Temporal Modeling on Multi-Temporal-Scale Spatiotemporal Atoms for Action Recognition

As an important branch of video analysis, human action recognition has attracted extensive research attention in computer vision and artificial intelligence communities. In this paper, we propose to model the temporal evolution of multi-temporal-scale atoms for action recognition. An action can be c...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Applied sciences Ročník 8; číslo 10; s. 1835
Hlavní autori: Yao, Guangle, Lei, Tao, Liu, Xianyuan, Jiang, Ping
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Basel MDPI AG 01.10.2018
Predmet:
ISSN:2076-3417, 2076-3417
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract As an important branch of video analysis, human action recognition has attracted extensive research attention in computer vision and artificial intelligence communities. In this paper, we propose to model the temporal evolution of multi-temporal-scale atoms for action recognition. An action can be considered as a temporal sequence of action units. These action units which we referred to as action atoms, can capture the key semantic and characteristic spatiotemporal features of actions in different temporal scales. We first investigate Res3D, a powerful 3D CNN architecture and create the variants of Res3D for different temporal scale. In each temporal scale, we design some practices to transfer the knowledge learned from RGB to optical flow (OF) and build RGB and OF streams to extract deep spatiotemporal information using Res3D. Then we propose an unsupervised method to mine action atoms in the deep spatiotemporal space. Finally, we use long short-term memory (LSTM) to model the temporal evolution of atoms for action recognition. The experimental results show that our proposed multi-temporal-scale spatiotemporal atoms modeling method achieves recognition performance comparable to that of state-of-the-art methods on two challenging action recognition datasets: UCF101 and HMDB51.
AbstractList As an important branch of video analysis, human action recognition has attracted extensive research attention in computer vision and artificial intelligence communities. In this paper, we propose to model the temporal evolution of multi-temporal-scale atoms for action recognition. An action can be considered as a temporal sequence of action units. These action units which we referred to as action atoms, can capture the key semantic and characteristic spatiotemporal features of actions in different temporal scales. We first investigate Res3D, a powerful 3D CNN architecture and create the variants of Res3D for different temporal scale. In each temporal scale, we design some practices to transfer the knowledge learned from RGB to optical flow (OF) and build RGB and OF streams to extract deep spatiotemporal information using Res3D. Then we propose an unsupervised method to mine action atoms in the deep spatiotemporal space. Finally, we use long short-term memory (LSTM) to model the temporal evolution of atoms for action recognition. The experimental results show that our proposed multi-temporal-scale spatiotemporal atoms modeling method achieves recognition performance comparable to that of state-of-the-art methods on two challenging action recognition datasets: UCF101 and HMDB51.
Author Lei, Tao
Liu, Xianyuan
Jiang, Ping
Yao, Guangle
Author_xml – sequence: 1
  givenname: Guangle
  orcidid: 0000-0002-3030-1598
  surname: Yao
  fullname: Yao, Guangle
– sequence: 2
  givenname: Tao
  orcidid: 0000-0002-0900-1582
  surname: Lei
  fullname: Lei, Tao
– sequence: 3
  givenname: Xianyuan
  orcidid: 0000-0002-3084-519X
  surname: Liu
  fullname: Liu, Xianyuan
– sequence: 4
  givenname: Ping
  surname: Jiang
  fullname: Jiang, Ping
BookMark eNpNUctqwzAQFCWFpmku_QJBbwW3Wsm2pGMIfQQSCk1yFpIsBQfHcmXn0L-v3TRt57A7zA6zC3uNRnWoHUK3QB4Yk-RRN40AAoJlF2hMCc8TlgIf_eNXaNq2e9JDAuu9Y7TduEMToq7wKhSuKusdDjVeHauuTM6jZG115fC60V0ZurN_1oVDi32IeGZ7vcbvzoZdXQ78Bl16XbVu-tMnaPv8tJm_Jsu3l8V8tkwso6RLpDEk1VpITzKTebAF9-B7QNqXQvhceG84sy7lggMYLWjhZMYNcG81ZRO0OOUWQe9VE8uDjp8q6FJ9CyHulI5daSunaJoTyoBwSUla0FzyzDENjpKcGV6IPuvulNXE8HF0baf24Rjr_nxFaUZACpENG-9PLhtD20bnf7cCUcMX1N8X2BfdD3uY
Cites_doi 10.1109/ICCV.2011.6126543
10.1109/TPAMI.2012.231
10.1109/34.868684
10.1162/neco.1997.9.8.1735
10.1109/ICCV.2013.441
10.1109/CVPR.2014.81
10.1109/TPAMI.2016.2572683
10.1007/978-3-319-10590-1_53
10.1109/TPAMI.2016.2599174
10.1109/TPAMI.2012.59
10.1109/CVPR.2015.7298594
10.1109/CVPR.2017.227
10.1109/CVPR.2017.604
10.1109/ICASSP.2013.6638947
10.1109/TPAMI.2010.31
10.1109/CVPR.2014.223
10.1109/CVPR.2015.7298878
10.1109/TPAMI.2010.214
10.1109/ICCV.2017.590
10.1007/s11042-016-3768-5
10.1145/1463563.1463590
10.1016/j.cviu.2016.03.013
10.1109/5.726791
10.1109/TCSVT.2017.2682196
10.7551/mitpress/3206.001.0001
10.1109/WACV.2016.7477589
10.1007/s11263-015-0816-y
10.5244/C.28.6
10.1109/TPAMI.2017.2712608
10.1109/CVPR.2007.383074
10.1109/CVPR.2015.7299059
10.1007/978-3-642-25446-8_4
10.1007/978-3-642-15822-3_20
10.1109/CVPR.2013.350
ContentType Journal Article
Copyright 2018. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2018. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
ABUWG
AFKRA
AZQEC
BENPR
CCPQU
DWQXO
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
DOA
DOI 10.3390/app8101835
DatabaseName CrossRef
ProQuest Central (Alumni Edition)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
ProQuest One Community College
ProQuest Central Korea
ProQuest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Academic UKI Edition
ProQuest Central Korea
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList
CrossRef
Publicly Available Content Database
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Sciences (General)
EISSN 2076-3417
ExternalDocumentID oai_doaj_org_article_2460231079204d26975e3a1e2063b7d8
10_3390_app8101835
GeographicLocations United States--US
Las Vegas Nevada
China
GeographicLocations_xml – name: Las Vegas Nevada
– name: China
– name: United States--US
GroupedDBID .4S
2XV
5VS
7XC
8CJ
8FE
8FG
8FH
AADQD
AAFWJ
AAYXX
ADBBV
ADMLS
AFFHD
AFKRA
AFPKN
AFZYC
ALMA_UNASSIGNED_HOLDINGS
APEBS
ARCSS
BCNDV
BENPR
CCPQU
CITATION
CZ9
D1I
D1J
D1K
GROUPED_DOAJ
IAO
IGS
IPNFZ
ITC
K6-
K6V
KC.
KQ8
L6V
LK5
LK8
M7R
MODMG
M~E
OK1
P62
PHGZM
PHGZT
PIMPY
PROAC
RIG
TUS
ABUWG
AZQEC
DWQXO
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c320t-9bb04aa89f05b5f1cd7f1ffff14fffd8f68ffb73ce478711ba82de957b17fca23
IEDL.DBID BENPR
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000448653700130&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2076-3417
IngestDate Tue Oct 14 19:04:11 EDT 2025
Mon Oct 20 02:53:33 EDT 2025
Sat Nov 29 07:10:24 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 10
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c320t-9bb04aa89f05b5f1cd7f1ffff14fffd8f68ffb73ce478711ba82de957b17fca23
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-3084-519X
0000-0002-3030-1598
0000-0002-0900-1582
OpenAccessLink https://www.proquest.com/docview/2250198852?pq-origsite=%requestingapplication%
PQID 2250198852
PQPubID 2032433
ParticipantIDs doaj_primary_oai_doaj_org_article_2460231079204d26975e3a1e2063b7d8
proquest_journals_2250198852
crossref_primary_10_3390_app8101835
PublicationCentury 2000
PublicationDate 2018-10-01
PublicationDateYYYYMMDD 2018-10-01
PublicationDate_xml – month: 10
  year: 2018
  text: 2018-10-01
  day: 01
PublicationDecade 2010
PublicationPlace Basel
PublicationPlace_xml – name: Basel
PublicationTitle Applied sciences
PublicationYear 2018
Publisher MDPI AG
Publisher_xml – name: MDPI AG
References ref_50
ref_14
ref_58
ref_13
ref_57
ref_12
ref_56
ref_55
ref_10
ref_54
Russakovsky (ref_32) 2015; 115
Shelhamer (ref_5) 2017; 39
ref_52
ref_51
ref_19
ref_16
ref_15
LeCun (ref_1) 1998; 86
Zhao (ref_53) 2017; 28
ref_25
ref_24
ref_23
ref_21
Varol (ref_20) 2018; 40
Yu (ref_17) 2017; 76
ref_29
ref_28
Hochreiter (ref_18) 1997; 9
Oliver (ref_26) 2000; 22
ref_35
ref_34
ref_33
ref_31
ref_30
Liu (ref_36) 2010; 32
ref_39
ref_38
ref_37
Donahue (ref_22) 2017; 39
Farabet (ref_4) 2013; 35
Peng (ref_48) 2016; 150
Ji (ref_11) 2013; 35
ref_47
ref_46
ref_45
ref_44
ref_43
ref_42
ref_41
ref_40
ref_3
ref_2
Wang (ref_27) 2011; 33
ref_49
ref_9
ref_8
Maaten (ref_59) 2008; 9
ref_7
ref_6
References_xml – ident: ref_9
– ident: ref_34
  doi: 10.1109/ICCV.2011.6126543
– ident: ref_55
– volume: 35
  start-page: 1915
  year: 2013
  ident: ref_4
  article-title: Learning hierarchical features for scene labeling
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.231
– volume: 22
  start-page: 255
  year: 2000
  ident: ref_26
  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: 9
  start-page: 1735
  year: 1997
  ident: ref_18
  article-title: Long short-term memory
  publication-title: Neural Comput.
  doi: 10.1162/neco.1997.9.8.1735
– ident: ref_35
– ident: ref_47
  doi: 10.1109/ICCV.2013.441
– ident: ref_23
– ident: ref_3
  doi: 10.1109/CVPR.2014.81
– ident: ref_58
– ident: ref_8
– ident: ref_52
– volume: 39
  start-page: 640
  year: 2017
  ident: ref_5
  article-title: Fully convolutional networks for semantic segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2572683
– ident: ref_13
– ident: ref_29
  doi: 10.1007/978-3-319-10590-1_53
– ident: ref_45
– volume: 39
  start-page: 677
  year: 2017
  ident: ref_22
  article-title: Long-term recurrent convolutional networks for visual recognition and description
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2599174
– volume: 35
  start-page: 221
  year: 2013
  ident: ref_11
  article-title: 3D convolutional neural networks for human action recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.59
– ident: ref_31
  doi: 10.1109/CVPR.2015.7298594
– ident: ref_16
  doi: 10.1109/CVPR.2017.227
– ident: ref_7
– ident: ref_24
– ident: ref_51
  doi: 10.1109/CVPR.2017.604
– ident: ref_42
  doi: 10.1109/ICASSP.2013.6638947
– volume: 32
  start-page: 2178
  year: 2010
  ident: ref_36
  article-title: A hierarchical visual model for video object summarization
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2010.31
– ident: ref_6
  doi: 10.1109/CVPR.2014.223
– ident: ref_21
  doi: 10.1109/CVPR.2015.7298878
– volume: 33
  start-page: 1310
  year: 2011
  ident: ref_27
  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
– ident: ref_56
  doi: 10.1109/ICCV.2017.590
– ident: ref_40
– ident: ref_37
– ident: ref_14
– volume: 76
  start-page: 13367
  year: 2017
  ident: ref_17
  article-title: Stratified pooling based deep convolutional neural networks for human action recognition
  publication-title: Multimedia Tools Appl.
  doi: 10.1007/s11042-016-3768-5
– ident: ref_38
  doi: 10.1145/1463563.1463590
– volume: 150
  start-page: 109
  year: 2016
  ident: ref_48
  article-title: Bag of visual words and fusion methods for action recognition
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2016.03.013
– volume: 86
  start-page: 2278
  year: 1998
  ident: ref_1
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proc. IEEE
  doi: 10.1109/5.726791
– volume: 28
  start-page: 1839
  year: 2017
  ident: ref_53
  article-title: Pooling the convolutional layers in deep ConvNets for video action recognition
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2017.2682196
– ident: ref_41
  doi: 10.7551/mitpress/3206.001.0001
– ident: ref_54
  doi: 10.1109/WACV.2016.7477589
– ident: ref_25
– ident: ref_50
– ident: ref_33
– ident: ref_2
– volume: 115
  start-page: 211
  year: 2015
  ident: ref_32
  article-title: ImageNet large scale visual recognition challenge
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-015-0816-y
– ident: ref_46
– ident: ref_12
– ident: ref_30
  doi: 10.5244/C.28.6
– volume: 40
  start-page: 1510
  year: 2018
  ident: ref_20
  article-title: Long-term temporal convolutions for action recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2017.2712608
– ident: ref_15
– ident: ref_28
  doi: 10.1109/CVPR.2007.383074
– ident: ref_19
– ident: ref_43
– volume: 9
  start-page: 2579
  year: 2008
  ident: ref_59
  article-title: Visualizing data using t-sne
  publication-title: J. Mach. Learn. Res.
– ident: ref_49
  doi: 10.1109/CVPR.2015.7299059
– ident: ref_10
  doi: 10.1007/978-3-642-25446-8_4
– ident: ref_44
  doi: 10.1007/978-3-642-15822-3_20
– ident: ref_57
– ident: ref_39
  doi: 10.1109/CVPR.2013.350
SSID ssj0000913810
Score 2.0881546
Snippet As an important branch of video analysis, human action recognition has attracted extensive research attention in computer vision and artificial intelligence...
SourceID doaj
proquest
crossref
SourceType Open Website
Aggregation Database
Index Database
StartPage 1835
SubjectTerms action atom
action recognition
Classification
convolutional neural network
International conferences
long short-term memory
Methods
Neural networks
Pattern recognition
Semantics
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrZ3NS8MwFMCDDA96EDcVp1MCetBDsPlokxynODwNcRvsVpImAUE7Wat_v0nauoEHL_bQQ5vQ8F6T9x7J-z0ArqUj1Bsqi4qQg8ZSZ5D2VhNlloUdRW6oMrHYBJ9OxXIpn7dKfYUzYQ0euBHcHWFZQJQlXJKEGZJJnlqqsCXetmpuYpqv93q2gqm4Bksc0FUNj5T6uD7sBweWlYh13TYWKIL6f63D0bhMDsFB6xXCcTOaPtix5QDsb7ECB6DfzsIK3rSo6NsjsJg3ZKk3GGqahcxyuCphTKpF3Ss082qwcBaPTtdd-3G9eq-g91jhOGY2wJfuJNGqPAaLyeP84Qm1hRJQQUlSI6l1wpQS0iWpTh0uDHfY-QszfzPCZcI5zWlhA4oHY60EMVamXGPuCkXoCeiVq9KeAuiwYhKbkH7LWCoL3zcT1HejRBGbkSG46oSXfzQ8jNzHEUHE-UbEQ3Af5PrTIjCs4wOv2bzVbP6XZodg1GklbydWlfvlxzulQqTk7D--cQ72vAfUAG7xCPTq9ae9ALvFV_1arS_jP_UNJFTOPQ
  priority: 102
  providerName: Directory of Open Access Journals
Title Temporal Modeling on Multi-Temporal-Scale Spatiotemporal Atoms for Action Recognition
URI https://www.proquest.com/docview/2250198852
https://doaj.org/article/2460231079204d26975e3a1e2063b7d8
Volume 8
WOSCitedRecordID wos000448653700130&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: 2076-3417
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913810
  issn: 2076-3417
  databaseCode: DOA
  dateStart: 20110101
  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: 2076-3417
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913810
  issn: 2076-3417
  databaseCode: M~E
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2076-3417
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913810
  issn: 2076-3417
  databaseCode: BENPR
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2076-3417
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913810
  issn: 2076-3417
  databaseCode: PIMPY
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpZ1Lb9QwEIBHsO0BDtAHiIVSWaKH9mARPxLbJ7RFrcqB1aoPqT1FSWwjJEjKJvD78ThOFwmJCzlESmxLUcb2jMeebwCOjOciKCpHG4xBk7m3tA5akxZO4o6isqKyMdmEWi717a1ZJYdbn45VTnNinKht16CP_H3od8Ea0TrnH-5_UMwahburKYXGY9hCUpmcwdbp2XJ1-eBlQeqlZtnIJRVhfY_7wsi00jG_20YTRWD_X_NxVDLnz__383bgWTIvyWLsD7vwyLV78PQP6OAe7Kbh3JPjxJw-2Yeb6xFR9Y1gcjQMUSddS2J0Lp2K6FWQpyNX8Qz2MNVfDN33ngTTlyxiiAS5nI4kde0LuDk_u_54QVPGBdoIng3U1HUmq0obn-V17lljlWc-XEyGm9W-0N7XSjQOmT6M1ZXm1plc1Uz5puLiJczarnWvgHhWScMsxvFKmZsmtC20CM0Er7gr-BzeTX-_vB_BGmVYkKCMyo2M5nCKgnmogTDs-KJbfynT2Cq5LJBilynDM2l5YVTuRMUcD-ZXrayew8EkszKN0L7cCOz1v4vfwJNgJI0MXHYAs2H9072F7ebX8LVfH6YOdxjX8uFp9enz6u43JOviiA
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB1VWyTgALSAWFrAEiDBwSJ2nNg-ILR8VF21Xa3oViqnkMQ2qtQm7SYF8af4jXicpIuExK0Hcsghtg-Jn96MY897AC-047EPVJaWWIMmEmdo4aMmTa3AHUVp4twEswk5m6njYz1fg19DLQweqxw4MRC1qUv8R_7G485nI0ol_N35BUXXKNxdHSw0Oljs2Z8__JKteTv96Of3Jec7nxYfdmnvKkDLmEct1UURiTxX2kVJkThWGumY8xcT_maUS5VzhYxLi7o1jBW54sbqRBZMujJHoQNP-evCg12NYH0-PZh_ufqrgyqbikWdDmoc6wj3oVFDSwU_uVXkCwYBf_F_CGo7d_-3z3EP7vTpM5l0eN-ANVttwu0_RBU3YaOnq4a86jW1X9-Ho0UnwXVK0PwNS_BJXZFQfUyHJnro8WrJYThj3g79J2191hCf2pNJKAEhn4cjV3X1AI6u5WUfwqiqK_sIiGO50MxgnbIQiS792FTFfljMc25TPobnw2xn551wSOYXXIiJbIWJMbxHIFz1QLHv8KBefst67si4SFGlL5KaR8LwVMvExjmz3KeXhTRqDNsDRrKegZpsBZDH_25-Bjd3Fwf72f50trcFt3xC2On9sm0YtctL-wRulN_bk2b5tAc7ga_XDajfBmRBdQ
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB1VLUJwAFpALBSwBEhwsBp_JLYPCC2UFavCakVbqZzSJLYREiRlE0D8NX4dYyfpIiFx64EccojtQ-LnmYk98x7AY-O5QEflaBVq0GTqLS3Ra9LMyXCiqKwobBSbUIuFPjkxyw34NdbChLTK0SZGQ22bKuyR7yHuMBrROuV7fkiLWO7PXpx9pUFBKpy0jnIaPUQO3M8f-PvWPp_v41w_4Xz2-ujVGzooDNBK8KSjpiwTWRTa-CQtU88qqzzzeDGJN6t9pr0vlahc4LBhrCw0t86kqmTKV0UgPUDzv4UhucQ1trWcv1t-ON_hCYybmiU9J6oQJgln0oFPS0dtubUXjGIBf_mC6OBm1__nT3MDrg1hNZn262AbNly9A1f_IFvcge3BjLXk6cC1_ewmHB_11FyfSRCFC6X5pKlJrEqmYxM9RBw7chhzz7ux_7RrvrQEQ34yjaUh5P2YitXUt-D4Ql72NmzWTe3uAPGskIbZUL8sZWoqHJtpgcMEL7jL-AQejTOfn_WEIjn-iAV85Gt8TOBlAMV5j0ACHh80q4_5YFNyLrPA3pcowxNpeWZU6kTBHMews1RWT2B3xEs-WKY2X4Pl7r-bH8JlRFH-dr44uAdXME7saYDZLmx2q2_uPlyqvnef2tWDAfcETi8aT78B4LxKNQ
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=Temporal+Modeling+on+Multi-Temporal-Scale+Spatiotemporal+Atoms+for+Action+Recognition&rft.jtitle=Applied+sciences&rft.au=Yao%2C+Guangle&rft.au=Lei%2C+Tao&rft.au=Liu%2C+Xianyuan&rft.au=Jiang%2C+Ping&rft.date=2018-10-01&rft.issn=2076-3417&rft.eissn=2076-3417&rft.volume=8&rft.issue=10&rft.spage=1835&rft_id=info:doi/10.3390%2Fapp8101835&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_app8101835
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2076-3417&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2076-3417&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2076-3417&client=summon