{"id":"https://openalex.org/W7131615295","doi":"https://doi.org/10.1109/access.2026.3668187","title":"A Taxonomy of Knowledge Bases for Retrieval-Augmented Methods in Vision: A Comprehensive Survey","display_name":"A Taxonomy of Knowledge Bases for Retrieval-Augmented Methods in Vision: A Comprehensive Survey","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131615295","doi":"https://doi.org/10.1109/access.2026.3668187"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3668187","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3668187","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3668187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Geonwoo Kim","orcid":"https://orcid.org/0009-0007-1567-9107"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geonwoo Kim","raw_affiliation_strings":["Department of Computer Education/Applied AI, Sungkyunkwan University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-1567-9107","affiliations":[{"raw_affiliation_string":"Department of Computer Education/Applied AI, Sungkyunkwan University, Seoul, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong-Hwan Lee","orcid":"https://orcid.org/0009-0001-2181-9213"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Hwan Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0001-2181-9213","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101596480","display_name":"Jang\u2010Hee Yoo","orcid":"https://orcid.org/0000-0003-0495-9211"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jang-Hee Yoo","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-0495-9211","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15625148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"32736","last_page":"32754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.28290000557899475,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.28290000557899475,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.12939999997615814,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0722000002861023,"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/taxonomy","display_name":"Taxonomy (biology)","score":0.6489999890327454},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6304000020027161},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.41290000081062317},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4097000062465668},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4068000018596649},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.3993000090122223},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.34380000829696655},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.32440000772476196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269000053405762},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6610999703407288},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6304000020027161},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3702999949455261},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2780613888","wikidata":"https://www.wikidata.org/wiki/Q6423394","display_name":"Knowledge retrieval","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3668187","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3668187","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:97897bbcae7d438381dec6ba180a6469","is_oa":true,"landing_page_url":"https://doaj.org/article/97897bbcae7d438381dec6ba180a6469","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 32736-32754 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3668187","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3668187","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6442080140113831,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G180690313","display_name":null,"funder_award_id":"RS-2024-00442120","funder_id":"https://openalex.org/F4320334879","funder_display_name":"Korea Evaluation Institute of Industrial Technology"}],"funders":[{"id":"https://openalex.org/F4320334879","display_name":"Korea Evaluation Institute of Industrial Technology","ror":"https://ror.org/03z9cwa38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"vision\u2013language":[1],"models":[2],"(VLMs)":[3],"demonstrate":[4],"impressive":[5],"performance":[6],"but":[7],"often":[8,155],"hallucinate":[9],"when":[10],"essential":[11],"knowledge":[12,25],"is":[13],"not":[14],"encoded":[15],"in":[16,33,176],"their":[17],"parameters.":[18],"Retrieval-augmented":[19],"generation":[20],"(RAG),":[21],"which":[22,55],"integrates":[23],"external":[24],"bases":[26],"(KBs),":[27],"has":[28,40,53],"thus":[29],"been":[30,42],"widely":[31],"adopted":[32],"computer":[34],"vision.":[35],"Beyond":[36],"VLMs,":[37],"retrieval":[38,118,174,184],"augmentation":[39],"also":[41],"applied":[43],"independently":[44],"to":[45],"improve":[46],"task":[47],"performance.":[48],"However,":[49],"no":[50],"systematic":[51],"analysis":[52,131],"investigated":[54],"types":[56],"of":[57,75,93,135],"KBs":[58],"are":[59],"most":[60,138],"suitable":[61],"for":[62,162,170,182],"particular":[63],"vision":[64,177],"tasks.":[65],"In":[66],"this":[67,153],"study,":[68],"we":[69,116,166],"present":[70],"the":[71,180],"first":[72],"comprehensive":[73],"survey":[74],"more":[76],"than":[77],"sixty":[78],"studies":[79],"(2021\u20132025)":[80],"with":[81,144],"a":[82,90,148],"novel":[83],"focus":[84],"on":[85,141],"KB":[86,136,171],"types.":[87],"We":[88],"propose":[89],"taxonomy":[91],"consisting":[92],"six":[94],"categories:":[95],"unstructured":[96],"text":[97],"(V-UT),":[98],"ontology":[99],"(V-OT),":[100],"image":[101],"(V-IM),":[102],"image\u2013text":[103],"pairs":[104],"(V-IT),":[105],"structured":[106],"graphs":[107],"(V-SG),":[108],"and":[109,124,173,178,186],"domain-specific":[110],"data":[111],"(V-DM).":[112],"For":[113],"each":[114],"category,":[115],"review":[117],"pipelines,":[119],"downstream":[120],"tasks,":[121],"representative":[122],"datasets,":[123],"indexing":[125],"strategies":[126],"under":[127],"consistent":[128],"criteria.":[129],"Our":[130],"shows":[132],"that,":[133],"regardless":[134],"type,":[137],"systems":[139],"converge":[140],"dense":[142],"encoders":[143],"vector":[145],"databases,":[146],"reflecting":[147],"mature":[149],"technical":[150],"stack.":[151],"Nevertheless,":[152],"convergence":[154],"underutilizes":[156],"KB-specific":[157,183],"structures,":[158],"highlighting":[159],"significant":[160],"opportunities":[161],"future":[163],"studies.":[164],"Finally,":[165],"provide":[167],"practical":[168],"guidelines":[169],"selection":[172],"design":[175],"emphasize":[179],"need":[181],"methods":[185],"standardized":[187],"benchmarks.":[188]},"counts_by_year":[],"updated_date":"2026-03-06T06:45:51.903784","created_date":"2026-02-27T00:00:00"}