{"id":"https://openalex.org/W3215495195","doi":"https://doi.org/10.1145/3469877.3490571","title":"Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages","display_name":"Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W3215495195","doi":"https://doi.org/10.1145/3469877.3490571","mag":"3215495195"},"language":"en","primary_location":{"id":"doi:10.1145/3469877.3490571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.12276","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013009514","display_name":"Shota Orihashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Orihashi","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020625328","display_name":"Yoshihiro Yamazaki","orcid":"https://orcid.org/0000-0002-9375-5239"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiro Yamazaki","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mana Ihori","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080550833","display_name":"Akihiko Takashima","orcid":"https://orcid.org/0000-0001-7361-4562"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiko Takashima","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009756622","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0001-7442-4912"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, JP","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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/T10601","display_name":"Handwritten Text Recognition Techniques","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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":0.9926999807357788,"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":0.8590936660766602},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7723373770713806},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5813084244728088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306678414344788},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5186092853546143},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4740678668022156},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4634656012058258},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4530879259109497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41697216033935547},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4123893976211548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590936660766602},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7723373770713806},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5813084244728088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306678414344788},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5186092853546143},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4740678668022156},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4634656012058258},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4530879259109497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41697216033935547},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4123893976211548},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3469877.3490571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.12276","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.12276","pdf_url":"https://arxiv.org/pdf/2111.12276","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.12276","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.12276","pdf_url":"https://arxiv.org/pdf/2111.12276","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1686810756","https://openalex.org/W1981283549","https://openalex.org/W2127141656","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2560835477","https://openalex.org/W2565591417","https://openalex.org/W2593572697","https://openalex.org/W2619328388","https://openalex.org/W2727586675","https://openalex.org/W2752225195","https://openalex.org/W2809273748","https://openalex.org/W2873558679","https://openalex.org/W2888894220","https://openalex.org/W2914120296","https://openalex.org/W2928555987","https://openalex.org/W2962835968","https://openalex.org/W2963403868","https://openalex.org/W2963431393","https://openalex.org/W2963517393","https://openalex.org/W2971325593","https://openalex.org/W2978036638","https://openalex.org/W2988326850","https://openalex.org/W2992430205","https://openalex.org/W3003642782","https://openalex.org/W3004846386","https://openalex.org/W3013262970","https://openalex.org/W3014074635","https://openalex.org/W3035374068","https://openalex.org/W3035449864","https://openalex.org/W3082397598","https://openalex.org/W3090232332","https://openalex.org/W3101411491","https://openalex.org/W3107826490","https://openalex.org/W3160233719","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W2916997151","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3094871513","https://openalex.org/W3100913109","https://openalex.org/W3198458223"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,31,40,90,123,175],"novel":[4],"training":[5],"method":[6,67,117,147],"for":[7,45,58,141],"end-to-end":[8,34],"scene":[9,13,142,171],"text":[10,14,143,172],"recognition.":[11,144],"End-to-end":[12],"recognition":[15,18,173],"offers":[16],"high":[17],"accuracy,":[19],"especially":[20,57],"when":[21],"using":[22,122,153,174],"the":[23,46,80,94,102,109,115,119,128,133,150,154,160,165,181,184],"encoder-decoder":[24,82],"model":[25,91],"based":[26],"on":[27,169],"Transformer.":[28],"To":[29,61,112],"train":[30,79],"highly":[32],"accurate":[33],"model,":[35],"we":[36],"need":[37],"to":[38,53,78,88,137,158,164],"prepare":[39],"large":[41,70],"image-to-text":[42],"paired":[43],"dataset":[44,125,131,136,157,179],"target":[47],"language.":[48,111,167],"However,":[49],"it":[50],"is":[51,87],"difficult":[52],"collect":[54],"this":[55,63,113],"data,":[56],"resource-poor":[59,81,110,129,155,166],"languages.":[60],"overcome":[62],"difficulty,":[64],"our":[65],"proposed":[66,116,146,185],"utilizes":[68],"well-prepared":[69],"datasets":[71],"in":[72,92,105],"resource-rich":[73,134],"languages":[74,100],"such":[75],"as":[76],"English,":[77],"model.":[83],"Our":[84],"key":[85],"idea":[86],"build":[89],"which":[93],"encoder":[95,120],"reflects":[96],"knowledge":[97,106,140],"of":[98,107,183],"multiple":[99],"while":[101],"decoder":[103,151,161],"specializes":[104],"just":[108],"end,":[114],"pre-trains":[118,149],"by":[121,152],"multilingual":[124],"that":[126],"combines":[127],"language\u2019s":[130,135,156],"and":[132],"learn":[138],"language-invariant":[139],"The":[145],"also":[148],"make":[159],"better":[162],"suited":[163],"Experiments":[168],"Japanese":[170],"small,":[176],"publicly":[177],"available":[178],"demonstrate":[180],"effectiveness":[182],"method.":[186]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}