{"id":"https://openalex.org/W3195209190","doi":"https://doi.org/10.1109/icip42928.2021.9506779","title":"Analysis of the Novel Transformer Module Combination for Scene Text Recognition","display_name":"Analysis of the Novel Transformer Module Combination for Scene Text Recognition","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3195209190","doi":"https://doi.org/10.1109/icip42928.2021.9506779","mag":"3195209190"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5003938284","display_name":"Yeon-gyu Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147982","display_name":"NHN (South Korea)","ror":"https://ror.org/03x1nzy67","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210147982"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeon-Gyu Kim","raw_affiliation_strings":["Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","institution_ids":["https://openalex.org/I4210147982"]},{"raw_affiliation_string":"NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119710417","display_name":"Hyunsu Kim","orcid":"https://orcid.org/0000-0003-2507-1721"},"institutions":[{"id":"https://openalex.org/I4210147982","display_name":"NHN (South Korea)","ror":"https://ror.org/03x1nzy67","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210147982"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunsu Kim","raw_affiliation_strings":["Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","institution_ids":["https://openalex.org/I4210147982"]},{"raw_affiliation_string":"NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034418151","display_name":"Minseok Kang","orcid":"https://orcid.org/0000-0002-7021-6873"},"institutions":[{"id":"https://openalex.org/I4210147982","display_name":"NHN (South Korea)","ror":"https://ror.org/03x1nzy67","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210147982"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minseok Kang","raw_affiliation_strings":["Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","institution_ids":["https://openalex.org/I4210147982"]},{"raw_affiliation_string":"NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066229979","display_name":"Hyug-Jae Lee","orcid":"https://orcid.org/0000-0002-2802-7243"},"institutions":[{"id":"https://openalex.org/I4210147982","display_name":"NHN (South Korea)","ror":"https://ror.org/03x1nzy67","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210147982"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyug-Jae Lee","raw_affiliation_strings":["Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","institution_ids":["https://openalex.org/I4210147982"]},{"raw_affiliation_string":"NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091650602","display_name":"Rokkyu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147982","display_name":"NHN (South Korea)","ror":"https://ror.org/03x1nzy67","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210147982"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Rokkyu Lee","raw_affiliation_strings":["Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","institution_ids":["https://openalex.org/I4210147982"]},{"raw_affiliation_string":"NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024803683","display_name":"Gunhan Park","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147982","display_name":"NHN (South Korea)","ror":"https://ror.org/03x1nzy67","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210147982"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunhan Park","raw_affiliation_strings":["Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Lab,NHN Corp,Seongnam-si,Gyeonggi-do,Republic of Korea","institution_ids":["https://openalex.org/I4210147982"]},{"raw_affiliation_string":"NHN Corp, Machine Learning Lab, Seongnam-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1229","last_page":"1233"},"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":0.9991999864578247,"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":0.9891999959945679,"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/encoder","display_name":"Encoder","score":0.8152605295181274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733206570148468},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7298359870910645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5754011869430542},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4689728021621704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46895402669906616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.351955771446228},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11918199062347412}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8152605295181274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733206570148468},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7298359870910645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5754011869430542},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4689728021621704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46895402669906616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.351955771446228},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11918199062347412},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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":1,"locations":[{"id":"doi:10.1109/icip42928.2021.9506779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2549139847","https://openalex.org/W2948981900","https://openalex.org/W2963420686","https://openalex.org/W2965066169","https://openalex.org/W2998382406","https://openalex.org/W3003642782","https://openalex.org/W3004846386","https://openalex.org/W3021293129","https://openalex.org/W3034414401","https://openalex.org/W3035682737","https://openalex.org/W3042011474","https://openalex.org/W3093712593","https://openalex.org/W3097777922","https://openalex.org/W3119350346","https://openalex.org/W3134064484","https://openalex.org/W4297665946","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6743731764","https://openalex.org/W6763608318","https://openalex.org/W6775845032","https://openalex.org/W6776684981","https://openalex.org/W6784012970"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2107949441"],"abstract_inverted_index":{"Various":[0],"methods":[1,12],"for":[2,58,138],"scene":[3],"text":[4,44],"recognition":[5],"(STR)":[6],"are":[7],"proposed":[8],"every":[9],"year.":[10],"These":[11],"dramatically":[13],"increase":[14],"the":[15,18,32,51,59,63,70,88,107,123,130],"performance":[16,52,121],"of":[17,34,53,62,77,91,125],"existing":[19],"STR":[20],"field;":[21],"however,":[22],"they":[23],"have":[24],"not":[25],"been":[26],"able":[27],"to":[28,79],"keep":[29],"up":[30],"with":[31,95],"progress":[33],"general-purpose":[35],"research":[36],"in":[37,65,111],"image":[38],"recognition,":[39,42],"detection,":[40],"speech":[41],"and":[43,114],"analysis.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,68],"evaluate":[50],"several":[54],"deep":[55],"learning":[56],"schemes":[57],"encoder":[60,78,92,105,135],"part":[61],"Transformer":[64],"STR.":[66],"First,":[67],"change":[69],"baseline":[71],"feed":[72],"forward":[73],"network":[74],"(FFN)":[75],"module":[76],"squeeze-and-excitation":[80],"(SE)-FFN":[81],"or":[82,101,116],"cross":[83],"stage":[84],"partial":[85],"(CSP)-FFN.":[86],"Second,":[87],"overall":[89],"architecture":[90],"is":[93,127],"replaced":[94],"local":[96],"dense":[97],"synthesizer":[98],"attention":[99,131],"(LDSA)":[100],"Conformer":[102,104],"structure.":[103],"achieves":[106],"best":[108],"test":[109],"accuracy":[110],"various":[112],"experiments,":[113],"SE":[115],"CSP-FFN":[117],"also":[118],"showed":[119],"competitive":[120],"when":[122],"number":[124],"parameters":[126],"considered.":[128],"Visualizing":[129],"maps":[132],"from":[133],"different":[134],"combinations":[136],"allows":[137],"qualitative":[139],"performance.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}