{"id":"https://openalex.org/W4293519256","doi":"https://doi.org/10.1109/icme52920.2022.9859826","title":"DBCAN: Dual-Branch Cross-Attention Network for Scene Text Recognition","display_name":"DBCAN: Dual-Branch Cross-Attention Network for Scene Text Recognition","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293519256","doi":"https://doi.org/10.1109/icme52920.2022.9859826"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859826","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101420812","display_name":"Xinjian Gao","orcid":"https://orcid.org/0000-0002-9795-5908"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinjian Gao","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102006884","display_name":"Ye Pang","orcid":"https://orcid.org/0009-0005-6393-8930"},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ye Pang","raw_affiliation_strings":["Ping An Technology Co"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology Co","institution_ids":["https://openalex.org/I4210105511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979565","display_name":"Yuyu Liu","orcid":"https://orcid.org/0009-0005-1541-5000"},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yuyu Liu","raw_affiliation_strings":["Ping An Technology Co"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology Co","institution_ids":["https://openalex.org/I4210105511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034261147","display_name":"Maokun Han","orcid":"https://orcid.org/0009-0007-9335-4025"},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Maokun Han","raw_affiliation_strings":["Ping An Technology Co"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology Co","institution_ids":["https://openalex.org/I4210105511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000544669","display_name":"Kai Hou","orcid":"https://orcid.org/0000-0001-7660-0393"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Hou","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100392327","display_name":"Wei Wang","orcid":"https://orcid.org/0009-0003-0550-497X"},"institutions":[{"id":"https://openalex.org/I4210105511","display_name":"Beacon Tech (Israel)","ror":"https://ror.org/00zbjch89","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210105511"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Ping An Technology Co"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology Co","institution_ids":["https://openalex.org/I4210105511"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07375595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9911999702453613,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9850000143051147,"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":0.8305078148841858},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5936883687973022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5710629224777222},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5601572394371033},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.515814483165741},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5150265693664551},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5040532350540161},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4906865358352661},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4139400124549866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.393693208694458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37825924158096313},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15885773301124573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305078148841858},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5936883687973022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710629224777222},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5601572394371033},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.515814483165741},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5150265693664551},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5040532350540161},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4906865358352661},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4139400124549866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.393693208694458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37825924158096313},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15885773301124573},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859826","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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 IEEE International Conference on Multimedia and Expo (ICME)","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":33,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2810983211","https://openalex.org/W2952285877","https://openalex.org/W2963517393","https://openalex.org/W2965066169","https://openalex.org/W2997749585","https://openalex.org/W2997864923","https://openalex.org/W3034414401","https://openalex.org/W3034447740","https://openalex.org/W3035449864","https://openalex.org/W3092894544","https://openalex.org/W3110267192","https://openalex.org/W3139049060","https://openalex.org/W3173990630","https://openalex.org/W3196199406","https://openalex.org/W3202415716","https://openalex.org/W3204778874","https://openalex.org/W3206651063","https://openalex.org/W4385245566","https://openalex.org/W6629590909","https://openalex.org/W6649973027","https://openalex.org/W6739901393","https://openalex.org/W6764306230","https://openalex.org/W6792695861","https://openalex.org/W6801347494"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W2379407973","https://openalex.org/W2350267540"],"abstract_inverted_index":{"Scene":[0],"text":[1,5,17,39],"recognition,":[2,6],"especially":[3],"irregular":[4],"is":[7,99,114,135],"a":[8,54,87,93],"challenging":[9,38],"task":[10],"due":[11],"to":[12,101],"the":[13,28,61,72,103,120],"large":[14],"variance":[15],"in":[16],"appearance.":[18],"Although":[19],"some":[20,37],"existing":[21],"methods":[22,63,122],"have":[23],"achieved":[24],"state-of-the-art":[25,125],"performance":[26,126],"with":[27,79],"attention-based":[29],"encoder-decoder":[30],"framework,":[31],"they":[32],"always":[33],"perform":[34],"poorly":[35],"on":[36,66,127],"such":[40],"as":[41],"severely":[42],"curved,":[43],"blurred,":[44],"and":[45,75,83,117,123],"incomplete-semantic":[46],"text.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"we":[52],"propose":[53],"Dual-Branch":[55],"Cross-Attention":[56,89],"Network":[57],"(DBCAN).":[58],"Different":[59],"from":[60],"previous":[62,121],"heavily":[64],"relying":[65],"semantic":[67,77],"information,":[68],"DBCAN":[69,113],"can":[70],"enhance":[71],"position":[73],"clues":[74],"learn":[76],"relations":[78],"two":[80],"separate":[81],"branches":[82],"fuse":[84],"them":[85],"by":[86],"tailored":[88],"Module":[90],"(CAM).":[91],"Furthermore,":[92],"Convolution-Based":[94],"2D":[95,104],"Positional":[96],"Embedding":[97],"(CBPE)":[98],"introduced":[100],"describe":[102],"spatial":[105],"dependencies":[106],"of":[107],"characters.":[108],"Extensive":[109],"experiments":[110],"demonstrate":[111],"our":[112],"more":[115],"accurate":[116],"robust":[118],"than":[119],"achieves":[124],"several":[128],"benchmarks,":[129],"particularly":[130],"CUTE":[131],"(93.4%).":[132],"Our":[133],"code":[134],"made":[136],"publicly":[137],"available":[138],"at":[139],"https://github.com/GaoXinJian-USTC/DBCAN.":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}