A Review of Human Activity Recognition Methods

Recognizing human activities from video sequences or still images is a challenging task due to problems such as background clutter, partial occlusion, changes in scale, viewpoint, lighting, and appearance. Many applications, including video surveillance systems, human-computer interaction, and robot...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in robotics and AI Vol. 2
Main Authors: Vrigkas, Michalis, Nikou, Christophoros, Kakadiaris, Ioannis A.
Format: Journal Article
Language:English
Published: Frontiers Media S.A 16.11.2015
Subjects:
Action recognition
action representation
Activity Categorization
Human activity recognition
review
Survey
ISSN:2296-9144, 2296-9144
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Recognizing human activities from video sequences or still images is a challenging task due to problems such as background clutter, partial occlusion, changes in scale, viewpoint, lighting, and appearance. Many applications, including video surveillance systems, human-computer interaction, and robotics for human behavior characterization, require a multiple activity recognition system. In this work, we provide a detailed review of recent and state-of-the-art research advances in the field of human activity classification. We propose a categorization of human activity methodologies and discuss their advantages and limitations. In particular, we divide human activity classification methods into two large categories according to whether they use data from different modalities or not. Then, each of these categories is further analyzed into sub-categories, which reflect how they model human activities and what type of activities they are interested in. Moreover, we provide a comprehensive analysis of the existing, publicly available human activity classification datasets and examine the requirements for an ideal human activity recognition dataset. Finally, we report the characteristics of future research directions and present some open issues on human activity recognition.
AbstractList Recognizing human activities from video sequences or still images is a challenging task due to problems such as background clutter, partial occlusion, changes in scale, viewpoint, lighting, and appearance. Many applications, including video surveillance systems, human-computer interaction, and robotics for human behavior characterization, require a multiple activity recognition system. In this work, we provide a detailed review of recent and state-of-the-art research advances in the field of human activity classification. We propose a categorization of human activity methodologies and discuss their advantages and limitations. In particular, we divide human activity classification methods into two large categories according to whether they use data from different modalities or not. Then, each of these categories is further analyzed into sub-categories, which reflect how they model human activities and what type of activities they are interested in. Moreover, we provide a comprehensive analysis of the existing, publicly available human activity classification datasets and examine the requirements for an ideal human activity recognition dataset. Finally, we report the characteristics of future research directions and present some open issues on human activity recognition.
Author Nikou, Christophoros
Vrigkas, Michalis
Kakadiaris, Ioannis A.
Author_xml – sequence: 1
  givenname: Michalis
  surname: Vrigkas
  fullname: Vrigkas, Michalis
– sequence: 2
  givenname: Christophoros
  surname: Nikou
  fullname: Nikou, Christophoros
– sequence: 3
  givenname: Ioannis A.
  surname: Kakadiaris
  fullname: Kakadiaris, Ioannis A.
BookMark eNp1kFtLAzEQhYMoWGvffdw_sGtum2QfS1FbqAiizyGX2ZrSbiQbK_33blsREXyaYc6cc-C7Qudd7AChG4IrxlRz26Zoc0UxqSuMMVVnaERpI8qGcH7-a79Ek75fDy-kVpxJOULVtHiGXYDPIrbF_GNrumLqctiFvB8EF1ddyCF2xSPkt-j7a3TRmk0Pk-85Rq_3dy-zebl8eljMpsvScSJzSa00tpWW29pzyaxnjAmgjZLKYvCOUau48ISBM95xSg2vubKSKQGi4YaN0eKU66NZ6_cUtibtdTRBHw8xrbRJObgNaFlb4qylhFs5lDMrnAcA42vPPBmaxwifslyKfZ-g_ckjWB_w6SM-fcCnj_gGi_hjcSGbA4icTNj8b_wCC4l3Lg
CitedBy_id crossref_primary_10_1155_2016_4073584
crossref_primary_10_1002_cpe_6137
crossref_primary_10_1080_00140139_2022_2039410
crossref_primary_10_1038_s41597_022_01324_3
crossref_primary_10_1109_JIOT_2025_3574733
crossref_primary_10_1007_s12652_022_03867_0
crossref_primary_10_1109_COMST_2024_3357591
crossref_primary_10_1049_iet_ipr_2019_0350
crossref_primary_10_1007_s11554_020_01057_9
crossref_primary_10_3390_s21196623
crossref_primary_10_1016_j_measen_2022_100512
crossref_primary_10_1061__ASCE_CP_1943_5487_0000756
crossref_primary_10_1007_s11042_016_3959_0
crossref_primary_10_1109_ACCESS_2024_3430049
crossref_primary_10_1109_ACCESS_2023_3249144
crossref_primary_10_1007_s11760_020_01800_6
crossref_primary_10_3390_s22155507
crossref_primary_10_1177_0018720819857266
crossref_primary_10_1088_1742_6596_2273_1_012023
crossref_primary_10_3390_s21186037
crossref_primary_10_1109_JSEN_2021_3113123
crossref_primary_10_3390_jimaging11030091
crossref_primary_10_1080_21681163_2024_2331052
crossref_primary_10_1007_s00500_019_04567_2
crossref_primary_10_36680_j_itcon_2025_038
crossref_primary_10_1080_1206212X_2023_2198785
crossref_primary_10_1109_LRA_2019_2899429
crossref_primary_10_1016_j_patrec_2017_09_033
crossref_primary_10_1109_JIOT_2018_2883905
crossref_primary_10_3389_frobt_2021_643010
crossref_primary_10_1063_5_0181265
crossref_primary_10_3390_electronics9091357
crossref_primary_10_1109_ACCESS_2019_2922244
crossref_primary_10_1109_ACCESS_2019_2917000
crossref_primary_10_1109_ACCESS_2022_3185112
crossref_primary_10_1016_j_engappai_2023_106345
crossref_primary_10_1017_S0890060424000313
crossref_primary_10_1016_j_enbenv_2023_09_001
crossref_primary_10_1109_ACCESS_2025_3598088
crossref_primary_10_3390_diagnostics15050537
crossref_primary_10_3233_AIS_180493
crossref_primary_10_1007_s11042_020_09893_4
crossref_primary_10_1109_ACCESS_2023_3282439
crossref_primary_10_3390_machines13050414
crossref_primary_10_1007_s11042_021_11828_6
crossref_primary_10_1007_s11042_020_10418_2
crossref_primary_10_1038_s41597_025_04632_6
crossref_primary_10_3390_s23249889
crossref_primary_10_1109_ACCESS_2019_2929107
crossref_primary_10_1109_ACCESS_2023_3282311
crossref_primary_10_1007_s40820_025_01888_w
crossref_primary_10_1016_j_compag_2021_106057
crossref_primary_10_3390_s21072368
crossref_primary_10_1088_2634_4386_ac5ddf
crossref_primary_10_1007_s11042_024_20354_0
crossref_primary_10_1007_s10462_020_09904_8
crossref_primary_10_3390_s23239613
crossref_primary_10_1007_s10618_023_00999_5
crossref_primary_10_1007_s44163_025_00503_6
crossref_primary_10_1111_exsy_13680
crossref_primary_10_3390_s22010403
crossref_primary_10_1109_ACCESS_2023_3316032
crossref_primary_10_3390_s17051034
crossref_primary_10_1155_2018_3508350
crossref_primary_10_1007_s11277_022_09816_6
crossref_primary_10_3389_frobt_2019_00072
crossref_primary_10_3390_app112412099
crossref_primary_10_1016_j_neucom_2020_05_078
crossref_primary_10_2478_ijcss_2024_0007
crossref_primary_10_1007_s11042_020_09004_3
crossref_primary_10_3390_a15110403
crossref_primary_10_1007_s12652_022_03880_3
crossref_primary_10_1049_iet_cvi_2016_0055
crossref_primary_10_1007_s00521_022_07937_4
crossref_primary_10_1109_THMS_2023_3327132
crossref_primary_10_3389_fnbot_2023_1155826
crossref_primary_10_1007_s11042_024_18993_4
crossref_primary_10_3390_s16081341
crossref_primary_10_3390_s19194266
crossref_primary_10_1016_j_procs_2022_12_317
crossref_primary_10_12677_SEA_2023_122020
crossref_primary_10_1007_s10044_020_00953_x
crossref_primary_10_3390_modelling6020033
crossref_primary_10_1080_01942638_2025_2482257
crossref_primary_10_1049_iet_cvi_2017_0118
crossref_primary_10_1016_j_jmsy_2022_02_001
crossref_primary_10_1007_s10639_025_13351_9
crossref_primary_10_3390_s21248378
crossref_primary_10_1016_j_scico_2021_102629
crossref_primary_10_1371_journal_pone_0303090
crossref_primary_10_3390_a12100217
crossref_primary_10_3390_s23135862
