{"id":"https://openalex.org/W4412567181","doi":"https://doi.org/10.1109/access.2025.3591447","title":"DialogueMLLM: Transforming Multimodal Emotion Recognition in Conversation Through Instruction-Tuned MLLM","display_name":"DialogueMLLM: Transforming Multimodal Emotion Recognition in Conversation Through Instruction-Tuned MLLM","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412567181","doi":"https://doi.org/10.1109/access.2025.3591447"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3591447","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591447","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3591447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100939949","display_name":"Yuanyuan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Sun","raw_affiliation_strings":["Central China Normal University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central China Normal University, Wuhan, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101629274","display_name":"Ting Zhou","orcid":"https://orcid.org/0009-0006-5876-788X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Zhou","raw_affiliation_strings":["Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-5876-788X","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":6.98,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9663154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"121048","last_page":"121060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9868999719619751,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9868999719619751,"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/conversation","display_name":"Conversation","score":0.8310098648071289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.736975908279419},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5589942932128906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5056295394897461},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44733816385269165},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32218414545059204},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.17560985684394836},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14707931876182556}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8310098648071289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736975908279419},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5589942932128906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5056295394897461},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44733816385269165},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32218414545059204},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.17560985684394836},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14707931876182556}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3591447","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591447","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7d2b13c0e41440948aa69c51e6b0d8cb","is_oa":true,"landing_page_url":"https://doaj.org/article/7d2b13c0e41440948aa69c51e6b0d8cb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 121048-121060 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3591447","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591447","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W2985882473","https://openalex.org/W3117369308","https://openalex.org/W3211488063","https://openalex.org/W3216650611","https://openalex.org/W4205991051","https://openalex.org/W4224322086","https://openalex.org/W4360595168","https://openalex.org/W4385245566","https://openalex.org/W4385570058","https://openalex.org/W4385570630","https://openalex.org/W4385571916","https://openalex.org/W4386071707","https://openalex.org/W4386435222","https://openalex.org/W4387573449","https://openalex.org/W4389519587","https://openalex.org/W4390414889","https://openalex.org/W4390638022","https://openalex.org/W4390690464","https://openalex.org/W4396919912","https://openalex.org/W4400770765","https://openalex.org/W4402701012","https://openalex.org/W4402713111","https://openalex.org/W4403262674","https://openalex.org/W4404784276","https://openalex.org/W4404869895","https://openalex.org/W4406857556","https://openalex.org/W4406915043","https://openalex.org/W4407049645","https://openalex.org/W4407559183","https://openalex.org/W4408259027","https://openalex.org/W4408352935","https://openalex.org/W4408353445","https://openalex.org/W4408459007","https://openalex.org/W4409154675","https://openalex.org/W4409992418","https://openalex.org/W4410428697","https://openalex.org/W6796581206","https://openalex.org/W6800666689","https://openalex.org/W6810081322","https://openalex.org/W6810334672","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6850729547","https://openalex.org/W6852447913","https://openalex.org/W6853688356","https://openalex.org/W6854866820","https://openalex.org/W6856800273","https://openalex.org/W6858268588","https://openalex.org/W6859726092","https://openalex.org/W6866333221","https://openalex.org/W6867724613","https://openalex.org/W6869164663","https://openalex.org/W6869315008","https://openalex.org/W6870379077","https://openalex.org/W6891821465"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Multimodal":[0,79],"Emotion":[1],"Recognition":[2],"in":[3,30,41,61,154,161],"Conversation":[4],"(MERC)":[5],"is":[6],"an":[7,86],"advanced":[8,89],"research":[9,37],"area":[10],"that":[11],"integrates":[12],"cross-modal":[13],"understanding":[14,153],"and":[15,44,55,64,88,137],"contextual":[16],"reasoning":[17,164],"through":[18,48],"text-speech-visual":[19],"fusion,":[20],"with":[21,108,112],"applications":[22],"spanning":[23],"diverse":[24],"scenarios":[25],"including":[26],"student":[27],"emotion":[28,96,106,152],"monitoring":[29],"high":[31],"school":[32],"classroom":[33],"interactions.":[34],"Although":[35],"existing":[36],"has":[38],"made":[39],"progress":[40],"multimodal":[42,95,163],"alignment":[43],"dialogue":[45],"relationship":[46],"modeling":[47],"architectures":[49],"such":[50],"as":[51],"graph":[52],"neural":[53],"networks":[54],"pre-trained":[56],"language":[57],"models,":[58],"challenges":[59],"persist":[60],"dataset":[62,109],"overfitting":[63],"underexplored":[65],"generative":[66,74],"approaches.":[67],"In":[68],"this":[69],"study,":[70],"we":[71],"pioneer":[72],"a":[73,120],"MERC":[75,145],"framework":[76],"based":[77],"on":[78,126,133],"Large":[80],"Language":[81],"Models":[82],"(MLLMs),":[83],"employing":[84],"Video-LLaMA,":[85],"open-source":[87],"tri-modal":[90],"foundation":[91],"model,":[92],"for":[93,114,143],"end-to-end":[94],"reasoning.":[97],"We":[98],"employ":[99],"carefully":[100],"crafted":[101],"structured":[102],"prompts":[103],"to":[104],"align":[105],"semantics":[107],"annotations,":[110],"combined":[111],"LoRA":[113],"parameter-efficient":[115],"optimization.":[116],"Our":[117],"method":[118],"achieves":[119],"state-of-the-art":[121],"weighted":[122],"F1-score":[123],"of":[124],"68.57%":[125],"the":[127],"MELD":[128],"benchmark.":[129],"Further,":[130],"exploratory":[131],"experiments":[132],"dynamic":[134],"modality":[135],"combinations":[136],"fine-tuning":[138],"strategies":[139],"offer":[140],"actionable":[141],"insights":[142],"MLLM-based":[144],"research.":[146],"This":[147],"work":[148],"not":[149],"only":[150],"advances":[151],"dialogues":[155],"but":[156],"also":[157],"highlights":[158],"MLLMs\u2019":[159],"potential":[160],"complex":[162],"tasks.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}