An asymmetrical-structure auto-encoder for unsupervised representation learning of skeleton sequences

Saved in:
Bibliographic Details
Published inComputer vision and image understanding Vol. 222; p. 103491
Main Authors Zhou, Jiaxin, Komuro, Takashi
Format Journal Article
LanguageEnglish
Published 01.09.2022
Online AccessGet full text

Cover

ArticleNumber 103491
Author Komuro, Takashi
Zhou, Jiaxin
Author_xml – sequence: 1
  givenname: Jiaxin
  orcidid: 0000-0002-3008-5127
  surname: Zhou
  fullname: Zhou, Jiaxin
– sequence: 2
  givenname: Takashi
  surname: Komuro
  fullname: Komuro, Takashi
BookMark eNp9kMtuwjAQRb2gUoH2B7ryD4R6nOAkS4T6kpC6adeWcSaVabDp2Ebi7xtEV12wmtEdnavRmbGJDx4ZewCxAAHqcbewR5cXUkg5BmXVwoRNQdR1UUIlb9ksxp0QAONhynDluYmn_R4TOWuGIibKNmVCbnIKBXobOiTeB-LZx3xAOrqIHSc8EEb0ySQXPB_QkHf-i4eex28cMI1hxJ88FmC8Yze9GSLe_805-3x--li_Fpv3l7f1alPYUqlUmA5lq_qu65ZCqEa01XYrxr0Gu6xkY5ZgJKJUtqpBWdk327YSsm5bqECIGss5ay69lkKMhL227vJgIuMGDUKfFemdPivSZ0X6omhE5T_0QG5v6HQN-gU_iHJ5
CitedBy_id crossref_primary_10_1016_j_cviu_2024_104070
crossref_primary_10_1109_TMM_2023_3253048
crossref_primary_10_20965_jaciii_2024_p0255
crossref_primary_10_3169_mta_12_123
crossref_primary_10_1016_j_imavis_2023_104785
crossref_primary_10_1007_s00521_024_10956_y
Cites_doi 10.1145/2964284.2967191
10.1109/ICCV.2015.510
10.1609/aaai.v30i1.10451
10.1109/CVPR42600.2020.00059
10.1109/CVPR.2017.751
10.1109/CVPR.2016.115
10.1109/CVPR.2019.00413
10.1109/CVPR42600.2020.00965
10.1609/aaai.v33i01.33018545
10.1109/CVPR.2017.502
10.1109/TPAMI.2019.2894422
10.1109/TMM.2021.3057503
10.1109/CVPR.2014.339
10.1109/CVPR46437.2021.00471
10.1109/CVPR.2017.139
10.1109/ICCV.2017.115
10.1145/3474085.3475307
10.1109/TPAMI.2019.2896631
10.1109/CVPR.2017.486
10.1109/ICCV48922.2021.01317
10.1609/aaai.v32i1.11853
10.1109/CVPR.2013.365
10.1109/CVPR46437.2021.01398
10.1145/3394171.3413548
10.1109/CVPR.2017.497
10.1109/CVPR.2013.98
10.1016/j.patcog.2017.02.030
10.1109/CVPR.2014.223
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.1016/j.cviu.2022.103491
DatabaseName CrossRef
DatabaseTitle CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
Computer Science
ExternalDocumentID 10_1016_j_cviu_2022_103491
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
6TJ
7-5
71M
8P~
AABNK
AAEDT
AAEDW
AAIKC
AAIKJ
AAKOC
AALRI
AAMNW
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
AAYXX
ABBOA
ABEFU
ABFNM
ABJNI
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFS
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADFGL
ADJOM
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AGCQF
AGHFR
AGQPQ
AGRNS
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
BNPGV
CAG
CITATION
COF
CS3
DM4
DU5
EBS
EFBJH
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HF~
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG5
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
XPP
ZMT
~G-
ID FETCH-LOGICAL-c366t-ade296fddd50068094bb0d5071c5428a51a2ee26c4716c2f8b9402799141007e3
ISSN 1077-3142
IngestDate Thu Apr 24 22:52:38 EDT 2025
Tue Jul 01 04:32:08 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c366t-ade296fddd50068094bb0d5071c5428a51a2ee26c4716c2f8b9402799141007e3
ORCID 0000-0002-3008-5127
ParticipantIDs crossref_citationtrail_10_1016_j_cviu_2022_103491
crossref_primary_10_1016_j_cviu_2022_103491
