{"id":"https://openalex.org/W4385570058","doi":"https://doi.org/10.18653/v1/2023.acl-long.861","title":"A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations","display_name":"A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385570058","doi":"https://doi.org/10.18653/v1/2023.acl-long.861"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-long.861","doi":"https://doi.org/10.18653/v1/2023.acl-long.861","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.861","pdf_url":"https://aclanthology.org/2023.acl-long.861.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.acl-long.861.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109059341","display_name":"Wenjie Zheng","orcid":"https://orcid.org/0009-0002-2965-9012","observed_orcids":["https://orcid.org/0009-0002-2965-9012"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084990301","display_name":"Jianfei Yu","orcid":"https://orcid.org/0000-0001-8380-0609","observed_orcids":["https://orcid.org/0000-0001-8380-0609"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfei Yu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035534911","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0002-0621-1058","observed_orcids":["https://orcid.org/0000-0002-0621-1058"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069365665","display_name":"Shijin Wang","orcid":"https://orcid.org/0000-0002-4788-0530","observed_orcids":["https://orcid.org/0000-0002-4788-0530"]},"institutions":[{"id":"https://openalex.org/I4401726934","display_name":"IFlyTek (China)","ror":"https://ror.org/009pwww24","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726934"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijin Wang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, Hefei, China","iFLYTEK AI Research (Central China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK AI Research (Central China)","institution_ids":["https://openalex.org/I4401726934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.7831,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.99424217,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"15445","last_page":"15459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0005000000237487257,"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":0.00019999999494757503,"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/multimodal-emotion-recognition","display_name":"multimodal emotion recognition","score":0.9580000042915344},{"id":"https://openalex.org/keywords/multiparty-conversation","display_name":"multi-party conversation","score":0.8679999709129333},{"id":"https://openalex.org/keywords/facial-expressions","display_name":"facial expressions","score":0.7900000214576721},{"id":"https://openalex.org/keywords/face-matching","display_name":"face matching","score":0.9789999723434448},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.8579999804496765},{"id":"https://openalex.org/keywords/meld-dataset","display_name":"MELD dataset","score":0.9319999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276732563972473},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.722581684589386},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6511408686637878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5890262722969055},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.58655846118927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5560617446899414},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.552811324596405},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.511814534664154},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5005311965942383},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.480092316865921},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4776146113872528},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4757670760154724},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4575906991958618},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4322693347930908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3206964135169983},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.acl-long.861","doi":"https://doi.org/10.18653/v1/2023.acl-long.861","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.861","pdf_url":"https://aclanthology.org/2023.acl-long.861.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-long.861","doi":"https://doi.org/10.18653/v1/2023.acl-long.861","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.861","pdf_url":"https://aclanthology.org/2023.acl-long.861.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.6299999952316284,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3452498813","display_name":null,"funder_award_id":"BK20200463","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G4800195568","display_name":null,"funder_award_id":"62076133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6056900124","display_name":null,"funder_award_id":"62006117","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/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385570058.pdf","grobid_xml":"https://content.openalex.org/works/W4385570058.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W237546731","https://openalex.org/W1494198834","https://openalex.org/W1509966554","https://openalex.org/W1522734439","https://openalex.org/W2035372623","https://openalex.org/W2103943262","https://openalex.org/W2164998314","https://openalex.org/W2194775991","https://openalex.org/W2341528187","https://openalex.org/W2395639500","https://openalex.org/W2515770085","https://openalex.org/W2626778328","https://openalex.org/W2885318751","https://openalex.org/W2895615590","https://openalex.org/W2896457183","https://openalex.org/W2947476638","https://openalex.org/W2949391930","https://openalex.org/W2964300796","https://openalex.org/W2964350391","https://openalex.org/W2965373594","https://openalex.org/W2965453734","https://openalex.org/W2981852735","https://openalex.org/W2982399380","https://openalex.org/W3036601975","https://openalex.org/W3083650259","https://openalex.org/W3091972294","https://openalex.org/W3113225429","https://openalex.org/W3116016199","https://openalex.org/W3118966983","https://openalex.org/W3119221111","https://openalex.org/W3133752603","https://openalex.org/W3138516171","https://openalex.org/W3168391820","https://openalex.org/W3169801598","https://openalex.org/W3173396651","https://openalex.org/W3175552668","https://openalex.org/W3199665477","https://openalex.org/W3206008172","https://openalex.org/W3206349670","https://openalex.org/W3210095593","https://openalex.org/W3211488063","https://openalex.org/W4220849944","https://openalex.org/W4221147459","https://openalex.org/W4221154966","https://openalex.org/W4225568094","https://openalex.org/W4226025958","https://openalex.org/W4281397735","https://openalex.org/W4283789934","https://openalex.org/W4283815599","https://openalex.org/W4287689635","https://openalex.org/W4287887917","https://openalex.org/W4288102735","https://openalex.org/W4292829120","https://openalex.org/W4293370939","https://openalex.org/W4303649263","https://openalex.org/W4304099179","https://openalex.org/W4309426823","https://openalex.org/W4312773554","https://openalex.org/W4360930863","https://openalex.org/W4385573848","https://openalex.org/W4403242122"],"related_works":["https://openalex.org/W4408352935","https://openalex.org/W4387687324","https://openalex.org/W7214086368","https://openalex.org/W7164920697","https://openalex.org/W7207648597","https://openalex.org/W4405513150","https://openalex.org/W4417051753","https://openalex.org/W4360853195","https://openalex.org/W4389650539","https://openalex.org/W4367856500"],"abstract_inverted_index":{"Multimodal":[0,95],"Emotion":[1],"Recognition":[2],"in":[3,18,54],"Multiparty":[4],"Conversations":[5],"(MERMC)":[6],"has":[7],"recently":[8],"attracted":[9],"considerable":[10],"attention.Due":[11],"to":[12,39,76,105,149],"the":[13,49,59,77,81,107,111,129,144,160,163,168],"complexity":[14],"of":[15,51,80,110,114,119,162],"visual":[16,34,44,52],"scenes":[17],"multi-party":[19],"conversations,":[20],"most":[21],"previous":[22,64],"MERMC":[23],"studies":[24],"mainly":[25],"focus":[26],"on":[27,156,167],"text":[28],"and":[29,46,126],"audio":[30],"modalities":[31],"while":[32],"ignoring":[33],"information.Recently,":[35],"several":[36],"works":[37],"proposed":[38,164],"extract":[40,106],"face":[41,60,108,121,124,127,131],"sequences":[42],"as":[43],"features":[45],"have":[47],"shown":[48],"importance":[50],"information":[53],"MERMC.However,":[55],"given":[56],"an":[57],"utterance,":[58,116],"sequence":[61,109],"extracted":[62,130],"by":[63],"methods":[65],"may":[66],"contain":[67],"multiple":[68],"people's":[69],"faces,":[70],"which":[71,117,142],"will":[72],"inevitably":[73],"introduce":[74],"noise":[75],"emotion":[78,139,147,153],"prediction":[79],"real":[82,112],"speaker.To":[83],"tackle":[84],"this":[85],"issue,":[86],"we":[87,133],"propose":[88,134],"a":[89,99,135],"two-stage":[90],"framework":[91,166],"named":[92],"Facial":[93],"expressionaware":[94],"Multi-Task":[96],"learning":[97],"(Fa-cialMMT).Specifically,":[98],"pipeline":[100],"method":[101],"is":[102],"first":[103],"designed":[104],"speaker":[113],"each":[115],"consists":[118],"multimodal":[120,136],"recognition,":[122],"unsupervised":[123],"clustering,":[125],"matching.With":[128],"sequences,":[132],"facial":[137,146],"expression-aware":[138],"recognition":[140,154],"model,":[141],"leverages":[143],"frame-level":[145],"distributions":[148],"help":[150],"improve":[151],"utterance-level":[152],"based":[155],"multi-task":[157],"learning.Experiments":[158],"demonstrate":[159],"effectiveness":[161],"FacialMMT":[165],"benchmark":[169],"MELD":[170],"dataset.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}