{"id":"https://openalex.org/W4400078320","doi":"https://doi.org/10.1109/tcss.2024.3402270","title":"Zero-Shot Cross-Lingual Knowledge Transfer in VQA via Multimodal Distillation","display_name":"Zero-Shot Cross-Lingual Knowledge Transfer in VQA via Multimodal Distillation","publication_year":2024,"publication_date":"2024-06-27","ids":{"openalex":"https://openalex.org/W4400078320","doi":"https://doi.org/10.1109/tcss.2024.3402270"},"language":"en","primary_location":{"id":"doi:10.1109/tcss.2024.3402270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2024.3402270","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"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 Computational Social Systems","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":"https://openalex.org/A5024296105","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 Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0787-550X","affiliations":[{"raw_affiliation_string":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, 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 Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0629-3805","affiliations":[{"raw_affiliation_string":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, 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 Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5643-3309","affiliations":[{"raw_affiliation_string":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, 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 Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2736-3878","affiliations":[{"raw_affiliation_string":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, 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 Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5064-6526","affiliations":[{"raw_affiliation_string":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423703","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 Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8522-565X","affiliations":[{"raw_affiliation_string":"Department of Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087225784","display_name":"Honghao Gao","orcid":"https://orcid.org/0000-0001-6861-9684"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghao Gao","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6861-9684","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2228,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89196208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"12","issue":"4","first_page":"1869","last_page":"1879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9879999756813049,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9879999756813049,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9747999906539917,"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/zero","display_name":"Zero (linguistics)","score":0.6280376315116882},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5558178424835205},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5270065665245056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4440472424030304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44208061695098877},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.24194493889808655},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.23257797956466675},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.21346458792686462},{"id":"https://openalex.org/keywords/metallurgy","display_name":"Metallurgy","score":0.0800844132900238}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6280376315116882},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5558178424835205},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5270065665245056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4440472424030304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44208061695098877},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.24194493889808655},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.23257797956466675},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.21346458792686462},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0800844132900238},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcss.2024.3402270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2024.3402270","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"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 Computational Social Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1625834043","display_name":null,"funder_award_id":"2020YFB1406702-3","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2079531865","display_name":null,"funder_award_id":"62006257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3141632398","display_name":null,"funder_award_id":"61772575","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G885349591","display_name":null,"funder_award_id":"Z231100001723002","funder_id":"https://openalex.org/F4320325902","funder_display_name":"Beijing Municipal Science and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325902","display_name":"Beijing Municipal Science and Technology Commission","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2963150162","https://openalex.org/W2963518342","https://openalex.org/W2981694290","https://openalex.org/W3034724424","https://openalex.org/W3035390927","https://openalex.org/W3090449556","https://openalex.org/W3094502228","https://openalex.org/W3099793224","https://openalex.org/W3100806282","https://openalex.org/W3101498587","https://openalex.org/W3114239154","https://openalex.org/W3159619744","https://openalex.org/W3173220247","https://openalex.org/W3174010726","https://openalex.org/W3175301726","https://openalex.org/W3177654849","https://openalex.org/W3200050180","https://openalex.org/W3202415077","https://openalex.org/W4230434605","https://openalex.org/W4381598461","https://openalex.org/W4385569837","https://openalex.org/W4385574335","https://openalex.org/W4385815642","https://openalex.org/W4386566532","https://openalex.org/W4388192945","https://openalex.org/W6638523607","https://openalex.org/W6639432524","https://openalex.org/W6676497082","https://openalex.org/W6686883664","https://openalex.org/W6739901393","https://openalex.org/W6751633227","https://openalex.org/W6751751081","https://openalex.org/W6754469826","https://openalex.org/W6759579507","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6767279747","https://openalex.org/W6768851824","https://openalex.org/W6773829392","https://openalex.org/W6788135285","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6811013733","https://openalex.org/W6842585177","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528"],"abstract_inverted_index":{"As":[0],"multilingual":[1,46,53,160],"artificial":[2],"intelligence":[3],"systems":[4],"proliferate,":[5],"achieving":[6],"robust":[7],"cross-lingual":[8,72,95],"understanding":[9,122],"remains":[10],"an":[11],"open":[12],"challenge.":[13],"Recent":[14],"works":[15],"have":[16],"made":[17],"progress":[18],"on":[19,27,49,132,199],"visual":[20],"question":[21],"answering":[22],"(VQA)":[23],"models":[24,40,83,125,162],"by":[25,126],"pretraining":[26],"large":[28],"English":[29,64,81,124],"image-text":[30,108],"datasets.":[31],"However,":[32],"there":[33],"is":[34],"a":[35,93,113],"language":[36],"gap":[37],"as":[38],"most":[39],"are":[41],"English-centric.":[42],"Existing":[43],"attempts":[44],"at":[45],"VQA":[47,82,161],"rely":[48],"machine":[50],"translation":[51],"or":[52],"model":[54],"pretraining,":[55],"but":[56],"cannot":[57],"effectively":[58,140],"transfer":[59,75,120,167],"rich":[60],"cross-modal":[61],"knowledge":[62,74,88,115,166],"from":[63,123,163,181],"models.":[65],"In":[66],"this":[67],"work,":[68],"we":[69,91],"propose":[70],"the":[71,133,153,176,188,196,200],"multimodal":[73,114],"(CMKT)":[76],"framework":[77],"to":[78,84,100,119,158,172],"efficiently":[79],"extend":[80],"non-English":[85,148,170],"languages":[86,105,171],"via":[87],"distillation.":[89],"Specifically,":[90],"introduce":[92],"code-mixed":[94],"mask":[96],"modeling":[97],"(CCM)":[98],"method":[99,118,151,190],"establish":[101],"representations":[102],"for":[103],"new":[104],"using":[106],"small":[107],"data.":[109],"We":[110],"also":[111,185],"design":[112],"distillation":[116],"(MMKD)":[117],"modal":[121],"imitating":[127],"their":[128],"sequence":[129],"processing.":[130],"Experiments":[131],"xGQA":[134,201],"benchmark":[135],"demonstrate":[136],"that":[137,187],"CMKT":[138],"can":[139],"improve":[141],"zero-shot":[142,197],"learning":[143,146],"and":[144,155,174],"few-shot":[145],"in":[147,195],"languages.":[149],"Our":[150],"reduces":[152],"data":[154],"computation":[156],"needed":[157],"train":[159],"scratch.":[164],"The":[165,183],"paradigm":[168],"enables":[169],"inherit":[173],"generalize":[175],"intricate":[177],"visual-semantic":[178],"relationships":[179],"learned":[180],"English.":[182],"results":[184],"show":[186],"proposed":[189],"outperforms":[191],"previous":[192],"state-of-the-art":[193],"methods":[194],"setting":[198],"dataset.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}