{"id":"https://openalex.org/W4406857556","doi":"https://doi.org/10.1109/tmm.2025.3535347","title":"Identity and Modality Attributes Driven Multimodal Fusion Networks for Emotion Recognition in Conversations","display_name":"Identity and Modality Attributes Driven Multimodal Fusion Networks for Emotion Recognition in Conversations","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406857556","doi":"https://doi.org/10.1109/tmm.2025.3535347"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535347","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5035197326","display_name":"Wuzhen Shi","orcid":"https://orcid.org/0000-0002-6819-0125"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wuzhen Shi","raw_affiliation_strings":["Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuping Chen","orcid":"https://orcid.org/0009-0002-0962-1199"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuping Chen","raw_affiliation_strings":["Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108909469","display_name":"Biyun Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biyun Yao","raw_affiliation_strings":["Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006980036","display_name":"Yang Wen","orcid":"https://orcid.org/0000-0001-6303-8178"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wen","raw_affiliation_strings":["Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Province Engineering Laboratory for Digital Creative Technology, Guangdong Provincial Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009598072","display_name":"Bin Sheng","orcid":"https://orcid.org/0000-0001-8678-2784"},"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":"Bin Sheng","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"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":5,"corresponding_author_ids":["https://openalex.org/A5035197326"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":10.089,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97661283,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"4361","last_page":"4371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.921999990940094,"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":0.921999990940094,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7753580808639526},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7215868830680847},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5864506959915161},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5821957588195801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45995795726776123},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4199369251728058},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.404339075088501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753580808639526},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7215868830680847},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5864506959915161},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5821957588195801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45995795726776123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4199369251728058},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.404339075088501},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535347","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1623375054","display_name":null,"funder_award_id":"2022A1515110101","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G4055915431","display_name":null,"funder_award_id":"2024A1515010496","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G5697656822","display_name":null,"funder_award_id":"62101346","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6310097882","display_name":null,"funder_award_id":"62301330","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/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1987048275","https://openalex.org/W2064675550","https://openalex.org/W2068124150","https://openalex.org/W2146334809","https://openalex.org/W2510642588","https://openalex.org/W2740550900","https://openalex.org/W2787581402","https://openalex.org/W2805662932","https://openalex.org/W2806669038","https://openalex.org/W2891359673","https://openalex.org/W2963351448","https://openalex.org/W2963446712","https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W2964346351","https://openalex.org/W2965453734","https://openalex.org/W2985882473","https://openalex.org/W3034294191","https://openalex.org/W3034330439","https://openalex.org/W3156669407","https://openalex.org/W3173396651","https://openalex.org/W3176399185","https://openalex.org/W3203741465","https://openalex.org/W3205272809","https://openalex.org/W4200013911","https://openalex.org/W4221154966","https://openalex.org/W4306250392","https://openalex.org/W4360595168","https://openalex.org/W4367281761","https://openalex.org/W4385834126","https://openalex.org/W4386076442","https://openalex.org/W4386766906","https://openalex.org/W4387969701","https://openalex.org/W4391454424","https://openalex.org/W4392904377","https://openalex.org/W4394595603","https://openalex.org/W6726873649","https://openalex.org/W6741668545","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,96],"in":[2,17,29,97,198],"conversations":[3],"(ERC)":[4],"is":[5,35,69],"a":[6,102],"crucial":[7],"aspect":[8],"of":[9,32,109,124,139,194],"human-computer":[10],"interaction":[11],"and":[12,23,74,85,210],"plays":[13],"an":[14,71,83,161],"important":[15],"role":[16],"various":[18],"domains,":[19],"including":[20],"healthcare,":[21],"entertainment,":[22],"education.":[24],"Since":[25],"the":[26,30,43,60,110,119,122,130,136,150,167,174,180,183,192,199,204,208,218],"conversation":[27,189],"data":[28,184],"form":[31],"multimodal":[33,145],"sequences":[34],"well":[36],"suited":[37],"to":[38,58,115,165,173,182],"be":[39],"constructed":[40],"into":[41],"graphs,":[42],"methods":[44,56],"based":[45],"on":[46,207],"graph":[47,104],"convolutional":[48],"network":[49,91,169],"(GCN)":[50],"show":[51,213],"incomparable":[52],"advantages.":[53],"However,":[54],"existing":[55],"attempt":[57],"model":[59],"highly":[61],"uncertain":[62],"emotional":[63,151],"relationships":[64],"between":[65,121,141,153],"different":[66,125],"speakers,":[67],"which":[68,134],"not":[70],"easy":[72],"task":[73],"may":[75],"even":[76],"introduce":[77,129],"interference":[78,120],"information.":[79],"Therefore,":[80],"we":[81,100,159,178,201],"propose":[82],"identity":[84],"modality":[86],"attributes":[87],"driven":[88],"multimodality":[89],"fusion":[90,168],"(dubbed":[92],"IMDNet)":[93],"for":[94,143,188,203],"emotion":[95],"conversations.":[98],"Specifically,":[99],"construct":[101],"speaker-centric":[103],"that":[105,149,214],"only":[106],"connects":[107],"nodes":[108,142],"same":[111],"speaker":[112],"within":[113],"modalities":[114],"each":[116],"other,":[117],"reducing":[118],"emotions":[123],"speakers.":[126],"We":[127],"also":[128],"attribute":[131],"embedding":[132],"mechanism,":[133],"facilitates":[135],"correct":[137],"calculation":[138],"correlations":[140],"better":[144],"feature":[146],"fusion.":[147],"Considering":[148],"correlation":[152],"utterances":[154],"will":[155],"decrease":[156],"over":[157],"time,":[158],"present":[160],"utterance":[162],"distance":[163],"attention":[164,172],"make":[166],"pay":[170],"more":[171],"adjacent":[175],"utterances.":[176],"Furthermore,":[177],"explore":[179],"solution":[181],"imbalance":[185],"problem":[186],"suitable":[187],"scenarios.":[190],"Given":[191],"presence":[193],"possible":[195],"anomalous":[196],"samples":[197],"dataset,":[200],"opt":[202],"BoundaryFocalLoss.":[205],"Experiments":[206],"IEMOCAP":[209],"MELD":[211],"datasets":[212],"our":[215],"IMDNet":[216],"outperforms":[217],"state-of-the-art":[219],"methods.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
