{"id":"https://openalex.org/W4415537502","doi":"https://doi.org/10.1145/3746027.3762066","title":"Emotion-Qwen-VL: A Fully Fine-Tuned Multimodal Large Language Model for Micro-Expression Visual Question Answering","display_name":"Emotion-Qwen-VL: A Fully Fine-Tuned Multimodal Large Language Model for Micro-Expression Visual Question Answering","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537502","doi":"https://doi.org/10.1145/3746027.3762066"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3762066","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3762066","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yujing Wang","orcid":"https://orcid.org/0009-0009-8089-4676"},"institutions":[{"id":"https://openalex.org/I4210132079","display_name":"Hangzhou Wanxiang Polytechnic","ror":"https://ror.org/03sxnxp24","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210132079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Wang","raw_affiliation_strings":["Lianxin Digital (Technology), Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0009-8089-4676","affiliations":[{"raw_affiliation_string":"Lianxin Digital (Technology), Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210132079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120131553","display_name":"Ruotong Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132079","display_name":"Hangzhou Wanxiang Polytechnic","ror":"https://ror.org/03sxnxp24","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210132079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruotong Fang","raw_affiliation_strings":["Lianxin Digital (Technology), Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0003-3611-814X","affiliations":[{"raw_affiliation_string":"Lianxin Digital (Technology), Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210132079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xing Huang","orcid":"https://orcid.org/0009-0008-2681-0614"},"institutions":[{"id":"https://openalex.org/I4210132079","display_name":"Hangzhou Wanxiang Polytechnic","ror":"https://ror.org/03sxnxp24","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210132079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Huang","raw_affiliation_strings":["Lianxin Digital (Technology), Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0008-2681-0614","affiliations":[{"raw_affiliation_string":"Lianxin Digital (Technology), Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210132079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyuan Han","orcid":"https://orcid.org/0009-0008-5630-5344"},"institutions":[{"id":"https://openalex.org/I4210132079","display_name":"Hangzhou Wanxiang Polytechnic","ror":"https://ror.org/03sxnxp24","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210132079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Han","raw_affiliation_strings":["Lianxin Digital (Technology), Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0008-5630-5344","affiliations":[{"raw_affiliation_string":"Lianxin Digital (Technology), Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210132079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108145981","display_name":"Xiaoqing Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132079","display_name":"Hangzhou Wanxiang Polytechnic","ror":"https://ror.org/03sxnxp24","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210132079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Lin","raw_affiliation_strings":["Lianxin Digital (Technology), Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0006-4793-2544","affiliations":[{"raw_affiliation_string":"Lianxin Digital (Technology), Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210132079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038317465","display_name":"Yuhao Shan","orcid":"https://orcid.org/0000-0003-4821-326X"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Shan","raw_affiliation_strings":["Southwest University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-4821-326X","affiliations":[{"raw_affiliation_string":"Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015527515","display_name":"Tong Chen","orcid":"https://orcid.org/0000-0003-3805-4138"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Chen","raw_affiliation_strings":["Southwest University, Chongqing, China and Institute of Psychology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3805-4138","affiliations":[{"raw_affiliation_string":"Southwest University, Chongqing, China and Institute of Psychology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25927791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13972","last_page":"13978"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9937999844551086,"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":0.9904999732971191,"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/question-answering","display_name":"Question answering","score":0.7465000152587891},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6491000056266785},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6037999987602234},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5885000228881836},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.583299994468689},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.529699981212616},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.492000013589859},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47440001368522644},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42559999227523804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313999772071838},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7465000152587891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.666700005531311},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6491000056266785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6464999914169312},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.492000013589859},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36649999022483826},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3762066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3762066","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:/ir.psych.ac.cn:311026/51491","is_oa":false,"landing_page_url":"https://ir.psych.ac.cn/handle/311026/51491","pdf_url":null,"source":{"id":"https://openalex.org/S4377196583","display_name":"Institutional Repository of Institute of Psychology, Chinese Academy of Sciences (Institute of Psychology, Chinese Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210131870","host_organization_name":"Institute of Psychology, Chinese Academy of Sciences","host_organization_lineage":["https://openalex.org/I4210131870"],"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":"\u4f1a\u8bae\u8bba\u6587"}],"best_oa_location":{"id":"doi:10.1145/3746027.3762066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3762066","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2056591378","https://openalex.org/W2101105183","https://openalex.org/W2139916508","https://openalex.org/W2526853616","https://openalex.org/W2538953432","https://openalex.org/W2603775219","https://openalex.org/W2804639553","https://openalex.org/W2959679536","https://openalex.org/W2964138343","https://openalex.org/W2974043081","https://openalex.org/W3128209522","https://openalex.org/W3128946893","https://openalex.org/W3134059694","https://openalex.org/W3141012605","https://openalex.org/W4280528148","https://openalex.org/W4386185600","https://openalex.org/W4387436689","https://openalex.org/W4408520705","https://openalex.org/W4410349225","https://openalex.org/W4411087518","https://openalex.org/W4411259898","https://openalex.org/W4415333775"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3],"solution":[4],"for":[5,51],"the":[6,14,23,106,138],"Micro-Expression":[7,17],"Visual":[8],"Question":[9],"Answering":[10],"(ME-VQA)":[11],"task":[12],"in":[13,31,93,147],"2025":[15,108],"Facial":[16],"Grand":[18],"Challenge":[19],"(MEGC).":[20],"To":[21],"address":[22],"limitations":[24],"of":[25,144],"traditional":[26],"micro-expression":[27,52,130,148],"recognition":[28],"(MER)":[29],"methods":[30],"dynamic":[32],"modeling,":[33],"semantic":[34],"interpretation,":[35],"and":[36,66,80,99,120,132,141],"natural":[37,72],"language":[38,48,73,133],"interaction,":[39],"we":[40,55],"propose":[41],"Emotion-Qwen-VL,":[42],"a":[43,57,86],"fully":[44],"fine-tuned":[45],"multimodal":[46],"large":[47,145],"model":[49],"tailored":[50],"understanding.":[53,149],"Specifically,":[54],"construct":[56],"structured,":[58],"instruction-based":[59],"QA":[60,74],"dataset":[61],"that":[62,112],"reformulates":[63],"emotion":[64],"categories":[65],"action":[67],"unit":[68],"(AU)":[69],"annotations":[70],"into":[71],"pairs,":[75],"covering":[76],"classification,":[77,128,131],"AU":[78],"detection,":[79],"causal":[81],"reasoning.":[82],"We":[83],"then":[84],"adopt":[85],"full-parameter":[87],"fine-tuning":[88],"strategy":[89],"to":[90],"guide":[91],"Qwen2.5-VL":[92,119],"learning":[94],"fine-grained":[95,129],"temporal":[96],"facial":[97],"dynamics":[98],"their":[100],"emotional":[101],"semantics.":[102],"Experimental":[103],"results":[104,136],"on":[105],"MEGC":[107],"test":[109],"set":[110],"demonstrate":[111],"Emotion-Qwen-VL":[113],"outperforms":[114],"strong":[115],"baselines":[116],"such":[117],"as":[118],"QVQ":[121],"across":[122],"multiple":[123],"dimensions,":[124],"including":[125],"coarse-grained":[126],"macro-expression":[127],"generation.":[134],"Our":[135],"highlight":[137],"effectiveness,":[139],"interpretability,":[140],"adaptation":[142],"potential":[143],"models":[146],"The":[150],"code":[151],"is":[152],"available":[153],"at:":[154],"https://github.com/2308623956/MEGC2025.":[155]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}