{"id":"https://openalex.org/W4304086659","doi":"https://doi.org/10.1145/3503161.3548243","title":"A Multi-view Spectral-Spatial-Temporal Masked Autoencoder for Decoding Emotions with Self-supervised Learning","display_name":"A Multi-view Spectral-Spatial-Temporal Masked Autoencoder for Decoding Emotions with Self-supervised Learning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304086659","doi":"https://doi.org/10.1145/3503161.3548243"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548243","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100360732","display_name":"Rui Li","orcid":"https://orcid.org/0000-0003-3691-1335"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389973","display_name":"Yiting Wang","orcid":"https://orcid.org/0000-0003-3224-239X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiting Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056335002","display_name":"Wei\u2010Long Zheng","orcid":"https://orcid.org/0000-0002-9474-6369"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Long Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040440605","display_name":"Bao\u2010Liang Lu","orcid":"https://orcid.org/0000-0001-8359-0058"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bao-Liang Lu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai , China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7741316556930542},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7445440888404846},{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.7342319488525391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6297552585601807},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5736215114593506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4832082986831665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.473166286945343},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4407612085342407},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3492886424064636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3338443636894226},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08777734637260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741316556930542},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7445440888404846},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.7342319488525391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6297552585601807},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5736215114593506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4832082986831665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.473166286945343},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4407612085342407},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3492886424064636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3338443636894226},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08777734637260437},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548243","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.41999998688697815,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1981328190","display_name":null,"funder_award_id":"No. 61976135","funder_id":"https://openalex.org/F4320334062","funder_display_name":"National Natural Science Foundation of China-Liaoning Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320334062","display_name":"National Natural Science Foundation of China-Liaoning Joint Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1575391563","https://openalex.org/W1947251450","https://openalex.org/W1970727126","https://openalex.org/W2022218469","https://openalex.org/W2025768430","https://openalex.org/W2082696270","https://openalex.org/W2157725122","https://openalex.org/W2171237477","https://openalex.org/W2587844010","https://openalex.org/W2613375858","https://openalex.org/W2786768213","https://openalex.org/W2790404832","https://openalex.org/W2808223797","https://openalex.org/W2950162539","https://openalex.org/W2962905870","https://openalex.org/W3024961463","https://openalex.org/W3033046106","https://openalex.org/W3093125198","https://openalex.org/W3101658985","https://openalex.org/W3173151551","https://openalex.org/W3205895886"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4392946183","https://openalex.org/W3088732000"],"abstract_inverted_index":{"Affective":[0],"Brain-computer":[1],"Interface":[2],"has":[3],"achieved":[4],"considerable":[5],"advances":[6],"that":[7,189],"researchers":[8],"can":[9,163,211],"successfully":[10],"interpret":[11],"labeled":[12,143],"and":[13,29,98,124],"flawless":[14],"EEG":[15,25,44,51,93,116,133,170,186],"data":[16,26,45,117,144,171],"collected":[17,43],"in":[18,38],"laboratory":[19],"settings.":[20],"However,":[21],"the":[22,36,89,109,129,137,153,157,168,202,208],"annotation":[23],"of":[24,92,104,114,205],"is":[27,80],"time-consuming":[28],"requires":[30],"a":[31,62,83,146],"vast":[32],"workforce":[33],"which":[34],"limits":[35],"application":[37],"practical":[39],"scenarios.":[40],"Furthermore,":[41],"daily":[42,76],"may":[46],"be":[47],"partially":[48],"damaged":[49,175],"since":[50],"signals":[52,94],"are":[53,121,149],"sensitive":[54],"to":[55,71,127,151],"noise.":[56],"In":[57,108,136,156,199],"this":[58],"paper,":[59],"we":[60],"propose":[61],"Multi-view":[63],"Spectral-Spatial-Temporal":[64],"Masked":[65],"Autoencoder":[66],"(MV-SSTMA)":[67],"with":[68,177],"self-supervised":[69],"learning":[70],"tackle":[72],"these":[73],"challenges":[74],"towards":[75],"applications.":[77],"The":[78],"MV-SSTMA":[79],"based":[81],"on":[82,182,196],"multi-view":[84],"CNN-Transformer":[85],"hybrid":[86],"structure,":[87],"interpreting":[88],"emotion-related":[90],"knowledge":[91],"from":[95,118,132,145,167],"spectral,":[96],"spatial,":[97],"temporal":[99],"perspectives.":[100],"Our":[101],"model":[102,162,192,210],"consists":[103],"three":[105],"stages:":[106],"1)":[107],"generalized":[110],"pre-training":[111],"stage,":[112,140,160],"channels":[113],"unlabeled":[115],"all":[119],"subjects":[120],"randomly":[122],"masked":[123],"later":[125],"reconstructed":[126],"learn":[128],"generic":[130],"representations":[131],"data;":[134],"2)":[135],"personalized":[138],"calibration":[139],"only":[141],"few":[142],"specific":[147],"subject":[148],"used":[150],"calibrate":[152],"model;":[154],"3)":[155],"personal":[158,165],"test":[159],"our":[161,190],"decode":[164],"emotions":[166],"sound":[169],"as":[172,174],"well":[173],"ones":[176],"missing":[178,206],"channels.":[179],"Extensive":[180],"experiments":[181],"two":[183],"open":[184],"emotional":[185],"datasets":[187],"demonstrate":[188],"proposed":[191,209],"achieves":[193],"state-of-the-art":[194],"performance":[195],"emotion":[197],"recognition.":[198],"addition,":[200],"under":[201],"abnormal":[203],"circumstance":[204],"channels,":[207],"still":[212],"effectively":[213],"recognize":[214],"emotions.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}