{"id":"https://openalex.org/W4410738163","doi":"https://doi.org/10.1109/tpami.2025.3573852","title":"Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning","display_name":"Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4410738163","doi":"https://doi.org/10.1109/tpami.2025.3573852","pmid":"https://pubmed.ncbi.nlm.nih.gov/40418601"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3573852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3573852","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.10575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049444898","display_name":"Chun-Mei Feng","orcid":"https://orcid.org/0000-0002-3025-8964"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Chun-Mei Feng","raw_affiliation_strings":["Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692616","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0001-6752-6216"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067953198","display_name":"Xinxing Xu","orcid":"https://orcid.org/0000-0003-1449-3072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinxing Xu","raw_affiliation_strings":["Microsoft Research Asia, Singapore","Microsoft Research Asia Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Singapore","institution_ids":[]},{"raw_affiliation_string":"Microsoft Research Asia Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000300751","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-9502-1749"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001599295","display_name":"Rick Siow Mong Goh","orcid":"https://orcid.org/0000-0001-9116-1595"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rick Siow Mong Goh","raw_affiliation_strings":["Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","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":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006207459","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0002-1590-2029"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5049444898"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79237465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"47","issue":"9","first_page":"7660","last_page":"7674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9883000254631042,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9883000254631042,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9782000184059143,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9541000127792358,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7488757967948914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6760144233703613},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5637234449386597},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.5500687956809998},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5480650663375854},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4972393810749054},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.49505415558815},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1289784014225006}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7488757967948914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6760144233703613},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5637234449386597},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5500687956809998},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5480650663375854},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4972393810749054},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.49505415558815},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1289784014225006},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2025.3573852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3573852","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40418601","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40418601","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2506.10575","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.10575","pdf_url":"https://arxiv.org/pdf/2506.10575","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.10575","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.10575","pdf_url":"https://arxiv.org/pdf/2506.10575","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2031489346","https://openalex.org/W2521365688","https://openalex.org/W2890153145","https://openalex.org/W2917792613","https://openalex.org/W2932399282","https://openalex.org/W2963300078","https://openalex.org/W2963676620","https://openalex.org/W2963745697","https://openalex.org/W2969792713","https://openalex.org/W2982112268","https://openalex.org/W2998420437","https://openalex.org/W3034472074","https://openalex.org/W3034600949","https://openalex.org/W3096831136","https://openalex.org/W3198377975","https://openalex.org/W3202858701","https://openalex.org/W3202884348","https://openalex.org/W4212944375","https://openalex.org/W4225930680","https://openalex.org/W4226342448","https://openalex.org/W4312310776","https://openalex.org/W4312824283","https://openalex.org/W4312884055","https://openalex.org/W4312933868","https://openalex.org/W4313175608","https://openalex.org/W4385567053","https://openalex.org/W4386072096","https://openalex.org/W4386113259","https://openalex.org/W4390873714","https://openalex.org/W4393148714","https://openalex.org/W4401024541","https://openalex.org/W4407937652","https://openalex.org/W4409262898","https://openalex.org/W6630792627","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6757817989","https://openalex.org/W6791353385","https://openalex.org/W6803272276","https://openalex.org/W6809885388","https://openalex.org/W6810334672","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6839546733","https://openalex.org/W6845281891","https://openalex.org/W6846260888","https://openalex.org/W6850625674","https://openalex.org/W6854511533"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2485605994","https://openalex.org/W2160602540","https://openalex.org/W4385571108","https://openalex.org/W4200251711"],"abstract_inverted_index":{"Benefited":[0],"from":[1,98],"image-text":[2],"contrastive":[3],"learning,":[4],"pre-trained":[5,88],"vision-language":[6],"models,":[7],"e.g.,":[8],"CLIP,":[9],"allow":[10],"to":[11,30,33,67,86,92,148],"direct":[12],"leverage":[13,87],"texts":[14],"as":[15,57],"images":[16,97],"(TaI)":[17],"for":[18,78,133,160,183],"parameter-efficient":[19],"fine-tuning":[20],"(PEFT).":[21],"While":[22],"CLIP":[23,180,189],"is":[24,85],"capable":[25],"of":[26,50,83,125,178],"making":[27,122],"image":[28,47,54],"features":[29,128],"be":[31],"similar":[32],"the":[34,38,69,103,123,158,168,175,179,214],"corresponding":[35],"text":[36,76,99],"features,":[37],"modality":[39,70,104],"gap":[40,71],"remains":[41],"a":[42,62,112],"nontrivial":[43],"issue":[44,72],"and":[45,95,115,131,145,172,199],"limits":[46],"recognition":[48,55,207],"performance":[49,208],"TaI.":[51],"Using":[52],"multi-label":[53,134],"(MLR)":[56],"an":[58],"example,":[59],"we":[60,139],"present":[61],"novel":[63],"method,":[64],"called":[65],"T2I-PAL":[66,84,110,152,204],"tackle":[68],"when":[73],"using":[74],"only":[75],"captions":[77],"PEFT.":[79],"The":[80],"core":[81],"design":[82],"text-to-image":[89],"generation":[90],"models":[91],"generate":[93],"photo-realistic":[94],"diverse":[96],"captions,":[100],"thereby":[101,166],"reducing":[102,167],"gap.":[105],"To":[106],"further":[107,140],"enhance":[108,149],"MLR,":[109],"incorporates":[111],"class-wise":[113],"heatmap":[114],"learnable":[116],"prototypes.":[117],"This":[118],"aggregates":[119],"local":[120,126],"similarities,":[121],"representation":[124],"visual":[127],"more":[129],"robust":[130],"informative":[132],"recognition.":[135],"For":[136],"better":[137],"PEFT,":[138],"combine":[141],"both":[142],"prompt":[143],"tuning":[144],"adapter":[146],"learning":[147],"classification":[150],"performance.":[151],"offers":[153],"significant":[154],"advantages:":[155],"it":[156,173],"eliminates":[157],"need":[159],"fully":[161],"semantically":[162],"annotated":[163],"training":[164],"images,":[165],"manual":[169],"annotation":[170],"workload,":[171],"preserves":[174],"intrinsic":[176],"mode":[177],"model,":[181],"allowing":[182],"seamless":[184],"integration":[185],"with":[186],"any":[187],"existing":[188],"framework.":[190],"Extensive":[191],"experiments":[192],"on":[193],"multiple":[194],"benchmarks,":[195],"including":[196],"MS-COCO,":[197],"VOC2007,":[198],"NUS-WIDE,":[200],"show":[201],"that":[202],"our":[203],"can":[205],"boost":[206],"by":[209],"3.47%":[210],"in":[211],"average":[212],"above":[213],"top-ranked":[215],"state-of-the-art":[216],"methods.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}