Zobrazit v EDS

Shot Boundary Detection with 3D Depthwise Convolutions and Visual Attention

Uloženo v:
Podrobná bibliografie
Název: Shot Boundary Detection with 3D Depthwise Convolutions and Visual Attention
Autoři: Esteve Brotons, Miguel José, Lucendo, Francisco Javier, Rodríguez Juan, Javier, Garcia-Rodriguez, Jose
Přispěvatelé: Universidad de Alicante. Departamento de Tecnología Informática y Computación, Arquitecturas Inteligentes Aplicadas (AIA)
Informace o vydavateli: MDPI
Rok vydání: 2023
Sbírka: RUA - Repositorio Institucional de la Universidad de Alicante
Témata: Shot boundary detection, 3D convolution, Depthwise convolution, Visual attention
Popis: Shot boundary detection is the process of identifying and locating the boundaries between individual shots in a video sequence. A shot is a continuous sequence of frames that are captured by a single camera, without any cuts or edits. Recent investigations have shown the effectiveness of the use of 3D convolutional networks to solve this task due to its high capacity to extract spatiotemporal features of the video and determine in which frame a transition or shot change occurs. When this task is used as part of a scene segmentation use case with the aim of improving the experience of viewing content from streaming platforms, the speed of segmentation is very important for live and near-live use cases such as start-over. The problem with models based on 3D convolutions is the large number of parameters that they entail. Standard 3D convolutions impose much higher CPU and memory requirements than do the same 2D operations. In this paper, we rely on depthwise separable convolutions to address the problem but with a scheme that significantly reduces the number of parameters. To compensate for the slight loss of performance, we analyze and propose the use of visual self-attention as a mechanism of improvement. ; We would like to thank “A way of making Europe” European Regional Development Fund (ERDF) and MCIN/AEI/10.13039/501100011033 for supporting this work under the TED2021-130890B (CHAN-TWIN) research project funded by MCIN/AEI /10.13039 /501100011033 and European Union NextGenerationEU/ PRTR. Additionally, the HORIZON-MSCA-2021-SE-0 action number: 101086387, REMARKABLE, Rural Environmental Monitoring via ultra wide-ARea networKs And distriButed federated Learning.
Druh dokumentu: article in journal/newspaper
Jazyk: English
Relation: https://doi.org/10.3390/s23167022; info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/TED2021-130890B-C21; info:eu-repo/grantAgreement/EC/HE/101086387; http://hdl.handle.net/10045/136718
DOI: 10.3390/s23167022
Dostupnost: http://hdl.handle.net/10045/136718
https://doi.org/10.3390/s23167022
Rights: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). ; info:eu-repo/semantics/openAccess
Přístupové číslo: edsbas.FBD6441D
Databáze: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: http://hdl.handle.net/10045/136718#
    Name: EDS - BASE (s4221598)
    Category: fullText
    Text: View record from BASE
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Brotons%20E
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsbas
DbLabel: BASE
An: edsbas.FBD6441D
RelevancyScore: 944
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 943.653564453125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Shot Boundary Detection with 3D Depthwise Convolutions and Visual Attention
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Esteve+Brotons%2C+Miguel+José%22">Esteve Brotons, Miguel José</searchLink><br /><searchLink fieldCode="AR" term="%22Lucendo%2C+Francisco+Javier%22">Lucendo, Francisco Javier</searchLink><br /><searchLink fieldCode="AR" term="%22Rodríguez+Juan%2C+Javier%22">Rodríguez Juan, Javier</searchLink><br /><searchLink fieldCode="AR" term="%22Garcia-Rodriguez%2C+Jose%22">Garcia-Rodriguez, Jose</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Universidad de Alicante. Departamento de Tecnología Informática y Computación<br />Arquitecturas Inteligentes Aplicadas (AIA)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: MDPI
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2023
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: RUA - Repositorio Institucional de la Universidad de Alicante
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Shot+boundary+detection%22">Shot boundary detection</searchLink><br /><searchLink fieldCode="DE" term="%223D+convolution%22">3D convolution</searchLink><br /><searchLink fieldCode="DE" term="%22Depthwise+convolution%22">Depthwise convolution</searchLink><br /><searchLink fieldCode="DE" term="%22Visual+attention%22">Visual attention</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Shot boundary detection is the process of identifying and locating the boundaries between individual shots in a video sequence. A shot is a continuous sequence of frames that are captured by a single camera, without any cuts or edits. Recent investigations have shown the effectiveness of the use of 3D convolutional networks to solve this task due to its high capacity to extract spatiotemporal features of the video and determine in which frame a transition or shot change occurs. When this task is used as part of a scene segmentation use case with the aim of improving the experience of viewing content from streaming platforms, the speed of segmentation is very important for live and near-live use cases such as start-over. The problem with models based on 3D convolutions is the large number of parameters that they entail. Standard 3D convolutions impose much higher CPU and memory requirements than do the same 2D operations. In this paper, we rely on depthwise separable convolutions to address the problem but with a scheme that significantly reduces the number of parameters. To compensate for the slight loss of performance, we analyze and propose the use of visual self-attention as a mechanism of improvement. ; We would like to thank “A way of making Europe” European Regional Development Fund (ERDF) and MCIN/AEI/10.13039/501100011033 for supporting this work under the TED2021-130890B (CHAN-TWIN) research project funded by MCIN/AEI /10.13039 /501100011033 and European Union NextGenerationEU/ PRTR. Additionally, the HORIZON-MSCA-2021-SE-0 action number: 101086387, REMARKABLE, Rural Environmental Monitoring via ultra wide-ARea networKs And distriButed federated Learning.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article in journal/newspaper
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://doi.org/10.3390/s23167022; info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/TED2021-130890B-C21; info:eu-repo/grantAgreement/EC/HE/101086387; http://hdl.handle.net/10045/136718
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3390/s23167022
– Name: URL
  Label: Availability
  Group: URL
  Data: http://hdl.handle.net/10045/136718<br />https://doi.org/10.3390/s23167022
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). ; info:eu-repo/semantics/openAccess
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.FBD6441D
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.FBD6441D
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/s23167022
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Shot boundary detection
        Type: general
      – SubjectFull: 3D convolution
        Type: general
      – SubjectFull: Depthwise convolution
        Type: general
      – SubjectFull: Visual attention
        Type: general
    Titles:
      – TitleFull: Shot Boundary Detection with 3D Depthwise Convolutions and Visual Attention
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Esteve Brotons, Miguel José
      – PersonEntity:
          Name:
            NameFull: Lucendo, Francisco Javier
      – PersonEntity:
          Name:
            NameFull: Rodríguez Juan, Javier
      – PersonEntity:
          Name:
            NameFull: Garcia-Rodriguez, Jose
      – PersonEntity:
          Name:
            NameFull: Universidad de Alicante. Departamento de Tecnología Informática y Computación
      – PersonEntity:
          Name:
            NameFull: Arquitecturas Inteligentes Aplicadas (AIA)
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
ResultId 1