{"id":"https://openalex.org/W4392172801","doi":"https://doi.org/10.1109/tpami.2024.3369699","title":"Vision-Language Models for Vision Tasks: A Survey","display_name":"Vision-Language Models for Vision Tasks: A Survey","publication_year":2024,"publication_date":"2024-02-26","ids":{"openalex":"https://openalex.org/W4392172801","doi":"https://doi.org/10.1109/tpami.2024.3369699","pmid":"https://pubmed.ncbi.nlm.nih.gov/38408000"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3369699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3369699","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":["crossref","pubmed"],"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/A5063757648","display_name":"J Zhang","orcid":"https://orcid.org/0000-0003-4519-8244"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingyi Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4519-8244","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067989804","display_name":"Jiaxing Huang","orcid":"https://orcid.org/0000-0002-8681-0471"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiaxing Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8681-0471","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001871038","display_name":"Sheng Jin","orcid":"https://orcid.org/0000-0001-7254-1664"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sheng Jin","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7254-1664","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023507910","display_name":"Shijian Lu","orcid":"https://orcid.org/0000-0002-6766-2506"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shijian Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6766-2506","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":126.7415,"has_fulltext":false,"cited_by_count":791,"citation_normalized_percentile":{"value":0.99989696,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"46","issue":"8","first_page":"5625","last_page":"5644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9713000059127808,"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":0.7946707010269165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6451011300086975},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5544549226760864},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5158385634422302},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5138214230537415},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.44097277522087097},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.44062697887420654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946707010269165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6451011300086975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5544549226760864},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5158385634422302},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5138214230537415},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.44097277522087097},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.44062697887420654},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3369699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3369699","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:38408000","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38408000","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":236,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W24089286","https://openalex.org/W780950768","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1846799578","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W1977295328","https://openalex.org/W1981283549","https://openalex.org/W1993309459","https://openalex.org/W2017814585","https://openalex.org/W2031489346","https://openalex.org/W2041616772","https://openalex.org/W2047643928","https://openalex.org/W2088252378","https://openalex.org/W2102731100","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2117876524","https://openalex.org/W2125215748","https://openalex.org/W2150066425","https://openalex.org/W2151103935","https://openalex.org/W2155904486","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2335728318","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2533598788","https://openalex.org/W2561715562","https://openalex.org/W2592962403","https://openalex.org/W2618530766","https://openalex.org/W2736506089","https://openalex.org/W2737258237","https://openalex.org/W2806857275","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2911964244","https://openalex.org/W2924485953","https://openalex.org/W2948672349","https://openalex.org/W2961193895","https://openalex.org/W2963530300","https://openalex.org/W2963855133","https://openalex.org/W2964194231","https://openalex.org/W2983943451","https://openalex.org/W3022140654","https://openalex.org/W3035524453","https://openalex.org/W3047467323","https://openalex.org/W3094502228","https://openalex.org/W3095670406","https://openalex.org/W3096609285","https://openalex.org/W3118608800","https://openalex.org/W3156892778","https://openalex.org/W3159619744","https://openalex.org/W3170863103","https://openalex.org/W3176641147","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3198675127","https://openalex.org/W3204392079","https://openalex.org/W3208314443","https://openalex.org/W3209532394","https://openalex.org/W3213454282","https://openalex.org/W3213647938","https://openalex.org/W3215626407","https://openalex.org/W3216939881","https://openalex.org/W4221152943","https://openalex.org/W4221167444","https://openalex.org/W4221167912","https://openalex.org/W4224232320","https://openalex.org/W4224246420","https://openalex.org/W4224545477","https://openalex.org/W4225166070","https://openalex.org/W4225307291","https://openalex.org/W4225683910","https://openalex.org/W4225700096","https://openalex.org/W4225832925","https://openalex.org/W4226058394","https://openalex.org/W4226255121","https://openalex.org/W4226427207","https://openalex.org/W4229042118","https://openalex.org/W4229453513","https://openalex.org/W4239510810","https://openalex.org/W4281838252","https://openalex.org/W4293824280","https://openalex.org/W4296406182","https://openalex.org/W4297808394","https://openalex.org/W4300980715","https://openalex.org/W4304699759","https://openalex.org/W4306313147","https://openalex.org/W4306820534","https://openalex.org/W4308241978","https://openalex.org/W4310418568","https://openalex.org/W4310418579","https://openalex.org/W4310557340","https://openalex.org/W4310633667","https://openalex.org/W4312310776","https://openalex.org/W4312420092","https://openalex.org/W4312424618","https://openalex.org/W4312458986","https://openalex.org/W4312559104","https://openalex.org/W4312563428","https://openalex.org/W4312629998","https://openalex.org/W4312651322","https://openalex.org/W4312709113","https://openalex.org/W4312747482","https://openalex.org/W4312773012","https://openalex.org/W4312818263","https://openalex.org/W4312890493","https://openalex.org/W4312910992","https://openalex.org/W4312912313","https://openalex.org/W4312935996","https://openalex.org/W4312956471","https://openalex.org/W4312960937","https://openalex.org/W4312980231","https://openalex.org/W4313026212","https://openalex.org/W4313052647","https://openalex.org/W4313136445","https://openalex.org/W4313139298","https://openalex.org/W4313156423","https://openalex.org/W4320813149","https://openalex.org/W4321021726","https://openalex.org/W4323570427","https://openalex.org/W4376226279","https://openalex.org/W4379089779","https://openalex.org/W4379539341","https://openalex.org/W4379539362","https://openalex.org/W4379929801","https://openalex.org/W4382457317","https://openalex.org/W4382458283","https://openalex.org/W4382468999","https://openalex.org/W4385245566","https://openalex.org/W4385338579","https://openalex.org/W4385572405","https://openalex.org/W4385572827","https://openalex.org/W4386065512","https://openalex.org/W4386065763","https://openalex.org/W4386065874","https://openalex.org/W4386066010","https://openalex.org/W4386071547","https://openalex.org/W4386071614","https://openalex.org/W4386071798","https://openalex.org/W4386071855","https://openalex.org/W4386072185","https://openalex.org/W4386075561","https://openalex.org/W4386075788","https://openalex.org/W4386075882","https://openalex.org/W4386076029","https://openalex.org/W4386076160","https://openalex.org/W4386076397","https://openalex.org/W4386076665","https://openalex.org/W4386113259","https://openalex.org/W4386523254","https://openalex.org/W4386790226","https://openalex.org/W4390871860","https://openalex.org/W4390872508","https://openalex.org/W4390872570","https://openalex.org/W4390873200","https://openalex.org/W4390873290","https://openalex.org/W4390873714","https://openalex.org/W4390874269","https://openalex.org/W4394593151","https://openalex.org/W6600983433","https://openalex.org/W6620707391","https://openalex.org/W6622693193","https://openalex.org/W6637373629","https://openalex.org/W6638677478","https://openalex.org/W6639432524","https://openalex.org/W6676497082","https://openalex.org/W6676647902","https://openalex.org/W6677919164","https://openalex.org/W6691459498","https://openalex.org/W6703116779","https://openalex.org/W6755207826","https://openalex.org/W6758857762","https://