Action recognition based on RGB and skeleton data sets: A survey

Action recognition is a major branch of computer vision research. As a widely used technology, action recognition has been applied to human–computer interaction, intelligent pension, and intelligent transportation system. Because of the explosive growth of action recognition related methods, the per...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 512; pp. 287 - 306
Main Authors: Yue, Rujing, Tian, Zhiqiang, Du, Shaoyi
Format: Journal Article
Language:English
Published: Elsevier B.V 01.11.2022
Subjects:
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Action recognition is a major branch of computer vision research. As a widely used technology, action recognition has been applied to human–computer interaction, intelligent pension, and intelligent transportation system. Because of the explosive growth of action recognition related methods, the performance of action recognition on many difficult data sets has improved significantly. In terms of the different data sets used for action recognition, action recognition can mainly be divided into RGB-based action recognition method and skeleton-based action recognition method. The former method can take advantage of the prior knowledge of image recognition. However, it has high requirements for computing power and storage ability, and it is difficult to avoid the influence of irrelevant background and illumination. In contrast, the latter method’s calculation amount and required storage space are reduced significantly. However, it lacks context information that is useful for action recognition. This review provides a comprehensive description of these two methods, covering the milestone algorithms, the state-of-the-art algorithms, the commonly used data sets, evaluation metrics, challenges, and promising future directions. So far as we know, this work is the first survey covering traditional methods of action recognition, RGB-based end-to-end action recognition method, pose estimation, and skeleton-based action recognition in one review. This survey aims to help scholars who study action recognition technology to systematically learn action recognition technology, select data sets, understand current challenges, and choose promising future research directions.
AbstractList Action recognition is a major branch of computer vision research. As a widely used technology, action recognition has been applied to human–computer interaction, intelligent pension, and intelligent transportation system. Because of the explosive growth of action recognition related methods, the performance of action recognition on many difficult data sets has improved significantly. In terms of the different data sets used for action recognition, action recognition can mainly be divided into RGB-based action recognition method and skeleton-based action recognition method. The former method can take advantage of the prior knowledge of image recognition. However, it has high requirements for computing power and storage ability, and it is difficult to avoid the influence of irrelevant background and illumination. In contrast, the latter method’s calculation amount and required storage space are reduced significantly. However, it lacks context information that is useful for action recognition. This review provides a comprehensive description of these two methods, covering the milestone algorithms, the state-of-the-art algorithms, the commonly used data sets, evaluation metrics, challenges, and promising future directions. So far as we know, this work is the first survey covering traditional methods of action recognition, RGB-based end-to-end action recognition method, pose estimation, and skeleton-based action recognition in one review. This survey aims to help scholars who study action recognition technology to systematically learn action recognition technology, select data sets, understand current challenges, and choose promising future research directions.
Author Tian, Zhiqiang
Yue, Rujing
Du, Shaoyi
Author_xml – sequence: 1
  givenname: Rujing
  surname: Yue
  fullname: Yue, Rujing
  organization: School of Software Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China
– sequence: 2
  givenname: Zhiqiang
  surname: Tian
  fullname: Tian, Zhiqiang
  organization: School of Software Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China
– sequence: 3
  givenname: Shaoyi
  surname: Du
  fullname: Du, Shaoyi
  organization: Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shaanxi, China
BookMark eNqFkMFKAzEQhoNUsK2-gYe8wK6TbHez24NYS61CQZDeQzaZldQ2K0la6NubWk8e9DQ_A9_PzDciA9c7JOSWQc6AVXeb3OFe97ucA-c5NDkIdkGGrBY8q3ldDcgQGl5mvGD8ioxC2AAwwXgzJA8zHW3vqEfdvzv7nVsV0NAU3paPVDlDwwduMaaFUVHRgDFM6YyGvT_g8Zpcdmob8OZnjsn6abGeP2er1-XLfLbKdCF4zGrNKyVAcF4ANi0qrCfaCNa1hUlXd6wqoUBgKBiY2lSqLVVZdoCFVhUXxZhMzrXa9yF47OSntzvlj5KBPEmQG3mWIE8SJDQySUjY9BembVSnL6NXdvsffH-GMf11sOhl0BadRmOTrihNb_8u-ALDG3xQ
CitedBy_id crossref_primary_10_3390_electronics13234733
crossref_primary_10_1016_j_compbiomed_2024_109399
crossref_primary_10_1016_j_neucom_2025_131078
crossref_primary_10_1142_S0218126625504079
crossref_primary_10_1016_j_neucom_2023_03_001
crossref_primary_10_1007_s13042_023_01774_0
crossref_primary_10_1007_s13735_023_00301_9
crossref_primary_10_1016_j_jmsy_2024_08_019
crossref_primary_10_1007_s11760_025_04366_3
crossref_primary_10_1016_j_patrec_2025_01_020
crossref_primary_10_1016_j_aei_2025_103315
crossref_primary_10_1016_j_asoc_2023_111166
crossref_primary_10_1061_JCEMD4_COENG_15830
crossref_primary_10_3390_inventions9040090
crossref_primary_10_1016_j_compbiomed_2023_107420
crossref_primary_10_1016_j_neucom_2025_129697
crossref_primary_10_3390_electronics14071307
crossref_primary_10_1049_ipr2_12703
crossref_primary_10_1111_1749_4877_12985
crossref_primary_10_1016_j_engappai_2025_111996
crossref_primary_10_1109_JBHI_2024_3511601
crossref_primary_10_1007_s11760_024_03613_3
crossref_primary_10_1109_LSP_2024_3525398
crossref_primary_10_1016_j_rcim_2025_103089
crossref_primary_10_1007_s11263_025_02484_6
crossref_primary_10_1038_s41598_025_06839_4
crossref_primary_10_1016_j_neunet_2023_07_051
crossref_primary_10_1016_j_engappai_2024_109569
crossref_primary_10_1007_s11042_023_15334_9
crossref_primary_10_1109_ACCESS_2023_3309420
crossref_primary_10_1007_s00371_024_03424_0
crossref_primary_10_3390_app15158746
crossref_primary_10_2196_51996
crossref_primary_10_1016_j_neucom_2023_126903
crossref_primary_10_1186_s13634_024_01156_w
crossref_primary_10_1016_j_neucom_2024_128636
crossref_primary_10_1016_j_imavis_2025_105689
crossref_primary_10_3390_app13042058
crossref_primary_10_3390_s23115179
crossref_primary_10_1016_j_neucom_2024_127482
crossref_primary_10_3390_ani14121774
crossref_primary_10_1016_j_knosys_2024_112453
crossref_primary_10_1016_j_neucom_2023_03_070
crossref_primary_10_1049_ipr2_12754
Cites_doi 10.1109/TMM.2019.2944745
10.1109/TPAMI.2019.2894422
10.1007/s11042-018-7108-9
10.1117/1.JEI.23.3.033016
10.1609/aaai.v34i07.6759
10.1109/TMM.2019.2960588
10.1007/s11263-022-01594-9
10.3390/su13020970
10.1016/S0019-9958(71)90706-6
10.1016/j.patrec.2017.08.015
10.14358/PERS.76.10.1123
10.1016/j.cviu.2017.10.011
10.1016/j.cviu.2013.01.013
10.1609/aaai.v32i1.11853
10.3390/app9102126
10.3390/s150305197
10.1016/j.jksuci.2019.09.004
10.1109/TPAMI.2017.2712608
10.1109/ACCESS.2020.3049029
10.1609/aaai.v31i1.11212
10.1016/j.patcog.2018.07.028
10.1109/ASAP.2019.00-44
10.1109/TPAMI.2019.2916873
10.1609/aaai.v30i1.10451
10.1109/CVPR.1997.609450
10.1109/TCSVT.2016.2643161
10.1007/11744085_28
10.1038/nbt1206-1565
10.5220/0007555407440748
10.1177/0278364917693927
10.1007/s00371-019-01644-3
10.1007/978-3-319-04114-8_40
10.1016/j.asoc.2019.105820
10.1049/iet-cvi.2016.0355
10.1016/j.gaitpost.2021.04.005
10.1038/nbt1004-1315
10.1109/TMM.2015.2505089
10.1007/s11042-017-5251-3
10.1609/aaai.v32i1.12324
10.3390/s21020452
10.1007/978-1-4471-4730-5_3
10.1109/TCSVT.2016.2576761
10.1109/ICPR.2004.1334462
10.1016/j.cviu.2010.10.002
10.1007/s10489-020-01823-z
10.4018/IJACI.2017100101
10.1109/TIP.2018.2812099
10.1016/j.imavis.2016.06.007
10.1007/978-3-031-19772-7_21
10.1007/s00426-011-0383-y
10.1007/s11760-014-0677-9
10.1109/CVPR52688.2022.01957
10.1007/BFb0053999
10.1016/j.patrec.2018.07.011
10.1609/aaai.v32i1.12333
10.1109/TPAMI.2017.2771306
10.1016/j.cad.2020.102984
10.1109/ACCESS.2020.3023599
10.1609/aaai.v33i01.33018561
10.1109/TII.2019.2910876
10.1016/j.cag.2012.11.004
10.1109/TPAMI.2022.3183112
10.1002/jgt.3190080102
10.1109/TPAMI.2019.2896631
10.1609/aaai.v33i01.33018989
10.1109/JBHI.2019.2904321
10.1016/j.patcog.2015.11.019
10.1007/978-3-319-10578-9_45
10.1109/TNNLS.2020.2978386
10.1186/s13640-020-00501-x
10.1109/ACCESS.2019.2910604
10.1016/j.procs.2018.07.059
10.1080/00401706.1991.10484833
10.1038/scientificamerican0675-76
10.1007/978-1-4899-7641-3_9
10.1007/s00138-010-0298-4
10.1109/TPAMI.2012.59
10.1117/1.JEI.27.4.043050
10.1016/j.procs.2018.05.048
10.1109/CVPR.1992.223161
10.1111/j.1467-9280.1997.tb00442.x
10.3390/s20123499
10.1007/978-1-4615-0377-4_5
10.1109/TIP.2020.3028207
10.1016/j.neucom.2020.05.118
10.1007/s11263-012-0594-8
10.1109/ACCESS.2018.2869751
10.1109/LSENS.2018.2878572
10.1109/TPAMI.2019.2929257
10.1016/j.jmsy.2020.04.007
10.1007/978-3-030-20893-6_23
10.1109/TNN.2008.2005605
10.1609/aaai.v36i1.19957
10.3390/sym12050744
10.1109/CVPR52688.2022.01933
10.1007/978-3-642-15549-9_36
10.1016/j.imavis.2017.01.010
10.1109/TMM.2017.2749159
10.1007/978-3-030-58558-7_31
10.3390/s20174758
10.1109/5.18626
10.1109/CVPR.1998.698711
10.1109/CVPR42600.2020.00059
10.1609/aaai.v33i01.33018303
10.1016/j.cad.2016.05.009
10.1016/j.patcog.2016.05.019
ContentType Journal Article
Copyright 2022 Elsevier B.V.
Copyright_xml – notice: 2022 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2022.09.071
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-8286
EndPage 306
ExternalDocumentID 10_1016_j_neucom_2022_09_071
S0925231222011596
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AADPK
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXLA
AAXUO
AAYFN
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SSN
SSV
SSZ
T5K
ZMT
~G-
29N
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
SEW
WUQ
XPP
~HD
ID FETCH-LOGICAL-c372t-8c26a7072230e9beae84cd71fb3d202f16503e01e710d8d6ab5a55f0e3ca6273
ISICitedReferencesCount 59
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000862479300004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0925-2312
IngestDate Sat Nov 29 07:12:59 EST 2025
Tue Nov 18 22:34:40 EST 2025
Fri Feb 23 02:39:21 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords RGB-based end-to-end action recognition method
Skeleton-based cascaded action recognition method
Pose estimation
Transfer learning
Unsupervised learning
Self-supervised learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c372t-8c26a7072230e9beae84cd71fb3d202f16503e01e710d8d6ab5a55f0e3ca6273
PageCount 20
ParticipantIDs crossref_primary_10_1016_j_neucom_2022_09_071
crossref_citationtrail_10_1016_j_neucom_2022_09_071
elsevier_sciencedirect_doi_10_1016_j_neucom_2022_09_071
PublicationCentury 2000
PublicationDate 2022-11-01
2022-11-00
PublicationDateYYYYMMDD 2022-11-01
PublicationDate_xml – month: 11
  year: 2022
  text: 2022-11-01
  day: 01
PublicationDecade 2020
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2022
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Cheng, Zhang, He, Chen, Cheng, Lu (b0105) 2020
Xiong, Zhang, Wang, Liu, Gao (b0475) 2020; 56
Ghadiyaram, Tran, Mahajan (b1220) 2019
Liu, Shahroudy, Perez, Wang, Duan, Kot (b1040) 2019; 42
Lima, Fernandes, Barros (b0585) 2017
Eddy (b0255) 2004; 22
Ye, Pu, Zhong, Li, Xie, Tang (b0880) 2020
Kumar Dwivedi, Gupta, Mitra, Ahmed, Jain (b0140) 2019
Papadopoulos, Axenopoulos, Daras (b0415) 2014
Zhu, Zhang, Shen, Song (b0320) 2016; 42
Tran, Wang, Torresani, Ray, LeCun, Paluri (b0570) 2018
C. Schuldt, I. Laptev, B. Caputo, Recognizing human actions: a local svm approach, in: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, Vol. 3, IEEE, 2004, pp. 32–36.
Zhang, Xu, Tao (b0875) 2020
Tsai, Hsu, Wang, Huang (b1135) 2020; 20
Chaquet, Carmona, Fernández-Caballero (b0090) 2013; 117
Juang, Rabiner (b0270) 1991; 33
Maeda, Ewerton, Neumann, Lioutikov, Peters (b0035) 2017; 36
Stroud, Ross, Sun, Deng, Sukthankar (b0545) 2020
Du, Fu, Wang (b0770) 2015
Shen, Wu, Xu (b1080) 2021
Khalid, Yu (b1300) 2018
Sun, Xiao, Liu, Wang (b0130) 2019
Si, Chen, Wang, Wang, Tan (b0750) 2019
Chen, Zhang, Yuan, Li, Deng, Hu (b0890) 2021
Thoker, Doughty, Snoek (b1385) 2021
Papadopoulos, Daras (b1165) 2016; 28
Du, Wang, Wang (b1110) 2015
F. Lv, R. Nevatia, Recognition and segmentation of 3-d human action using hmm and multi-class adaboost, in: European conference on computer vision, Springer, 2006, pp. 359–372.
Plesník (b0265) 1984; 8
Weinland, Özuysal, Fua (b0185) 2010
Yang, Tian (b0400) 2012
Yang, Yuan, Li, Du, Xing, Hu, Maybank (b0515) 2019; 85
Wang, Schmid (b0250) 2013
Hara, Kataoka, Satoh (b0535) 2017
Hussein, Torki, Gowayyed, El-Saban (b0380) 2013
S. Takeuchi, S. Tamura, S. Hayamizu, Human action recognition using acceleration information based on hidden markov model, in: Proceedings: APSIPA ASC 2009: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference, Asia-Pacific Signal and Information Processing Association, 2009 Annual, 2009, pp. 829–832.
Qin, Mo, Li, Luo (b0900) 2020; 36
Carreira, Zisserman (b0955) 2017
Gales, Young (b0280) 2007; 1
Song, Zhang, Wang (b0920) 2019
Materzynska, Xiao, Herzig, Xu, Wang, Darrell (b1245) 2020
Cao, Simon, Wei, Sheikh (b0705) 2017
Presti, La Cascia (b0115) 2016; 53
Cui, Zhu, Hua, Yin, Liu (b0815) 2018; 27
Noble (b0175) 2006; 24
Ahad, Tan, Kim, Ishikawa (b0215) 2012; 23
He, Wu, Cheng, Yuan, Jiang (b0600) 2021; 444
Yan, Xiong, Lin (b0835) 2018
Ke, Bennamoun, An, Sohel, Boussaid (b0810) 2018; 27
Gammulle, Denman, Sridharan, Fookes (b0500) 2017
Jaouedi, Boujnah, Bouhlel (b0940) 2020; 32
S. Alfasly, J. Lu, C. Xu, Y. Zou, Learnable irrelevant modality dropout for multimodal action recognition on modality-specific annotated videos, arXiv preprint arXiv:2203.03014 (2022).
Nagrani, Sun, Ross, Sukthankar, Schmid, Zisserman (b1285) 2020
Shi, Zhang, Cheng, Lu (b0870) 2019
Zheng, Hong, Zhang, Li, Li (b0635) 2016; 78
Khalid, Gochoo, Jalal, Kim (b0010) 2021; 13
Mishra, Verma, Reddy, Arulkumar, Rai, Mittal (b0145) 2018
Vemulapalli, Arrate, Chellappa (b0385) 2014
Ke, Bennamoun, An, Sohel, Boussaid (b0805) 2017
Zheng, Li, Zhang, Huang, Wang (b0740) 2019
He, Zhang, Ren, Sun (b0670) 2016
Ryoo, Aggarwal (b0340) 2006; Vol. 2
Lu, Yao, Zhao, Sun, Zhang (b0580) 2019; 78
Liu, Shahroudy, Xu, Kot, Wang (b1045) 2017; 40
Wang, Hu, Lai, Zhang, Zheng (b1430) 2019
Li, Liu, Zhang, Ni, Wang, Li (b0480) 2021
T. Lan, T.-C. Chen, S. Savarese, A hierarchical representation for future action prediction, in: European conference on computer vision, Springer, 2014, pp. 689–704.
Song, Zhang, Shan, Wang (b0925) 2020
J. Carreira, E. Noland, C. Hillier, A. Zisserman, A short note on the kinetics-700 human action dataset, arXiv preprint arXiv:1907.06987 (2019).
Shu, Tang, Qi, Song, Li, Zhang (b1150) 2017
Bates, Ramirez-Amaro, Inamura, Cheng (b0045) 2017
S. Suthaharan, Support vector machine, in: Machine learning models and algorithms for big data classification, Springer, 2016, pp. 207–235.
D. He, F. Li, Q. Zhao, X. Long, Y. Fu, S. Wen, Exploiting spatial-temporal modelling and multi-modal fusion for human action recognition, arXiv preprint arXiv:1806.10319 (2018).
W. Kay, J. Carreira, K. Simonyan, B. Zhang, C. Hillier, S. Vijayanarasimhan, F. Viola, T. Green, T. Back, P. Natsev, et al., The kinetics human action video dataset, arXiv preprint arXiv:1705.06950 (2017).
Yang, Liu, Lu, Er, Kot (b1255) 2020
Iqbal, Garbade, Gall (b1265) 2017
Sudha, Sriraghav, Jacob, Manisha (b0050) 2017; 8
Aho, Ullman (b0335) 1971; 19
Tu, Liu, Meng, Liu, Ding (b1190) 2018
Chen, Wu, Konrad, Ishwar (b0455) 2017
Chen, Wang, Peng, Zhang, Yu, Sun (b0660) 2018
Caetano, Brémond, Schwartz (b0780) 2019
Sudhakaran, Escalera, Lanz (b0985) 2020
K. Liu, W. Liu, C. Gan, M. Tan, H. Ma, T-c3d: Temporal convolutional 3d network for real-time action recognition, in: Proceedings of the AAAI conference on artificial intelligence, Vol. 32, 2018.
Liu, Akhtar, Mian (b0165) 2020
H. Fan, C. Luo, C. Zeng, M. Ferianc, Z. Que, S. Liu, X. Niu, W. Luk, F-e3d: Fpga-based acceleration of an efficient 3d convolutional neural network for human action recognition, in: 2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP), Vol. 2160, IEEE, 2019, pp. 1–8.
Pony, Naeh, Mannor (b0155) 2021
Oliver, Horvitz, Garg (b0310) 2002
Kwon, Kim, Kwak, Cho (b0990) 2021
Urgesi, Savonitto, Fabbro, Aglioti (b1410) 2012; 76
Simon, Joo, Matthews, Sheikh (b0710) 2017
Zhao, Xu, Su, Ji (b0325) 2019
Wang, Tong, Ji, Wu (b1000) 2021
Xu, Hospedales, Gong (b1305) 2015
Y. Zhu, Z. Lan, S. Newsam, A. Hauptmann, Hidden two-stream convolutional networks for action recognition, in: Asian conference on computer vision, Springer, 2018, pp. 363–378.
Wang, Xiong, Lin, Van Gool (b1210) 2017
Jing, Ye, Yang, Tian (b0575) 2017
Guenterberg, Ghasemzadeh, Loseu, Jafari (b0300) 2009
Cai, Jiang, Han, Jia, Lu (b0210) 2021
Fan, Yu, Ding, Yang, Kankanhalli (b0645) 2020
Leberl, Irschara, Pock, Meixner, Gruber, Scholz, Wiechert (b0630) 2010; 76
Elharrouss, Almaadeed, Al-Maadeed, Bouridane, Beghdadi (b0005) 2021; 51
Kong, Tao, Fu (b1420) 2017
Y. Wang, Y. Xiao, F. Xiong, W. Jiang, Z. Cao, J.T. Zhou, J. Yuan, 3dv: 3d dynamic voxel for action recognition in depth video, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 511–520.
Li, Liu, Yongkang, Nishimura, Kankanhalli (b1140) 2020
A. Thatipelli, S. Narayan, S. Khan, R.M. Anwer, F.S. Khan, B. Ghanem, Spatio-temporal relation modeling for few-shot action recognition, arXiv preprint arXiv:2112.05132 (2021).
Li, Gavrilyuk, Gavves, Jain, Snoek (b1085) 2018; 166
A. Veenendaal, E. Jones, Z. Gang, E. Daly, S. Vartak, R. Patwardhan, Dynamic probabilistic network based human action recognition, arXiv preprint arXiv:1610.06395 (2016).
Dawar, Ostadabbas, Kehtarnavaz (b1195) 2018; 3
Munro, Damen (b1295) 2020
Eum, Yoon, Lee, Park (b0240) 2015; 15
Huynh-The, Hua, Kim (b1200) 2019; 16
Diwadkar, McNamara (b0190) 1997; 8
S. Song, C. Lan, J. Xing, W. Zeng, J. Liu, An end-to-end spatio-temporal attention model for human action recognition from skeleton data, in: Proceedings of the AAAI conference on artificial intelligence, Vol. 31, 2017.
Bagautdinov, Alahi, Fleuret, Fua, Savarese (b1145) 2017
Cai, Zhou, Wu, Luo, Li (b0410) 2015; 18
Gao, Oh, Grauman, Torresani (b1100) 2020
Kong, Fu (b0085) 2022; 130
Wang, He, Peng, Shao, Yang, Zhou, Hogg (b0160) 2021
De Boissiere, Noumeir (b1120) 2020; 8
Li, Huang, Wang, Hou, Yang (b0650) 2021
Xia, Gao (b1055) 2021; 9
Fan, Buch, Wang, Cao, Zhu, Niebles, Fei-Fei (b1095) 2020
Yang, Zhang, Cai, Xu (b1060) 2021; 21
Jiang, Wang, Gan, Wu, Yan (b0970) 2019
Li, Dai, Cheng, Chen, Lin, He (b0755) 2017
Arunnehru, Chamundeeswari, Bharathi (b0565) 2018; 133
T. Guo, H. Liu, Z. Chen, M. Liu, T. Wang, R. Ding, Contrastive learning from extremely augmented skeleton sequences for self-supervised action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, 2022, pp. 762–770.
Zhao, Man, Smith, Siddique, Guan (b0495) 2020; 2020
Shao, Zhao, Dai, Lin (b1025) 2020
Cao, Hidalgo, Simon, Wei, Sheikh (b0680) 2019; 43
H. Goto, J. Miura, J. Sugiyama, Human-robot collaborative assembly by on-line human action recognition based on an fsm task model, in: Human-robot interaction 2013 workshop on collaborative manipulation, 2013.
Han, Zhang, Zhuo, Huang, Zhang (b0470) 2018; 107
J. Carreira, E. Noland, A. Banki-Horvath, C. Hillier, A. Zisserman, A short note about kinetics-600, arXiv preprint arXiv:1808.01340 (2018).
M. Monfort, K. Ramakrishnan, A. Andonian, B.A. McNamara, A. Lascelles, B. Pan, Q. Fan, D. Gutfreund, R. Feris, A. Oliva, Multi-moments in time: Learning and interpreting models for multi-action video understanding, arXiv preprint arXiv:1911.00232 (2019).
Chen, Chen, Chen, Lee (b0405) 2006
Kumar, Kumar, Seah, Xia, Shao (b1400) 2020
Iosifidis, Tefas, Pitas (b1175) 2012
Li, Hou, Wang, Gao, Xu, Li (b0620) 2021
J. Gao, T. Zhang, C. Xu, I know the relationships: Zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs, in: Proceedings of the AAAI conference on artificial intelligence, Vol. 33, 2019, pp. 8303–8311.
Lan, Zhu, Zamir, Savarese (b0330) 2015
Zhu, Shao, Xie, Fang (b0070) 2016; 55
Shahroudy, Liu, Ng, Wang (b1035) 2016
Goyal, Ebrahimi Kahou, Michalski, Materzynska, Westphal, Kim, Haenel, Fruend, Yianilos, Mueller-Freitag (b0980) 2017
K. Soomro, A.R. Zamir, M. Shah, Ucf101: A dataset of 101 human actions classes from videos in the wild, arXiv preprint arXiv:1212.0402 (2012).
Zhang, Li, Ogunbona, Wang, Tang (b0100) 2016; 60
Jiang, Rozgic, Adali (b0550) 2017
Kim, Yun, Park, Choi (b1125) 2019
Yeung, Yang, Cheng, Du, Tong (b0125) 2021; 87
Johansson (b0170) 1975; 232
Singh, Kushwaha, Srivastava (b0020) 2019; 78
Liu, Wang, Hu, Duan, Kot (b0735) 2017
Zhang, Lan, Zeng, Xing, Xue, Zheng (b0110) 2020
Zhang, Lan, Xing, Zeng, Xue, Zheng (b0785) 2019; 41
Liu, Akhtar, Mian (b0800) 2019
Ji, Xu, Yang, Yu (b0510) 2012; 35
C.S. Pinhanez, A.F. Bobick, Human action detection using pnf propagation of temporal constraints, in: Proceedings. 1998 IEEE Computer
Choi (10.1016/j.neucom.2022.09.071_b1360) 2020
Zhou (10.1016/j.neucom.2022.09.071_b0200) 2021
10.1016/j.neucom.2022.09.071_b0260
Kong (10.1016/j.neucom.2022.09.071_b0085) 2022; 130
Ji (10.1016/j.neucom.2022.09.071_b0510) 2012; 35
Xu (10.1016/j.neucom.2022.09.071_b1305) 2015
Si (10.1016/j.neucom.2022.09.071_b1380) 2020
Khalid (10.1016/j.neucom.2022.09.071_b0010) 2021; 13
Elharrouss (10.1016/j.neucom.2022.09.071_b0005) 2021; 51
Dong (10.1016/j.neucom.2022.09.071_b1075) 2019; 9
Zheng (10.1016/j.neucom.2022.09.071_b0640) 2021; 132
Wu (10.1016/j.neucom.2022.09.071_b1105) 2018
Li (10.1016/j.neucom.2022.09.071_b1350) 2021
Liu (10.1016/j.neucom.2022.09.071_b0165) 2020
Shahroudy (10.1016/j.neucom.2022.09.071_b1035) 2016
Wang (10.1016/j.neucom.2022.09.071_b0590) 2018
Feichtenhofer (10.1016/j.neucom.2022.09.071_b0450) 2019
10.1016/j.neucom.2022.09.071_b1235
Yeung (10.1016/j.neucom.2022.09.071_b0125) 2021; 87
Zheng (10.1016/j.neucom.2022.09.071_b0635) 2016; 78
10.1016/j.neucom.2022.09.071_b0945
10.1016/j.neucom.2022.09.071_b0030
Dawar (10.1016/j.neucom.2022.09.071_b1195) 2018; 3
Herath (10.1016/j.neucom.2022.09.071_b0075) 2017; 60
Lu (10.1016/j.neucom.2022.09.071_b0580) 2019; 78
Eum (10.1016/j.neucom.2022.09.071_b0240) 2015; 15
Wang (10.1016/j.neucom.2022.09.071_b0245) 2013; 103
10.1016/j.neucom.2022.09.071_b0150
10.1016/j.neucom.2022.09.071_b1365
Hwang (10.1016/j.neucom.2022.09.071_b1395) 2021
Mishra (10.1016/j.neucom.2022.09.071_b0145) 2018
10.1016/j.neucom.2022.09.071_b0390
Tran (10.1016/j.neucom.2022.09.071_b0570) 2018
Hsiao (10.1016/j.neucom.2022.09.071_b1270) 2021
Wang (10.1016/j.neucom.2022.09.071_b1430) 2019
Sun (10.1016/j.neucom.2022.09.071_b0095) 2022
Xu (10.1016/j.neucom.2022.09.071_b0460) 2018
Wang (10.1016/j.neucom.2022.09.071_b0250) 2013
10.1016/j.neucom.2022.09.071_b1005
10.1016/j.neucom.2022.09.071_b1010
Sudha (10.1016/j.neucom.2022.09.071_b0050) 2017; 8
Ahsan (10.1016/j.neucom.2022.09.071_b1230) 2019
Cao (10.1016/j.neucom.2022.09.071_b0680) 2019; 43
Simon (10.1016/j.neucom.2022.09.071_b0710) 2017
10.1016/j.neucom.2022.09.071_b0285
10.1016/j.neucom.2022.09.071_b1375
Li (10.1016/j.neucom.2022.09.071_b0755) 2017
Kwon (10.1016/j.neucom.2022.09.071_b0490) 2018; 112
Cheng (10.1016/j.neucom.2022.09.071_b0105) 2020
Guenterberg (10.1016/j.neucom.2022.09.071_b0300) 2009
Wang (10.1016/j.neucom.2022.09.071_b0160) 2021
Wu (10.1016/j.neucom.2022.09.071_b0830) 2020; 32
Hara (10.1016/j.neucom.2022.09.071_b0535) 2017
Vo (10.1016/j.neucom.2022.09.071_b0355) 2014
10.1016/j.neucom.2022.09.071_b1015
He (10.1016/j.neucom.2022.09.071_b0600) 2021; 444
10.1016/j.neucom.2022.09.071_b0965
10.1016/j.neucom.2022.09.071_b0295
Rosani (10.1016/j.neucom.2022.09.071_b0345) 2014; 23
Akkaladevi (10.1016/j.neucom.2022.09.071_b0025) 2015
Caetano (10.1016/j.neucom.2022.09.071_b0780) 2019
Kumar Dwivedi (10.1016/j.neucom.2022.09.071_b0140) 2019
Vemulapalli (10.1016/j.neucom.2022.09.071_b0385) 2014
Chen (10.1016/j.neucom.2022.09.071_b0540) 2019
Hussein (10.1016/j.neucom.2022.09.071_b0380) 2013
10.1016/j.neucom.2022.09.071_b0290
Aho (10.1016/j.neucom.2022.09.071_b0335) 1971; 19
Juang (10.1016/j.neucom.2022.09.071_b0270) 1991; 33
Zhang (10.1016/j.neucom.2022.09.071_b0100) 2016; 60
Fan (10.1016/j.neucom.2022.09.071_b1095) 2020
De Boissiere (10.1016/j.neucom.2022.09.071_b1120) 2020; 8
10.1016/j.neucom.2022.09.071_b0730
Yang (10.1016/j.neucom.2022.09.071_b1355) 2021
Dai (10.1016/j.neucom.2022.09.071_b0425) 2019
Liu (10.1016/j.neucom.2022.09.071_b0655) 2019; 42
10.1016/j.neucom.2022.09.071_b0860
Chen (10.1016/j.neucom.2022.09.071_b0195) 2021
Gales (10.1016/j.neucom.2022.09.071_b0280) 2007; 1
Chaquet (10.1016/j.neucom.2022.09.071_b0090) 2013; 117
10.1016/j.neucom.2022.09.071_b0180
Wang (10.1016/j.neucom.2022.09.071_b0560) 2016; 27
10.1016/j.neucom.2022.09.071_b1390
Cai (10.1016/j.neucom.2022.09.071_b0210) 2021
Girdhar (10.1016/j.neucom.2022.09.071_b0615) 2019
Diwadkar (10.1016/j.neucom.2022.09.071_b0190) 1997; 8
Arunnehru (10.1016/j.neucom.2022.09.071_b0565) 2018; 133
Gammulle (10.1016/j.neucom.2022.09.071_b0500) 2017
Wang (10.1016/j.neucom.2022.09.071_b0720) 2018; 6
Li (10.1016/j.neucom.2022.09.071_b0530) 2017
10.1016/j.neucom.2022.09.071_b0625
10.1016/j.neucom.2022.09.071_b0745
Wei (10.1016/j.neucom.2022.09.071_b0700) 2016
Thoker (10.1016/j.neucom.2022.09.071_b1385) 2021
Yang (10.1016/j.neucom.2022.09.071_b0515) 2019; 85
Weinland (10.1016/j.neucom.2022.09.071_b0185) 2010
10.1016/j.neucom.2022.09.071_b1160
10.1016/j.neucom.2022.09.071_b1280
Perrett (10.1016/j.neucom.2022.09.071_b0610) 2019
Li (10.1016/j.neucom.2022.09.071_b0840) 2019
Shu (10.1016/j.neucom.2022.09.071_b1150) 2017
Rasouli (10.1016/j.neucom.2022.09.071_b1405) 2022
Zheng (10.1016/j.neucom.2022.09.071_b0740) 2019
Liu (10.1016/j.neucom.2022.09.071_b0850) 2020
Tran (10.1016/j.neucom.2022.09.071_b0440) 2017
10.1016/j.neucom.2022.09.071_b0995
Kong (10.1016/j.neucom.2022.09.071_b1420) 2017
Li (10.1016/j.neucom.2022.09.071_b0620) 2021
Stroud (10.1016/j.neucom.2022.09.071_b0545) 2020
Papadopoulos (10.1016/j.neucom.2022.09.071_b1165) 2016; 28
Jiang (10.1016/j.neucom.2022.09.071_b0970) 2019
Feichtenhofer (10.1016/j.neucom.2022.09.071_b0435) 2016
Liu (10.1016/j.neucom.2022.09.071_b0800) 2019
Shen (10.1016/j.neucom.2022.09.071_b1080) 2021
Scarselli (10.1016/j.neucom.2022.09.071_b0825) 2008; 20
Du (10.1016/j.neucom.2022.09.071_b1110) 2015
Wang (10.1016/j.neucom.2022.09.071_b1210) 2017
Mandal (10.1016/j.neucom.2022.09.071_b1310) 2019
10.1016/j.neucom.2022.09.071_b1290
Song (10.1016/j.neucom.2022.09.071_b0920) 2019
Nguyen (10.1016/j.neucom.2022.09.071_b1215) 2018
Johansson (10.1016/j.neucom.2022.09.071_b0170) 1975; 232
Wang (10.1016/j.neucom.2022.09.071_b1070) 2014
Tsai (10.1016/j.neucom.2022.09.071_b1135) 2020; 20
Zhou (10.1016/j.neucom.2022.09.071_b1275) 2020; 84
Liu (10.1016/j.neucom.2022.09.071_b1115) 2019
Eddy (10.1016/j.neucom.2022.09.071_b0255) 2004; 22
Cui (10.1016/j.neucom.2022.09.071_b0725) 2018
Han (10.1016/j.neucom.2022.09.071_b0470) 2018; 107
Leberl (10.1016/j.neucom.2022.09.071_b0630) 2010; 76
Noble (10.1016/j.neucom.2022.09.071_b0175) 2006; 24
10.1016/j.neucom.2022.09.071_b0520
Zhang (10.1016/j.neucom.2022.09.071_b0110) 2020
Xia (10.1016/j.neucom.2022.09.071_b1055) 2021; 9
Luvizon (10.1016/j.neucom.2022.09.071_b1260) 2018
10.1016/j.neucom.2022.09.071_b0525
10.1016/j.neucom.2022.09.071_b1065
Bilen (10.1016/j.neucom.2022.09.071_b1205) 2016
Xiong (10.1016/j.neucom.2022.09.071_b0475) 2020; 56
Yamamoto (10.1016/j.neucom.2022.09.071_b0350) 2006
Chen (10.1016/j.neucom.2022.09.071_b0890) 2021
Zhang (10.1016/j.neucom.2022.09.071_b0875) 2020
10.1016/j.neucom.2022.09.071_b1180
Dai (10.1016/j.neucom.2022.09.071_b0505) 2020; 86
Materzynska (10.1016/j.neucom.2022.09.071_b1245) 2020
Li (10.1016/j.neucom.2022.09.071_b1085) 2018; 166
Kwon (10.1016/j.neucom.2022.09.071_b0990) 2021
Zhou (10.1016/j.neucom.2022.09.071_b1240) 2015
Fan (10.1016/j.neucom.2022.09.071_b0645) 2020
10.1016/j.neucom.2022.09.071_b0895
Liu (10.1016/j.neucom.2022.09.071_b1040) 2019; 42
Chen (10.1016/j.neucom.2022.09.071_b0695) 2020; 12
10.1016/j.neucom.2022.09.071_b0420
Demir (10.1016/j.neucom.2022.09.071_b1090) 2021