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2022-09-00
PublicationDateYYYYMMDD 2022-09-01
PublicationDate_xml – month: 09
  year: 2022
  text: 2022-09-00
PublicationDecade 2020
PublicationTitle Computer vision and image understanding
PublicationYear 2022
References Li (10.1016/j.cviu.2022.103491_b14) 2021
Xu (10.1016/j.cviu.2022.103491_b44) 2021
10.1016/j.cviu.2022.103491_b17
Li (10.1016/j.cviu.2022.103491_b13) 2017
10.1016/j.cviu.2022.103491_b15
Fan (10.1016/j.cviu.2022.103491_b5) 2021
Zhang (10.1016/j.cviu.2022.103491_b46) 2019; 41
10.1016/j.cviu.2022.103491_b25
Liu (10.1016/j.cviu.2022.103491_b20) 2016
10.1016/j.cviu.2022.103491_b22
10.1016/j.cviu.2022.103491_b23
Zhu (10.1016/j.cviu.2022.103491_b48) 2022; 24
Wang (10.1016/j.cviu.2022.103491_b42) 2016
Simonyan (10.1016/j.cviu.2022.103491_b31) 2014; 27
Ranzato (10.1016/j.cviu.2022.103491_b29) 2014
Li (10.1016/j.cviu.2022.103491_b12) 2014
Misra (10.1016/j.cviu.2022.103491_b24) 2016
10.1016/j.cviu.2022.103491_b49
Evangelidis (10.1016/j.cviu.2022.103491_b4) 2014
10.1016/j.cviu.2022.103491_b10
Liu (10.1016/j.cviu.2022.103491_b18) 2019; 42
10.1016/j.cviu.2022.103491_b11
Fan (10.1016/j.cviu.2022.103491_b7) 2021
Pedregosa (10.1016/j.cviu.2022.103491_b27) 2011; 12
10.1016/j.cviu.2022.103491_b39
Rahmani (10.1016/j.cviu.2022.103491_b28) 2014
10.1016/j.cviu.2022.103491_b37
10.1016/j.cviu.2022.103491_b38
Loshchilov (10.1016/j.cviu.2022.103491_b21) 2019
10.1016/j.cviu.2022.103491_b8
10.1016/j.cviu.2022.103491_b9
10.1016/j.cviu.2022.103491_b43
10.1016/j.cviu.2022.103491_b40
10.1016/j.cviu.2022.103491_b41
Du (10.1016/j.cviu.2022.103491_b2) 2015
Srivastava (10.1016/j.cviu.2022.103491_b34) 2015
10.1016/j.cviu.2022.103491_b47
10.1016/j.cviu.2022.103491_b6
10.1016/j.cviu.2022.103491_b45
10.1016/j.cviu.2022.103491_b1
10.1016/j.cviu.2022.103491_b3
Smith (10.1016/j.cviu.2022.103491_b33) 2017
10.1016/j.cviu.2022.103491_b26
Li (10.1016/j.cviu.2022.103491_b16) 2018
10.1016/j.cviu.2022.103491_b32
10.1016/j.cviu.2022.103491_b30
10.1016/j.cviu.2022.103491_b35
10.1016/j.cviu.2022.103491_b36
Liu (10.1016/j.cviu.2022.103491_b19) 2017; 68
References_xml – ident: 10.1016/j.cviu.2022.103491_b39
  doi: 10.1145/2964284.2967191
– ident: 10.1016/j.cviu.2022.103491_b37
  doi: 10.1109/ICCV.2015.510
– ident: 10.1016/j.cviu.2022.103491_b49
  doi: 10.1609/aaai.v30i1.10451
– year: 2016
  ident: 10.1016/j.cviu.2022.103491_b24
  article-title: Shuffle and learn: unsupervised learning using temporal order verification
– year: 2018
  ident: 10.1016/j.cviu.2022.103491_b16
  article-title: Unsupervised learning of view-invariant action representations
– start-page: 1
  year: 2021
  ident: 10.1016/j.cviu.2022.103491_b5
  article-title: Motion video-content: Towards unsupervised learning of motion representation from videos
– start-page: 4513
  year: 2014
  ident: 10.1016/j.cviu.2022.103491_b4
  article-title: Skeletal quads: Human action recognition using joint quadruples
– ident: 10.1016/j.cviu.2022.103491_b41
  doi: 10.1109/CVPR42600.2020.00059
– ident: 10.1016/j.cviu.2022.103491_b22
  doi: 10.1109/CVPR.2017.751
– year: 2021
  ident: 10.1016/j.cviu.2022.103491_b14
– ident: 10.1016/j.cviu.2022.103491_b30
  doi: 10.1109/CVPR.2016.115
– ident: 10.1016/j.cviu.2022.103491_b38
  doi: 10.1109/CVPR.2019.00413
– start-page: 464
  year: 2017
  ident: 10.1016/j.cviu.2022.103491_b33
  article-title: Cyclical learning rates for training neural networks
– ident: 10.1016/j.cviu.2022.103491_b35
  doi: 10.1109/CVPR42600.2020.00965
– ident: 10.1016/j.cviu.2022.103491_b10
  doi: 10.1609/aaai.v33i01.33018545
– volume: 27
  start-page: 568
  year: 2014
  ident: 10.1016/j.cviu.2022.103491_b31
  article-title: Two-stream convolutional networks for action recognition in videos
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 579
  year: 2015
  ident: 10.1016/j.cviu.2022.103491_b2
  article-title: Skeleton based action recognition with convolutional neural network
– ident: 10.1016/j.cviu.2022.103491_b1
  doi: 10.1109/CVPR.2017.502
– volume: 42
  start-page: 494
  year: 2019
  ident: 10.1016/j.cviu.2022.103491_b18
  article-title: Feature boosting network for 3d pose estimation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2019.2894422
– volume: 24
  start-page: 668
  year: 2022
  ident: 10.1016/j.cviu.2022.103491_b48
  article-title: Temporal cross-layer correlation mining for action recognition
  publication-title: IEEE Trans. Multimed.
  doi: 10.1109/TMM.2021.3057503
– start-page: 34
  year: 2021
  ident: 10.1016/j.cviu.2022.103491_b44
  article-title: Unsupervised motion representation learning with capsule autoencoders
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.cviu.2022.103491_b40
  doi: 10.1109/CVPR.2014.339
– ident: 10.1016/j.cviu.2022.103491_b15
  doi: 10.1109/CVPR46437.2021.00471
– start-page: 601
  year: 2017
  ident: 10.1016/j.cviu.2022.103491_b13
  article-title: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn
– ident: 10.1016/j.cviu.2022.103491_b26
  doi: 10.1109/CVPR.2017.139
– start-page: 742
  year: 2014
  ident: 10.1016/j.cviu.2022.103491_b28
  article-title: Hopc: Histogram of oriented principal components of 3d pointclouds for action recognition
– ident: 10.1016/j.cviu.2022.103491_b11
  doi: 10.1109/ICCV.2017.115
– ident: 10.1016/j.cviu.2022.103491_b36
  doi: 10.1145/3474085.3475307
– start-page: 1
  year: 2021
  ident: 10.1016/j.cviu.2022.103491_b7
  article-title: Deep hierarchical representation of point cloud videos via spatio-temporal decomposition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 41
  start-page: 1963
  year: 2019
  ident: 10.1016/j.cviu.2022.103491_b46
  article-title: View adaptive neural networks for high performance skeleton-based human action recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2019.2896631
– ident: 10.1016/j.cviu.2022.103491_b9
  doi: 10.1109/CVPR.2017.486
– year: 2014
  ident: 10.1016/j.cviu.2022.103491_b29
– ident: 10.1016/j.cviu.2022.103491_b45
  doi: 10.1109/ICCV48922.2021.01317
– ident: 10.1016/j.cviu.2022.103491_b47
  doi: 10.1609/aaai.v32i1.11853
– year: 2019
  ident: 10.1016/j.cviu.2022.103491_b21
  article-title: Decoupled weight decay regularization
– start-page: 332
  year: 2014
  ident: 10.1016/j.cviu.2022.103491_b12
  article-title: 3D human pose estimation from monocular images with deep convolutional neural network
– volume: 12
  start-page: 2825
  year: 2011
  ident: 10.1016/j.cviu.2022.103491_b27
  article-title: Scikit-learn: Machine learning in Python
  publication-title: J. Mach. Learn. Res.
