Multi‐stream adaptive spatial‐temporal attention graph convolutional network for skeleton‐based action recognition

Skeleton‐based action recognition algorithms have been widely applied to human action recognition. Graph convolutional networks (GCNs) generalize convolutional neural networks (CNNs) to non‐Euclidean graphs and achieve significant performance in skeleton‐based action recognition. However, existing G...

Full description

Saved in:
Bibliographic Details
Published in:IET computer vision Vol. 16; no. 2; pp. 143 - 158
Main Authors: Yu, Lubin, Tian, Lianfang, Du, Qiliang, Bhutto, Jameel Ahmed
Format: Journal Article
Language:English
Published: Stevenage John Wiley & Sons, Inc 01.03.2022
Wiley
Subjects:
ISSN:1751-9632, 1751-9640
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Skeleton‐based action recognition algorithms have been widely applied to human action recognition. Graph convolutional networks (GCNs) generalize convolutional neural networks (CNNs) to non‐Euclidean graphs and achieve significant performance in skeleton‐based action recognition. However, existing GCN‐based models have several issues, such as the topology of the graph is defined based on the natural skeleton of the human body, which is fixed during training, and it may not be applied to different layers of the GCN model and diverse datasets. Besides, the higher‐order information of the joint data, for example, skeleton and dynamic information is not fully utilised. This work proposes a novel multi‐stream adaptive spatial‐temporal attention GCN model that overcomes the aforementioned issues. The method designs a learnable topology graph to adaptively adjust the connection relationship and strength, which is updated with training along with other network parameters. Simultaneously, the adaptive connection parameters are utilised to optimise the connection of the natural skeleton graph and the adaptive topology graph. The spatial‐temporal attention module is embedded in each graph convolution layer to ensure that the network focuses on the more critical joints and frames. A multi‐stream framework is built to integrate multiple inputs, which further improves the performance of the network. The final network achieves state‐of‐the‐art performance on both the NTU‐RGBD and Kinetics‐Skeleton action recognition datasets. The simulation results prove that the proposed method reveals better results than existing methods in all perspectives and that shows the superiority of the proposed method.
AbstractList Skeleton‐based action recognition algorithms have been widely applied to human action recognition. Graph convolutional networks (GCNs) generalize convolutional neural networks (CNNs) to non‐Euclidean graphs and achieve significant performance in skeleton‐based action recognition. However, existing GCN‐based models have several issues, such as the topology of the graph is defined based on the natural skeleton of the human body, which is fixed during training, and it may not be applied to different layers of the GCN model and diverse datasets. Besides, the higher‐order information of the joint data, for example, skeleton and dynamic information is not fully utilised. This work proposes a novel multi‐stream adaptive spatial‐temporal attention GCN model that overcomes the aforementioned issues. The method designs a learnable topology graph to adaptively adjust the connection relationship and strength, which is updated with training along with other network parameters. Simultaneously, the adaptive connection parameters are utilised to optimise the connection of the natural skeleton graph and the adaptive topology graph. The spatial‐temporal attention module is embedded in each graph convolution layer to ensure that the network focuses on the more critical joints and frames. A multi‐stream framework is built to integrate multiple inputs, which further improves the performance of the network. The final network achieves state‐of‐the‐art performance on both the NTU‐RGBD and Kinetics‐Skeleton action recognition datasets. The simulation results prove that the proposed method reveals better results than existing methods in all perspectives and that shows the superiority of the proposed method.