Ghadiyaram (10.1016/j.neucom.2022.09.071_b1220) 2019
Zhang (10.1016/j.neucom.2022.09.071_b0760) 2017
Varol (10.1016/j.neucom.2022.09.071_b0950) 2017; 40
Gao (10.1016/j.neucom.2022.09.071_b1100) 2020
Sun (10.1016/j.neucom.2022.09.071_b0130) 2019
Alp (10.1016/j.neucom.2022.09.071_b0230) 2017
Qiao (10.1016/j.neucom.2022.09.071_b0690) 2017
Ke (10.1016/j.neucom.2022.09.071_b0805) 2017
Chen (10.1016/j.neucom.2022.09.071_b1320) 2021
10.1016/j.neucom.2022.09.071_b0305
Kuehne (10.1016/j.neucom.2022.09.071_b0960) 2011
Pony (10.1016/j.neucom.2022.09.071_b0155) 2021
Yang (10.1016/j.neucom.2022.09.071_b1255) 2020
Seemanthini (10.1016/j.neucom.2022.09.071_b0015) 2018; 132
Xiao (10.1016/j.neucom.2022.09.071_b0665) 2018
Shi (10.1016/j.neucom.2022.09.071_b0870) 2019
Jing (10.1016/j.neucom.2022.09.071_b0575) 2017
Koohzadi (10.1016/j.neucom.2022.09.071_b0080) 2017; 11
Chan (10.1016/j.neucom.2022.09.071_b0855) 2020; 20
Cao (10.1016/j.neucom.2022.09.071_b0705) 2017
Smaira (10.1016/j.neucom.2022.09.071_b1020) 2020
Lin (10.1016/j.neucom.2022.09.071_b1370) 2020
Li (10.1016/j.neucom.2022.09.071_b0480) 2021
10.1016/j.neucom.2022.09.071_b0795
10.1016/j.neucom.2022.09.071_b0675
Canton-Ferrer (10.1016/j.neucom.2022.09.071_b1170) 2006
Tekin (10.1016/j.neucom.2022.09.071_b1250) 2019
Si (10.1016/j.neucom.2022.09.071_b0750) 2019
Phang (10.1016/j.neucom.2022.09.071_b1130) 2019
Li (10.1016/j.neucom.2022.09.071_b0975) 2020
Rabiner (10.1016/j.neucom.2022.09.071_b0275) 1989; 77
Xia (10.1016/j.neucom.2022.09.071_b0395) 2012
Singh (10.1016/j.neucom.2022.09.071_b0020) 2019; 78
Duan (10.1016/j.neucom.2022.09.071_b0555) 2020
Shi (10.1016/j.neucom.2022.09.071_b0865) 2020; 29
Zhu (10.1016/j.neucom.2022.09.071_b0320) 2016; 42
Lima (10.1016/j.neucom.2022.09.071_b0585) 2017
10.1016/j.neucom.2022.09.071_b0445
Weinland (10.1016/j.neucom.2022.09.071_b0065) 2011; 115
Kumar (10.1016/j.neucom.2022.09.071_b1400) 2020
10.1016/j.neucom.2022.09.071_b0685
Elkholy (10.1016/j.neucom.2022.09.071_b0060) 2019; 24
Suma (10.1016/j.neucom.2022.09.071_b0055) 2013; 37
Liu (10.1016/j.neucom.2022.09.071_b0735) 2017
10.1016/j.neucom.2022.09.071_b1415
Angelini (10.1016/j.neucom.2022.09.071_b1185) 2019; 22
Zhao (10.1016/j.neucom.2022.09.071_b0495) 2020; 2020
Liu (10.1016/j.neucom.2022.09.071_b0595) 2016; Vol. 1
Huynh-The (10.1016/j.neucom.2022.09.071_b1200) 2019; 16
Duan (10.1016/j.neucom.2022.09.071_b0820) 2022
Kim (10.1016/j.neucom.2022.09.071_b1125) 2019
Li (10.1016/j.neucom.2022.09.071_b0205) 2021
Gu (10.1016/j.neucom.2022.09.071_b0225) 2018
10.1016/j.neucom.2022.09.071_b1425
Su (10.1016/j.neucom.2022.09.071_b1225) 2020
Li (10.1016/j.neucom.2022.09.071_b0650) 2021
Nagrani (10.1016/j.neucom.2022.09.071_b1285) 2020
Sabater (10.1016/j.neucom.2022.09.071_b1340) 2021
Papadopoulos (10.1016/j.neucom.2022.09.071_b0415) 2014
Patwardhan (10.1016/j.neucom.2022.09.071_b0365) 2015
Ryoo (10.1016/j.neucom.2022.09.071_b0340) 2006; Vol. 2
Lee (10.1016/j.neucom.2022.09.071_b0715) 2017
Chen (10.1016/j.neucom.2022.09.071_b0405) 2006
10.1016/j.neucom.2022.09.071_b0220
Bagautdinov (10.1016/j.neucom.2022.09.071_b1145) 2017
Urges
References_xml – volume: 42
  start-page: 494
  year: 2019
  end-page: 501
  ident: b0655
  article-title: Feature boosting network for 3d pose estimation
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– volume: 53
  start-page: 130
  year: 2016
  end-page: 147
  ident: b0115
  article-title: 3d skeleton-based human action classification: A survey
  publication-title: Pattern Recognition
– start-page: 5137
  year: 2018
  end-page: 5146
  ident: b1260
  article-title: 2d/3d pose estimation and action recognition using multitask deep learning, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 232
  start-page: 76
  year: 1975
  end-page: 89
  ident: b0170
  article-title: Visual motion perception
  publication-title: Scientific American
– volume: 23
  year: 2014
  ident: b0345
  article-title: Human action recognition using a context-free grammar
  publication-title: Journal of Electronic Imaging
– start-page: 12026
  year: 2019
  end-page: 12035
  ident: b0845
  article-title: Two-stream adaptive graph convolutional networks for skeleton-based action recognition, in
  publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
– volume: 11
  start-page: 623
  year: 2017
  end-page: 632
  ident: b0080
  article-title: Survey on deep learning methods in human action recognition
  publication-title: IET Computer Vision
– start-page: 1607
  year: 2018
  end-page: 1615
  ident: b0460
  article-title: Fully-coupled two-stream spatiotemporal networks for extremely low resolution action recognition
  publication-title: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
– reference: A. Thatipelli, S. Narayan, S. Khan, R.M. Anwer, F.S. Khan, B. Ghanem, Spatio-temporal relation modeling for few-shot action recognition, arXiv preprint arXiv:2112.05132 (2021).
– reference: D. He, F. Li, Q. Zhao, X. Long, Y. Fu, S. Wen, Exploiting spatial-temporal modelling and multi-modal fusion for human action recognition, arXiv preprint arXiv:1806.10319 (2018).
– start-page: 91
  year: 2022
  end-page: 97
  ident: b1405
  article-title: Multi-modal hybrid architecture for pedestrian action prediction
  publication-title: 2022 IEEE Intelligent Vehicles Symposium (IV)
– year: 2018
  ident: b0835
  article-title: Spatial temporal graph convolutional networks for skeleton-based action recognition
  publication-title: Thirty-second AAAI conference on artificial intelligence
– start-page: 2702
  year: 2016
  end-page: 2706
  ident: b0040
  article-title: Multimodal human action recognition in assistive human-robot interaction
  publication-title: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
– start-page: 395
  year: 2018
  end-page: 400
  ident: b0225
  article-title: Depth mhi based deep learning model for human action recognition
  publication-title: 2018 13th World Congress on Intelligent Control and Automation (WCICA)
– reference: F. Lv, R. Nevatia, Recognition and segmentation of 3-d human action using hmm and multi-class adaboost, in: European conference on computer vision, Springer, 2006, pp. 359–372.
– start-page: 635
  year: 2010
  end-page: 648
  ident: b0185
  article-title: Making action recognition robust to occlusions and viewpoint changes, in
  publication-title: European Conference on Computer Vision, Springer
– start-page: 1717
  year: 2020
  end-page: 1726
  ident: b1360
  article-title: Unsupervised and semi-supervised domain adaptation for action recognition from drones, in
  publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
– volume: 16
  start-page: 3100
  year: 2019
  end-page: 3111
  ident: b1200
  article-title: Encoding pose features to images with data augmentation for 3-d action recognition
  publication-title: IEEE Transactions on Industrial Informatics
– reference: K. Liu, W. Liu, C. Gan, M. Tan, H. Ma, T-c3d: Temporal convolutional 3d network for real-time action recognition, in: Proceedings of the AAAI conference on artificial intelligence, Vol. 32, 2018.
– year: 2020
  ident: b0645
  article-title: Pstnet: Point spatio-temporal convolution on point cloud sequences, in
– start-page: 171
  year: 2006
  end-page: 178
  ident: b0405
  article-title: Human action recognition using star skeleton, in
  publication-title: Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks
– volume: 13
  start-page: 970
  year: 2021
  ident: b0010
  article-title: Modeling two-person segmentation and locomotion for stereoscopic action identification: A sustainable video surveillance system
  publication-title: Sustainability
– start-page: 2641
  year: 2014
  end-page: 2648
  ident: b0355
  article-title: From stochastic grammar to bayes network: Probabilistic parsing of complex activity, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 12
  start-page: 744
  year: 2020
  ident: b0695
  article-title: Fall detection based on key points of human-skeleton using openpose
  publication-title: Symmetry
– year: 2020
  ident: b1020
  article-title: A short note on the kinetics-700-2020 human action dataset
– start-page: 61
  year: 2019
  end-page: 70
  ident: b1125
  article-title: Skeleton-based action recognition of people handling objects
  publication-title: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
– start-page: 212
  year: 2017
  end-page: 216
  ident: b0230
  article-title: Action recognition using mhi based hu moments with hmms
  publication-title: IEEE EUROCON 2017–17th International Conference on Smart Technologies
– start-page: 4511
  year: 2019
  end-page: 4520
  ident: b1250
  article-title: H+ o: Unified egocentric recognition of 3d hand-object poses and interactions, in
  publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
– start-page: 317
  year: 2006
  end-page: 322
  ident: b0350
  article-title: Bayesian classification of task-oriented actions based on stochastic context-free grammar, in
  publication-title: 7th International Conference on Automatic Face and Gesture Recognition (FGR06)
– start-page: 2735
  year: 2021
  end-page: 2744
  ident: b0210
  article-title: Jolo-gcn: mining joint-centered light-weight information for skeleton-based action recognition
  publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
– start-page: 3510
  year: 2017
  end-page: 3515
  ident: b0045
  article-title: On-line simultaneous learning and recognition of everyday activities from virtual reality performances
  publication-title: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
– volume: 7
  start-page: 57267
  year: 2019
  end-page: 57275
  ident: b0485
  article-title: A spatiotemporal heterogeneous two-stream network for action recognition
  publication-title: IEEE Access
– start-page: 7668
  year: 2021
  end-page: 7676
  ident: b1395
  article-title: Just one moment: Structural vulnerability of deep action recognition against one frame attack
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– start-page: 3478
  year: 2018
  end-page: 3482
  ident: b1190
  article-title: Spatial-temporal data augmentation based on lstm autoencoder network for skeleton-based human action recognition
  publication-title: 2018 25th IEEE International Conference on Image Processing (ICIP)
– start-page: 99
  year: 2017
  end-page: 107
  ident: b0605
  article-title: Football action recognition using hierarchical lstm, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition workshops
– year: 2022
  ident: b0095
  article-title: Human action recognition from various data modalities: A review
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– reference: Z. Ghahramani, Learning dynamic bayesian networks, in: International School on Neural Networks, Initiated by IIASS and EMFCSC, Springer, 1997, pp. 168–197.
– volume: 36
  start-page: 621
  year: 2020
  end-page: 631
  ident: b0900
  article-title: Skeleton-based action recognition by part-aware graph convolutional networks
  publication-title: The visual computer
– volume: 20
  start-page: 3499
  year: 2020
  ident: b0855
  article-title: Gas-gcn: Gated action-specific graph convolutional networks for skeleton-based action recognition
  publication-title: Sensors
– volume: 22
  start-page: 1315
  year: 2004
  end-page: 1316
  ident: b0255
  article-title: What is a hidden markov model?
  publication-title: Nature biotechnology
– reference: M.A. Ahad, Motion history image, in: Motion history images for action recognition and understanding, Springer, 2013, pp. 31–76.
– start-page: 601
  year: 2017
  end-page: 604
  ident: b0755
  article-title: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn
  publication-title: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
– reference: J. Gao, T. Zhang, C. Xu, I know the relationships: Zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs, in: Proceedings of the AAAI conference on artificial intelligence, Vol. 33, 2019, pp. 8303–8311.
– reference: Y. Zhu, Z. Lan, S. Newsam, A. Hauptmann, Hidden two-stream convolutional networks for action recognition, in: Asian conference on computer vision, Springer, 2018, pp. 363–378.
– start-page: 143
  year: 2020
  end-page: 152
  ident: b0850
  article-title: Disentangling and unifying graph convolutions for skeleton-based action recognition
  publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
– volume: 36
  start-page: 1579
  year: 2017
  end-page: 1594
  ident: b0035
  article-title: Phase estimation for fast action recognition and trajectory generation in human–robot collaboration
  publication-title: The International Journal of Robotics Research
– volume: 33
  start-page: 251
  year: 1991
  end-page: 272
  ident: b0270
  article-title: Hidden markov models for speech recognition
  publication-title: Technometrics
– start-page: 617
  year: 2017
  end-page: 622
  ident: b0775
  article-title: Investigation of different skeleton features for cnn-based 3d action recognition
  publication-title: 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
– start-page: 12046
  year: 2019
  end-page: 12055
  ident: b1220
  article-title: Large-scale weakly-supervised pre-training for video action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 3288
  year: 2017
  end-page: 3297
  ident: b0805
  article-title: A new representation of skeleton sequences for 3d action recognition
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– reference: J. Carreira, E. Noland, C. Hillier, A. Zisserman, A short note on the kinetics-700 human action dataset, arXiv preprint arXiv:1907.06987 (2019).
