{"id":"https://openalex.org/W3207379732","doi":"https://doi.org/10.1145/3475957.3484457","title":"Hybrid Mutimodal Fusion for Dimensional Emotion Recognition","display_name":"Hybrid Mutimodal Fusion for Dimensional Emotion Recognition","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3207379732","doi":"https://doi.org/10.1145/3475957.3484457","mag":"3207379732"},"language":"en","primary_location":{"id":"doi:10.1145/3475957.3484457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3475957.3484457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge","raw_type":"proceedings-article"},"type":"article","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/A5016070961","display_name":"Ziyu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziyu Ma","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090221825","display_name":"Fuyan Ma","orcid":"https://orcid.org/0000-0003-0483-8866"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyan Ma","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641761","display_name":"Bin Sun","orcid":"https://orcid.org/0000-0002-7029-8784"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Sun","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067097659","display_name":"Shutao Li","orcid":"https://orcid.org/0000-0002-0585-9848"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutao Li","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016070961"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":3.0913,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91469391,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/arousal","display_name":"Arousal","score":0.7644557356834412},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6344300508499146},{"id":"https://openalex.org/keywords/trier-social-stress-test","display_name":"Trier social stress test","score":0.6310804486274719},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.6186634302139282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5670616626739502},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.4813474118709564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46079808473587036},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4531181752681732},{"id":"https://openalex.org/keywords/emotional-valence","display_name":"Emotional valence","score":0.44963783025741577},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4213706851005554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36980101466178894},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18642881512641907},{"id":"https://openalex.org/keywords/fight-or-flight-response","display_name":"Fight-or-flight response","score":0.17704173922538757},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.0972852110862732},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08084598183631897}],"concepts":[{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.7644557356834412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6344300508499146},{"id":"https://openalex.org/C2778597338","wikidata":"https://www.wikidata.org/wiki/Q7841444","display_name":"Trier social stress test","level":4,"score":0.6310804486274719},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.6186634302139282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5670616626739502},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.4813474118709564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46079808473587036},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4531181752681732},{"id":"https://openalex.org/C3020774634","wikidata":"https://www.wikidata.org/wiki/Q3113318","display_name":"Emotional valence","level":3,"score":0.44963783025741577},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4213706851005554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36980101466178894},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18642881512641907},{"id":"https://openalex.org/C78604142","wikidata":"https://www.wikidata.org/wiki/Q1640582","display_name":"Fight-or-flight response","level":3,"score":0.17704173922538757},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.0972852110862732},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08084598183631897},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3475957.3484457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3475957.3484457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2016430603","https://openalex.org/W2025427990","https://openalex.org/W2026243162","https://openalex.org/W2049146462","https://openalex.org/W2085662862","https://openalex.org/W2124737236","https://openalex.org/W2149628368","https://openalex.org/W2149735953","https://openalex.org/W2156848952","https://openalex.org/W2168056503","https://openalex.org/W2239141610","https://openalex.org/W2250539671","https://openalex.org/W2325939864","https://openalex.org/W2514240795","https://openalex.org/W2526050071","https://openalex.org/W2584561145","https://openalex.org/W2593116425","https://openalex.org/W2765291577","https://openalex.org/W2766925079","https://openalex.org/W2896480997","https://openalex.org/W2897337310","https://openalex.org/W2917316317","https://openalex.org/W2950133940","https://openalex.org/W2972660800","https://openalex.org/W2981938460","https://openalex.org/W2995179497","https://openalex.org/W3016138882","https://openalex.org/W3097075955","https://openalex.org/W3206776536"],"related_works":["https://openalex.org/W2087245461","https://openalex.org/W3080495370","https://openalex.org/W4386983308","https://openalex.org/W2170701947","https://openalex.org/W4285597148","https://openalex.org/W2026281216","https://openalex.org/W4382195843","https://openalex.org/W2013608943","https://openalex.org/W4385782599","https://openalex.org/W2901531394"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,118,211],"extensively":[4],"present":[5],"our":[6,120],"solutions":[7,121],"for":[8,135,191,247],"the":[9,13,30,45,53,76,88,115,126,130,140,146,157,161,170,197,204,208,214,218,225,229,233,242,249,254,257,272,278],"MuSe-Stress":[10,25,116],"sub-challenge":[11,15,26,49],"and":[12,35,44,129,189,193,217,232],"MuSe-Physio":[14,48,209],"of":[16,24,32,47,55,87,187,269],"Multimodal":[17],"Sentiment":[18],"Challenge":[19],"(MuSe)":[20],"2021.":[21],"The":[22,79],"goal":[23,46],"is":[27,50,83,109,149,165,261],"to":[28,51,151,167],"predict":[29,52],"level":[31,54],"emotional":[33,136],"arousal":[34,57,194],"valence":[36,192],"in":[37,99,111,122,203,253,277],"a":[38,84,100],"time-continuous":[39],"manner":[40],"from":[41,58,75,221],"audio-visual":[42,89,127,215],"recordings":[43],"psycho-physiological":[56],"a)":[59],"human":[60],"annotations":[61],"fused":[62],"with":[63,145,228],"b)":[64],"galvanic":[65],"skin":[66],"response":[67],"(also":[68],"known":[69],"as":[70,239,241],"Electrodermal":[71],"Activity":[72],"(EDA))":[73],"signals":[74],"stressed":[77],"people.":[78],"Ulm-TSST":[80],"dataset":[81,94],"which":[82,200,275],"novel":[85],"subset":[86],"textual":[90],"Ulm-Trier":[91],"Social":[92,102],"Stress":[93,103],"that":[95],"features":[96,128,132,216,220],"German":[97],"speakers":[98],"Trier":[101],"Test":[104],"(TSST)":[105],"induced":[106],"stress":[107],"situation":[108],"used":[110,134],"both":[112,201],"sub-challenges.":[113],"For":[114,207],"sub-challenge,":[117,210],"highlight":[119],"three":[123],"aspects:":[124],"1)":[125],"bio-signal":[131,219],"are":[133,245],"state":[137],"recognition.":[138],"2)":[139],"Long":[141],"Short-Term":[142],"Memory":[143],"(LSTM)":[144],"self-attention":[147,230],"mechanism":[148],"utilized":[150,246],"capture":[152],"complex":[153,250],"temporal":[154,251],"dependencies":[155,252],"within":[156],"feature":[158],"sequences.":[159,181],"3)":[160],"late":[162,258],"fusion":[163,259],"strategy":[164,260],"adopted":[166],"further":[168],"boost":[169],"model's":[171],"recognition":[172],"performance":[173],"by":[174],"exploiting":[175],"complementary":[176],"information":[177],"scattered":[178],"across":[179],"multimodal":[180],"Our":[182,263],"proposed":[183,264],"model":[184],"achieves":[185,267],"CCC":[186,268],"0.6159":[188],"0.4609":[190],"respectively":[195],"on":[196,271],"test":[198,273],"set,":[199,274],"rank":[202],"top":[205,279],"3.":[206,280],"first":[212],"extract":[213],"multiple":[222],"modalities.":[223],"Then,":[224],"LSTM":[226,243],"module":[227],"mechanism,":[231],"Gated":[234],"Convolutional":[235],"Neural":[236],"Networks":[237],"(GCNN)":[238],"well":[240],"network":[244],"modeling":[248],"sequence.":[255],"Finally,":[256],"used.":[262],"method":[265],"also":[266],"0.5412":[270],"ranks":[276]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}