{"id":"https://openalex.org/W4385815642","doi":"https://doi.org/10.1109/cvprw59228.2023.00258","title":"Adapting Grounded Visual Question Answering Models to Low Resource Languages","display_name":"Adapting Grounded Visual Question Answering Models to Low Resource Languages","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4385815642","doi":"https://doi.org/10.1109/cvprw59228.2023.00258"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw59228.2023.00258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw59228.2023.00258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-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/A5036877034","display_name":"Ying Wang","orcid":"https://orcid.org/0000-0002-1456-3192"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ying Wang","raw_affiliation_strings":["New York University,Center for Data Science","Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024983536","display_name":"Jonas Pfeiffer","orcid":"https://orcid.org/0000-0002-8634-6170"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonas Pfeiffer","raw_affiliation_strings":["New York University,Center for Data Science","Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029981206","display_name":"Nicolas Carion","orcid":"https://orcid.org/0000-0002-2308-9680"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Carion","raw_affiliation_strings":["New York University,Center for Data Science","Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yann LeCun","raw_affiliation_strings":["New York University,Center for Data Science","Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077791956","display_name":"Aishwarya Kamath","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aishwarya Kamath","raw_affiliation_strings":["New York University,Center for Data Science","Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036877034"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.9825,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77820192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2596","last_page":"2605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9909999966621399,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9817000031471252,"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":0.8675490021705627},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5814346671104431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5493119955062866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5340954661369324},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5307868719100952},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4896309971809387},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4533313512802124},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.42072904109954834},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.413576602935791},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.160002201795578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8675490021705627},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5814346671104431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493119955062866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5340954661369324},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5307868719100952},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4896309971809387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4533313512802124},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.42072904109954834},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.413576602935791},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.160002201795578},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvprw59228.2023.00258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw59228.2023.00258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2741631785","https://openalex.org/W2842511635","https://openalex.org/W2886641317","https://openalex.org/W2903343986","https://openalex.org/W2914120296","https://openalex.org/W2948902769","https://openalex.org/W2963331233","https://openalex.org/W2963518342","https://openalex.org/W2963527096","https://openalex.org/W2963778889","https://openalex.org/W2963909453","https://openalex.org/W2965373594","https://openalex.org/W2970231061","https://openalex.org/W3034724424","https://openalex.org/W3091588028","https://openalex.org/W3093871477","https://openalex.org/W3099793224","https://openalex.org/W3101498587","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3174010726","https://openalex.org/W3177654849","https://openalex.org/W3200050180","https://openalex.org/W3204138855","https://openalex.org/W4230579319","https://openalex.org/W4283009931","https://openalex.org/W4297808394","https://openalex.org/W4312846625","https://openalex.org/W4312956471","https://openalex.org/W4385569837","https://openalex.org/W4385574335","https://openalex.org/W6751487307","https://openalex.org/W6759455113","https://openalex.org/W6762718338","https://openalex.org/W6766673545","https://openalex.org/W6784447870","https://openalex.org/W6791353385","https://openalex.org/W6809616361","https://openalex.org/W6839220867"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"While":[0],"huge":[1],"progress":[2],"has":[3,47],"been":[4,21,48],"made":[5],"on":[6,100,137,204,213,223,231],"a":[7,77,94,139,171,176],"variety":[8],"of":[9,31,118,134,199],"vision":[10],"and":[11,34,183,187,201,218,226],"language":[12,26],"tasks":[13],"in":[14,37,154,215],"recent":[15],"years,":[16],"most":[17,117],"major":[18],"advances":[19],"have":[20],"restricted":[22],"to":[23,28,43,49,65,108,128,132,195],"the":[24,29,101,119,135,155,197],"English":[25,70],"due":[27],"scarcity":[30],"relevant":[32],"training":[33,170],"evaluation":[35],"datasets":[36,53,57],"other":[38,232],"languages.":[39,233],"A":[40],"popular":[41],"approach":[42,61],"address":[44],"this":[45],"gap,":[46],"utilize":[50],"machine-translated":[51,112],"multi-modal":[52,71,200,206],"or":[54],"multi-lingual":[55,95,156,202,205],"text-only":[56],"for":[58,80,151,185],"pre-training.":[59],"This":[60],"not":[62,76,87],"only":[63],"fails":[64],"exploit":[66],"existing":[67],"pre-trained":[68,120,126],"state-of-the-art":[69,102],"models,":[72],"but":[73],"also":[74,115,146,191],"is":[75,86,145],"viable":[78],"solution":[79],"low-resource":[81],"languages":[82,110],"where":[83],"translation":[84],"quality":[85],"as":[88,163,165,169],"reliable.":[89],"Therefore,":[90],"we":[91],"propose":[92],"xMDETR,":[93],"grounded":[96],"vision-language":[97],"model":[98,103],"based":[99],"MDETR,":[104],"by":[105],"adapting":[106],"it":[107],"new":[109,172],"without":[111],"data,":[113,207],"while":[114,228],"keeping":[116],"weights":[121],"frozen.":[122],"xMDETR":[123,212],"leverages":[124],"mono-lingual":[125],"MDETR":[127],"achieve":[129],"results":[130,222],"competitive":[131,230],"state":[133],"art":[136],"xGQA,":[138],"standard":[140],"multilingual":[141],"VQA":[142],"benchmark.":[143],"It":[144],"interpretable,":[147],"providing":[148],"bounding":[149],"boxes":[150],"key":[152],"phrases":[153],"questions.":[157],"Our":[158],"method":[159],"utilizes":[160],"several":[161],"architectural":[162],"well":[164],"data-driven":[166],"techniques":[167],"such":[168],"embedding":[173],"space":[174],"with":[175],"Masked":[177],"Language":[178],"Modeling":[179],"(MLM)":[180],"objective,":[181],"code-switching,":[182],"adapters":[184],"efficient":[186],"modular":[188],"training.":[189],"We":[190,210],"explore":[192],"contrastive":[193],"losses":[194],"enforce":[196],"bridging":[198],"representations":[203],"when":[208],"available.":[209],"evaluate":[211],"xGQA":[214],"both":[216],"zero-shot":[217],"few-shot":[219],"settings,":[220],"improving":[221],"Portuguese,":[224],"Indonesian":[225],"Bengali,":[227],"remaining":[229]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}