{"id":"https://openalex.org/W4416252057","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227919","title":"Emotion-Aware Text Generation for Instructing Audio-Visual Emotion Recognition","display_name":"Emotion-Aware Text Generation for Instructing Audio-Visual Emotion Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252057","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227919"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227919","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":"https://openalex.org/A5107658643","display_name":"Lin Wei","orcid":"https://orcid.org/0009-0007-5567-2735"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Wei","raw_affiliation_strings":["China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079420533","display_name":"Yuanyuan Liu","orcid":"https://orcid.org/0000-0002-1913-0089"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Liu","raw_affiliation_strings":["China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056493143","display_name":"Kejun Liu","orcid":"https://orcid.org/0000-0003-1721-2723"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejun Liu","raw_affiliation_strings":["China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404215","display_name":"Yuxuan Huang","orcid":"https://orcid.org/0009-0007-1094-934X"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Huang","raw_affiliation_strings":["China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010895370","display_name":"Shaoze Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoze Feng","raw_affiliation_strings":["China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Geosciences (Wuhan),School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I3124059619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3124059619"],"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":0.6876000165939331,"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":0.6876000165939331,"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":0.05400000140070915,"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/T11309","display_name":"Music and Audio Processing","score":0.04670000076293945,"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/modalities","display_name":"Modalities","score":0.6470999717712402},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5719000101089478},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5058000087738037},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.5052000284194946},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4634000062942505},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4442000091075897},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178999781608582},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6470999717712402},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5214999914169312},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4117000102996826},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227919","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1628791547","https://openalex.org/W2191779130","https://openalex.org/W2409534643","https://openalex.org/W2604799547","https://openalex.org/W2792616458","https://openalex.org/W2964216663","https://openalex.org/W2979826702","https://openalex.org/W3002732654","https://openalex.org/W3005450949","https://openalex.org/W3015906487","https://openalex.org/W3016092640","https://openalex.org/W3093370878","https://openalex.org/W3116238789","https://openalex.org/W3176362845","https://openalex.org/W3211666705","https://openalex.org/W4230277160","https://openalex.org/W4289874551","https://openalex.org/W4304099179","https://openalex.org/W4313178214","https://openalex.org/W4386699383","https://openalex.org/W4393181080","https://openalex.org/W4400276083","https://openalex.org/W4401452744","https://openalex.org/W4402916290","https://openalex.org/W4403780753"],"related_works":[],"abstract_inverted_index":{"Audio-visual":[0],"emotion":[1,35,147,179,216],"recognition":[2,180],"(AVER)":[3],"is":[4],"crucial":[5],"in":[6,21,32,117,170,191,214],"various":[7],"AI":[8],"applications,":[9],"such":[10],"as":[11],"digital":[12],"humans.":[13],"However,":[14],"due":[15],"to":[16,65,75,134,159],"the":[17,25,72,84,112,130,137,209],"incomplete":[18],"and":[19,27,37,70,80,107,125,139,165,173,195,203,219],"heterogeneity":[20],"emotional":[22,68,77,118,161],"expression":[23],"between":[24],"audio":[26,106],"visual":[28],"modalities,":[29,109],"challenges":[30],"remain":[31],"achieving":[33,198],"effective":[34],"interaction":[36],"fusion.":[38],"To":[39],"address":[40],"these":[41],"issues,":[42],"we":[43],"propose":[44],"a":[45],"novel":[46],"approach,":[47],"Emotion-Aware":[48,96,103,132],"Text":[49,97],"Generation":[50,98],"for":[51,111],"Instructing":[52],"Audio-Visual":[53],"Emotion":[54],"Recognition":[55],"(ETG-AVER).":[56],"This":[57],"method":[58],"generates":[59,102],"emotion-Aware":[60],"text":[61,74],"from":[62,105],"audio-visual":[63,115,142],"modalities":[64,116],"explicitly":[66],"capture":[67],"cues,":[69],"utilizes":[71],"generated":[73,131],"guide":[76,136],"feature":[78],"extraction":[79,138],"fusion,":[81],"thereby":[82,176],"improving":[83,177],"performance":[85],"of":[86,91,114,141,193,211],"AVER.":[87],"Specifically,":[88],"ETG-AVER":[89,186],"consists":[90],"three":[92],"key":[93],"components:":[94],"(1)":[95],"module,":[99,127,153],"which":[100,128,154],"first":[101],"texts":[104,133],"video":[108],"compensating":[110],"limitations":[113],"expression;":[119],"(2)":[120],"Text-Instruct":[121],"Multimodal":[122],"Feature":[123],"Extraction":[124],"Fusion":[126],"uses":[129,155],"precisely":[135],"fusion":[140],"features,":[143],"effectively":[144],"enhancing":[145],"cross-modal":[146,178],"interaction;":[148],"(3)":[149],"Hierarchical":[150],"Loss":[151],"Optimization":[152],"hierarchical":[156],"loss":[157],"functions":[158],"align":[160],"features":[162],"across":[163],"unimodal":[164],"multimodal":[166],"sources,":[167],"ensuring":[168],"consistency":[169],"both":[171],"semantic":[172],"representational":[174],"levels,":[175],"accuracy.":[181],"Experimental":[182],"results":[183],"demonstrate":[184],"that":[185],"significantly":[187],"outperforms":[188],"existing":[189],"methods":[190],"terms":[192],"accuracy":[194],"fine-grained":[196],"classification,":[197],"60.78%":[199],"WAR":[200,205],"on":[201,206],"MAFW":[202],"78.36%":[204],"DFEW,":[207],"validating":[208],"effectiveness":[210],"our":[212],"approach":[213],"refining":[215],"information":[217],"transfer":[218],"recognition.":[220]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}