– ident: 10.1016/j.cviu.2022.103491_b43
  doi: 10.1109/CVPR.2013.365
– ident: 10.1016/j.cviu.2022.103491_b32
– ident: 10.1016/j.cviu.2022.103491_b6
  doi: 10.1109/CVPR46437.2021.01398
– start-page: 843
  year: 2015
  ident: 10.1016/j.cviu.2022.103491_b34
  article-title: Unsupervised learning of video representations using lstms
– start-page: 20
  year: 2016
  ident: 10.1016/j.cviu.2022.103491_b42
  article-title: Temporal segment networks: Towards good practices for deep action recognition
– ident: 10.1016/j.cviu.2022.103491_b17
  doi: 10.1145/3394171.3413548
– ident: 10.1016/j.cviu.2022.103491_b23
  doi: 10.1109/CVPR.2017.497
– ident: 10.1016/j.cviu.2022.103491_b25
  doi: 10.1109/CVPR.2013.98
– ident: 10.1016/j.cviu.2022.103491_b3
– start-page: 816
  year: 2016
  ident: 10.1016/j.cviu.2022.103491_b20
  article-title: Spatio-temporal lstm with trust gates for 3d human action recognition
– volume: 68
  start-page: 346
  year: 2017
  ident: 10.1016/j.cviu.2022.103491_b19
  article-title: Enhanced skeleton visualization for view invariant human action recognition
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2017.02.030
– ident: 10.1016/j.cviu.2022.103491_b8
  doi: 10.1109/CVPR.2014.223
SSID ssj0011491
Score 2.4160144
SourceID crossref
SourceType Enrichment Source
Index Database
StartPage 103491
Title An asymmetrical-structure auto-encoder for unsupervised representation learning of skeleton sequences
Volume 222
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1La-MwEBZ9XLqHvpft9oEOvQWbWJGc-BiWllJoTyn0ZiRZhrSNHXC8tHvY394Zy7Kdkpa2FxOEIozmYzyfNN8MIeeGCzaScuQlEMx7PALOqlQQeEMJn_e-YTrVqHe-uQ2v7vj1vbhv2x1V6pKF8vW_lbqS71gVxsCuqJL9gmWbRWEAfoN94QkWhuenbDzOerJ4mc2wKxbstWeLwVZXAuUi97BGJZaKwEzCMivKOfqFwqBeZd6qjjLXOaLKfi4e4TuEpTaaHOtu-Op6QPSsJN3ePMww7afsimTa0-i8rGAylc_T9ro_n9Xqmol8xF5O3ZMHIK0utco5y_4Qzzj5kjdlVmZc-8MAy98EK121PTV48PXfaenj8n47ebku9pvvVZNF6BLUHmJcI8Y1YrvGOtlkQBuwo4X_v0n5AepXdVBs3rsWUdl8v7fv0QlUOhHHZJds11SBjq3d98iayfbJTk0baO2UCxhyVnFj--RHp8zkATHjjK7GCe3ihAJOaBcndBkn1OGE5il1OKENTg7J3eXF5M-VV7fX8PQgDBeeTAyLwjRJElF1YIm4Uv0E-YEWQEqlCCQzhoUa4pdQs3SkIt5nQyAUHFNrzOAn2cjyzPwiVKRyZEIeKaDfPBEKpiih08HAAAFOQnFEAreXsa5rz2MLlKf4fRsekV7zn7mtvPLB7N9fmn1MtlpAn5AN2HVzCsHlQp1ViHkF_v9_Pg
linkProvider Elsevier
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=An+asymmetrical-structure+auto-encoder+for+unsupervised+representation+learning+of+skeleton+sequences&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Zhou%2C+Jiaxin&rft.au=Komuro%2C+Takashi&rft.date=2022-09-01&rft.issn=1077-3142&rft.volume=222&rft.spage=103491&rft_id=info:doi/10.1016%2Fj.cviu.2022.103491&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cviu_2022_103491
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon