{"id":"https://openalex.org/W4386590374","doi":"https://doi.org/10.1109/icip49359.2023.10222653","title":"Distilling Knowledge of Bidirectional Language Model for Scene Text Recognition","display_name":"Distilling Knowledge of Bidirectional Language Model for Scene Text Recognition","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386590374","doi":"https://doi.org/10.1109/icip49359.2023.10222653"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222653","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/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,NTT Computer and Data Science Laboratories,Japan","NTT Computer and Data Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer and Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Computer and Data Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037013625","display_name":"Yoshihiro Yamazaki","orcid":"https://orcid.org/0000-0002-6404-0031"},"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,NTT Computer and Data Science Laboratories,Japan","NTT Computer and Data Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer and Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Computer and Data Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008141813","display_name":"Mihiro Uchida","orcid":"https://orcid.org/0009-0002-1350-6038"},"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":"Mihiro Uchida","raw_affiliation_strings":["NTT Corporation,NTT Computer and Data Science Laboratories,Japan","NTT Computer and Data Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer and Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Computer and Data Science Laboratories, NTT Corporation, Japan","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,NTT Computer and Data Science Laboratories,Japan","NTT Computer and Data Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer and Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Computer and Data Science Laboratories, NTT Corporation, Japan","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,NTT Computer and Data Science Laboratories,Japan","NTT Computer and Data Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer and Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Computer and Data Science Laboratories, NTT Corporation, Japan","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2165","last_page":"2169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9884999990463257,"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":0.9850000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8392170667648315},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7614670991897583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6557854413986206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6547274589538574},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6184611320495605},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5682997703552246},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.5444281697273254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4900132715702057},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09197825193405151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392170667648315},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7614670991897583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6557854413986206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6547274589538574},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6184611320495605},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5682997703552246},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.5444281697273254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4900132715702057},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09197825193405151},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222653","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"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":33,"referenced_works":["https://openalex.org/W1915251500","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2565591417","https://openalex.org/W2619328388","https://openalex.org/W2727586675","https://openalex.org/W2888894220","https://openalex.org/W2963585992","https://openalex.org/W2972991710","https://openalex.org/W2978036638","https://openalex.org/W2988326850","https://openalex.org/W3003642782","https://openalex.org/W3003868038","https://openalex.org/W3024308166","https://openalex.org/W3034447740","https://openalex.org/W3034775979","https://openalex.org/W3035449864","https://openalex.org/W3043311956","https://openalex.org/W3082397598","https://openalex.org/W3096297644","https://openalex.org/W3111885845","https://openalex.org/W3134064484","https://openalex.org/W3163463193","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W3207037366","https://openalex.org/W4320855770","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6640059789","https://openalex.org/W6767164110","https://openalex.org/W6775150526","https://openalex.org/W6850778630"],"related_works":["https://openalex.org/W2140798747","https://openalex.org/W2948169060","https://openalex.org/W2730112582","https://openalex.org/W2110696645","https://openalex.org/W2358580169","https://openalex.org/W2111347279","https://openalex.org/W4399426197","https://openalex.org/W2487211728","https://openalex.org/W2378096925","https://openalex.org/W4386590374"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,123,164],"knowledge":[4,61,129],"distillation":[5,165],"method":[6,162],"for":[7],"an":[8,76,131],"external":[9,77,132],"bidirectional":[10,133,183],"language":[11,16,78,134,139,184],"model":[12,79,126,135,177],"trained":[13,136],"by":[14,55,103,127,137],"masked":[15,138],"modeling":[17],"to":[18,35,64,87,121,152,179],"achieve":[19],"high":[20],"accuracy":[21],"in":[22,39,92,157],"scene":[23,189],"text":[24,37,66,94,100,105,124,158,175,190],"recognition.":[25],"In":[26],"Asian":[27],"languages":[28],"such":[29],"as":[30,151],"Japanese,":[31],"it":[32],"is":[33,62,120],"necessary":[34],"perform":[36],"recognition":[38,95,106,125,176,191],"units":[40],"of":[41,130,173,181,195],"multiple":[42],"words":[43,49,51],"or":[44],"sentences":[45],"rather":[46],"than":[47],"individual":[48],"because":[50,96],"are":[52],"not":[53,143],"separated":[54],"spaces,":[56],"and":[57],"so":[58],"high-level":[59],"linguistic":[60,70],"needed":[63],"recognize":[65],"correctly.":[67],"To":[68,113],"enhance":[69,122],"knowledge,":[71],"several":[72],"methods":[73,85],"that":[74,168,180],"use":[75],"have":[80],"been":[81],"proposed,":[82],"but":[83,146],"these":[84],"fail":[86],"consider":[88,109,154],"future":[89,148,155],"context":[90,156],"well":[91],"performing":[93],"they":[97],"revise":[98],"the":[99,170,174,182,193,196],"candidates":[101],"yielded":[102],"autoregressive":[104],"models,":[107],"which":[108,141],"mainly":[110],"past":[111,145],"context.":[112,149],"overcome":[114],"this":[115],"deficiency,":[116],"our":[117,160],"key":[118],"idea":[119],"utilizing":[128],"modeling,":[140],"reflects":[142],"only":[144],"also":[147],"So":[150],"actively":[153],"recognition,":[159],"proposed":[161,197],"introduces":[163],"loss":[166],"term":[167],"makes":[169],"output":[171],"probability":[172],"closer":[178],"model.":[185],"Experiments":[186],"on":[187],"Japanese":[188],"demonstrate":[192],"effectiveness":[194],"method.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}