{"id":"https://openalex.org/W4388820998","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317160","title":"Hybrid Multi-Task Learning for End-To-End Multimodal Emotion Recognition","display_name":"Hybrid Multi-Task Learning for End-To-End Multimodal Emotion Recognition","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820998","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317160"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317160","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5033905932","display_name":"Junjie Chen","orcid":"https://orcid.org/0000-0002-3536-3501"},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Chen","raw_affiliation_strings":["Tianjin Normal University,College of Computer and Information Engineering,Tianjin,China","College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Normal University,College of Computer and Information Engineering,Tianjin,China","institution_ids":["https://openalex.org/I15062923"]},{"raw_affiliation_string":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100717753","display_name":"Yongwei Li","orcid":"https://orcid.org/0000-0001-7799-366X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Li","raw_affiliation_strings":["Chinese Academy of Sciences,National Laboratory of Pattern Recognition, Institute of Automation,Beijing,China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,National Laboratory of Pattern Recognition, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052655362","display_name":"Ziping Zhao","orcid":"https://orcid.org/0000-0002-8719-6389"},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziping Zhao","raw_affiliation_strings":["Tianjin Normal University,College of Computer and Information Engineering,Tianjin,China","College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Normal University,College of Computer and Information Engineering,Tianjin,China","institution_ids":["https://openalex.org/I15062923"]},{"raw_affiliation_string":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048672759","display_name":"Xuefei Liu","orcid":"https://orcid.org/0000-0001-5120-0633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Liu","raw_affiliation_strings":["Chinese Academy of Sciences,National Laboratory of Pattern Recognition, Institute of Automation,Beijing,China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,National Laboratory of Pattern Recognition, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Chinese Academy of Sciences,National Laboratory of Pattern Recognition, Institute of Automation,Beijing,China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,National Laboratory of Pattern Recognition, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China","Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1966","last_page":"1971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T11795","display_name":"Humor Studies and Applications","score":0.9800999760627747,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7636715769767761},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.669620156288147},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6528608798980713},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5912137031555176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5510384440422058},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.5331776738166809},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49351418018341064},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48192858695983887},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4775972366333008},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46991291642189026},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.430270791053772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35229405760765076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33528369665145874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3233509063720703},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061070531606674194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636715769767761},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.669620156288147},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6528608798980713},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5912137031555176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510384440422058},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.5331776738166809},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49351418018341064},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48192858695983887},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4775972366333008},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46991291642189026},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.430270791053772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35229405760765076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33528369665145874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3233509063720703},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061070531606674194},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317160","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"},{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2896457183","https://openalex.org/W2962770129","https://openalex.org/W2972463723","https://openalex.org/W2972602947","https://openalex.org/W3088631780","https://openalex.org/W3094805191","https://openalex.org/W3095251683","https://openalex.org/W3096723250","https://openalex.org/W3096963953","https://openalex.org/W3097571315","https://openalex.org/W3156064856","https://openalex.org/W3177692126","https://openalex.org/W3198220993","https://openalex.org/W3208480086","https://openalex.org/W3209072429","https://openalex.org/W3209984917","https://openalex.org/W4224916778","https://openalex.org/W4224916926","https://openalex.org/W4224917001","https://openalex.org/W4224920209","https://openalex.org/W4225319211","https://openalex.org/W4290072727","https://openalex.org/W4297841926","https://openalex.org/W4372260395","https://openalex.org/W4372266796"],"related_works":["https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W4301248618","https://openalex.org/W2165343651","https://openalex.org/W2242427765","https://openalex.org/W2075830955","https://openalex.org/W1550318927","https://openalex.org/W2343790552","https://openalex.org/W4305042383","https://openalex.org/W2546649374"],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1,24,58,74,82,89,104,133],"recognition":[2],"plays":[3],"a":[4,66,141],"pivotal":[5],"role":[6],"in":[7,76,101,129],"the":[8,27,38,48,55,78,85,107,112,147],"advancement":[9],"of":[10,32,41,57,97,149],"natural":[11],"human-computer":[12],"interaction":[13],"systems.":[14],"Recent":[15],"studies":[16],"have":[17],"attempted":[18],"to":[19,23,36,47,52],"apply":[20],"multi-task":[21,28,68],"learning":[22,56,69],"recognition.":[25],"However,":[26],"shared":[29],"feature":[30,39,49,136],"extractor":[31,50],"traditional":[33],"methods":[34],"needs":[35],"integrate":[37],"representations":[40],"different":[42],"tasks,":[43],"which":[44,77],"may":[45],"lead":[46],"failing":[51],"focus":[53],"on":[54,140],"representations.":[59],"To":[60],"address":[61],"this":[62],"problem,":[63],"we":[64],"propose":[65],"hybrid":[67],"framework":[70,95],"for":[71],"end-to-end":[72],"multimodal":[73],"recognition,":[75,105],"primary":[79],"task":[80],"is":[81],"classification,":[83],"and":[84,91,103,134],"auxiliary":[86],"tasks":[87],"are":[88],"regression":[90],"gender":[92,102,135],"classification.":[93],"This":[94],"consists":[96],"two":[98],"networks":[99],"specialized":[100],"where":[106],"latter":[108],"transfers":[109],"knowledge":[110],"from":[111],"former":[113],"through":[114],"our":[115,150],"proposed":[116,151],"Deep":[117],"Aggregation":[118],"LSTM":[119],"(DA-LSTM).":[120],"The":[121],"DA-LSTM":[122],"could":[123],"more":[124],"precisely":[125],"capture":[126],"emotional":[127],"information":[128],"discourse":[130],"by":[131],"aggregating":[132],"extractors.":[137],"Experimental":[138],"results":[139],"commonly":[142],"used":[143],"dataset":[144],"IEMOCAP":[145],"demonstrate":[146],"effectiveness":[148],"method.":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}