{"id":"https://openalex.org/W4404564061","doi":"https://doi.org/10.1109/uemcon62879.2024.10754673","title":"Fully Auto-Regressive Multi-modal Large Language Model for Contextual Emotion Recognition","display_name":"Fully Auto-Regressive Multi-modal Large Language Model for Contextual Emotion Recognition","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4404564061","doi":"https://doi.org/10.1109/uemcon62879.2024.10754673"},"language":"en","primary_location":{"id":"doi:10.1109/uemcon62879.2024.10754673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/uemcon62879.2024.10754673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 15th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","raw_type":"proceedings-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/A5006330700","display_name":"Hiroshi Nonaka","orcid":null},"institutions":[{"id":"https://openalex.org/I67607428","display_name":"Soka University of America","ror":"https://ror.org/03rr7xb36","country_code":"US","type":"education","lineage":["https://openalex.org/I67607428"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hiroshi Nonaka","raw_affiliation_strings":["Soka University of America,Aliso Viejo,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soka University of America,Aliso Viejo,USA","institution_ids":["https://openalex.org/I67607428"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071972698","display_name":"Damian Valles","orcid":"https://orcid.org/0000-0002-5684-9498"},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Damian Valles","raw_affiliation_strings":["Texas State University,Ingram School of Engineering,San Marcos,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas State University,Ingram School of Engineering,San Marcos,USA","institution_ids":["https://openalex.org/I13511017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75117293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"0291","last_page":"0299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.930899977684021,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.930899977684021,"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/computer-science","display_name":"Computer science","score":0.7554028630256653},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6617000102996826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5317097306251526},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48753759264945984},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4748827815055847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4395866394042969},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.43009430170059204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554028630256653},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6617000102996826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5317097306251526},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48753759264945984},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4748827815055847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4395866394042969},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.43009430170059204},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/uemcon62879.2024.10754673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/uemcon62879.2024.10754673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 15th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W3105646692","https://openalex.org/W4387914125","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,47],"gained":[5],"popularity":[6],"due":[7],"to":[8,23,35,50,69,91,131,162],"their":[9,21],"high":[10,159],"performance":[11,160],"in":[12,84],"natural":[13,66],"language":[14],"processing.":[15],"This":[16,114],"capability":[17],"is":[18],"underpinned":[19],"by":[20,57,65],"ability":[22],"contextualize":[24,92],"relations":[25],"within":[26],"text":[27,62],"data.":[28,63],"The":[29],"application":[30],"of":[31,95,117,170],"LLMs":[32,52,177],"also":[33],"extends":[34],"multi-modal":[36,78,103],"tasks,":[37],"such":[38],"as":[39],"image":[40],"captioning":[41],"and":[42,61,124,148],"video":[43],"analysis.":[44],"Research":[45],"endeavors":[46],"been":[48],"undertaken":[49],"leverage":[51],"for":[53,81,105,178],"emotion":[54,70,82],"recognition":[55,83],"tasks":[56],"utilizing":[58],"visual,":[59],"audio,":[60],"Inspired":[64],"human":[67],"approaches":[68],"recognition,":[71],"we":[72],"propose":[73],"a":[74,121],"simple":[75],"yet":[76],"powerful,":[77],"LLM":[79,104,133,147],"architecture":[80],"conversations":[85],"(ERC).":[86],"Our":[87],"proposed":[88],"framework":[89],"aims":[90],"the":[93,100,118,132,142,146,168],"change":[94],"emotions":[96],"better.":[97],"We":[98],"developed":[99],"Fully":[101],"Auto-Regressive":[102],"Contextual":[106],"Emotion":[107],"Recognition":[108],"(FARCER)":[109],"based":[110],"on":[111],"this":[112],"idea.":[113],"model":[115],"consists":[116],"instruction-tuned":[119],"LLaMA3,":[120],"vision":[122,149],"encoder,":[123],"linear":[125],"layers":[126],"that":[127],"map":[128],"visual":[129],"embeddings":[130],"input":[134],"space.":[135],"FARCER":[136,157],"significantly":[137],"improved":[138],"ERC":[139],"benchmarks":[140],"over":[141],"uni-modal":[143],"LLaMA3-Instruct,":[144],"although":[145],"encoder\u2019s":[150],"parameters":[151],"remained":[152],"frozen":[153],"during":[154],"training.":[155],"Fine-tuned":[156],"demonstrated":[158],"comparable":[161],"other":[163],"state-of-the-art":[164],"(SOTA)":[165],"models,":[166],"highlighting":[167],"potential":[169],"our":[171],"context-focused":[172],"design":[173],"combined":[174],"with":[175],"conversational":[176],"ERC.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}