{"id":"https://openalex.org/W4312835200","doi":"https://doi.org/10.1109/icpr56361.2022.9956695","title":"Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task","display_name":"Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312835200","doi":"https://doi.org/10.1109/icpr56361.2022.9956695"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956695","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5101810188","display_name":"Cong Ma","orcid":"https://orcid.org/0000-0002-9787-6273"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cong Ma","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366779","display_name":"Ya\u2010Ping Zhang","orcid":"https://orcid.org/0000-0002-5401-1114"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaping Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108647194","display_name":"Mei Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Tu","raw_affiliation_strings":["Samsung Research China - Beijing (SRC-B)"],"affiliations":[{"raw_affiliation_string":"Samsung Research China - Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101714742","display_name":"Xu Han","orcid":"https://orcid.org/0009-0004-2070-1741"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Han","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108067274","display_name":"L. J. Wu","orcid":"https://orcid.org/0009-0000-1053-5496"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghui Wu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101961736","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0002-3126-4944"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,P.R. China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,National Laboratory of Pattern Recognition (NLPR),Beijing,P.R. China,100190","Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,National Laboratory of Pattern Recognition (NLPR),Beijing,P.R. China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd, Beijing, P.R. China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101810188"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.8989,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.82781976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1664","last_page":"1670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9979000091552734,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.994700014591217,"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":0.8178275227546692},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7974568605422974},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6658420562744141},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.650869607925415},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6490000486373901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5939653515815735},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5444948673248291},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5268793702125549},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.42249929904937744},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.41814783215522766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.396962970495224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178275227546692},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7974568605422974},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6658420562744141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.650869607925415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6490000486373901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5939653515815735},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5444948673248291},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5268793702125549},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.42249929904937744},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.41814783215522766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.396962970495224},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956695","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W770111601","https://openalex.org/W1522301498","https://openalex.org/W2103642579","https://openalex.org/W2130942839","https://openalex.org/W2168011783","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2552839021","https://openalex.org/W2750938222","https://openalex.org/W2786343958","https://openalex.org/W2959965583","https://openalex.org/W2982910584","https://openalex.org/W3004846386","https://openalex.org/W3035169087","https://openalex.org/W3103062353","https://openalex.org/W3106271744","https://openalex.org/W3114894085","https://openalex.org/W3161816735","https://openalex.org/W3174554374","https://openalex.org/W3178360617","https://openalex.org/W3198612422","https://openalex.org/W4241881105","https://openalex.org/W4385245566","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6739901393","https://openalex.org/W6748139205","https://openalex.org/W6795115536"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W4288069866","https://openalex.org/W4389232935","https://openalex.org/W2936127876","https://openalex.org/W4387421677","https://openalex.org/W4213477128","https://openalex.org/W2957407072","https://openalex.org/W4312511225","https://openalex.org/W4281776416"],"abstract_inverted_index":{"End-to-end":[0],"text":[1,34,61,64,73,97,118],"image":[2,35,65],"translation":[3,62,74,119,127],"(TIT),":[4],"which":[5,67],"aims":[6],"at":[7],"translating":[8],"the":[9,16,30,69,112],"source":[10],"language":[11],"embedded":[12],"in":[13,23],"images":[14],"to":[15,43,90],"target":[17],"language,":[18],"has":[19],"attracted":[20],"intensive":[21],"attention":[22],"recent":[24],"research.":[25],"However,":[26],"data":[27],"sparsity":[28],"limits":[29],"performance":[31],"of":[32,94],"end-to-end":[33,70,109],"translation.":[36],"Multi-task":[37],"learning":[38,115],"is":[39,88],"a":[40,59],"nontrivial":[41],"way":[42],"alleviate":[44],"this":[45,55],"problem":[46],"via":[47],"exploring":[48],"knowledge":[49],"from":[50],"complementary":[51],"related":[52],"tasks.":[53],"In":[54],"paper,":[56],"we":[57],"propose":[58],"novel":[60],"enhanced":[63],"translation,":[66],"trains":[68],"model":[71,81,87],"with":[72,116],"as":[75],"an":[76],"auxiliary":[77,130],"task.":[78],"By":[79],"sharing":[80],"parameters":[82],"and":[83,111,120,128],"multi-task":[84,114],"training,":[85],"our":[86,104],"able":[89],"take":[91],"full":[92],"advantage":[93],"easily-available":[95],"large-scale":[96],"parallel":[98],"corpus.":[99],"Extensive":[100],"experimental":[101],"results":[102],"show":[103],"proposed":[105],"method":[106],"outperforms":[107],"existing":[108],"methods,":[110],"joint":[113],"both":[117],"recognition":[121,129],"tasks":[122,131],"achieves":[123],"better":[124],"results,":[125],"proving":[126],"are":[132],"complementary.":[133],"<sup":[134],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}