{"id":"https://openalex.org/W4388848051","doi":"https://doi.org/10.1145/3633517","title":"Scene Text Recognition via Dual-path Network with Shape-driven Attention Alignment","display_name":"Scene Text Recognition via Dual-path Network with Shape-driven Attention Alignment","publication_year":2023,"publication_date":"2023-11-21","ids":{"openalex":"https://openalex.org/W4388848051","doi":"https://doi.org/10.1145/3633517"},"language":"en","primary_location":{"id":"doi:10.1145/3633517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3633517","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5100626608","display_name":"Yijie Hu","orcid":"https://orcid.org/0009-0006-5968-3389"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yijie Hu","raw_affiliation_strings":["School of Advanced Technology, Xi\u2019an Jiaotong-Liverpool University, China","School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi\u2019an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107678840","display_name":"Bin Dong","orcid":"https://orcid.org/0009-0000-8431-0644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Dong","raw_affiliation_strings":["Ricoh Software Research Center(Beijing) Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"Ricoh Software Research Center(Beijing) Co., Ltd., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026022035","display_name":"Kaizhu Huang","orcid":"https://orcid.org/0000-0002-3034-9639"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107678611","display_name":"Lei Ding","orcid":"https://orcid.org/0009-0006-5201-5564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Ding","raw_affiliation_strings":["Ricoh Software Research Center(Beijing) Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"Ricoh Software Research Center(Beijing) Co., Ltd., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391855","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-0707-8076"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["School of Advanced Technology, Xi\u2019an Jiaotong-Liverpool University, China","School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi\u2019an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020085889","display_name":"Xiaowei Huang","orcid":"https://orcid.org/0000-0001-6267-0366"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaowei Huang","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053452551","display_name":"Qiufeng Wang","orcid":"https://orcid.org/0000-0002-0918-4606"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiu-Feng Wang","raw_affiliation_strings":["School of Advanced Technology, Xi\u2019an Jiaotong-Liverpool University, China","School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi\u2019an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of Advanced Technology, Xi'an Jiaotong-Liverpool University, China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100626608"],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":0.5943,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.699114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"20"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9987000226974487,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8645777702331543},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6396842002868652},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6317176818847656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5635771155357361},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.493314653635025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37777960300445557},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16208097338676453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8645777702331543},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6396842002868652},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6317176818847656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5635771155357361},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.493314653635025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37777960300445557},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16208097338676453},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3633517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3633517","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1364539167","display_name":"FOUNDATIONS FOR CONTINUOUS ENGINEERING OF TRUSTWORTHY AUTONOMY","funder_award_id":"956123","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1365771416","display_name":null,"funder_award_id":"2020006","funder_id":"https://openalex.org/F4320321605","funder_display_name":"Government of Jiangsu Province"},{"id":"https://openalex.org/G1472713335","display_name":null,"funder_award_id":"62276258","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1698772872","display_name":null,"funder_award_id":"92370119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3615643766","display_name":"Electrochemiluminescent biosensor for screening of coeliac disease","funder_award_id":"237011","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3910829908","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3936357396","display_name":null,"funder_award_id":"BE2020006-4","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5866557873","display_name":null,"funder_award_id":"62376113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6661291015","display_name":"EnnCore: End-to-End Conceptual Guarding of Neural Architectures","funder_award_id":"EP/T026995/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G712068865","display_name":null,"funder_award_id":"2020006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7341722744","display_name":null,"funder_award_id":"92370119, 62376113, and 62276258","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8452545418","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G849311619","display_name":null,"funder_award_id":"EP/T026995/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2033404582","https://openalex.org/W2097117768","https://openalex.org/W2099247484","https://openalex.org/W2156338447","https://openalex.org/W2186222003","https://openalex.org/W2194187530","https://openalex.org/W2309693750","https://openalex.org/W2607306668","https://openalex.org/W2810983211","https://openalex.org/W2963526661","https://openalex.org/W2997351497","https://openalex.org/W3006871679","https://openalex.org/W3111278072","https://openalex.org/W3136792391","https://openalex.org/W3149839747","https://openalex.org/W3177505580","https://openalex.org/W3206651063","https://openalex.org/W3214007456","https://openalex.org/W4206982465","https://openalex.org/W4221141431","https://openalex.org/W4229030834","https://openalex.org/W4247050319","https://openalex.org/W4283819468","https://openalex.org/W6791990631"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Scene":[0],"text":[1,146],"recognition":[2],"(STR),":[3],"one":[4],"typical":[5],"sequence-to-sequence":[6],"problem,":[7],"has":[8],"drawn":[9],"much":[10],"attention":[11,67,92],"recently":[12],"in":[13],"multimedia":[14],"applications.":[15],"To":[16],"guarantee":[17],"good":[18],"performance,":[19],"it":[20],"is":[21,71],"essential":[22],"for":[23],"STR":[24],"to":[25,73,84,89,103,130,138],"obtain":[26,74],"aligned":[27],"character-wise":[28,75,105],"features":[29,106],"from":[30],"the":[31,91,140],"whole-image":[32],"feature":[33],"maps.":[34],"While":[35],"most":[36],"present":[37],"works":[38],"adopt":[39],"fully":[40],"data-driven":[41],"attention-based":[42],"alignment,":[43],"such":[44],"practice":[45],"ignores":[46],"specific":[47],"character":[48],"geometric":[49,60],"information.":[50],"In":[51],"this":[52],"article,":[53],"built":[54],"upon":[55],"a":[56,64,81,86,96,111,115,126,178],"group":[57],"of":[58,98],"learnable":[59],"points,":[61],"we":[62,78],"propose":[63,110],"novel":[65],"shape-driven":[66],"alignment":[68],"method":[69,142,172],"that":[70,121,170],"able":[72],"features.":[76],"Concretely,":[77],"first":[79],"design":[80],"corner":[82],"detector":[83],"generate":[85],"shape":[87],"map":[88],"guide":[90],"alignments":[93],"explicitly,":[94],"where":[95],"series":[97],"points":[99],"can":[100,173],"be":[101],"learned":[102],"represent":[104],"flexibly.":[107],"We":[108,134],"then":[109],"dual-path":[112],"network":[113],"with":[114,125,177],"mutual":[116],"learning":[117],"and":[118,152,161,163],"cooperating":[119],"strategy":[120],"successfully":[122],"combines":[123],"CNN":[124],"ViT-based":[127],"model,":[128],"leading":[129],"further":[131],"accuracy":[132],"improvement.":[133],"conduct":[135],"extensive":[136],"experiments":[137],"evaluate":[139],"proposed":[141],"on":[143],"various":[144],"scene":[145],"benchmarks,":[147],"including":[148],"six":[149],"popular":[150],"regular":[151],"irregular":[153],"datasets,":[154],"two":[155],"more":[156],"challenging":[157],"datasets":[158],"(i.e.,":[159],"WordArt":[160],"OST),":[162],"three":[164],"Chinese":[165],"datasets.":[166],"Experimental":[167],"results":[168],"indicate":[169],"our":[171],"achieve":[174],"superior":[175],"performance":[176],"comparable":[179],"model":[180],"size":[181],"against":[182],"many":[183],"state-of-the-art":[184],"models.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
