{"id":"https://openalex.org/W3113987534","doi":"https://doi.org/10.1109/tip.2020.3045602","title":"SLOAN: Scale-Adaptive Orientation Attention Network for Scene Text Recognition","display_name":"SLOAN: Scale-Adaptive Orientation Attention Network for Scene Text Recognition","publication_year":2020,"publication_date":"2020-12-23","ids":{"openalex":"https://openalex.org/W3113987534","doi":"https://doi.org/10.1109/tip.2020.3045602","mag":"3113987534","pmid":"https://pubmed.ncbi.nlm.nih.gov/33360990"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.3045602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3045602","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5070078619","display_name":"Pengwen Dai","orcid":"https://orcid.org/0000-0002-6262-982X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Pengwen Dai","raw_affiliation_strings":["State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6262-982X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408716","display_name":"Hua Zhang","orcid":"https://orcid.org/0000-0002-7627-4142"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Zhang","raw_affiliation_strings":["State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7627-4142","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068837264","display_name":"Xiaochun Cao","orcid":"https://orcid.org/0000-0001-7141-708X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Xiaochun Cao","raw_affiliation_strings":["State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","Peng Cheng Laboratory, Cyberspace Security Research Center, Shenzhen, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7141-708X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Cyberspace Security Research Center, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7322,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.8560656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1687","last_page":"1701"},"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":0.9871000051498413,"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":0.9825999736785889,"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":0.7489280104637146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6434933543205261},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.558012068271637},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5183180570602417},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4978823661804199},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41642069816589355},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4120737612247467},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40072256326675415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36888760328292847},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09494614601135254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489280104637146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434933543205261},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.558012068271637},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5183180570602417},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4978823661804199},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41642069816589355},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4120737612247467},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40072256326675415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36888760328292847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09494614601135254},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2020.3045602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3045602","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:33360990","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33360990","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G171606249","display_name":null,"funder_award_id":"U1803264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3418581704","display_name":null,"funder_award_id":"61733007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5091324188","display_name":null,"funder_award_id":"62072454","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5635581044","display_name":null,"funder_award_id":"4202084","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G644162162","display_name":null,"funder_award_id":"2020YFB1406704","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7747502101","display_name":null,"funder_award_id":"U1736219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W1488125194","https://openalex.org/W1491389626","https://openalex.org/W1922126009","https://openalex.org/W1981283549","https://openalex.org/W1995249206","https://openalex.org/W1998042868","https://openalex.org/W2006653496","https://openalex.org/W2008806374","https://openalex.org/W2059607459","https://openalex.org/W2122221966","https://openalex.org/W2127102696","https://openalex.org/W2130942839","https://openalex.org/W2135231474","https://openalex.org/W2140132917","https://openalex.org/W2144554289","https://openalex.org/W2167207289","https://openalex.org/W2193145675","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2341629100","https://openalex.org/W2343052201","https://openalex.org/W2556967412","https://openalex.org/W2557205807","https://openalex.org/W2565591417","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2752225195","https://openalex.org/W2777652944","https://openalex.org/W2782364420","https://openalex.org/W2784050770","https://openalex.org/W2788069964","https://openalex.org/W2795619303","https://openalex.org/W2809273748","https://openalex.org/W2810983211","https://openalex.org/W2886603769","https://openalex.org/W2896034938","https://openalex.org/W2921147815","https://openalex.org/W2949782066","https://openalex.org/W2949846184","https://openalex.org/W2962790387","https://openalex.org/W2962986948","https://openalex.org/W2963233387","https://openalex.org/W2963327605","https://openalex.org/W2963517393","https://openalex.org/W2963526661","https://openalex.org/W2963564809","https://openalex.org/W2963712589","https://openalex.org/W2964018263","https://openalex.org/W2964300754","https://openalex.org/W2965066169","https://openalex.org/W2967615747","https://openalex.org/W2970910956","https://openalex.org/W2979371747","https://openalex.org/W2979382951","https://openalex.org/W2986036729","https://openalex.org/W2988098900","https://openalex.org/W2991609675","https://openalex.org/W2997749585","https://openalex.org/W2998382406","https://openalex.org/W3005436539","https://openalex.org/W3034792612","https://openalex.org/W3082397598","https://openalex.org/W3101507774","https://openalex.org/W3102695566","https://openalex.org/W3106250896","https://openalex.org/W3106271744","https://openalex.org/W4293362962","https://openalex.org/W6629021407","https://openalex.org/W6629590909","https://openalex.org/W6638296183","https://openalex.org/W6640226783","https://openalex.org/W6649973027","https://openalex.org/W6679436768","https://openalex.org/W6729983426","https://openalex.org/W6730023239","https://openalex.org/W6743757654","https://openalex.org/W6744310024","https://openalex.org/W6748446516"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2142795561","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2334580170"],"abstract_inverted_index":{"Scene":[0],"text":[1,9,48,81],"recognition,":[2,82],"the":[3,7,29,40,52,96,101,107,116,119,127,134,171,187],"final":[4],"step":[5],"of":[6,85,112,191],"scene":[8,34,43,47,80,113],"reading":[10],"system,":[11],"has":[12],"made":[13],"impressive":[14],"progress":[15],"based":[16],"on":[17,181],"deep":[18],"neural":[19],"networks.":[20],"However,":[21],"existing":[22],"recognition":[23,93,136],"methods":[24],"devote":[25],"to":[26,39,104,125,151],"dealing":[27],"with":[28],"geometrically":[30],"regular":[31],"or":[32],"irregular":[33],"text.":[35,44,178],"They":[36],"are":[37],"limited":[38],"semantically":[41],"arbitrary-orientation":[42,79],"Meanwhile,":[45],"previous":[46],"recognizers":[49],"usually":[50],"learn":[51],"single-scale":[53],"feature":[54],"representations":[55],"for":[56,64,78,156],"various-scale":[57,157],"characters,":[58],"which":[59,83,122,142],"cannot":[60],"model":[61],"effective":[62],"contexts":[63,155],"different":[65],"characters.":[66,158],"In":[67],"this":[68],"paper,":[69],"we":[70],"propose":[71],"a":[72,86,91,144],"novel":[73,145],"scale-adaptive":[74],"orientation":[75],"attention":[76,149],"network":[77,137],"consists":[84],"dynamic":[87,97],"log-polar":[88,98,102,120],"transformer":[89,99],"and":[90,110,129,174,189],"sequence":[92,135],"network.":[94],"Specifically,":[95],"learns":[100],"origin":[103],"adaptively":[105],"convert":[106],"arbitrary":[108],"rotations":[109],"scales":[111],"texts":[114],"into":[115],"shifts":[117],"in":[118,165],"space,":[121],"is":[123,138],"helpful":[124],"generate":[126],"rotation-aware":[128],"scale-aware":[130],"visual":[131],"representation.":[132],"Next,":[133],"an":[139,166],"encoder-decoder":[140],"model,":[141],"incorporates":[143],"character-level":[146],"receptive":[147],"field":[148],"module":[150],"encode":[152],"more":[153],"valid":[154],"The":[159],"whole":[160],"architecture":[161],"can":[162],"be":[163],"trained":[164],"end-to-end":[167],"manner,":[168],"only":[169],"requiring":[170],"word":[172],"image":[173],"its":[175],"corresponding":[176],"ground-truth":[177],"Extensive":[179],"experiments":[180],"several":[182],"public":[183],"datasets":[184],"have":[185],"demonstrated":[186],"effectiveness":[188],"superiority":[190],"our":[192],"proposed":[193],"method.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}