Human Action Recognition From Various Data Modalities: A Review

Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 3; pp. 3200 - 3225
Main Authors Sun, Zehua, Ke, Qiuhong, Rahmani, Hossein, Bennamoun, Mohammed, Wang, Gang, Liu, Jun
Format Journal Article
LanguageEnglish
Published United States IEEE 01.03.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Acceleration
Algorithms
Computer vision
data modality
Deep learning
Feature extraction
Human action recognition
Human Activities
Human activity recognition
Human motion
Humans
Machine learning
multi-modality
Optical imaging
Pattern Recognition, Automated - methods
Radar
single modality
Skeleton
Teaching methods
Three-dimensional displays
Visualization
Online AccessGet full text
ISSN0162-8828
1939-3539
2160-9292
1939-3539
DOI10.1109/TPAMI.2022.3183112

Cover

Abstract Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, radar, and WiFi signal, which encode different sources of useful yet distinct information and have various advantages depending on the application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this article, we present a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality. Specifically, we review the current mainstream deep learning methods for single data modalities and multiple data modalities, including the fusion-based and the co-learning-based frameworks. We also present comparative results on several benchmark datasets for HAR, together with insightful observations and inspiring future research directions.
AbstractList Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, radar, and WiFi signal, which encode different sources of useful yet distinct information and have various advantages depending on the application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this article, we present a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality. Specifically, we review the current mainstream deep learning methods for single data modalities and multiple data modalities, including the fusion-based and the co-learning-based frameworks. We also present comparative results on several benchmark datasets for HAR, together with insightful observations and inspiring future research directions.
Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, radar, and WiFi signal, which encode different sources of useful yet distinct information and have various advantages depending on the application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this article, we present a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality. Specifically, we review the current mainstream deep learning methods for single data modalities and multiple data modalities, including the fusion-based and the co-learning-based frameworks. We also present comparative results on several benchmark datasets for HAR, together with insightful observations and inspiring future research directions.Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions can be represented using various data modalities, such as RGB, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, radar, and WiFi signal, which encode different sources of useful yet distinct information and have various advantages depending on the application scenarios. Consequently, lots of existing works have attempted to investigate different types of approaches for HAR using various modalities. In this article, we present a comprehensive survey of recent progress in deep learning methods for HAR based on the type of input data modality. Specifically, we review the current mainstream deep learning methods for single data modalities and multiple data modalities, including the fusion-based and the co-learning-based frameworks. We also present comparative results on several benchmark datasets for HAR, together with insightful observations and inspiring future research directions.
Author Sun, Zehua
Wang, Gang
Bennamoun, Mohammed
Liu, Jun
Ke, Qiuhong
Rahmani, Hossein
Author_xml – sequence: 1
  givenname: Zehua
  orcidid: 0000-0002-8568-2121
  surname: Sun
  fullname: Sun, Zehua
  email: zehua.sun@my.cityu.edu.hk
  organization: Singapore University of Technology and Design, Singapore
– sequence: 2
  givenname: Qiuhong
  orcidid: 0000-0001-9998-3614
  surname: Ke
  fullname: Ke, Qiuhong
  email: Qiuhong.Ke@monash.edu
  organization: Monash University, Clayton, VIC, Australia
– sequence: 3
  givenname: Hossein
  orcidid: 0000-0003-1920-0371
  surname: Rahmani
  fullname: Rahmani, Hossein
  email: h.rahmani@lancaster.ac.uk
  organization: Lancaster University, Lancaster, UK
– sequence: 4
  givenname: Mohammed
  orcidid: 0000-0002-6603-3257
  surname: Bennamoun
  fullname: Bennamoun, Mohammed
  email: mohammed.bennamoun@uwa.edu.au
  organization: University of Western Australia, Crawley, WA, Australia
– sequence: 5
  givenname: Gang
  orcidid: 0000-0002-1816-1457
  surname: Wang
  fullname: Wang, Gang
  email: wanggang@ntu.edu.sg
  organization: Alibaba Group, Hangzhou, Zhejiang, China
– sequence: 6
  givenname: Jun
  orcidid: 0000-0002-4365-4165
  surname: Liu
  fullname: Liu, Jun
  email: jun_liu@sutd.edu.sg
  organization: Singapore University of Technology and Design, Singapore
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35700242$$D View this record in MEDLINE/PubMed
BookMark eNp9kE1r3DAQhkVJaTZp_0ALwZBLL96OJFuWcglLviGhpaS9ClkaFwXbSiQ7If--2uw2hxw6B41Azzsanj2yM4YRCflMYUkpqG-3P1Y3V0sGjC05lZxS9o4sGBVQKqbYDlkAFayUksldspfSHQCtauAfyC6vGwBWsQU5vpwHMxYrO_kwFj_Rhj-jf7mfxzAUv030YU7FqZlMcROc6fMjpqNildlHj08fyfvO9Ak_bfs--XV-dntyWV5_v7g6WV2XlgtZl60z0tFWcslq6rAVvJUAhlMlGlSdwcaBVVVn20p2AplqwVkEcC3L5Wq-T75u5t7H8DBjmvTgk8W-NyPmBTUTjVD54Cqjh2_QuzDHMW-nWdPwqq45iEwdbKm5HdDp--gHE5_1PzUZYBvAxpBSxO4VoaDX_vWLf732r7f-c0i-CVk_mbXPKRrf_z_6ZRP1iPj6l2pULYXifwEkb5A3
CODEN ITPIDJ
CitedBy_id crossref_primary_10_1109_ACCESS_2024_3483896
crossref_primary_10_1109_TCSVT_2024_3455799
crossref_primary_10_1109_ACCESS_2024_3481631
crossref_primary_10_1049_cvi2_12253
crossref_primary_10_1109_TCE_2024_3361480
crossref_primary_10_3389_fnbot_2024_1502071
crossref_primary_10_1007_s11042_023_15443_5
crossref_primary_10_1016_j_iot_2024_101182
crossref_primary_10_1145_3678503
crossref_primary_10_1109_TMM_2022_3232034
crossref_primary_10_1016_j_neucom_2024_128426
crossref_primary_10_1109_ACCESS_2025_3551610
crossref_primary_10_3390_s23052422
crossref_primary_10_3389_fnins_2023_1225312
crossref_primary_10_3389_fncom_2024_1508297
crossref_primary_10_1007_s11265_023_01892_6
crossref_primary_10_1016_j_patcog_2024_110301
crossref_primary_10_1109_TPAMI_2024_3429387
crossref_primary_10_54097_h8wf8vah
crossref_primary_10_1109_TMM_2024_3521767
crossref_primary_10_1016_j_neucom_2023_126903
crossref_primary_10_1109_TMC_2023_3325399
crossref_primary_10_1007_s40747_025_01811_1
crossref_primary_10_1109_ACCESS_2025_3546266
crossref_primary_10_1016_j_engappai_2024_107850
crossref_primary_10_1109_TIP_2023_3345153
crossref_primary_10_1109_ACCESS_2024_3392356
crossref_primary_10_1109_OJCOMS_2024_3373177
crossref_primary_10_3389_fnins_2024_1370024
crossref_primary_10_1109_ACCESS_2024_3366807
crossref_primary_10_1109_ACCESS_2024_3507272
crossref_primary_10_1038_s41597_024_03344_7
crossref_primary_10_1109_JIOT_2024_3394050
crossref_primary_10_1109_TIP_2024_3433581
crossref_primary_10_1109_TMC_2024_3501299
crossref_primary_10_1109_JSEN_2024_3443308
crossref_primary_10_1109_TCE_2024_3425610
