Masked Autoencoders for Spatial-Temporal Relationship in Video-Based Group Activity Recognition

Group Activity Recognition (GAR) is a challenging problem involving several intricacies. The core of GAR lies in delving into spatiotemporal features to generate appropriate scene representations. Previous methods, however, either feature a complex framework requiring individual action labels or nee...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE access Ročník 12; s. 132084 - 132095
Hlavní autoři:	Yadav, Rajeshwar, Halder, Raju, Banda, Gourinath
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Activity recognition CAD Cognitive tasks Collaborative software Complexity Computer aided design Crime Datasets Encoding Feature recognition Group activity recognition (GAR) hostage crime IITP hostage dataset Image reconstruction Labels masked autoencoder Predictive models Representations Solid modeling spatial and temporal interaction Spatiotemporal data Spatiotemporal phenomena Video Videos vision transformer
ISSN:	2169-3536, 2169-3536
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Group Activity Recognition (GAR) is a challenging problem involving several intricacies. The core of GAR lies in delving into spatiotemporal features to generate appropriate scene representations. Previous methods, however, either feature a complex framework requiring individual action labels or need more adequate modelling of spatial and temporal features. To address these concerns, we propose a masking strategy for learning task-specific GAR scene representations through reconstruction. Furthermore, we elucidate how this methodology can effectively capture task-specific spatiotemporal features. In particular, three notable findings emerge from our framework: 1) GAR is simplified, eliminating the need for individual action labels; 2) the generation of target-specific spatiotemporal features yields favourable outcomes for various datasets; and 3) this method demonstrates effectiveness even for datasets with a small number of videos, highlighting its capability with limited training data. Further, the existing GAR datasets have fewer videos per class and only a few actors are considered, restricting the existing model from being generalised effectively. To this aim, we introduce 923 videos for a crime activity named IITP Hostage, which contains two categories, hostage and non-hostage. To our knowledge, this is the first attempt to recognize crime-based activities in GAR. Our framework achieves MCA of 96.8%, 97.0%, 97.0% on Collective Activity Dataset (CAD), new CAD, extended CAD datasets and 84.3%, 95.6%, 96.78% for IITP Hostage, hostage+CAD and subset of UCF crime datasets. The hostage and non-hostage scenarios introduce additional complexity, making it more challenging for the model to accurately recognize the activities compared to hostage+CAD and other datasets. This observation underscores the necessity to delve deeper into the complexity of GAR activities.
AbstractList	Group Activity Recognition (GAR) is a challenging problem involving several intricacies. The core of GAR lies in delving into spatiotemporal features to generate appropriate scene representations. Previous methods, however, either feature a complex framework requiring individual action labels or need more adequate modelling of spatial and temporal features. To address these concerns, we propose a masking strategy for learning task-specific GAR scene representations through reconstruction. Furthermore, we elucidate how this methodology can effectively capture task-specific spatiotemporal features. In particular, three notable findings emerge from our framework: 1) GAR is simplified, eliminating the need for individual action labels; 2) the generation of target-specific spatiotemporal features yields favourable outcomes for various datasets; and 3) this method demonstrates effectiveness even for datasets with a small number of videos, highlighting its capability with limited training data. Further, the existing GAR datasets have fewer videos per class and only a few actors are considered, restricting the existing model from being generalised effectively. To this aim, we introduce 923 videos for a crime activity named IITP Hostage, which contains two categories, hostage and non-hostage. To our knowledge, this is the first attempt to recognize crime-based activities in GAR. Our framework achieves MCA of 96.8%, 97.0%, 97.0% on Collective Activity Dataset (CAD), new CAD, extended CAD datasets and 84.3%, 95.6%, 96.78% for IITP Hostage, hostage+CAD and subset of UCF crime datasets. The hostage and non-hostage scenarios introduce additional complexity, making it more challenging for the model to accurately recognize the activities compared to hostage+CAD and other datasets. This observation underscores the necessity to delve deeper into the complexity of GAR activities.
Author	Yadav, Rajeshwar Halder, Raju Banda, Gourinath
Author_xml	– sequence: 1 givenname: Rajeshwar orcidid: 0009-0000-6228-7340 surname: Yadav fullname: Yadav, Rajeshwar email: rajeshwar_2021cs06@iitp.ac.in organization: Department of Computer Science and Engineering, Indian Institute of Technology Patna, Bihta, India – sequence: 2 givenname: Raju orcidid: 0000-0002-8873-8258 surname: Halder fullname: Halder, Raju organization: Department of Computer Science and Engineering, Indian Institute of Technology Patna, Bihta, India – sequence: 3 givenname: Gourinath orcidid: 0000-0003-1447-4330 surname: Banda fullname: Banda, Gourinath organization: Department of Computer Science and Engineering, Indian Institute of Technology Indore, Indore, Madhya Pradesh, India
BookMark	eNpNkUtrGzEUhUVJoGmSX9AuBroeV6_RY-maNDGkFOIkW6GR7rhyx6OpNC7k30fOhGJtrjic812h8wmdDXEAhD4TvCAE62_L1epms1lQTPmC8UaW-QFdUCJ0zRomzk7uH9F1zjtcjipSIy-Q-WnzH_DV8jBFGFz0kHLVxVRtRjsF29ePsB9jsn31AH1R4pB_h7EKQ_UcPMT6u80lfZviYayWbgr_wvRSrC5uh3B0X6HzzvYZrt_nJXr6cfO4uqvvf92uV8v72rFGT3VLlefSU8J8K6RVpLUanBRCa-ct8FZ5hoEJzYE4qTx46hyhnDdaYkI9u0Trmeuj3Zkxhb1NLybaYN6EmLbGpim4HkzbKMuF4sLpYx6rAuWia3ErFe4oL6yvM2tM8e8B8mR28ZCG8nzDyodzpQUnxcVml0sx5wTd_60Em2MxZi7GHIsx78WU1Jc5FQDgJCEkbgr0FYQ8iww
CODEN	IAECCG
Cites_doi	10.1109/CVPR.2016.516 10.1109/ICCV48922.2021.00738 10.1007/978-3-642-33765-9_16 10.1016/j.patcog.2021.108487 10.1109/ICCV.2015.510 10.48550/ARXIV.1706.03762 10.1109/TPAMI.2020.3034233 10.1109/CVPR42600.2020.00106 10.1109/ICCV48922.2021.00747 10.1016/j.neucom.2018.10.095 10.1007/978-3-319-10599-4_37 10.1109/ACCESS.2021.3059170 10.1109/TPAMI.2011.228 10.1109/TMM.2019.2930344 10.1109/TIP.2019.2918725 10.1109/CVPR52688.2022.01945 10.1109/IC4ME2.2018.8465583 10.1109/TCSVT.2023.3249906 10.1109/CVPR.2014.223 10.1007/978-3-030-69541-5_3 10.1109/TPAMI.2019.2928540 10.1155/2022/3454167 10.1109/IROS.2017.8206288 10.1007/978-3-030-58598-3_13 10.1145/3503161.3547825 10.1109/CVPR.2019.00033 10.1109/CVPR52688.2022.00320 10.1109/CVPR.2018.00678 10.1109/ICCV.2017.313 10.1109/CVPR.2019.00808 10.1145/3240508.3240576 10.1109/ACCESS.2022.3189162 10.1109/CVPR.2017.365 10.1109/TPAMI.2012.59 10.1109/CVPR.2016.217 10.1109/WACV.2018.00180 10.1109/CVPR.2017.783 10.1109/ICCV48922.2021.00676 10.1007/978-3-030-01219-9_44 10.1109/CVPR.2019.01020 10.48550/arXiv.2102.05095 10.1109/TIP.2019.2914577 10.1109/CVPR.2017.453 10.1109/CVPR52688.2022.00300 10.1109/TCSVT.2019.2894161 10.1109/CVPR42600.2020.00092 10.1109/TCSVT.2022.3233069 10.1109/CVPR52688.2022.01553 10.1109/ICETIETR.2018.8529108 10.1016/j.cviu.2021.103219 10.1109/ICCV48922.2021.01341 10.1609/aaai.v35i4.16437 10.1145/3240508.3240572 10.1007/978-3-030-58589-1_35 10.1109/CVPR.2015.7298875
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2024.3457024
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts 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 METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research 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: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	132095
ExternalDocumentID	oai_doaj_org_article_b58a46846c944590894e46fb0b780f24 10_1109_ACCESS_2024_3457024 10670541
Genre	orig-research
GrantInformation_xml	– fundername: Science and Engineering Research Board, Department of Science and Technology, Government of India, through the IMPACTING RESEARCH INNOVATION AND TECHNOLOGY-2 Project, grantid: IMP/2018/000523
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c359t-b28d47d213db67a81ba9ec76699cdae4b8d30e3694e1c78ded2cc1244597012d3
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001320474900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:53:44 EDT 2025 Mon Jun 30 15:48:20 EDT 2025 Sat Nov 29 04:27:04 EST 2025 Wed Aug 27 01:59:03 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c359t-b28d47d213db67a81ba9ec76699cdae4b8d30e3694e1c78ded2cc1244597012d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0000-6228-7340 0000-0002-8873-8258 0000-0003-1447-4330
OpenAccessLink	https://ieeexplore.ieee.org/document/10670541
PQID	3109489641
PQPubID	4845423
PageCount	12
ParticipantIDs	proquest_journals_3109489641 crossref_primary_10_1109_ACCESS_2024_3457024 doaj_primary_oai_doaj_org_article_b58a46846c944590894e46fb0b780f24 ieee_primary_10670541
PublicationCentury	2000
PublicationDate	20240000 2024-00-00 20240101 2024-01-01
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– year: 2024 text: 20240000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2024
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	ref13 ref57 ref12 ref56 ref58 ref53 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 Varshney (ref5) 2021 ref44 ref43 ref49 (ref59) 2024 ref8 ref7 ref9 ref4 ref3 ref6 Yi (ref21) 2021 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 Dosovitskiy (ref15) 2020 ref39 ref38 ref24 ref23 ref26 ref25 ref20 ref22 ref28 ref27 ref29 ref60 Tong (ref14); 35
References_xml	– ident: ref42 doi: 10.1109/CVPR.2016.516 – ident: ref33 doi: 10.1109/ICCV48922.2021.00738 – ident: ref40 doi: 10.1007/978-3-642-33765-9_16 – ident: ref19 doi: 10.1016/j.patcog.2021.108487 – ident: ref9 doi: 10.1109/ICCV.2015.510 – volume: 35 start-page: 10078 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref14 article-title: VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training – ident: ref17 doi: 10.48550/ARXIV.1706.03762 – ident: ref32 doi: 10.1109/TPAMI.2020.3034233 – ident: ref54 doi: 10.1109/CVPR42600.2020.00106 – year: 2020 ident: ref15 article-title: An image is worth 16\times16 words: Transformers for image recognition at scale publication-title: arXiv:2010.11929 – ident: ref20 doi: 10.1109/ICCV48922.2021.00747 – ident: ref11 doi: 10.1016/j.neucom.2018.10.095 – ident: ref44 doi: 10.1007/978-3-319-10599-4_37 – year: 2021 ident: ref21 article-title: ASFormer: Transformer for action segmentation publication-title: arXiv:2110.08568 – ident: ref4 doi: 10.1109/ACCESS.2021.3059170 – ident: ref39 doi: 10.1109/TPAMI.2011.228 – ident: ref52 doi: 10.1109/TMM.2019.2930344 – ident: ref48 doi: 10.1109/TIP.2019.2918725 – ident: ref25 doi: 10.1109/CVPR52688.2022.01945 – ident: ref6 doi: 10.1109/IC4ME2.2018.8465583 – ident: ref38 doi: 10.1109/TCSVT.2023.3249906 – ident: ref7 doi: 10.1109/CVPR.2014.223 – ident: ref23 doi: 10.1007/978-3-030-69541-5_3 – ident: ref29 doi: 10.1109/TPAMI.2019.2928540 – ident: ref60 doi: 10.1155/2022/3454167 – ident: ref10 doi: 10.1109/IROS.2017.8206288 – ident: ref56 doi: 10.1007/978-3-030-58598-3_13 – ident: ref36 doi: 10.1145/3503161.3547825 – ident: ref18 doi: 10.1109/CVPR.2019.00033 – ident: ref16 doi: 10.1109/CVPR52688.2022.00320 – ident: ref41 doi: 10.1109/CVPR.2018.00678 – ident: ref46 doi: 10.1109/ICCV.2017.313 – ident: ref53 doi: 10.1109/CVPR.2019.00808 – ident: ref28 doi: 10.1145/3240508.3240576 – ident: ref1 doi: 10.1109/ACCESS.2022.3189162 – ident: ref49 doi: 10.1109/CVPR.2017.365 – ident: ref8 doi: 10.1109/TPAMI.2012.59 – ident: ref43 doi: 10.1109/CVPR.2016.217 – ident: ref47 doi: 10.1109/WACV.2018.00180 – ident: ref50 doi: 10.1109/CVPR.2017.783 – ident: ref12 doi: 10.1109/ICCV48922.2021.00676 – ident: ref51 doi: 10.1007/978-3-030-01219-9_44 – ident: ref31 doi: 10.1109/CVPR.2019.01020 – ident: ref13 doi: 10.48550/arXiv.2102.05095 – ident: ref55 doi: 10.1109/TIP.2019.2914577 – ident: ref26 doi: 10.1109/CVPR.2017.453 – ident: ref37 doi: 10.1109/CVPR52688.2022.00300 – ident: ref27 doi: 10.1109/TCSVT.2019.2894161 – ident: ref58 doi: 10.1109/CVPR42600.2020.00092 – ident: ref2 doi: 10.1109/TCSVT.2022.3233069 – volume-title: A Deep Learning Based Approach to Detect Suspicious Weapons year: 2021 ident: ref5 – ident: ref24 doi: 10.1109/CVPR52688.2022.01553 – ident: ref3 doi: 10.1109/ICETIETR.2018.8529108 – ident: ref22 doi: 10.1016/j.cviu.2021.103219 – ident: ref35 doi: 10.1109/ICCV48922.2021.01341 – ident: ref34 doi: 10.1609/aaai.v35i4.16437 – ident: ref30 doi: 10.1145/3240508.3240572 – ident: ref57 doi: 10.1007/978-3-030-58589-1_35 – ident: ref45 doi: 10.1109/CVPR.2015.7298875 – volume-title: Ultralytics YOLOv8 year: 2024 ident: ref59
SSID	ssj0000816957
Score	2.3069372
Snippet	Group Activity Recognition (GAR) is a challenging problem involving several intricacies. The core of GAR lies in delving into spatiotemporal features to...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Index Database Publisher
StartPage	132084
SubjectTerms	Activity recognition CAD Cognitive tasks Collaborative software Complexity Computer aided design Crime Datasets Encoding Feature recognition Group activity recognition (GAR) hostage crime IITP hostage dataset Image reconstruction Labels masked autoencoder Predictive models Representations Solid modeling spatial and temporal interaction Spatiotemporal data Spatiotemporal phenomena Video Videos vision transformer
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PT9swFLYmxAEO04CilTHkw46YxrHjH8e2WrXDQBNiqDfL9rNFxZQiWvb3z3bSqmgHLlyjKI6_5_h7z3r5PoS-RelpA1VDQmwk4YFH4prakxBq7xiXMoryo_BPeXOj5nP9a8fqK_eEdfLAHXAj1yjLRWJJrznPBt06PVBEVzmpqlgXJdBK6p1iquzBigrdyF5miFZ6NJ5O04xSQVjzK8YbWdX8FRUVxf7eYuW_fbmQzewT-thniXjcvd0R-hDaY3S4ox14gsy1XT0GwOOX9TKLUeaGZJwyUJxNhtOiIned6NQfvO13e1g84UWL7xcQlmSS6AtwOXrCY995SODbTTvRsh2g37Pvd9MfpHdLIJ41ek1crYBLqCkDJ6RN6ajVwUshtPZgA3cKWBWYSPhRLxUEqL3P7J5KisRSwE7RXrtsw2eELWjKPSgdPePeggKw0kXqg42RSTZElxvgzFMnimFKMVFp0-FsMs6mx3mIJhnc7a1Z0bpcSHE2fZzNW3EeokEOzc54QqZ0kw7R-SZWpv_8VibLnXKlBadn7zH2F3SQ59OdvJyjvfXzS_iK9v3f9WL1fFFW3j8rvdtD priority: 102 providerName: Directory of Open Access Journals
Title	Masked Autoencoders for Spatial-Temporal Relationship in Video-Based Group Activity Recognition
URI	https://ieeexplore.ieee.org/document/10670541 https://www.proquest.com/docview/3109489641 https://doaj.org/article/b58a46846c944590894e46fb0b780f24
Volume	12
WOSCitedRecordID	wos001320474900001&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: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 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: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELag6qEcoC_EQlv5wBG3Sez4cdyuWnGgFUKl6s2yPWOxAiVVd5djf3ttJ7sqQhy4RFGUx8SfnXlk5htCPkYV6haqlmFsFRMoIvNtExhiEzwXSkVZCoW_qOtrfXdnvo7F6qUWBhFL8hme5t3yLx_6sMqhsrNMd5ZMjOTsvFRKDsVam4BK7iBhWjUyC9WVOZvOZuklkg_YiFMuWlU14g_tU0j6x64qf32Ki365fPOfku2S16MhSacD8nvkBXb75NUzesEDYq_c4icCna6WfearzDnLNBmpNPchTvOO3Qy8VL_oJiXux_yezjt6Owfs2XnScEBLdIpOw9Bmgn5bZxz13SH5fnlxM_vMxoYKLPDWLJlvNAgFTc3BS-WSxeoMBiWlMQEcCq-BV8ilEVgHpQGhCSEbAMnrSIoM-Fuy1fUdviPUgalFAG1i4CI40ABO-VgHdDFyxSfk03qg7f3Am2GLv1EZO-BiMy52xGVCzjMYm1Mz6XU5kEbZjmvI-lY7IZPBFEwWqdJJTiGjr7zSVcw3OczIPHveAMqEHK2xteMKXdjMiCq0kaJ-_4_LPpCdLOIQbzkiW8uHFR6T7fB7OV88nBTnPW2vHi9OykR8AhEN3DY
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELZQQQIOPItYKOADR9wmsR3bx-2KqojtCqEF9WbZnrG6AiVVd5ffj-1kV0WIA7coymPsz848MvMNIe-jCrWESjKMUjGBIjIvm8AQm-C5UCq2pVB4rhYLfXlpvozF6qUWBhFL8hke58PyLx_6sM2hspNMd5ZMjOTs3JVCNNVQrrUPqeQeEkaqkVuorszJdDZLw0heYCOOuZCqasQf-qfQ9I99Vf76GBcNc_b4P2V7Qh6NpiSdDtg_JXewe0Ye3iIYfE7shVv_QKDT7abPjJU5a5kmM5XmTsRp5bHlwEz1k-6T4q5W13TV0e8rwJ6dJh0HtMSn6DQMjSbo113OUd8dkm9nH5ezcza2VGCBS7NhvtEgFDQ1B98ql2xWZzCotjUmgEPhNfAKeWsE1kFpQGhCyCZA8juSKgP-ghx0fYcvCXVgahFAmxi4CA40gFM-1gFdjFzxCfmwm2h7PTBn2OJxVMYOuNiMix1xmZDTDMb-0kx7XU6kWbbjLrJeaifaZDIFk0WqdJJTtNFXXukq5occZmRuvW8AZUKOdtjacY-ubeZEFdq0on71j9vekfvny4u5nX9afH5NHmRxh-jLETnY3GzxDbkXfm1W65u3ZSH-BkiI3Vc
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=Masked+Autoencoders+for+Spatial-Temporal+Relationship+in+Video-Based+Group+Activity+Recognition&rft.jtitle=IEEE+access&rft.au=Yadav%2C+Rajeshwar&rft.au=Halder%2C+Raju&rft.au=Banda%2C+Gourinath&rft.date=2024&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=12&rft.spage=132084&rft.epage=132095&rft_id=info:doi/10.1109%2FACCESS.2024.3457024&rft.externalDocID=10670541
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon