Human Action Recognition by Semilatent Topic Models

We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words" representation, where each frame corresponds to a "word". Our models differ from previous latent topic models for visual recog...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on pattern analysis and machine intelligence Vol. 31; no. 10; pp. 1762 - 1774
Main Authors:	Yang Wang, Mori, G.
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.10.2009 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms bag-of-words Cluster Analysis Computer vision Decoupling event and activity understanding Hidden Markov models Human Human action recognition Human Activities - classification Humans Image analysis Image motion analysis Image recognition Image sequence analysis Image sequences Labels Locomotion - physiology Mathematical models Models, Biological Motion Movement - physiology Object recognition Pattern Recognition, Automated - methods probabilistic graphical models Recognition Studies Training video analysis Video sequences Visual
ISSN:	0162-8828, 1939-3539
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words" representation, where each frame corresponds to a "word". Our models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in our models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in our case. Our models have several advantages over other latent topic models used in visual recognition. First of all, the training is much easier due to the decoupling of the model parameters. Second, it alleviates the issue of how to choose the appropriate number of latent topics. Third, it achieves much better performance by utilizing the information provided by the class labels in the training set. We present action classification results on five different data sets. Our results are either comparable to, or significantly better than previously published results on these data sets.
AbstractList	First of all, the training is much easier due to the decoupling of the model parameters. We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words" representation, where each frame corresponds to a "word." Our models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in our models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in our case. Our models have several advantages over other latent topic models used in visual recognition. First of all, the training is much easier due to the decoupling of the model parameters. Second, it alleviates the issue of how to choose the appropriate number of latent topics. Third, it achieves much better performance by utilizing the information provided by the class labels in the training set. We present action classification results on five different data sets. Our results are either comparable to, or significantly better than previously published results on these data sets. We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words" representation, where each frame corresponds to a "word." Our models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in our models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in our case. Our models have several advantages over other latent topic models used in visual recognition. First of all, the training is much easier due to the decoupling of the model parameters. Second, it alleviates the issue of how to choose the appropriate number of latent topics. Third, it achieves much better performance by utilizing the information provided by the class labels in the training set. We present action classification results on five different data sets. Our results are either comparable to, or significantly better than previously published results on these data sets.We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words" representation, where each frame corresponds to a "word." Our models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in our models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in our case. Our models have several advantages over other latent topic models used in visual recognition. First of all, the training is much easier due to the decoupling of the model parameters. Second, it alleviates the issue of how to choose the appropriate number of latent topics. Third, it achieves much better performance by utilizing the information provided by the class labels in the training set. We present action classification results on five different data sets. Our results are either comparable to, or significantly better than previously published results on these data sets.
Author	Mori, G. Yang Wang
Author_xml	– sequence: 1 surname: Yang Wang fullname: Yang Wang organization: Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada – sequence: 2 givenname: G. surname: Mori fullname: Mori, G. organization: Sch. of Comput. Sci., Simon Fraser Univ., Burnaby, BC, Canada
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/19696448$$D View this record in MEDLINE/PubMed
BookMark	eNqF0U1v1DAQBmALFdFt4cgJCUU90FMWOx5_zHFVAa3UCgTL2XKcCXKVxEucHPrvyXZLD5UKp5nDMyPNvCfsaEgDMfZW8LUQHD9uv21urtYV57gG-YKtBEospZJ4xFZc6Kq0trLH7CTnW84FKC5fsWOBGjWAXTF5Ofd-KDZhimkovlNIv4Z439d3xQ_qY-cnGqZim3YxFDepoS6_Zi9b32V681BP2c_Pn7YXl-X11y9XF5vrMoA2U9lWViLWXipFRoaGG6MU1kYYQW0toIJAXjUhtAaC9FxVtQJtyQA02La1PGXnh727Mf2eKU-ujzlQ1_mB0pyd1WgBueaL_PBPqY1ChOr_UAKiAGkWePYE3qZ5HJZznVUGtJKVWND7BzTXPTVuN8bej3fu73sXIA8gjCnnkVoX4uT3751GHzsnuNuH6O5DdPsQHchlqnwy9bj4Gf_u4CMRPVowVoEB-QeVkqOe
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1155_2018_6598025 crossref_primary_10_1016_j_patcog_2010_06_018 crossref_primary_10_1016_j_neucom_2012_03_003 crossref_primary_10_1109_TIP_2019_2922100 crossref_primary_10_1109_TGRS_2019_2939001 crossref_primary_10_1109_TCSVT_2019_2890829 crossref_primary_10_1109_TPAMI_2013_128 crossref_primary_10_1587_transinf_E96_D_1783 crossref_primary_10_1016_j_patrec_2011_03_006 crossref_primary_10_1016_j_cviu_2011_09_006 crossref_primary_10_1016_j_cviu_2011_09_007 crossref_primary_10_1177_0165551519877049 crossref_primary_10_1016_j_neucom_2011_10_033 crossref_primary_10_1061__ASCE_CP_1943_5487_0000237 crossref_primary_10_1016_j_cviu_2015_02_012 crossref_primary_10_1016_j_asoc_2017_10_021 crossref_primary_10_1109_TNNLS_2020_3027539 crossref_primary_10_1016_j_pmcj_2014_05_007 crossref_primary_10_1109_TCSVT_2018_2816960 crossref_primary_10_1155_2013_506752 crossref_primary_10_1016_j_eswa_2018_08_029 crossref_primary_10_1049_iet_cvi_2012_0121 crossref_primary_10_2478_jee_2019_0077 crossref_primary_10_1016_j_patrec_2014_07_014 crossref_primary_10_1155_2014_810185 crossref_primary_10_3141_2387_02 crossref_primary_10_1016_j_patcog_2012_10_004 crossref_primary_10_1109_TCDS_2016_2577044 crossref_primary_10_1109_TCSVT_2012_2199390 crossref_primary_10_1016_j_patrec_2012_01_007 crossref_primary_10_1007_s10115_017_1095_4 crossref_primary_10_1080_01691864_2019_1627243 crossref_primary_10_1109_TPAMI_2014_2313122 crossref_primary_10_1016_j_sigpro_2025_110028 crossref_primary_10_1007_s11263_012_0596_6 crossref_primary_10_1016_j_aei_2013_09_001 crossref_primary_10_1109_TPAMI_2014_2339851 crossref_primary_10_1109_ACCESS_2016_2614525 crossref_primary_10_1016_j_aeue_2015_12_016 crossref_primary_10_1007_s11276_019_02234_w crossref_primary_10_1007_s11432_013_4794_9 crossref_primary_10_1016_j_imavis_2009_11_014 crossref_primary_10_3390_su9040497 crossref_primary_10_1007_s11042_012_0993_4 crossref_primary_10_7717_peerj_cs_923 crossref_primary_10_1109_TPAMI_2011_38 crossref_primary_10_1016_j_patrec_2014_07_011 crossref_primary_10_1016_j_ins_2016_06_016 crossref_primary_10_1016_j_neucom_2013_01_012 crossref_primary_10_1007_s11042_014_1924_3 crossref_primary_10_1007_s11063_018_9852_2 crossref_primary_10_1109_TII_2011_2172452 crossref_primary_10_1007_s00138_013_0589_7 crossref_primary_10_1007_s11263_016_0896_3 crossref_primary_10_1109_TPAMI_2015_2414422 crossref_primary_10_1016_j_patrec_2012_10_019 crossref_primary_10_1111_coin_12429 crossref_primary_10_1007_s10462_020_09904_8 crossref_primary_10_1162_neco_a_01148 crossref_primary_10_3141_2393_09 crossref_primary_10_1007_s00530_019_00629_5 crossref_primary_10_1049_iet_cvi_2015_0420 crossref_primary_10_1007_s11263_015_0833_x crossref_primary_10_1049_iet_its_2014_0257 crossref_primary_10_1109_TPAMI_2011_253 crossref_primary_10_1016_j_robot_2015_11_013 crossref_primary_10_1007_s11042_016_3630_9 crossref_primary_10_1016_j_patrec_2013_01_008 crossref_primary_10_1016_j_neucom_2012_12_077 crossref_primary_10_1007_s00138_016_0768_4 crossref_primary_10_3390_electronics8101169 crossref_primary_10_1007_s11042_016_4197_1 crossref_primary_10_1080_01691864_2016_1172506 crossref_primary_10_1109_TIP_2013_2292550 crossref_primary_10_1007_s11263_011_0510_7 crossref_primary_10_1016_j_neucom_2012_06_011 crossref_primary_10_1155_2014_723213 crossref_primary_10_1109_TMM_2014_2326734 crossref_primary_10_1016_j_inffus_2014_01_002 crossref_primary_10_1109_TCSVT_2014_2382984 crossref_primary_10_1016_j_patcog_2012_09_027 crossref_primary_10_1016_j_patcog_2016_07_024 crossref_primary_10_1016_j_neucom_2012_02_002 crossref_primary_10_1007_s00521_022_07937_4 crossref_primary_10_1007_s00371_011_0652_1 crossref_primary_10_1145_2340416_2340419 crossref_primary_10_1016_j_knosys_2021_107051 crossref_primary_10_1049_iet_cvi_2013_0306 crossref_primary_10_1109_TPAMI_2011_157 crossref_primary_10_1007_s11042_012_1084_2 crossref_primary_10_1016_j_patcog_2012_03_010 crossref_primary_10_1016_j_patcog_2017_07_013 crossref_primary_10_1007_s11042_017_5588_7 crossref_primary_10_1109_TFUZZ_2014_2370678 crossref_primary_10_1016_j_imavis_2011_12_006 crossref_primary_10_1016_j_neucom_2012_09_008 crossref_primary_10_1109_JIOT_2020_2985082 crossref_primary_10_1080_08839514_2012_629540 crossref_primary_10_1007_s00371_018_1560_4 crossref_primary_10_1016_j_sigpro_2012_07_017 crossref_primary_10_1016_j_eswa_2015_04_039 crossref_primary_10_1016_j_image_2020_115802 crossref_primary_10_1016_j_trc_2013_04_007 crossref_primary_10_1016_j_eswa_2017_02_026 crossref_primary_10_1109_TGRS_2012_2205579 crossref_primary_10_5402_2012_376804 crossref_primary_10_1016_j_patcog_2015_09_017 crossref_primary_10_1177_0278364917690592 crossref_primary_10_1109_TIM_2019_2925410 crossref_primary_10_1016_j_patcog_2012_04_024 crossref_primary_10_1007_s10462_011_9232_z crossref_primary_10_1016_j_patcog_2012_10_016 crossref_primary_10_1145_2597627 crossref_primary_10_1155_2013_816836 crossref_primary_10_1080_01621459_2017_1285773 crossref_primary_10_1007_s00530_015_0474_5 crossref_primary_10_1109_TCSVT_2011_2135290 crossref_primary_10_1016_j_patcog_2017_06_035 crossref_primary_10_1007_s11042_017_4711_0 crossref_primary_10_3390_rs8030231 crossref_primary_10_1016_j_imavis_2012_08_006 crossref_primary_10_3389_frobt_2020_503452 crossref_primary_10_1155_2014_238234 crossref_primary_10_1109_TFUZZ_2013_2242894 crossref_primary_10_1371_journal_pone_0124640 crossref_primary_10_1016_j_aeue_2019_05_023
Cites_doi	10.1109/CVPR.2008.4587756 10.1007/s11263-007-0122-4 10.1109/CVPR.2006.326 10.1109/34.868681 10.5244/C.20.127 10.1109/ICCV.2007.4408988 10.1007/s11263-006-9794-4 10.1007/s11263-006-4329-6 10.1109/ICCV.2007.4409049 10.1109/34.910878 10.1109/CVPR.2008.4587727 10.1093/bioinformatics/bti515 10.1109/ICCV.2007.4409105 10.1023/A:1007975200487 10.1109/ICCV.2003.1238378 10.1007/11744085_40 10.1007/978-3-540-75703-0_17 10.1109/CVPR.2007.383074 10.1109/34.643892 10.1109/CVPR.2005.16 10.1109/CVPR.2007.383332 10.1109/CVPR.2008.4587735 10.1016/j.cviu.2004.02.004 10.1109/ICCV.2005.239 10.1109/TPAMI.2006.79 10.1109/CVPR.2005.328 10.5555/944919.944937 10.1109/CVPR.2008.4587723 10.1109/ICCV.2005.10 10.1109/CVPR.2006.132 10.1109/CVPR.2007.383132 10.1109/CVPR.2008.4587730 10.1109/ICCV.2005.59 10.1109/ICCV.2005.142 10.1109/ICCV.2003.1238420 10.1109/CVPR.1992.223161 10.1109/VSPETS.2005.1570899 10.1109/TDPVT.2002.1024148 10.1109/ICCV.2005.85 10.1109/ICCV.2005.77 10.1109/CVPR.2008.4587721 10.1109/ICCV.2005.28 10.7551/mitpress/7503.003.0026 10.1109/ICPR.2004.1334462 10.1109/CVPR.2007.383168 10.1145/312624.312649 10.1016/j.imavis.2008.02.008 10.1007/3-540-47969-4_42
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2009
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2009
DBID	97E RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7SC 7SP 8FD JQ2 L7M L~C L~D F28 FR3 7X8
DOI	10.1109/TPAMI.2009.43
DatabaseName	IEEE Xplore (IEEE) 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 ANTE: Abstracts in New Technology & Engineering Engineering Research Database 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 Engineering Research Database ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic
DatabaseTitleList	Technology Research Database MEDLINE Technology Research Database MEDLINE - Academic Technology Research Database
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1939-3539
EndPage	1774
ExternalDocumentID	2295178451 19696448 10_1109_TPAMI_2009_43 4785474
Genre	orig-research Research Support, Non-U.S. Gov't Journal Article
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E 9M8 AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETEA AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P FA8 HZ~ H~9 IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNI RNS RXW RZB TAE TN5 UHB VH1 XJT ~02 AAYXX CITATION CGR CUY CVF ECM EIF NPM RIG 7SC 7SP 8FD JQ2 L7M L~C L~D F28 FR3 7X8
ID	FETCH-LOGICAL-c467t-f28399ba355e73cd077559b7171efb1424cea5dccf74c3a052b5468e744d9ffb3
IEDL.DBID	RIE
ISICitedReferencesCount	217
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000268996500004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828
IngestDate	Sat Sep 27 19:38:57 EDT 2025 Thu Oct 02 18:04:08 EDT 2025 Sun Nov 09 10:25:22 EST 2025 Mon Jun 30 06:10:00 EDT 2025 Mon Jul 21 06:07:25 EDT 2025 Sat Nov 29 08:12:47 EST 2025 Tue Nov 18 22:11:23 EST 2025 Tue Aug 26 16:47:39 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	10
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c467t-f28399ba355e73cd077559b7171efb1424cea5dccf74c3a052b5468e744d9ffb3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Article-2 ObjectType-Feature-1 content type line 23
PMID	19696448
PQID	857465321
PQPubID	23500
PageCount	13
ParticipantIDs	proquest_miscellaneous_67599420 proquest_miscellaneous_34991437 ieee_primary_4785474 pubmed_primary_19696448 crossref_citationtrail_10_1109_TPAMI_2009_43 proquest_miscellaneous_869849060 proquest_journals_857465321 crossref_primary_10_1109_TPAMI_2009_43
PublicationCentury	2000
PublicationDate	2009-10-01
PublicationDateYYYYMMDD	2009-10-01
PublicationDate_xml	– month: 10 year: 2009 text: 2009-10-01 day: 01
PublicationDecade	2000
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	2009
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	ref12 ref15 ref14 ref53 ref52 ref11 ref10 ref54 ref17 ref16 ref19 ref18 Lucas (ref49) ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref8 ref7 ref9 Huang (ref51) 2009 ref4 ref6 ref5 ref40 Blei (ref22) 2008; 20 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 Little (ref3) 1998; 1 Blei (ref13) 2006; 18 ref24 ref23 ref26 ref25 ref20 ref21 ref28 ref27 ref29 Minka (ref50) 2000
References_xml	– ident: ref46 doi: 10.1109/CVPR.2008.4587756 – ident: ref47 doi: 10.1007/s11263-007-0122-4 – ident: ref18 doi: 10.1109/CVPR.2006.326 – ident: ref1 doi: 10.1109/34.868681 – ident: ref20 doi: 10.5244/C.20.127 – ident: ref29 doi: 10.1109/ICCV.2007.4408988 – ident: ref54 doi: 10.1007/s11263-006-9794-4 – ident: ref11 doi: 10.1007/s11263-006-4329-6 – ident: ref42 doi: 10.1109/ICCV.2007.4409049 – year: 2009 ident: ref51 article-title: Fitting a Hierarchical Logistic Normal Distribution – ident: ref27 doi: 10.1109/34.910878 – ident: ref31 doi: 10.1109/CVPR.2008.4587727 – ident: ref23 doi: 10.1093/bioinformatics/bti515 – ident: ref45 doi: 10.1109/ICCV.2007.4409105 – ident: ref4 doi: 10.1023/A:1007975200487 – ident: ref38 doi: 10.1109/ICCV.2003.1238378 – ident: ref15 doi: 10.1007/11744085_40 – ident: ref24 doi: 10.1007/978-3-540-75703-0_17 – ident: ref35 doi: 10.1109/CVPR.2007.383074 – volume: 20 volume-title: Advances in Neural Information Processing Systems year: 2008 ident: ref22 article-title: Supervised Topic Models – ident: ref10 doi: 10.1109/34.643892 – ident: ref16 doi: 10.1109/CVPR.2005.16 – ident: ref48 doi: 10.1109/CVPR.2007.383332 – ident: ref53 doi: 10.1109/CVPR.2008.4587735 – ident: ref33 doi: 10.1016/j.cviu.2004.02.004 – ident: ref7 doi: 10.1109/ICCV.2005.239 – ident: ref6 doi: 10.1109/TPAMI.2006.79 – ident: ref28 doi: 10.1109/CVPR.2005.328 – ident: ref12 doi: 10.5555/944919.944937 – ident: ref43 doi: 10.1109/CVPR.2008.4587723 – ident: ref8 doi: 10.1109/ICCV.2005.10 – ident: ref37 doi: 10.1109/CVPR.2006.132 – ident: ref44 doi: 10.1109/CVPR.2007.383132 – ident: ref30 doi: 10.1109/CVPR.2008.4587730 – ident: ref36 doi: 10.1109/ICCV.2005.59 – ident: ref17 doi: 10.1109/ICCV.2005.142 – volume: 1 start-page: 1 issue: 2 year: 1998 ident: ref3 article-title: Recognizing People by Their Gait: The Shape of Motion publication-title: Videre – volume-title: technical report, Massachusetts Inst. of Technology year: 2000 ident: ref50 article-title: Estimating a Dirichlet Distribution – ident: ref2 doi: 10.1109/ICCV.2003.1238420 – ident: ref9 doi: 10.1109/CVPR.1992.223161 – ident: ref40 doi: 10.1109/VSPETS.2005.1570899 – ident: ref32 doi: 10.1109/TDPVT.2002.1024148 – ident: ref41 doi: 10.1109/ICCV.2005.85 – start-page: 121 volume-title: Proc. Defense Advanced Research Projects Agency Image Understanding Workshop ident: ref49 article-title: An Iterative Image Registration Technique with an Application to Stereo Vision – ident: ref19 doi: 10.1109/ICCV.2005.77 – ident: ref26 doi: 10.1109/CVPR.2008.4587721 – volume: 18 volume-title: Advances in Neural Information Processing Systems year: 2006 ident: ref13 article-title: Correlated Topic Models – ident: ref52 doi: 10.1109/ICCV.2005.28 – ident: ref21 doi: 10.7551/mitpress/7503.003.0026 – ident: ref39 doi: 10.1109/ICPR.2004.1334462 – ident: ref34 doi: 10.1109/CVPR.2007.383168 – ident: ref14 doi: 10.1145/312624.312649 – ident: ref25 doi: 10.1016/j.imavis.2008.02.008 – ident: ref5 doi: 10.1007/3-540-47969-4_42
SSID	ssj0014503
Score	2.466051
Snippet	We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel "bag-of-words"... First of all, the training is much easier due to the decoupling of the model parameters.
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1762
SubjectTerms	Algorithms bag-of-words Cluster Analysis Computer vision Decoupling event and activity understanding Hidden Markov models Human Human action recognition Human Activities - classification Humans Image analysis Image motion analysis Image recognition Image sequence analysis Image sequences Labels Locomotion - physiology Mathematical models Models, Biological Motion Movement - physiology Object recognition Pattern Recognition, Automated - methods probabilistic graphical models Recognition Studies Training video analysis Video sequences Visual
Title	Human Action Recognition by Semilatent Topic Models
URI	https://ieeexplore.ieee.org/document/4785474 https://www.ncbi.nlm.nih.gov/pubmed/19696448 https://www.proquest.com/docview/857465321 https://www.proquest.com/docview/34991437 https://www.proquest.com/docview/67599420 https://www.proquest.com/docview/869849060
Volume	31
WOSCitedRecordID	wos000268996500004&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1939-3539 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9swDCWSYof2sG792LJsrQ5FT3Hr2JQlHYNhwXZYUbQpkJthyzQQIHWKJhnQf19KdpwelkNvAsyDLJISKVLvAVxEyDuvHFLg4KMCzDIKTFmWQZFENk8KVcqGbELd3Ojp1Nx2YNC-hSEi33xGV27oa_nFwq7dVdk1Ki1RYRe6SiX1W622YoDSsyBzBMMezmnEFk_zenI7-vunhqZEz5vjEGHQMf68OYo8t8ruMNMfN-PD9030E3xswkoxqu3gM3SoOoLDDWWDaDz4CA7e4A8eQ-yv8MXIv20Qd5teIh7nL-KeHmdzjkSrlZgsnmZWONq0-fIEHsa_Jj9_Bw2LQmB5E1wFJQcQxuQZBxakYls4zDtpck7jhlS6KyDWViYLa0uFNs5CGeUSE00KsWC15fEp7FWLir6CkGFCBetQJpihLUhLHcaKSk5mdZgP4x4MNgua2gZi3DFdzFOfaoQm9apw1JcmRRa_bMWfamyNXYLHbo1boWZ5e9DfaCttPG-ZaqkcZFw07MF5-5VdxtVBsooW62Uac5bHYaLaLcFZlDEYhT0QOyR0YjSaMGGRL7WdbH-hMa9v_591H_Z9Rco3BH6HvdXzmn7AB_tvNVs-n7FpT_WZN-1X2l7zkQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB3BthJwAAoUFmjxoeqJQDYZx_ZxVYFAhRWiW4lblDgTaaVtFu1Hpf57xk42cGAPvVnKHBzPjD3jGb8H8C1C3nlljwIHHxVgllFgyrIMiiSyeVKoUjZkE2ow0E9P5mENztu3METkm8_owg19Lb-Y2IW7KrtEpSUqXIcPEjEK69dabc0ApedB5hiGfZwTiVdEzcvhQ__-tganRM-c4zBh0HH-vDmMPLvK6kDTHzjXO_831V3YbgJL0a8t4ROsUbUHO0vSBtH48B5svUEg3IfYX-KLvn_dIB6X3UQ8zv-JX_RnNOZYtJqL4eR5ZIUjThvPDuD39dXwx03Q8CgElrfBeVByCGFMnnFoQSq2hUO9kybnRK5HpbsEYn1lsrC2VGjjLJRRLjHRpBALVlwef4ZONanoCIQMEypYizLBDG1BWuowVlRyOqvDvBd34Xy5oKltQMYd18U49clGaFKvCkd-aVJk8e-t-HONrrFKcN-tcSvULG8XTpbaShvfm6VaKgcaF_W6cNZ-ZadxlZCsoslilsac53GgqFZLcB5lDNtYF8QKCZ0YjSZMWOSwtpPXX2jM6_j9WZ_Bxs3w_i69ux38PIFNX5_y7YGn0JlPF_QFPtq_89Fs-tUb-Avr2fXw
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+by+Semilatent+Topic+Models&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Wang%2C+Yang&rft.au=Mori%2C+G&rft.date=2009-10-01&rft.issn=0162-8828&rft.volume=31&rft.issue=10&rft.spage=1762&rft.epage=1774&rft_id=info:doi/10.1109%2FTPAMI.2009.43&rft.externalDBID=NO_FULL_TEXT
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