{"id":"https://openalex.org/W4388191278","doi":"https://doi.org/10.1145/3581783.3612403","title":"Fine-Grained Visual Prompt Learning of Vision-Language Models for Image Recognition","display_name":"Fine-Grained Visual Prompt Learning of Vision-Language Models for Image Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388191278","doi":"https://doi.org/10.1145/3581783.3612403"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612403","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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":"https://openalex.org/A5100755638","display_name":"Hongbo Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Sun","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2639-9035","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017511861","display_name":"Xiangteng He","orcid":"https://orcid.org/0000-0001-8502-5685"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangteng He","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8502-5685","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055004003","display_name":"Jiahuan Zhou","orcid":"https://orcid.org/0000-0002-3301-747X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahuan Zhou","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3301-747X","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047811387","display_name":"Yuxin Peng","orcid":"https://orcid.org/0000-0001-7658-3845"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Peng","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7658-3845","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5828","last_page":"5836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.998199999332428,"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":0.8280754089355469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7049866914749146},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6227344870567322},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5630326271057129},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5607410669326782},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5207145810127258},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5059184432029724},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4681420922279358},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4614746570587158},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45058247447013855},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4296857416629791},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4183095693588257},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41390925645828247},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.404299795627594},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3833240866661072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.382354736328125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280754089355469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7049866914749146},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6227344870567322},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5630326271057129},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5607410669326782},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5207145810127258},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5059184432029724},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4681420922279358},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4614746570587158},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45058247447013855},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4296857416629791},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4183095693588257},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41390925645828247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.404299795627594},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3833240866661072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.382354736328125},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612403","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6071309851","display_name":null,"funder_award_id":"61925201, 62132001, 62272013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":19,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2133059825","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2533598788","https://openalex.org/W2765268259","https://openalex.org/W2964194231","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3173909648","https://openalex.org/W3198377975","https://openalex.org/W3206734547","https://openalex.org/W4304084267","https://openalex.org/W4312310776","https://openalex.org/W4313175608"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2761785940","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W2129933262"],"abstract_inverted_index":{"Large-scale":[0],"pre-trained":[1],"vision-language":[2,100,126,171],"(VL)":[3],"models":[4,101],"have":[5],"shown":[6],"powerful":[7],"generic":[8],"representation":[9],"capabilities":[10],"for":[11,55,102,128,147,182],"adapting":[12],"to":[13,24,33,42,50,83,158],"downstream":[14,60,86],"tasks":[15],"with":[16,105,185],"limited":[17],"training":[18,107,180,204],"data,":[19],"which":[20,80,141,207],"are":[21],"data-efficient":[22],"solutions":[23],"various":[25],"applications":[26],"such":[27],"as":[28],"image":[29,78,103,122,148,197],"recognition.":[30,149],"In":[31,89],"order":[32],"enhance":[34],"the":[35,47,56,59,67,77,85,110,121,125,131,139,160,166,170,174,178,186,202],"adaption":[36],"performance,":[37],"most":[38],"existing":[39],"methods":[40],"attempt":[41],"introduce":[43],"learnable":[44],"vectors":[45],"into":[46,120],"text":[48,68],"prompt":[49,96,117],"generate":[51],"adaptive":[52,72,153],"classification":[53],"weights":[54],"class":[57],"in":[58],"task.":[61],"However,":[62],"they":[63],"generally":[64],"focus":[65],"on":[66,76,130,195],"side":[69],"while":[70],"neglecting":[71],"visual":[73,95,116,145,175],"feature":[74,189],"generation":[75],"side,":[79],"is":[81,118,156,219],"insufficient":[82],"fit":[84],"task":[87],"data.":[88],"this":[90],"paper,":[91],"we":[92],"propose":[93],"fine-grained":[94],"learning":[97],"(FG-VPL)":[98],"of":[99,124,169,177,188],"recognition":[104,154,198],"few":[106,203],"samples,":[108],"and":[109,134,163,173],"main":[111],"contributions":[112],"are:":[113],"(1)":[114],"Fine-grained":[115],"introduced":[119],"encoder":[123],"model":[127,172],"focusing":[129],"target":[132],"object":[133],"conducting":[135],"information":[136,176],"interaction":[137],"within":[138],"object,":[140],"facilitates":[142],"generating":[143],"discriminative":[144],"features":[146],"(2)":[150],"A":[151],"two-pathway":[152],"module":[155],"proposed":[157,211],"narrow":[159],"domain":[161],"gap":[162],"utilize":[164],"both":[165],"cross-modal":[167],"knowledge":[168],"few-sample":[179],"set":[181],"classifying":[183],"images":[184],"help":[187],"adapters.":[190],"We":[191],"conduct":[192],"extensive":[193],"experiments":[194],"11":[196],"benchmark":[199],"datasets":[200],"under":[201],"samples":[205],"setting,":[206],"demonstrate":[208],"that":[209],"our":[210],"approach":[212],"can":[213],"achieve":[214],"state-of-the-art":[215],"performance.":[216],"The":[217],"code":[218],"available":[220],"at":[221],"https://github.com/PKU-ICST-MIPL/FG-VPL_ACMMM2023.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}