crossref_primary_10_3389_fpsyg_2024_1407458
crossref_primary_10_3390_s23135869
crossref_primary_10_1109_JIOT_2023_3338697
crossref_primary_10_1007_s11042_023_17752_1
crossref_primary_10_1016_j_jnca_2020_102738
crossref_primary_10_1109_JBHI_2024_3406737
crossref_primary_10_1016_j_bbe_2020_04_007
crossref_primary_10_1109_ACCESS_2024_3377103
crossref_primary_10_3390_s21134443
crossref_primary_10_1145_3699736
crossref_primary_10_1016_j_bspc_2022_104255
crossref_primary_10_1080_08839514_2022_2093705
crossref_primary_10_1016_j_procs_2023_09_011
crossref_primary_10_1186_s43067_023_00124_y
crossref_primary_10_1109_TBDATA_2018_2803838
crossref_primary_10_1109_TNNLS_2022_3175480
crossref_primary_10_1145_3214269
crossref_primary_10_1109_ACCESS_2022_3204755
crossref_primary_10_1016_j_neucom_2025_130911
crossref_primary_10_1016_j_cobeha_2019_04_004
crossref_primary_10_1177_0018720820964343
crossref_primary_10_3390_en15176117
crossref_primary_10_1007_s40747_023_01218_w
crossref_primary_10_1016_j_ssci_2020_105130
crossref_primary_10_3390_app12115408
crossref_primary_10_3390_s21082760
crossref_primary_10_1080_01969722_2022_2062850
crossref_primary_10_1155_2022_8311371
crossref_primary_10_3390_s22134755
crossref_primary_10_3390_s23042182
crossref_primary_10_1109_ACCESS_2022_3211673
crossref_primary_10_2478_ijssis_2022_0021
crossref_primary_10_1016_j_imavis_2022_104465
crossref_primary_10_1155_2022_1808990
crossref_primary_10_33769_aupse_1306885
crossref_primary_10_32604_cmc_2022_022959
crossref_primary_10_1177_1550147719853987
crossref_primary_10_1109_ACCESS_2020_2968529
crossref_primary_10_1038_s41598_024_53143_8
crossref_primary_10_3390_s21186316
crossref_primary_10_1038_s42256_019_0110_8
crossref_primary_10_1007_s11831_021_09681_9
crossref_primary_10_1007_s11042_023_16001_9
crossref_primary_10_1016_j_heliyon_2022_e09633
crossref_primary_10_3390_s20133803
crossref_primary_10_1002_ett_4506
crossref_primary_10_1109_ACCESS_2024_3457912
crossref_primary_10_1109_TCSVT_2018_2887061
crossref_primary_10_1007_s11042_023_14666_w
crossref_primary_10_1109_ACCESS_2024_3353138
crossref_primary_10_3389_fnins_2023_1233037
crossref_primary_10_1007_s11042_018_7116_9
crossref_primary_10_1007_s11042_017_5038_6
crossref_primary_10_1371_journal_pone_0321754
crossref_primary_10_1109_ACCESS_2025_3590073
crossref_primary_10_3390_s21165270
crossref_primary_10_1016_j_knosys_2021_106970
crossref_primary_10_1016_j_patcog_2019_03_031
crossref_primary_10_3390_electronics11060932
crossref_primary_10_3390_app12189305
crossref_primary_10_1016_j_patcog_2019_107039
crossref_primary_10_1051_e3sconf_202020215008
crossref_primary_10_1007_s42979_024_02643_5
crossref_primary_10_1049_iet_ipr_2020_0709
crossref_primary_10_3390_app15158746
crossref_primary_10_1007_s12559_020_09740_6
crossref_primary_10_1109_ACCESS_2025_3555426
crossref_primary_10_1109_JSEN_2022_3161797
crossref_primary_10_5057_ijae_IJAE_D_17_00020
crossref_primary_10_1007_s11263_016_0918_1
crossref_primary_10_1109_TNSRE_2024_3371474
crossref_primary_10_3390_jimaging6060046
crossref_primary_10_1038_s41598_023_28195_x
crossref_primary_10_1109_JIOT_2019_2897334
crossref_primary_10_1016_j_compbiomed_2023_106835
crossref_primary_10_3390_diagnostics15010060
crossref_primary_10_3390_s23239393
crossref_primary_10_1109_TCSVT_2019_2912988
crossref_primary_10_1007_s11263_016_0985_3
crossref_primary_10_3390_s25134028
crossref_primary_10_3390_s18103529
crossref_primary_10_1007_s11227_019_02802_z
crossref_primary_10_3390_ijerph18041690
crossref_primary_10_3390_s21216997
crossref_primary_10_1038_s41598_023_44718_y
crossref_primary_10_1038_s41598_023_49739_1
crossref_primary_10_3390_app11135798
crossref_primary_10_1002_cpe_7250
crossref_primary_10_1007_s00607_025_01548_2
crossref_primary_10_1109_JSEN_2021_3108011
crossref_primary_10_1080_0951192X_2023_2177742
crossref_primary_10_1007_s00521_022_07665_9
crossref_primary_10_1109_JSEN_2022_3198395
crossref_primary_10_3390_electronics11152427
crossref_primary_10_1016_j_neucom_2024_127389
crossref_primary_10_1007_s11042_024_20484_5
crossref_primary_10_3390_make6020040
crossref_primary_10_1016_j_iot_2023_101018
crossref_primary_10_1145_3610907
crossref_primary_10_3390_s22124596
crossref_primary_10_3390_data3030024
crossref_primary_10_1109_LSP_2016_2643691
crossref_primary_10_3390_s23104899
crossref_primary_10_3390_app15169134
crossref_primary_10_3390_inventions9040090
crossref_primary_10_1007_s11042_023_17345_y
crossref_primary_10_1007_s10207_022_00640_4
crossref_primary_10_1007_s11042_023_15830_y
crossref_primary_10_1109_JSEN_2023_3323314
crossref_primary_10_1145_3569504
crossref_primary_10_3390_s25030918
crossref_primary_10_1016_j_future_2019_05_059
crossref_primary_10_1049_iet_cvi_2016_0326
Cites_doi 10.1109/T-AFFC.2011.37
10.1109/TITS.2009.2030963
10.1007/s10044-013-0349-3
10.1016/j.patrec.2013.09.015
10.1109/TPAMI.2010.214
10.1016/j.imavis.2013.09.007
10.1109/TPAMI.2010.156
10.1109/TPAMI.2013.137
10.1016/0146-664X(81)90073-3
10.1109/MCI.2013.2247823
10.1006/cviu.1998.0744
10.1007/s11263-013-0677-1
10.1007/s11263-014-0710-z
10.1016/j.patrec.2014.04.011
10.1016/j.imavis.2011.07.004
10.1017/CBO9780511996504
10.1016/j.patcog.2011.12.028
10.1016/j.cviu.2013.01.013
10.1109/TIFS.2013.2258152
10.1109/TPAMI.2011.253
10.1006/cviu.1998.0716
10.1109/TPAMI.2007.70711
10.1109/TPAMI.2007.1124
10.1016/S0031-3203(02)00100-0
10.1109/TNNLS.2012.2224882
10.1016/j.imavis.2013.08.005
10.1007/s11263-007-0122-4
10.1109/TPAMI.2008.52
10.1109/TCSVT.2008.2005594
10.1016/j.patcog.2013.05.019
10.1109/JSTSP.2012.2196975
10.1016/j.cviu.2012.09.008
10.1109/TMM.2014.2326734
10.1109/TSMCA.2012.2226575
10.1109/TIFS.2014.2344448
10.1109/TPAMI.2014.16
10.1109/TIP.2013.2271850
10.1016/j.cviu.2012.01.003
10.1109/TPAMI.2012.67
10.1109/TMM.2013.2293060
10.1109/34.868684
10.1515/9780691214696
10.1023/B:STCO.0000035301.49549.88
10.1007/s11263-014-0758-9
10.1016/j.patcog.2015.02.019
10.1007/s00138-013-0521-1
10.3390/s120201702
10.1155/S111086570321101X
10.1007/BF00204594
10.1016/j.cviu.2014.10.005
10.1162/neco.2006.18.7.1527
10.1007/s11263-012-0594-8
10.1016/j.neucom.2007.12.044
10.1109/JPROC.2010.2057231
10.1016/j.imavis.2009.11.014
10.1109/TNNLS.2011.2181865
10.1037/e526112012-054
10.1109/TMM.2014.2328311
10.1109/TPAMI.2012.24
10.1109/TPAMI.2013.128
10.1109/TPAMI.2011.64
10.1007/s00530-010-0182-0
10.1016/j.imavis.2012.07.003
10.1145/1922649.1922653
10.1007/978-3-642-24571-8_53
10.1016/j.patcog.2013.10.019
10.1007/s11263-013-0662-8
10.1016/j.cviu.2014.08.001
10.1016/j.imavis.2009.05.010
10.1109/TPAMI.2014.2303090
10.1007/s00138-012-0450-4
10.1109/TPAMI.2009.83
10.1109/JPROC.2003.823147
10.1162/0899766042321814
10.1109/TPAMI.2012.253
10.1109/TMM.2013.2267205
10.1016/j.cviu.2006.10.019
10.1016/j.cviu.2006.08.002
10.1109/JPROC.2002.801448
10.1109/T-AFFC.2011.9
10.1016/j.imavis.2012.08.018
10.1109/TIP.2012.2197008
10.1016/j.neucom.2012.02.002
10.1016/j.cviu.2013.11.007
10.1016/j.patrec.2013.02.006
10.1109/TAFFC.2014.2352268
10.1016/j.patcog.2014.04.018
10.1109/TIFS.2011.2175921
10.1016/j.neucom.2014.06.085
10.1109/JSTSP.2012.2193556
10.1109/TPAMI.2011.228
10.1016/j.patcog.2004.12.013
10.1007/s11263-005-1838-7
10.1016/j.cviu.2006.07.006
10.1016/j.cviu.2011.09.010
10.1109/MAES.2007.327521
10.1007/s11263-011-0493-4
10.1016/j.jvcir.2013.03.008
10.1145/2523819
10.1109/T-AFFC.2011.40
10.1162/15324430152748236
10.1109/TMM.2007.906583
10.1007/978-3-540-74889-2_7
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.3389/frobt.2015.00028
DatabaseName CrossRef
Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2296-9144
ExternalDocumentID oai_doaj_org_article_75b1cbb214b74173b6cdeeead5d3d1d3
10_3389_frobt_2015_00028
GroupedDBID 53G
5VS
9T4
AAFWJ
AAYXX
ACGFS
ADBBV
AFPKN
ALMA_UNASSIGNED_HOLDINGS
BCNDV
CITATION
GROUPED_DOAJ
IPNFZ
KQ8
M~E
OK1
PGMZT
RIG
ID FETCH-LOGICAL-c417t-2b7abf7b4b5d473bd3336e29878b0edc32b846d13ecadc422a4548b7386e694a3
IEDL.DBID DOA
ISICitedReferencesCount 344
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000421362200017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2296-9144
IngestDate Fri Oct 03 12:52:26 EDT 2025
Sat Nov 29 02:58:24 EST 2025
Tue Nov 18 22:00:32 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c417t-2b7abf7b4b5d473bd3336e29878b0edc32b846d13ecadc422a4548b7386e694a3
OpenAccessLink https://doaj.org/article/75b1cbb214b74173b6cdeeead5d3d1d3
ParticipantIDs doaj_primary_oai_doaj_org_article_75b1cbb214b74173b6cdeeead5d3d1d3
crossref_primary_10_3389_frobt_2015_00028
crossref_citationtrail_10_3389_frobt_2015_00028
PublicationCentury 2000
PublicationDate 2015-11-16
PublicationDateYYYYMMDD 2015-11-16
PublicationDate_xml – month: 11
  year: 2015
  text: 2015-11-16
  day: 16
PublicationDecade 2010
PublicationTitle Frontiers in robotics and AI
PublicationYear 2015
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Wang (B260) 2008
Jiang (B100) 2011
Singh (B221) 2011
Vrigkas (B248) 2013
Yao (B279) 2011
Kuehne (B114) 2011
Wang (B258) 2003; 36
Tipping (B238) 2001; 1
Lan (B120) 2014
Ikizler (B88) 2007
Robertson (B192) 2006; 104
Sigal (B218) 2012a; 98
Bousmalis (B20) 2013a; 31
Chen (B34) 2014
Reddy (B191) 2013; 24
Ouyang (B170) 2014
Hoai (B82) 2011
Guha (B72) 2012; 34
Raptis (B189) 2012
Gaidon (B66) 2014; 107
Jaimes (B92) 2007; 108
Eweiwi (B51) 2014
Jain (B93) 2014
Xu (B269) 2015
Lafferty (B118) 2001
Schindler (B205) 2008
Murray (B159) 1994
Li (B128) 2012
Kong (B110) 2014a; 36
Farhadi (B52) 2009
Oikonomopoulos (B168) 2009; 27
Song (B225) 2012a
Amin (B8) 2013
Martinez (B144) 2013; 8
Sanchez-Riera (B201) 2012
Pantic (B173) 2003; 91
Satkin (B204) 2010
Wang (B259) 2014; 16
Burenius (B23) 2013
Candamo (B25) 2010; 11
Heilbron (B79) 2015
Zhou (B288) 2012
Dollár (B42) 2005
Schuldt (B206) 2004
Tran (B240) 2014a; 36
Vemulapalli (B245) 2014
Li (B129) 2012
Haralick (B76) 1981; 15
Pirsiavash (B180) 2014
Fu (B64) 2012
Bojanowski (B19) 2013
Shivappa (B214) 2010; 98
Guadarrama (B71) 2013
Rawlinson (B190) 2007; 22
Lichtenauer (B130) 2011; 29
Metallinou (B152) 2012; 3
Singh (B220) 2010
Yun (B284) 2012
Wang (B254) 2013; 103
Laptev (B125) 2008
Xiong (B268) 2015
Kong (B111) 2014b
Fothergill (B62) 2012
Gorelick (B70) 2007; 29
Dalal (B41) 2006
Healey (B78) 2011
Fouhey (B63) 2014; 110
Moutzouris (B157) 2015; 132
Siddiquie (B217) 2013
Sun (B231) 2009
Yao (B278) 2012; 34
Rudovic (B197) 2013
Gavrila (B69) 1999; 73
Cui (B39) 2011
Theodorakopoulos (B234) 2014; 25
Choi (B36) 2011
Blank (B18) 2005
Gan (B67) 2015
Hoai (B83) 2014
Marszałek (B143) 2009
Wu (B264) 2015
Metallinou (B148) 2013; 31
Cherian (B35) 2014
Wang (B257) 2012c
Chen (B30) 2012
Salakhutdinov (B199) 2011
Pishchulin (B181) 2013
Fisher (B58) 2004
Amer (B7) 2012
Soomro (B228) 2012
Wang (B261) 2010
Kim (B105) 2013
Andriluka (B9) 2014
Soleymani (B224) 2012; 3
Sun (B230) 2005; 38
Bilakhia (B16) 2013
Ye (B280) 2013
Kong (B109) 2014
Fu (B65) 2014; 36
Turaga (B243) 2008; 18
Fisher (B59) 2007a
Gao (B68) 2015; 151
Bousmalis (B22) 2011
Li (B127) 2011
Liu (B135) 2009
Smola (B222) 2004; 14
Gupta (B75) 2009; 31
Nicolaou (B163) 2011; 2
Urtasun (B244) 2008
Roshtkhari (B196) 2013; 31
Poppe (B182) 2010; 28
Yang (B275) 2014; 16
Hinton (B80) 2006; 18
Ramanathan (B188) 2013
Seo (B210) 2011; 33
Mumtaz (B158) 2014
Fernando (B56) 2015
Perez (B176) 2004; 92
Fergie (B55) 2013; 31
Toshev (B239) 2014
Metallinou (B151) 2013
Zeng (B285) 2009; 31
Kuehne (B113) 2014
Liu (B134) 2011b
Wang (B252) 2011b
Elgammal (B47) 2002; 90
Yang (B273) 2010
Ramanathan (B187) 2015
Schuller (B207) 2011; 6975
Shafer (B212) 1976
Klami (B106) 2008; 72
Castellano (B26) 2007; 4738
Morris (B156) 2011; 33
Morariu (B155) 2011
Bishop (B17) 2006
Sadanand (B198) 2012
Le (B126) 2011
Oliver (B169) 2000; 22
Fisher (B60) 2007b
Xu (B270) 2012
Chaquet (B28) 2013; 117
Rodriguez (B193) 2008
Sedai (B208) 2013a; 46
Chen (B31) 2015
Rohrbach (B195) 2012
Yi (B281) 2012; 21
Kovashka (B112) 2010
Jung (B102) 2015
Vinciarelli (B246) 2009
Kläser (B107) 2008
Ma (B140) 2015
Iosifidis (B91) 2012b; 23
Karpathy (B103) 2014
Sargin (B203) 2007; 9
Metallinou (B150) 2008
Park (B174) 2015
Thurau (B236) 2008
Zhou (B289) 2014; 9
Moeslund (B154) 2006; 104
Messing (B147) 2009
Snoek (B223) 2005
Kulkarni (B116) 2014
Tian (B237) 2013
Chen (B33) 2013b; 34
Bousmalis (B21) 2013b; 24
Zhang (B286) 2013; 8
Samanta (B200) 2014; 16
Picard (B178) 1997
Tran (B241) 2014b; 44
Zhang (B287) 2015; 18
Lu (B139) 2011
Song (B227) 2013
Yan (B271) 2014; 47
Yu (B282) 2015
Ni (B161) 2015
Vinyals (B247) 2015
Andriluka (B10) 2012
Perronnin (B177) 2007
Guo (B73) 2014; 47
Tang (B232) 2013
Yao (B276) 2010
Jiang (B99) 2014
Wu (B266) 2010
Ikizler-Cinbis (B89) 2010
Rahmani (B186) 2015
Lan (B123) 2011
Theodoridis (B235) 2008
Aggarwal (B3) 2014; 48
Sedai (B209) 2013b; 22
Mikolajczyk (B153) 2008
Lan (B122) 2012b; 34
Tran (B242) 2012; 45
Chakraborty (B27) 2012; 116
Fathi (B53) 2012
Oh (B167) 2011
Pantic (B172) 2006
Ciresan (B38) 2012
Ni (B162) 2014
Yao (B277) 2010
Lillo (B131) 2014
Gupta (B74) 2007
Hardoon (B77) 2004; 16
Jhuang (B97) 2013
Jiang (B101) 2013; 117
Jayaraman (B96) 2014
Shu (B216) 2015
Aggarwal (B1) 1999; 73
Livne (B137) 2012; 116
Nie (B165) 2015
Rahmani (B185) 2014
Atrey (B12) 2010; 16
Donahue (B43) 2015
Sapienza (B202) 2014; 110
Liu (B136) 2010
Lampert (B119) 2009
Sigal (B219) 2012b; 98
Ciresan (B37) 2011
Fathi (B54) 2008
Ngiam (B160) 2011
Shao (B213) 2015
Ekman (B46) 2002
Ho (B81) 1995
Wang (B251) 2011a
Evgeniou (B50) 2004
Wang (B256) 2012b
Akata (B4) 2013
Holte (B84) 2012a; 6
Patron-Perez (B175) 2012; 34
Quattoni (B184) 2007; 29
Bandla (B13) 2013
Baxter (B14) 2015; 48
Jhuang (B98) 2007
Dalal (B40) 2005
Khamis (B104) 2012
Yu (B283) 2012
Shabani (B211) 2011
Belagiannis (B15) 2014
Niebles (B166) 2008; 79
Chen (B32) 2013a
Wang (B262) 2011; 33
Kulkarni (B115) 2015; 112
Yan (B272) 2012; 87
Chaudhry (B29) 2009
Evangelopoulos (B49) 2013; 15
(B108) 2001
Wang (B255) 2012a
Lin (B132) 2009
Burgos-Artizzu (B24) 2012
Nicolaou (B164) 2014; 36
Jain (B94) 2013
Fogel (B61) 1989; 61
Jainy (B95) 2015
Vrigkas (B249) 2014a; 119
Westerveld (B263) 2003; 2003
Efros (B45) 2003
Laptev (B124) 2005; 64
AlZoubi (B6) 2013
Vrigkas (B250) 2014b
Metallinou (B149) 2010
Shotton (B215) 2011
Kviatkovsky (B117) 2014; 129
Lu (B138) 2015
Anirudh (B11) 2015
Holte (B85) 2012b; 6
Palatucci (B171) 2009
Yang (B274) 2013; 35
Rodríguez (B194) 2014; 46
Matikainen (B146) 2009
Tenorth (B233) 2009
Wu (B265) 2013; 43
Prince (B183) 2012
Alahi (B5) 2014
Du (B44) 2015
Wu (B267) 2011
Escalera (B48) 2012; 12
Ferrari (B57) 2009
Hussain (B87) 2011
Song (B226) 2012b
Lan (B121) 2012a
Maji (B141) 2011
Huang (B86) 2011
Iosifidis (B90) 2012a; 7
Marín-Jiménez (B142) 2014; 25
Wang (B253) 2011c
Aggarwal (B2) 2011; 43
Sun (B229) 2013
Liu (B133) 2011a
Martinez (B145) 2014; 5
Pirsiavash (B179) 2012
References_xml – start-page: 588
  year: 2014
  ident: B245
  article-title: “Human action recognition by representing 3D skeletons as points in a lie group,”
– start-page: 240
  year: 2013
  ident: B6
  article-title: “Affect detection and classification from the non-stationary physiological data,”
– start-page: 260
  year: 2012
  ident: B10
  article-title: “Human context: modeling human-human interactions for monocular 3D pose estimation,”
– start-page: 1653
  year: 2014
  ident: B239
  article-title: “Deeppose: human pose estimation via deep neural networks,”
– start-page: 3464
  year: 2014
  ident: B96
  article-title: “Zero-shot recognition with unreliable attributes,”
– start-page: 3562
  year: 2013
  ident: B227
  article-title: “Action recognition by hierarchical sequence summarization,”
– start-page: 27
  year: 2012a
  ident: B225
  article-title: “Multimodal human behavior analysis: learning correlation and interaction across modalities,”
– volume: 3
  start-page: 211
  year: 2012
  ident: B224
  article-title: Multimodal emotion recognition in response to videos
  publication-title: IEEE Trans. Affective Comput.
  doi: 10.1109/T-AFFC.2011.37
– start-page: 1737
  year: 2012
  ident: B62
  article-title: “Instructing people for training gestural interactive systems,”
– start-page: 1
  year: 2007
  ident: B74
  article-title: “Objects in action: an approach for combining action understanding and object perception,”
