{"id":"https://openalex.org/W4408345636","doi":"https://doi.org/10.1109/icassp49660.2025.10888476","title":"MMTP: Meta-learning-based Multi-Textual Prompt Tuning for Visual-Language Models","display_name":"MMTP: Meta-learning-based Multi-Textual Prompt Tuning for Visual-Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345636","doi":"https://doi.org/10.1109/icassp49660.2025.10888476"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"display_name":"Fangtong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangtong Sun","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100582535","display_name":"Junjie Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Zhu","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035490519","display_name":"Zunlin Fan","orcid":"https://orcid.org/0000-0003-2226-9505"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zunlin Fan","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102770021","display_name":"Yiying Li","orcid":"https://orcid.org/0000-0002-2632-5175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiying Li","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462299","display_name":"Zhiyuan Wang","orcid":"https://orcid.org/0000-0002-9730-1461"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Wang","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038256457","display_name":"Ke Yang","orcid":"https://orcid.org/0000-0002-6164-274X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Yang","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL),Beijing,China,100091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL),Beijing,China,100091","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9886000156402588,"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":0.9886000156402588,"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/T10028","display_name":"Topic Modeling","score":0.9495000243186951,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9433000087738037,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7978519797325134},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49954724311828613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4970274269580841},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46886685490608215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978519797325134},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49954724311828613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4970274269580841},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46886685490608215}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2533598788","https://openalex.org/W2964194231","https://openalex.org/W3037492894","https://openalex.org/W3174770825","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4205991051","https://openalex.org/W4312310776","https://openalex.org/W4319163914","https://openalex.org/W4386041175","https://openalex.org/W4386065763","https://openalex.org/W4386071547","https://openalex.org/W4386072228","https://openalex.org/W4390873714","https://openalex.org/W4391305834","https://openalex.org/W4393148291","https://openalex.org/W4402753597","https://openalex.org/W4402783842","https://openalex.org/W4403222982","https://openalex.org/W6600983433","https://openalex.org/W6638677478","https://openalex.org/W6683379805","https://openalex.org/W6751797489","https://openalex.org/W6758853722","https://openalex.org/W6763468762","https://openalex.org/W6764990469","https://openalex.org/W6778883912","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6802386650","https://openalex.org/W6802744804","https://openalex.org/W6845152577","https://openalex.org/W6853774274"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Pre-trained":[0],"Visual-Language":[1],"Models":[2],"(VLMs)":[3],"have":[4,22],"demonstrated":[5],"powerful":[6],"performance":[7,67],"on":[8,68],"various":[9],"downstream":[10],"tasks.":[11,28,71],"Recently,":[12],"many":[13],"prompt":[14,126],"tuning":[15,82],"methods":[16,32,64],"represented":[17],"by":[18],"Context":[19],"Optimization":[20],"(CoOp)":[21],"effectively":[23],"adapted":[24],"VLMs":[25],"to":[26,36,44,53,65,92,106,124,132,156],"few-shot":[27,69],"However,":[29],"the":[30,41,94,108,111,115,129,138,158],"CoOp-based":[31],"suffer":[33],"from":[34],"overfitting":[35],"base":[37,118],"classes,":[38,55],"which":[39,85],"impairs":[40],"model\u2019s":[42,96,130],"generalization":[43,99,131,145,148],"new":[45,54,133],"classes.":[46,119,134],"Considering":[47],"that":[48],"meta-learning":[49,58,91,123],"excels":[50],"at":[51],"generalizing":[52],"we":[56,75,102,121,151],"combine":[57],"with":[59],"CoOp-like":[60],"vision-language":[61],"model":[62,112],"fine-tuning":[63],"improve":[66],"generation":[70],"In":[72],"this":[73],"paper,":[74],"present":[76],"a":[77],"novel":[78],"Meta-learning-based":[79],"Multi-Textual":[80],"Prompt":[81],"(MMTP)":[83],"method,":[84],"learns":[86],"multiple":[87],"textual":[88],"prompts":[89,105],"leveraging":[90],"enhance":[93,107],"visual-language":[95],"representation":[97,109],"and":[98,146],"capabilities.":[100],"Specifically,":[101],"introduce":[103],"multi-textual":[104],"of":[110,117,140,160],"for":[113],"improving":[114],"recognition":[116],"Simultaneously,":[120],"employ":[122],"optimize":[125],"training,":[127],"bolstering":[128],"Extensive":[135],"experiments":[136],"demonstrate":[137],"superiority":[139],"our":[141],"method":[142],"under":[143],"base-to-new":[144],"cross-domain":[147],"settings.":[149],"Furthermore,":[150],"also":[152],"conduct":[153],"ablation":[154],"studies":[155],"validate":[157],"effectiveness":[159],"each":[161],"component.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}