{"id":"https://openalex.org/W7131875351","doi":"https://doi.org/10.1109/tmm.2026.3668469","title":"Context Modeling With Multimodal Prompts for Emotion Recognition in Conversation","display_name":"Context Modeling With Multimodal Prompts for Emotion Recognition in Conversation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131875351","doi":"https://doi.org/10.1109/tmm.2026.3668469"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668469","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/A5127049615","display_name":"Qian Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Dong","raw_affiliation_strings":["School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0881-006X","affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122076239","display_name":"Weihong Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihong Ren","raw_affiliation_strings":["School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3839-0078","affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045611560","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-1069-2157"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gao","raw_affiliation_strings":["School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5875-7626","affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039205892","display_name":"Jianzhuang Liu","orcid":"https://orcid.org/0000-0002-7960-9382"},"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/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhuang Liu","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7960-9382","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126305847","display_name":"Honghai Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghai Liu","raw_affiliation_strings":["School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2880-4698","affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, the State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20342133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5288","last_page":"5302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8640999794006348,"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":0.8640999794006348,"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/T12031","display_name":"Speech and dialogue systems","score":0.042399998754262924,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.014100000262260437,"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/conversation","display_name":"Conversation","score":0.631600022315979},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4512999951839447},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44279998540878296},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4007999897003174},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.3804999887943268},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.3797000050544739},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3736000061035156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159000277519226},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4968999922275543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47110000252723694},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44279998540878296},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668469","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/G3208793249","display_name":null,"funder_award_id":"62573163","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6281694414","display_name":null,"funder_award_id":"62503139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8622328191","display_name":null,"funder_award_id":"2024A1515012028","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Emotion":[0],"Recognition":[1],"in":[2,9,70,102,176,209],"Conversation":[3],"(ERC)":[4],"plays":[5],"an":[6,154],"important":[7],"role":[8],"driving":[10],"the":[11,17,21,34,39,60,88,162,171],"development":[12],"of":[13,20,33,94],"human-machine":[14],"interaction.":[15],"After":[16],"extensive":[18],"exploration":[19],"text":[22],"modality,":[23,77],"visual":[24,76],"and":[25,63,87,92,167,169,178],"audio":[26,95],"information":[27],"has":[28],"attracted":[29],"considerable":[30],"attention.":[31],"Most":[32],"existing":[35],"approaches":[36],"adopt":[37],"either":[38,140],"attention":[40],"mechanism":[41],"or":[42,144],"graph":[43],"neural":[44],"networks":[45],"to":[46,67,107,129,174,183,193],"conduct":[47],"multi-modal":[48,112],"fusion":[49,110,157],"by":[50,114],"directly":[51],"utilizing":[52],"pre-extracted":[53],"single":[54],"modal":[55,117,180],"features,":[56],"but":[57],"they":[58],"ignore":[59],"inherent":[61,116],"priors":[62],"characteristics":[64],"(highly":[65],"related":[66],"emotions)":[68],"contained":[69],"different":[71,125,130],"modalities.":[72],"For":[73],"example,":[74],"for":[75,124],"facial":[78],"expression":[79],"can":[80,137],"well":[81],"reveal":[82],"a":[83,189],"person's":[84],"emotional":[85,99],"state,":[86],"intonation,":[89],"speech":[90],"rate":[91],"volume":[93],"modality":[96],"also":[97],"reflect":[98],"fluctuation.":[100],"Thus,":[101],"this":[103],"work,":[104],"we":[105,120,152,187],"aim":[106],"promote":[108],"context":[109],"among":[111,197],"features":[113,166],"exploring":[115],"priors.":[118],"Firstly,":[119],"create":[121],"textual":[122],"descriptions":[123],"emotion":[126],"categories":[127],"belonging":[128],"modalities,":[131],"denoted":[132],"as":[133],"multimodal":[134,172,185,190],"prompts":[135,173],"which":[136,159],"be":[138],"generated":[139],"from":[141],"common":[142],"sense":[143],"using":[145],"large":[146],"language":[147],"models":[148,208],"(e.g.,":[149],"ChatGPT).":[150],"Then,":[151],"propose":[153],"adaptive":[155],"gating":[156],"module":[158],"dynamically":[160],"learns":[161],"weights":[163],"between":[164],"unimodal":[165],"prompts,":[168],"allows":[170],"participate":[175],"encoding":[177],"enriching":[179],"information.":[181],"Finally,":[182],"facilitate":[184],"fusion,":[186],"design":[188],"progressive":[191],"encoder":[192],"learn":[194],"inter-modal":[195],"interactions":[196],"conversational":[198],"utterances.":[199],"Experimental":[200],"results":[201],"show":[202],"that":[203],"our":[204],"model":[205],"outperforms":[206],"state-of-the-art":[207],"ERC":[210],"on":[211],"two":[212],"popular":[213],"benchmark":[214],"datasets.":[215]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-28T00:00:00"}