crossref_primary_10_1109_TNNLS_2023_3291793
crossref_primary_10_1109_TII_2024_3450021
crossref_primary_10_1016_j_inffus_2024_102457
crossref_primary_10_1016_j_jvcir_2023_103960
crossref_primary_10_1016_j_asoc_2024_111344
crossref_primary_10_3390_electronics12010117
crossref_primary_10_1109_JIOT_2023_3314150
crossref_primary_10_1016_j_iot_2024_101487
crossref_primary_10_1109_ACCESS_2024_3389499
crossref_primary_10_1109_ACCESS_2024_3390004
crossref_primary_10_1016_j_neucom_2022_09_071
crossref_primary_10_1016_j_neucom_2023_127194
crossref_primary_10_1109_JSEN_2023_3347718
crossref_primary_10_1109_ACCESS_2025_3528880
crossref_primary_10_1007_s11042_022_14214_y
crossref_primary_10_1109_ACCESS_2025_3547360
crossref_primary_10_1016_j_eswa_2024_125642
crossref_primary_10_1109_JIOT_2023_3330996
crossref_primary_10_1007_s00521_024_09630_0
crossref_primary_10_1109_JIOT_2024_3485614
crossref_primary_10_1109_TMM_2024_3521749
crossref_primary_10_1177_00491241241277524
crossref_primary_10_1088_2053_1583_ad6912
crossref_primary_10_1016_j_asoc_2024_112550
crossref_primary_10_1016_j_neucom_2024_127914
crossref_primary_10_1016_j_jvcir_2023_103959
crossref_primary_10_1016_j_neucom_2024_127882
crossref_primary_10_1109_TNNLS_2024_3360990
crossref_primary_10_1109_JMW_2025_3535525
crossref_primary_10_1109_LRA_2024_3455904
crossref_primary_10_1016_j_neucom_2024_127482
crossref_primary_10_1109_ACCESS_2023_3316032
crossref_primary_10_3934_era_2024129
crossref_primary_10_3390_s22145259
crossref_primary_10_1016_j_eswa_2024_126178
crossref_primary_10_15625_1813_9663_18043
crossref_primary_10_1016_j_neucom_2022_07_080
crossref_primary_10_1049_cvi2_12298
crossref_primary_10_1117_1_JEI_34_1_013056
crossref_primary_10_1016_j_neunet_2023_11_002
crossref_primary_10_1109_TIM_2024_3374286
crossref_primary_10_62486_latia20234
crossref_primary_10_1109_JSEN_2025_3529889
crossref_primary_10_1109_TIM_2024_3398094
crossref_primary_10_1109_TBC_2023_3332015
crossref_primary_10_1109_TSMC_2024_3377198
crossref_primary_10_1016_j_compbiomed_2023_106835
crossref_primary_10_1016_j_neucom_2023_127135
crossref_primary_10_1007_s11633_023_1487_8
crossref_primary_10_1109_JSEN_2023_3344789
crossref_primary_10_1145_3643553
crossref_primary_10_1016_j_neucom_2024_127496
crossref_primary_10_1016_j_jvcir_2024_104281
crossref_primary_10_1109_TCSVT_2023_3298978
crossref_primary_10_1109_TKDE_2024_3386794
crossref_primary_10_1109_RBME_2023_3296938
crossref_primary_10_1016_j_neucom_2024_128636
crossref_primary_10_1016_j_neucom_2024_127389
crossref_primary_10_1109_JIOT_2024_3394244
crossref_primary_10_1109_LRA_2024_3355752
crossref_primary_10_1007_s44196_024_00689_0
crossref_primary_10_1016_j_neucom_2025_129781
crossref_primary_10_1016_j_neucom_2023_03_070
crossref_primary_10_1109_TCSVT_2022_3217763
crossref_primary_10_3389_fnins_2023_1278584
crossref_primary_10_3390_s23020734
crossref_primary_10_1007_s11548_024_03158_3
crossref_primary_10_1016_j_neucom_2023_03_001
crossref_primary_10_1109_OJCS_2024_3406645
crossref_primary_10_1109_TPAMI_2024_3378753
crossref_primary_10_1088_2057_1976_ad17f9
crossref_primary_10_1109_JSEN_2024_3491183
crossref_primary_10_3233_AIC_220188
crossref_primary_10_1109_TCE_2024_3384974
crossref_primary_10_1016_j_displa_2023_102434
crossref_primary_10_1016_j_compbiomed_2023_107420
crossref_primary_10_1016_j_engappai_2023_106150
crossref_primary_10_1109_JIOT_2023_3240247
crossref_primary_10_1109_TIP_2023_3308750
crossref_primary_10_1109_LSP_2024_3525398
crossref_primary_10_1109_JSEN_2022_3225031
crossref_primary_10_3389_fninf_2024_1324981
crossref_primary_10_1109_JBHI_2023_3339703
crossref_primary_10_1109_LSENS_2024_3357941
crossref_primary_10_1016_j_cviu_2024_104013
crossref_primary_10_1109_JSEN_2024_3464416
crossref_primary_10_1109_JSEN_2024_3483835
crossref_primary_10_1109_JIOT_2023_3324791
crossref_primary_10_1109_TAP_2024_3484014
crossref_primary_10_1109_LAWP_2024_3397033
crossref_primary_10_1007_s10462_023_10650_w
crossref_primary_10_1109_TMM_2023_3307933
crossref_primary_10_1016_j_eswa_2023_122314
crossref_primary_10_1109_TPAMI_2024_3367879
crossref_primary_10_3390_app12115408
Cites_doi 10.1016/j.patrec.2009.11.017
10.1109/ICCV.2017.316
10.3115/v1/d14-1179
10.1109/ICASSP.2019.8683606
10.1109/ICCV.2015.304
10.1109/CVPR.2013.98
10.1109/CVPR.2016.291
10.1109/WACV45572.2020.9093274
10.1109/ICCV.2015.522
10.1109/LSENS.2018.2878572
10.1109/CVPRW.2017.207
10.1109/CVPR42600.2020.00118
10.1109/CVPR.2019.01232
10.1109/CVPR.2017.337
10.1007/978-3-319-46466-4_50
10.1007/978-3-030-58586-0_32
10.1109/CVPR.2019.00807
10.1109/TPAMI.2019.2896631
10.1109/CVPR.2004.1315191
10.1007/s11390-011-9430-9
10.1109/CVPR52688.2022.00298
10.1109/ICCV.2015.510
10.1145/3472722
10.1109/TMM.2018.2875510
10.1109/CVPR42600.2020.00043
10.1007/978-3-642-15552-9_29
10.1609/aaai.v34i03.5652
10.1109/ACPR.2015.7486569
10.1016/j.procs.2014.07.009
10.1109/ACCESS.2019.2923743
10.1109/ICPR48806.2021.9412632
10.3390/s19173680
10.1109/ICME.2018.8486486
10.1109/LSP.2016.2611485
10.1109/ICME.2019.00187
10.1007/s11263-021-01508-1
10.1007/978-3-319-46484-8_2
10.1145/2964284.2967191
10.1007/s11042-019-08576-z
10.1109/WACV48630.2021.00280
10.1109/TSMC.2018.2850149
10.1109/CVPR.2018.00054
10.1109/CVPR46437.2021.00193
10.1016/j.neucom.2018.10.095
10.1109/CVPR.2019.00371
10.1007/978-3-030-58555-6_40
10.1007/978-3-319-10605-2_48
10.1109/TPAMI.2019.2898954
10.1109/CVPR.2018.00871
10.1007/s00521-020-05144-7
10.1109/ICCV.2017.621
10.1016/j.patcog.2015.09.028
10.1109/FG47880.2020.00018
10.1109/CVPR46437.2021.00332
10.1016/j.bica.2013.05.008
10.3390/s16121990
10.1109/MCOM.2017.1700082
10.1109/FUTURETECH.2010.5482729
10.1016/j.sigpro.2014.08.038
10.1109/CVPR42600.2020.01271
10.1109/CVPR.2019.00319
10.1109/CVPR42600.2020.00067
10.1109/ACCESS.2020.3023599
10.1109/CVPR.2012.6248093
10.1109/ICCV.2017.73
10.1109/ICCV.2013.396
10.1109/WACV48630.2021.00089
10.1109/CVPR46437.2021.01302
10.1007/s11263-013-0636-x
10.1109/CVPR.2019.00810
10.1609/aaai.v32i1.12228
10.1109/CVPR46437.2021.00470
10.1109/TPAMI.2017.2691768
10.1007/s12652-019-01239-9
10.1109/AVSS.2017.8078497
10.1109/SMC.2015.263
10.1016/j.inffus.2022.03.001
10.1016/j.jvcir.2013.03.008
10.1145/3386252
10.1109/ICCV.2019.00092
10.1109/WACV45572.2020.9093307
10.1109/ICCV.2017.402
10.1109/ICPR48806.2021.9412991
10.1109/ICCV.2019.00875
10.1109/CVPR.2011.5995407
10.1007/978-3-030-01237-3_7
10.1145/3132734.3132739
10.1109/CVPR42600.2020.00580
10.1609/aaai.v33i01.33018989
10.3390/s16010115
10.1109/CVPR.2017.787
10.1007/978-3-319-46604-0_47
10.1007/s11263-005-1838-7
10.1109/CVPR.2015.7299101
10.1177/0278364913478446
10.1007/s11263-012-0550-7
10.1109/ICIP.2017.8296630
10.1109/CVPR46437.2021.01600
10.1109/CVPR.2019.00136
10.1145/1964897.1964918
10.1609/aaai.v31i1.11212
10.1109/TNNLS.2019.2935173
10.1007/s11042-021-11058-w
10.1109/CVPR42600.2020.01434
10.1007/978-981-15-4163-6_3
10.1109/ICCVW.2017.123
10.1007/978-3-030-58545-7_5
10.1109/ICMEW.2017.8026282
10.1109/TCYB.2017.2682280
10.1109/LSP.2017.2690339
10.1007/978-3-319-46487-9_50
10.1109/ICCVW.2011.6130379
10.1007/978-3-030-58571-6_6
10.1007/978-3-319-46448-0_31
10.1016/j.cviu.2006.07.013
10.1109/CVPR46437.2021.00966
10.1145/2789168.2790093
10.1109/JSAC.2017.2679658
10.1109/CVPR.2019.00137
10.1145/2733373.2806333
10.1109/CVPR.2017.243
10.1109/ICCV.2017.233
10.1109/CVPR.2019.01019
10.1109/TVT.2017.2737553
10.1109/CVPR42600.2020.00028
10.3390/app9040716
