{"id":"https://openalex.org/W2810983211","doi":"https://doi.org/10.1109/tpami.2018.2848939","title":"ASTER: An Attentional Scene Text Recognizer with Flexible Rectification","display_name":"ASTER: An Attentional Scene Text Recognizer with Flexible Rectification","publication_year":2018,"publication_date":"2018-06-25","ids":{"openalex":"https://openalex.org/W2810983211","doi":"https://doi.org/10.1109/tpami.2018.2848939","mag":"2810983211","pmid":"https://pubmed.ncbi.nlm.nih.gov/29994467"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2018.2848939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2848939","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5080734619","display_name":"Baoguang Shi","orcid":"https://orcid.org/0000-0001-6886-8189"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baoguang Shi","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058252339","display_name":"Mingkun Yang","orcid":"https://orcid.org/0000-0002-6078-6100"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkun Yang","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037191476","display_name":"Xinggang Wang","orcid":"https://orcid.org/0000-0001-6732-7823"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinggang Wang","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027156714","display_name":"Pengyuan Lyu","orcid":"https://orcid.org/0000-0003-3153-8519"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Lyu","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669593","display_name":"Cong Yao","orcid":"https://orcid.org/0000-0001-6564-4796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Yao","raw_affiliation_strings":["Megvii (Face++) Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Megvii (Face++) Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5080734619"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":36.5488,"has_fulltext":false,"cited_by_count":909,"citation_normalized_percentile":{"value":0.99776838,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"41","issue":"9","first_page":"2035","last_page":"2048"},"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":0.9962000250816345,"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":0.9955999851226807,"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":0.7995626330375671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7172154188156128},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.6503668427467346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5348255634307861},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5017213821411133},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4397623836994171},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4366152286529541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3931795358657837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995626330375671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7172154188156128},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.6503668427467346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5348255634307861},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5017213821411133},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4397623836994171},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4366152286529541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3931795358657837},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2018.2848939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2848939","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:29994467","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29994467","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":100,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W18999703","https://openalex.org/W70975097","https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W654550266","https://openalex.org/W854541894","https://openalex.org/W1488125194","https://openalex.org/W1491389626","https://openalex.org/W1521064364","https://openalex.org/W1607307044","https://openalex.org/W1895191496","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1972065312","https://openalex.org/W1978729128","https://openalex.org/W1988461287","https://openalex.org/W1990550880","https://openalex.org/W1998042868","https://openalex.org/W2006653496","https://openalex.org/W2008806374","https://openalex.org/W2029189646","https://openalex.org/W2043075591","https://openalex.org/W2049951199","https://openalex.org/W2053317383","https://openalex.org/W2057175746","https://openalex.org/W2061802763","https://openalex.org/W2064675550","https://openalex.org/W2099247484","https://openalex.org/W2112796928","https://openalex.org/W2118117136","https://openalex.org/W2122221966","https://openalex.org/W2122585011","https://openalex.org/W2124404372","https://openalex.org/W2127141656","https://openalex.org/W2128409098","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2135231474","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2153182373","https://openalex.org/W2157331557","https://openalex.org/W2160299344","https://openalex.org/W2163605009","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2239173263","https://openalex.org/W2294053032","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2344822769","https://openalex.org/W2395611524","https://openalex.org/W2402144811","https://openalex.org/W2532759528","https://openalex.org/W2550687635","https://openalex.org/W2605982830","https://openalex.org/W2613904329","https://openalex.org/W2740767790","https://openalex.org/W2741147179","https://openalex.org/W2750938222","https://openalex.org/W2752225195","https://openalex.org/W2777652944","https://openalex.org/W2953384591","https://openalex.org/W2962773189","https://openalex.org/W2962790387","https://openalex.org/W2963446712","https://openalex.org/W2963517393","https://openalex.org/W2963648432","https://openalex.org/W2964265128","https://openalex.org/W2964296749","https://openalex.org/W2964300754","https://openalex.org/W2964308564","https://openalex.org/W3106250896","https://openalex.org/W3106271744","https://openalex.org/W4294629828","https://openalex.org/W6600284362","https://openalex.org/W6600775145","https://openalex.org/W6602936574","https://openalex.org/W6618372016","https://openalex.org/W6623517193","https://openalex.org/W6629021407","https://openalex.org/W6629590909","https://openalex.org/W6636382570","https://openalex.org/W6638296183","https://openalex.org/W6640226783","https://openalex.org/W6642972425","https://openalex.org/W6649973027","https://openalex.org/W6677457056","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682488149","https://openalex.org/W6684191040","https://openalex.org/W6713134421","https://openalex.org/W6729791593","https://openalex.org/W6737778391","https://openalex.org/W6741742085","https://openalex.org/W6744310024","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2355499516","https://openalex.org/W3210974833","https://openalex.org/W2599000612","https://openalex.org/W2811475781","https://openalex.org/W2094246381","https://openalex.org/W2361137193","https://openalex.org/W2377736761","https://openalex.org/W2353928006","https://openalex.org/W2797910360","https://openalex.org/W3198761544"],"abstract_inverted_index":{"A":[0],"challenging":[1],"aspect":[2],"of":[3,83,132,141],"scene":[4],"text":[5,10,19,22,67,84],"recognition":[6,51,93,139,154],"is":[7,71,87,95,113,148],"to":[8,31,116,159],"handle":[9],"with":[11],"distortions":[12],"or":[13],"irregular":[14],"layout.":[15],"In":[16,33],"particular,":[17],"perspective":[18],"and":[20,28,49,86,121,135],"curved":[21],"are":[23,29],"common":[24],"in":[25,68,152],"natural":[26],"scenes":[27],"difficult":[30],"recognize.":[32],"this":[34],"work,":[35],"we":[36,128,144],"introduce":[37],"ASTER,":[38],"an":[39,58,96],"end-to-end":[40,153],"neural":[41],"network":[42,48,55,94],"model":[43,99,112],"that":[44,100,146],"comprises":[45],"a":[46,50,62,74,81,102,149],"rectification":[47,54,134],"network.":[52],"The":[53,92,110],"adaptively":[56],"transforms":[57],"input":[59],"image":[60],"into":[61],"new":[63],"one,":[64],"rectifying":[65],"the":[66,107,130,133,137,161],"it.":[69],"It":[70],"powered":[72],"by":[73],"flexible":[75],"Thin-Plate":[76],"Spline":[77],"transformation":[78],"which":[79],"handles":[80],"variety":[82],"irregularities":[85],"trained":[88,114],"without":[89],"human":[90],"annotations.":[91],"attentional":[97],"sequence-to-sequence":[98],"predicts":[101],"character":[103],"sequence":[104],"directly":[105],"from":[106],"rectified":[108],"image.":[109],"whole":[111],"end":[115],"end,":[117],"requiring":[118],"only":[119],"images":[120],"their":[122],"groundtruth":[123],"text.":[124],"Through":[125],"extensive":[126],"experiments,":[127],"verify":[129],"effectiveness":[131],"demonstrate":[136,145],"state-of-the-art":[138],"performance":[140],"ASTER.":[142],"Furthermore,":[143],"ASTER":[147],"powerful":[150],"component":[151],"systems,":[155],"for":[156],"its":[157],"ability":[158],"enhance":[160],"detector.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":101},{"year":2024,"cited_by_count":149},{"year":2023,"cited_by_count":157},{"year":2022,"cited_by_count":139},{"year":2021,"cited_by_count":150},{"year":2020,"cited_by_count":121},{"year":2019,"cited_by_count":63},{"year":2018,"cited_by_count":10}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}