– start-page: 547
  year: 2018
  end-page: 552
  ident: b0725
  article-title: Multi-source learning for skeleton-based action recognition using deep lstm networks
  publication-title: 2018 24th International Conference on Pattern Recognition (ICPR)
– start-page: 6165
  year: 2021
  end-page: 6175
  ident: b0195
  article-title: Deep analysis of cnn-based spatio-temporal representations for action recognition
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 7733
  year: 2019
  end-page: 7742
  ident: b0325
  article-title: Bayesian hierarchical dynamic model for human action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 1
  year: 2017
  end-page: 6
  ident: b0585
  article-title: Human action recognition with 3d convolutional neural network
  publication-title: 2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI)
– reference: W. Kay, J. Carreira, K. Simonyan, B. Zhang, C. Hillier, S. Vijayanarasimhan, F. Viola, T. Green, T. Back, P. Natsev, et al., The kinetics human action video dataset, arXiv preprint arXiv:1705.06950 (2017).
– start-page: 3551
  year: 2013
  end-page: 3558
  ident: b0250
  article-title: Action recognition with improved trajectories, in
  publication-title: Proceedings of the IEEE international conference on computer vision
– start-page: 1227
  year: 2019
  end-page: 1236
  ident: b0750
  article-title: An attention enhanced graph convolutional lstm network for skeleton-based action recognition
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 3829
  year: 2020
  end-page: 3837
  ident: b1400
  article-title: Finding achilles’ heel: Adversarial attack on multi-modal action recognition
  publication-title: Proceedings of the 28th ACM International Conference on Multimedia
– start-page: 7387
  year: 2021
  end-page: 7394
  ident: b1090
  article-title: Tinyvirat: Low-resolution video action recognition
  publication-title: 2020 25th International Conference on Pattern Recognition (ICPR)
– volume: 6
  start-page: 50788
  year: 2018
  end-page: 50800
  ident: b0720
  article-title: Skeleton feature fusion based on multi-stream lstm for action recognition
  publication-title: IEEE Access
– volume: 115
  start-page: 224
  year: 2011
  end-page: 241
  ident: b0065
  article-title: A survey of vision-based methods for action representation, segmentation and recognition
  publication-title: Computer vision and image understanding
– start-page: 55
  year: 2020
  end-page: 63
  ident: b0880
  article-title: Dynamic gcn: Context-enriched topology learning for skeleton-based action recognition
  publication-title: Proceedings of the 28th ACM International Conference on Multimedia
– volume: 15
  start-page: 5197
  year: 2015
  end-page: 5227
  ident: b0240
  article-title: Continuous human action recognition using depth-mhi-hog and a spotter model
  publication-title: Sensors
– start-page: 3110
  year: 2017
  end-page: 3119
  ident: b0440
  article-title: Two-stream flow-guided convolutional attention networks for action recognition, in
  publication-title: Proceedings of the IEEE International Conference on Computer Vision Workshops
– start-page: 1625
  year: 2020
  end-page: 1633
  ident: b0925
  article-title: Stronger, faster and more explainable: A graph convolutional baseline for skeleton-based action recognition
  publication-title: Proceedings of the 28th ACM International Conference on Multimedia
– year: 2019
  ident: b0885
  article-title: Spatial residual layer and dense connection block enhanced spatial temporal graph convolutional network for skeleton-based action recognition
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops
– reference: S. Takeuchi, S. Tamura, S. Hayamizu, Human action recognition using acceleration information based on hidden markov model, in: Proceedings: APSIPA ASC 2009: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference, Asia-Pacific Signal and Information Processing Association, 2009 Annual, 2009, pp. 829–832.
– start-page: 508
  year: 2020
  end-page: 516
  ident: b1140
  article-title: Weakly-supervised multi-person action recognition in 360<error l=”619” c=”Undefined command ”/> videos
  publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
– start-page: 7103
  year: 2018
  end-page: 7112
  ident: b0660
  article-title: Cascaded pyramid network for multi-person pose estimation
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 1
  year: 2006
  end-page: 5
  ident: b1170
  article-title: Human model and motion based 3d action recognition in multiple view scenarios
  publication-title: 2006 14th European Signal Processing Conference
– start-page: 3154
  year: 2017
  end-page: 3160
  ident: b0535
  article-title: Learning spatio-temporal features with 3d residual networks for action recognition, in
  publication-title: Proceedings of the IEEE International Conference on Computer Vision Workshops
– volume: 42
  start-page: 19
  year: 2016
  end-page: 30
  ident: b0320
  article-title: Human action recognition using multi-layer codebooks of key poses and atomic motions
  publication-title: Signal Processing: Image Communication
– start-page: 1647
  year: 2017
  end-page: 1656
  ident: b0735
  article-title: Global context-aware attention lstm networks for 3d action recognition
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 63
  year: 2015
  end-page: 67
  ident: b1305
  article-title: Semantic embedding space for zero-shot action recognition
  publication-title: 2015 IEEE International Conference on Image Processing (ICIP)
– volume: 56
  start-page: 605
  year: 2020
  end-page: 614
  ident: b0475
  article-title: Transferable two-stream convolutional neural network for human action recognition
  publication-title: Journal of Manufacturing Systems
– reference: K. Simonyan, A. Zisserman, Two-stream convolutional networks for action recognition in videos, arXiv preprint arXiv:1406.2199 (2014).
– volume: 28
  start-page: 1807
  year: 2016
  end-page: 1823
  ident: b1165
  article-title: Human action recognition using 3d reconstruction data
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– volume: 19
  start-page: 439
  year: 1971
  end-page: 475
  ident: b0335
  article-title: Translations on a context free grammar
  publication-title: Information and Control
– reference: C. Schuldt, I. Laptev, B. Caputo, Recognizing human actions: a local svm approach, in: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, Vol. 3, IEEE, 2004, pp. 32–36.
– volume: 9
  start-page: 36475
  year: 2021
  end-page: 36484
  ident: b1055
  article-title: Multi-scale mixed dense graph convolution network for skeleton-based action recognition
  publication-title: IEEE Access
– start-page: 8984
  year: 2021
  end-page: 8993
  ident: b0200
  article-title: Graph-based high-order relation modeling for long-term action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 37
  start-page: 193
  year: 2013
  end-page: 201
  ident: b0055
  article-title: Adapting user interfaces for gestural interaction with the flexible action and articulated skeleton toolkit
  publication-title: Computers & Graphics
– volume: 8
  start-page: 1
  year: 1984
  end-page: 21
  ident: b0265
  article-title: On the sum of all distances in a graph or digraph
  publication-title: Journal of Graph Theory
– start-page: 14
  year: 2012
  end-page: 19
  ident: b0400
  article-title: Eigenjoints-based action recognition using naive-bayes-nearest-neighbor
  publication-title: 2012 IEEE computer society conference on computer vision and pattern recognition workshops
– start-page: 1112
  year: 2020
  end-page: 1121
  ident: b0110
  article-title: Semantics-guided neural networks for efficient skeleton-based human action recognition
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 1
  year: 2019
  end-page: 5
  ident: b0920
  article-title: Richly activated graph convolutional network for action recognition with incomplete skeletons
  publication-title: 2019 IEEE International Conference on Image Processing (ICIP)
– volume: 55
  start-page: 42
  year: 2016
  end-page: 52
  ident: b0070
  article-title: From handcrafted to learned representations for human action recognition: A survey
  publication-title: Image and Vision Computing
– start-page: 175
  year: 2019
  end-page: 180
  ident: b1130
  article-title: Real-time multi-camera multi-person action recognition using pose estimation, in
  publication-title: Proceedings of the 3rd International Conference on Machine Learning and Soft Computing
– reference: A. Antonucci, R. De Rosa, A. Giusti, Action recognition by imprecise hidden markov models, in: Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV), The Steering Committee of The World Congress in Computer Science, Computer, 2011, p. 1.
– start-page: 4724
  year: 2016
  end-page: 4732
  ident: b0700
  article-title: Convolutional pose machines, in
  publication-title: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition
– reference: M. Müller, T. Röder, M. Clausen, B. Eberhardt, B. Krüger, A. Weber, Documentation mocap database hdm05 (2007).
– reference: Y. Kong, S. Gao, B. Sun, Y. Fu, Action prediction from videos via memorizing hard-to-predict samples, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, 2018.
– start-page: 94
  year: 2015
  end-page: 99
  ident: b0025
  article-title: Action recognition for human robot interaction in industrial applications
  publication-title: 2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS)
– start-page: 6299
  year: 2017
  end-page: 6308
  ident: b0955
  article-title: Quo vadis, action recognition? a new model and the kinetics dataset, in
  publication-title: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– reference: H. Fan, C. Luo, C. Zeng, M. Ferianc, Z. Que, S. Liu, X. Niu, W. Luk, F-e3d: Fpga-based acceleration of an efficient 3d convolutional neural network for human action recognition, in: 2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP), Vol. 2160, IEEE, 2019, pp. 1–8.
– start-page: 473
  year: 2014
  end-page: 483
  ident: b0415
  article-title: Real-time skeleton-tracking-based human action recognition using kinect data, in
  publication-title: International Conference on Multimedia Modeling, Springer
– start-page: 6752
  year: 2018
  end-page: 6761
  ident: b1215
  article-title: Weakly supervised action localization by sparse temporal pooling network, in
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 35
  year: 2020
  end-page: 51
  ident: b1380
  article-title: Adversarial self-supervised learning for semi-supervised 3d action recognition, in
  publication-title: European Conference on Computer Vision, Springer
– volume: 51
  start-page: 690
  year: 2021
  end-page: 712
  ident: b0005
  article-title: A combined multiple action recognition and summarization for surveillance video sequences
  publication-title: Applied Intelligence
– start-page: 14333
  year: 2020
  end-page: 14342
  ident: b0875
  article-title: Context aware graph convolution for skeleton-based action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 694
  year: 2021
  end-page: 701
  ident: b1050
  article-title: Spatial temporal transformer network for skeleton-based action recognition, in
  publication-title: International Conference on Pattern Recognition, Springer
– volume: 43
  start-page: 172
  year: 2019
  end-page: 186
  ident: b0680
  article-title: Openpose: realtime multi-person 2d pose estimation using part affinity fields
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– start-page: 177
  year: 2017
  end-page: 186
  ident: b0500
  publication-title: Two stream lstm: A deep fusion framework for human action recognition, in 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
– volume: Vol. 1
  start-page: 178
  year: 2016
  end-page: 181
  ident: b0595
  article-title: Action recognition based on features fusion and 3d convolutional neural networks
  publication-title: 2016 9th International Symposium on Computational Intelligence and Design (ISCID)
– reference: Y. Wang, Y. Xiao, F. Xiong, W. Jiang, Z. Cao, J.T. Zhou, J. Yuan, 3dv: 3d dynamic voxel for action recognition in depth video, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 511–520.
– start-page: 466
  year: 2018
  end-page: 481
  ident: b0665
  article-title: Simple baselines for human pose estimation and tracking, in
  publication-title: Proceedings of the European conference on computer vision (ECCV)
– start-page: 6026
  year: 2018
  end-page: 6035
  ident: b1105
  article-title: Compressed video action recognition, in
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– reference: S. Song, C. Lan, J. Xing, W. Zeng, J. Liu, An end-to-end spatio-temporal attention model for human action recognition from skeleton data, in: Proceedings of the AAAI conference on artificial intelligence, Vol. 31, 2017.
– start-page: 14656
  year: 2021
  end-page: 14665
  ident: b0160
  article-title: Understanding the robustness of skeleton-based action recognition under adversarial attack
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 4552
  year: 2015
  end-page: 4560
  ident: b0330
  article-title: Action recognition by hierarchical mid-level action elements, in
  publication-title: Proceedings of the IEEE international conference on computer vision
– start-page: 625
  year: 2020
  end-page: 634
  ident: b0545
  article-title: D3d: Distilled 3d networks for video action recognition, in
  publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
– start-page: 2000
  year: 2019
  end-page: 2009
  ident: b0970
  article-title: Stm: Spatiotemporal and motion encoding for action recognition
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– volume: 117
  start-page: 633
  year: 2013
  end-page: 659
  ident: b0090
  article-title: A survey of video datasets for human action and activity recognition
  publication-title: Computer Vision and Image Understanding
– year: 2019
  ident: b0140
  article-title: Protogan: Towards few shot learning for action recognition
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops
– start-page: 4325
  year: 2017
  end-page: 4334
  ident: b1210
  article-title: Untrimmednets for weakly supervised action recognition and detection, in
  publication-title: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition
– start-page: 1
  year: 2018
  end-page: 6
  ident: b0430
  article-title: Improving human action recognition with two-stream 3d convolutional neural network
  publication-title: 2018 1st International Conference on Multimedia Analysis and Pattern Recognition (MAPR) IEEE
– start-page: 1110
  year: 2015
  end-page: 1118
  ident: b1110
  article-title: Hierarchical recurrent neural network for skeleton based action recognition, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 1655
  year: 2021
  end-page: 1663
  ident: b1385
  article-title: Skeleton-contrastive 3d action representation learning, in
  publication-title: Proceedings of the 29th ACM International Conference on Multimedia
– volume: 23
  start-page: 255
  year: 2012
  end-page: 281
  ident: b0215
  article-title: Motion history image: its variants and applications
  publication-title: Machine Vision and Applications
– reference: S. Alfasly, J. Lu, C. Xu, Y. Zou, Learnable irrelevant modality dropout for multimodal action recognition on modality-specific annotated videos, arXiv preprint arXiv:2203.03014 (2022).
– volume: 76
  start-page: 542
  year: 2012
  end-page: 560
  ident: b1410
  article-title: Long-and short-term plastic modeling of action prediction abilities in volleyball
  publication-title: Psychological research
– start-page: 1290
  year: 2012
  end-page: 1297
  ident: b0375
  article-title: Mining actionlet ensemble for action recognition with depth cameras
  publication-title: 2012 IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 16266
  year: 2021
  end-page: 16275
  ident: b0480
  article-title: Uav-human: A large benchmark for human behavior understanding with unmanned aerial vehicles
  publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
– volume: 78
  start-page: 17165
  year: 2019
  end-page: 17196
  ident: b0020
  article-title: Multi-view recognition system for human activity based on multiple features for video surveillance system
  publication-title: Multimedia Tools and Applications
– reference: Y.-H. Wen, L. Gao, H. Fu, F.-L. Zhang, S. Xia, Graph cnns with motif and variable temporal block for skeleton-based action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 8989–8996.
– volume: 133
  start-page: 471
  year: 2018
  end-page: 477
  ident: b0565
  article-title: Human action recognition using 3d convolutional neural networks with 3d motion cuboids in surveillance videos
  publication-title: Procedia computer science
– volume: 3
  start-page: 1
  year: 2018
  end-page: 4
  ident: b1195
  article-title: Data augmentation in deep learning-based fusion of depth and inertial sensing for action recognition
  publication-title: IEEE Sensors Letters
– reference: M. Bishay, G. Zoumpourlis, I. Patras, Tarn: Temporal attentive relation network for few-shot and zero-shot action recognition, arXiv preprint arXiv:1907.09021 (2019).
– start-page: 1012
  year: 2017
  end-page: 1020
  ident: b0715
  article-title: Ensemble deep learning for skeleton-based action recognition using temporal sliding lstm networks
  publication-title: Proceedings of the IEEE international conference on computer vision
– volume: 22
  start-page: 2481
  year: 2019
  end-page: 2496
  ident: b0765
  article-title: 2-d skeleton-based action recognition via two-branch stacked lstm-rnns
  publication-title: IEEE Transactions on Multimedia
– start-page: 1049
  year: 2020
  end-page: 1059
  ident: b1245
  article-title: Something-else: Compositional action recognition with spatial-temporal interaction networks
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– year: 2019
  ident: b0800
  article-title: Skepxels: Spatio-temporal image representation of human skeleton joints for action recognition., in
  publication-title: CVPR workshops
– start-page: 258
  year: 2019
  end-page: 264
  ident: b1115
  article-title: Action recognition based on 3d skeleton and rgb frame fusion
  publication-title: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
– start-page: 1933
  year: 2016
  end-page: 1941
  ident: b0435
  article-title: Convolutional two-stream network fusion for video action recognition, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 5386
  year: 2020
  end-page: 5395
  ident: b0135
  article-title: Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 115
  year: 2017
  end-page: 123
  ident: b0550
  article-title: Learning spatiotemporal features for infrared action recognition with 3d convolutional neural networks, in
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops
– start-page: 2556
  year: 2011
  end-page: 2563
  ident: b0960
  article-title: Hmdb: a large video database for human motion recognition
  publication-title: 2011 International conference on computer vision
– start-page: 10317
  year: 2020
  end-page: 10326
  ident: b1285
  article-title: Speech2action: Cross-modal supervision for action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 139
  year: 2017
  end-page: 147
  ident: b0455
  article-title: Semi-coupled two-stream fusion convnets for action recognition at extremely low resolutions
  publication-title: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
– start-page: 145
  year: 2009
  end-page: 158
  ident: b0300
  article-title: Distributed continuous action recognition using a hidden markov model in body sensor networks
  publication-title: International Conference on Distributed Computing in Sensor Systems
– volume: 27
  start-page: 2613
  year: 2016
  end-page: 2622
  ident: b0560
  article-title: Temporal pyramid pooling-based convolutional neural network for action recognition
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– volume: 42
  start-page: 2684
  year: 2019
  end-page: 2701
  ident: b1040
  article-title: Ntu rgb+ d 120: A large-scale benchmark for 3d human activity understanding
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– start-page: 438
  year: 2017
  end-page: 445
  ident: b1265
  article-title: Pose for action-action for pose
  publication-title: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)
– start-page: 513
  year: 2018
  end-page: 528
  ident: b1030
  article-title: Resound: Towards action recognition without representation bias, in
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– reference: H. Goto, J. Miura, J. Sugiyama, Human-robot collaborative assembly by on-line human action recognition based on an fsm task model, in: Human-robot interaction 2013 workshop on collaborative manipulation, 2013.
– start-page: 2649
  year: 2014
  end-page: 2656
  ident: b1070
  article-title: Cross-view action modeling, learning and recognition, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 925
  year: 2009
  end-page: 931
  ident: b1155
  article-title: Fast realistic multi-action recognition using mined dense spatio-temporal features
  publication-title: 2009 IEEE 12th international conference on computer vision
– year: 2013
  ident: b0380
  article-title: Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations
  publication-title: Twenty-third international joint conference on artificial intelligence
– reference: S.-C. Wang, Artificial neural network, in: Interdisciplinary computing in java programming, Springer, 2003, pp. 81–100.
– year: 2021
  ident: b0205
  article-title: Memory attention networks for skeleton-based action recognition
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– volume: 8
  start-page: 1
  year: 2017
  end-page: 18
  ident: b0050
  article-title: Approaches and applications of virtual reality and gesture recognition: A review
  publication-title: International Journal of Ambient Computing and Intelligence (IJACI)
– volume: 27
  start-page: 2842
  year: 2018
  end-page: 2855
  ident: b0810
  article-title: Learning clip representations for skeleton-based 3d action recognition
  publication-title: IEEE Transactions on Image Processing
– start-page: 1837
  year: 2017
  end-page: 1841
  ident: b0575
  article-title: 3d convolutional neural network with multi-model framework for action recognition
  publication-title: 2017 IEEE international conference on image processing (ICIP)
– start-page: 20
  year: 2012
  end-page: 27
  ident: b0395
  article-title: View invariant human action recognition using histograms of 3d joints
  publication-title: 2012 IEEE computer society conference on computer vision and pattern recognition workshops
– start-page: 1102
  year: 2020
  end-page: 1111
  ident: b0985
  article-title: Gate-shift networks for video action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– reference: B. Ren, M. Liu, R. Ding, H. Liu, A survey on 3d skeleton-based action recognition using learning method, arXiv preprint arXiv:2002.05907 (2020).
– start-page: 3595
  year: 2019
  end-page: 3603
  ident: b0840
  article-title: Actional-structural graph convolutional networks for skeleton-based action recognition
  publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
– reference: H. Zhang, L. Zhang, X. Qi, H. Li, P.H. Torr, P. Koniusz, Few-shot action recognition with permutation-invariant attention, in: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16, Springer, 2020, pp. 525–542.
– year: 2004
  ident: b0315
  article-title: Modeling individual and group actions in meetings: a two-layer hmm framework
  publication-title: 2004 Conference on Computer Vision and Pattern Recognition Workshop
– volume: 27
  year: 2018
  ident: b0815
  article-title: Multisource learning for skeleton-based action recognition using deep lstm and cnn
  publication-title: Journal of Electronic Imaging
– start-page: 10457
  year: 2020
  end-page: 10467
  ident: b1100
  article-title: Listen to look: Action recognition by previewing audio, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 1010
  year: 2016
  end-page: 1019
  ident: b1035
  article-title: Ntu rgb+ d: A large scale dataset for 3d human activity analysis
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 2020
  start-page: 1
  year: 2020
  end-page: 9
  ident: b0495
  article-title: Improved two-stream module for human action recognition
  publication-title: EURASIP Journal on Image and Video Processing
– reference: B. Li, X. Li, Z. Zhang, F. Wu, Spatio-temporal graph routing for skeleton-based action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 8561–8568.
– volume: Vol. 2
  start-page: 1709
  year: 2006
  end-page: 1718
  ident: b0340
  publication-title: Recognition of composite human activities through context-free grammar based representation in: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06)
– volume: 20
  start-page: 61
  year: 2008
  end-page: 80
  ident: b0825
  article-title: The graph neural network model
  publication-title: IEEE transactions on neural networks
– start-page: 5832
  year: 2017
  end-page: 5841
  ident: b0790
  article-title: Learning action recognition model from depth and skeleton videos, in
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– volume: 1
  start-page: 195
  year: 2007
  end-page: 304
  ident: b0280
  article-title: The application of hidden markov models in speech recognition
  publication-title: Signal Processing
– start-page: 588
  year: 2014
  end-page: 595
  ident: b0385
  article-title: Human action recognition by representing 3d skeletons as points in a lie group, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 20
  start-page: 634
  year: 2017
  end-page: 644
  ident: b0465
  article-title: Two-stream 3-d convnet fusion for action recognition in videos with arbitrary size and length
  publication-title: IEEE Transactions on Multimedia
– start-page: 2777
  year: 2021
  end-page: 2785
  ident: b1340
  article-title: One-shot action recognition in challenging therapy scenarios
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 1
  year: 2019
  end-page: 6
  ident: b0540
  article-title: An improved two-stream 3d convolutional neural network for human action recognition
  publication-title: 2019 25th International Conference on Automation and Computing (ICAC)
– reference: W. Zhu, C. Lan, J. Xing, W. Zeng, Y. Li, L. Shen, X. Xie, Co-occurrence feature learning for skeleton based action recognition using regularized deep lstm networks, in: Proceedings of the AAAI conference on artificial intelligence, Vol. 30, 2016.
– reference: A. Veenendaal, E. Jones, Z. Gang, E. Daly, S. Vartak, R. Patwardhan, Dynamic probabilistic network based human action recognition, arXiv preprint arXiv:1610.06395 (2016).
– start-page: 7852
  year: 2019
  end-page: 7861
  ident: b0610
  article-title: Ddlstm: dual-domain lstm for cross-dataset action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 7291
  year: 2017
  end-page: 7299
  ident: b0705
  article-title: Realtime multi-person 2d pose estimation using part affinity fields, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 60
  start-page: 86
  year: 2016
  end-page: 105
  ident: b0100
  article-title: Rgb-d-based action recognition datasets: A survey
  publication-title: Pattern Recognition
– start-page: 3158
  year: 2021
  end-page: 3162
  ident: b1270
  article-title: Language-guided multi-modal fusion for video action recognition, in
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– reference: D. Osokin, Real-time 2d multi-person pose estimation on cpu: Lightweight openpose, arXiv preprint arXiv:1811.12004 (2018).
– reference: T. Lan, T.-C. Chen, S. Savarese, A hierarchical representation for future action prediction, in: European conference on computer vision, Springer, 2014, pp. 689–704.
– start-page: 770
  year: 2016
  end-page: 778
  ident: b0670
  article-title: Deep residual learning for image recognition, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 1
  year: 2017
  end-page: 6
  ident: b0690
  article-title: Real-time human gesture grading based on openpose
  publication-title: 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
– start-page: 1
  year: 2018
  end-page: 4
  ident: b0590
  article-title: Enhanced action recognition with visual attribute-augmented 3d convolutional neural network
  publication-title: 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
– start-page: 9631
  year: 2020
  end-page: 9640
  ident: b1225
  article-title: Predict & cluster: Unsupervised skeleton based action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 77
  start-page: 257
  year: 1989
  end-page: 286
  ident: b0275
  article-title: A tutorial on hidden markov models and selected applications in speech recognition
  publication-title: Proceedings of the IEEE
– reference: N. Inkawhich, M. Inkawhich, Y. Chen, H. Li, Adversarial attacks for optical flow-based action recognition classifiers, arXiv preprint arXiv:1811.11875 (2018).
– reference: T. Guo, H. Liu, Z. Chen, M. Liu, T. Wang, R. Ding, Contrastive learning from extremely augmented skeleton sequences for self-supervised action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, 2022, pp. 762–770.
– start-page: 13065
  year: 2021
  end-page: 13075
  ident: b0990
  article-title: Learning self-similarity in space and time as generalized motion for video action recognition
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– start-page: 3323
  year: 2015
  end-page: 3331
  ident: b1240
  article-title: Interaction part mining: A mid-level approach for fine-grained action recognition
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– reference: M. Monfort, K. Ramakrishnan, A. Andonian, B.A. McNamara, A. Lascelles, B. Pan, Q. Fan, D. Gutfreund, R. Feris, A. Oliva, Multi-moments in time: Learning and interpreting models for multi-action video understanding, arXiv preprint arXiv:1911.00232 (2019).
– year: 2015
  ident: b0365
  article-title: Walking, lifting, standing activity recognition using probabilistic networks
  publication-title: International Research Journal of Engineering and Technology (IRJET)
– volume: 130
  start-page: 1366
  year: 2022
  end-page: 1401
  ident: b0085
  article-title: Human action recognition and prediction: A survey
  publication-title: International Journal of Computer Vision
– start-page: 2969
  year: 2022
  end-page: 2978
  ident: b0820
  article-title: Revisiting skeleton-based action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 103
  year: 2018
  end-page: 118
  ident: b0930
  article-title: Skeleton-based action recognition with spatial reasoning and temporal stack learning
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– volume: 24
  start-page: 280
  year: 2019
  end-page: 291
  ident: b0060
  article-title: Efficient and robust skeleton-based quality assessment and abnormality detection in human action performance
  publication-title: IEEE journal of biomedical and health informatics
– volume: 87
  start-page: 19
  year: 2021
  end-page: 26
  ident: b0125
  article-title: Effects of camera viewing angles on tracking kinematic gait patterns using azure kinect, kinect v2 and orbbec astra pro v2
  publication-title: Gait & posture
– volume: 76
  start-page: 1123
  year: 2010
  end-page: 1134
  ident: b0630
  article-title: Point clouds
  publication-title: Photogrammetric Engineering & Remote Sensing
– start-page: 13638
  year: 2021
  end-page: 13647
  ident: b1320
  article-title: Elaborative rehearsal for zero-shot action recognition, in
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– reference: J. Yamato, J. Ohya, K. Ishii, Recognizing human action in time-sequential images using hidden markov model., in: CVPR, Vol. 92, 1992, pp. 379–385.
– year: 2021
  ident: b0620
  article-title: Trear: Transformer-based rgb-d egocentric action recognition
  publication-title: IEEE Transactions on Cognitive and Developmental Systems
– reference: N. Zheng, J. Wen, R. Liu, L. Long, J. Dai, Z. Gong, Unsupervised representation learning with long-term dynamics for skeleton based action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, 2018.
– volume: 103
  start-page: 60
  year: 2013
  end-page: 79
  ident: b0245
  article-title: Dense trajectories and motion boundary descriptors for action recognition
  publication-title: International journal of computer vision
– volume: 40
  start-page: 1510
  year: 2017
  end-page: 1517
  ident: b0950
  article-title: Long-term temporal convolutions for action recognition
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– reference: W. Li, Z. Wang, B. Yin, Q. Peng, Y. Du, T. Xiao, G. Yu, H. Lu, Y. Wei, J. Sun, Rethinking on multi-stage networks for human pose estimation, arXiv preprint arXiv:1901.00148 (2019).
– volume: 78
  start-page: 507
  year: 2019
  end-page: 523
  ident: b0580
  article-title: Action recognition with multi-scale trajectory-pooled 3d convolutional descriptors
  publication-title: Multimedia Tools and Applications
– volume: 60
  start-page: 4
  year: 2017
  end-page: 21
  ident: b0075
  article-title: Going deeper into action recognition: A survey
  publication-title: Image and vision computing
– start-page: 769
  year: 2020
  end-page: 786
  ident: b1255
  article-title: Collaborative learning of gesture recognition and 3d hand pose estimation with multi-order feature analysis, in
  publication-title: European Conference on Computer Vision, Springer
– year: 2021
  ident: b1080
  article-title: Fexnet: Foreground extraction network for human action recognition
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– volume: 32
  start-page: 447
  year: 2020
  end-page: 453
  ident: b0940
  article-title: A new hybrid deep learning model for human action recognition
  publication-title: Journal of King Saud University-Computer and Information Sciences
– reference: N. Ikizler-Cinbis, S. Sclaroff, Object, scene and actions: Combining multiple features for human action recognition, in: European conference on computer vision, Springer, 2010, pp. 494–507.
– start-page: 179
  year: 2019
  end-page: 189
  ident: b1230
  article-title: Video jigsaw: Unsupervised learning of spatiotemporal context for video action recognition
  publication-title: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
– start-page: 13359
  year: 2021
  end-page: 13368
  ident: b0890
  article-title: Channel-wise topology refinement graph convolution for skeleton-based action recognition
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– volume: 22
  start-page: 1433
  year: 2019
  end-page: 1446
  ident: b1185
  article-title: 2d pose-based real-time human action recognition with occlusion-handling
  publication-title: IEEE Transactions on Multimedia
– start-page: 122
  year: 2020
  end-page: 132
  ident: b1295
  article-title: Multi-modal domain adaptation for fine-grained action recognition, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 5693
  year: 2019
  end-page: 5703
  ident: b0130
  article-title: Deep high-resolution representation learning for human pose estimation, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 85
  start-page: 1
  year: 2019
  end-page: 12
  ident: b0515
  article-title: Asymmetric 3d convolutional neural networks for action recognition
  publication-title: Pattern recognition
– volume: 40
  start-page: 3007
  year: 2017
  end-page: 3021
  ident: b1045
  article-title: Skeleton-based action recognition using spatio-temporal lstm network with trust gates
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– reference: M. Brand, N. Oliver, A. Pentland, Coupled hidden markov models for complex action recognition, in: Proceedings of IEEE computer society conference on computer vision and pattern recognition, IEEE, 1997, pp. 994–999.
– volume: 8
  start-page: 168297
  year: 2020
  end-page: 168308
  ident: b1120
  article-title: Infrared and 3d skeleton feature fusion for rgb-d action recognition
  publication-title: IEEE Access
– start-page: 11139
  year: 2017
  end-page: 11144
  ident: b0530
  article-title: Using gabor filter in 3d convolutional neural networks for human action recognition
  publication-title: 2017 36th Chinese Control Conference (CCC)
– year: 2021
  ident: b0650
  article-title: Sequentialpointnet: A strong parallelized point cloud sequence network for 3d action recognition
– volume: 132
  year: 2021
  ident: b0640
  article-title: A hardware-adaptive deep feature matching pipeline for real-time 3d reconstruction
  publication-title: Computer-Aided Design
– start-page: 1895
  year: 2021
  end-page: 1904
  ident: b1000
  publication-title: Tdn: Temporal difference networks for efficient action recognition, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 13423
  year: 2021
  end-page: 13433
  ident: b1355
  article-title: Skeleton cloud colorization for unsupervised 3d action representation learning
  publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision
– volume: 20
  start-page: 4758
  year: 2020
  ident: b1135
  article-title: Deep learning-based real-time multiple-person action recognition system
  publication-title: Sensors
– volume: 84
  year: 2020
  ident: b1275
  article-title: Human action recognition toward massive-scale sport sceneries based on deep multi-model feature fusion
  publication-title: Signal Processing: Image Communication
– year: 2020
  ident: b0165
  article-title: Adversarial attack on skeleton-based human action recognition
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– reference: J. Carreira, E. Noland, A. Banki-Horvath, C. Hillier, A. Zisserman, A short note about kinetics-600, arXiv preprint arXiv:1808.01340 (2018).
– volume: 86
  year: 2020
  ident: b0505
  article-title: Human action recognition using two-stream attention based lstm networks
  publication-title: Applied soft computing
– volume: 444
  start-page: 319
  year: 2021
  end-page: 331
  ident: b0600
  article-title: Db-lstm: Densely-connected bi-directional lstm for human action recognition
  publication-title: Neurocomputing
– start-page: 826
  year: 2019
  end-page: 831
  ident: b0740
  article-title: Relational network for skeleton-based action recognition
  publication-title: 2019 IEEE International Conference on Multimedia and Expo (ICME)
– start-page: 3210
  year: 2018
  end-page: 3215
  ident: b1300
  article-title: Multi-modal three-stream network for action recognition
  publication-title: 2018 24th International Conference on Pattern Recognition (ICPR)
– volume: 8
  start-page: 302
  year: 1997
  end-page: 307
  ident: b0190
  article-title: Viewpoint dependence in scene recognition
  publication-title: Psychological science
– start-page: 5323
  year: 2018
  end-page: 5332
  ident: b0915
  article-title: Deep progressive reinforcement learning for skeleton-based action recognition, in
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 1129
  year: 2012
  end-page: 1133
  ident: b1175
  article-title: Multi-view human action recognition under occlusion based on fuzzy distances and neural networks
  publication-title: 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)
– start-page: 244
  year: 2019
  end-page: 253
  ident: b0615
  article-title: Video action transformer network, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 78
  start-page: 107
  year: 2016
  end-page: 117
  ident: b0635
  article-title: A multi-frame graph matching algorithm for low-bandwidth rgb-d slam
  publication-title: Computer-Aided Design
– reference: L. Huang, Y. Huang, W. Ouyang, L. Wang, Part-level graph convolutional network for skeleton-based action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 2020, pp. 11045–11052.