Abstract Skeleton‐based action recognition algorithms have been widely applied to human action recognition. Graph convolutional networks (GCNs) generalize convolutional neural networks (CNNs) to non‐Euclidean graphs and achieve significant performance in skeleton‐based action recognition. However, existing GCN‐based models have several issues, such as the topology of the graph is defined based on the natural skeleton of the human body, which is fixed during training, and it may not be applied to different layers of the GCN model and diverse datasets. Besides, the higher‐order information of the joint data, for example, skeleton and dynamic information is not fully utilised. This work proposes a novel multi‐stream adaptive spatial‐temporal attention GCN model that overcomes the aforementioned issues. The method designs a learnable topology graph to adaptively adjust the connection relationship and strength, which is updated with training along with other network parameters. Simultaneously, the adaptive connection parameters are utilised to optimise the connection of the natural skeleton graph and the adaptive topology graph. The spatial‐temporal attention module is embedded in each graph convolution layer to ensure that the network focuses on the more critical joints and frames. A multi‐stream framework is built to integrate multiple inputs, which further improves the performance of the network. The final network achieves state‐of‐the‐art performance on both the NTU‐RGBD and Kinetics‐Skeleton action recognition datasets. The simulation results prove that the proposed method reveals better results than existing methods in all perspectives and that shows the superiority of the proposed method.
Author Bhutto, Jameel Ahmed
Du, Qiliang
Yu, Lubin
Tian, Lianfang
Author_xml – sequence: 1
  givenname: Lubin
  orcidid: 0000-0002-6831-0545
  surname: Yu
  fullname: Yu, Lubin
  organization: South China University and Technology
– sequence: 2
  givenname: Lianfang
  surname: Tian
  fullname: Tian, Lianfang
  organization: Ministry of Natural Resources
– sequence: 3
  givenname: Qiliang
  surname: Du
  fullname: Du, Qiliang
  email: qldu@scut.edu.cn
  organization: Key Laboratory of Autonomous Systems and Network Control of Ministry of Education
– sequence: 4
  givenname: Jameel Ahmed
  surname: Bhutto
  fullname: Bhutto, Jameel Ahmed
  organization: South China University and Technology
BookMark eNp9kc1u1DAUhSNUJNrChieIxA5pWv8m8RKN-BmpiA2wtW7s68FTTxxsz5TueASekSdpMgEWCLHy1b3nO_LRuajOhjhgVT2n5IoSoa7N0bMrykgrH1XntJV0pRpBzv7MnD2pLnLeESIbpcR59e39IRT_8_uPXBLCvgYLY_FHrPMIxUOYLgX3Y0wQaigFh-LjUG8TjF9qE4djDId5M10HLHcx3dYupjrfYsASh4nuIaOtwZy4hCZuBz_PT6vHDkLGZ7_ey-rTm9cf1-9WNx_ebtavblZGCCZXrIc5gWk5BYeOyq6fcopeto4jc8h7bnviGOmlaZAZ3inbCsctMtVNKL-sNouvjbDTY_J7SPc6gtenRUxbDal4E1Bby2RHGoOdaYURFASHxnElWmElgdnrxeI1pvj1gLnoXTykKXzWnCjGFBOETCqyqEyKOSd02vgCc-aSwAdNiZ670nNX-tTVhLz8C_n90X-K6SK-8wHv_6PU688btjAPTeGsEQ
CitedBy_id crossref_primary_10_1142_S0218126625502391
crossref_primary_10_1007_s10489_022_04179_8
crossref_primary_10_3390_app14188185
crossref_primary_10_1007_s10489_024_05719_0
crossref_primary_10_1016_j_cag_2022_12_008
crossref_primary_10_1515_nleng_2025_0143
Cites_doi 10.1109/CVPR.2019.00810
10.1145/3394171.3413941
10.1109/ICMEW.2017.8026285
10.1109/Tip.2020.3028207
10.1016/j.patrec.2017.04.004
10.1109/CVPR.2016.331
10.1109/CVPR.2015.7299176
10.1007/978-3-030-01246-5_7
10.1109/CVPRW.2017.207
10.1109/CVPR42600.2020.01434
10.1109/ICMEW.2017.8026282
10.1109/CVPR.2017.143
10.1016/j.neucom.2018.06.071
10.1109/CVPR.2017.486
10.1109/ICCV.2017.233
10.1609/aaai.v34i03.5652
10.1007/978-3-030-01228-1_25
10.1145/3343031.3351170
10.1016/j.aei.2016.04.009
10.1609/aaai.v32i1.12328
10.1145/2907069
10.1109/TMM.2017.2666540
10.1609/aaai.v33i01.33018561
10.1007/s11042-015-3112-5
10.1109/Access.2020.3049029
10.1109/CVPR.2014.82
10.1109/CVPR.2016.115
ContentType Journal Article
Copyright 2021 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
2022. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2021 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.
