Learning Unsupervised Visual Representations using 3D Convolutional Autoencoder with Temporal Contrastive Modeling for Video Retrieval

The rapid growth of tag-free user-generated videos (on the Internet), surgical recorded videos, and surveillance videos has necessitated the need for effective content-based video retrieval systems. Earlier methods for video representations are based on hand-crafted, which hardly performed well on t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of mathematical, engineering and management sciences Jg. 7; H. 2; S. 272 - 287
Hauptverfasser: Kumar, Vidit, Tripathi, Vikas, Pant, Bhaskar
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Dehradun International Journal of Mathematical, Engineering and Management Sciences 01.04.2022
Ram Arti Publishers
Schlagworte:
ISSN:2455-7749, 2455-7749
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The rapid growth of tag-free user-generated videos (on the Internet), surgical recorded videos, and surveillance videos has necessitated the need for effective content-based video retrieval systems. Earlier methods for video representations are based on hand-crafted, which hardly performed well on the video retrieval tasks. Subsequently, deep learning methods have successfully demonstrated their effectiveness in both image and video-related tasks, but at the cost of creating massively labeled datasets. Thus, the economic solution is to use freely available unlabeled web videos for representation learning. In this regard, most of the recently developed methods are based on solving a single pretext task using 2D or 3D convolutional network. However, this paper designs and studies a 3D convolutional autoencoder (3D-CAE) for video representation learning (since it does not require labels). Further, this paper proposes a new unsupervised video feature learning method based on joint learning of past and future prediction using 3D-CAE with temporal contrastive learning. The experiments are conducted on UCF-101 and HMDB-51 datasets, where the proposed approach achieves better retrieval performance than state-of-the-art. In the ablation study, the action recognition task is performed by fine-tuning the unsupervised pre-trained model where it outperforms other methods, which further confirms the superiority of our method in learning underlying features. Such an unsupervised representation learning approach could also benefit the medical domain, where it is expensive to create large label datasets.
AbstractList The rapid growth of tag-free user-generated videos (on the Internet), surgical recorded videos, and surveillance videos has necessitated the need for effective content-based video retrieval systems. Earlier methods for video representations are based on hand-crafted, which hardly performed well on the video retrieval tasks. Subsequently, deep learning methods have successfully demonstrated their effectiveness in both image and video-related tasks, but at the cost of creating massively labeled datasets. Thus, the economic solution is to use freely available unlabeled web videos for representation learning. In this regard, most of the recently developed methods are based on solving a single pretext task using 2D or 3D convolutional network. However, this paper designs and studies a 3D convolutional autoencoder (3D-CAE) for video representation learning (since it does not require labels). Further, this paper proposes a new unsupervised video feature learning method based on joint learning of past and future prediction using 3D-CAE with temporal contrastive learning. The experiments are conducted on UCF-101 and HMDB-51 datasets, where the proposed approach achieves better retrieval performance than state-of-the-art. In the ablation study, the action recognition task is performed by fine-tuning the unsupervised pre-trained model where it outperforms other methods, which further confirms the superiority of our method in learning underlying features. Such an unsupervised representation learning approach could also benefit the medical domain, where it is expensive to create large label datasets.
Author Kumar, Vidit
Tripathi, Vikas
Pant, Bhaskar
Author_xml – sequence: 1
  givenname: Vidit
  surname: Kumar
  fullname: Kumar, Vidit
  organization: Department of Computer Science and Engineering, Graphic Era Deemed to be University Dehradun, India
– sequence: 2
  givenname: Vikas
  surname: Tripathi
  fullname: Tripathi, Vikas
  organization: Department of Computer Science and Engineering, Graphic Era Deemed to be University, Dehradun, India
– sequence: 3
  givenname: Bhaskar
  surname: Pant
  fullname: Pant, Bhaskar
  organization: Department of Computer Science and Engineering, Graphic Era Deemed to be University, Dehradun, India
BookMark eNp9Uc1u1DAQtlCRKKVvwCES5w2Of9Y2t2ppYdGukKDlajn2pHiV2sF2FvECPDfeBiHEgZOtme9nZr7n6CzEAAi97HBLqZTq9fbD_nr_uSWYkFa0pMWdfILOCeN8JQRTZ3_9n6HLnA8YYyIU5R05Rz93YFLw4b65C3meIB19Btd88Xk2Y_MJpgQZQjHFx5CbOZ-Q9G2zieEYx_lUrbCruUQINjpIzXdfvja38DDFVDsVV5LJxR-h2df-eOIPMVUDB7Hql-ThaMYX6OlgxgyXv98LdHdzfbt5v9p9fLfdXO1WlqqurCwThitJesYkNpKBxUQRQzAf6tbWuX7t3JpT2UtDmKJWGMqF7KgbuFU9phdou-i6aA56Sv7BpB86Gq8fCzHda5OKtyPoAYNhtgeieM-oo72p7ozTQYDDridV69WiNaX4bYZc9CHOqd4ja7JmdUy15rKi2IKyKeacYPjj2mH9GKBeAtSnALXQRNdVKu3NPzTrlxTqPf34f_Ivu1CmXg
CitedBy_id crossref_primary_10_1007_s10489_024_05460_8
Cites_doi 10.1145/3204949.3208141
10.1016/j.neucom.2015.09.114
10.1109/iccv.2017.79
10.1007/s12046-016-0574-8
10.1609/aaai.v33i01.33018545
10.1145/3439950
10.1109/icme46284.2020.9102724
10.1109/icacc.2013.49
10.1162/neco.2006.18.7.1527
10.1007/978-981-16-2354-7_46
10.1145/3444693
10.1109/dicta51227.2020.9363408
10.1109/CONECCT52877.2021.9622562.
10.1007/s11548-021-02493-z
10.1109/spin48934.2020.9071334
10.21236/ada164453
10.1609/aaai.v34i07.6840
10.1109/cvpr.2014.223
10.1109/dcc.2017.31
10.1007/978-3-319-46466-4_5
10.1109/cvpr.2018.00675
10.1109/tpami.2016.2572683
10.1109/conecct52877.2021.9622562
10.1007/s11042-019-07805-9
10.1007/978-3-319-10590-1_38
10.1145/2396761.2398433
10.1007/978-3-030-01267-0_47
10.7551/mitpress/7503.003.0024
10.1109/cvpr.2019.01058
10.1145/1282280.1282352
10.1007/s11042-019-07793-w
10.1109/cvpr.2017.607
10.1109/iccv.2015.510
10.1109/iccv.2011.6126543
10.1007/978-3-030-58520-4_30
10.1023/A:1007379606734
10.1109/tcsvt.2017.2667710
10.1007/978-3-319-46448-0_32
10.1007/s00521-020-04742-9
10.1007/978-3-319-56991-8_27
10.1109/access.2021.3084840
10.1109/tpami.2016.2577031
10.1109/76.718510
10.1109/icpr.2018.8546122
10.1007/s11042-017-4962-9
10.1109/cvpr42600.2020.00994
10.1007/s11548-021-02343-y
10.1145/3078971.3079041
10.1007/978-3-030-81462-5_61
10.1145/3065386
10.1145/3204949
10.1109/tits.2014.2311123
10.1007/s00799-018-0236-z
10.1007/978-3-030-42699-6_8
ContentType Journal Article
Copyright 2022. This work is published 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: 2022. This work is published 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
3V.
7WY
7WZ
7XB
87Z
8FK
8FL
ABUWG
AFKRA
AZQEC
BENPR
BEZIV
CCPQU
DWQXO
FRNLG
F~G
K60
K6~
L.-
M0C
PHGZM
PHGZT
PIMPY
PKEHL
PQBIZ
PQBZA
PQEST
PQQKQ
PQUKI
PRINS
Q9U
DOA
DOI 10.33889/IJMEMS.2022.7.2.018
DatabaseName CrossRef
ProQuest Central (Corporate)
ProQuest ABI/INFORM Collection
ABI/INFORM Global (PDF only)
ProQuest Central (purchase pre-March 2016)
ABI/INFORM Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
ABI/INFORM Collection (Alumni Edition)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
Business Premium Collection
ProQuest One Community College
ProQuest Central
Business Premium Collection (Alumni)
ABI/INFORM Global (Corporate)
ProQuest Business Collection (Alumni Edition)
ProQuest Business Collection
ABI/INFORM Professional Advanced
ABI/INFORM Global
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Business
ProQuest One Business (Alumni)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
ProQuest Central Basic
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
ABI/INFORM Global (Corporate)
ProQuest Business Collection (Alumni Edition)
ProQuest One Business
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest Central China
ABI/INFORM Complete
ProQuest Central
ABI/INFORM Professional Advanced
ProQuest Central Korea
ProQuest Central (New)
ABI/INFORM Complete (Alumni Edition)
Business Premium Collection
ABI/INFORM Global
ABI/INFORM Global (Alumni Edition)
ProQuest Central Basic
ProQuest One Academic Eastern Edition
ProQuest Business Collection
ProQuest One Academic UKI Edition
ProQuest One Business (Alumni)
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
Business Premium Collection (Alumni)
DatabaseTitleList Publicly Available Content Database

CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Open Access Full Text
  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
EISSN 2455-7749
EndPage 287
ExternalDocumentID oai_doaj_org_article_f0ea4cbe295b43d3bac47453f7ed0db2
10_33889_IJMEMS_2022_7_2_018
GeographicLocations India
GeographicLocations_xml – name: India
GroupedDBID 7WY
8FL
AAYXX
ABUWG
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
BENPR
BEZIV
CCPQU
CITATION
DWQXO
FRNLG
GROUPED_DOAJ
M0C
M~E
OK1
PHGZM
PHGZT
PIMPY
PQBIZ
PQBZA
3V.
7XB
8FK
AZQEC
K60
K6~
L.-
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
Q9U
ID FETCH-LOGICAL-c391t-c47a5982b4480a84ec0292a205f018cddb6dd6538b8a2493c7a357813df5c9b03
IEDL.DBID BENPR
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000770306000008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2455-7749
IngestDate Mon Nov 10 04:35:35 EST 2025
Wed Oct 08 14:10:34 EDT 2025
Tue Nov 18 21:36:27 EST 2025
Sat Nov 29 05:40:54 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c391t-c47a5982b4480a84ec0292a205f018cddb6dd6538b8a2493c7a357813df5c9b03
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://www.proquest.com/docview/2645989658?pq-origsite=%requestingapplication%
PQID 2645989658
PQPubID 5363605
PageCount 16
ParticipantIDs doaj_primary_oai_doaj_org_article_f0ea4cbe295b43d3bac47453f7ed0db2
proquest_journals_2645989658
crossref_primary_10_33889_IJMEMS_2022_7_2_018
crossref_citationtrail_10_33889_IJMEMS_2022_7_2_018
PublicationCentury 2000
PublicationDate 2022-04-01
PublicationDateYYYYMMDD 2022-04-01
PublicationDate_xml – month: 04
  year: 2022
  text: 2022-04-01
  day: 01
PublicationDecade 2020
PublicationPlace Dehradun
PublicationPlace_xml – name: Dehradun
PublicationTitle International journal of mathematical, engineering and management sciences
PublicationYear 2022
Publisher International Journal of Mathematical, Engineering and Management Sciences
Ram Arti Publishers
Publisher_xml – name: International Journal of Mathematical, Engineering and Management Sciences
– name: Ram Arti Publishers
References ref13
ref57
ref12
ref56
ref15
ref59
ref14
ref58
ref53
ref52
ref11
ref55
ref10
ref54
ref17
ref16
ref19
ref18
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref43
ref49
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref0
ref2
ref1
ref39
ref38
ref24
ref68
ref23
ref67
ref26
ref25
ref20
ref64
ref63
ref22
ref66
ref21
ref65
ref28
ref27
ref29
ref60
ref62
ref61
References_xml – ident: ref1
– ident: ref12
  doi: 10.1145/3204949.3208141
– ident: ref68
  doi: 10.1016/j.neucom.2015.09.114
– ident: ref66
– ident: ref37
  doi: 10.1109/iccv.2017.79
– ident: ref6
  doi: 10.1007/s12046-016-0574-8
– ident: ref28
  doi: 10.1609/aaai.v33i01.33018545
– ident: ref24
– ident: ref47
  doi: 10.1145/3439950
– ident: ref65
  doi: 10.1109/icme46284.2020.9102724
– ident: ref2
  doi: 10.1109/icacc.2013.49
– ident: ref17
– ident: ref20
  doi: 10.1162/neco.2006.18.7.1527
– ident: ref36
  doi: 10.1007/978-981-16-2354-7_46
– ident: ref42
  doi: 10.1145/3444693
– ident: ref13
– ident: ref23
  doi: 10.1109/dicta51227.2020.9363408
– ident: ref35
  doi: 10.1109/CONECCT52877.2021.9622562.
– ident: ref48
  doi: 10.1007/s11548-021-02493-z
– ident: ref32
  doi: 10.1109/spin48934.2020.9071334
– ident: ref26
– ident: ref53
  doi: 10.21236/ada164453
– ident: ref39
  doi: 10.1609/aaai.v34i07.6840
– ident: ref27
  doi: 10.1109/cvpr.2014.223
– ident: ref38
  doi: 10.1109/dcc.2017.31
– ident: ref46
  doi: 10.1007/978-3-319-46466-4_5
– ident: ref59
  doi: 10.1109/cvpr.2018.00675
– ident: ref54
  doi: 10.1109/tpami.2016.2572683
– ident: ref34
  doi: 10.1109/conecct52877.2021.9622562
– ident: ref50
  doi: 10.1007/s11042-019-07805-9
– ident: ref3
  doi: 10.1007/978-3-319-10590-1_38
– ident: ref62
  doi: 10.1145/2396761.2398433
– ident: ref7
  doi: 10.1007/978-3-030-01267-0_47
– ident: ref5
  doi: 10.7551/mitpress/7503.003.0024
– ident: ref64
  doi: 10.1109/cvpr.2019.01058
– ident: ref25
  doi: 10.1145/1282280.1282352
– ident: ref57
  doi: 10.1007/s11042-019-07793-w
– ident: ref45
– ident: ref16
  doi: 10.1109/cvpr.2017.607
– ident: ref29
  doi: 10.1609/aaai.v33i01.33018545
– ident: ref58
  doi: 10.1109/iccv.2015.510
– ident: ref31
  doi: 10.1109/iccv.2011.6126543
– ident: ref61
  doi: 10.1007/978-3-030-58520-4_30
– ident: ref9
  doi: 10.1023/A:1007379606734
– ident: ref0
  doi: 10.1109/tcsvt.2017.2667710
– ident: ref19
– ident: ref55
– ident: ref41
  doi: 10.1007/978-3-319-46448-0_32
– ident: ref15
– ident: ref22
  doi: 10.1007/s00521-020-04742-9
– ident: ref49
  doi: 10.1007/978-3-319-56991-8_27
– ident: ref11
  doi: 10.1109/access.2021.3084840
– ident: ref51
  doi: 10.1109/tpami.2016.2577031
– ident: ref52
  doi: 10.1109/76.718510
– ident: ref60
  doi: 10.1109/icpr.2018.8546122
– ident: ref67
– ident: ref43
  doi: 10.1007/s11042-017-4962-9
– ident: ref4
  doi: 10.1109/cvpr42600.2020.00994
– ident: ref63
  doi: 10.1007/s11548-021-02343-y
– ident: ref40
  doi: 10.1145/3078971.3079041
– ident: ref33
  doi: 10.1007/978-3-030-81462-5_61
– ident: ref56
– ident: ref18
– ident: ref30
  doi: 10.1145/3065386
– ident: ref14
  doi: 10.1145/3204949
– ident: ref21
  doi: 10.1109/tits.2014.2311123
– ident: ref10
– ident: ref44
  doi: 10.1007/s00799-018-0236-z
– ident: ref8
  doi: 10.1007/978-3-030-42699-6_8
SSID ssj0002793512
Score 2.2262428
Snippet The rapid growth of tag-free user-generated videos (on the Internet), surgical recorded videos, and surveillance videos has necessitated the need for effective...
SourceID doaj
proquest
crossref
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
StartPage 272
SubjectTerms content-based search
contrastive learning
convolutional autoencoder
Datasets
Deep learning
future prediction
Teaching methods
unsupervised learning
User generated content
video retrieval
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrZ1LT9wwEICtCvXQS9WKVl1e8oFrFq_txPGRpwoCVLVQcbNsj4NAKIs2WX5CfzczTkArceDSazRxHM947EnG3zC2q5tA2HMoNOhY6LKGwnrTFDPVlNHMvDI-Q1zPzeVlfXNjf62U-qKcsAEPPAzcXiOS1zEkacugFajgoza6VI1JICBk74u7npVg6j7_TrMKl7LhrBxGYbXdOz27OL74gxGhlFMzlVNBdT5W1qKM7H_jkfMyc_KFfR73h3x_6NdX9iG16-zfSEG95ddtt3yk6d0l4H_vuiXK_s7JrOMZorbjlMp-y9URP5y3T6NlUZPLfk7USkgLTl9f-dVApXoguX7hO3J8nGqj0Ql1jptZfACkObZPRbfQIr-x65Pjq8OfxVhAoYjKzvoCR8oToC9gDCZ8rVMU0kovRdng20eAUAFU6PJC7TEMU9F4gt_MFKCibBDqO1tr5236wXjlJYBXlRfaa1WFIGwgeFeAyqdGpglTL0Pp4kgXpyIXDw6jjKwANyjAkQKccdJhFyaseL3rcaBrvCN_QFp6lSU2dr6AFuNGi3HvWcyEbb3o2I0TtnOSoDo1kXA2_sczNtkn6veQ4rPF1vrFMm2zj_Gpv-sWO9lWnwGjq_GO
  priority: 102
  providerName: Directory of Open Access Journals
Title Learning Unsupervised Visual Representations using 3D Convolutional Autoencoder with Temporal Contrastive Modeling for Video Retrieval
URI https://www.proquest.com/docview/2645989658
https://doaj.org/article/f0ea4cbe295b43d3bac47453f7ed0db2
Volume 7
WOSCitedRecordID wos000770306000008&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 Open Access Full Text
  customDbUrl:
  eissn: 2455-7749
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002793512
  issn: 2455-7749
  databaseCode: DOA
  dateStart: 20160101
  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: 2455-7749
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002793512
  issn: 2455-7749
  databaseCode: M~E
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ABI/INFORM Collection
  customDbUrl:
  eissn: 2455-7749
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002793512
  issn: 2455-7749
  databaseCode: 7WY
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/abicomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ABI/INFORM Global
  customDbUrl:
  eissn: 2455-7749
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002793512
  issn: 2455-7749
  databaseCode: M0C
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/abiglobal
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2455-7749
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002793512
  issn: 2455-7749
  databaseCode: BENPR
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2455-7749
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002793512
  issn: 2455-7749
  databaseCode: PIMPY
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3Nb9MwFLdYx4ELHwJEx6h84JrOtZ04OSFWOjFEq2pssJ0sf6WaNCWlSfcn8HfzXuIWJCQ4cMnBeXEs_56f816ef4-Qt7K0SHvuE-mlS2Sa-6QwqkwmokydmhihTEfi-lktFvn1dbGMAbcmplXubGJnqH3tMEZ-wpH1JEeqknfr7wlWjcK_q7GExgE5RKYyOSCHp7PF8mIfZeGgfrCl9WfmwBvLi5PzT_PZ_At4hpyP1ZiPGdb7-G1P6qj7_7DM3XZz9uR_B_qUPI4fmvR9rxnPyINQPSc_Ip3qil5VzXaNdqIJnn69bbYge9FlxcbDSFVDMSd-RcUHOq2r-6ii2OW2rZH-0ocNxTAuvezpre5Qrt2YBi0oxSJreNSdwlcxvMCHGvrH6l2g2i_I1dnscvoxiZUYEieKSZs4qQwy_Vlw5pjJZXCMF9xwlpYwfc57m3mfge20uQF_TjhlkEVnIjwgXlgmXpJBVVfhFaGZ4d4bkRkmjRSZtaywyAJmfWZCycOQiB0W2kWacqyWcafBXekQ1D2CGhHUSnMNQxiSZP_Uuqfp-If8KcK8l0WS7a6h3qx0XLO6ZMFIZwMvUiuFF9bAPMhUlCp45i0fkuOdBui48hv9C_6jv99-TR7hiPosoGMyaDfb8IY8dPftbbMZkQP17WYU1XnURQrgOmdTaFuez5c3PwF6HQRT
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwELZKQYILDwFioYAPcMzWsZ3XASHYturS3RWCLerN-JVVpSpZkmwRf4Cfw29kJo8FCQlOPXBNHMexv5nxODPfEPJC5gZpz10gnbSBjFIXZDrJg1DkkU1CLRLdkrjOksUiPTvL3u-QH0MuDIZVDjqxVdSutHhGvs-R9SRFqpLX6y8BVo3Cv6tDCY0OFif-21dw2epX0wNY35ecHx0uJ8dBX1UgsCILm8DKRCNrnQHHhOlUest4xjVnUc7C1DpnYudi0AMm1eCbCJtoZIQJhYPRZ4YJ6PcauS4liAOGCrLJ9kyHA9jBgHYZeuD7pdn-9N38cP4R_FDOx8mYjxlWF_nNAraFAv6wA61xO7rzv03LXXK730bTNx3u75EdX9wn33uy2BU9LerNGrVg7R39dF5voO2HNua3T7UqaooR_ysqDuikLC57AcQuN02J5J7OVxQPqemyI--6wHZNpWu0DxRLyGEiP4U9P7zA-RL6x9pkILgPyOmVfPpDsluUhX9EaKy5c1rEmkktRWwMywxynBkXa59zPyJiWHtlexJ2rAVyocAZaxGjOsQoRIxKFFcwhBEJtk-tOxKSf7R_i7DatkUK8fZCWa1Ur5FUzryW1nieRUYKJ4yGeZCRyBPvmDN8RPYGxKler9XqF9we__32c3LzeDmfqdl0cfKE3MLRdfFOe2S3qTb-KblhL5vzunrWihAln68anD8BddlZwg
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=Learning+Unsupervised+Visual+Representations+using+3D+Convolutional+Autoencoder+with+Temporal+Contrastive+Modeling+for+Video+Retrieval&rft.jtitle=International+journal+of+mathematical%2C+engineering+and+management+sciences&rft.au=Kumar%2C+Vidit&rft.au=Tripathi%2C+Vikas&rft.au=Pant%2C+Bhaskar&rft.date=2022-04-01&rft.issn=2455-7749&rft.eissn=2455-7749&rft.volume=7&rft.issue=2&rft.spage=272&rft.epage=287&rft_id=info:doi/10.33889%2FIJMEMS.2022.7.2.018&rft.externalDBID=n%2Fa&rft.externalDocID=10_33889_IJMEMS_2022_7_2_018
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2455-7749&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2455-7749&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2455-7749&client=summon