10.1109/ICCV.2015.460
10.1016/j.patcog.2017.10.037
10.1007/978-3-030-58621-8_25
10.1016/j.cogsys.2018.04.002
10.1109/CVPR42600.2020.00059
10.1145/3242587.3242609
10.1109/BSN.2006.6
10.1109/MSN48538.2019.00026
10.1145/2733373.2806222
10.1109/ICASSP.2017.7952132
10.1109/TPAMI.2021.3053765
10.1109/CVPR46437.2021.01025
10.1109/RADAR41533.2019.171307
10.1109/CVPR.2017.113
10.1109/CVPR.2016.213
10.1109/CVPR.2014.82
10.1007/978-3-642-33868-7_6
10.1145/2639108.2639143
10.1007/s11042-022-12091-z
10.1109/CVPR46437.2021.00887
10.24963/ijcai.2018/109
10.1109/COMPEM.2018.8496654
10.1145/1922649.1922653
10.3390/s19071644
10.1109/TCSVT.2016.2628339
10.1145/2671188.2749340
10.1109/CVPR.2017.168
10.1007/978-3-030-68238-5_48
10.1109/CVPR46437.2021.01301
10.1109/TCSVT.2018.2808682
10.1109/TPAMI.2017.2691321
10.1109/TPAMI.2007.70711
10.1109/CVPR.2018.00633
10.1109/DSW.2018.8439897
10.1109/TPAMI.2012.59
10.1007/s11263-021-01467-7
10.1609/aaai.v32i1.12328
10.1007/978-3-030-58583-9_26
10.1109/TIP.2020.3023597
10.1016/j.ins.2018.12.050
10.1109/ICCIA49625.2020.00028
10.1109/ICCVW.2019.00216
10.1145/3460426.3463643
10.1109/ICCV.2019.00718
10.1109/WACV.2014.6836044
10.1007/s11042-019-7404-z
10.1109/CVPR46437.2021.00411
10.3389/fnins.2016.00594
10.1109/CVPR.2015.7299152
10.1109/ICPR.2004.1334462
10.1109/ICCV.2019.00558
10.1109/ICACCI.2016.7732038
10.1007/978-3-030-01231-1_24
10.1016/j.patcog.2018.07.028
10.1007/978-3-642-25446-8_4
10.1109/JSEN.2019.2947446
10.1109/TIP.2021.3086590
10.1109/CVPR.2008.4587756
10.1007/978-3-030-20893-6_23
10.1109/CVPR.2016.333
10.1109/ICCV.2017.236
10.1109/TPAMI.2016.2533389
10.1109/AVSS.2019.8909840
10.1109/CVPR.2019.01230
10.1109/CVPR.2015.7298878
10.1109/CVPR.2019.01018
10.1109/CVPR42600.2020.01212
10.1109/ICPR.2014.604
10.1109/ICASSP.2016.7472168
10.1109/TIP.2020.2967577
10.1109/ICIP.2019.8802909
10.1109/TMM.2017.2749159
10.1007/978-3-030-58565-5_45
10.1109/ICCV.2019.00889
10.1109/CVPR.2015.7298714
10.1109/TPAMI.2018.2798607
10.1109/ACCESS.2017.2778011
10.1109/WACV.2017.24
10.1145/3314404
10.4108/icst.mobicase.2014.257786
10.1109/ICCVW.2019.00189
10.1109/CVPR46437.2021.01398
10.1109/TIP.2020.2965299
10.5244/C.24.97
10.1007/978-3-319-09396-3_9
10.1109/CVPR42600.2020.00022
10.1609/aaai.v33i01.33018561
10.1007/s11760-014-0677-9
10.1016/j.asoc.2017.09.027
10.1109/TMC.2018.2878233
10.1109/ICCV.2019.00631
10.24963/ijcai.2018/227
10.1145/3240508.3240675
10.1109/TPAMI.2016.2558148
10.1109/ICCVW.2017.77
10.1109/CVPR.2015.7299059
10.1145/2393347.2396381
10.1109/LSP.2018.2823910
10.1016/j.neucom.2016.05.094
10.1609/aaai.v33i01.33014683
10.1109/WACV.2017.27
10.1016/j.neucom.2020.05.118
10.1109/CVPR42600.2020.00119
10.1109/CVPR.2014.223
10.1109/JIOT.2020.2973272
10.1109/TIM.2021.3106101
10.1109/TPAMI.2017.2712608
10.1007/978-3-030-01231-1_39
10.1609/aaai.v30i1.10451
10.1109/WACV.2019.00199
10.1109/TPAMI.2019.2916873
10.1016/j.cviu.2017.10.011
10.1016/j.dsp.2019.01.013
10.1109/CVPR.2019.00804
10.1109/TPAMI.2019.2929038
10.3390/s20113305
10.1007/978-3-030-58539-6_17
10.1109/ICCV.2017.590
10.1109/CVPR.2011.5995316
10.1109/TPAMI.2017.2670560
10.1109/TPAMI.2017.2771306
10.1109/CBMI.2019.8877429
10.1109/JSEN.2018.2872849
10.1016/j.patcog.2020.107356
10.1109/CVPR.2018.00558
10.1109/ICCV.2019.00934
10.1109/IROS.2017.8206288
10.3390/rs11091068
10.1109/RADAR41533.2019.171243
10.1109/IROS45743.2020.9341699
10.1007/s11263-016-0982-6
10.1109/EMBC.2017.8037349
10.1109/ICCV.2017.115
10.1109/CVPRW.2012.6239233
10.1109/CVPR.2019.00132
10.1007/978-3-030-01234-2_21
10.3390/app7101101
10.1109/CVPR.2018.00572
10.1109/JSEN.2020.3028561
10.1109/IJCNN.2016.7727435
10.1109/ICCV.2011.6126543
10.1109/ICCV.2015.368
10.1109/CVPR.2017.502
10.1109/LSP.2018.2841649
10.1109/TCSVT.2020.3019293
10.1007/978-3-030-58558-7_31
10.1007/978-3-642-21257-4_36
10.1007/978-3-030-01216-8_43
10.1007/978-3-030-01246-5_7
10.1007/978-981-10-7895-8_32
10.1007/s10489-019-01603-4
10.1109/ICCA.2018.8444326
10.1109/CVPR42600.2020.00990
10.1016/j.infrared.2019.103014
10.1109/TMM.2018.2818329
10.1109/CVPR.2017.391
10.1016/j.patrec.2018.04.035
10.1109/CVPR.2015.7298708
10.23919/APSIPA.2018.8659539
10.1007/978-3-030-01225-0_18
10.1007/s11263-021-01531-2
10.1145/3338533.3366569
10.1109/CVPR.2017.604
10.1109/CVPR.2014.108
10.1109/TPAMI.2013.198
10.1109/TAES.2007.4441754
10.1117/12.2262719
10.1109/TMC.2020.3035045
10.1109/TVT.2016.2635161
10.1109/WACV.2017.30
10.1109/CVPR42600.2020.01047
10.1109/ICCV.2017.84
10.1109/WACV.2013.6474999
10.1007/978-3-030-01267-0_19
10.1109/TIP.2018.2812099
10.1109/WACV48630.2021.00278
10.1109/CVPR46437.2021.00078
10.1109/CVPRW.2017.44
10.1109/TPAMI.2015.2505295
10.1109/CVPR.2019.00034
10.1109/TMM.2018.2802648
10.1016/j.cviu.2013.01.013
10.1109/IJCNN48605.2020.9206681
10.1109/CVPR.2016.167
10.1109/WACV48630.2021.00381
10.1109/CVPR.2015.7299172
10.1109/TPAMI.2019.2901464
10.5555/3045118.3045336
10.1016/j.patcog.2019.107037
10.1109/TPAMI.2022.3157033
10.1109/CVPR.2018.00813
10.1109/CVPRW.2019.00217
10.1109/JSSC.2007.914337
10.1109/ISCAS45731.2020.9181247
10.1016/j.imavis.2021.104108
10.1109/JSEN.2019.2911204
10.1007/s11042-022-14075-5
10.14569/IJACSA.2019.0100311
10.2991/cnci-19.2019.95
10.1109/CVPR.2016.495
10.1109/CVPR.2018.00675
10.1109/CVPR.2014.339
10.1142/9789812833709_0030
10.1109/CVPR.2017.486
10.1109/IROS45743.2020.9341160
10.1109/CVPR.2016.115
10.1109/CVPR46437.2021.00471
10.1109/CVPR.2019.00033
10.1109/ICIP.2015.7350781
10.14722/ndss.2017.23023
10.1109/ICCV.2019.00756
10.1109/TIP.2017.2785279
10.1109/ICCV.2019.00630
10.1109/CVPR.2017.52
10.1016/j.patcog.2017.02.030
10.1109/CVPR.2019.00584
10.1109/CVPRW.2010.5543273
10.1109/ACPR.2017.136
10.1109/TCYB.2014.2347057
10.1109/CVPR42600.2020.00985
10.1109/TITS.2019.2935152
10.1109/LGRS.2015.2491329
10.1109/CVPR46437.2021.01103
10.1016/j.matpr.2020.09.052
10.1109/CVPR.2015.7298698
10.1109/CVPR.2017.781
10.1109/TIFS.2020.2985628
10.1016/j.patrec.2013.02.006
10.1109/CVPR42600.2020.00026
10.1109/CVPR.2018.00155
10.1109/CVPR.2017.387
10.1109/CVPR46437.2021.00748
10.1109/TVT.2018.2878754
10.1109/ICCV.2019.00096
10.1109/LSP.2017.2678539
10.1016/j.imavis.2009.11.014
10.1007/978-3-030-58577-8_2
10.1145/2393347.2396382
10.1109/34.910878
10.1109/WACV51458.2022.00073
10.1109/CVPRW.2019.00056
10.1109/CVPR.2010.5540234
10.1109/CVPR.2009.5206557
10.1109/CVPR.2016.297
10.1109/CVPR.2012.6247813
10.1109/TIP.2006.891352
10.1109/SIBGRAPI.2019.00011
10.1109/ICCV.2019.00289
10.1109/TPAMI.2017.2769085
10.1109/THMS.2015.2504550
10.1007/978-3-642-15567-3_11
10.1109/ISCAS.2008.4542023
10.1109/SIBGRAPI.2018.00019
10.1109/ICCV.2019.00559
10.1109/ICCV.2019.00272
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TPAMI.2022.3183112
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList
MEDLINE
MEDLINE - Academic
Technology Research Database
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 2160-9292
1939-3539
EndPage 3225
ExternalDocumentID 35700242
10_1109_TPAMI_2022_3183112
9795869
Genre orig-research
Research Support, Non-U.S. Gov't
Journal Article
Review
GrantInformation_xml – fundername: TAILOR
– fundername: SUTD SRG
– fundername: EU Horizon 2020 research and innovation programme
  grantid: 952215
– fundername: National Research Foundation, Singapore
  grantid: AISG-100E-2020-065
GroupedDBID ---
-DZ
-~X
.DC
0R~
29I
4.4
53G
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
UHB
~02
5VS
9M8
AAYOK
AAYXX
ABFSI
ADRHT
AETEA
AETIX
AGSQL
AI.
