Mostrar el registro sencillo del ítem
dc.contributor.author
Atencio, Pedro
dc.contributor.author
Sanchez Torres, German
dc.contributor.author
Branch, John
dc.contributor.author
Delrieux, Claudio Augusto
dc.date.available
2020-06-14T22:40:20Z
dc.date.issued
2019-05-13
dc.identifier.citation
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
dc.identifier.issn
1751-9632
dc.identifier.uri
http://hdl.handle.net/11336/107468
dc.description.abstract
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.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Institution of Engineering and Technology
dc.rights
info:eu-repo/semantics/openAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.subject
VIDEO SUMMARIZATION METHOD
dc.subject
TRANSFER LEARNING
dc.subject
DCN
dc.subject.classification
Ciencias de la Computación
dc.subject.classification
Ciencias de la Computación e Información
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS
dc.title
Video summarisation by deep visual and categorical diversity
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2020-05-04T13:31:43Z
dc.identifier.eissn
1751-9640
dc.journal.volume
13
dc.journal.number
6
dc.journal.pagination
569-577
dc.journal.pais
Reino Unido
dc.description.fil
Fil: Atencio, Pedro. Instituto Tecnológico Metropolitano.; Colombia
dc.description.fil
Fil: Sanchez Torres, German. Universidad del Magdalena; Colombia
dc.description.fil
Fil: Branch, John. Universidad Nacional de Colombia. Sede Medellin. Facultad de Minas; Colombia
dc.description.fil
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
dc.journal.title
Iet Computer Vision
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2018.5436
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/ 10.1049/iet-cvi.2018.5436
Archivos asociados