{"id":"https://openalex.org/W7164864871","doi":"https://doi.org/10.1145/3805622.3810767","title":"Augmenting medical vision-language pretraining via domain-aware retrieval-augmented caption enrichment","display_name":"Augmenting medical vision-language pretraining via domain-aware retrieval-augmented caption enrichment","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164864871","doi":"https://doi.org/10.1145/3805622.3810767"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810767","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810767","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810767","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111093063","display_name":"Xiaoyang Wei","orcid":"https://orcid.org/0009-0003-8861-0427"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xiaoyang Wei","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9 - LIPADE, Paris, France"],"raw_orcid":"https://orcid.org/0009-0003-8861-0427","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9 - LIPADE, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I4210091437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090167453","display_name":"Camille Kurtz","orcid":"https://orcid.org/0000-0001-9254-7537"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Camille Kurtz","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9 - LIPADE, Paris, France"],"raw_orcid":"https://orcid.org/0000-0001-9254-7537","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9 - LIPADE, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I4210091437"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053762793","display_name":"Florence Cloppet","orcid":"https://orcid.org/0000-0002-4807-299X"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florence Cloppet","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9 - LIPADE, Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-4807-299X","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9 - LIPADE, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I4210091437"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74843695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2219","last_page":"2227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9810000061988831,"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":0.9810000061988831,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.005100000184029341,"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":0.0010999999940395355,"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/context","display_name":"Context (archaeology)","score":0.6000999808311462},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5220000147819519},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5131000280380249},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4677000045776367},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.444599986076355},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.39590001106262207},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38530001044273376},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.36500000953674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7578999996185303},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6000999808311462},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5489000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356000065803528},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36500000953674316},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3224000036716461},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25040000677108765},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810767","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810767","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810767","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810767","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8295556902885437}],"awards":[{"id":"https://openalex.org/G1168208309","display_name":null,"funder_award_id":"202208330098","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2086962047","https://openalex.org/W2159583324","https://openalex.org/W3046375318","https://openalex.org/W3099700870","https://openalex.org/W3104050923","https://openalex.org/W3158665049","https://openalex.org/W4230097545","https://openalex.org/W4385573131","https://openalex.org/W4386587829","https://openalex.org/W4401752980","https://openalex.org/W4403012879","https://openalex.org/W4405728682","https://openalex.org/W4409263655","https://openalex.org/W4413145389","https://openalex.org/W7133182869","https://openalex.org/W7133193597","https://openalex.org/W7133195915","https://openalex.org/W7133236445","https://openalex.org/W7133243546","https://openalex.org/W7133250524"],"related_works":[],"abstract_inverted_index":{"Contrastive":[0],"Language-Image":[1],"Pre-training":[2],"(CLIP)":[3],"has":[4],"demonstrated":[5,154],"strong":[6],"potential":[7,174],"in":[8,60,70,79,132,155,178],"learning":[9],"transferable":[10],"visual":[11,56],"models":[12,100],"/":[13],"representations":[14],"by":[15,43,88,124],"aligning":[16],"paired":[17],"images":[18,106],"and":[19,85,107],"textual":[20],"descriptions.":[21],"Nevertheless,":[22],"the":[23,83,109,133,156],"quality":[24,96],"of":[25,74,111,162],"training":[26,141],"data":[27,65],"remains":[28],"a":[29,119,139,160],"significant":[30],"bottleneck.":[31],"In":[32,114],"many":[33],"real-world":[34],"scenarios,":[35],"image-text":[36],"pairs":[37],"are":[38,46],"often":[39],"noisy":[40],"or":[41,50],"accompanied":[42],"captions":[44,80,131],"that":[45,81,143],"either":[47],"too":[48,51],"short":[49],"generic":[52],"to":[53,93,128],"convey":[54],"key":[55],"attributes.":[57],"For":[58],"example,":[59],"medical":[61,134,157],"imaging,":[62],"most":[63],"available":[64,184],"come":[66],"from":[67],"illustrative":[68],"figures":[69],"public":[71],"literature":[72],"instead":[73],"detailed":[75],"clinical":[76],"reports,":[77],"resulting":[78],"lack":[82],"precision":[84],"context":[86],"provided":[87],"expert":[89,125],"annotations.":[90],"Recent":[91],"efforts":[92],"improve":[94],"caption":[95],"using":[97],"large":[98],"language":[99],"have":[101],"largely":[102],"focused":[103],"on":[104,167],"natural":[105],"overlook":[108],"integration":[110],"domain-specific":[112],"knowledge.":[113],"this":[115],"study,":[116],"we":[117],"propose":[118],"retrieval-augmented":[120],"generation":[121],"framework":[122],"guided":[123],"semantic":[126],"knowledge":[127],"enrich":[129],"image":[130],"context.":[135],"We":[136],"further":[137],"introduce":[138],"multi-text":[140],"strategy":[142],"effectively":[144],"incorporates":[145],"these":[146],"enriched":[147],"descriptions":[148],"into":[149],"CLIP":[150],"training.":[151],"Our":[152,181],"approach,":[153],"domain":[158],"as":[159],"proof":[161],"concept,":[163],"achieves":[164],"state-of-the-art":[165],"performances":[166],"multiple":[168],"downstream":[169],"tasks,":[170],"highlighting":[171],"its":[172],"broader":[173],"for":[175],"vision-language":[176],"pretraining":[177],"specialized":[179],"domains.":[180],"code":[182],"is":[183],"at:":[185],"https://github.com/Wxy-24/RaceCLIP.":[186]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-16T00:00:00"}