AIBXA
ALLEH
CITATION
FA8
H~9
IBMZZ
ICLAB
IFJZH
RIG
RNI
RZB
VH1
XJT
CGR
CUY
CVF
ECM
EIF
NPM
PKN
RIC
Z5M
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c3685-bda8d1b838251deb63b800a31967e9fae7d0c94fcb48f6e29b0dce00db2222d53
IEDL.DBID RIE
ISSN 0162-8828
1939-3539
IngestDate Fri Jul 11 10:13:15 EDT 2025
Sun Jun 29 16:00:02 EDT 2025
Wed Feb 19 02:23:57 EST 2025
Thu Apr 24 23:02:07 EDT 2025
Tue Jul 01 01:43:04 EDT 2025
Wed Aug 27 02:47:54 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3685-bda8d1b838251deb63b800a31967e9fae7d0c94fcb48f6e29b0dce00db2222d53
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-3
content type line 23
ObjectType-Review-1
ORCID 0000-0002-1816-1457
0000-0002-4365-4165
0000-0001-9998-3614
0000-0002-8568-2121
0000-0002-6603-3257
0000-0003-1920-0371
PMID 35700242
PQID 2773455306
PQPubID 85458
PageCount 26
ParticipantIDs crossref_primary_10_1109_TPAMI_2022_3183112
proquest_miscellaneous_2676926739
pubmed_primary_35700242
crossref_citationtrail_10_1109_TPAMI_2022_3183112
proquest_journals_2773455306
ieee_primary_9795869
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2023-03-01
PublicationDateYYYYMMDD 2023-03-01
PublicationDate_xml – month: 03
  year: 2023
  text: 2023-03-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev TPAMI
PublicationTitleAlternate IEEE Trans Pattern Anal Mach Intell
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref207
ref328
ref56
ref208
ref329
ref59
ref205
ref326
ref58
ref206
ref327
Korbar (ref369)
ref53
ref203
ref324
ref52
ref204
ref325
ref55
ref201
Qi (ref254)
ref322
ref54
ref202
ref323
Sung (ref388)
Shah (ref229)
ref209
Fan (ref247)
ref210
ref331
ref211
ref332
ref51
ref50
ref330
ref46
ref218
Trommel (ref281)
ref339
ref45
ref219
ref48
ref216
ref337
ref47
ref217
ref338
ref42
ref214
ref335
ref41
ref215
ref336
ref212
ref333
ref43
ref213
ref334
Feichtenhofer (ref113) 2016
ref49
Chung (ref92) 2014
ref100
ref221
ref342
ref101
ref222
ref343
ref40
ref340
ref220
ref341
ref35
ref306
ref34
ref307
ref37
ref304
ref425
ref36
ref305
ref31
ref302
ref423
ref30
ref303
ref424
ref33
ref300
ref421
ref32
ref301
ref422
ref39
ref38
ref308
ref309
Goyal (ref381)
ref310
ref24
ref317
ref23
Girdhar (ref81)
ref318
ref26
ref315
ref25
ref20
ref313
ref314
ref22
ref311
ref21
ref312
ref28
ref27
ref319
ref29
ref320
ref200
ref321
Wang (ref62) 2015
ref128
ref249
ref129
ref97
ref126
ref368
ref96
ref127
ref248
ref99
ref124
ref245
ref98
ref125
ref246
ref93
ref133
ref134
ref255
ref95
ref131
ref252
ref94
ref253
ref371
ref130
ref251
ref372
ref91
ref90
ref370
ref139
ref86
ref137
ref258
ref85
ref138
ref259
ref88
ref135
ref256
ref136
Gorban (ref379) 2015
ref82
ref144
ref265
ref386
ref145
ref387
ref84
ref263
ref83
ref143
ref264
ref385
ref140
ref261
ref382
ref141
ref262
ref383
ref80
ref380
ref260
ref79
ref108
ref109
ref106
ref227
ref348
ref107
ref228
ref75
ref104
ref225
ref346
ref74
ref105
ref226
ref347
ref77
ref223
ref344
ref76
ref103
ref224
ref345
ref71
ref111
ref232
ref353
ref70
ref112
ref233
ref73
Shi (ref349)
ref351
ref110
ref231
ref352
ref350
ref68
ref119
ref67
ref117
ref238
ref359
ref69
ref118
ref239
ref64
ref115
ref236
ref357
ref63
ref116
ref237
ref358
ref66
ref234
ref355
ref65
ref114
ref235
ref356
Diba (ref102) 2017
ref60
ref122
ref243
ref364
ref123
ref244
ref365
ref120
ref241
ref362
ref61
ref121
ref242
ref363
Zhang (ref142)
ref360
ref240
ref361
ref168
ref169
ref290
ref170
ref291
Carreira (ref376) 2018
ref298
ref178
ref299
ref175
ref296
ref176
ref297
ref173
ref294
ref174
ref295
ref171
ref292
ref172
ref293
ref179
Damen (ref378)
ref180
ref181
ref188
ref189
ref186
ref187
ref184
ref185
ref182
ref183
ref148
ref269
ref149
ref146
ref267
ref147
ref268
ref389
ref390
ref155
ref276
ref397
ref156
ref277
ref398
ref153
ref274
ref395
ref154
ref275
ref396
ref151
ref272
ref393
ref152
ref273
ref394
ref270
ref391
ref150
ref271
ref392
ref159
ref157
ref278
ref399
ref158
Yang (ref289) 2019
ref280
ref166
ref287
ref167
ref288
ref164
ref285
ref165
ref286
ref162
ref283
ref163
ref284
ref160
ref161
ref282
ref2
ref1
ref191
ref192
ref190
ref199
ref197
ref198
ref195
ref196
ref193
ref194
Baradel (ref316) 2017
Carreira (ref377) 2019
Ballas (ref87)
Alwassel (ref367) 2019
Berner (ref257)
Miech (ref413) 2020
ref8
ref7
ref9
ref4
ref3
ref6
ref5
Liu (ref177)
Stove (ref279)
Ghosh (ref12) 2019
Li (ref132)
Triantaphyllou (ref354) 1998; 15
Meglouli (ref230) 2019; 21
Soomro (ref374) 2012
Srivastava (ref72)
Wang (ref16) 2019
Xiao (ref266) 2020
Kay (ref375) 2017
Devlin (ref373) 2018
Huang (ref250) 2020
Dwibedi (ref89)
Ren (ref18) 2020
Müller (ref384) 2007
ref13
ref405
ref406
ref15
ref403
ref14
ref404
ref402
ref11
ref10
ref400
ref17
ref409
ref19
ref407
ref408
Simonyan (ref44)
ref416
ref417
ref414
ref415
ref412
ref410
ref411
ref418
ref419
ref420
Hinton (ref366)
Sharma (ref78) 2015
Abu-El-Haija (ref401) 2016
References_xml – ident: ref216
  doi: 10.1016/j.patrec.2009.11.017
– ident: ref313
  doi: 10.1109/ICCV.2017.316
– ident: ref91
  doi: 10.3115/v1/d14-1179
– ident: ref362
  doi: 10.1109/ICASSP.2019.8683606
– ident: ref226
  doi: 10.1109/ICCV.2015.304
– ident: ref219
  doi: 10.1109/CVPR.2013.98
– ident: ref59
  doi: 10.1109/CVPR.2016.291
– ident: ref124
  doi: 10.1109/WACV45572.2020.9093274
– ident: ref129
  doi: 10.1109/ICCV.2015.522
– ident: ref336
  doi: 10.1109/LSENS.2018.2878572
– ident: ref168
  doi: 10.1109/CVPRW.2017.207
– ident: ref135
  doi: 10.1109/CVPR42600.2020.00118
– ident: ref144
  doi: 10.1109/CVPR.2019.01232
– ident: ref51
  doi: 10.1109/CVPR.2017.337
– ident: ref145
  doi: 10.1007/978-3-319-46466-4_50
– year: 2018
  ident: ref373
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
– year: 2015
  ident: ref379
  article-title: THUMOS challenge: Action recognition with a large number of classes
– ident: ref191
  doi: 10.1007/978-3-030-58586-0_32
– year: 2017
  ident: ref316
  article-title: Pose-conditioned spatio-temporal attention for human action recognition
– year: 2019
  ident: ref289
  article-title: Action recognition using indoor radar systems
– volume: 15
  start-page: 175
  issue: 1998
  year: 1998
  ident: ref354
  article-title: Multi-criteria decision making: An operations research approach
  publication-title: Encyclopedia Elect. Electron. Eng.
– ident: ref125
  doi: 10.1109/CVPR.2019.00807
– ident: ref179
  doi: 10.1109/TPAMI.2019.2896631
– ident: ref215
  doi: 10.1109/CVPR.2004.1315191
– start-page: 568
  volume-title: Proc. 27th Int. Conf. Neural Informat. Process. Syst.
  ident: ref44
  article-title: Two-stream convolutional networks for action recognition in videos
– ident: ref301
  doi: 10.1007/s11390-011-9430-9
– ident: ref321
  doi: 10.1109/CVPR52688.2022.00298
– ident: ref66
  doi: 10.1109/ICCV.2015.510
– ident: ref183
  doi: 10.1145/3472722
– ident: ref356
  doi: 10.1109/TMM.2018.2875510
– start-page: C186
  volume-title: Proc. Symp. VLSI Circuits
  ident: ref257
  article-title: A 240 × 180 10mw 12us latency sparse-output vision sensor for mobile applications
– ident: ref127
  doi: 10.1109/CVPR42600.2020.00043
– ident: ref387
  doi: 10.1007/978-3-642-15552-9_29
– ident: ref194
  doi: 10.1609/aaai.v34i03.5652
– ident: ref208
  doi: 10.1109/ACPR.2015.7486569
– ident: ref268
  doi: 10.1016/j.procs.2014.07.009
– ident: ref409
  doi: 10.1109/ACCESS.2019.2923743
– ident: ref236
  doi: 10.1109/ICPR48806.2021.9412632
– ident: ref338
  doi: 10.3390/s19173680
– ident: ref317
  doi: 10.1109/ICME.2018.8486486
– ident: ref96
  doi: 10.1109/LSP.2016.2611485
– ident: ref211
  doi: 10.1109/ICME.2019.00187
– ident: ref73
  doi: 10.1007/s11263-021-01508-1
– start-page: 5843
  volume-title: Proc. IEEE/CVF Int. Conf. Comput. Vis.
  ident: ref381
  article-title: The “something something
– ident: ref50
  doi: 10.1007/978-3-319-46484-8_2
– ident: ref170
  doi: 10.1145/2964284.2967191
– ident: ref312
  doi: 10.1007/s11042-019-08576-z
– ident: ref358
  doi: 10.1109/WACV48630.2021.00280
– ident: ref324
  doi: 10.1109/TSMC.2018.2850149
– ident: ref110
  doi: 10.1109/CVPR.2018.00054
– ident: ref136
  doi: 10.1109/CVPR46437.2021.00193
– ident: ref74
  doi: 10.1016/j.neucom.2018.10.095
– ident: ref193
  doi: 10.1109/CVPR.2019.00371
– ident: ref143
  doi: 10.1007/978-3-030-58555-6_40
– ident: ref253
  doi: 10.1007/978-3-319-10605-2_48
– ident: ref350
  doi: 10.1109/TPAMI.2019.2898954
– ident: ref419
  doi: 10.1109/CVPR.2018.00871
– ident: ref84
  doi: 10.1007/s00521-020-05144-7
– ident: ref323
  doi: 10.1109/ICCV.2017.621
– ident: ref31
  doi: 10.1016/j.patcog.2015.09.028
– ident: ref305
  doi: 10.1109/FG47880.2020.00018
– ident: ref139
  doi: 10.1109/CVPR46437.2021.00332
– ident: ref393
  doi: 10.1016/j.bica.2013.05.008
– ident: ref280
  doi: 10.3390/s16121990
– ident: ref21
  doi: 10.1109/MCOM.2017.1700082
– ident: ref269
  doi: 10.1109/FUTURETECH.2010.5482729
– ident: ref399
  doi: 10.1016/j.sigpro.2014.08.038
– ident: ref417
  doi: 10.1109/CVPR42600.2020.01271
– ident: ref255
  doi: 10.1109/CVPR.2019.00319
– ident: ref119
  doi: 10.1109/CVPR42600.2020.00067
– ident: ref333
  doi: 10.1109/ACCESS.2020.3023599
– ident: ref40
  doi: 10.1109/CVPR.2012.6248093
– ident: ref368
  doi: 10.1109/ICCV.2017.73
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref247
  article-title: PSTNet: Point spatio-temporal convolution on point cloud sequences
– issue: CG-2007-2
  year: 2007
  ident: ref384
  article-title: Documentation mocap database HDM05
– ident: ref394
  doi: 10.1109/ICCV.2013.396
– ident: ref412
  doi: 10.1109/WACV48630.2021.00089
– ident: ref420
  doi: 10.1109/CVPR46437.2021.01302
– ident: ref48
  doi: 10.1007/s11263-013-0636-x
– ident: ref187
  doi: 10.1109/CVPR.2019.00810
– ident: ref58
  doi: 10.1609/aaai.v32i1.12228
– ident: ref128
  doi: 10.1109/CVPR46437.2021.00470
– ident: ref123
  doi: 10.1109/TPAMI.2017.2691768
– ident: ref235
  doi: 10.1007/s12652-019-01239-9
– ident: ref228
  doi: 10.1109/AVSS.2017.8078497
– ident: ref271
  doi: 10.1109/SMC.2015.263
– ident: ref335
  doi: 10.1016/j.inffus.2022.03.001
– ident: ref397
  doi: 10.1016/j.jvcir.2013.03.008
– ident: ref421
  doi: 10.1145/3386252
– ident: ref318
  doi: 10.1109/ICCV.2019.00092
– ident: ref365
  doi: 10.1109/WACV45572.2020.9093307
– ident: ref67
  doi: 10.1109/ICCV.2017.402
– ident: ref252
  doi: 10.1109/ICPR48806.2021.9412991
– ident: ref299
  doi: 10.1109/ICCV.2019.00875
– start-page: 149
  volume-title: Proc. 1st Eur. Radar Conf.
  ident: ref279
  article-title: Modern FMCW radar-techniques and applications
– ident: ref43
  doi: 10.1109/CVPR.2011.5995407
– ident: ref357
  doi: 10.1007/978-3-030-01237-3_7
– ident: ref28
  doi: 10.1145/3132734.3132739
– ident: ref243
  doi: 10.1109/CVPR42600.2020.00580
– ident: ref202
  doi: 10.1609/aaai.v33i01.33018989
– ident: ref343
  doi: 10.3390/s16010115
– ident: ref53
  doi: 10.1109/CVPR.2017.787
– ident: ref224
  doi: 10.1007/978-3-319-46604-0_47
– ident: ref42
  doi: 10.1007/s11263-005-1838-7
– ident: ref71
  doi: 10.1109/CVPR.2015.7299101
– ident: ref392
  doi: 10.1177/0278364913478446
– ident: ref395
  doi: 10.1007/s11263-012-0550-7
– ident: ref363
  doi: 10.1109/ICIP.2017.8296630
– ident: ref416
  doi: 10.1109/CVPR46437.2021.01600
– ident: ref126
  doi: 10.1109/CVPR.2019.00136
– start-page: 1
  volume-title: Proc. NeurIPS Deep Learn. Representation Learn. Workshop
  ident: ref366
  article-title: Distilling the knowledge in a neural network
– ident: ref34
  doi: 10.1145/1964897.1964918
– ident: ref165
  doi: 10.1609/aaai.v31i1.11212
– ident: ref189
  doi: 10.1109/TNNLS.2019.2935173
– year: 2014
  ident: ref92
  article-title: Empirical evaluation of gated recurrent neural networks on sequence modeling
– ident: ref341
  doi: 10.1007/s11042-021-11058-w
– ident: ref195
  doi: 10.1109/CVPR42600.2020.01434
– ident: ref287
  doi: 10.1007/978-981-15-4163-6_3
– ident: ref56
  doi: 10.1109/ICCVW.2017.123
– ident: ref320
  doi: 10.1007/978-3-030-58545-7_5
– ident: ref181
  doi: 10.1109/ICMEW.2017.8026282
– ident: ref355
  doi: 10.1109/TCYB.2017.2682280
– ident: ref180
  doi: 10.1109/LSP.2017.2690339
– ident: ref162
  doi: 10.1007/978-3-319-46487-9_50
– ident: ref29
  doi: 10.1109/ICCVW.2011.6130379
– ident: ref70
  doi: 10.1007/978-3-030-58571-6_6
– ident: ref400
  doi: 10.1007/978-3-319-46448-0_31
– ident: ref383
  doi: 10.1016/j.cviu.2006.07.013
– ident: ref425
  doi: 10.1109/CVPR46437.2021.00966
– ident: ref35
  doi: 10.1145/2789168.2790093
– ident: ref293
  doi: 10.1109/JSAC.2017.2679658
– start-page: 10
  volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops
  ident: ref177
  article-title: Skepxels: Spatio-temporal image representation of human skeleton joints for action recognition
– ident: ref83
  doi: 10.1109/CVPR.2019.00137
– volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref142
  article-title: V4D: 4D convolutional neural networks for video-level representation learning
– ident: ref342
  doi: 10.1145/2733373.2806333
– ident: ref103
  doi: 10.1109/CVPR.2017.243
– ident: ref206
  doi: 10.1109/ICCV.2017.233
– year: 2017
  ident: ref375
  article-title: The kinetics human action video dataset
– ident: ref80
  doi: 10.1109/CVPR.2019.01019
– year: 2019
  ident: ref16
  article-title: Temporal unet: Sample level human action recognition using WiFi
– ident: ref298
  doi: 10.1109/TVT.2017.2737553
– ident: ref147
  doi: 10.1109/CVPR42600.2020.00028
– ident: ref325
  doi: 10.3390/app9040716
– ident: ref159
  doi: 10.1109/ICCV.2015.460
– ident: ref90
  doi: 10.1016/j.patcog.2017.10.037
– ident: ref418
  doi: 10.1007/978-3-030-58621-8_25
– ident: ref227
  doi: 10.1016/j.cogsys.2018.04.002
– year: 2019
  ident: ref377
  article-title: A short note on the kinetics-700 human action dataset
– ident: ref11
  doi: 10.1109/CVPR42600.2020.00059
– ident: ref262
  doi: 10.1145/3242587.3242609
– ident: ref270
  doi: 10.1109/BSN.2006.6
– ident: ref295
  doi: 10.1109/MSN48538.2019.00026
– ident: ref93
  doi: 10.1145/2733373.2806222
– ident: ref263
  doi: 10.1109/ICASSP.2017.7952132
– ident: ref205
  doi: 10.1109/TPAMI.2021.3053765
– ident: ref424
  doi: 10.1109/CVPR46437.2021.01025
– ident: ref284
  doi: 10.1109/RADAR41533.2019.171307
– ident: ref173
  doi: 10.1109/CVPR.2017.113
– ident: ref65
  doi: 10.1109/CVPR.2016.213
– year: 2020
  ident: ref18
  article-title: A survey on 3D skeleton-based action recognition using learning method
– ident: ref154
  doi: 10.1109/CVPR.2014.82
– ident: ref389
  doi: 10.1007/978-3-642-33868-7_6
– ident: ref292
  doi: 10.1145/2639108.2639143
– year: 2017
  ident: ref102
  article-title: Temporal 3D convnets: New architecture and transfer learning for video classification
– ident: ref222
  doi: 10.1007/s11042-022-12091-z
– ident: ref140
  doi: 10.1109/CVPR46437.2021.00887
– ident: ref174
  doi: 10.24963/ijcai.2018/109
– ident: ref283
  doi: 10.1109/COMPEM.2018.8496654
– year: 2012
  ident: ref374
  article-title: UCF101: A dataset of 101 human actions classes from videos in the wild
– ident: ref17
  doi: 10.1145/1922649.1922653
– ident: ref277
  doi: 10.3390/s19071644
– ident: ref169
  doi: 10.1109/TCSVT.2016.2628339
– year: 2020
  ident: ref413
  article-title: RareAct: A video dataset of unusual interactions
– ident: ref331
  doi: 10.1145/2671188.2749340
– ident: ref52
  doi: 10.1109/CVPR.2017.168
– ident: ref148
  doi: 10.1007/978-3-030-68238-5_48
– volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops
  ident: ref89
  article-title: Temporal reasoning in videos using convolutional gated recurrent units
– ident: ref137
  doi: 10.1109/CVPR46437.2021.01301
– ident: ref214
  doi: 10.1109/TCSVT.2018.2808682
– ident: ref327
  doi: 10.1109/TPAMI.2017.2691321
– ident: ref41
  doi: 10.1109/TPAMI.2007.70711
– ident: ref402
  doi: 10.1109/CVPR.2018.00633
– volume: 21
  start-page: 43
  issue: 4
  year: 2019
  ident: ref230
  article-title: A new technique based on 3D convolutional neural networks and filtering optical flow maps for action classification in infrared video
  publication-title: Control Eng. Appl. Inf.
– ident: ref185
  doi: 10.1109/DSW.2018.8439897
– ident: ref99
  doi: 10.1109/TPAMI.2012.59
– ident: ref122
  doi: 10.1007/s11263-021-01467-7
– ident: ref152
  doi: 10.1609/aaai.v32i1.12328
– ident: ref97
  doi: 10.1007/978-3-030-58583-9_26
– ident: ref261
  doi: 10.1109/TIP.2020.3023597
– ident: ref57
  doi: 10.1016/j.ins.2018.12.050
– ident: ref77
  doi: 10.1109/ICCIA49625.2020.00028
– ident: ref197
  doi: 10.1109/ICCVW.2019.00216
– ident: ref422
  doi: 10.1145/3460426.3463643
– ident: ref134
  doi: 10.1109/ICCV.2019.00718
– ident: ref351
  doi: 10.1109/WACV.2014.6836044
– ident: ref79
  doi: 10.1007/s11042-019-7404-z
– ident: ref121
  doi: 10.1109/CVPR46437.2021.00411
– ident: ref259
  doi: 10.3389/fnins.2016.00594
– ident: ref225
  doi: 10.1109/CVPR.2015.7299152
– ident: ref382
  doi: 10.1109/ICPR.2004.1334462
– ident: ref117
  doi: 10.1109/ICCV.2019.00558
– ident: ref307
  doi: 10.1109/ICACCI.2016.7732038
– ident: ref361
  doi: 10.1007/978-3-030-01231-1_24
– year: 2016
  ident: ref401
  article-title: YouTube-8M: A large-scale video classification benchmark
– ident: ref133
  doi: 10.1016/j.patcog.2018.07.028
– ident: ref95
  doi: 10.1007/978-3-642-25446-8_4
– ident: ref339
  doi: 10.1109/JSEN.2019.2947446
– start-page: 81
  volume-title: Proc. Eur. Radar Conf.
  ident: ref281
  article-title: Multi-target human gait classification using deep convolutional neural networks on micro-doppler spectrograms
– start-page: 5105
  volume-title: Proc. 27th Int. Conf. Neural Informat. Process. Syst.
  ident: ref254
  article-title: PointNet++: Deep hierarchical feature learning on point sets in a metric space
– year: 2015
  ident: ref62
  article-title: Towards good practices for very deep two-stream convnets
– ident: ref364
  doi: 10.1109/TIP.2021.3086590
– ident: ref385
  doi: 10.1109/CVPR.2008.4587756
– ident: ref111
  doi: 10.1007/978-3-030-20893-6_23
– ident: ref24
  doi: 10.1109/CVPR.2016.333
– ident: ref68
  doi: 10.1109/ICCV.2017.236
– ident: ref239
  doi: 10.1109/TPAMI.2016.2533389
– ident: ref175
  doi: 10.1109/AVSS.2019.8909840
– ident: ref196
  doi: 10.1109/CVPR.2019.01230
– ident: ref7
  doi: 10.1109/CVPR.2015.7298878
– ident: ref61
  doi: 10.1109/CVPR.2019.01018
– ident: ref120
  doi: 10.1109/CVPR42600.2020.01212
– ident: ref398
  doi: 10.1109/ICPR.2014.604
– ident: ref4
  doi: 10.1109/ICASSP.2016.7472168
– ident: ref26
  doi: 10.1109/TIP.2020.2967577
– ident: ref360
  doi: 10.1109/ICIP.2019.8802909
– ident: ref98
  doi: 10.1109/TMM.2017.2749159
– ident: ref190
  doi: 10.1007/978-3-030-58565-5_45
– year: 2019
  ident: ref12
  article-title: Spatiotemporal filtering for event-based action recognition
– ident: ref64
  doi: 10.1109/ICCV.2019.00889
– ident: ref155
  doi: 10.1109/CVPR.2015.7298714
– ident: ref306
  doi: 10.1109/TPAMI.2018.2798607
– ident: ref75
  doi: 10.1109/ACCESS.2017.2778011
– ident: ref156
  doi: 10.1109/WACV.2017.24
– ident: ref13
  doi: 10.1145/3314404
– ident: ref14
  doi: 10.4108/icst.mobicase.2014.257786
– ident: ref82
  doi: 10.1109/ICCVW.2019.00189
– ident: ref246
  doi: 10.1109/CVPR46437.2021.01398
– ident: ref310
  doi: 10.1109/TIP.2020.2965299
– ident: ref38
  doi: 10.5244/C.24.97
– ident: ref36
  doi: 10.1007/978-3-319-09396-3_9
– ident: ref199
  doi: 10.1109/CVPR42600.2020.00022
– ident: ref198
  doi: 10.1609/aaai.v33i01.33018561
– ident: ref232
  doi: 10.1007/s11760-014-0677-9
– volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref132
  article-title: CT-net: Channel tensorization network for video classification
– ident: ref273
  doi: 10.1016/j.asoc.2017.09.027
– ident: ref297
  doi: 10.1109/TMC.2018.2878233
– ident: ref309
  doi: 10.1109/ICCV.2019.00631
– ident: ref207
  doi: 10.24963/ijcai.2018/227
– start-page: 33
  volume-title: Proc. 27th Int. Conf. Neural Informat. Process. Syst.