– start-page: 16
  year: 2019
  end-page: 23
  ident: b0780
  article-title: Skeleton image representation for 3d action recognition based on tree structure and reference joints
  publication-title: 2019 32nd SIBGRAPI conference on graphics, patterns and images (SIBGRAPI)
– reference: C.S. Pinhanez, A.F. Bobick, Human action detection using pnf propagation of temporal constraints, in: Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No. 98CB36231), IEEE, 1998, pp. 898–904.
– reference: N. Ma, H. Zhang, X. Li, S. Zhou, Z. Zhang, J. Wen, H. Li, J. Gu, J. Bu, Learning spatial-preserved skeleton representations for few-shot action recognition.
– start-page: 372
  year: 2018
  end-page: 380
  ident: b0145
  article-title: A generative approach to zero-shot and few-shot action recognition
  publication-title: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
– reference: A. Li, M. Thotakuri, D.A. Ross, J. Carreira, A. Vostrikov, A. Zisserman, The ava-kinetics localized human actions video dataset, arXiv preprint arXiv:2005.00214 (2020).
– volume: 21
  start-page: 452
  year: 2021
  ident: b1060
  article-title: Shallow graph convolutional network for skeleton-based action recognition
  publication-title: Sensors
– volume: 32
  start-page: 4
  year: 2020
  end-page: 24
  ident: b0830
  article-title: A comprehensive survey on graph neural networks
  publication-title: IEEE transactions on neural networks and learning systems
– start-page: 1
  year: 2017
  end-page: 8
  ident: b1150
  article-title: Concurrence-aware long short-term sub-memories for person-person action recognition
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops
– reference: S. Suthaharan, Support vector machine, in: Machine learning models and algorithms for big data classification, Springer, 2016, pp. 207–235.
– start-page: 1
  year: 2019
  end-page: 8
  ident: b0425
  article-title: Two-stream convolution neural network with video-stream for action recognition
  publication-title: 2019 International Joint Conference on Neural Networks (IJCNN)
– volume: 41
  start-page: 1963
  year: 2019
  end-page: 1978
  ident: b0785
  article-title: View adaptive neural networks for high performance skeleton-based human action recognition
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– start-page: 9985
  year: 2019
  end-page: 9993
  ident: b1310
  article-title: Out-of-distribution detection for generalized zero-shot action recognition
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 2117
  year: 2017
  end-page: 2126
  ident: b0760
  article-title: View adaptive recurrent neural networks for high performance human action recognition from skeleton data
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– volume: 24
  start-page: 1565
  year: 2006
  end-page: 1567
  ident: b0175
  article-title: What is a support vector machine?
  publication-title: Nature biotechnology
– start-page: 515
  year: 2021
  end-page: 524
  ident: b0155
  article-title: Over-the-air adversarial flickering attacks against video recognition networks
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 112
  start-page: 161
  year: 2018
  end-page: 167
  ident: b0490
  article-title: First person action recognition via two-stream convnet with long-term fusion pooling
  publication-title: Pattern Recognition Letters
– start-page: 6450
  year: 2018
  end-page: 6459
  ident: b0570
  article-title: A closer look at spatiotemporal convolutions for action recognition
  publication-title: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition
– reference: K. Thakkar, P. Narayanan, Part-based graph convolutional network for action recognition, arXiv preprint arXiv:1809.04983 (2018).
– start-page: 579
  year: 2015
  end-page: 583
  ident: b0770
  article-title: Skeleton based action recognition with convolutional neural network
  publication-title: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)
– start-page: 670
  year: 2020
  end-page: 688
  ident: b0555
  article-title: Omni-sourced webly-supervised learning for video recognition, in
  publication-title: European Conference on Computer Vision, Springer
– start-page: 3556
  year: 2019
  end-page: 3565
  ident: b1430
  article-title: Progressive teacher-student learning for early action prediction, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 35
  start-page: 221
  year: 2012
  end-page: 231
  ident: b0510
  article-title: 3d convolutional neural networks for human action recognition
  publication-title: IEEE transactions on pattern analysis and machine intelligence
– reference: F. Mahdisoltani, G. Berger, W. Gharbieh, D. Fleet, R. Memisevic, Fine-grained video classification and captioning, arXiv preprint arXiv:1804.09235 5 (6) (2018).
– volume: 29
  start-page: 9532
  year: 2020
  end-page: 9545
  ident: b0865
  article-title: Skeleton-based action recognition with multi-stream adaptive graph convolutional networks
  publication-title: IEEE Transactions on Image Processing
– start-page: 1145
  year: 2017
  end-page: 1153
  ident: b0710
  article-title: Hand keypoint detection in single images using multiview bootstrapping, in
  publication-title: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition
– volume: 132
  start-page: 1317
  year: 2018
  end-page: 1326
  ident: b0015
  article-title: Human detection and tracking using hog for action recognition
  publication-title: Procedia computer science
– volume: 9
  start-page: 1897
  year: 2015
  end-page: 1906
  ident: b0235
  article-title: Optical flow-motion history image (of-mhi) for action recognition
  publication-title: Signal, Image and Video Processing
– start-page: 183
  year: 2020
  end-page: 192
  ident: b0105
  article-title: Skeleton-based action recognition with shift graph convolutional network, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 9
  start-page: 2126
  year: 2019
  ident: b1075
  article-title: Human action recognition based on foreground trajectory and motion difference descriptors
  publication-title: Applied Sciences
– start-page: 6202
  year: 2019
  end-page: 6211
  ident: b0450
  article-title: Slowfast networks for video recognition, in
  publication-title: Proceedings of the IEEE/CVF international conference on computer vision
– start-page: 505
  year: 2020
  end-page: 521
  ident: b1095
  article-title: Rubiksnet: Learnable 3d-shift for efficient video action recognition, in
  publication-title: European Conference on Computer Vision, Springer
– start-page: 5842
  year: 2017
  end-page: 5850
  ident: b0980
  article-title: The something something video database for learning and evaluating visual common sense
  publication-title: Proceedings of the IEEE international conference on computer vision
– volume: 166
  start-page: 41
  year: 2018
  end-page: 50
  ident: b1085
  article-title: Videolstm convolves, attends and flows for action recognition
  publication-title: Computer Vision and Image Understanding
– volume: 107
  start-page: 83
  year: 2018
  end-page: 90
  ident: b0470
  article-title: Going deeper with two-stream convnets for action recognition in video surveillance
  publication-title: Pattern Recognition Letters
– start-page: 4741
  year: 2021
  end-page: 4750
  ident: b1350
  article-title: 3d human action representation learning via cross-view consistency pursuit
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 909
  year: 2020
  end-page: 918
  ident: b0975
  article-title: Tea: Temporal excitation and aggregation for action recognition
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– reference: H. Liu, J. Tu, M. Liu, Two-stream 3d convolutional neural network for skeleton-based action recognition, arXiv preprint arXiv:1705.08106 (2017).
– start-page: 1473
  year: 2017
  end-page: 1481
  ident: b1420
  article-title: Deep sequential context networks for action prediction, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– start-page: 2490
  year: 2020
  end-page: 2498
  ident: b1370
  article-title: Ms2l: Multi-task self-supervised learning for skeleton based action recognition
  publication-title: Proceedings of the 28th ACM International Conference on Multimedia
– reference: K. Soomro, A.R. Zamir, M. Shah, Ucf101: A dataset of 101 human actions classes from videos in the wild, arXiv preprint arXiv:1212.0402 (2012).
– start-page: 2616
  year: 2020
  end-page: 2625
  ident: b1025
  article-title: Finegym: A hierarchical video dataset for fine-grained action understanding, in
  publication-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
– start-page: 3034
  year: 2016
  end-page: 3042
  ident: b1205
  article-title: Dynamic image networks for action recognition, in
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 18
  start-page: 141
  year: 2015
  end-page: 154
  ident: b0410
  article-title: Effective active skeleton representation for low latency human action recognition
  publication-title: IEEE Transactions on Multimedia
– start-page: 4315
  year: 2017
  end-page: 4324
  ident: b1145
  article-title: Social scene understanding: End-to-end multi-person action localization and collective activity recognition
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– reference: Y. Huang, L. Yang, Y. Sato, Compound prototype matching for few-shot action recognition (2022).
– start-page: 7912
  year: 2019
  end-page: 7921
  ident: b0870
  article-title: Skeleton-based action recognition with directed graph neural networks, in
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 3
  year: 2002
  end-page: 8
  ident: b0310
  article-title: Layered representations for human activity recognition, in: Proceedings
  publication-title: Fourth IEEE International Conference on Multimodal Interfaces
– start-page: 3154
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0535
  article-title: Learning spatio-temporal features with 3d residual networks for action recognition, in
– start-page: 2702
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0040
  article-title: Multimodal human action recognition in assistive human-robot interaction
– year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0140
  article-title: Protogan: Towards few shot learning for action recognition
– start-page: 395
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0225
  article-title: Depth mhi based deep learning model for human action recognition
– start-page: 5842
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0980
  article-title: The something something video database for learning and evaluating visual common sense
– start-page: 14656
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0160
  article-title: Understanding the robustness of skeleton-based action recognition under adversarial attack
– start-page: 3034
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b1205
  article-title: Dynamic image networks for action recognition, in
– start-page: 372
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0145
  article-title: A generative approach to zero-shot and few-shot action recognition
– start-page: 625
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0545
  article-title: D3d: Distilled 3d networks for video action recognition, in
– start-page: 2969
  year: 2022
  ident: 10.1016/j.neucom.2022.09.071_b0820
  article-title: Revisiting skeleton-based action recognition, in
– volume: 22
  start-page: 1433
  issue: 6
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1185
  article-title: 2d pose-based real-time human action recognition with occlusion-handling
  publication-title: IEEE Transactions on Multimedia
  doi: 10.1109/TMM.2019.2944745
– volume: 42
  start-page: 494
  issue: 2
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0655
  article-title: Feature boosting network for 3d pose estimation
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2019.2894422
– start-page: 6026
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b1105
  article-title: Compressed video action recognition, in
– start-page: 3478
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b1190
  article-title: Spatial-temporal data augmentation based on lstm autoencoder network for skeleton-based human action recognition
– year: 2013
  ident: 10.1016/j.neucom.2022.09.071_b0380
  article-title: Human action recognition using a temporal hierarchy of covariance descriptors on 3d joint locations
– volume: 78
  start-page: 17165
  issue: 12
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0020
  article-title: Multi-view recognition system for human activity based on multiple features for video surveillance system
  publication-title: Multimedia Tools and Applications
  doi: 10.1007/s11042-018-7108-9
– volume: 23
  issue: 3
  year: 2014
  ident: 10.1016/j.neucom.2022.09.071_b0345
  article-title: Human action recognition using a context-free grammar
  publication-title: Journal of Electronic Imaging
  doi: 10.1117/1.JEI.23.3.033016
– ident: 10.1016/j.neucom.2022.09.071_b0910
  doi: 10.1609/aaai.v34i07.6759
– volume: 22
  start-page: 2481
  issue: 10
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0765
  article-title: 2-d skeleton-based action recognition via two-branch stacked lstm-rnns
  publication-title: IEEE Transactions on Multimedia
  doi: 10.1109/TMM.2019.2960588
– start-page: 3595
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0840
  article-title: Actional-structural graph convolutional networks for skeleton-based action recognition
– volume: 130
  start-page: 1366
  issue: 5
  year: 2022
  ident: 10.1016/j.neucom.2022.09.071_b0085
  article-title: Human action recognition and prediction: A survey
  publication-title: International Journal of Computer Vision
  doi: 10.1007/s11263-022-01594-9
– volume: 13
  start-page: 970
  issue: 2
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0010
  article-title: Modeling two-person segmentation and locomotion for stereoscopic action identification: A sustainable video surveillance system
  publication-title: Sustainability
  doi: 10.3390/su13020970
– volume: 19
  start-page: 439
  issue: 5
  year: 1971
  ident: 10.1016/j.neucom.2022.09.071_b0335
  article-title: Translations on a context free grammar
  publication-title: Information and Control
  doi: 10.1016/S0019-9958(71)90706-6
– volume: 107
  start-page: 83
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0470
  article-title: Going deeper with two-stream convnets for action recognition in video surveillance
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2017.08.015
– ident: 10.1016/j.neucom.2022.09.071_b1005
– volume: 76
  start-page: 1123
  issue: 10
  year: 2010
  ident: 10.1016/j.neucom.2022.09.071_b0630
  article-title: Point clouds
  publication-title: Photogrammetric Engineering & Remote Sensing
  doi: 10.14358/PERS.76.10.1123
– start-page: 2649
  year: 2014
  ident: 10.1016/j.neucom.2022.09.071_b1070
  article-title: Cross-view action modeling, learning and recognition, in
– start-page: 11139
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0530
  article-title: Using gabor filter in 3d convolutional neural networks for human action recognition
– volume: 166
  start-page: 41
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b1085
  article-title: Videolstm convolves, attends and flows for action recognition
  publication-title: Computer Vision and Image Understanding
  doi: 10.1016/j.cviu.2017.10.011
– start-page: 7668
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1395
  article-title: Just one moment: Structural vulnerability of deep action recognition against one frame attack
– volume: 117
  start-page: 633
  issue: 6
  year: 2013
  ident: 10.1016/j.neucom.2022.09.071_b0090
  article-title: A survey of video datasets for human action and activity recognition
  publication-title: Computer Vision and Image Understanding
  doi: 10.1016/j.cviu.2013.01.013
– volume: Vol. 2
  start-page: 1709
  year: 2006
  ident: 10.1016/j.neucom.2022.09.071_b0340
– ident: 10.1016/j.neucom.2022.09.071_b1365
  doi: 10.1609/aaai.v32i1.11853
– volume: 9
  start-page: 2126
  issue: 10
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1075
  article-title: Human action recognition based on foreground trajectory and motion difference descriptors
  publication-title: Applied Sciences
  doi: 10.3390/app9102126
– start-page: 7103
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0660
  article-title: Cascaded pyramid network for multi-person pose estimation
– start-page: 4724
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0700
  article-title: Convolutional pose machines, in
– volume: 15
  start-page: 5197
  issue: 3
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b0240
  article-title: Continuous human action recognition using depth-mhi-hog and a spotter model
  publication-title: Sensors
  doi: 10.3390/s150305197
– volume: 32
  start-page: 447
  issue: 4
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0940
  article-title: A new hybrid deep learning model for human action recognition
  publication-title: Journal of King Saud University-Computer and Information Sciences
  doi: 10.1016/j.jksuci.2019.09.004
– volume: 40
  start-page: 1510
  issue: 6
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0950
  article-title: Long-term temporal convolutions for action recognition
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2017.2712608
– ident: 10.1016/j.neucom.2022.09.071_b0905
– volume: 42
  start-page: 19
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0320
  article-title: Human action recognition using multi-layer codebooks of key poses and atomic motions
  publication-title: Signal Processing: Image Communication
– ident: 10.1016/j.neucom.2022.09.071_b1160
– start-page: 10317
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1285
  article-title: Speech2action: Cross-modal supervision for action recognition, in
– start-page: 115
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0550
  article-title: Learning spatiotemporal features for infrared action recognition with 3d convolutional neural networks, in
– start-page: 3158
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1270
  article-title: Language-guided multi-modal fusion for video action recognition, in
– start-page: 617
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0775
  article-title: Investigation of different skeleton features for cnn-based 3d action recognition
– start-page: 1
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0590
  article-title: Enhanced action recognition with visual attribute-augmented 3d convolutional neural network
– start-page: 1933
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0435
  article-title: Convolutional two-stream network fusion for video action recognition, in
– start-page: 4325
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b1210
  article-title: Untrimmednets for weakly supervised action recognition and detection, in
– volume: 9
  start-page: 36475
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1055
  article-title: Multi-scale mixed dense graph convolution network for skeleton-based action recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.3049029
– ident: 10.1016/j.neucom.2022.09.071_b0730
  doi: 10.1609/aaai.v31i1.11212
– ident: 10.1016/j.neucom.2022.09.071_b0030
– start-page: 258
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1115
  article-title: Action recognition based on 3d skeleton and rgb frame fusion
– start-page: 7291
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0705
  article-title: Realtime multi-person 2d pose estimation using part affinity fields, in
– volume: 85
  start-page: 1
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0515
  article-title: Asymmetric 3d convolutional neural networks for action recognition
  publication-title: Pattern recognition
  doi: 10.1016/j.patcog.2018.07.028
– ident: 10.1016/j.neucom.2022.09.071_b0520
  doi: 10.1109/ASAP.2019.00-44
– ident: 10.1016/j.neucom.2022.09.071_b1010
– volume: 42
  start-page: 2684
  issue: 10
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1040
  article-title: Ntu rgb+ d 120: A large-scale benchmark for 3d human activity understanding
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2019.2916873
– ident: 10.1016/j.neucom.2022.09.071_b0745
  doi: 10.1609/aaai.v30i1.10451
– start-page: 438
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b1265
  article-title: Pose for action-action for pose
– ident: 10.1016/j.neucom.2022.09.071_b0965
– start-page: 3110
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0440
  article-title: Two-stream flow-guided convolutional attention networks for action recognition, in
– start-page: 183
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0105
  article-title: Skeleton-based action recognition with shift graph convolutional network, in
– ident: 10.1016/j.neucom.2022.09.071_b0305
  doi: 10.1109/CVPR.1997.609450
– volume: 28
  start-page: 1807
  issue: 8
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b1165
  article-title: Human action recognition using 3d reconstruction data
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
  doi: 10.1109/TCSVT.2016.2643161
– start-page: 1012
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0715
  article-title: Ensemble deep learning for skeleton-based action recognition using temporal sliding lstm networks
– start-page: 1625
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0925
  article-title: Stronger, faster and more explainable: A graph convolutional baseline for skeleton-based action recognition
– start-page: 2490
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1370
  article-title: Ms2l: Multi-task self-supervised learning for skeleton based action recognition
– ident: 10.1016/j.neucom.2022.09.071_b0390
  doi: 10.1007/11744085_28
– volume: 24
  start-page: 1565
  issue: 12
  year: 2006
  ident: 10.1016/j.neucom.2022.09.071_b0175
  article-title: What is a support vector machine?
