{"id":"https://openalex.org/W2981243646","doi":"https://doi.org/10.1145/3352631.3352641","title":"Recognition of Japanese historical text lines by an attention-based encoder-decoder and text line generation","display_name":"Recognition of Japanese historical text lines by an attention-based encoder-decoder and text line generation","publication_year":2019,"publication_date":"2019-09-20","ids":{"openalex":"https://openalex.org/W2981243646","doi":"https://doi.org/10.1145/3352631.3352641","mag":"2981243646"},"language":"en","primary_location":{"id":"doi:10.1145/3352631.3352641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3352631.3352641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Historical Document Imaging and Processing","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/A5058292518","display_name":"Anh Duc Le","orcid":"https://orcid.org/0000-0002-9359-9686"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Anh Duc Le","raw_affiliation_strings":["The Center for Open Data in the Humanities, Japan"],"affiliations":[{"raw_affiliation_string":"The Center for Open Data in the Humanities, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078855310","display_name":"Daichi Mochihashi","orcid":"https://orcid.org/0000-0003-0344-5382"},"institutions":[{"id":"https://openalex.org/I4210134673","display_name":"The Institute of Statistical Mathematics","ror":"https://ror.org/03jcejr58","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210134673","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Mochihashi","raw_affiliation_strings":["The Institute of Statistical Mathematics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The Institute of Statistical Mathematics, Tokyo, Japan","institution_ids":["https://openalex.org/I4210134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032607510","display_name":"Katsuya Masuda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuya Masuda","raw_affiliation_strings":["Center for Research and Development of Higher Education, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Research and Development of Higher Education, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018243718","display_name":"Hideki Mima","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Mima","raw_affiliation_strings":["Center for Research and Development of Higher Education, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Research and Development of Higher Education, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018335549","display_name":"Nam Tuan Ly","orcid":"https://orcid.org/0000-0002-0856-3196"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nam Tuan Ly","raw_affiliation_strings":["Tokyo University of Agriculture and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology, Japan","institution_ids":["https://openalex.org/I92614990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058292518"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54696186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"41"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9801999926567078,"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":0.8563965559005737},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7615292072296143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6027381420135498},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5847251415252686},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5824650526046753},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5176123380661011},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.5067115426063538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5043612718582153},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46624866127967834},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4291384816169739},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3945241868495941},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39402449131011963},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33618593215942383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8563965559005737},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7615292072296143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6027381420135498},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5847251415252686},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5824650526046753},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5176123380661011},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.5067115426063538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5043612718582153},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46624866127967834},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4291384816169739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3945241868495941},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39402449131011963},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33618593215942383},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3352631.3352641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3352631.3352641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W161608171","https://openalex.org/W2194187530","https://openalex.org/W2782356320","https://openalex.org/W4229847583","https://openalex.org/W4242177601","https://openalex.org/W4249708626"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Inspired":[0],"by":[1,145],"the":[2,65,108,112,121,127,130,159,164],"recent":[3],"successes":[4],"of":[5,91,111,118,129,141],"attention":[6,56],"based":[7],"encoder-decoder":[8],"(AED)":[9],"approach":[10],"on":[11,120],"image":[12],"captioning,":[13],"machine":[14],"translation,":[15],"we":[16,81],"present":[17,98],"an":[18,22],"AED":[19],"model":[20,57,66,69],"as":[21],"end-to-end":[23],"recognition":[24,32,135,156,170],"system":[25,33,136,157],"for":[26,43,58,85,93],"recognizing":[27],"Japanese":[28],"historical":[29],"documents.":[30],"The":[31,68,116],"has":[34],"two":[35],"main":[36],"modules:":[37],"a":[38,47,89,99],"dense":[39],"convolution":[40],"neural":[41],"network":[42],"extracting":[44],"features,":[45],"and":[46,76,87,123,143,148],"Long":[48],"Shor":[49],"Term":[50],"Memory":[51],"(LSTM)":[52],"decoder":[53],"integrating":[54],"with":[55,147],"generating":[59],"target":[60],"text.":[61],"We":[62,96],"can":[63],"train":[64],"end-to-end.":[67],"requires":[70],"only":[71],"input":[72],"text":[73,104,131,151],"line":[74,132],"images":[75],"corresponding":[77],"output":[78],"characters.":[79],"Therefore,":[80],"don't":[82],"need":[83],"annotations":[84],"characters":[86],"save":[88],"lot":[90],"time":[92],"making":[94],"annotations.":[95],"also":[97],"method":[100],"to":[101,106],"generate":[102],"artificial":[103,124,150],"lines":[105],"solve":[107],"imbalance":[109],"problem":[110],"current":[113],"annotated":[114,122],"database.":[115],"results":[117,166],"experiments":[119],"databases":[125],"demonstrate":[126],"effectiveness":[128],"generation.":[133],"Our":[134],"achieved":[137,163],"Character":[138],"Error":[139],"Rate":[140],"23.76%":[142],"22.52%":[144],"training":[146],"without":[149],"lines,":[152],"respectively.":[153],"Moreover,":[154],"our":[155],"outperforms":[158],"CNN-LSTM":[160],"system,":[161],"which":[162],"state-of-art":[165],"in":[167],"other":[168],"document":[169],"tasks.":[171]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}