Multi-Scale Masked Autoencoders for Cross-Session Emotion Recognition

Affective brain-computer interfaces (aBCIs) have garnered widespread applications, with remarkable advancements in utilizing electroencephalogram (EEG) technology for emotion recognition. However, the time-consuming process of annotating EEG data, inherent individual differences, non-stationary char...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on neural systems and rehabilitation engineering Ročník 32; s. 1637 - 1646
Hlavní autori:	Pang, Miaoqi, Wang, Hongtao, Huang, Jiayang, Vong, Chi-Man, Zeng, Zhiqiang, Chen, Chuangquan
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States IEEE 2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Adult Algorithms Brain modeling Brain-Computer Interfaces cross-session Data collection Data mining Data models EEG EEG-based emotion recognition Electroencephalography Electroencephalography - methods Emotion recognition Emotional factors Emotions Emotions - physiology Feature extraction Female Human-computer interface Humans Invariants Machine Learning Male Neural Networks, Computer Representations Robustness self-supervised learning Task analysis transformer
ISSN:	1534-4320, 1558-0210, 1558-0210
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Affective brain-computer interfaces (aBCIs) have garnered widespread applications, with remarkable advancements in utilizing electroencephalogram (EEG) technology for emotion recognition. However, the time-consuming process of annotating EEG data, inherent individual differences, non-stationary characteristics of EEG data, and noise artifacts in EEG data collection pose formidable challenges in developing subject-specific cross-session emotion recognition models. To simultaneously address these challenges, we propose a unified pre-training framework based on multi-scale masked autoencoders (MSMAE), which utilizes large-scale unlabeled EEG signals from multiple subjects and sessions to extract noise-robust, subject-invariant, and temporal-invariant features. We subsequently fine-tune the obtained generalized features with only a small amount of labeled data from a specific subject for personalization and enable cross-session emotion recognition. Our framework emphasizes: 1) multi-scale representation to capture diverse aspects of EEG signals, obtaining comprehensive information; 2) an improved masking mechanism for robust channel-level representation learning, addressing missing channel issues while preserving inter-channel relationships; and 3) invariance learning for regional correlations in spatial-level representation, minimizing inter-subject and inter-session variances. Under these elaborate designs, the proposed MSMAE exhibits a remarkable ability to decode emotional states from a different session of EEG data during the testing phase. Extensive experiments conducted on the two publicly available datasets, i.e., SEED and SEED-IV, demonstrate that the proposed MSMAE consistently achieves stable results and outperforms competitive baseline methods in cross-session emotion recognition.
AbstractList	Affective brain-computer interfaces (aBCIs) have garnered widespread applications, with remarkable advancements in utilizing electroencephalogram (EEG) technology for emotion recognition. However, the time-consuming process of annotating EEG data, inherent individual differences, non-stationary characteristics of EEG data, and noise artifacts in EEG data collection pose formidable challenges in developing subject-specific cross-session emotion recognition models. To simultaneously address these challenges, we propose a unified pre-training framework based on multi-scale masked autoencoders (MSMAE), which utilizes large-scale unlabeled EEG signals from multiple subjects and sessions to extract noise-robust, subject-invariant, and temporal-invariant features. We subsequently fine-tune the obtained generalized features with only a small amount of labeled data from a specific subject for personalization and enable cross-session emotion recognition. Our framework emphasizes: 1) multi-scale representation to capture diverse aspects of EEG signals, obtaining comprehensive information; 2) an improved masking mechanism for robust channel-level representation learning, addressing missing channel issues while preserving inter-channel relationships; and 3) invariance learning for regional correlations in spatial-level representation, minimizing inter-subject and inter-session variances. Under these elaborate designs, the proposed MSMAE exhibits a remarkable ability to decode emotional states from a different session of EEG data during the testing phase. Extensive experiments conducted on the two publicly available datasets, i.e., SEED and SEED-IV, demonstrate that the proposed MSMAE consistently achieves stable results and outperforms competitive baseline methods in cross-session emotion recognition. Affective brain-computer interfaces (aBCIs) have garnered widespread applications, with remarkable advancements in utilizing electroencephalogram (EEG) technology for emotion recognition. However, the time-consuming process of annotating EEG data, inherent individual differences, non-stationary characteristics of EEG data, and noise artifacts in EEG data collection pose formidable challenges in developing subject-specific cross-session emotion recognition models. To simultaneously address these challenges, we propose a unified pre-training framework based on multi-scale masked autoencoders (MSMAE), which utilizes large-scale unlabeled EEG signals from multiple subjects and sessions to extract noise-robust, subject-invariant, and temporal-invariant features. We subsequently fine-tune the obtained generalized features with only a small amount of labeled data from a specific subject for personalization and enable cross-session emotion recognition. Our framework emphasizes: 1) Multi-scale representation to capture diverse aspects of EEG signals, obtaining comprehensive information; 2) An improved masking mechanism for robust channel-level representation learning, addressing missing channel issues while preserving inter-channel relationships; and 3) Invariance learning for regional correlations in spatial-level representation, minimizing inter-subject and inter-session variances. Under these elaborate designs, the proposed MSMAE exhibits a remarkable ability to decode emotional states from a different session of EEG data during the testing phase. Extensive experiments conducted on the two publicly available datasets, i.e., SEED and SEED-IV, demonstrate that the proposed MSMAE consistently achieves stable results and outperforms competitive baseline methods in cross-session emotion recognition.Affective brain-computer interfaces (aBCIs) have garnered widespread applications, with remarkable advancements in utilizing electroencephalogram (EEG) technology for emotion recognition. However, the time-consuming process of annotating EEG data, inherent individual differences, non-stationary characteristics of EEG data, and noise artifacts in EEG data collection pose formidable challenges in developing subject-specific cross-session emotion recognition models. To simultaneously address these challenges, we propose a unified pre-training framework based on multi-scale masked autoencoders (MSMAE), which utilizes large-scale unlabeled EEG signals from multiple subjects and sessions to extract noise-robust, subject-invariant, and temporal-invariant features. We subsequently fine-tune the obtained generalized features with only a small amount of labeled data from a specific subject for personalization and enable cross-session emotion recognition. Our framework emphasizes: 1) Multi-scale representation to capture diverse aspects of EEG signals, obtaining comprehensive information; 2) An improved masking mechanism for robust channel-level representation learning, addressing missing channel issues while preserving inter-channel relationships; and 3) Invariance learning for regional correlations in spatial-level representation, minimizing inter-subject and inter-session variances. Under these elaborate designs, the proposed MSMAE exhibits a remarkable ability to decode emotional states from a different session of EEG data during the testing phase. Extensive experiments conducted on the two publicly available datasets, i.e., SEED and SEED-IV, demonstrate that the proposed MSMAE consistently achieves stable results and outperforms competitive baseline methods in cross-session emotion recognition.
Author	Vong, Chi-Man Chen, Chuangquan Pang, Miaoqi Wang, Hongtao Zeng, Zhiqiang Huang, Jiayang
Author_xml	– sequence: 1 givenname: Miaoqi surname: Pang fullname: Pang, Miaoqi organization: School of Electronics and Information Engineering, Wuyi University, Jiangmen, China – sequence: 2 givenname: Hongtao orcidid: 0000-0002-6564-5753 surname: Wang fullname: Wang, Hongtao organization: School of Electronics and Information Engineering, Wuyi University, Jiangmen, China – sequence: 3 givenname: Jiayang surname: Huang fullname: Huang, Jiayang organization: School of Electronics and Information Engineering, Wuyi University, Jiangmen, China – sequence: 4 givenname: Chi-Man orcidid: 0000-0001-7997-8279 surname: Vong fullname: Vong, Chi-Man organization: Department of Computer and Information Science, University of Macau, Macau, China – sequence: 5 givenname: Zhiqiang orcidid: 0000-0002-9544-5605 surname: Zeng fullname: Zeng, Zhiqiang organization: School of Electronics and Information Engineering, Wuyi University, Jiangmen, China – sequence: 6 givenname: Chuangquan orcidid: 0000-0002-3811-296X surname: Chen fullname: Chen, Chuangquan email: chenchuangquan87@163.com organization: School of Electronics and Information Engineering, Wuyi University, Jiangmen, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/38619940$$D View this record in MEDLINE/PubMed
BookMark	eNp9kUtv1DAUhS1URB_wBxBCkdiwyXD9tpfVaIBKLUidsrYc-6bKkImLnSz49ySdKUJdsLpX1neOfM85JydDGpCQtxRWlIL9dPdte7tZMWBixbmxwPULckalNDUwCifLzkUtOINTcl7KDoBqJfUrcsqNotYKOCObm6kfu3obfI_VjS8_MVaX05hwCCliLlWbcrXOqZR6i6V0aag2-zQu8xZDuh-6ZX9NXra-L_jmOC_Ij8-bu_XX-vr7l6v15XUdhGJj3XCNrNFGsahopCwaCYIHhRoNAnK0gnnVshhViNBC4GABRWuV95IH4Bfk6uAbk9-5h9ztff7tku_c40PK987nsQs9uihpi8xrjg0XjeHWqwhcGtlqOlvb2evjweshp18TltHtuxKw7_2AaSqOA7cGtNFqRj88Q3dpysN86UwJoSRlwGfq_ZGamj3Gv997CnsGzAEIS54ZWxe60S_5jdl3vaPgll7dY69u6dUde52l7Jn0yf2_oncHUYeI_wgkzEFo_gdzHKwO
CODEN	ITNSB3
CitedBy_id	crossref_primary_10_1038_s41598_025_95178_5 crossref_primary_10_1016_j_knosys_2025_113018 crossref_primary_10_3390_s24216912 crossref_primary_10_1007_s12559_025_10463_9 crossref_primary_10_1007_s11571_025_10277_3 crossref_primary_10_1109_TIM_2025_3590828 crossref_primary_10_3389_fphys_2024_1425582 crossref_primary_10_1088_1741_2552_ade290 crossref_primary_10_1109_TIM_2025_3565702 crossref_primary_10_1016_j_neunet_2025_107853
Cites_doi	10.1109/TAFFC.2022.3199075 10.1016/0013-4694(94)90053-1 10.1109/TCYB.2019.2904052 10.1109/TAFFC.2017.2712143 10.1109/TCYB.2018.2797176 10.1109/ICASSP43922.2022.9747398 10.1016/j.patrec.2014.05.011 10.1109/TBME.2012.2217495 10.1109/LSP.2019.2906826 10.1109/NER.2013.6695876 10.1109/TCYB.2017.2788081 10.1016/j.ins.2022.07.121 10.1109/TAFFC.2020.2994159 10.1109/TAFFC.2019.2922912 10.14569/IJACSA.2017.081046 10.1364/JOSA.55.000247 10.1109/TCDS.2019.2949306 10.1109/TAFFC.2017.2714671 10.1109/LSENS.2023.3347648 10.1109/TAFFC.2022.3170369 10.1155/2021/2520394 10.1109/TBME.2019.2897651 10.1109/ACCESS.2019.2945059 10.1038/s41597-023-02650-w 10.1109/TAFFC.2018.2817622 10.1109/tnnls.2022.3225855 10.1109/tim.2022.3168927 10.1145/3503161.3548243 10.1016/j.knosys.2021.107982 10.1016/j.dsp.2018.02.020 10.1177/1557234X11410385 10.1016/0013-4694(94)00181-2 10.1109/JSEN.2018.2883497 10.48550/ARXIV.1706.03762 10.1109/CVPR52688.2022.01553 10.1109/MCI.2015.2501545 10.1609/aaai.v34i03.5656 10.1109/TITB.2009.2034649 10.3389/fnins.2021.778488 10.1109/ACCESS.2020.2971600 10.1007/978-3-030-36708-4_3
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 CGR CUY CVF ECM EIF NPM 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D NAPCQ P64 7X8 DOA
DOI	10.1109/TNSRE.2024.3389037
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access (Activated by CARLI) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Neurosciences Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Nursing & Allied Health Premium Biotechnology and BioEngineering Abstracts MEDLINE - Academic DOAJ
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Materials Research Database Civil Engineering Abstracts Aluminium Industry Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Ceramic Abstracts Neurosciences Abstracts Materials Business File METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Aerospace Database Nursing & Allied Health Premium Engineered Materials Abstracts Biotechnology Research Abstracts Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic
DatabaseTitleList	MEDLINE Materials Research Database MEDLINE - Academic
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 4 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Occupational Therapy & Rehabilitation
EISSN	1558-0210
EndPage	1646
ExternalDocumentID	oai_doaj_org_article_d51fe2a73eb34b839a6d03585f710f09 38619940 10_1109_TNSRE_2024_3389037 10500357
Genre	orig-research Research Support, U.S. Gov't, Non-P.H.S Research Support, Non-U.S. Gov't Journal Article
GrantInformation_xml	– fundername: Projects for International Scientific and Technological Cooperation of Guangdong Province grantid: 2023A0505050144 – fundername: Hong Kong and Macau Joint Research and Development Fund of Wuyi University grantid: 2021WGALH19 – fundername: Guangdong Basic and Applied Basic Research Foundation grantid: 2023A1515011978; 2020A1515111154 funderid: 10.13039/501100021171 – fundername: National Natural Science Foundation of China grantid: 62201402 funderid: 10.13039/501100001809 – fundername: Department of Education of Guangdong Province; Educational Commission of Guangdong Province grantid: 2021KTSCX136 funderid: 10.13039/501100010226
GroupedDBID	--- -~X 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAFWJ AAJGR AASAJ AAWTH ABAZT ABVLG ACGFO ACGFS ACIWK ACPRK AENEX AETIX AFPKN AFRAH AGSQL AIBXA ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD ESBDL F5P GROUPED_DOAJ HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL OK1 P2P RIA RIE RNS AAYXX CITATION CGR CUY CVF ECM EIF NPM RIG 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D NAPCQ P64 7X8
ID	FETCH-LOGICAL-c462t-b37e2b7862d61d12d85043c6e7e8e0e3e942a6f2dd6cd0f0c3090e4f96aa53c03
IEDL.DBID	RIE
ISICitedReferencesCount	20
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001209532400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1534-4320 1558-0210
IngestDate	Fri Oct 03 12:47:41 EDT 2025 Sun Nov 09 09:34:16 EST 2025 Fri Jul 25 08:30:31 EDT 2025 Wed Feb 19 01:58:14 EST 2025 Tue Nov 18 21:45:11 EST 2025 Sat Nov 29 01:47:19 EST 2025 Wed Aug 27 02:06:33 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c462t-b37e2b7862d61d12d85043c6e7e8e0e3e942a6f2dd6cd0f0c3090e4f96aa53c03
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-7997-8279 0000-0002-6564-5753 0000-0002-3811-296X 0000-0002-9544-5605
OpenAccessLink	https://ieeexplore.ieee.org/document/10500357
PMID	38619940
PQID	3044651203
PQPubID	85423
PageCount	10
ParticipantIDs	proquest_journals_3044651203 pubmed_primary_38619940 crossref_citationtrail_10_1109_TNSRE_2024_3389037 doaj_primary_oai_doaj_org_article_d51fe2a73eb34b839a6d03585f710f09 ieee_primary_10500357 proquest_miscellaneous_3039807876 crossref_primary_10_1109_TNSRE_2024_3389037
PublicationCentury	2000
PublicationDate	20240000 2024-00-00 20240101 2024-01-01
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– year: 2024 text: 20240000
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on neural systems and rehabilitation engineering
PublicationTitleAbbrev	TNSRE
PublicationTitleAlternate	IEEE Trans Neural Syst Rehabil Eng
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 ref35 ref12 ref34 ref15 ref14 ref36 ref31 ref30 ref11 ref10 ref32 ref2 ref1 ref17 ref39 ref16 ref38 ref19 ref18 Beyer (ref33) 2022 Dosovitskiy (ref37) 2020 ref24 ref23 ref26 ref25 ref20 ref42 ref41 ref22 ref21 ref43 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40
References_xml	– ident: ref42 doi: 10.1109/TAFFC.2022.3199075 – ident: ref3 doi: 10.1016/0013-4694(94)90053-1 – ident: ref6 doi: 10.1109/TCYB.2019.2904052 – ident: ref31 doi: 10.1109/TAFFC.2017.2712143 – ident: ref32 doi: 10.1109/TCYB.2018.2797176 – ident: ref12 doi: 10.1109/ICASSP43922.2022.9747398 – ident: ref1 doi: 10.1016/j.patrec.2014.05.011 – volume-title: An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale year: 2020 ident: ref37 – ident: ref40 doi: 10.1109/TBME.2012.2217495 – ident: ref10 doi: 10.1109/LSP.2019.2906826 – ident: ref16 doi: 10.1109/NER.2013.6695876 – ident: ref24 doi: 10.1109/TCYB.2017.2788081 – ident: ref18 doi: 10.1016/j.ins.2022.07.121 – ident: ref8 doi: 10.1109/TAFFC.2020.2994159 – ident: ref7 doi: 10.1109/TAFFC.2019.2922912 – ident: ref23 doi: 10.14569/IJACSA.2017.081046 – ident: ref15 doi: 10.1364/JOSA.55.000247 – ident: ref26 doi: 10.1109/TCDS.2019.2949306 – ident: ref4 doi: 10.1109/TAFFC.2017.2714671 – ident: ref19 doi: 10.1109/LSENS.2023.3347648 – ident: ref35 doi: 10.1109/TAFFC.2022.3170369 – ident: ref34 doi: 10.1155/2021/2520394 – ident: ref41 doi: 10.1109/TBME.2019.2897651 – ident: ref21 doi: 10.1109/ACCESS.2019.2945059 – ident: ref43 doi: 10.1038/s41597-023-02650-w – ident: ref36 doi: 10.1109/TAFFC.2018.2817622 – ident: ref39 doi: 10.1109/tnnls.2022.3225855 – ident: ref22 doi: 10.1109/tim.2022.3168927 – ident: ref28 doi: 10.1145/3503161.3548243 – ident: ref9 doi: 10.1016/j.knosys.2021.107982 – ident: ref20 doi: 10.1016/j.dsp.2018.02.020 – ident: ref2 doi: 10.1177/1557234X11410385 – ident: ref13 doi: 10.1016/0013-4694(94)00181-2 – ident: ref17 doi: 10.1109/JSEN.2018.2883497 – year: 2022 ident: ref33 article-title: Better plain ViT baselines for ImageNet-1k publication-title: arXiv:2205.01580 – ident: ref30 doi: 10.48550/ARXIV.1706.03762 – ident: ref29 doi: 10.1109/CVPR52688.2022.01553 – ident: ref5 doi: 10.1109/MCI.2015.2501545 – ident: ref38 doi: 10.1609/aaai.v34i03.5656 – ident: ref14 doi: 10.1109/TITB.2009.2034649 – ident: ref25 doi: 10.3389/fnins.2021.778488 – ident: ref11 doi: 10.1109/ACCESS.2020.2971600 – ident: ref27 doi: 10.1007/978-3-030-36708-4_3
SSID	ssj0017657
Score	2.5057106
Snippet	Affective brain-computer interfaces (aBCIs) have garnered widespread applications, with remarkable advancements in utilizing electroencephalogram (EEG)...
SourceID	doaj proquest pubmed crossref ieee
SourceType	Open Website Aggregation Database Index Database Enrichment Source Publisher
StartPage	1637
SubjectTerms	Adult Algorithms Brain modeling Brain-Computer Interfaces cross-session Data collection Data mining Data models EEG EEG-based emotion recognition Electroencephalography Electroencephalography - methods Emotion recognition Emotional factors Emotions Emotions - physiology Feature extraction Female Human-computer interface Humans Invariants Machine Learning Male Neural Networks, Computer Representations Robustness self-supervised learning Task analysis transformer
SummonAdditionalLinks	– databaseName: DOAJ dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nj9MwELXQigMXxMcCgQUZCbggs27s2PFxWXXFhQq1Rdqb5dgTCYHS1bbl9zNjJ1U5ABeujeNO3owzMxn7DWNvbJJgjA7ChmSENsGJDjMh0bU6GacBs66Um03YxaK9vnZfjlp90Z6wQg9cgDtPzayHOliFWZ_u0J0Hk6TCILdH39iXo3vSuimZGusH1mSOT1zOWmhVy-m4jHTn68VqOcfEsNYfUCgnqQP6kUvKzP1jq5U_R53Z-1w9YPfHsJFfFHEfsjswPGJvjymC-brwA_B3fPkb-_ZjNs-nbMUK1QH8c9h-h8Qv9rsNcVjSPmaOgSu_JNnEqtB08Hnp7sOX0_6izXDKvl7N15efxNg-QURt6h1ibqHuLKYsyczSrE4tsZVFAxZakKDA6TqYvk7JxIRQRiWdBN07E0KjolRP2MmwGeAZ4wGaGGvoWtkDzu26hsp31vb4Omih0xWbTQj6OD4dtbj44XOOIZ3PqHtC3Y-oV-z94Z6bwqzx19EfSTGHkcSKnX9AW_Gjrfh_2UrFTkmtR3_XUCUVJz-b9OzHJbz1ikrdGA5JVbHXh8u4-KiiEgbY7GmMckTYb03Fnhb7OEyuWkO8y_L5_5D8BbtHaJRvP2fsZHe7h5fsbvy5-7a9fZVt_xfqDQJu priority: 102 providerName: Directory of Open Access Journals
Title	Multi-Scale Masked Autoencoders for Cross-Session Emotion Recognition
URI	https://ieeexplore.ieee.org/document/10500357 https://www.ncbi.nlm.nih.gov/pubmed/38619940 https://www.proquest.com/docview/3044651203 https://www.proquest.com/docview/3039807876 https://doaj.org/article/d51fe2a73eb34b839a6d03585f710f09
Volume	32
WOSCitedRecordID	wos001209532400001&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: 1558-0210 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017657 issn: 1534-4320 databaseCode: DOA dateStart: 20210101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0210 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017657 issn: 1534-4320 databaseCode: RIE dateStart: 20010101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELZoxYELzwIpZWUk4IJSvLZjx8dSbcWFFdpdpL1Fjj2REChB3V1-f2ech9pDkbhFieNHPk884_F8w9h7GwUYo31ufTS5Nt7lNVpCeV3qaJwGtLpiSjZhl8tyu3Xfh2D1FAsDAOnwGZzTZfLlxy4caKsMJbwgz5c9YkfWmj5Ya3IZWJNoPVGCda6VFGOEjHCfN8v1aoG2oNTn2A8nFKXeU6UhXlxxZ0FKvP1DopX7dc609lw9-c9eP2WPByWTX_Sz4hl7AO1z9uE2oTDf9GwC_CNf3eHqfsEWKSY3XyN4wL_53S-I_OKw74jxkk49c1Rz-SWNJV_3pB580ecC4qvxNFLXnrAfV4vN5dd8SLaQB23kHhGyIGuLBk408ziXsSRus2DAQgkCFDgtvWlkjCZE0YighBOgG2e8L1QQ6iU7brsWXjPuoQhBQl2KBrBuVxfk7LO2wZ9HCbXO2Hz84lUYRkcJMX5XySIRrkqAVQRYNQCWsU_TO396Ho5_lv5CQE4liUM73UBgqkEkq1jMG5DeKqiVrlFR9CYiTmXRoNbVCJexEwLzVnM9jhk7G-dFNQj8rlLkGEflSaiMvZseo6iS_8W30B2ojHJE729Nxl7182mqfJyNp_c0-oY9ogH2mz9n7Hh_fYC37GH4u_-5u56hPGzLWdpPmCWpuAFuQwPR
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5BQYILzxYCBYwEXFCK13bs-FiqrYpoV2h3kXqLHHsioVZZ1N3l9-NxHmoPReIWJY4f-TzxjMfzDcAHEzhqrVxuXNC50s7mdbSE8rpUQVuF0eoKKdmEmc3K83P7ow9WT7EwiJgOn-EBXSZfflj5LW2VRQkvyPNl7sK9QinBu3Ct0WlgdCL2jDKsciUFH2JkuP2ynC3m02gNCnUQe2K5pOR7stTEjMtvLEmJub9PtXK71plWn-PH_9nvJ_CoVzPZYTcvnsIdbJ_Bx-uUwmzZ8QmwT2x-g637OUxTVG6-iPAhO3PrCwzscLtZEeclnXtmUdFlRzSWfNHRerBplw2IzYfzSKt2F34eT5dHJ3mfbiH3SotNxMigqE00cYKehIkIJbGbeY0GS-Qo0SrhdCNC0D7whnvJLUfVWO1cIT2Xe7DTrlp8Ccxh4b3AuuQNxrptXZC7z5gm_j5KrFUGk-GLV74fHaXEuKySTcJtlQCrCLCqByyDz-M7vzsmjn-W_kpAjiWJRTvdiMBUvVBWoZg0KJyRWEtVR1XR6RBxKosm6l0NtxnsEpjXmutwzGB_mBdVL_LrSpJrPKpPXGbwfnwchZU8MK7F1ZbKSEsE_0Zn8KKbT2Plw2x8dUuj7-DByfLstDr9Nvv-Gh7SYLutoH3Y2Vxt8Q3c9382v9ZXb5NU_AXaMAU7
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=Multi-Scale+Masked+Autoencoders+for+Cross-Session+Emotion+Recognition&rft.jtitle=IEEE+transactions+on+neural+systems+and+rehabilitation+engineering&rft.au=Pang%2C+Miaoqi&rft.au=Wang%2C+Hongtao&rft.au=Huang%2C+Jiayang&rft.au=Vong%2C+Chi-Man&rft.date=2024&rft.pub=IEEE&rft.issn=1534-4320&rft.volume=32&rft.spage=1637&rft.epage=1646&rft_id=info:doi/10.1109%2FTNSRE.2024.3389037&rft_id=info%3Apmid%2F38619940&rft.externalDocID=10500357
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1534-4320&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1534-4320&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1534-4320&client=summon