  ident: ref81
  article-title: Attentional pooling for action recognition
– ident: ref405
  doi: 10.1145/3240508.3240675
– ident: ref55
  doi: 10.1109/TPAMI.2016.2558148
– ident: ref314
  doi: 10.1109/ICCVW.2017.77
– ident: ref47
  doi: 10.1109/CVPR.2015.7299059
– ident: ref390
  doi: 10.1145/2393347.2396381
– ident: ref231
  doi: 10.1109/LSP.2018.2823910
– ident: ref30
  doi: 10.1016/j.neucom.2016.05.094
– ident: ref146
  doi: 10.1609/aaai.v33i01.33014683
– ident: ref94
  doi: 10.1109/WACV.2017.27
– ident: ref76
  doi: 10.1016/j.neucom.2020.05.118
– ident: ref200
  doi: 10.1109/CVPR42600.2020.00119
– ident: ref45
  doi: 10.1109/CVPR.2014.223
– ident: ref296
  doi: 10.1109/JIOT.2020.2973272
– ident: ref244
  doi: 10.1109/TIM.2021.3106101
– ident: ref105
  doi: 10.1109/TPAMI.2017.2712608
– ident: ref264
  doi: 10.1007/978-3-030-01231-1_39
– start-page: 843
  volume-title: Proc. 32nd Int. Conf. Int. Conf. Mach. Learn.
  ident: ref72
  article-title: Unsupervised learning of video representations using LSTMs
– ident: ref160
  doi: 10.1609/aaai.v30i1.10451
– ident: ref249
  doi: 10.1109/WACV.2019.00199
– ident: ref151
  doi: 10.1109/TPAMI.2019.2916873
– ident: ref85
  doi: 10.1016/j.cviu.2017.10.011
– ident: ref288
  doi: 10.1016/j.dsp.2019.01.013
– ident: ref69
  doi: 10.1109/CVPR.2019.00804
– ident: ref359
  doi: 10.1109/TPAMI.2019.2929038
– start-page: 249
  volume-title: Proc. Opt. Photon. Informat. Process. XII
  ident: ref229
  article-title: A spatio-temporal deep learning approach for human action recognition in infrared videos
– ident: ref311
  doi: 10.3390/s20113305
– ident: ref101
  doi: 10.1007/978-3-030-58539-6_17
– ident: ref130
  doi: 10.1109/ICCV.2017.590
– ident: ref5
  doi: 10.1109/CVPR.2011.5995316
– ident: ref403
  doi: 10.1109/TPAMI.2017.2670560
– ident: ref8
  doi: 10.1109/TPAMI.2017.2771306
– ident: ref407
  doi: 10.1109/CBMI.2019.8877429
– ident: ref285
  doi: 10.1109/JSEN.2018.2872849
– ident: ref319
  doi: 10.1016/j.patcog.2020.107356
– ident: ref188
  doi: 10.1109/CVPR.2018.00558
– ident: ref242
  doi: 10.1109/ICCV.2019.00934
– ident: ref315
  doi: 10.1109/IROS.2017.8206288
– ident: ref22
  doi: 10.3390/rs11091068
– ident: ref286
  doi: 10.1109/RADAR41533.2019.171243
– ident: ref345
  doi: 10.1109/IROS45743.2020.9341699
– ident: ref347
  doi: 10.1007/s11263-016-0982-6
– ident: ref272
  doi: 10.1109/EMBC.2017.8037349
– ident: ref166
  doi: 10.1109/ICCV.2017.115
– ident: ref391
  doi: 10.1109/CVPRW.2012.6239233
– ident: ref201
  doi: 10.1109/CVPR.2019.00132
– ident: ref328
  doi: 10.1007/978-3-030-01234-2_21
– ident: ref404
  doi: 10.3390/app7101101
– ident: ref167
  doi: 10.1109/CVPR.2018.00572
– start-page: 47
  volume-title: Proc. AAAI Conf. Artif. Intell.
  ident: ref388
  article-title: Human activity detection from RGBD images
– ident: ref340
  doi: 10.1109/JSEN.2020.3028561
– ident: ref334
  doi: 10.1109/IJCNN.2016.7727435
– ident: ref27
  doi: 10.1109/ICCV.2011.6126543
– ident: ref49
  doi: 10.1109/ICCV.2015.368
– ident: ref108
  doi: 10.1109/CVPR.2017.502
– ident: ref210
  doi: 10.1109/LSP.2018.2841649
– ident: ref212
  doi: 10.1109/TCSVT.2020.3019293
– ident: ref100
  doi: 10.1007/978-3-030-58558-7_31
– year: 2020
  ident: ref266
  article-title: Audiovisual slowfast networks for video recognition
– ident: ref267
  doi: 10.1007/978-3-642-21257-4_36
– ident: ref115
  doi: 10.1007/978-3-030-01216-8_43
– ident: ref186
  doi: 10.1007/978-3-030-01246-5_7
– ident: ref330
  doi: 10.1007/978-981-10-7895-8_32
– start-page: 7774
  volume-title: Proc. 27th Int. Conf. Neural Informat. Process. Syst.
  ident: ref369
  article-title: Cooperative learning of audio and video models from self-supervised synchronization
– ident: ref2
  doi: 10.1007/s10489-019-01603-4
– year: 2015
  ident: ref78
  article-title: Action recognition using visual attention
– ident: ref337
  doi: 10.1109/ICCA.2018.8444326
– ident: ref371
  doi: 10.1109/CVPR42600.2020.00990
– ident: ref234
  doi: 10.1016/j.infrared.2019.103014
– ident: ref217
  doi: 10.1109/TMM.2018.2818329
– ident: ref163
  doi: 10.1109/CVPR.2017.391
– ident: ref329
  doi: 10.1016/j.patrec.2018.04.035
– ident: ref346
  doi: 10.1109/CVPR.2015.7298708
– ident: ref332
  doi: 10.23919/APSIPA.2018.8659539
– ident: ref104
  doi: 10.1007/978-3-030-01225-0_18
– ident: ref410
  doi: 10.1007/s11263-021-01531-2
– ident: ref182
  doi: 10.1145/3338533.3366569
– ident: ref63
  doi: 10.1109/CVPR.2017.604
– ident: ref218
  doi: 10.1109/CVPR.2014.108
– ident: ref153
  doi: 10.1109/TPAMI.2013.198
– ident: ref278
  doi: 10.1109/TAES.2007.4441754
– ident: ref282
  doi: 10.1117/12.2262719
– ident: ref304
  doi: 10.1109/TMC.2020.3035045
– ident: ref294
  doi: 10.1109/TVT.2016.2635161
– ident: ref233
  doi: 10.1109/WACV.2017.30
– ident: ref265
  doi: 10.1109/CVPR42600.2020.01047
– ident: ref88
  doi: 10.1109/ICCV.2017.84
– year: 2016
  ident: ref113
  article-title: Spatiotemporal residual networks for video action recognition
– ident: ref33
  doi: 10.1109/WACV.2013.6474999
– ident: ref131
  doi: 10.1007/978-3-030-01267-0_19
– ident: ref209
  doi: 10.1109/TIP.2018.2812099
– ident: ref322
  doi: 10.1109/WACV48630.2021.00278
– ident: ref414
  doi: 10.1109/CVPR46437.2021.00078
– ident: ref10
  doi: 10.1109/CVPRW.2017.44
– year: 2020
  ident: ref250
  article-title: Event-based action recognition using timestamp image encoding network
– start-page: 802
  volume-title: Proc. 27th Int. Conf. Neural Informat. Process. Syst.
  ident: ref349
  article-title: Convolutional LSTM network: A machine learning approach for precipitation nowcasting
– ident: ref352
  doi: 10.1109/TPAMI.2015.2505295
– ident: ref106
  doi: 10.1109/CVPR.2019.00034
– ident: ref157
  doi: 10.1109/TMM.2018.2802648
– ident: ref37
  doi: 10.1016/j.cviu.2013.01.013
– ident: ref260
  doi: 10.1109/IJCNN48605.2020.9206681
– ident: ref9
  doi: 10.1109/CVPR.2016.167
– ident: ref245
  doi: 10.1109/WACV48630.2021.00381
– ident: ref353
  doi: 10.1109/CVPR.2015.7299172
– ident: ref408
  doi: 10.1109/TPAMI.2019.2901464
– ident: ref86
  doi: 10.5555/3045118.3045336
– ident: ref114
  doi: 10.1016/j.patcog.2019.107037
– ident: ref204
  doi: 10.1109/TPAMI.2022.3157033
– ident: ref107
  doi: 10.1109/CVPR.2018.00813
– ident: ref32
  doi: 10.1109/CVPRW.2019.00217
– ident: ref256
  doi: 10.1109/JSSC.2007.914337
– ident: ref251
  doi: 10.1109/ISCAS45731.2020.9181247
– ident: ref54
  doi: 10.1016/j.imavis.2021.104108
– ident: ref275
  doi: 10.1109/JSEN.2019.2911204
– ident: ref223
  doi: 10.1007/s11042-022-14075-5
– ident: ref20
  doi: 10.14569/IJACSA.2019.0100311
– ident: ref274
  doi: 10.2991/cnci-19.2019.95
– ident: ref423
  doi: 10.1109/CVPR.2016.495
– ident: ref109
  doi: 10.1109/CVPR.2018.00675
– ident: ref238
  doi: 10.1109/CVPR.2014.339
– ident: ref276
  doi: 10.1142/9789812833709_0030
– ident: ref172
  doi: 10.1109/CVPR.2017.486
– ident: ref411
  doi: 10.1109/IROS45743.2020.9341160
– ident: ref161
  doi: 10.1109/CVPR.2016.115
– year: 2019
  ident: ref367
  article-title: Self-supervised learning by cross-modal audio-video clustering
– ident: ref213
  doi: 10.1109/CVPR46437.2021.00471
– ident: ref141
  doi: 10.1109/CVPR.2019.00033
– ident: ref300
  doi: 10.1109/ICIP.2015.7350781
– ident: ref303
  doi: 10.14722/ndss.2017.23023
– ident: ref372
  doi: 10.1109/ICCV.2019.00756
– ident: ref158
  doi: 10.1109/TIP.2017.2785279
– ident: ref112
  doi: 10.1109/ICCV.2019.00630
– ident: ref308
  doi: 10.1109/CVPR.2017.52
– ident: ref178
  doi: 10.1016/j.patcog.2017.02.030
– ident: ref150
  doi: 10.1109/CVPR.2019.00584
– ident: ref240
  doi: 10.1109/CVPRW.2010.5543273
– ident: ref258
  doi: 10.1109/ACPR.2017.136
– ident: ref396
  doi: 10.1109/TCYB.2014.2347057
– ident: ref118
  doi: 10.1109/CVPR42600.2020.00985
– ident: ref184
  doi: 10.1109/TITS.2019.2935152
– ident: ref15
  doi: 10.1109/LGRS.2015.2491329
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref87
  article-title: Delving deeper into convolutional networks for learning video representations
– ident: ref415
  doi: 10.1109/CVPR46437.2021.01103
– ident: ref326
  doi: 10.1016/j.matpr.2020.09.052
– ident: ref380
  doi: 10.1109/CVPR.2015.7298698
– ident: ref241
  doi: 10.1109/CVPR.2017.781
– ident: ref344
  doi: 10.1109/TIFS.2020.2985628
– ident: ref19
  doi: 10.1016/j.patrec.2013.02.006
– ident: ref203
  doi: 10.1109/CVPR42600.2020.00026
– ident: ref116
  doi: 10.1109/CVPR.2018.00155
– ident: ref164
  doi: 10.1109/CVPR.2017.387
– ident: ref149
  doi: 10.1109/CVPR46437.2021.00748
– ident: ref291
  doi: 10.1109/TVT.2018.2878754
– ident: ref302
  doi: 10.1109/ICCV.2019.00096
– ident: ref171
  doi: 10.1109/LSP.2017.2678539
– ident: ref6
  doi: 10.1016/j.imavis.2009.11.014
– ident: ref192
  doi: 10.1007/978-3-030-58577-8_2
– ident: ref220
  doi: 10.1145/2393347.2396382
– ident: ref348
  doi: 10.1109/34.910878
– ident: ref248
  doi: 10.1109/WACV51458.2022.00073
– ident: ref290
  doi: 10.1109/CVPRW.2019.00056
– ident: ref39
  doi: 10.1109/CVPR.2010.5540234
– ident: ref386
  doi: 10.1109/CVPR.2009.5206557
– ident: ref60
  doi: 10.1109/CVPR.2016.297
– ident: ref237
  doi: 10.1109/CVPR.2012.6247813
– ident: ref3
  doi: 10.1109/TIP.2006.891352
– ident: ref176
  doi: 10.1109/SIBGRAPI.2019.00011
– ident: ref406
  doi: 10.1109/ICCV.2019.00289
– start-page: 753
  volume-title: Proc. Eur. Conf. Comput. Vis.
  ident: ref378
  article-title: Scaling egocentric vision: The epic-kitchens dataset
– ident: ref46
  doi: 10.1109/TPAMI.2017.2769085
– ident: ref221
  doi: 10.1109/THMS.2015.2504550
– ident: ref138
  doi: 10.1007/978-3-642-15567-3_11
– ident: ref1
  doi: 10.1109/ISCAS.2008.4542023
– ident: ref23
  doi: 10.1109/SIBGRAPI.2018.00019
– ident: ref25
  doi: 10.1109/ICCV.2019.00559
– ident: ref370
  doi: 10.1109/ICCV.2019.00272
– year: 2018
  ident: ref376
  article-title: A short note about kinetics-600
SSID ssj0014503
Score 2.7378032
SecondaryResourceType review_article
Snippet Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 3200
SubjectTerms Acceleration
Algorithms
Computer vision
data modality
Deep learning
Feature extraction
Human action recognition
Human Activities
Human activity recognition
Human motion
Humans
Machine learning
multi-modality
Optical imaging
Pattern Recognition, Automated - methods
Radar
single modality
Skeleton
Teaching methods
Three-dimensional displays
Visualization
Title Human Action Recognition From Various Data Modalities: A Review
URI https://ieeexplore.ieee.org/document/9795869
https://www.ncbi.nlm.nih.gov/pubmed/35700242
https://www.proquest.com/docview/2773455306
https://www.proquest.com/docview/2676926739
Volume 45
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1JS8QwFH6MHkQP7su4EcGbdmzTbeJFBnUYhRERFW8laZKLOhWdufjrfS9dUFHxUgJN0_Yt7ffyNoD91OdS2iDxrEQ24FdSeSpNjOe6PMTWkjeKoi2uksFddPkQP7TgsMmFMca44DPToaHz5esin9BW2ZFIRdxNxBRMoZiVuVqNxyCKXRdkRDCo4WhG1Akyvji6ve4NL9AU5LxDEowIYxZmQirsziP-5X_kGqz8jjXdP6e_AMP6actQk8fOZKw6-fu3Qo7_fZ1FmK_AJ-uV0rIELTNahoW6sQOr9HwZ5j5VKVyBE7fRz3ouA4Ld1BFHOO6_Fs_sHq3tYvLGzuRYsmGhCdij-X3Meqx0PKzCXf_89nTgVX0XvJzK0XtKy64OVDektFZtVBIqhJWSlDU1wkqTaj8Xkc1V1LWJ4UL5Oje-rxWCDa7jcA2mR8XIbABz5fODWCMMslFgYmGtRMSEuCdOVR7yNgQ19bO8KkpOvTGeMmec-CJzzMuIeVnFvDYcNNe8lCU5_py9QpRvZlZEb8N2zeSs0tq3jKdpGFEfpaQNe81p1DdyosiRQWJmnGKC8RDiEuulcDRr1zK1-fM9t2CWmtWXEWzbMD1-nZgdhDRjtetk-QMbK-yG
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB6VRSrlQF9QFtriSr1BtokTJ2suaAVdbWm3qtAW9WbZsX2BbtB298KvZ8Z5qEWAuESW4rzmEX_jeQEcFzHX2id55DWyAf-SJjJF7qLQ5UF4T94oira4zCfX2ecbcbMG77pcGOdcCD5zAxoGX76tyhVtlZ3IQophLh_BY1z3M1Fna3U-g0yEPsiIYVDH0ZBoU2RieTK7Gk3P0BjkfEAyjBhjA9ZTKu3OM_5gRQotVv6ONsOqM96Eafu-dbDJt8FqaQblz99KOf7vB23BswZ-slEtL9uw5uY7sNm2dmCNpu_A03t1CnfhQ9jqZ6OQA8G-tDFHOB4vqlv2Fe3tanXHPumlZtPKErRHA_w9G7Ha9fAcrsens4-TqOm8EJVUkD4yVg9tYoYpJbZaZ_LUILDUpK6Fk167wsalzHxpsqHPHZcmtqWLY2sQbnAr0hfQm1dz9xJYKKCfCItAyGeJE9J7jZgJkY8oTJnyPiQt9VXZlCWn7hjfVTBPYqkC8xQxTzXM68Pb7pofdVGOf87eJcp3Mxui92G_ZbJq9PZO8aJIM-qklPfhqDuNGkduFD13SEzFKSoYDyneYq8Wju7erUy9-vMz38CTyWx6oS7OLs9fwwa1rq_j2faht1ys3AECnKU5DHL9C6g879M
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=Human+Action+Recognition+From+Various+Data+Modalities%3A+A+Review&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Sun%2C+Zehua&rft.au=Ke%2C+Qiuhong&rft.au=Rahmani%2C+Hossein&rft.au=Bennamoun%2C+Mohammed&rft.date=2023-03-01&rft.issn=0162-8828&rft.eissn=2160-9292&rft.spage=1&rft.epage=20&rft_id=info:doi/10.1109%2FTPAMI.2022.3183112&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPAMI_2022_3183112
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon