{"id":"https://openalex.org/W4392903778","doi":"https://doi.org/10.1109/icassp48485.2024.10447194","title":"Multimodal Multi-View Spectral-Spatial-Temporal Masked Autoencoder for Self-Supervised Emotion Recognition","display_name":"Multimodal Multi-View Spectral-Spatial-Temporal Masked Autoencoder for Self-Supervised Emotion Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903778","doi":"https://doi.org/10.1109/icassp48485.2024.10447194"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5114137001","display_name":"Pengxuan Gao","orcid":null},"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":"Pengxuan Gao","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017004315","display_name":"Tianyu Liu","orcid":"https://orcid.org/0000-0002-9412-6573"},"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":"Tianyu Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617624","display_name":"Jiawen Liu","orcid":"https://orcid.org/0000-0001-8673-1514"},"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":"Jia-Wen Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","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,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, 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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1926","last_page":"1930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9968000054359436,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7517569065093994},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7078076004981995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6926141977310181},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5971803069114685},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5079498887062073},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4992196559906006},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4237879812717438},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4159961938858032},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36291563510894775},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2851349711418152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7517569065093994},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7078076004981995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6926141977310181},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5971803069114685},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5079498887062073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4992196559906006},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4237879812717438},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4159961938858032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36291563510894775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2851349711418152},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G126313119","display_name":null,"funder_award_id":"2022ZD0208500","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5856684975","display_name":null,"funder_award_id":"62376158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6059964893","display_name":null,"funder_award_id":"STI 2030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"},{"id":"https://openalex.org/F4320330117","display_name":"Ruijin Hospital","ror":"https://ror.org/01hv94n30"},{"id":"https://openalex.org/F4320335305","display_name":"School of Medicine, Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1539811621","https://openalex.org/W1947251450","https://openalex.org/W2074788634","https://openalex.org/W2126698740","https://openalex.org/W2517194566","https://openalex.org/W2525648609","https://openalex.org/W2546919788","https://openalex.org/W2786768213","https://openalex.org/W2792191740","https://openalex.org/W2842511635","https://openalex.org/W2945331847","https://openalex.org/W2962905870","https://openalex.org/W3002833466","https://openalex.org/W3101658985","https://openalex.org/W3159301005","https://openalex.org/W3177342940","https://openalex.org/W4297808394","https://openalex.org/W4304086659","https://openalex.org/W6631216910","https://openalex.org/W6774314701"],"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/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,54],"is":[2,114],"a":[3,39],"primary":[4],"and":[5,59,83,103,145,173],"complex":[6],"task":[7],"in":[8,176],"emotional":[9],"intelligence.":[10],"Due":[11],"to":[12,50,77,97,101,116,122],"the":[13,24,28,71,89,92,98,105,109,124,134,139,150,167],"complexity":[14],"of":[15,31,126,161,169],"human":[16],"emotions,":[17],"utilizing":[18],"multimodal":[19,52,135,170],"fusion":[20,136,175],"methods":[21],"can":[22,153],"enhance":[23],"performance":[25],"by":[26],"leveraging":[27],"complementary":[29],"properties":[30],"different":[32,127],"modalities.":[33],"In":[34,70,88,108,148],"this":[35],"paper,":[36],"we":[37,74],"propose":[38],"Multimodal":[40],"Multi-view":[41],"Spectral-Spatial-Temporal":[42],"Masked":[43],"Autoencoder":[44],"(Multimodal":[45],"MV-SSTMA)":[46],"with":[47,119,158],"self-supervised":[48,171],"learning":[49,172],"investigate":[51],"emotion":[53,177],"based":[55],"on":[56,142],"electroencephalogram":[57],"(EEG)":[58],"eye":[60,84],"movement":[61,85],"signals.":[62],"Our":[63,129],"experimental":[64,130],"process":[65],"comprises":[66],"three":[67],"stages:":[68],"1)":[69],"pre-training":[72],"stage,":[73,91,111],"employ":[75],"MV-SSTMA":[76],"train":[78],"feature":[79,99],"extractors":[80,100],"for":[81],"EEG":[82],"signals;":[86],"2)":[87],"fine-tuning":[90],"labeled":[93],"data":[94,121,174],"are":[95],"input":[96],"fuse":[102],"fine-tune":[104],"features;":[106],"3)":[107],"testing":[110],"our":[112],"model":[113,137,141,152],"applied":[115],"recognize":[117,156],"emotions":[118,157],"test":[120],"calculate":[123],"accuracies":[125],"methods.":[128],"results":[131,165],"demonstrate":[132],"that":[133],"outperforms":[138],"unimodal":[140],"both":[143],"SEED-IV":[144],"SEED-V":[146],"datasets.":[147],"addition,":[149],"proposed":[151],"still":[154],"effectively":[155],"various":[159],"ratios":[160],"missing":[162],"data.":[163],"These":[164],"underscore":[166],"efficiency":[168],"recognition.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}