{"id":"https://openalex.org/W4403713271","doi":"https://doi.org/10.1145/3689092.3689404","title":"SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition","display_name":"SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition","publication_year":2024,"publication_date":"2024-10-23","ids":{"openalex":"https://openalex.org/W4403713271","doi":"https://doi.org/10.1145/3689092.3689404"},"language":"en","primary_location":{"id":"doi:10.1145/3689092.3689404","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689092.3689404","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.10500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053952600","display_name":"Zebang Cheng","orcid":"https://orcid.org/0009-0001-2854-7425"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Zebang Cheng","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Shenzhen Technology University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Shenzhen Technology University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025369047","display_name":"Shuyuan Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuyuan Tu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109532449","display_name":"Dawei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Huang","raw_affiliation_strings":["Shenzhen Technology University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Minghan Li","orcid":"https://orcid.org/0009-0009-5153-2406"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minghan Li","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033413473","display_name":"Xiaojiang Peng","orcid":"https://orcid.org/0000-0002-5783-321X"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojiang Peng","raw_affiliation_strings":["Shenzhen Technology University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058898461","display_name":"Zhi-Qi Cheng","orcid":"https://orcid.org/0000-0002-1720-2085"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhi-Qi Cheng","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Shenzhen Technology University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Shenzhen Technology University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103099928","display_name":"Alexander G. Hauptmann","orcid":"https://orcid.org/0000-0003-2123-0684"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander G. Hauptmann","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5053952600"],"corresponding_institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.4572,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92974643,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9976000189781189,"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":0.6478824019432068},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5938501358032227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47792941331863403},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.41542333364486694},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36862361431121826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33216166496276855},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3046349287033081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6478824019432068},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5938501358032227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47792941331863403},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.41542333364486694},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36862361431121826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33216166496276855},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3046349287033081}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3689092.3689404","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689092.3689404","pdf_url":null,"source":null,"license":null,"license_id":null,"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"},{"id":"pmh:oai:arXiv.org:2408.10500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.10500","pdf_url":"https://arxiv.org/pdf/2408.10500","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.10500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.10500","pdf_url":"https://arxiv.org/pdf/2408.10500","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3700909421","display_name":null,"funder_award_id":"62176165","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3800138795","display_name":"Collaborative Research: Cosmic magnetic fields: origin, evolution, and signatures","funder_award_id":"1109180","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3817646177","display_name":"Long-Term Analysis of Benthic Population and Community      Dynamics on a Coral Reef","funder_award_id":"8110918","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3835096260","display_name":"Structure of the Shoot Apex in Tropical Angiosperms Malvales","funder_award_id":"6217616","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5141548552","display_name":"Student Travel Support for 2019 ACM International Conference on Multimedia (ACM MM)","funder_award_id":"1937998","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320319297","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403713271.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2152498377","https://openalex.org/W2194775991","https://openalex.org/W2239141610","https://openalex.org/W2526050071","https://openalex.org/W2981072818","https://openalex.org/W3021636956","https://openalex.org/W3093370878","https://openalex.org/W3102725307","https://openalex.org/W3169801598","https://openalex.org/W3209059054","https://openalex.org/W4224916413","https://openalex.org/W4285294723","https://openalex.org/W4312544061","https://openalex.org/W4376455521","https://openalex.org/W4378907171","https://openalex.org/W4385823319","https://openalex.org/W4386072325","https://openalex.org/W4387698140","https://openalex.org/W4387968043","https://openalex.org/W4388188113","https://openalex.org/W4388191637","https://openalex.org/W4399547912","https://openalex.org/W4402727142"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2536562190","https://openalex.org/W2951359407","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,67,73,98],"winning":[4],"approach":[5],"for":[6,34,102,131],"the":[7,13,23,38,64,70,84,95,118],"MER-NOISE":[8,71],"and":[9,57,86,91,112,129],"MER-OV":[10,96],"tracks":[11],"of":[12,28,40,66,81,100],"MER2024":[14],"Challenge":[15],"on":[16],"multimodal":[17,46,125],"emotion":[18],"recognition.":[19],"Our":[20],"system":[21,74],"leverages":[22],"advanced":[24],"emotional":[25],"understanding":[26],"capabilities":[27],"Emotion-LLaMA":[29,101,132],"to":[30,115],"generate":[31],"high-quality":[32],"annotations":[33],"unlabeled":[35],"samples,":[36],"addressing":[37],"challenge":[39],"limited":[41],"labeled":[42],"data.":[43],"To":[44],"enhance":[45],"fusion":[47],"while":[48],"mitigating":[49],"modality-specific":[50],"noise,":[51],"we":[52],"introduce":[53],"Conv-Attention,":[54],"a":[55,76],"lightweight":[56],"efficient":[58],"hybrid":[59],"framework.":[60],"Extensive":[61],"experimentation":[62],"validates":[63],"effectiveness":[65],"approach.":[68],"In":[69],"track,":[72,97],"achieves":[75],"state-of-the-art":[77],"weighted":[78],"average":[79,110],"F-score":[80],"85.30%,":[82],"surpassing":[83],"second":[85],"third-place":[87],"teams":[88],"by":[89],"1.47%":[90],"1.65%,":[92],"respectively.":[93],"For":[94],"utilization":[99],"open-vocabulary":[103],"annotation":[104],"yields":[105],"an":[106],"8.52%":[107],"improvement":[108],"in":[109],"accuracy":[111],"recall":[113],"compared":[114],"GPT-4V,":[116],"securing":[117],"highest":[119],"score":[120],"among":[121],"all":[122],"participating":[123],"large":[124],"models.":[126],"The":[127],"code":[128],"model":[130],"are":[133],"available":[134],"at":[135],"https://github.com/ZebangCheng/Emotion-LLaMA.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2024-10-25T00:00:00"}