  publication-title: Nature biotechnology
  doi: 10.1038/nbt1206-1565
– ident: 10.1016/j.neucom.2022.09.071_b0685
  doi: 10.5220/0007555407440748
– start-page: 6752
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b1215
  article-title: Weakly supervised action localization by sparse temporal pooling network, in
– year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0650
– volume: 36
  start-page: 1579
  issue: 13–14
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0035
  article-title: Phase estimation for fast action recognition and trajectory generation in human–robot collaboration
  publication-title: The International Journal of Robotics Research
  doi: 10.1177/0278364917693927
– start-page: 826
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0740
  article-title: Relational network for skeleton-based action recognition
– volume: 36
  start-page: 621
  issue: 3
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0900
  article-title: Skeleton-based action recognition by part-aware graph convolutional networks
  publication-title: The visual computer
  doi: 10.1007/s00371-019-01644-3
– start-page: 547
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0725
  article-title: Multi-source learning for skeleton-based action recognition using deep lstm networks
– start-page: 694
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1050
  article-title: Spatial temporal transformer network for skeleton-based action recognition, in
  publication-title: International Conference on Pattern Recognition, Springer
– start-page: 473
  year: 2014
  ident: 10.1016/j.neucom.2022.09.071_b0415
  article-title: Real-time skeleton-tracking-based human action recognition using kinect data, in
  publication-title: International Conference on Multimedia Modeling, Springer
  doi: 10.1007/978-3-319-04114-8_40
– start-page: 2641
  year: 2014
  ident: 10.1016/j.neucom.2022.09.071_b0355
  article-title: From stochastic grammar to bayes network: Probabilistic parsing of complex activity, in
– volume: 86
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0505
  article-title: Human action recognition using two-stream attention based lstm networks
  publication-title: Applied soft computing
  doi: 10.1016/j.asoc.2019.105820
– start-page: 6299
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0955
  article-title: Quo vadis, action recognition? a new model and the kinetics dataset, in
– volume: 11
  start-page: 623
  issue: 8
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0080
  article-title: Survey on deep learning methods in human action recognition
  publication-title: IET Computer Vision
  doi: 10.1049/iet-cvi.2016.0355
– start-page: 3829
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1400
  article-title: Finding achilles’ heel: Adversarial attack on multi-modal action recognition
– start-page: 909
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0975
  article-title: Tea: Temporal excitation and aggregation for action recognition
– start-page: 2735
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0210
  article-title: Jolo-gcn: mining joint-centered light-weight information for skeleton-based action recognition
– start-page: 1655
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1385
  article-title: Skeleton-contrastive 3d action representation learning, in
– volume: 87
  start-page: 19
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0125
  article-title: Effects of camera viewing angles on tracking kinematic gait patterns using azure kinect, kinect v2 and orbbec astra pro v2
  publication-title: Gait & posture
  doi: 10.1016/j.gaitpost.2021.04.005
– start-page: 3556
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1430
  article-title: Progressive teacher-student learning for early action prediction, in
– start-page: 635
  year: 2010
  ident: 10.1016/j.neucom.2022.09.071_b0185
  article-title: Making action recognition robust to occlusions and viewpoint changes, in
  publication-title: European Conference on Computer Vision, Springer
– volume: 22
  start-page: 1315
  issue: 10
  year: 2004
  ident: 10.1016/j.neucom.2022.09.071_b0255
  article-title: What is a hidden markov model?
  publication-title: Nature biotechnology
  doi: 10.1038/nbt1004-1315
– volume: 18
  start-page: 141
  issue: 2
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b0410
  article-title: Effective active skeleton representation for low latency human action recognition
  publication-title: IEEE Transactions on Multimedia
  doi: 10.1109/TMM.2015.2505089
– volume: 78
  start-page: 507
  issue: 1
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0580
  article-title: Action recognition with multi-scale trajectory-pooled 3d convolutional descriptors
  publication-title: Multimedia Tools and Applications
  doi: 10.1007/s11042-017-5251-3
– ident: 10.1016/j.neucom.2022.09.071_b1425
  doi: 10.1609/aaai.v32i1.12324
– volume: 21
  start-page: 452
  issue: 2
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1060
  article-title: Shallow graph convolutional network for skeleton-based action recognition
  publication-title: Sensors
  doi: 10.3390/s21020452
– ident: 10.1016/j.neucom.2022.09.071_b0220
  doi: 10.1007/978-1-4471-4730-5_3
– start-page: 3323
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b1240
  article-title: Interaction part mining: A mid-level approach for fine-grained action recognition
– start-page: 7733
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0325
  article-title: Bayesian hierarchical dynamic model for human action recognition, in
– volume: 27
  start-page: 2613
  issue: 12
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0560
  article-title: Temporal pyramid pooling-based convolutional neural network for action recognition
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
  doi: 10.1109/TCSVT.2016.2576761
– start-page: 2117
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0760
  article-title: View adaptive recurrent neural networks for high performance human action recognition from skeleton data
– start-page: 10457
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1100
  article-title: Listen to look: Action recognition by previewing audio, in
– start-page: 769
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1255
  article-title: Collaborative learning of gesture recognition and 3d hand pose estimation with multi-order feature analysis, in
  publication-title: European Conference on Computer Vision, Springer
– start-page: 5137
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b1260
  article-title: 2d/3d pose estimation and action recognition using multitask deep learning, in
– ident: 10.1016/j.neucom.2022.09.071_b0420
– start-page: 601
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0755
  article-title: Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn
– ident: 10.1016/j.neucom.2022.09.071_b0935
  doi: 10.1109/ICPR.2004.1334462
– volume: 115
  start-page: 224
  issue: 2
  year: 2011
  ident: 10.1016/j.neucom.2022.09.071_b0065
  article-title: A survey of vision-based methods for action representation, segmentation and recognition
  publication-title: Computer vision and image understanding
  doi: 10.1016/j.cviu.2010.10.002
– volume: 51
  start-page: 690
  issue: 2
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0005
  article-title: A combined multiple action recognition and summarization for surveillance video sequences
  publication-title: Applied Intelligence
  doi: 10.1007/s10489-020-01823-z
– volume: 8
  start-page: 1
  issue: 4
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0050
  article-title: Approaches and applications of virtual reality and gesture recognition: A review
  publication-title: International Journal of Ambient Computing and Intelligence (IJACI)
  doi: 10.4018/IJACI.2017100101
– volume: 27
  start-page: 2842
  issue: 6
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0810
  article-title: Learning clip representations for skeleton-based 3d action recognition
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2018.2812099
– volume: 55
  start-page: 42
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0070
  article-title: From handcrafted to learned representations for human action recognition: A survey
  publication-title: Image and Vision Computing
  doi: 10.1016/j.imavis.2016.06.007
– start-page: 177
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0500
– ident: 10.1016/j.neucom.2022.09.071_b0360
– start-page: 7387
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1090
  article-title: Tinyvirat: Low-resolution video action recognition
– year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0165
  article-title: Adversarial attack on skeleton-based human action recognition
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– ident: 10.1016/j.neucom.2022.09.071_b1325
  doi: 10.1007/978-3-031-19772-7_21
– start-page: 1895
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1000
– start-page: 2616
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1025
  article-title: Finegym: A hierarchical video dataset for fine-grained action understanding, in
– start-page: 94
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b0025
  article-title: Action recognition for human robot interaction in industrial applications
– start-page: 1717
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1360
  article-title: Unsupervised and semi-supervised domain adaptation for action recognition from drones, in
– start-page: 1112
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0110
  article-title: Semantics-guided neural networks for efficient skeleton-based human action recognition
– start-page: 588
  year: 2014
  ident: 10.1016/j.neucom.2022.09.071_b0385
  article-title: Human action recognition by representing 3d skeletons as points in a lie group, in
– start-page: 5323
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0915
  article-title: Deep progressive reinforcement learning for skeleton-based action recognition, in
– volume: 76
  start-page: 542
  issue: 4
  year: 2012
  ident: 10.1016/j.neucom.2022.09.071_b1410
  article-title: Long-and short-term plastic modeling of action prediction abilities in volleyball
  publication-title: Psychological research
  doi: 10.1007/s00426-011-0383-y
– start-page: 925
  year: 2009
  ident: 10.1016/j.neucom.2022.09.071_b1155
  article-title: Fast realistic multi-action recognition using mined dense spatio-temporal features
– volume: 9
  start-page: 1897
  issue: 8
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b0235
  article-title: Optical flow-motion history image (of-mhi) for action recognition
  publication-title: Signal, Image and Video Processing
  doi: 10.1007/s11760-014-0677-9
– ident: 10.1016/j.neucom.2022.09.071_b0285
– ident: 10.1016/j.neucom.2022.09.071_b0795
– ident: 10.1016/j.neucom.2022.09.071_b1290
  doi: 10.1109/CVPR52688.2022.01957
– ident: 10.1016/j.neucom.2022.09.071_b0260
  doi: 10.1007/BFb0053999
– volume: 112
  start-page: 161
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0490
  article-title: First person action recognition via two-stream convnet with long-term fusion pooling
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2018.07.011
– ident: 10.1016/j.neucom.2022.09.071_b0525
  doi: 10.1609/aaai.v32i1.12333
– start-page: 14333
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0875
  article-title: Context aware graph convolution for skeleton-based action recognition, in
– volume: 40
  start-page: 3007
  issue: 12
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b1045
  article-title: Skeleton-based action recognition using spatio-temporal lstm network with trust gates
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2017.2771306
– start-page: 35
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1380
  article-title: Adversarial self-supervised learning for semi-supervised 3d action recognition, in
  publication-title: European Conference on Computer Vision, Springer
– volume: 1
  start-page: 195
  issue: 3
  year: 2007
  ident: 10.1016/j.neucom.2022.09.071_b0280
  article-title: The application of hidden markov models in speech recognition
  publication-title: Signal Processing
– volume: 132
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0640
  article-title: A hardware-adaptive deep feature matching pipeline for real-time 3d reconstruction
  publication-title: Computer-Aided Design
  doi: 10.1016/j.cad.2020.102984
– volume: 8
  start-page: 168297
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1120
  article-title: Infrared and 3d skeleton feature fusion for rgb-d action recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.3023599
– start-page: 670
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0555
  article-title: Omni-sourced webly-supervised learning for video recognition, in
  publication-title: European Conference on Computer Vision, Springer
– start-page: 2777
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1340
  article-title: One-shot action recognition in challenging therapy scenarios
– ident: 10.1016/j.neucom.2022.09.071_b0860
  doi: 10.1609/aaai.v33i01.33018561
– volume: 16
  start-page: 3100
  issue: 5
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1200
  article-title: Encoding pose features to images with data augmentation for 3-d action recognition
  publication-title: IEEE Transactions on Industrial Informatics
  doi: 10.1109/TII.2019.2910876
– start-page: 13359
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0890
  article-title: Channel-wise topology refinement graph convolution for skeleton-based action recognition
– start-page: 3210
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b1300
  article-title: Multi-modal three-stream network for action recognition
– start-page: 1129
  year: 2012
  ident: 10.1016/j.neucom.2022.09.071_b1175
  article-title: Multi-view human action recognition under occlusion based on fuzzy distances and neural networks
– start-page: 7852
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0610
  article-title: Ddlstm: dual-domain lstm for cross-dataset action recognition, in
– start-page: 13065
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0990
  article-title: Learning self-similarity in space and time as generalized motion for video action recognition
– start-page: 4511
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1250
  article-title: H+ o: Unified egocentric recognition of 3d hand-object poses and interactions, in
– volume: 37
  start-page: 193
  issue: 3
  year: 2013
  ident: 10.1016/j.neucom.2022.09.071_b0055
  article-title: Adapting user interfaces for gestural interaction with the flexible action and articulated skeleton toolkit
  publication-title: Computers & Graphics
  doi: 10.1016/j.cag.2012.11.004
– year: 2022
  ident: 10.1016/j.neucom.2022.09.071_b0095
  article-title: Human action recognition from various data modalities: A review
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2022.3183112
– volume: 8
  start-page: 1
  issue: 1
  year: 1984
  ident: 10.1016/j.neucom.2022.09.071_b0265
  article-title: On the sum of all distances in a graph or digraph
  publication-title: Journal of Graph Theory
  doi: 10.1002/jgt.3190080102
– start-page: 3510
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0045
  article-title: On-line simultaneous learning and recognition of everyday activities from virtual reality performances
– start-page: 103
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0930
  article-title: Skeleton-based action recognition with spatial reasoning and temporal stack learning
– volume: 41
  start-page: 1963
  issue: 8
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0785
  article-title: View adaptive neural networks for high performance skeleton-based human action recognition
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2019.2896631
– ident: 10.1016/j.neucom.2022.09.071_b0895
  doi: 10.1609/aaai.v33i01.33018989
– start-page: 171
  year: 2006
  ident: 10.1016/j.neucom.2022.09.071_b0405
  article-title: Human action recognition using star skeleton, in
– start-page: 513
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b1030
  article-title: Resound: Towards action recognition without representation bias, in
– year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0645
– start-page: 9985
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1310
  article-title: Out-of-distribution detection for generalized zero-shot action recognition
– volume: 24
  start-page: 280
  issue: 1
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0060
  article-title: Efficient and robust skeleton-based quality assessment and abnormality detection in human action performance
  publication-title: IEEE journal of biomedical and health informatics
  doi: 10.1109/JBHI.2019.2904321
– volume: 53
  start-page: 130
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0115
  article-title: 3d skeleton-based human action classification: A survey
  publication-title: Pattern Recognition
  doi: 10.1016/j.patcog.2015.11.019
– start-page: 3551
  year: 2013
  ident: 10.1016/j.neucom.2022.09.071_b0250
  article-title: Action recognition with improved trajectories, in
– start-page: 5386
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0135
  article-title: Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation
– start-page: 9631
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1225
  article-title: Predict & cluster: Unsupervised skeleton based action recognition, in
– ident: 10.1016/j.neucom.2022.09.071_b1415
  doi: 10.1007/978-3-319-10578-9_45
– start-page: 317
  year: 2006
  ident: 10.1016/j.neucom.2022.09.071_b0350
  article-title: Bayesian classification of task-oriented actions based on stochastic context-free grammar, in
– start-page: 12026
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0845
  article-title: Two-stream adaptive graph convolutional networks for skeleton-based action recognition, in
– start-page: 1473
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b1420
  article-title: Deep sequential context networks for action prediction, in
– volume: 32
  start-page: 4
  issue: 1
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0830
  article-title: A comprehensive survey on graph neural networks
  publication-title: IEEE transactions on neural networks and learning systems
  doi: 10.1109/TNNLS.2020.2978386
– start-page: 91
  year: 2022
  ident: 10.1016/j.neucom.2022.09.071_b1405
  article-title: Multi-modal hybrid architecture for pedestrian action prediction
– start-page: 1
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0540
  article-title: An improved two-stream 3d convolutional neural network for human action recognition
– start-page: 13423
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1355
  article-title: Skeleton cloud colorization for unsupervised 3d action representation learning
– start-page: 7912
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0870
  article-title: Skeleton-based action recognition with directed graph neural networks, in
– ident: 10.1016/j.neucom.2022.09.071_b1330
– volume: 2020
  start-page: 1
  issue: 1
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0495
  article-title: Improved two-stream module for human action recognition
  publication-title: EURASIP Journal on Image and Video Processing
  doi: 10.1186/s13640-020-00501-x
– ident: 10.1016/j.neucom.2022.09.071_b0995
– volume: 7
  start-page: 57267
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0485
  article-title: A spatiotemporal heterogeneous two-stream network for action recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2910604
– year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0620
  article-title: Trear: Transformer-based rgb-d egocentric action recognition
  publication-title: IEEE Transactions on Cognitive and Developmental Systems
– year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1020
– volume: 133
  start-page: 471
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0565
  article-title: Human action recognition using 3d convolutional neural networks with 3d motion cuboids in surveillance videos
