Research on Action Recognition Algorithm Based on SlowFast Network

As a major branch of video understanding, human action recognition has become a popular research topic in the field of computer vision and has a wide range of applications in many areas. To address the problems of high parameter consumption and weak spatiotemporal modeling capabilities in existing a...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of advanced computational intelligence and intelligent informatics Ročník 29; číslo 5; s. 1056 - 1061
Hlavní autori: Xu, Yinhao, Lu, Yuanyao
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Tokyo Fuji Technology Press Co. Ltd 20.09.2025
Predmet:
Accuracy
Algorithms
Computer vision
Consumption
Design
Human activity recognition
Informatics
Network design
Neural networks
Parameters
Semantics
ISSN:1343-0130, 1883-8014
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract As a major branch of video understanding, human action recognition has become a popular research topic in the field of computer vision and has a wide range of applications in many areas. To address the problems of high parameter consumption and weak spatiotemporal modeling capabilities in existing action recognition methods, this study proposes a lightweight dual-branch convolutional network called SlowFast-Light Net. Inspired and influenced by the renowned two-branch SlowFast network proposed by the expert Kaiming He, this study adopts a lightweight two-branch network design, which is an improvement based on the SlowFast network. The network significantly reduces parameter consumption by introducing a lightweight feature extraction network and accelerating the model convergence speed. This study conducts experimental verification on the UCF101 and HMDB51 datasets, achieving an action recognition accuracy of 93.80% and 80.00%, respectively, on the two test sets. The experimental results showed that the model proposed in this study achieved a recognition accuracy comparable to that of the original model with a considerably lower number of parameters.
AbstractList As a major branch of video understanding, human action recognition has become a popular research topic in the field of computer vision and has a wide range of applications in many areas. To address the problems of high parameter consumption and weak spatiotemporal modeling capabilities in existing action recognition methods, this study proposes a lightweight dual-branch convolutional network called SlowFast-Light Net. Inspired and influenced by the renowned two-branch SlowFast network proposed by the expert Kaiming He, this study adopts a lightweight two-branch network design, which is an improvement based on the SlowFast network. The network significantly reduces parameter consumption by introducing a lightweight feature extraction network and accelerating the model convergence speed. This study conducts experimental verification on the UCF101 and HMDB51 datasets, achieving an action recognition accuracy of 93.80% and 80.00%, respectively, on the two test sets. The experimental results showed that the model proposed in this study achieved a recognition accuracy comparable to that of the original model with a considerably lower number of parameters.
Author Xu, Yinhao
Lu, Yuanyao
Author_xml – sequence: 1
  givenname: Yinhao
  surname: Xu
  fullname: Xu, Yinhao
  organization: School of Information Science and Technology, North China University of Technology, No.5 Jinyuanzhuang Road, Shijingshan District, Beijing 100144, China
– sequence: 2
  givenname: Yuanyao
  orcidid: 0000-0003-0019-3028
  surname: Lu
  fullname: Lu, Yuanyao
  organization: School of Information Science and Technology, North China University of Technology, No.5 Jinyuanzhuang Road, Shijingshan District, Beijing 100144, China
BookMark eNotkE1PAjEURRuDiYj8AVeTuB5sX9v5WAIRNSGaoK6b8qaFIkyxHUL89xZwde9LTu5Lzi3ptb41hNwzOgJaF_Jxo9E5lw6Qoz2jsrgifVZVPK8oE73UueA5ZZzekGGMG0pTh4IK1ieThYlGB1xnvs3G2LkUC4N-1bpzH29XPrhuvcsmOprmRH1s_XGmY5e9me7ow_cdubZ6G83wPwfka_b0OX3J5-_Pr9PxPEcB0OWIpTYMsFqKJQAKiSVaw2nNKS9L2XAr0PKGFkWCGgDbaAONRLBaQ41LPiAPl9198D8HEzu18YfQppeKgwTG6yQjUXChMPgYg7FqH9xOh1_FqDrrUhdd6qRLnXXxP0LIYPM
Cites_doi 10.20965/jaciii.2023.p0673
10.1109/ICCVW.2019.00240
10.1109/ICCV.2019.00630
10.1109/ICCV.2015.510
10.1109/CVPR.2018.00633
10.3389/fnbot.2024.1457843
10.1007/978-3-030-01264-9_8
10.1016/j.cviu.2022.103484
10.1109/CVPR.2018.00474
10.1109/CVPR42600.2020.00099
10.1109/CVPR.2017.502
10.1109/CVPR.2018.00716
10.1109/CVPR.2016.213
10.20965/jaciii.2023.p1086
10.20965/jaciii.2020.p0346
10.1109/ICCV.2017.590
ContentType Journal Article
Copyright Copyright © 2025 Fuji Technology Press Ltd.
Copyright_xml – notice: Copyright © 2025 Fuji Technology Press Ltd.
DBID AAYXX
CITATION
7SC
7SP
8FD
8FE
8FG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
GNUQQ
HCIFZ
JQ2
K7-
L7M
L~C
L~D
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOI 10.20965/jaciii.2025.p1056
DatabaseName CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central - New (Subscription)
Technology collection
ProQuest One Community College
ProQuest Central
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DatabaseTitle CrossRef
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Advanced Technologies & Aerospace Collection
ProQuest One Academic Eastern Edition
Electronics & Communications Abstracts
ProQuest Technology Collection
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList Computer Science Database
CrossRef
Database_xml – sequence: 1
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1883-8014
EndPage 1061
ExternalDocumentID 10_20965_jaciii_2025_p1056
GroupedDBID AAYXX
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
ARCSS
BENPR
BGLVJ
CCPQU
CITATION
GROUPED_DOAJ
HCIFZ
ISHAI
JSI
JSP
K7-
P2P
PHGZM
PHGZT
PQGLB
RJT
RZJ
TUS
7SC
7SP
8FD
8FE
8FG
AZQEC
DWQXO
GNUQQ
JQ2
L7M
L~C
L~D
P62
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c422t-cc7ae12c8b4b22c45c7cfe309303775d3f4cf3d06612cd22fdae2d5c2faa29cb3
IEDL.DBID P5Z
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001576722900023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1343-0130
IngestDate Tue Oct 07 11:14:01 EDT 2025
Sat Nov 29 07:30:39 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c422t-cc7ae12c8b4b22c45c7cfe309303775d3f4cf3d06612cd22fdae2d5c2faa29cb3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-0019-3028
OpenAccessLink https://doi.org/10.20965/jaciii.2025.p1056
PQID 3252139096
PQPubID 4911628
PageCount 6
ParticipantIDs proquest_journals_3252139096
crossref_primary_10_20965_jaciii_2025_p1056
PublicationCentury 2000
PublicationDate 2025-09-20
PublicationDateYYYYMMDD 2025-09-20
PublicationDate_xml – month: 09
  year: 2025
  text: 2025-09-20
  day: 20
PublicationDecade 2020
PublicationPlace Tokyo
PublicationPlace_xml – name: Tokyo
PublicationTitle Journal of advanced computational intelligence and intelligent informatics
PublicationYear 2025
Publisher Fuji Technology Press Co. Ltd
Publisher_xml – name: Fuji Technology Press Co. Ltd
References key-10.20965/jaciii.2025.p1056-2
key-10.20965/jaciii.2025.p1056-1
key-10.20965/jaciii.2025.p1056-6
key-10.20965/jaciii.2025.p1056-5
key-10.20965/jaciii.2025.p1056-4
key-10.20965/jaciii.2025.p1056-3
key-10.20965/jaciii.2025.p1056-19
key-10.20965/jaciii.2025.p1056-9
key-10.20965/jaciii.2025.p1056-18
key-10.20965/jaciii.2025.p1056-8
key-10.20965/jaciii.2025.p1056-17
key-10.20965/jaciii.2025.p1056-7
key-10.20965/jaciii.2025.p1056-16
key-10.20965/jaciii.2025.p1056-15
key-10.20965/jaciii.2025.p1056-14
key-10.20965/jaciii.2025.p1056-13
key-10.20965/jaciii.2025.p1056-12
key-10.20965/jaciii.2025.p1056-23
key-10.20965/jaciii.2025.p1056-11
key-10.20965/jaciii.2025.p1056-22
key-10.20965/jaciii.2025.p1056-10
key-10.20965/jaciii.2025.p1056-21
key-10.20965/jaciii.2025.p1056-20
References_xml – ident: key-10.20965/jaciii.2025.p1056-14
  doi: 10.20965/jaciii.2023.p0673
– ident: key-10.20965/jaciii.2025.p1056-4
– ident: key-10.20965/jaciii.2025.p1056-19
– ident: key-10.20965/jaciii.2025.p1056-18
– ident: key-10.20965/jaciii.2025.p1056-22
  doi: 10.1109/ICCVW.2019.00240
– ident: key-10.20965/jaciii.2025.p1056-2
  doi: 10.1109/ICCV.2019.00630
– ident: key-10.20965/jaciii.2025.p1056-8
  doi: 10.1109/ICCV.2015.510
– ident: key-10.20965/jaciii.2025.p1056-17
  doi: 10.1109/CVPR.2018.00633
– ident: key-10.20965/jaciii.2025.p1056-21
  doi: 10.3389/fnbot.2024.1457843
– ident: key-10.20965/jaciii.2025.p1056-6
– ident: key-10.20965/jaciii.2025.p1056-12
  doi: 10.1007/978-3-030-01264-9_8
– ident: key-10.20965/jaciii.2025.p1056-5
– ident: key-10.20965/jaciii.2025.p1056-20
– ident: key-10.20965/jaciii.2025.p1056-11
– ident: key-10.20965/jaciii.2025.p1056-23
  doi: 10.1016/j.cviu.2022.103484
– ident: key-10.20965/jaciii.2025.p1056-13
  doi: 10.1109/CVPR.2018.00474
– ident: key-10.20965/jaciii.2025.p1056-16
  doi: 10.1109/CVPR42600.2020.00099
– ident: key-10.20965/jaciii.2025.p1056-10
  doi: 10.1109/CVPR.2017.502
– ident: key-10.20965/jaciii.2025.p1056-3
  doi: 10.1109/CVPR.2018.00716
– ident: key-10.20965/jaciii.2025.p1056-7
  doi: 10.1109/CVPR.2016.213
– ident: key-10.20965/jaciii.2025.p1056-15
  doi: 10.20965/jaciii.2023.p1086
– ident: key-10.20965/jaciii.2025.p1056-1
  doi: 10.20965/jaciii.2020.p0346
– ident: key-10.20965/jaciii.2025.p1056-9
  doi: 10.1109/ICCV.2017.590
SSID ssj0001326041
ssib051641541
Score 2.3350496
Snippet As a major branch of video understanding, human action recognition has become a popular research topic in the field of computer vision and has a wide range of...
SourceID proquest
crossref
SourceType Aggregation Database
Index Database
StartPage 1056
SubjectTerms Accuracy
Algorithms
Computer vision
Consumption
Design
Human activity recognition
Informatics
Network design
Neural networks
Parameters
Semantics
Title Research on Action Recognition Algorithm Based on SlowFast Network
URI https://www.proquest.com/docview/3252139096
Volume 29
WOSCitedRecordID wos001576722900023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: DOA
  dateStart: 20070101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib051641541
  issn: 1343-0130
  databaseCode: M~E
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: P5Z
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: K7-
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: BENPR
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELagZWChPEWhVBnYUCB17DiZUItaIYGiqoBUsUSOHzxU0tIE-Pv4nERVFxaWDMnJiu7O9_L5PoTOU0ailPRSlwfUJCiShi6nkXQ9bbyJokFItB2Zf8_iOJxOo3FVcMurtsraJlpDLecCauRXPjaOxiToUXC9-HQBNQpOVysIjU3UhCkJAN0wps-1PlGTCpgIobequZhYxSNlDkagjcj3yns0GGagXL1zAQMdsAkDLheASL_uq9ZNtfU_o9Z__3wX7VSRp9MvVWUPbahsH7VqVAen2uQHaFA34znzzOnbaw_OpG4zglezF7N68frhDIwHlED1MJv_jHheOHHZVH6InkbDx5tbt0JacAXBuHCFYFz1sAhTkmIsCBVMaAWHpJ7PGJW-JkL70oQnhkhirCVXWFKBNec4Eql_hBrZPFPHyFGUaRWFjMFc_QAwC5khopGvcSplxNvoouZpsigHaiQmEbESSEoJJCCBxEqgjTo1T5Nqc-XJiqEnf38-RduwFLR3YK-DGsXyS52hLfFdvOXLLmoOhvF40rVpuHneMbdr9ecXww7JBg
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LT9wwEB5RQCoXoNCKd30opyolO7Hj5IAQrxVol1XVgsQtdfwoINhd2ADiT_EbGSdrIS69ceg1tiw533i-GXseAN9KyfOSt8pIpYIcFCOySIncRLEjNrEizbirS-Z3Za-XnZ_nPyfgOeTC-LDKoBNrRW0G2t-RbyVIREMOep7uDG8j3zXKv66GFhqNWHTs0yO5bKPt4wPCdxOxfXi6fxSNuwpEmiNWkdZS2RbqrOQlouZCS-2sfxCMEymFSRzXLjFExTTJIDqjLBqh0SmFuS4TWvcDTPEkk_5cdWQU5FeQ60EWSev1jodso5g3Ph_3YUtJ3OTtoK-5snWltC8ggWR2_BiSnZO-5ca31FDzXXvuf_tT8zA7tqzZbnMUPsGE7S_AXOhawcZKbBH2QrAhG_TZbp3WwX6FMCr_6fov7aa6uGF7xPDGz_p9PXhsq1HFek3Q_Gc4e5edfIHJ_qBvl4BZIZ3NMyl934DU92SUNEnkicPSmFwtw_eAYTFsCoYU5GjViBcN4oVHvKgRX4a1gGExVh6j4hXAlX8Pf4WPR6cn3aJ73Ouswoxf1oeyYLwGk9XdvV2Haf1QXY7uNmo5ZfDnveF-AREbJP8
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Research+on+Action+Recognition+Algorithm+Based+on+SlowFast+Network&rft.jtitle=Journal+of+advanced+computational+intelligence+and+intelligent+informatics&rft.au=Xu%2C+Yinhao&rft.au=Lu%2C+Yuanyao&rft.date=2025-09-20&rft.issn=1343-0130&rft.eissn=1883-8014&rft.volume=29&rft.issue=5&rft.spage=1056&rft.epage=1061&rft_id=info:doi/10.20965%2Fjaciii.2025.p1056&rft.externalDBID=n%2Fa&rft.externalDocID=10_20965_jaciii_2025_p1056
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1343-0130&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1343-0130&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1343-0130&client=summon