– notice: 2022. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 24P
AAYXX
CITATION
3V.
7XB
8AL
8FE
8FG
8FK
ABJCF
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
GNUQQ
HCIFZ
JQ2
K7-
L6V
M0N
M7S
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
Q9U
S0W
DOA
DOI 10.1049/cvi2.12075
DatabaseName Open Access: Wiley-Blackwell Open Access Journals
CrossRef
ProQuest Central (Corporate)
ProQuest Central (purchase pre-March 2016)
Computing Database (Alumni Edition)
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
AUTh Library subscriptions: ProQuest Central
Technology collection
ProQuest One
ProQuest Central
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
ProQuest Engineering Collection
Computing Database
Engineering Database
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
Engineering Collection
ProQuest Central Basic
DELNET Engineering & Technology Collection
Directory of Open Access Journals
DatabaseTitle CrossRef
Computer Science Database
ProQuest Central Student
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest Central Korea
ProQuest Central (New)
Engineering Collection
Advanced Technologies & Aerospace Collection
ProQuest Computing
Engineering Database
ProQuest Central Basic
ProQuest Computing (Alumni Edition)
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest DELNET Engineering and Technology Collection
Materials Science & Engineering Collection
ProQuest One Academic
ProQuest Central (Alumni)
ProQuest One Academic (New)
DatabaseTitleList CrossRef


Computer Science Database
Database_xml – sequence: 1
  dbid: 24P
  name: Wiley Online Library Open Access
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
– sequence: 2
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 3
  dbid: BENPR
  name: Proquest Central Journals
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISSN 1751-9640
EndPage 158
ExternalDocumentID oai_doaj_org_article_dd25806ce8c74c41a43a6f39474d50a6
10_1049_cvi2_12075
CVI212075
Genre article
GrantInformation_xml – fundername: Key‐Area Research and Development Program of Guangdong Province
  funderid: 2018B010109001; 2019B020214001; 2020B1111010002
– fundername: Guangdong Marine Economic Development Project
  funderid: GDNRC[2020]018
GroupedDBID .DC
0R~
0ZK
1OC
24P
29I
3V.
5GY
6IK
8FE
8FG
8VB
AAHHS
AAHJG
AAJGR
ABJCF
ABQXS
ABUWG
ACCFJ
ACCMX
ACESK
ACGFO
ACGFS
ACIWK
ACXQS
ADEYR
ADZOD
AEEZP
AEGXH
AENEX
AEQDE
AFKRA
AIWBW
AJBDE
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ARAPS
AVUZU
AZQEC
BENPR
BGLVJ
BPHCQ
CCPQU
CS3
DU5
DWQXO
EBS
EJD
ESX
GNUQQ
GROUPED_DOAJ
HCIFZ
HZ~
IAO
IFIPE
IPLJI
ITC
J9A
JAVBF
K1G
K6V
K7-
L6V
LAI
LXU
M0N
M43
M7S
MCNEO
MS~
NADUK
NXXTH
O9-
OCL
OK1
P62
PQQKQ
PROAC
PTHSS
QWB
RIE
RNS
RUI
S0W
UNMZH
ZL0
~ZZ
AAMMB
AAYXX
AEFGJ
AFFHD
AGXDD
AIDQK
AIDYY
CITATION
IDLOA
PHGZM
PHGZT
PQGLB
WIN
7XB
8AL
8FK
JQ2
PKEHL
PQEST
PQUKI
PRINS
Q9U
ID FETCH-LOGICAL-c4425-2ba9640c731afef158b0494b57f3e2fe3b3db0f20b5c6e2c389d74f3de298a963
IEDL.DBID WIN
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000712514300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1751-9632
IngestDate Mon Nov 10 04:33:13 EST 2025
Wed Aug 13 08:10:38 EDT 2025
Wed Oct 29 21:24:00 EDT 2025
Tue Nov 18 22:38:58 EST 2025
Wed Jan 22 16:27:13 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
License Attribution-NonCommercial-NoDerivs
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4425-2ba9640c731afef158b0494b57f3e2fe3b3db0f20b5c6e2c389d74f3de298a963
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-6831-0545
OpenAccessLink https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fcvi2.12075
PQID 3092292400
PQPubID 1936354
PageCount 16
ParticipantIDs doaj_primary_oai_doaj_org_article_dd25806ce8c74c41a43a6f39474d50a6
proquest_journals_3092292400
crossref_citationtrail_10_1049_cvi2_12075
crossref_primary_10_1049_cvi2_12075
wiley_primary_10_1049_cvi2_12075_CVI212075
PublicationCentury 2000
PublicationDate March 2022
2022-03-00
20220301
2022-03-01
PublicationDateYYYYMMDD 2022-03-01
PublicationDate_xml – month: 03
  year: 2022
  text: March 2022
PublicationDecade 2020
PublicationPlace Stevenage
PublicationPlace_xml – name: Stevenage
PublicationTitle IET computer vision
PublicationYear 2022
Publisher John Wiley & Sons, Inc
Wiley
Publisher_xml – name: John Wiley & Sons, Inc
– name: Wiley
References 2021; 9
2017; 92
2018; 315
2019; 33
2020
2016; 75
2019
2016; 30
2018
2017
2017; 19
2016
2015
2020; 34
2014
2016; 23
2020; 29
e_1_2_11_10_1
Li C. (e_1_2_11_12_1) 2017
e_1_2_11_31_1
e_1_2_11_30_1
e_1_2_11_36_1
e_1_2_11_35_1
e_1_2_11_34_1
e_1_2_11_11_1
e_1_2_11_7_1
e_1_2_11_29_1
e_1_2_11_6_1
e_1_2_11_28_1
e_1_2_11_5_1
e_1_2_11_27_1
e_1_2_11_4_1
e_1_2_11_3_1
e_1_2_11_2_1
Li B. (e_1_2_11_13_1) 2017
Cheng K. (e_1_2_11_32_1)
e_1_2_11_20_1
e_1_2_11_25_1
e_1_2_11_24_1
Niepert M. (e_1_2_11_26_1) 2016
e_1_2_11_9_1
e_1_2_11_23_1
e_1_2_11_8_1
e_1_2_11_22_1
e_1_2_11_18_1
e_1_2_11_17_1
e_1_2_11_16_1
e_1_2_11_15_1
e_1_2_11_19_1
Du Y. (e_1_2_11_14_1) 2015
Liu Z.Y. (e_1_2_11_33_1)
Shi L. (e_1_2_11_21_1) 2019
References_xml – start-page: 103
  year: 2018
  end-page: 118
– volume: 33
  start-page: 8561
  issue: 01
  year: 2019
  end-page: 8568
– volume: 9
  start-page: 36475
  year: 2021
  end-page: 36484
  article-title: Multi‐scale mixed dense graph convolution network for skeleton‐based action recognition
  publication-title: Ieee Access
– start-page: 2014
  year: 2016
  end-page: 2023
– volume: 75
  start-page: 12155
  issue: 19
  year: 2016
  end-page: 12172
  article-title: Video structured description technology based intelligence analysis of surveillance videos for public security applications
  publication-title: Multimed. Tool. Appl.
– volume: 29
  start-page: 9532
  year: 2020
  end-page: 9545
  article-title: Skeleton‐based action recognition with multi‐stream adaptive graph convolutional networks
  publication-title: IEEE Trans Image Process
– start-page: 5378
  year: 2015
  end-page: 5387
– start-page: 1110
  year: 2015
  end-page: 1118
– volume: 23
  start-page: 38
  issue: 3
  year: 2016
  end-page: 44
  article-title: Research contributions in human‐computer interaction
  publication-title: Interactions
– start-page: 14333
  year: 2020
  end-page: 14342
– start-page: 601
  year: 2017
  end-page: 604
– start-page: 180
  end-page: 189
– start-page: 140
  end-page: 149
– start-page: 588
  year: 2014
  end-page: 595
– start-page: 399
  year: 2018
  end-page: 417
– volume: 19
  start-page: 1510
  issue: 7
  year: 2017
  end-page: 1520
  article-title: Sequential deep trajectory descriptor for action recognition with three‐stream CNN
  publication-title: IEEE Trans. Multimed.
– start-page: 597
  year: 2017
  end-page: 600
– start-page: 601
  year: 2019
  end-page: 610
– volume: 92
  start-page: 33
  year: 2017
  end-page: 40
  article-title: Three‐stream CNNs for action recognition
  publication-title: Pattern. Recogn. Lett.
– volume: 34
  start-page: 2669
  issue: 03
  year: 2020
  end-page: 2676
– volume: 30
  start-page: 327
  issue: 3
  year: 2016
  end-page: 336
  article-title: Vision‐based action recognition of construction workers using dense trajectories
  publication-title: Adv. Eng. Inf.
– start-page: 1010
  year: 2016
  end-page: 1019
– volume: 315
  start-page: 221
  year: 2018
  end-page: 233
  article-title: Action recognition using spatial‐optical data organization and sequential learning framework
  publication-title: Neurocomputing
– start-page: 2117
  year: 2017
  end-page: 2126
– start-page: 3034
  year: 2016
  end-page: 3042
– start-page: 3288
  year: 2017
  end-page: 3297
– start-page: 12018
  year: 2019
  end-page: 12027
– start-page: 7912
  year: 2019
  end-page: 7921
– start-page: 7291
  year: 2017
  end-page: 7299
– start-page: 55
  year: 2020
  end-page: 63
– start-page: 1623
  year: 2017
  end-page: 1631
– ident: e_1_2_11_22_1
  doi: 10.1109/CVPR.2019.00810
– ident: e_1_2_11_31_1
  doi: 10.1145/3394171.3413941
– start-page: 597
  volume-title: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  year: 2017
  ident: e_1_2_11_12_1
  doi: 10.1109/ICMEW.2017.8026285
– start-page: 12018
  volume-title: Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  year: 2019
  ident: e_1_2_11_21_1
– ident: e_1_2_11_24_1
– ident: e_1_2_11_29_1
  doi: 10.1109/Tip.2020.3028207
– ident: e_1_2_11_5_1
  doi: 10.1016/j.patrec.2017.04.004
– ident: e_1_2_11_7_1
  doi: 10.1109/CVPR.2016.331
– ident: e_1_2_11_9_1
  doi: 10.1109/CVPR.2015.7299176
– ident: e_1_2_11_17_1
  doi: 10.1007/978-3-030-01246-5_7
– ident: e_1_2_11_10_1
  doi: 10.1109/CVPRW.2017.207
– start-page: 1110
  volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
  year: 2015
  ident: e_1_2_11_14_1
– ident: e_1_2_11_30_1
  doi: 10.1109/CVPR42600.2020.01434
– start-page: 601
  volume-title: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  year: 2017
  ident: e_1_2_11_13_1
  doi: 10.1109/ICMEW.2017.8026282
– start-page: 2014
  volume-title: International Conference on Machine Learning
  year: 2016
  ident: e_1_2_11_26_1
– ident: e_1_2_11_35_1
  doi: 10.1109/CVPR.2017.143
– ident: e_1_2_11_28_1
  doi: 10.1016/j.neucom.2018.06.071
– ident: e_1_2_11_11_1
  doi: 10.1109/CVPR.2017.486
– ident: e_1_2_11_16_1
  doi: 10.1109/ICCV.2017.233
– ident: e_1_2_11_23_1
  doi: 10.1609/aaai.v34i03.5652
– ident: e_1_2_11_27_1
  doi: 10.1007/978-3-030-01228-1_25
– ident: e_1_2_11_20_1
  doi: 10.1145/3343031.3351170
– ident: e_1_2_11_4_1
  doi: 10.1016/j.aei.2016.04.009
– ident: e_1_2_11_18_1
  doi: 10.1609/aaai.v32i1.12328
– ident: e_1_2_11_2_1
  doi: 10.1145/2907069
– ident: e_1_2_11_6_1
  doi: 10.1109/TMM.2017.2666540
– ident: e_1_2_11_25_1
– start-page: 140
  volume-title: 2020 Ieee/Cvf Conference on Computer Vision and Pattern Recognition (Cvpr)
  ident: e_1_2_11_33_1
– ident: e_1_2_11_19_1
  doi: 10.1609/aaai.v33i01.33018561
– ident: e_1_2_11_36_1
– ident: e_1_2_11_3_1
  doi: 10.1007/s11042-015-3112-5
– start-page: 180
  volume-title: 2020 Ieee/Cvf Conference on Computer Vision and Pattern Recognition (Cvpr)
  ident: e_1_2_11_32_1
– ident: e_1_2_11_34_1
  doi: 10.1109/Access.2020.3049029
– ident: e_1_2_11_8_1
  doi: 10.1109/CVPR.2014.82
– ident: e_1_2_11_15_1
  doi: 10.1109/CVPR.2016.115
SSID ssj0056994
Score 2.306493
Snippet Skeleton‐based action recognition algorithms have been widely applied to human action recognition. Graph convolutional networks (GCNs) generalize convolutional...
Abstract Skeleton‐based action recognition algorithms have been widely applied to human action recognition. Graph convolutional networks (GCNs) generalize...
SourceID doaj
proquest
crossref
wiley
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 143
SubjectTerms Algorithms
Artificial neural networks
Cognition & reasoning
computer graphics
computer vision
convolutional neural nets
Datasets
Deep learning
Fourier transforms
graph theory
graphics processing units
Graphs
Human activity recognition
Human body
image colour analysis
image motion analysis
image thinning
learning (artificial intelligence)
Lie groups
Methods
Network topologies
Neural networks
Parameters
Performance enhancement
Semantics
space‐time adaptive processing
topology
SummonAdditionalLinks – databaseName: Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PSxwxFA4iHry0Wlu6ukqgXipMnXnJJJOjiksLRTxY2VvIT5BuZ5eddfHon-Df2L-kSSa7KEh76W2YJEzIe8n7wnzvewgdK0LAlMoU4XAUBbWWFtrwqhBMhdtC45myqWrJd3511YzH4vpZqa_ICevlgfuFO7UW6qZkxjWGU0MrRYlingjKqa1LlcS2Sy5Wl6n-DK6ZSCUQQ2yMnyWwEial4tQs7-BLFcbUL0JRUux_ATOfg9UUbUY76E2Gifisn94u2nDtO_Q2Q0acN2S3hx5SAu3vx6eY86F-YWXVLB5guItMaTUJLVl8aoKjkmbiNuKkUo0j4Tw7Xmhtez44DiAWdz9DMAqgMIyOUc7iPvsBr9lG0_Y9-jG6vLn4WuRiCoWhYV8WoJVgtDScVMo7X9WNjtIwuuaeOPCOaGJ16aHUtWEOTAAyllNPrAPRhKHkA9psp637iHDAUMQC14pZTx1pNPAaLCMeqAkXMD5An1frKk1WGo8FLyYy_fGmQkYbyGSDAfq07jvr9TVe7XUezbPuETWx04vgKTJ7ivyXpwzQcGVcmTdqJ0kpAEQk0g7QSTL4X6YhL26_QXra_x8TOkDbEJMpEqNtiDYX83t3iLbMcnHXzY-SQ_8B4I_9SQ
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: Advanced Technologies & Aerospace Database
  dbid: P5Z
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Nb9QwELVKy4FLS_kQCwVZggtIocnYseNTBRVVK1VVD4AqLpY_K8SS3W4K4shP4DfyS-rxOkuRUC_cosRxIs145jl584aQF4YxcLVxVQqOquLe88o62VRKmLRb6KIwPnctOZYnJ93ZmTotH9yGQqscY2IO1H7m8Bv5LqsVgELG4978osKuUfh3tbTQuEU2GkhYP_nzaftpjMStULkRYsqQ-HAGozwpV7tpUnjdQI38wmsJKev2_wU2r0PWnHMOtv73be-SzYI26Zule2yTtdDfI1sFedKyrof75Eeuw_398xeWjpiv1HgzxzhIByRcm2m6UjSsphQFOTNFkmaxa4q89eK_6Wq_pJXThIXp8CXltIQt092YLD1dFlHQFWlp1j8gHw7evd8_rEpPhsrxtLwrsEYJXjvJGhNDbNrOosKMbWVkAWJglnlbR6ht60QAl_CQlzwyH0B16Vb2kKz3sz48IjRBMeZBWiN85IF1FmQLXrAI3KV9nJyQl6NhtCuC5dg3Y6rzj3OuNBpRZyNOyPPV2PlSpuOfo96ifVcjUFo7n5gtznVZqdp7aLtauNA5yR1vDGdGRKa45L6tjZiQndHkuqz3Qf-x94S8yh5zw2vo_Y9HkI8e3zzXE3IHsNoiU952yPrl4lt4Sm6775efh8Wz7OtXMfILqQ
  priority: 102
  providerName: ProQuest
Title Multi‐stream adaptive spatial‐temporal attention graph convolutional network for skeleton‐based action recognition
URI https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fcvi2.12075
https://www.proquest.com/docview/3092292400
https://doaj.org/article/dd25806ce8c74c41a43a6f39474d50a6
Volume 16
WOSCitedRecordID wos000712514300001&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: 1751-9640
  dateEnd: 20241231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: DOA
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1751-9640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: K7-
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Engineering Database
  customDbUrl:
  eissn: 1751-9640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: M7S
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest advanced technologies & aerospace journals
  customDbUrl:
  eissn: 1751-9640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: P5Z
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Proquest Central Journals
  customDbUrl:
  eissn: 1751-9640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: BENPR
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVWIB
  databaseName: Wiley Online Library Free Content
  customDbUrl:
  eissn: 1751-9640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: WIN
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1751-9640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: 24P
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1baxUxEA61-uBL6xVPrUtAXxRWdyfZZAO-2NJiUQ4Hr8WXJVcpPd1TztbSx_4Ef6O_xEl292hBBPElLJuEDUlm5kt25htCnmjGwBba5qgcVc6d47mxssyV0HhaqIPQLmUteSun0_rwUM3WyMsxFqbnh1hduEXJSPo6Crg2fRYSBLW4iPb8CJ6XgCYPFXDJk1R-PpiOargSKmVBRPMYv8xg5Cbl6sWvrlesUSLtv4I0f8eryeDsb_7fUG-RjQFo0lf9zrhN1nx7h2wOoJMOIt3dJRcpBPfH5fcYNaJPqHb6NKpA2kVfaz3HmoG-ak4jF2fyjqSJ55pGl_Vh62Jt23uUU4TBtDtGc4awEntHO-loHz9BV_5Ki_Ye-bi_92H3dT6kY8gtR8nOwWgleGElK3XwoaxqE8llTCUD8xA8M8yZIkBhKis8WIRCTvLAnAdVY1d2n6y3i9Y_IBRRGHMgjRYucM9qA7ICJ1gAbvEIJyfk6bgsjR24ymPKjHmT_plz1cQpbdKUTsjjVdvTnqHjj6124uquWkRW7fRisfzaDELaOAdVXQjrayu55aXmTIvAFJfcVYUWE7I97o1mEPWuYYUCUNEVd0KepV3wl2E0u58OID1t_Uvjh-QmxLCL5Pu2TdbPlt_8I3LDnp8ddcuMXAM-y8j1nb3p7F2WbhWwfCPzLHqyvsdyVn3JknT8BMARECU
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LbtQwFL0qBQk2lKcYKGAJWIAUmtiOHS8QgkLVUYdRFwVVbIzjB6o6zAyT8trxCXwJH8WX4OskQ5FQd12wixIniicn5x5nzr0X4L5hjNrc2CySo8q4czyrrSwyJUxcLVRBGJe6lozkeFzt76vdFfjZ58KgrbLnxETUbmbxG_kGyxWlCh2PT-cfM-wahf-u9i00Wljs-G9f4pKteTJ8EZ_vA0q3Xu5tbmddV4HM8gjQjNZGCZ5byQoTfCjKqsYaKXUpA_M0eFYzV-eB5nVphac2RnQneWDOU1XFU1m87hk4G2WEQiLYLd_2zF8KlRovxoiMk2W0L4fK1UacBH1c0Bz9jMcCYOoT8Je4PS6RU4zbWvvffp1LcLFT0-RZC__LsOKnV2CtU9ak463mKnxNeca_vv_A1BjzgRhn5sjzpEFDuZnEI12NrgnBgqPJAkpSMW-Cvvzu_YxHp61tnkStT5rDGLOjdo5noxhwpE0SIUtT1mx6DV6fyvyvw-p0NvU3gESpyRyVtREucM-qmsqSOsEC5TauU-UAHvZA0LYryI59QSY6GQO40gganUAzgHvLsfO2DMk_Rz1HPC1HYOnwtGO2eK87JtLO0bLKhfWVldzywnBmRGCKS-7K3IgBrPcQ0x2fNfoPvgbwKCH0hNvQm2-GNG3dPPlad-H89t6rkR4Nxzu34ALFzJJk71uH1aPFJ38bztnPRwfN4k56zwi8O23o_gb8s2iw
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LbtQwFL0qLUJsKE8xUMASsAApTGI7drxAiD5GjFqNRghQd67jB0IMmWFSXjs-ge_hc_gSbMcZioS664JdlNhWnJz7Ss69F-CBIgTrXOnMK0eRUWNoVmteZIIpHy1UjikTu5Yc8MmkOjwU0zX42efCBFplrxOjojZzHb6RD0kuMBaB8Th0iRYx3R09W3zMQgep8Ke1b6fRQWTffvviw7f26XjXv-uHGI_2Xu28yFKHgUxTD9YM10owmmtOCuWsK8qqDvVS6pI7YrGzpCamzh3O61Izi7W37oZTR4zFovJTiV_3HGxwInIvXRvbe5Ppy94OlEzENozePoetE9wXR6Vi6LeEnxQ4D-zGE-Ywdg34y9U96TBHizfa_J-f1WW4lPxs9LwTjCuwZpursJl8bpQ0WnsNvsYM5F_ff4SkGfUBKaMWwQKgNlDN1cxfSdW7ZiiUIo3kUBTLfKPA2E-S6682HaEe-SgAte-9NfdetZ8d3ASDuvQRtKJrzZvr8PpM9n8D1pt5Y28C8k4oMZjXihlHLalqzEtsGHGYah_B8gE86kEhdSrVHjqGzGSkDFAhA4BkBNAA7q_GLroCJf8ctR2wtRoRiorHE_PlW5l0lDQGl1XOtK00p5oWihLFHBGUU1Pmig1gq4ebTJqulX-wNoDHEa2n3IbceTPG8ejW6WvdgwsesfJgPNm_DRdxSDmJvL8tWD9efrJ34Lz-fPyuXd5NQofg6Kyx-xuuzHKo
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=Multi%E2%80%90stream+adaptive+spatial%E2%80%90temporal+attention+graph+convolutional+network+for+skeleton%E2%80%90based+action+recognition&rft.jtitle=IET+computer+vision&rft.au=Yu%2C+Lubin&rft.au=Tian%2C+Lianfang&rft.au=Du%2C+Qiliang&rft.au=Bhutto%2C+Jameel+Ahmed&rft.date=2022-03-01&rft.issn=1751-9632&rft.eissn=1751-9640&rft.volume=16&rft.issue=2&rft.spage=143&rft.epage=158&rft_id=info:doi/10.1049%2Fcvi2.12075&rft.externalDBID=n%2Fa&rft.externalDocID=10_1049_cvi2_12075
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-9632&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-9632&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-9632&client=summon