  publication-title: Procedia computer science
  doi: 10.1016/j.procs.2018.07.059
– start-page: 466
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0665
  article-title: Simple baselines for human pose estimation and tracking, in
– ident: 10.1016/j.neucom.2022.09.071_b0290
– start-page: 2556
  year: 2011
  ident: 10.1016/j.neucom.2022.09.071_b0960
  article-title: Hmdb: a large video database for human motion recognition
– start-page: 5693
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0130
  article-title: Deep high-resolution representation learning for human pose estimation, in
– start-page: 2000
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0970
  article-title: Stm: Spatiotemporal and motion encoding for action recognition
– start-page: 13638
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1320
  article-title: Elaborative rehearsal for zero-shot action recognition, in
– volume: 33
  start-page: 251
  issue: 3
  year: 1991
  ident: 10.1016/j.neucom.2022.09.071_b0270
  article-title: Hidden markov models for speech recognition
  publication-title: Technometrics
  doi: 10.1080/00401706.1991.10484833
– start-page: 139
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0455
  article-title: Semi-coupled two-stream fusion convnets for action recognition at extremely low resolutions
– start-page: 1
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0585
  article-title: Human action recognition with 3d convolutional neural network
– volume: 232
  start-page: 76
  issue: 6
  year: 1975
  ident: 10.1016/j.neucom.2022.09.071_b0170
  article-title: Visual motion perception
  publication-title: Scientific American
  doi: 10.1038/scientificamerican0675-76
– start-page: 3
  year: 2002
  ident: 10.1016/j.neucom.2022.09.071_b0310
  article-title: Layered representations for human activity recognition, in: Proceedings
– ident: 10.1016/j.neucom.2022.09.071_b0180
  doi: 10.1007/978-1-4899-7641-3_9
– volume: 23
  start-page: 255
  issue: 2
  year: 2012
  ident: 10.1016/j.neucom.2022.09.071_b0215
  article-title: Motion history image: its variants and applications
  publication-title: Machine Vision and Applications
  doi: 10.1007/s00138-010-0298-4
– start-page: 6202
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0450
  article-title: Slowfast networks for video recognition, in
– start-page: 143
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0850
  article-title: Disentangling and unifying graph convolutions for skeleton-based action recognition
– start-page: 1
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b1150
  article-title: Concurrence-aware long short-term sub-memories for person-person action recognition
– ident: 10.1016/j.neucom.2022.09.071_b0675
– start-page: 63
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b1305
  article-title: Semantic embedding space for zero-shot action recognition
– start-page: 179
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1230
  article-title: Video jigsaw: Unsupervised learning of spatiotemporal context for video action recognition
– volume: 35
  start-page: 221
  issue: 1
  year: 2012
  ident: 10.1016/j.neucom.2022.09.071_b0510
  article-title: 3d convolutional neural networks for human action recognition
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2012.59
– ident: 10.1016/j.neucom.2022.09.071_b1280
– volume: 27
  issue: 4
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0815
  article-title: Multisource learning for skeleton-based action recognition using deep lstm and cnn
  publication-title: Journal of Electronic Imaging
  doi: 10.1117/1.JEI.27.4.043050
– start-page: 61
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1125
  article-title: Skeleton-based action recognition of people handling objects
– start-page: 1290
  year: 2012
  ident: 10.1016/j.neucom.2022.09.071_b0375
  article-title: Mining actionlet ensemble for action recognition with depth cameras
– year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0800
  article-title: Skepxels: Spatio-temporal image representation of human skeleton joints for action recognition., in
  publication-title: CVPR workshops
– year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1080
  article-title: Fexnet: Foreground extraction network for human action recognition
  publication-title: IEEE Transactions on Circuits and Systems for Video Technology
– start-page: 4315
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b1145
  article-title: Social scene understanding: End-to-end multi-person action localization and collective activity recognition
– volume: 132
  start-page: 1317
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0015
  article-title: Human detection and tracking using hog for action recognition
  publication-title: Procedia computer science
  doi: 10.1016/j.procs.2018.05.048
– start-page: 1049
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1245
  article-title: Something-else: Compositional action recognition with spatial-temporal interaction networks
– start-page: 4741
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b1350
  article-title: 3d human action representation learning via cross-view consistency pursuit
– ident: 10.1016/j.neucom.2022.09.071_b0295
  doi: 10.1109/CVPR.1992.223161
– volume: 8
  start-page: 302
  issue: 4
  year: 1997
  ident: 10.1016/j.neucom.2022.09.071_b0190
  article-title: Viewpoint dependence in scene recognition
  publication-title: Psychological science
  doi: 10.1111/j.1467-9280.1997.tb00442.x
– start-page: 1607
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0460
  article-title: Fully-coupled two-stream spatiotemporal networks for extremely low resolution action recognition
– start-page: 244
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0615
  article-title: Video action transformer network, in
– volume: 20
  start-page: 3499
  issue: 12
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0855
  article-title: Gas-gcn: Gated action-specific graph convolutional networks for skeleton-based action recognition
  publication-title: Sensors
  doi: 10.3390/s20123499
– start-page: 14
  year: 2012
  ident: 10.1016/j.neucom.2022.09.071_b0400
  article-title: Eigenjoints-based action recognition using naive-bayes-nearest-neighbor
– ident: 10.1016/j.neucom.2022.09.071_b1180
  doi: 10.1007/978-1-4615-0377-4_5
– volume: 29
  start-page: 9532
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0865
  article-title: Skeleton-based action recognition with multi-stream adaptive graph convolutional networks
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2020.3028207
– year: 2004
  ident: 10.1016/j.neucom.2022.09.071_b0315
  article-title: Modeling individual and group actions in meetings: a two-layer hmm framework
– volume: 444
  start-page: 319
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0600
  article-title: Db-lstm: Densely-connected bi-directional lstm for human action recognition
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.05.118
– volume: 103
  start-page: 60
  issue: 1
  year: 2013
  ident: 10.1016/j.neucom.2022.09.071_b0245
  article-title: Dense trajectories and motion boundary descriptors for action recognition
  publication-title: International journal of computer vision
  doi: 10.1007/s11263-012-0594-8
– ident: 10.1016/j.neucom.2022.09.071_b1065
– ident: 10.1016/j.neucom.2022.09.071_b1015
– start-page: 122
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1295
  article-title: Multi-modal domain adaptation for fine-grained action recognition, in
– volume: 6
  start-page: 50788
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0720
  article-title: Skeleton feature fusion based on multi-stream lstm for action recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2869751
– start-page: 16266
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0480
  article-title: Uav-human: A large benchmark for human behavior understanding with unmanned aerial vehicles
– volume: 3
  start-page: 1
  issue: 1
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b1195
  article-title: Data augmentation in deep learning-based fusion of depth and inertial sensing for action recognition
  publication-title: IEEE Sensors Letters
  doi: 10.1109/LSENS.2018.2878572
– start-page: 20
  year: 2012
  ident: 10.1016/j.neucom.2022.09.071_b0395
  article-title: View invariant human action recognition using histograms of 3d joints
– volume: 43
  start-page: 172
  issue: 1
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0680
  article-title: Openpose: realtime multi-person 2d pose estimation using part affinity fields
  publication-title: IEEE transactions on pattern analysis and machine intelligence
  doi: 10.1109/TPAMI.2019.2929257
– volume: 56
  start-page: 605
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0475
  article-title: Transferable two-stream convolutional neural network for human action recognition
  publication-title: Journal of Manufacturing Systems
  doi: 10.1016/j.jmsy.2020.04.007
– ident: 10.1016/j.neucom.2022.09.071_b0945
– start-page: 8984
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0200
  article-title: Graph-based high-order relation modeling for long-term action recognition, in
– start-page: 1
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0690
  article-title: Real-time human gesture grading based on openpose
– start-page: 4552
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b0330
  article-title: Action recognition by hierarchical mid-level action elements, in
– start-page: 508
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1140
  article-title: Weakly-supervised multi-person action recognition in 360<error l=”619” c=”Undefined command ”/> videos
– year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0835
  article-title: Spatial temporal graph convolutional networks for skeleton-based action recognition
– start-page: 515
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0155
  article-title: Over-the-air adversarial flickering attacks against video recognition networks
– ident: 10.1016/j.neucom.2022.09.071_b0445
  doi: 10.1007/978-3-030-20893-6_23
– start-page: 175
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1130
  article-title: Real-time multi-camera multi-person action recognition using pose estimation, in
– start-page: 99
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0605
  article-title: Football action recognition using hierarchical lstm, in
– volume: 20
  start-page: 61
  issue: 1
  year: 2008
  ident: 10.1016/j.neucom.2022.09.071_b0825
  article-title: The graph neural network model
  publication-title: IEEE transactions on neural networks
  doi: 10.1109/TNN.2008.2005605
– start-page: 1
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0920
  article-title: Richly activated graph convolutional network for action recognition with incomplete skeletons
– ident: 10.1016/j.neucom.2022.09.071_b1375
  doi: 10.1609/aaai.v36i1.19957
– ident: 10.1016/j.neucom.2022.09.071_b0120
– start-page: 579
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b0770
  article-title: Skeleton based action recognition with convolutional neural network
– start-page: 12046
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b1220
  article-title: Large-scale weakly-supervised pre-training for video action recognition, in
– start-page: 1227
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0750
  article-title: An attention enhanced graph convolutional lstm network for skeleton-based action recognition
– start-page: 16
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0780
  article-title: Skeleton image representation for 3d action recognition based on tree structure and reference joints
– start-page: 1
  year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0425
  article-title: Two-stream convolution neural network with video-stream for action recognition
– volume: 12
  start-page: 744
  issue: 5
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0695
  article-title: Fall detection based on key points of human-skeleton using openpose
  publication-title: Symmetry
  doi: 10.3390/sym12050744
– start-page: 1
  year: 2006
  ident: 10.1016/j.neucom.2022.09.071_b1170
  article-title: Human model and motion based 3d action recognition in multiple view scenarios
– year: 2019
  ident: 10.1016/j.neucom.2022.09.071_b0885
  article-title: Spatial residual layer and dense connection block enhanced spatial temporal graph convolutional network for skeleton-based action recognition
– start-page: 55
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0880
  article-title: Dynamic gcn: Context-enriched topology learning for skeleton-based action recognition
– ident: 10.1016/j.neucom.2022.09.071_b1335
  doi: 10.1109/CVPR52688.2022.01933
– ident: 10.1016/j.neucom.2022.09.071_b1235
  doi: 10.1007/978-3-642-15549-9_36
– volume: 60
  start-page: 4
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0075
  article-title: Going deeper into action recognition: A survey
  publication-title: Image and vision computing
  doi: 10.1016/j.imavis.2017.01.010
– start-page: 1010
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b1035
  article-title: Ntu rgb+ d: A large scale dataset for 3d human activity analysis
– year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b0365
  article-title: Walking, lifting, standing activity recognition using probabilistic networks
  publication-title: International Research Journal of Engineering and Technology (IRJET)
– start-page: 1110
  year: 2015
  ident: 10.1016/j.neucom.2022.09.071_b1110
  article-title: Hierarchical recurrent neural network for skeleton based action recognition, in
– volume: 84
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1275
  article-title: Human action recognition toward massive-scale sport sceneries based on deep multi-model feature fusion
  publication-title: Signal Processing: Image Communication
– start-page: 1102
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b0985
  article-title: Gate-shift networks for video action recognition, in
– volume: 20
  start-page: 634
  issue: 3
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0465
  article-title: Two-stream 3-d convnet fusion for action recognition in videos with arbitrary size and length
  publication-title: IEEE Transactions on Multimedia
  doi: 10.1109/TMM.2017.2749159
– ident: 10.1016/j.neucom.2022.09.071_b0150
  doi: 10.1007/978-3-030-58558-7_31
– start-page: 6165
  year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0195
  article-title: Deep analysis of cnn-based spatio-temporal representations for action recognition
– volume: 20
  start-page: 4758
  issue: 17
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1135
  article-title: Deep learning-based real-time multiple-person action recognition system
  publication-title: Sensors
  doi: 10.3390/s20174758
– start-page: 6450
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0570
  article-title: A closer look at spatiotemporal convolutions for action recognition
– start-page: 1647
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0735
  article-title: Global context-aware attention lstm networks for 3d action recognition
– start-page: 3288
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0805
  article-title: A new representation of skeleton sequences for 3d action recognition
– start-page: 1
  year: 2018
  ident: 10.1016/j.neucom.2022.09.071_b0430
  article-title: Improving human action recognition with two-stream 3d convolutional neural network
– volume: 77
  start-page: 257
  issue: 2
  year: 1989
  ident: 10.1016/j.neucom.2022.09.071_b0275
  article-title: A tutorial on hidden markov models and selected applications in speech recognition
  publication-title: Proceedings of the IEEE
  doi: 10.1109/5.18626
– start-page: 1145
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0710
  article-title: Hand keypoint detection in single images using multiview bootstrapping, in
– start-page: 505
  year: 2020
  ident: 10.1016/j.neucom.2022.09.071_b1095
  article-title: Rubiksnet: Learnable 3d-shift for efficient video action recognition, in
  publication-title: European Conference on Computer Vision, Springer
– ident: 10.1016/j.neucom.2022.09.071_b0370
  doi: 10.1109/CVPR.1998.698711
– ident: 10.1016/j.neucom.2022.09.071_b1390
– start-page: 212
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0230
  article-title: Action recognition using mhi based hu moments with hmms
– ident: 10.1016/j.neucom.2022.09.071_b0625
  doi: 10.1109/CVPR42600.2020.00059
– start-page: 5832
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0790
  article-title: Learning action recognition model from depth and skeleton videos, in
– start-page: 1837
  year: 2017
  ident: 10.1016/j.neucom.2022.09.071_b0575
  article-title: 3d convolutional neural network with multi-model framework for action recognition
– volume: Vol. 1
  start-page: 178
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0595
  article-title: Action recognition based on features fusion and 3d convolutional neural networks
– ident: 10.1016/j.neucom.2022.09.071_b1315
  doi: 10.1609/aaai.v33i01.33018303
– volume: 78
  start-page: 107
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0635
  article-title: A multi-frame graph matching algorithm for low-bandwidth rgb-d slam
  publication-title: Computer-Aided Design
  doi: 10.1016/j.cad.2016.05.009
– start-page: 145
  year: 2009
  ident: 10.1016/j.neucom.2022.09.071_b0300
  article-title: Distributed continuous action recognition using a hidden markov model in body sensor networks
– start-page: 770
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0670
  article-title: Deep residual learning for image recognition, in
– ident: 10.1016/j.neucom.2022.09.071_b1345
– volume: 60
  start-page: 86
  year: 2016
  ident: 10.1016/j.neucom.2022.09.071_b0100
  article-title: Rgb-d-based action recognition datasets: A survey
  publication-title: Pattern Recognition
  doi: 10.1016/j.patcog.2016.05.019
– year: 2021
  ident: 10.1016/j.neucom.2022.09.071_b0205
  article-title: Memory attention networks for skeleton-based action recognition
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
SSID ssj0017129
Score 2.5699618
Snippet Action recognition is a major branch of computer vision research. As a widely used technology, action recognition has been applied to human–computer...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 287
SubjectTerms Pose estimation
RGB-based end-to-end action recognition method
Self-supervised learning
Skeleton-based cascaded action recognition method
Transfer learning
Unsupervised learning
Title Action recognition based on RGB and skeleton data sets: A survey
URI https://dx.doi.org/10.1016/j.neucom.2022.09.071
Volume 512
WOSCitedRecordID wos000862479300004&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Jb9QwFLbKlAOXQllEKSAfuKGgxG5im1MDFGiFKlRGaOASeYs6Q0nLZFKVf8_zkjBlEJvEJbKseMbx-_T8-fktCD1KBVNaCZXomugEEFInSjInEE2FVrYmPtvn-zfs8JBPJuJtjC5pfTkB1jT84kKc_VdRQx8I24XO_oW4hx-FDmiD0OEJYofnHwm-DMW_B88gaLutyrhrgaNXz_xtQfsJdhuXUMM5iD5u7aINEeptNz-_fNHrk3doX_ohGhXKzy63gnFAGowIHzpvFz3qZv1O6D17g3H14_H0CzSH_hedN7key9Ov02WjA5xXs0tGh9VomGBSJHkCfDFoVxsUKmfEh6ova9w8vhJ1Ztxxw_ZLfQKCVc0ejAyzJ43tnJuPm5RPUBsKuPyQM_udm4qbCXH8JhfFFbROWC74CK2X-3uTg-GiiWUkpGOMU--jK70L4Op__Zy9LDGS8Q20EY8SuAwQ2ERrtrmJrvdlOnDU2rfQbkAEXkIE9ojA0ABEYEAE7hGBHSKwQ8RTXOKAh9to_HJv_Px1EgtnJJoyski4JoVkKQPql1qhrLR8RxuW1Yoa-Jg6A1pObZpZoJeGm0KqXOZ5nVqqZQF89g4aNaeNvYuwMVlRWMEoN8Dl-I6iMitSKxWcgm1K1Rai_XpUOiaVd7VNTqree3BWhVWs3CpWqahgFbdQMow6C0lVfvM-65e6isQwEL4K0PHLkff-eeQ2uvYd-PfRaDHv7AN0VZ8vpu38YYTRN033hpY
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=Action+recognition+based+on+RGB+and+skeleton+data+sets%3A+A+survey&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Yue%2C+Rujing&rft.au=Tian%2C+Zhiqiang&rft.au=Du%2C+Shaoyi&rft.date=2022-11-01&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=512&rft.spage=287&rft.epage=306&rft_id=info:doi/10.1016%2Fj.neucom.2022.09.071&rft.externalDocID=S0925231222011596
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon