{"id":"https://openalex.org/W4388007692","doi":"https://doi.org/10.1145/3607540.3617140","title":"An Empirical Study of Multilingual Scene-Text Visual Question Answering","display_name":"An Empirical Study of Multilingual Scene-Text Visual Question Answering","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4388007692","doi":"https://doi.org/10.1145/3607540.3617140"},"language":"en","primary_location":{"id":"doi:10.1145/3607540.3617140","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3607540.3617140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on User-centric Narrative Summarization of Long Videos","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7553-6916","affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007189982","display_name":"Haohan Zhang","orcid":"https://orcid.org/0009-0008-5219-7278"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohan Zhang","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0008-5219-7278","affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023449927","display_name":"Zeqin Fang","orcid":"https://orcid.org/0009-0004-3121-8050"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeqin Fang","raw_affiliation_strings":["iFLYTEK Corporation, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0004-3121-8050","affiliations":[{"raw_affiliation_string":"iFLYTEK Corporation, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"8"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9932000041007996,"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":0.8367655873298645},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7744179964065552},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6852124929428101},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6703056693077087},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6204769611358643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5808478593826294},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4965360760688782},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4593631625175476},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35792863368988037},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28922152519226074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367655873298645},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7744179964065552},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6852124929428101},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6703056693077087},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6204769611358643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5808478593826294},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4965360760688782},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4593631625175476},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35792863368988037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28922152519226074},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3607540.3617140","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3607540.3617140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on User-centric Narrative Summarization of Long Videos","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2053317383","https://openalex.org/W2090048052","https://openalex.org/W2307512708","https://openalex.org/W2561675875","https://openalex.org/W2613718673","https://openalex.org/W2746097825","https://openalex.org/W2747329762","https://openalex.org/W2988326850","https://openalex.org/W3004268082","https://openalex.org/W3006923065","https://openalex.org/W3034336960","https://openalex.org/W3034943799","https://openalex.org/W3043311956","https://openalex.org/W3094502228","https://openalex.org/W3108319047","https://openalex.org/W3200050180","https://openalex.org/W4285236007","https://openalex.org/W4293518934","https://openalex.org/W6761041305","https://openalex.org/W6778668228","https://openalex.org/W6843740573"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,12,24,38,44,89,111,121,135],"focus":[4],"on":[5,81,101],"multilingual":[6,56,115,124],"modeling":[7],"has":[8],"intensified,":[9],"driven":[10],"by":[11],"necessity":[13],"to":[14,127],"enable":[15],"cross-lingual":[16,63],"Text-based":[17],"Visual":[18],"Question":[19],"Answering":[20],"(TextVQA),":[21],"which":[22],"requires":[23],"understanding":[25],"of":[26,40,46,91,104,114,123,137],"questions":[27],"and":[28,43,67,72,96,144],"answers":[29],"across":[30],"diverse":[31],"languages.":[32],"Existing":[33],"research":[34],"predominantly":[35],"revolves":[36],"around":[37],"fusion":[39],"multimodal":[41],"information":[42],"processing":[45],"OCR":[47,93,142],"data.":[48],"This":[49],"paper":[50],"undertakes":[51],"an":[52],"empirical":[53],"investigation":[54],"into":[55,110],"scene-text":[57],"visual":[58,98,139],"question":[59],"answering,":[60],"addressing":[61],"both":[62],"(English":[64,69],"<->":[65,70,74],"Chinese)":[66,75],"monolingual":[68],"English":[71],"Chinese":[73],"tasks,":[76],"with":[77],"a":[78,102],"primary":[79],"emphasis":[80],"accuracy-based":[82],"metrics.":[83],"Our":[84],"study":[85],"not":[86],"only":[87],"elucidates":[88],"impact":[90],"varying":[92],"feature":[94,99],"extractors":[95,100],"distinct":[97],"selection":[103],"state-of-the-art":[105],"models":[106,126],"but":[107],"also":[108],"delves":[109],"broader":[112],"landscape":[113],"TextVQA.":[116],"The":[117],"experimental":[118],"outcomes":[119],"underscore":[120,134],"capability":[122],"pretrained":[125],"effectively":[128],"handle":[129],"text-based":[130],"questions.":[131],"Moreover,":[132],"they":[133],"importance":[136],"leveraging":[138],"features":[140],"from":[141],"data":[143],"images":[145],"in":[146],"enhancing":[147],"answering":[148],"performance.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}