{"id":"https://openalex.org/W7137971006","doi":"https://doi.org/10.1609/aaai.v40i5.37336","title":"uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data","display_name":"uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137971006","doi":"https://doi.org/10.1609/aaai.v40i5.37336"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i5.37336","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37336","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37336/41298","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37336/41298","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129668009","display_name":"Dahyun Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dahyun Chung","raw_affiliation_strings":["Korea University"],"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020354733","display_name":"Dongik Shin","orcid":"https://orcid.org/0000-0003-4551-231X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghyun Shin","raw_affiliation_strings":["Korea University"],"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129709014","display_name":"Yujin Sung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujin Sung","raw_affiliation_strings":["Korea University"],"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Seunggi Moon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seunggi Moon","raw_affiliation_strings":["Korea University"],"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129658019","display_name":"Jinwoo Jeon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinwoo Jeon","raw_affiliation_strings":["Korea University"],"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129649114","display_name":"Byung-Jun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byung-Jun Lee","raw_affiliation_strings":["Korea University"],"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129668009"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23133236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3399","last_page":"3406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9435999989509583,"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":0.9435999989509583,"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":0.011900000274181366,"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/T10028","display_name":"Topic Modeling","score":0.003599999938160181,"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/encoder","display_name":"Encoder","score":0.6430000066757202},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4562000036239624},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44699999690055847},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4456999897956848},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.3628000020980835},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.34850001335144043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882000207901001},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6430000066757202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5771999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.569599986076355},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i5.37336","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37336","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37336/41298","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37336","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37336","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37336/41298","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.42970719933509827,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137971006.pdf","grobid_xml":"https://content.openalex.org/works/W7137971006.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contrastive":[0],"Language\u2013Image":[1],"Pre-training":[2],"(CLIP)":[3],"has":[4],"demonstrated":[5],"strong":[6],"generalization":[7],"across":[8,128],"a":[9,63,95,103],"wide":[10],"range":[11],"of":[12,32,136,156],"visual":[13],"tasks":[14],"by":[15],"leveraging":[16],"large-scale":[17],"English\u2013image":[18],"pairs.":[19],"However,":[20],"its":[21],"extension":[22],"to":[23,29],"low-resource":[24],"languages":[25,122,145],"remains":[26],"limited":[27,124],"due":[28],"the":[30,54,84,134,154],"scarcity":[31],"high-quality":[33],"multilingual":[34,38,69,89,118,130],"image\u2013text":[35,76],"data.":[36],"Existing":[37],"vision\u2013language":[39,70],"models":[40,148],"exhibit":[41],"consistently":[42],"low":[43],"retrieval":[44,131],"performance":[45],"in":[46,142],"underrepresented":[47,144],"languages\u2014including":[48],"Czech,":[49],"Finnish,":[50],"Croatian,":[51],"Hungarian,":[52],"Romanian\u2014on":[53],"Crossmodal-3600":[55],"(XM3600)":[56],"benchmark.":[57],"To":[58],"address":[59],"this,":[60],"we":[61],"propose":[62],"lightweight":[64],"and":[65,81,88],"data-efficient":[66],"framework":[67],"for":[68,121,162],"alignment.":[71],"Our":[72],"approach":[73],"requires":[74],"no":[75],"pairs":[77,80],"or":[78],"text-text":[79],"freezes":[82],"both":[83],"pretrained":[85],"image":[86],"encoder":[87,91],"text":[90],"during":[92],"training.":[93],"Only":[94],"compact":[96],"1.7M-parameter":[97],"projection":[98],"module":[99],"is":[100],"trained,":[101],"using":[102],"contrastive":[104],"loss":[105],"over":[106],"English":[107],"representations":[108],"as":[109],"semantic":[110],"anchors.":[111],"This":[112],"minimal":[113],"training":[114],"setup":[115],"enables":[116],"robust":[117],"alignment":[119,160],"even":[120],"with":[123],"supervision.":[125],"Extensive":[126],"evaluation":[127],"multiple":[129],"benchmarks":[132],"confirms":[133],"effectiveness":[135,155],"our":[137,157],"method,":[138],"showing":[139],"significant":[140],"gains":[141],"five":[143],"where":[146],"existing":[147],"typically":[149],"underperform.":[150],"These":[151],"findings":[152],"highlight":[153],"pivot-based,":[158],"parameter-efficient":[159],"strategy":[161],"inclusive":[163],"multimodal":[164],"learning.":[165]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-18T00:00:00"}