openalex.org/W6759579507","https://openalex.org/W6762718338","https://openalex.org/W6765307894","https://openalex.org/W6776700526","https://openalex.org/W6776929863","https://openalex.org/W6778883912","https://openalex.org/W6781586772","https://openalex.org/W6784333009","https://openalex.org/W6787972765","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6796761347","https://openalex.org/W6797399245","https://openalex.org/W6800767728","https://openalex.org/W6802009570","https://openalex.org/W6802517928","https://openalex.org/W6802987763","https://openalex.org/W6803476161","https://openalex.org/W6803728867","https://openalex.org/W6803872405","https://openalex.org/W6803953248","https://openalex.org/W6809591836","https://openalex.org/W6809938868","https://openalex.org/W6809963190","https://openalex.org/W6810039040","https://openalex.org/W6810151762","https://openalex.org/W6810154958","https://openalex.org/W6810545074","https://openalex.org/W6810715974","https://openalex.org/W6811072154","https://openalex.org/W6811102192","https://openalex.org/W6811433417","https://openalex.org/W6811529827","https://openalex.org/W6838865580","https://openalex.org/W6839009181","https://openalex.org/W6839220867","https://openalex.org/W6839546733","https://openalex.org/W6839701648","https://openalex.org/W6842574522","https://openalex.org/W6842585177","https://openalex.org/W6842874653","https://openalex.org/W6843136616","https://openalex.org/W6843495165","https://openalex.org/W6844194202","https://openalex.org/W6845484831","https://openalex.org/W6846004651","https://openalex.org/W6846007759","https://openalex.org/W6846043717","https://openalex.org/W6846157311","https://openalex.org/W6846835116","https://openalex.org/W6846881023","https://openalex.org/W6846977184","https://openalex.org/W6849976536","https://openalex.org/W6850255523","https://openalex.org/W6853279121","https://openalex.org/W6853336233","https://openalex.org/W6853540583"],"related_works":["https://openalex.org/W1564680838","https://openalex.org/W2003125260","https://openalex.org/W2060591604","https://openalex.org/W1992291644","https://openalex.org/W2166791242","https://openalex.org/W2585162246","https://openalex.org/W1934413089","https://openalex.org/W2098419343","https://openalex.org/W2051178964","https://openalex.org/W2989714914"],"abstract_inverted_index":{"Most":[0],"visual":[1,24,33,72,86,91,103,178],"recognition":[2,25,34,73,92,104],"studies":[3,176],"rely":[4],"heavily":[5],"on":[6,63,70],"crowd-labelled":[7],"data":[8],"in":[9,126,172],"deep":[10],"neural":[11],"networks":[12],"(DNNs)":[13],"training,":[14],"and":[15,31,66,119,129,134,145,154,164],"they":[16],"usually":[17],"train":[18],"a":[19,29,76,82],"DNN":[20],"for":[21,89,177],"each":[22],"single":[23,77],"task,":[26],"leading":[27],"to":[28],"laborious":[30],"time-consuming":[32],"paradigm.":[35],"To":[36],"address":[37],"the":[38,64,96,100,107,113,123,132,151,157,173],"two":[39],"challenges,":[40],"Vision-Language":[41],"Models":[42],"(VLMs)":[43],"have":[44],"been":[45],"intensively":[46],"investigated":[47],"recently,":[48],"which":[49],"learns":[50],"rich":[51],"vision-language":[52],"correlation":[53],"from":[54],"web-scale":[55],"image-text":[56],"pairs":[57],"that":[58,98,111,168],"are":[59],"almost":[60],"infinitely":[61],"available":[62],"Internet":[65],"enables":[67],"zero-shot":[68],"predictions":[69],"various":[71,90],"tasks":[74],"with":[75],"VLM.":[78],"This":[79],"paper":[80],"provides":[81],"systematic":[83],"review":[84,133],"of":[85,102,109,136,156],"language":[87],"models":[88],"tasks,":[93],"including:":[94],"(1)":[95],"background":[97],"introduces":[99],"development":[101],"paradigms;":[105],"(2)":[106],"foundations":[108],"VLM":[110,127,138,141,146,175],"summarize":[112],"widely-adopted":[114,124],"network":[115],"architectures,":[116],"pre-training":[117,128,139],"objectives,":[118],"downstream":[120],"tasks;":[121],"(3)":[122],"datasets":[125],"evaluations;":[130],"(4)":[131],"categorization":[135],"existing":[137],"methods,":[140,144],"transfer":[142],"learning":[143],"knowledge":[147],"distillation":[148],"methods;":[149,159],"(5)":[150],"benchmarking,":[152],"analysis":[153],"discussion":[155],"reviewed":[158],"(6)":[160],"several":[161],"research":[162,166],"challenges":[163],"potential":[165],"directions":[167],"could":[169],"be":[170],"pursued":[171],"future":[174],"recognition.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":232},{"year":2025,"cited_by_count":457},{"year":2024,"cited_by_count":96},{"year":2023,"cited_by_count":6}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}