{"id":"https://openalex.org/W7105670524","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229075","title":"SupGATE: Supervised Contrastive Learning and Attention-Gated Multimodal Fusion for Emotion Recognition in Conversations","display_name":"SupGATE: Supervised Contrastive Learning and Attention-Gated Multimodal Fusion for Emotion Recognition in Conversations","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105670524","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229075"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"Jiajun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Wang","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chunqi Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunqi Tian","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":null,"display_name":"Haiping Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiping Sun","raw_affiliation_strings":["Tongji University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9891999959945679,"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":0.9891999959945679,"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":0.0017999999690800905,"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/T12031","display_name":"Speech and dialogue systems","score":0.0010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7197999954223633},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6022999882698059},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5530999898910522},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.5185999870300293},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.498199999332428},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.446399986743927},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4154999852180481},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4050999879837036}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7197999954223633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958000063896179},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37310001254081726},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5014626979827881}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1988085234","https://openalex.org/W2102953093","https://openalex.org/W2146334809","https://openalex.org/W2157331557","https://openalex.org/W2158943324","https://openalex.org/W2745497104","https://openalex.org/W2805662932","https://openalex.org/W2963446712","https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W2973049979","https://openalex.org/W2985882473","https://openalex.org/W2996849360","https://openalex.org/W3156636935","https://openalex.org/W3173396651","https://openalex.org/W3173751215","https://openalex.org/W3184236853","https://openalex.org/W3203741465","https://openalex.org/W3204870390","https://openalex.org/W4221147459","https://openalex.org/W4221154966","https://openalex.org/W4226025958","https://openalex.org/W4226425326","https://openalex.org/W4285106979","https://openalex.org/W4298007538","https://openalex.org/W4303649263","https://openalex.org/W4312327819","https://openalex.org/W4367281761","https://openalex.org/W4385570058","https://openalex.org/W4385573172","https://openalex.org/W4385573848","https://openalex.org/W4392405713","https://openalex.org/W4394862741","https://openalex.org/W4401043060","https://openalex.org/W4402352659","https://openalex.org/W4406983175"],"related_works":[],"abstract_inverted_index":{"Emotion":[0],"Recognition":[1],"in":[2,70,199],"Conversations":[3],"(ERC)":[4],"is":[5],"vital":[6],"for":[7],"developing":[8],"empathetic":[9],"and":[10,16,36,74,102,119,133,211,223,230],"responsive":[11],"systems":[12],"that":[13,137,194],"accurately":[14],"understand":[15],"react":[17],"to":[18,57,111,127,163,173],"users\u2019":[19],"emotional":[20,46,90,178,187,197,207],"states.":[21],"While":[22],"traditional":[23],"ERC":[24,114],"methods":[25],"primarily":[26],"rely":[27],"on":[28,218,228,233],"textual":[29],"data,":[30],"incorporating":[31],"multimodal":[32,62,113],"information\u2014such":[33],"as":[34],"audio":[35],"visual":[37,134],"cues\u2014can":[38],"significantly":[39],"improve":[40],"its":[41],"performance":[42,227],"by":[43,115],"capturing":[44,204],"complementary":[45],"signals.":[47,179],"However,":[48],"effectively":[49],"leveraging":[50],"these":[51],"diverse":[52],"modalities":[53,67],"remains":[54],"challenging":[55],"due":[56],"the":[58,86,140,167,171,175,183,196,200,205],"inherent":[59],"heterogeneity":[60],"of":[61,88,139,148,186],"data.":[63],"Features":[64],"from":[65,80,92],"different":[66,149],"often":[68],"reside":[69],"distinct":[71],"semantic":[72],"spaces":[73],"noisy":[75],"or":[76],"less":[77],"relevant":[78],"signals":[79],"one":[81],"modality":[82,117,165],"may":[83],"interfere":[84],"with":[85],"extraction":[87],"meaningful":[89],"cues":[91],"others.":[93],"In":[94],"this":[95],"paper,":[96],"we":[97],"propose":[98],"Supervised":[99],"Contrastive":[100],"Learning":[101],"Attention-Gated":[103],"Multimodal":[104],"Fusion":[105],"(SupGATE),":[106],"a":[107],"novel":[108],"framework":[109],"designed":[110],"enhance":[112],"addressing":[116],"alignment":[118],"fusion.":[120],"SupGATE":[121,189,217],"utilizes":[122],"supervised":[123],"contrastive":[124],"learning":[125],"(SCL)":[126],"align":[128],"features":[129],"across":[130],"textual,":[131],"acoustic,":[132],"modalities,":[135],"ensuring":[136],"representations":[138],"same":[141],"emotion":[142],"are":[143,151],"closely":[144],"clustered":[145],"while":[146],"those":[147],"emotions":[150],"distinctly":[152],"separated.":[153],"Additionally,":[154],"our":[155],"Attention-Guided":[156],"Gating":[157],"Module":[158],"(AGGM)":[159],"dynamically":[160],"assigns":[161],"weights":[162],"each":[164],"during":[166],"fusion":[168],"process,":[169],"enabling":[170],"model":[172],"prioritize":[174],"most":[176],"informative":[177],"To":[180],"further":[181],"enrich":[182],"model\u2019s":[184],"understanding":[185],"dynamics,":[188],"incorporates":[190],"an":[191],"auxiliary":[192],"task":[193],"predicts":[195],"transition":[198],"subsequent":[201],"conversational":[202],"turn,":[203],"evolving":[206],"context":[208],"within":[209],"multi-turn":[210],"multi-party":[212],"dialogues.":[213],"Finally,":[214],"We":[215],"evaluate":[216],"two":[219],"benchmark":[220],"datasets,":[221],"IEMOCAP":[222],"MELD,":[224],"achieving":[225],"state-of-the-art":[226],"MELD":[229],"competitive":[231],"results":[232],"IEMOCAP.":[234]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}