{"id":"https://openalex.org/W4409129259","doi":"https://doi.org/10.1109/tmm.2025.3557678","title":"Cross-Lingual Adaptation for Vision-Language Model via Multimodal Semantic Distillation","display_name":"Cross-Lingual Adaptation for Vision-Language Model via Multimodal Semantic Distillation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409129259","doi":"https://doi.org/10.1109/tmm.2025.3557678"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3557678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557678","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yu Weng","orcid":"https://orcid.org/0000-0002-0787-550X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Weng","raw_affiliation_strings":["Department of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0787-550X","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102783209","display_name":"Wenbin He","orcid":"https://orcid.org/0009-0006-5643-3309"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin He","raw_affiliation_strings":["Department of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5643-3309","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044053594","display_name":"Jun Dong","orcid":"https://orcid.org/0009-0009-0629-3805"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Dong","raw_affiliation_strings":["Department of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0629-3805","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044240037","display_name":"Chaomurilige Chaomurilige","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaomurilige","raw_affiliation_strings":["Department of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2736-3878","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362313","display_name":"Xuan Liu","orcid":"https://orcid.org/0000-0002-5064-6526"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Liu","raw_affiliation_strings":["Department of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5064-6526","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0002-8522-565X"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["Department of Information Engineering, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8522-565X","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145897649"],"apc_list":null,"apc_paid":null,"fwci":1.059,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7393108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"27","issue":null,"first_page":"3184","last_page":"3196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.979200005531311,"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":0.979200005531311,"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":0.8819789886474609},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5901939272880554},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5795059204101562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5675082802772522},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4747783839702606},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34181761741638184}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8819789886474609},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5901939272880554},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5795059204101562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5675082802772522},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4747783839702606},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34181761741638184},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3557678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557678","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2128728535","https://openalex.org/W2185175083","https://openalex.org/W2560730294","https://openalex.org/W2593341061","https://openalex.org/W2896457183","https://openalex.org/W2951977278","https://openalex.org/W2963518342","https://openalex.org/W2963530300","https://openalex.org/W2970231061","https://openalex.org/W3034368386","https://openalex.org/W3035390927","https://openalex.org/W3100806282","https://openalex.org/W3101498587","https://openalex.org/W3174010726","https://openalex.org/W3175301726","https://openalex.org/W3177654849","https://openalex.org/W3200050180","https://openalex.org/W3202415077","https://openalex.org/W3208314443","https://openalex.org/W4289830194","https://openalex.org/W4312877428","https://openalex.org/W4312898116","https://openalex.org/W4382202846","https://openalex.org/W4382999123","https://openalex.org/W4385245566","https://openalex.org/W4385569837","https://openalex.org/W4385570714","https://openalex.org/W4385571124","https://openalex.org/W4385574335","https://openalex.org/W4385815642","https://openalex.org/W4386071687","https://openalex.org/W4386566532","https://openalex.org/W4389524513","https://openalex.org/W4389665280","https://openalex.org/W4392172801","https://openalex.org/W4401109855","https://openalex.org/W4401750504","https://openalex.org/W4402669950","https://openalex.org/W4402671493","https://openalex.org/W4402727669","https://openalex.org/W4404356490","https://openalex.org/W4406552230","https://openalex.org/W4407230380","https://openalex.org/W6638523607","https://openalex.org/W6732520560","https://openalex.org/W6752136759","https://openalex.org/W6757817989","https://openalex.org/W6767021515","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6767737316","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6809616361","https://openalex.org/W6811013733","https://openalex.org/W6839015040","https://openalex.org/W6842585177","https://openalex.org/W6849177959","https://openalex.org/W6850503672","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6856606850","https://openalex.org/W6858268588","https://openalex.org/W6861475616","https://openalex.org/W6862303416","https://openalex.org/W6862315596","https://openalex.org/W6867984073","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2997567050","https://openalex.org/W2775554247","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"Multimodal":[1,68,123],"Models":[2],"(LMMs)":[3],"excel":[4],"in":[5,12,56,191],"English":[6,116,134],"multimedia":[7],"tasks":[8],"but":[9],"face":[10],"challenges":[11],"adapting":[13],"to":[14,18,78,112,132,147,163],"other":[15],"languages":[16,80,149,165],"due":[17],"linguistic":[19],"diversity,":[20],"limited":[21],"non-English":[22],"multimodal":[23,34,93,139,156],"data,":[24],"and":[25,46,137,187],"high":[26],"training":[27],"costs.":[28],"Existing":[29],"approaches":[30],"rely":[31],"on":[32,172],"machine-translated":[33],"corpora":[35],"or":[36],"multilingual":[37,109,185],"large":[38],"language":[39],"models,":[40],"yet":[41],"they":[42],"demand":[43],"substantial":[44],"resources":[45],"achieve":[47],"only":[48],"modest":[49],"zero-shot":[50,181],"cross-lingual":[51,119,192],"transfer":[52],"performance,":[53],"as":[54],"shown":[55],"the":[57,130,152,173],"IGLUE":[58,174],"benchmark.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"propose":[64],"SMSA,":[65],"a":[66,82,103,122,167],"Syntax-aware":[67,104],"Semantic":[69,124],"Adaptation":[70],"approach,":[71],"which":[72,107,128],"efficiently":[73],"extends":[74],"vision-language":[75,193],"models":[76,97],"(VLMs)":[77],"multiple":[79],"via":[81],"lightweight":[83],"adaptation":[84,146],"module.":[85],"Instead":[86],"of":[87],"learning":[88],"from":[89,95],"scratch,":[90],"SMSA":[91,178],"transfers":[92],"knowledge":[94],"English-trained":[96],"using":[98,166],"two":[99],"key":[100],"components:":[101],"(1)":[102],"Adapter":[105],"(SAA),":[106],"restructures":[108],"text":[110],"representations":[111],"align":[113],"better":[114],"with":[115],"syntax,":[117],"reducing":[118],"misalignment;":[120],"(2)":[121],"Distillation":[125],"(MSD)":[126],"method,":[127],"enables":[129],"model":[131],"mimic":[133],"sequence":[135],"processing":[136],"retain":[138],"associations":[140],"across":[141],"languages.":[142],"This":[143],"allows":[144],"efficient":[145],"new":[148],"while":[150],"preserving":[151],"original":[153],"model's":[154],"strong":[155,180],"capabilities.":[157],"We":[158],"extend":[159],"an":[160],"MoE-based":[161],"VLM":[162],"8":[164],"small":[168],"translation":[169],"dataset.":[170],"Evaluations":[171],"benchmark":[175],"show":[176],"that":[177],"achieves":[179],"transfer,":[182],"outperforming":[183],"some":[184],"LMMs":[186],"demonstrating":[188],"its":[189],"effectiveness":[190],"adaptation.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}