{"id":"https://openalex.org/W4409129027","doi":"https://doi.org/10.1109/tcsvt.2025.3557474","title":"Progressive Multi-Prompt Learning for Vision-Language Models","display_name":"Progressive Multi-Prompt Learning for Vision-Language Models","publication_year":2025,"publication_date":"2025-04-03","ids":{"openalex":"https://openalex.org/W4409129027","doi":"https://doi.org/10.1109/tcsvt.2025.3557474"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3557474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3557474","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Jun Liu","orcid":"https://orcid.org/0009-0007-4759-2276"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Liu","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-4759-2276","affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103069321","display_name":"Ziqian Lu","orcid":"https://orcid.org/0009-0007-3579-9130"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqian Lu","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-3579-9130","affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Luo","orcid":"https://orcid.org/0000-0002-3233-326X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Luo","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3233-326X","affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083531923","display_name":"Zhe\u2010Ming Lu","orcid":"https://orcid.org/0000-0003-1785-7847"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheming Lu","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1785-7847","affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025598497","display_name":"Yangming Zheng","orcid":"https://orcid.org/0000-0002-7577-4778"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangming Zheng","raw_affiliation_strings":["School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":4.533,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94268521,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"35","issue":"10","first_page":"9562","last_page":"9574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9632999897003174,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9591000080108643,"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":0.7279641032218933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5428616404533386},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4779201149940491},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37738269567489624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279641032218933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5428616404533386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4779201149940491},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37738269567489624}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3557474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3557474","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1928906481","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2533598788","https://openalex.org/W2964194231","https://openalex.org/W2970476646","https://openalex.org/W3035030897","https://openalex.org/W3035038672","https://openalex.org/W3037492894","https://openalex.org/W3177096435","https://openalex.org/W3182683290","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3213454282","https://openalex.org/W4205991051","https://openalex.org/W4229453513","https://openalex.org/W4297697565","https://openalex.org/W4309811444","https://openalex.org/W4310557340","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4312935996","https://openalex.org/W4315473444","https://openalex.org/W4321021726","https://openalex.org/W4385569741","https://openalex.org/W4386065835","https://openalex.org/W4386071547","https://openalex.org/W4388266798","https://openalex.org/W4390872773","https://openalex.org/W4390873004","https://openalex.org/W4392426151","https://openalex.org/W4396505919","https://openalex.org/W4400904454","https://openalex.org/W4403791538"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recently,":[0],"methods":[1,106],"that":[2,107],"utilize":[3,108,229],"prompt":[4,109],"tuning":[5,110],"to":[6,13,36,111,118,141,220,236,244,260,294],"rapidly":[7,112],"transfer":[8,113],"pretrained":[9,114],"vision-language":[10,115],"models":[11,21,116,126],"(VLMs)":[12,117],"downstream":[14,119],"tasks":[15,120],"have":[16,22,121,127],"been":[17,122],"proposed.":[18,123],"Although":[19,124],"these":[20,97,125,202],"produced":[23,128],"reasonable":[24,129],"results,":[25,130],"they":[26,131],"typically":[27,132],"learn":[28,133],"a":[29,71,134,176,217,230,245],"single":[30,135],"prompt,":[31,136],"which":[32,75,137,180],"limits":[33,138],"their":[34,139],"ability":[35,42,140,147],"capture":[37,142],"more":[38,84,143,189],"diverse":[39,144],"information.":[40,145,224],"This":[41,81,146,186],"is":[43,148,304],"crucial":[44,149],"for":[45,90,150,195,254],"addressing":[46,151],"fine-grained":[47,152],"classification":[48,153],"challenges":[49,154],"and":[50,59,92,155,164,197,242,278,291],"intraclass":[51,156],"visual":[52,157],"variability":[53,158],"(<italic":[54,159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55,160,232],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e.g.</i>,":[56,161],"color,":[57,162],"pose,":[58,163],"size":[60,165],"variations":[61,166],"within":[62,167],"the":[63,78,87,168,183,192,238,252,262,297],"same":[64,169],"category).":[65,170],"However,":[66,171],"learning":[67,104,172,209],"multiple":[68,173,214],"prompts":[69,174,215,241,253],"provides":[70,175],"larger":[72,177],"optimization":[73,178,264],"space,":[74,179],"further":[76,181,295],"exacerbates":[77,182],"overfitting":[79,184],"phenomenon.":[80,185],"makes":[82,187],"it":[83,188],"challenging":[85,190],"balance":[86,191,251],"performances":[88,193],"acienved":[89,194],"base":[91,196],"new":[93,198],"categories.":[94,199],"To":[95,200,225],"address":[96,201],"issues,":[98,203],"we":[99,204,212,228,250,285],"propose":[100,205],"progressive":[101,206],"multi-prompt":[102],"(PMP)":[103,208],"method.ecently,":[105],"multiprompt":[207],"method.R":[210],"Specifically,":[211],"introduce":[213],"in":[216,274],"step-by-step":[218],"manner":[219],"focus":[221],"on":[222],"various":[223],"reduce":[226],"overfitting,":[227],"<italic":[231],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">late":[233],"attaching</i>":[234],"mechanism":[235],"defer":[237],"interactions":[239],"of":[240,299],"features":[243],"deeper":[246],"encoding":[247],"layer.":[248],"Furthermore,":[249],"different":[255],"layers":[256],"with":[257,270],"learnable":[258],"weights":[259],"guide":[261],"optimal":[263],"procedure.":[265],"We":[266],"compared":[267],"our":[268,300],"method":[269],"several":[271],"state-of-the-art":[272],"approaches":[273],"base-to-new":[275],"task":[276],"settings":[277],"demonstrate":[279],"superior":[280],"base-new":[281],"tradeoff":[282],"performance.":[283],"Additionally,":[284],"conducted":[286],"cross-dataset":[287],"transfer,":[288],"domain":[289],"generalization,":[290],"few-shot":[292],"experiments":[293],"validate":[296],"effectiveness":[298],"method.":[301],"Our":[302],"code":[303],"available":[305],"at":[306],"https://github.com/JunLGeek/PMP.git.":[307]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}