{"id":"https://openalex.org/W4386113259","doi":"https://doi.org/10.1109/cvpr52729.2023.00275","title":"Texts as Images in Prompt Tuning for Multi-Label Image Recognition","display_name":"Texts as Images in Prompt Tuning for Multi-Label Image Recognition","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386113259","doi":"https://doi.org/10.1109/cvpr52729.2023.00275"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.00275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5101873331","display_name":"Zixian Guo","orcid":"https://orcid.org/0009-0008-9032-8101"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixian Guo","raw_affiliation_strings":["Harbin Institute of Technology","Harbin Institute of Technology; Tomorrow Advancing Life"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology; Tomorrow Advancing Life","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760029","display_name":"Bowen Dong","orcid":"https://orcid.org/0000-0001-7379-1286"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Dong","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024537984","display_name":"Zhilong Ji","orcid":"https://orcid.org/0000-0002-8799-3409"},"institutions":[{"id":"https://openalex.org/I4210154505","display_name":"Tomorrows Children\u2019s Fund","ror":"https://ror.org/04wgs4413","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210154505"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhilong Ji","raw_affiliation_strings":["Tomorrow Advancing Life"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tomorrow Advancing Life","institution_ids":["https://openalex.org/I4210154505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036032938","display_name":"Jinfeng Bai","orcid":"https://orcid.org/0000-0001-8940-480X"},"institutions":[{"id":"https://openalex.org/I4210154505","display_name":"Tomorrows Children\u2019s Fund","ror":"https://ror.org/04wgs4413","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210154505"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinfeng Bai","raw_affiliation_strings":["Tomorrow Advancing Life"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tomorrow Advancing Life","institution_ids":["https://openalex.org/I4210154505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067005644","display_name":"Yiwen Guo","orcid":"https://orcid.org/0000-0002-0709-4877"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiwen Guo","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636655","display_name":"Wangmeng Zuo","orcid":"https://orcid.org/0000-0002-3330-783X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["Pazhou Lab,Guangzhou","Harbin Institute of Technology; Pazhou Lab, Guangzhou; Tomorrow Advancing Life"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pazhou Lab,Guangzhou","institution_ids":[]},{"raw_affiliation_string":"Harbin Institute of Technology; Pazhou Lab, Guangzhou; Tomorrow Advancing Life","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3817,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.97718616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2808","last_page":"2817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.8459019660949707},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7119789719581604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6249290108680725},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5830487012863159},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5384483337402344},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5357524156570435},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42652732133865356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42513296008110046},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41266143321990967},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40529724955558777},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33614930510520935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8459019660949707},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7119789719581604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6249290108680725},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5830487012863159},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5384483337402344},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5357524156570435},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42652732133865356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42513296008110046},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41266143321990967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40529724955558777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33614930510520935},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.00275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1567302070","https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2031489346","https://openalex.org/W2560096627","https://openalex.org/W2788361849","https://openalex.org/W2917792613","https://openalex.org/W2932399282","https://openalex.org/W2936881865","https://openalex.org/W2963346784","https://openalex.org/W2963745697","https://openalex.org/W2966628364","https://openalex.org/W2969792713","https://openalex.org/W2982112268","https://openalex.org/W3039406286","https://openalex.org/W3093484105","https://openalex.org/W3099518117","https://openalex.org/W3126337491","https://openalex.org/W3166396011","https://openalex.org/W3198377975","https://openalex.org/W3204250462","https://openalex.org/W3207750165","https://openalex.org/W3212456749","https://openalex.org/W3215626407","https://openalex.org/W4212944375","https://openalex.org/W4214673031","https://openalex.org/W4225323055","https://openalex.org/W4225930680","https://openalex.org/W4226342448","https://openalex.org/W4229453513","https://openalex.org/W4283206785","https://openalex.org/W4283313485","https://openalex.org/W4296151208","https://openalex.org/W4312310776","https://openalex.org/W4313175608","https://openalex.org/W4388543952","https://openalex.org/W4390873714","https://openalex.org/W6630792627","https://openalex.org/W6633994051","https://openalex.org/W6639102338","https://openalex.org/W6780449859","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6802347785","https://openalex.org/W6803728867","https://openalex.org/W6803872405","https://openalex.org/W6803953248","https://openalex.org/W6810334672","https://openalex.org/W6810601475","https://openalex.org/W6811219898","https://openalex.org/W6838789006","https://openalex.org/W6838789509","https://openalex.org/W6839023802","https://openalex.org/W6839546733","https://openalex.org/W6840581212","https://openalex.org/W6842574522"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W4312518048","https://openalex.org/W3094960827","https://openalex.org/W2996769815"],"abstract_inverted_index":{"Prompt":[0],"tuning":[1,72,124],"has":[2],"been":[3],"employed":[4],"as":[5,68,112],"an":[6],"efficient":[7],"way":[8],"to":[9,17,65,79,87,102,114,129,176],"adapt":[10],"large":[11,154],"vision-language":[12],"pre-trained":[13],"models":[14],"(e.g.":[15],"CLIP)":[16,60],"various":[18],"downstream":[19],"tasks":[20],"in":[21,38,53,108],"data-limited":[22],"or":[23],"label-limited":[24],"settings.":[25],"Nonetheless,":[26],"visual":[27,81],"data":[28],"(e.g.,":[29],"images)":[30],"is":[31,126,183],"by":[32,152],"default":[33],"prerequisite":[34],"for":[35,70,116,136],"learning":[36,52],"prompts":[37],"existing":[39,170],"methods.":[40],"In":[41,77],"this":[42],"work,":[43],"we":[44,98],"advocate":[45],"that":[46,145],"the":[47,55,80,109,138],"effectiveness":[48],"of":[49,172],"image-text":[50],"contrastive":[51],"aligning":[54],"two":[56],"modalities":[57],"(for":[58],"training":[59],"further":[61,127],"makes":[62],"it":[63,165],"feasible":[64],"treat":[66],"texts":[67],"images":[69,115,175],"prompt":[71,117,123],"and":[73,89,133,162],"introduce":[74],"TaI":[75,100],"prompting.":[76],"contrast":[78],"data,":[82],"text":[83],"descriptions":[84],"are":[85],"easy":[86],"collect,":[88],"their":[90],"class":[91],"labels":[92],"can":[93,166],"be":[94,167],"directly":[95],"derived.":[96],"Particularly,":[97],"apply":[99],"prompting":[101,173],"multi-label":[103,139],"image":[104],"recognition,":[105],"where":[106],"sentences":[107],"wild":[110],"serve":[111],"alternatives":[113],"tuning.":[118],"Moreover,":[119],"with":[120,169],"TaI,":[121],"double-grained":[122],"(TaI-DPT)":[125],"presented":[128],"extract":[130],"both":[131],"coarse-grained":[132],"fine-grained":[134],"embeddings":[135],"enhancing":[137],"recognition":[140,178],"performance.":[141],"Experimental":[142],"results":[143],"show":[144],"our":[146],"proposed":[147],"TaI-DPT":[148],"outperforms":[149],"zero-shot":[150],"CLIP":[151],"a":[153],"margin":[155],"on":[156],"multiple":[157],"benchmarks,":[158],"e.g.,":[159],"MS-COCO,":[160],"VOC2007,":[161],"NUS-WIDE,":[163],"while":[164],"combined":[168],"methods":[171],"from":[174],"improve":[177],"performance":[179],"further.":[180],"The":[181],"code":[182],"released":[184],"at":[185],"https://github.com/guozix/TaI-DPT.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}