{"id":"https://openalex.org/W3200050180","doi":"https://doi.org/10.18653/v1/2022.findings-acl.196","title":"xGQA: Cross-Lingual Visual Question Answering","display_name":"xGQA: Cross-Lingual Visual Question Answering","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3200050180","doi":"https://doi.org/10.18653/v1/2022.findings-acl.196","mag":"3200050180"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.findings-acl.196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.196","pdf_url":"https://aclanthology.org/2022.findings-acl.196.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.findings-acl.196.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024983536","display_name":"Jonas Pfeiffer","orcid":"https://orcid.org/0000-0002-8634-6170"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jonas Pfeiffer","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018004671","display_name":"Gregor Geigle","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gregor Geigle","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","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":["Center for Data Science, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007546503","display_name":"Jan-Martin O. Steitz","orcid":"https://orcid.org/0000-0002-3549-312X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan-Martin Steitz","raw_affiliation_strings":["Visual Inference Lab, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Inference Lab, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056098625","display_name":"Stefan Roth","orcid":"https://orcid.org/0000-0001-9002-9832"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Roth","raw_affiliation_strings":["Visual Inference Lab, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Inference Lab, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094319437","display_name":"Ivan Vuli\u0107","orcid":"https://orcid.org/0000-0002-3663-7252"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ivan Vuli\u0107","raw_affiliation_strings":["Language Technology Lab, University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab, Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5024983536"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":2.4202,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.9241908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2497","last_page":"2511"},"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":0.9987999796867371,"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":0.9833999872207642,"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/computer-science","display_name":"Computer science","score":0.8583681583404541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5793108940124512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5484604835510254},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.518453061580658},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4882188141345978},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.45464572310447693},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4328978657722473},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.4175128936767578},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4146648049354553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8583681583404541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5793108940124512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5484604835510254},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.518453061580658},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4882188141345978},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.45464572310447693},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4328978657722473},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.4175128936767578},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4146648049354553},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2022.findings-acl.196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.196","pdf_url":"https://aclanthology.org/2022.findings-acl.196.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:132653","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/132653/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.findings-acl.196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.196","pdf_url":"https://aclanthology.org/2022.findings-acl.196.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2075345162","display_name":"Enabling Multilingual Conversational AI","funder_award_id":"957356","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G380019826","display_name":"Robust, Explainable Deep Networks in Computer Vision","funder_award_id":"866008","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3200050180.pdf","grobid_xml":"https://content.openalex.org/works/W3200050180.grobid-xml"},"referenced_works_count":78,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2109586012","https://openalex.org/W2277195237","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2849425149","https://openalex.org/W2886194718","https://openalex.org/W2886641317","https://openalex.org/W2911300548","https://openalex.org/W2952638691","https://openalex.org/W2963211188","https://openalex.org/W2963341956","https://openalex.org/W2963518342","https://openalex.org/W2963530300","https://openalex.org/W2963909453","https://openalex.org/W2964303773","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2970854433","https://openalex.org/W2970925270","https://openalex.org/W2995230342","https://openalex.org/W2998356391","https://openalex.org/W3026990524","https://openalex.org/W3033518368","https://openalex.org/W3034469191","https://openalex.org/W3035390927","https://openalex.org/W3035579820","https://openalex.org/W3035688398","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3096966601","https://openalex.org/W3099219382","https://openalex.org/W3099793224","https://openalex.org/W3100198908","https://openalex.org/W3101498587","https://openalex.org/W3105421296","https://openalex.org/W3110570034","https://openalex.org/W3112302586","https://openalex.org/W3126337491","https://openalex.org/W3135000221","https://openalex.org/W3135099046","https://openalex.org/W3139017368","https://openalex.org/W3139243190","https://openalex.org/W3156892778","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3171668871","https://openalex.org/W3171927989","https://openalex.org/W3172698324","https://openalex.org/W3173220247","https://openalex.org/W3173954987","https://openalex.org/W3174010726","https://openalex.org/W3174765737","https://openalex.org/W3197394194","https://openalex.org/W3201264086","https://openalex.org/W3202415077","https://openalex.org/W3214578205","https://openalex.org/W3215139360","https://openalex.org/W3215626407","https://openalex.org/W3217059257","https://openalex.org/W3217799312","https://openalex.org/W4205712089","https://openalex.org/W4206178588","https://openalex.org/W4221151248","https://openalex.org/W4230579319","https://openalex.org/W4287245501","https://openalex.org/W4287597359","https://openalex.org/W4310486995","https://openalex.org/W4312910992","https://openalex.org/W4385245566","https://openalex.org/W4385573483","https://openalex.org/W4386566532"],"related_works":["https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W207304934","https://openalex.org/W3204607391","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W4224103871","https://openalex.org/W2970044932","https://openalex.org/W4377703168","https://openalex.org/W4287761227"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,73,111,131],"multimodal":[3,22,86,105,152,157],"vision":[4,165],"and":[5,35,57,69,166],"language":[6,168],"modeling":[7,26],"have":[8],"predominantly":[9],"focused":[10],"on":[11],"the":[12,18,44,51,116,121,135],"English":[13,53],"language,":[14],"mostly":[15],"due":[16],"to":[17,24,60,67,84,89,95],"lack":[19],"of":[20,126,137,151],"multilingual":[21,40,104,156,167],"datasets":[23],"steer":[25],"efforts.":[27],"In":[28],"this":[29,33,142],"work,":[30],"we":[31],"address":[32],"gap":[34],"provide":[36],"xGQA,":[37],"a":[38,123],"new":[39,81],"evaluation":[41],"benchmark":[42],"for":[43,141,160,164],"visual":[45,75],"question":[46,76],"answering":[47],"task.":[48,143],"We":[49,78],"extend":[50],"established":[52],"GQA":[54],"dataset":[55],"(Hudson":[56],"Manning,":[58],"2019)":[59],"7":[61],"typologically":[62],"diverse":[63],"languages,":[64],"enabling":[65],"us":[66],"detect":[68],"explore":[70],"crucial":[71],"challenges":[72],"cross-lingual":[74,113,139,149],"answering.":[77],"further":[79],"propose":[80],"adapter-based":[82],"approaches":[83],"adapt":[85],"transformer-based":[87],"models":[88,94,106,153],"become":[90,96],"multilingual,":[91],"and-vice":[92],"versa-multilingual":[93],"multimodal.":[97],"Our":[98,144],"proposed":[99],"methods":[100,163],"outperform":[101],"current":[102],"state-of-the-art":[103],"(e.g.,":[107],"M":[108],"3":[109],"P)":[110],"zeroshot":[112],"settings,":[114],"but":[115],"accuracy":[117,129],"remains":[118],"low":[119],"across":[120],"board;":[122],"performance":[124],"drop":[125],"around":[127],"38":[128],"points":[130],"target":[132],"languages":[133],"showcases":[134],"difficulty":[136],"zero-shot":[138],"transfer":[140,150],"results":[145],"suggest":[146],"that":[147],"simple":[148],"yields":[154],"latent":[155],"misalignment,":[158],"calling":[159],"more":[161],"sophisticated":[162],"modeling.":[169],"1":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":5}],"updated_date":"2026-05-17T08:19:37.847499","created_date":"2025-10-10T00:00:00"}