{"id":"https://openalex.org/W4403582635","doi":"https://doi.org/10.1145/3627673.3679963","title":"Meta-Prompt Tuning Vision-Language Model for Multi-Label Few-Shot Image Recognition","display_name":"Meta-Prompt Tuning Vision-Language Model for Multi-Label Few-Shot Image Recognition","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582635","doi":"https://doi.org/10.1145/3627673.3679963"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-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":"https://openalex.org/A5102424079","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0002-8373-9366"},"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":true,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["School of Computer Science, Peking University & Institute of Computational Social Science, Peking University (Qingdao), Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University & Institute of Computational Social Science, Peking University (Qingdao), Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344431","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-4069-6423"},"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":"Wei Chen","raw_affiliation_strings":["School of Computer Science, Peking University & Institute of Computational Social Science, Peking University (Qingdao), Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University & Institute of Computational Social Science, Peking University (Qingdao), Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911810","display_name":"Fei Ding","orcid":"https://orcid.org/0009-0006-5431-4744"},"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":"Fei Ding","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University & Institute for Artificial Intelligence, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University & Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024699604","display_name":"Tengjiao Wang","orcid":"https://orcid.org/0000-0002-7395-5567"},"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":"Tengjiao Wang","raw_affiliation_strings":["School of Computer Science, Peking University & Institute of Computational Social Science, Peking University (Qingdao), Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University & Institute of Computational Social Science, Peking University (Qingdao), Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856304","display_name":"Dezhen Lu","orcid":"https://orcid.org/0000-0002-3787-2107"},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Lu","raw_affiliation_strings":["State Grid Information and Telecommunication Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Grid Information and Telecommunication Group, Beijing, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035808152","display_name":"Jiabin Zheng","orcid":"https://orcid.org/0009-0000-9832-1125"},"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":"Jiabin Zheng","raw_affiliation_strings":["School of Computer Science, Peking University & Institute of Computational Social Science, Peking University (Qingdao), Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University & Institute of Computational Social Science, Peking University (Qingdao), Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102424079"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55237787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4258","last_page":"4262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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":0.9980999827384949,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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":0.7461917400360107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6366575956344604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6148048639297485},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5653793215751648},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5543125867843628},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32591119408607483}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461917400360107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6366575956344604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6148048639297485},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5653793215751648},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5543125867843628},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32591119408607483},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W2560674852","https://openalex.org/W3087020912","https://openalex.org/W3089555680","https://openalex.org/W3109067582","https://openalex.org/W3174396085","https://openalex.org/W4297683907","https://openalex.org/W4312238419","https://openalex.org/W4382202923","https://openalex.org/W4386113259","https://openalex.org/W4390203943"],"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":{"Multi-label":[0],"few-shot":[1,90],"image":[2,91,139],"recognition":[3,140],"aims":[4],"to":[5,57,63,74,83,101,114,123],"identify":[6],"multiple":[7],"unseen":[8],"objects":[9],"using":[10],"only":[11],"a":[12,34,76,97],"handful":[13],"of":[14,129,145],"examples.":[15],"Recent":[16],"methods":[17],"typically":[18],"tune":[19],"pre-trained":[20],"vision-language":[21],"models":[22],"with":[23],"shared":[24,35],"or":[25],"class-specific":[26],"prompts.":[27,130],"However,":[28],"they":[29],"still":[30],"have":[31],"drawbacks.":[32],"Tuning":[33],"prompt":[36,78,82,99],"is":[37,55,112],"insufficient":[38],"for":[39,52,88],"all":[40],"samples":[41,104],"especially":[42],"when":[43],"the":[44,109,127,143],"tasks":[45,106,122],"are":[46],"complex":[47,103],"and":[48,105,117],"tuning":[49],"specific":[50],"prompts":[51],"each":[53,81],"class":[54],"inevitable":[56],"lose":[58],"generalization":[59,128],"ability,":[60],"thus":[61],"failing":[62],"capture":[64],"diverse":[65,98],"visual":[66],"knowledge.":[67],"To":[68],"address":[69],"these":[70],"issues,":[71],"we":[72,94],"propose":[73],"meta-tune":[75],"generalized":[77],"pool,":[79],"enabling":[80],"act":[84],"as":[85],"an":[86],"expert":[87],"multi-label":[89,138],"recognition.":[92],"Specifically,":[93],"first":[95],"construct":[96],"pool":[100],"handle":[102],"effectively.":[107],"Then,":[108],"meta-tuning":[110],"strategy":[111],"designed":[113],"learn":[115],"meta-knowledge":[116],"transfer":[118],"it":[119],"from":[120],"source":[121],"target":[124],"tasks,":[125],"enhancing":[126],"Extensive":[131],"experimental":[132],"results":[133],"on":[134],"two":[135],"widely":[136],"used":[137],"datasets":[141],"demonstrate":[142],"effectiveness":[144],"our":[146],"method.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}