– start-page: 689
  year: 2014
  ident: B120
  article-title: “A hierarchical representation for future action prediction,”
– start-page: 2458
  year: 2015
  ident: B186
  article-title: “Learning a non-linear knowledge transfer model for cross-view action recognition,”
– volume: 11
  start-page: 206
  year: 2010
  ident: B25
  article-title: Understanding transit scenes: a survey on human behavior-recognition algorithms
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2009.2030963
– start-page: 3487
  year: 2013
  ident: B181
  article-title: “Strong appearance and expressive spatial models for human pose estimation,”
– start-page: 789
  year: 2013
  ident: B197
  article-title: “Bimodal log-linear regression for fusion of audio and visual features,”
– start-page: 1410
  year: 2009
  ident: B171
  article-title: “Zero-shot learning with semantic output codes,”
– volume: 18
  start-page: 157
  year: 2015
  ident: B287
  article-title: Robust relative attributes for human action recognition
  publication-title: Pattern Anal. Appl.
  doi: 10.1007/s10044-013-0349-3
– start-page: 2030
  year: 2010
  ident: B273
  article-title: “Recognizing human actions from still images with latent poses,”
– start-page: 5024
  year: 2015
  ident: B140
  article-title: “Space-time tree ensemble for action recognition,”
– start-page: 2556
  year: 2011
  ident: B114
  article-title: “HMDB: a large video database for human motion recognition,”
– start-page: 3698
  year: 2015
  ident: B161
  article-title: “Motion part regularization: improving action recognition via trajectory group selection,”
– start-page: 113
  year: 2011
  ident: B221
  article-title: “Action recognition in cluttered dynamic scenes using pose-specific part models,”
– volume: 44
  start-page: 49
  year: 2014b
  ident: B241
  article-title: Activity analysis in crowded environments using social cues for group discovery and human interaction modeling
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2013.09.015
– start-page: 3642
  year: 2012
  ident: B38
  article-title: “Multi-column deep neural networks for image classification,”
– volume: 33
  start-page: 1310
  year: 2011
  ident: B262
  article-title: Hidden part models for human action recognition: probabilistic versus max margin
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2010.214
– start-page: 3289
  year: 2011
  ident: B155
  article-title: “Multi-agent event recognition in structured scenarios,”
– volume: 31
  start-page: 949
  year: 2013
  ident: B55
  article-title: Mixtures of Gaussian process models for human pose estimation
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2013.09.007
– start-page: 1089
  volume-title: Proc. IEEE International Workshop on Tracking Humans for the Evaluation of Their Motion in Image Sequences (THEMIS)
  year: 2009
  ident: B233
  article-title: “The TUM kitchen data set of everyday manipulation activities for motion tracking and action recognition,”
– start-page: 568
  year: 2011
  ident: B87
  article-title: “Hybrid fusion approach for detecting affects from multichannel physiology,”
– start-page: 913
  year: 2013
  ident: B229
  article-title: “ACTIVE: activity concept transitions in video event classification,”
– start-page: 112
  year: 2013
  ident: B248
  article-title: “Action recognition by matching clustered trajectories of motion vectors,”
– start-page: 107
  year: 2011
  ident: B78
  article-title: “Recording affect in the field: towards methods and metrics for improving ground truth labels,”
– volume: 33
  start-page: 867
  year: 2011
  ident: B210
  article-title: Action recognition from one example
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2010.156
– start-page: 1
  year: 2008
  ident: B125
  article-title: “Learning realistic human actions from movies,”
– volume: 36
  start-page: 404
  year: 2014a
  ident: B240
  article-title: Video event detection: from subvolume localization to spatiotemporal path search
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2013.137
– start-page: 1297
  year: 2011
  ident: B215
  article-title: “Real-time human pose recognition in parts from single depth images,”
– start-page: 995
  year: 2008
  ident: B107
  article-title: “A spatio-temporal descriptor based on 3D-gradients,”
– start-page: 3273
  year: 2011
  ident: B36
  article-title: “Learning context for collective activity recognition,”
– volume: 15
  start-page: 113
  year: 1981
  ident: B76
  article-title: A facet model for image data
  publication-title: Comput. Graph. Image Process.
  doi: 10.1016/0146-664X(81)90073-3
– start-page: 1
  year: 2007
  ident: B98
  article-title: “A biologically inspired system for action recognition,”
– volume: 8
  start-page: 20
  year: 2013
  ident: B144
  article-title: Learning deep physiological models of affect
  publication-title: IEEE Comput. Intell. Mag.
  doi: 10.1109/MCI.2013.2247823
– volume: 73
  start-page: 428
  year: 1999
  ident: B1
  article-title: Human motion analysis: a review
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1006/cviu.1998.0744
– volume: 107
  start-page: 219
  year: 2014
  ident: B66
  article-title: Activity representation with motion hierarchies
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-013-0677-1
– volume-title: Self-Organizing Maps
  year: 2001
  ident: B108
– volume: 110
  start-page: 259
  year: 2014
  ident: B63
  article-title: People watching: human actions as a cue for single view geometry
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-014-0710-z
– start-page: 1322
  year: 2012
  ident: B24
  article-title: “Social behavior recognition in continuous video,”
– start-page: 3762
  year: 2015
  ident: B138
  article-title: “Human action segmentation with hierarchical supervoxel consistency,”
– start-page: 32
  year: 2004
  ident: B206
  article-title: “Recognizing human actions: a local SVM approach,”
– volume: 48
  start-page: 70
  year: 2014
  ident: B3
  article-title: Human activity recognition from 3D data: a review
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2014.04.011
– start-page: 1242
  year: 2012
  ident: B189
  article-title: “Discovering discriminative action parts from mid-level video representations,”
– start-page: 1237
  year: 2011
  ident: B37
  article-title: “Flexible, high performance convolutional neural networks for image classification,”
– volume: 29
  start-page: 666
  year: 2011
  ident: B130
  article-title: Cost-effective solution to synchronised audio-visual data capture using multiple sensors
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2011.07.004
– start-page: 3185
  year: 2011b
  ident: B252
  article-title: “Action recognition with multiscale spatio-temporal contexts,”
– start-page: 489
  year: 2011
  ident: B267
  article-title: “Action recognition using context and appearance distribution features,”
– start-page: 596
  year: 2014b
  ident: B111
  article-title: “A discriminative model with multiple temporal scales for action prediction,”
– start-page: 48
  year: 2010
  ident: B220
  article-title: “Muhavi: a multicamera human action video dataset for the evaluation of action recognition methods,”
– start-page: 1669
  year: 2014
  ident: B15
  article-title: “3D pictorial structures for multiple human pose estimation,”
– volume-title: Computer Vision: Models Learning and Inference
  year: 2012
  ident: B183
  doi: 10.1017/CBO9780511996504
– volume: 45
  start-page: 2562
  year: 2012
  ident: B242
  article-title: Part-based motion descriptor image for human action recognition
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2011.12.028
– volume: 117
  start-page: 633
  year: 2013
  ident: B28
  article-title: A survey of video datasets for human action and activity recognition
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2013.01.013
– volume: 8
  start-page: 1600
  year: 2013
  ident: B286
  article-title: Attribute regularization based human action recognition
  publication-title: IEEE Trans. Inform. Forensics Secur.
  doi: 10.1109/TIFS.2013.2258152
– volume: 34
  start-page: 1576
  year: 2012
  ident: B72
  article-title: Learning sparse representations for human action recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2011.253
– start-page: 2847
  year: 2012
  ident: B179
  article-title: “Detecting activities of daily living in first-person camera views,”
– start-page: 239
  year: 2006
  ident: B172
  article-title: “Human computing and machine understanding of human behavior: a survey,”
– volume: 73
  start-page: 82
  year: 1999
  ident: B69
  article-title: The visual analysis of human movement: a survey
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1006/cviu.1998.0716
– volume: 29
  start-page: 2247
  year: 2007
  ident: B70
  article-title: Actions as space-time shapes
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2007.70711
– start-page: 3147
  year: 2015
  ident: B11
  article-title: “Elastic functional coding of human actions: from vector-fields to latent variables,”
– start-page: 1
  year: 2011
  ident: B211
  article-title: “Improved spatio-temporal salient feature detection for action recognition,”
– start-page: 250
  year: 2008
  ident: B150
  article-title: “Audio-visual emotion recognition using Gaussian mixture models for face and voice,”
– volume: 29
  start-page: 1848
  year: 2007
  ident: B184
  article-title: Hidden conditional random fields
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2007.1124
– volume-title: Facial Action Coding System (FACS): Manual
  year: 2002
  ident: B46
– volume: 36
  start-page: 585
  year: 2003
  ident: B258
  article-title: Recent developments in human motion analysis
  publication-title: Pattern Recognit.
  doi: 10.1016/S0031-3203(02)00100-0
– start-page: 17
  year: 2010
  ident: B277
  article-title: “Modeling mutual context of object and human pose in human-object interaction activities,”
– volume: 24
  start-page: 170
  year: 2013b
  ident: B21
  article-title: Infinite hidden conditional random fields for human behavior analysis
  publication-title: IEEE Trans. Neural Networks Learn. Syst.
  doi: 10.1109/TNNLS.2012.2224882
– volume: 31
  start-page: 864
  year: 2013
  ident: B196
  article-title: Human activity recognition in videos using a single example
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2013.08.005
– start-page: 819
  year: 2013
  ident: B4
  article-title: “Label-embedding for attribute-based classification,”
– start-page: 3177
  year: 2011
  ident: B141
  article-title: “Action recognition from a distributed representation of pose and appearance,”
– year: 2004
  ident: B58
  publication-title: PETS04 Surveillance Ground Truth Dataset
– start-page: 4362
  year: 2015
  ident: B264
  article-title: “Watch-n-patch: unsupervised understanding of actions and relations,”
– start-page: 530
  year: 2012
  ident: B64
  article-title: “Attribute learning for understanding unstructured social activity,”
– start-page: 1
  year: 2013
  ident: B151
  article-title: “Annotation and processing of continuous emotional attributes: challenges and opportunities,”
– start-page: 28
  year: 2012
  ident: B284
  article-title: “Two-person interaction detection using body-pose features and multiple instance learning,”
– volume: 79
  start-page: 299
  year: 2008
  ident: B166
  article-title: Unsupervised learning of human action categories using spatial-temporal words
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-007-0122-4
– start-page: 3193
  year: 2011
  ident: B127
  article-title: “Activity recognition using dynamic subspace angles,”
– start-page: 114
  year: 2012
  ident: B270
  article-title: “Combining skeletal pose with local motion for human activity recognition,”
– start-page: 1
  year: 2013
  ident: B8
  article-title: “Multi-view pictorial structures for 3D human pose estimation,”
– start-page: 1
  year: 2009
  ident: B135
  article-title: “Recognizing realistic actions from videos in the wild,”
– year: 2007a
  ident: B59
  publication-title: Behave: Computer-Assisted Prescreening of Video Streams for Unusual Activities
– start-page: 1725
  year: 2014
  ident: B103
  article-title: “Large-scale video classification with convolutional neural networks,”
– start-page: 1362
  year: 2012
  ident: B128
  article-title: “Cross-view activity recognition using hankelets,”
– start-page: 740
  year: 2014
  ident: B93
  article-title: “Action localization with tubelets from motion,”
– start-page: 1
  year: 2008
  ident: B54
  article-title: “Action recognition by learning mid-level motion features,”
– start-page: 123
  year: 2013
  ident: B16
  article-title: “Audiovisual detection of behavioural mimicry,”
– start-page: 2120
  year: 2012b
  ident: B226
  article-title: “Multi-view latent variable discriminative models for action recognition,”
– volume: 31
  start-page: 39
  year: 2009
  ident: B285
  article-title: A survey of affect recognition methods: audio, visual, and spontaneous expressions
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2008.52
– volume: 18
  start-page: 1473
  year: 2008
  ident: B243
  article-title: Machine recognition of human activities: a survey
  publication-title: Proc. IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2008.2005594
– start-page: 886
  year: 2005
  ident: B40
  article-title: “Histograms of oriented gradients for human detection,”
– start-page: 1354
  year: 2012a
  ident: B121
  article-title: “Social roles in hierarchical models for human activity recognition,”
– volume: 46
  start-page: 3223
  year: 2013a
  ident: B208
  article-title: Discriminative fusion of shape and appearance features for human pose estimation
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2013.05.019
– volume: 6
  start-page: 538
  year: 2012b
  ident: B85
  article-title: Human pose estimation and activity recognition from multi-view videos: comparative explorations of recent developments
  publication-title: IEEE J. Sel. Top. Signal Process.
  doi: 10.1109/JSTSP.2012.2196975
– start-page: 5378
  year: 2015
  ident: B56
  article-title: “Modeling video evolution for action recognition,”
– start-page: 1
  year: 2011
  ident: B86
  article-title: “Latent boosting for action recognition,”
– start-page: 693
  year: 2012
  ident: B283
  article-title: “Propagative Hough voting for human activity recognition,”
– start-page: 2061
  year: 2010
  ident: B276
  article-title: “A Hough transform-based voting framework for action recognition,”
– start-page: 220
  year: 2014
  ident: B116
  article-title: “Transfer learning via attributes for improved on-the-fly classification,”
– volume: 117
  start-page: 1345
  year: 2013
  ident: B101
  article-title: A unified tree-based framework for joint action localization, recognition and segmentation
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2012.09.008
– volume: 16
  start-page: 1525
  year: 2014
  ident: B200
  article-title: Space-time facet model for human activity classification
  publication-title: IEEE Trans. Multimedia
  doi: 10.1109/TMM.2014.2326734
– volume: 43
  start-page: 875
  year: 2013
  ident: B265
  article-title: Realistic human action recognition with multimodal feature selection and fusion
  publication-title: IEEE Trans. Syst. Man Cybern. Syst.
  doi: 10.1109/TSMCA.2012.2226575
– volume: 9
  start-page: 1581
  year: 2014
  ident: B289
  article-title: Human action recognition with multiple-instance Markov model
  publication-title: IEEE Trans. Inform. Forensics Secur
  doi: 10.1109/TIFS.2014.2344448
– volume: 36
  start-page: 1299
  year: 2014
  ident: B164
  article-title: Dynamic probabilistic CCA for analysis of affective behavior and fusion of continuous annotations
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2014.16
– start-page: 2568
  year: 2015
  ident: B67
  article-title: “DevNet: a deep event network for multimedia event detection and evidence recounting,”
– volume: 22
  start-page: 4286
  year: 2013b
  ident: B209
  article-title: A Gaussian process guided particle filter for tracking 3D human pose in video
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2013.2271850
– start-page: 29
  year: 2011
  ident: B100
  article-title: “Consumer video understanding: a benchmark database and an evaluation of human and machine performance,”
– volume: 116
  start-page: 648
  year: 2012
  ident: B137
  article-title: Human attributes from 3D pose tracking
  publication-title: Comput. Vis. Image Understanding
  doi: 10.1016/j.cviu.2012.01.003
– volume: 34
  start-page: 1691
  year: 2012
  ident: B278
  article-title: Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.67
– start-page: 3249
  year: 2011
  ident: B139
  article-title: “Identifying players in broadcast sports videos using conditional random fields,”
– volume: 16
  start-page: 289
  year: 2014
  ident: B259
  article-title: Semi-supervised multiple feature analysis for action recognition
  publication-title: IEEE Trans. Multimedia
  doi: 10.1109/TMM.2013.2293060
– start-page: 2625
  year: 2015
  ident: B43
  article-title: “Long-term recurrent convolutional networks for visual recognition and description,”
– start-page: 332
  year: 2012
  ident: B201
  article-title: “Action recognition robust to background clutter by using stereo vision,”
– volume: 22
  start-page: 831
  year: 2000
  ident: B169
  article-title: A Bayesian computer vision system for modeling human interactions
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/34.868684
– volume-title: A Mathematical Theory of Evidence
  year: 1976
  ident: B212
  doi: 10.1515/9780691214696
– start-page: 1293
  year: 2015
  ident: B165
  article-title: “Joint action recognition and pose estimation from video,”
– volume: 14
  start-page: 199
  year: 2004
  ident: B222
  article-title: A tutorial on support vector regression
  publication-title: Stat. Comput.
  doi: 10.1023/B:STCO.0000035301.49549.88
– start-page: 3686
  year: 2014
  ident: B9
  article-title: “2D human pose estimation: new benchmark and state of the art analysis,”
– start-page: 726
  year: 2003
  ident: B45
  article-title: “Recognizing action at a distance,”
– start-page: 291
  year: 2012
  ident: B288
  article-title: “Atomic action features: a new feature for action recognition,”
– volume: 112
  start-page: 90
  year: 2015
  ident: B115
  article-title: Continuous action recognition based on sequence alignment
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-014-0758-9
– start-page: 1370
  year: 2012b
  ident: B256
  article-title: “Action recognition by exploring data distribution and feature correlation,”
– volume-title: Pattern Recognition
  year: 2008
  ident: B235
– volume: 48
  start-page: 2377
  year: 2015
  ident: B14
  article-title: Human behaviour recognition in data-scarce domains
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2015.02.019
– volume: 25
  start-page: 71
  year: 2014
  ident: B142
  article-title: Human interaction categorization by using audio-visual cues
  publication-title: Mach. Vis. Appl.
  doi: 10.1007/s00138-013-0521-1
– start-page: 444
  year: 2009
  ident: B132
  article-title: “Recognizing actions by shape-motion prototype trees,”
– start-page: 2003
  year: 2011
  ident: B123
  article-title: “Discriminative figure-centric models for joint action localization and recognition,”
– volume: 12
  start-page: 1702
  year: 2012
  ident: B48
  article-title: Social network extraction and analysis based on multimodal dyadic interaction
  publication-title: Sensors
  doi: 10.3390/s120201702
– start-page: 3618
  year: 2013
  ident: B23
  article-title: “3D pictorial structures for multiple view articulated pose estimation,”
– volume: 2003
  start-page: 186
  year: 2003
  ident: B263
  article-title: A probabilistic multimedia retrieval model and its evaluation
  publication-title: EURASIP J. Appl. Signal Process.
  doi: 10.1155/S111086570321101X
– start-page: 905
  year: 2013
  ident: B188
  article-title: “Video event understanding using natural language descriptions,”
– start-page: 428
  year: 2006
  ident: B41
  article-title: “Human detection using oriented histograms of flow and appearance,”
– volume: 61
  start-page: 103
  year: 1989
  ident: B61
  article-title: Gabor filters as texture discriminator
  publication-title: Biol. Cybern.
  doi: 10.1007/BF00204594
– start-page: 2467
  year: 2015
  ident: B102
  article-title: “Random treewalk toward instantaneous 3D human pose estimation,”
– start-page: 746
  year: 2011
  ident: B22
  article-title: “Modeling hidden dynamics of multimodal cues for spontaneous agreement and disagreement recognition,”
– start-page: 3265
  year: 2011
  ident: B82
  article-title: “Joint segmentation and classification of human actions in video,”
– start-page: 29
  year: 2014
  ident: B109
  article-title: “Modeling supporting regions for close human interaction recognition,”
– start-page: 4576
  year: 2015
  ident: B216
  article-title: “Joint inference of groups, events and human roles in aerial videos,”
– start-page: 1932
  year: 2009
  ident: B29
  article-title: “Histograms of oriented optical flow and Binet-Cauchy kernels on nonlinear dynamical systems for the recognition of human actions,”
– start-page: 2211
  year: 2014
  ident: B5
  article-title: “Socially-aware large-scale crowd forecasting,”
– volume: 132
  start-page: 75
  year: 2015
  ident: B157
  article-title: Efficient tracking of human poses using a manifold hierarchy
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2014.10.005
– volume: 18
  start-page: 1527
  year: 2006
  ident: B80
  article-title: A fast learning algorithm for deep belief nets
  publication-title: Neural Comput.
  doi: 10.1162/neco.2006.18.7.1527
– volume: 103
  start-page: 60
  year: 2013
  ident: B254
  article-title: Dense trajectories and motion boundary descriptors for action recognition
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-012-0594-8
– volume: 72
  start-page: 39
  year: 2008
  ident: B106
  article-title: Probabilistic approach to detecting dependencies between data sets
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2007.12.044
– start-page: 1398
  year: 2010
  ident: B136
  article-title: “A Bayesian framework for 3D human motion tracking from monocular image,”
– volume: 98
  start-page: 1692
  year: 2010
  ident: B214
  article-title: Audiovisual information fusion in human-computer interfaces and intelligent environments: a survey
  publication-title: Proc. IEEE
  doi: 10.1109/JPROC.2010.2057231
– start-page: 2280
  year: 2013
  ident: B19
  article-title: “Finding actors and actions in movies,”
– start-page: 3361
  year: 2011
  ident: B126
  article-title: “Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis,”
– start-page: 1290
  year: 2012a
  ident: B255
  article-title: “Mining actionlet ensemble for action recognition with depth cameras,”
– volume: 28
  start-page: 976
  year: 2010
  ident: B182
  article-title: A survey on vision-based human action recognition
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2009.11.014
– start-page: 1331
  year: 2011
  ident: B279
  article-title: “Human action recognition by learning bases of action attributes and parts,”
– start-page: 1
  year: 2013
  ident: B217
  article-title: “Affect analysis in natural human interaction using joint hidden conditional random fields,”
– start-page: 961
  year: 2015
  ident: B79
  article-title: “ActivityNet: a large-scale video benchmark for human activity understanding,”
– start-page: 195
  year: 2011b
  ident: B134
  article-title: “Associating textual features with visual ones to improve affective image classification,”
– year: 2007b
  ident: B60
  publication-title: PETS07 Benchmark Dataset
– start-page: 1218
  year: 2012
  ident: B104
  article-title: “A flow model for joint action recognition and identity maintenance,”
– start-page: 1314
  year: 2012
  ident: B7
  article-title: “Sum-product networks for modeling activities with stochastic structure,”
– start-page: 1
  volume-title: Proc. Multimodal Corpora: Advances in Capturing, Coding and Analyzing Multimodality
  year: 2010
  ident: B149
  article-title: “The USC creative IT database: a multimodal database of theatrical improvisation,”
– start-page: 1
  year: 2009
  ident: B57
  article-title: “Pose search: retrieving people using their pose,”
– start-page: 368
  year: 2014
  ident: B158
  article-title: “Joint motion segmentation and background estimation in dynamic scenes,”
– start-page: 399
  year: 2005
  ident: B223
  article-title: “Early versus late fusion in semantic video analysis,”
– start-page: 1
  year: 2008
  ident: B205
  article-title: “Action snippets: how many frames does human action recognition require?,”
– start-page: 1600
  year: 2015
  ident: B268
  article-title: “Recognize complex events from static images by fusing deep channels,”
– start-page: 1833
  year: 2013
  ident: B13
  article-title: “Active learning of an action detector from untrimmed videos,”
– start-page: 748
  year: 2014
  ident: B34
  article-title: “Actionness ranking with lattice conditional ordinal random fields,”
– start-page: 1234
  year: 2012
  ident: B198
  article-title: “Action bank: a high-level representation of activity in video,”
– volume: 23
  start-page: 412
  year: 2012b
  ident: B91
  article-title: View-invariant action recognition based on artificial neural networks
  publication-title: IEEE Trans. Neural Networks Learn. Syst.
  doi: 10.1109/TNNLS.2011.2181865
– volume-title: Affective Computing
  year: 1997
  ident: B178
  doi: 10.1037/e526112012-054
– start-page: 1274
  year: 2012
  ident: B30
  article-title: “Efficient activity detection with max-subgraph search,”
– start-page: 2384
  year: 2011c
  ident: B253
  article-title: “Kernel cross-modal factor analysis for multimodal information fusion,”
– volume: 16
  start-page: 1766
  year: 2014
  ident: B275
  article-title: Analysis and predictive modeling of body language behavior in dyadic interactions from multimodal interlocutor cues
  publication-title: IEEE Trans. Multimedia
  doi: 10.1109/TMM.2014.2328311
– start-page: 3337
  year: 2011a
  ident: B133
  article-title: “Recognizing human actions by attributes,”
– volume-title: UCF101: A Dataset of 101 Human Actions Classes from Videos in the Wild
  year: 2012
  ident: B228
– start-page: 1721
  year: 2008
  ident: B260
  article-title: “Learning a discriminative hidden part model for human action recognition,”
– start-page: 149
  volume-title: Time-of-Flight and Depth Imaging, Lecture Notes in Computer Science
  year: 2013
  ident: B280
  article-title: “A survey on human motion analysis from depth data,”
– start-page: 1
  year: 2008
  ident: B193
  article-title: “Action MACH: a spatio-temporal maximum average correlation height filter for action recognition,”
– start-page: 780
  year: 2014
  ident: B113
  article-title: “The language of actions: recovering the syntax and semantics of goal-directed human activities,”
– volume: 34
  start-page: 2441
  year: 2012
  ident: B175
  article-title: Structured learning of human interactions in TV shows
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.24
– volume: 36
  start-page: 303
  year: 2014
  ident: B65
  article-title: Learning multimodal latent attributes
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2013.128
– start-page: 3192
  year: 2013
  ident: B97
  article-title: “Towards understanding action recognition,”
– start-page: 58
  year: 2009
  ident: B231
  article-title: “Action recognition via local descriptors and holistic features,”
– start-page: 1
  year: 2008
  ident: B236
  article-title: “Pose primitive based human action recognition in videos or still images,”
– start-page: 46
  year: 2015
  ident: B95
  article-title: “What do 15,000 object categories tell us about classifying and localizing actions?,”
– volume: 33
  start-page: 2287
  year: 2011
  ident: B156
  article-title: Trajectory learning for activity understanding: unsupervised, multilevel, and long-term adaptive approach
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2011.64
– volume: 16
  start-page: 345
  year: 2010
  ident: B12
  article-title: Multimodal fusion for multimedia analysis: a survey
  publication-title: Multimed. Syst.
  doi: 10.1007/s00530-010-0182-0
– volume: 31
  start-page: 203
  year: 2013a
  ident: B20
  article-title: Towards the automatic detection of spontaneous agreement and disagreement based on nonverbal behaviour: a survey of related cues, databases, and tools
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2012.07.003
– start-page: 2642
  year: 2013
  ident: B237
  article-title: “Spatiotemporal deformable part models for action detection,”
– volume: 43
  start-page: 1
  year: 2011
  ident: B2
  article-title: Human activity analysis: a review
  publication-title: ACM Comput. Surv.
  doi: 10.1145/1922649.1922653
– start-page: 2855
  year: 2012
  ident: B129
  article-title: “Discriminative virtual views for cross-view action recognition,”
– volume: 6975
  start-page: 415
  year: 2011
  ident: B207
  article-title: “Avec 2011 -the first international audio visual emotion challenge,”
  publication-title: Proc. International Audio/Visual Emotion Challenge and Workshop, Lecture Notes in Computer Science
  doi: 10.1007/978-3-642-24571-8_53
– start-page: 1481
  year: 2011
  ident: B199
  article-title: “Learning to share visual appearance for multiclass object detection,”
– volume: 47
  start-page: 1626
  year: 2014
  ident: B271
  article-title: Modeling local behavior for predicting social interactions towards human tracking
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2013.10.019
– start-page: 951
  year: 2009
  ident: B119
  article-title: “Learning to detect unseen object classes by between-class attribute transfer,”
– volume: 110
  start-page: 30
  year: 2014
  ident: B202
  article-title: Learning discriminative space-time action parts from weakly labelled videos
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-013-0662-8
– volume: 129
  start-page: 15
  year: 2014
  ident: B117
  article-title: Online action recognition using covariance of shape and motion
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2014.08.001
– start-page: 1
  year: 2008
  ident: B153
  article-title: “Action recognition with motion-appearance vocabulary forest,”
– start-page: 1302
  year: 2015
  ident: B282
  article-title: “Fast action proposals for human action detection and search,”
– volume: 27
  start-page: 1814
  year: 2009
  ident: B168
  article-title: Sparse B-spline polynomial descriptors for human activity recognition
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2009.05.010
– volume: 36
  start-page: 1775
  year: 2014a
  ident: B110
  article-title: Interactive phrases: semantic descriptions for human interaction recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2014.2303090
– volume: 24
  start-page: 971
  year: 2013
  ident: B191
  article-title: Recognizing 50 human action categories of web videos
  publication-title: Mach. Vis. Appl.
  doi: 10.1007/s00138-012-0450-4
– start-page: 1778
  year: 2009
  ident: B52
  article-title: “Describing objects by their attributes,”
– volume-title: Pattern Recognition and Machine Learning
  year: 2006
  ident: B17
– start-page: 2929
  year: 2009
  ident: B143
  article-title: “Actions in context,”
– start-page: 1110
  year: 2015
  ident: B44
  article-title: “Hierarchical recurrent neural network for skeleton based action recognition,”
– volume: 31
  start-page: 1775
  year: 2009
  ident: B75
  article-title: Observing human-object interactions: using spatial and functional compatibility for recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2009.83
– start-page: 109
  year: 2004
  ident: B50
  article-title: “Regularized multi-task learning,”
– start-page: 875
  year: 2014
  ident: B83
  article-title: “Talking heads: detecting humans and recognizing their interactions,”
– volume: 92
  start-page: 495
  year: 2004
  ident: B176
  article-title: Data fusion for visual tracking with particles
  publication-title: Proc. IEEE
  doi: 10.1109/JPROC.2003.823147
– volume: 16
  start-page: 2639
  year: 2004
  ident: B77
  article-title: Canonical correlation analysis: an overview with application to learning methods
  publication-title: Neural Comput.
  doi: 10.1162/0899766042321814
– volume: 35
  start-page: 1635
  year: 2013
  ident: B274
  article-title: Discovering motion primitives for unsupervised grouping and one-shot learning of human actions, gestures, and expressions
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.253
– volume: 15
  start-page: 1553
  year: 2013
  ident: B49
  article-title: Multimodal saliency and fusion for movie summarization based on aural, visual, and textual attention
  publication-title: IEEE Trans. Multimedia
  doi: 10.1109/TMM.2013.2267205
– volume: 108
  start-page: 116
  year: 2007
  ident: B92
  article-title: “Multimodal human-computer interaction: a survey,”
  publication-title: Computer Vision and Image Understanding
  doi: 10.1016/j.cviu.2006.10.019
– volume: 104
  start-page: 90
  year: 2006
  ident: B154
  article-title: A survey of advances in vision-based human motion capture and analysis
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2006.08.002
– start-page: 2361
  year: 2014
  ident: B35
  article-title: “Mixing body-part sequences for human pose estimation,”
– volume: 90
  start-page: 1151
  year: 2002
  ident: B47
  article-title: Background and foreground modeling using nonparametric kernel density for visual surveillance
  publication-title: Proc. IEEE
  doi: 10.1109/JPROC.2002.801448
– start-page: 2712
  year: 2013
  ident: B71
  article-title: “Youtube2text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition,”
– start-page: 1330
  year: 2012c
  ident: B257
  article-title: “Substructure and boundary modeling for continuous action recognition,”
– start-page: 288
  year: 2010
  ident: B266
  article-title: “Realistic human action recognition with audio context,”
– start-page: 514
  volume-title: Workshop on Video-Oriented Object and Event Classification, in Conjunction with ICCV
  year: 2009
  ident: B146
  article-title: “Trajectons: action recognition through the motion analysis of tracked features,”
– start-page: 1226
  year: 2012
  ident: B53
  article-title: “Social interactions: a first-person perspective,”
– start-page: 3169
  year: 2011a
  ident: B251
  article-title: “Action recognition by dense trajectories,”
– volume: 2
  start-page: 92
  year: 2011
  ident: B163
  article-title: Continuous prediction of spontaneous affect from multiple cues and modalities in valence-arousal space
  publication-title: IEEE Trans. Affective Comput.
  doi: 10.1109/T-AFFC.2011.9
– start-page: 1776
  year: 2014
  ident: B99
  article-title: “Decision level fusion of domain specific regions for facial action recognition,”
– volume: 31
  start-page: 137
  year: 2013
  ident: B148
  article-title: Tracking continuous emotional trends of participants during affective dyadic interactions using body language and speech information
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2012.08.018
– start-page: 104
  year: 2009
  ident: B147
  article-title: “Activity recognition using the velocity histories of tracked keypoints,”
– volume: 21
  start-page: 3416
  year: 2012
  ident: B281
  article-title: Human activity as a manifold-valued random process
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2012.2197008
– volume: 87
  start-page: 51
  year: 2012
  ident: B272
  article-title: Recognizing human actions using a new descriptor based on spatial-temporal interest points and weighted-output classifier
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2012.02.002
– start-page: 689
  year: 2011
  ident: B160
  article-title: “Multimodal deep learning,”
– volume: 119
  start-page: 27
  year: 2014a
  ident: B249
  article-title: Matching mixtures of curves for human action recognition
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2013.11.007
– volume: 34
  start-page: 1995
  year: 2013b
  ident: B33
  article-title: A survey of human motion analysis using depth imagery
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2013.02.006
– volume: 5
  start-page: 314
  year: 2014
  ident: B145
  article-title: Don’t classify ratings of affect; rank them!
  publication-title: IEEE Trans. Affective Comput.
  doi: 10.1109/TAFFC.2014.2352268
– volume: 47
  start-page: 3343
  year: 2014
  ident: B73
  article-title: A survey on still image based human action recognition
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2014.04.018
– volume: 7
  start-page: 530
  year: 2012a
  ident: B90
  article-title: Activity-based person identification using fuzzy representation and discriminant learning
  publication-title: IEEE Trans. Inform. Forensics Secur.
  doi: 10.1109/TIFS.2011.2175921
– volume: 151
  start-page: 554
  year: 2015
  ident: B68
  article-title: Multi-perspective and multi-modality joint representation and recognition model for 3D action recognition
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2014.06.085
– start-page: 612
  year: 2014
  ident: B180
  article-title: “Parsing videos of actions with segmental grammars,”
– start-page: 1100
  year: 2015
  ident: B187
  article-title: “Learning semantic relationships for better action retrieval in images,”
– start-page: 278
  year: 1995
  ident: B81
  article-title: “Random decision forests,”
– start-page: 2264
  year: 2015
  ident: B269
  article-title: “Can humans fly? Action understanding with multiple classes of actors,”
– start-page: 756
  year: 2014
  ident: B162
  article-title: “Multiple granularity analysis for fine-grained action detection,”
– start-page: 95
  year: 2014b
  ident: B250
  article-title: “Classifying behavioral attributes using conditional random fields,”
– start-page: 1395
  year: 2005
  ident: B18
  article-title: “Actions as space-time shapes,”
– start-page: 271
  year: 2007
  ident: B88
  article-title: “Human action recognition using distribution of oriented rectangular patches,”
– volume: 6
  start-page: 553
  year: 2012a
  ident: B84
  article-title: A local 3-D motion descriptor for multi-view human action recognition from 4-D spatio-temporal interest points
  publication-title: IEEE J. Sel. Top. Signal Process.
  doi: 10.1109/JSTSP.2012.2193556
– volume: 34
  start-page: 1549
  year: 2012b
  ident: B122
  article-title: Discriminative latent models for recognizing contextual group activities
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2011.228
– start-page: 155
  year: 2010
  ident: B261
  article-title: “A discriminative latent model of object classes and attributes,”
– start-page: 4777
  year: 2015
  ident: B174
  article-title: “Social saliency prediction,”
– volume: 38
  start-page: 2437
  year: 2005
  ident: B230
  article-title: A new method of feature fusion and its application in image recognition
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2004.12.013
– start-page: 2337
  year: 2014
  ident: B170
  article-title: “Multi-source deep learning for human pose estimation,”
– start-page: 3687
  year: 2013
  ident: B105
  article-title: “Deep learning for robust feature generation in audiovisual emotion recognition,”
– volume: 64
  start-page: 107
  year: 2005
  ident: B124
  article-title: On space-time interest points
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-005-1838-7
– volume: 104
  start-page: 232
  year: 2006
  ident: B192
  article-title: A general method for human activity recognition in video
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2006.07.006
– start-page: 2046
  year: 2010
  ident: B112
  article-title: “Learning a hierarchy of discriminative space-time neighborhood features for human action recognition,”
– start-page: 4657
  year: 2015
  ident: B213
  article-title: “Deeply learned attributes for crowded scene understanding,”
– volume: 116
  start-page: 396
  year: 2012
  ident: B27
  article-title: Selective spatio-temporal interest points
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2011.09.010
– start-page: 812
  year: 2014
  ident: B131
  article-title: “Discriminative hierarchical modeling of spatio-temporally composable human activities,”
– volume: 22
  start-page: 26
  year: 2007
  ident: B190
  article-title: The significance of letter position in word recognition
  publication-title: IEEE Aerosp. Electron. Syst. Mag.
  doi: 10.1109/MAES.2007.327521
– volume: 98
  start-page: 15
  year: 2012a
  ident: B218
  article-title: Loose-limbed people: estimating 3D human pose and motion using non-parametric belief propagation
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-011-0493-4
– start-page: 65
  year: 2005
  ident: B42
  article-title: “Behavior recognition via sparse spatio-temporal features,”
– volume: 25
  start-page: 12
  year: 2014
  ident: B234
  article-title: Pose-based human action recognition via sparse representation in dissimilarity space
  publication-title: J. Vis. Commun. Image Represent.
  doi: 10.1016/j.jvcir.2013.03.008
– volume: 46
  start-page: 1
  year: 2014
  ident: B194
  article-title: A survey on ontologies for human behavior recognition
  publication-title: ACM Comput. Surv.
  doi: 10.1145/2523819
– volume: 3
  start-page: 184
  year: 2012
  ident: B152
  article-title: Context-sensitive learning for enhanced audiovisual emotion classification
  publication-title: IEEE Trans. Affective Comput.
  doi: 10.1109/T-AFFC.2011.40
– start-page: 2666
  year: 2013a
  ident: B32
  article-title: “Event recognition in videos by learning from heterogeneous web sources,”
– start-page: 3153
  year: 2011
  ident: B167
  article-title: “A large-scale benchmark dataset for event recognition in surveillance video,”
– start-page: 494
  year: 2010
  ident: B89
  article-title: “Object, scene and actions: combining multiple features for human action recognition,”
– start-page: 3156
  year: 2015
  ident: B247
  article-title: “Show and tell: a neural image caption generator,”
– volume-title: A Mathematical Introduction to Robotic Manipulation
  year: 1994
  ident: B159
– start-page: 1
  year: 2007
  ident: B177
  article-title: “Fisher kernels on visual vocabularies for image categorization,”
– start-page: 536
  year: 2010
  ident: B204
  article-title: “Modeling the temporal extent of actions,”
– start-page: 428
  year: 2014
  ident: B51
  article-title: “Efficient pose-based action recognition,”
– volume: 98
  start-page: 15
  year: 2012b
  ident: B219
  article-title: Loose-limbed people: estimating 3D human pose and motion using non-parametric belief propagation
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-011-0493-4
– start-page: 282
  year: 2001
  ident: B118
  article-title: “Conditional random fields: probabilistic models for segmenting and labeling sequence data,”
– volume: 1
  start-page: 211
  year: 2001
  ident: B238
  article-title: Sparse Bayesian learning and the relevance vector machine
  publication-title: J. Mach. Learn. Res.
  doi: 10.1162/15324430152748236
– start-page: 2555
  year: 2013
  ident: B94
  article-title: “Better exploiting motion for better action recognition,”
– volume: 9
  start-page: 1396
  year: 2007
  ident: B203
  article-title: Audiovisual synchronization and fusion using canonical correlation analysis
  publication-title: IEEE Trans. Multimedia
  doi: 10.1109/TMM.2007.906583
– start-page: 3161
  year: 2011
  ident: B39
  article-title: “Abnormal detection using interaction energy potentials,”
– start-page: 1836
  year: 2015
  ident: B31
  article-title: “3D model-based continuous emotion recognition,”
– volume: 91
  start-page: 1370
  year: 2003
  ident: B173
  article-title: “Towards an affect-sensitive multimodal human-computer interaction,”
  publication-title: Proc. IEEE, Special Issue on Multimodal Human-Computer Interaction, Invited Paper
– start-page: 2696
  year: 2013
  ident: B232
  article-title: “Combining the right features for complex event recognition,”
– start-page: 1194
  year: 2012
  ident: B195
  article-title: “A database for fine grained activity detection of cooking activities,”
– start-page: 626
  year: 2014
  ident: B185
  article-title: “Real time action recognition using histograms of depth gradients and random decision forests,”
– volume: 4738
  start-page: 71
  year: 2007
  ident: B26
  article-title: “Recognising human emotions from body movement and gesture dynamics,”
  publication-title: Proc. Affective Computing and Intelligent Interaction, Lecture Notes in Computer Science
  doi: 10.1007/978-3-540-74889-2_7
– start-page: 1
  year: 2008
  ident: B244
  article-title: “Sparse probabilistic regression for activity-independent human pose inference,”
– start-page: 1
  year: 2009
  ident: B246
  article-title: “Canal9: a database of political debates for analysis of social interactions,”
SSID ssj0001584377
Score 2.5176814
SecondaryResourceType review_article
Snippet Recognizing human activities from video sequences or still images is a challenging task due to problems such as background clutter, partial occlusion, changes...
SourceID doaj
crossref
SourceType Open Website
Enrichment Source
Index Database
SubjectTerms Action recognition
action representation
Activity Categorization
Human activity recognition
review
Survey
Title A Review of Human Activity Recognition Methods
URI https://doaj.org/article/75b1cbb214b74173b6cdeeead5d3d1d3
Volume 2
WOSCitedRecordID wos000421362200017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2296-9144
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001584377
  issn: 2296-9144
  databaseCode: DOA
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2296-9144
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001584377
  issn: 2296-9144
  databaseCode: M~E
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQxQAD4inKSx5YGEzj2LHjsaBWDLRCCFC3KGc7EhJKUB-M_Hb8SKtMsLBkiJzI912ku3Puvg-ha8pKmwmwRLpkiPBKCgK0tATKjFcuPCQQ5rjfHuV0ms9m6qkj9eV7wiI9cARuIDOgGiClHFzwkwyENtY6-zPDDDWB59NlPZ1iKs4H55xJGf9LuipMDap5A753kvozlMSLr3fiUIeuP8SV8T7aaxNCPIwbOUBbtj5Eux2awCN0O8TxCB83FQ6n7nioo-oDfl43ADU1ngQ16MUxeh2PXu4fSKtzQLSzaElSkCVUEjhkhjsLDWNM2FTlMofEGs1SB5gwlFldGs3TtOSuzgAv12mF4iU7Qb26qe0pwi6-a2NEYgzTvEqY8lw3lcok2FQLpfposLa60C0JuNei-ChcMeBxKgJOhcepCDj10c3mic9IgPHL2jsP5Gadp64ON5xDi9ahxV8OPfuPl5yjHb8tPzRIxQXqLecre4m29dfyfTG_Ct-Ku06-Rz_nisXw
linkProvider Directory of Open Access Journals
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=A+Review+of+Human+Activity+Recognition+Methods&rft.jtitle=Frontiers+in+robotics+and+AI&rft.au=Vrigkas%2C+Michalis&rft.au=Nikou%2C+Christophoros&rft.au=Kakadiaris%2C+Ioannis+A.&rft.date=2015-11-16&rft.issn=2296-9144&rft.eissn=2296-9144&rft.volume=2&rft_id=info:doi/10.3389%2Ffrobt.2015.00028&rft.externalDBID=n%2Fa&rft.externalDocID=10_3389_frobt_2015_00028
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-9144&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-9144&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-9144&client=summon