{"id":"https://openalex.org/W4403713255","doi":"https://doi.org/10.1145/3689092.3689403","title":"Multimodal Emotion Captioning Using Large Language Model with Prompt Engineering","display_name":"Multimodal Emotion Captioning Using Large Language Model with Prompt Engineering","publication_year":2024,"publication_date":"2024-10-23","ids":{"openalex":"https://openalex.org/W4403713255","doi":"https://doi.org/10.1145/3689092.3689403"},"language":"en","primary_location":{"id":"doi:10.1145/3689092.3689403","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689092.3689403","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3689092.3689403","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015396622","display_name":"Yaoxun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaoxun Xu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-7063-7317","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749226","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0009-0002-6363-891X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Zhou","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-6363-891X","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004864776","display_name":"Yunrui Cai","orcid":"https://orcid.org/0009-0009-4431-2886"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunrui Cai","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-4431-2886","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055370974","display_name":"Jingran Xie","orcid":"https://orcid.org/0009-0007-2050-263X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingran Xie","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-2050-263X","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Runchuan Ye","orcid":"https://orcid.org/0009-0006-9113-6318"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runchuan Ye","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-9113-6318","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8533-0524","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015396622"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.1435,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79948285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9939000010490417,"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":0.991100013256073,"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/closed-captioning","display_name":"Closed captioning","score":0.891394853591919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743802011013031},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42271244525909424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33364272117614746}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.891394853591919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743802011013031},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42271244525909424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33364272117614746},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3689092.3689403","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689092.3689403","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3689092.3689403","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3689092.3689403","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2164699598","https://openalex.org/W2610961739","https://openalex.org/W2963104701","https://openalex.org/W3003908700","https://openalex.org/W3156576211","https://openalex.org/W3206603478","https://openalex.org/W3206842948","https://openalex.org/W3207379732","https://openalex.org/W4224234075","https://openalex.org/W4297510543","https://openalex.org/W4321482228","https://openalex.org/W4390640143","https://openalex.org/W4393147046","https://openalex.org/W4393178509"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0,82],"paper":[1,57],"addresses":[2],"the":[3,11,30,59,85,94,109],"challenges":[4],"in":[5],"MER":[6],"2024":[7],"by":[8,47],"focusing":[9],"on":[10],"Open":[12],"Vocabulary":[13],"(OV)":[14],"task,":[15],"which":[16],"extends":[17],"beyond":[18],"traditional":[19],"fixed":[20],"label":[21],"space":[22],"for":[23,99],"multimodal":[24,44],"emotion":[25,51,101],"recognition.":[26],"The":[27,56],"study":[28],"emphasizes":[29],"use":[31],"of":[32,61,97],"Large":[33],"Language":[34],"Models":[35],"(LLMs)":[36],"to":[37,76,108],"interpret":[38],"and":[39,53,90,104],"extract":[40],"emotional":[41],"information":[42],"from":[43],"inputs,":[45],"complemented":[46],"speech":[48,50],"transcription,":[49],"description,":[52],"video":[54,89],"clues.":[55],"explores":[58],"integration":[60],"these":[62],"features":[63],"into":[64,68],"a":[65,69,106],"prompt":[66,74],"fed":[67],"pre-trained":[70],"LLaMA3-8B":[71],"model,":[72],"utilizing":[73],"engineering":[75],"achieve":[77],"satisfactory":[78],"results":[79],"without":[80],"fine-tuning.":[81],"approach":[83],"bridges":[84],"gap":[86],"between":[87],"speech,":[88],"text":[91],"data,":[92],"leveraging":[93],"full":[95],"potential":[96],"LLMs":[98],"open-ended":[100],"recognition":[102],"tasks":[103],"introducing":[105],"solution":[107],"field.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-11T08:15:01.531666","created_date":"2025-10-10T00:00:00"}