network (DCN) and a pre-trained word-embedding matrix. Using visual and categorical information they obtain a video diversity estimation, which is used as an importance score to select segments from the input video that best describes it. Their method also allows performing queries during the search process, in this way personalising the resulting video summaries according to the particular intended purposes. The performance of the method is evaluated using different pre-trained DCN models in order to select the architecture with the best throughput. They then compare it with other state-of-the-art proposals in video summarisation using a data-driven approach with the public dataset SumMe, which contains annotated videos with per-fragment importance. The results show that their method outperforms other proposals in most of the examples. As an additional advantage, their method requires a simple and direct implementation that does not require a training stage.
publishDate 2019
dc.date.none.fl_str_mv 2019-05-13
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/107468
Atencio, Pedro; Sanchez Torres, German; Branch, John; Delrieux, Claudio Augusto; Video summarisation by deep visual and categorical diversity; Institution of Engineering and Technology; Iet Computer Vision; 13; 6; 13-5-2019; 569-577
1751-9632
1751-9640
CONICET Digital
CONICET
url http://hdl.handle.net/11336/107468
identifier_str_mv Atencio, Pedro; Sanchez Torres, German; Branch, John; Delrieux, Claudio Augusto; Video summarisation by deep visual and categorical diversity; Institution of Engineering and Technology; Iet Computer Vision; 13; 6; 13-5-2019; 569-577
1751-9632
1751-9640
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2018.5436
info:eu-repo/semantics/altIdentifier/doi/ 10.1049/iet-cvi.2018.5436
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Institution of Engineering and Technology
publisher.none.fl_str_mv Institution of Engineering and Technology
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842268667821162496
score 13.13397

Publicaciones similares