{"id":"https://openalex.org/W2970910956","doi":"https://doi.org/10.1109/tpami.2019.2937086","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","display_name":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","publication_year":2019,"publication_date":"2019-08-27","ids":{"openalex":"https://openalex.org/W2970910956","doi":"https://doi.org/10.1109/tpami.2019.2937086","mag":"2970910956","pmid":"https://pubmed.ncbi.nlm.nih.gov/31449005"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2019.2937086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2937086","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/A5030174783","display_name":"Minghui Liao","orcid":"https://orcid.org/0000-0002-2583-4314"},"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":"Minghui Liao","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2583-4314","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"],"raw_orcid":"https://orcid.org/0000-0003-3153-8519","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/A5025388895","display_name":"Minghang He","orcid":null},"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":"Minghang He","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"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"],"raw_orcid":"https://orcid.org/0000-0001-6564-4796","affiliations":[{"raw_affiliation_string":"Megvii (Face++) Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015819673","display_name":"Wenhao Wu","orcid":"https://orcid.org/0000-0002-8511-743X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Wu","raw_affiliation_strings":["Megvii (Face++) Inc., Beijing, China"],"raw_orcid":null,"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"],"raw_orcid":"https://orcid.org/0000-0002-3449-5940","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/A5030174783"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":15.2108,"has_fulltext":false,"cited_by_count":244,"citation_normalized_percentile":{"value":0.99182471,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"43","issue":"2","first_page":"532","last_page":"548"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9886000156402588,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/spotting","display_name":"Spotting","score":0.8090592622756958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7840551733970642},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7505725622177124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7070420980453491},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.6706423759460449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5697553753852844},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.548004150390625},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.531037449836731},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5200914144515991},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5184826254844666},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.4793551564216614},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4358721971511841},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4301929473876953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3762466013431549},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23807761073112488},{"id":"https://openalex.org/keywords/text-graph","display_name":"Text graph","score":0.23190680146217346}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8090592622756958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840551733970642},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7505725622177124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7070420980453491},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.6706423759460449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5697553753852844},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.548004150390625},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.531037449836731},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5200914144515991},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5184826254844666},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.4793551564216614},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4358721971511841},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4301929473876953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3762466013431549},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23807761073112488},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.23190680146217346},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2019.2937086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2019.2937086","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:31449005","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31449005","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":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336648","display_name":"National Program for Support of Top-notch Young Professionals","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":122,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W70975097","https://openalex.org/W117491841","https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W654550266","https://openalex.org/W1488125194","https://openalex.org/W1491389626","https://openalex.org/W1536680647","https://openalex.org/W1607307044","https://openalex.org/W1812645736","https://openalex.org/W1895191496","https://openalex.org/W1903029394","https://openalex.org/W1922126009","https://openalex.org/W1935817682","https://openalex.org/W1947481528","https://openalex.org/W1971822075","https://openalex.org/W1972065312","https://openalex.org/W1978729128","https://openalex.org/W1981283549","https://openalex.org/W1988461287","https://openalex.org/W1990550880","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2049951199","https://openalex.org/W2053317383","https://openalex.org/W2061802763","https://openalex.org/W2064675550","https://openalex.org/W2065613686","https://openalex.org/W2102605133","https://openalex.org/W2122221966","https://openalex.org/W2127141656","https://openalex.org/W2140132917","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2153182373","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2239285313","https://openalex.org/W2253806798","https://openalex.org/W2294053032","https://openalex.org/W2296073425","https://openalex.org/W2317851288","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2344822769","https://openalex.org/W2395360388","https://openalex.org/W2395611524","https://openalex.org/W2407521645","https://openalex.org/W2464918637","https://openalex.org/W2519818067","https://openalex.org/W2532759528","https://openalex.org/W2550687635","https://openalex.org/W2555182955","https://openalex.org/W2560023338","https://openalex.org/W2565639579","https://openalex.org/W2604243686","https://openalex.org/W2604735854","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2613904329","https://openalex.org/W2704256938","https://openalex.org/W2727586675","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2777652944","https://openalex.org/W2779757316","https://openalex.org/W2784050770","https://openalex.org/W2785383245","https://openalex.org/W2786962101","https://openalex.org/W2795619303","https://openalex.org/W2810028092","https://openalex.org/W2810983211","https://openalex.org/W2831607544","https://openalex.org/W2875814315","https://openalex.org/W2962773189","https://openalex.org/W2962790387","https://openalex.org/W2962804639","https://openalex.org/W2962984063","https://openalex.org/W2962986948","https://openalex.org/W2963037989","https://openalex.org/W2963114696","https://openalex.org/W2963150697","https://openalex.org/W2963187132","https://openalex.org/W2963299604","https://openalex.org/W2963327605","https://openalex.org/W2963517393","https://openalex.org/W2963840241","https://openalex.org/W2963840672","https://openalex.org/W2963977642","https://openalex.org/W2964018263","https://openalex.org/W2964265128","https://openalex.org/W2964294787","https://openalex.org/W2964296749","https://openalex.org/W2964300754","https://openalex.org/W2964308564","https://openalex.org/W2964312704","https://openalex.org/W3102695566","https://openalex.org/W3106250896","https://openalex.org/W3106271744","https://openalex.org/W4295246343","https://openalex.org/W4297734170","https://openalex.org/W4297813700","https://openalex.org/W4301185181","https://openalex.org/W6618372016","https://openalex.org/W6629021407","https://openalex.org/W6629590909","https://openalex.org/W6636382570","https://openalex.org/W6638296183","https://openalex.org/W6640226783","https://openalex.org/W6649973027","https://openalex.org/W6679434410","https://openalex.org/W6682488149","https://openalex.org/W6691603626","https://openalex.org/W6696085341","https://openalex.org/W6712036928","https://openalex.org/W6729791593","https://openalex.org/W6737778391","https://openalex.org/W6745516741","https://openalex.org/W6748339197","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2949229884","https://openalex.org/W4225683503","https://openalex.org/W2875814315","https://openalex.org/W4323366758","https://openalex.org/W2982121298","https://openalex.org/W4226291595","https://openalex.org/W3205597380","https://openalex.org/W3005922567","https://openalex.org/W2777652944","https://openalex.org/W2988098900"],"abstract_inverted_index":{"Unifying":[0],"text":[1,4,18,40,46,68,138,170,194,198],"detection":[2,47,98,132,167],"and":[3,29,48,80,90,99,122,133,154,168,192],"recognition":[5,49,83,100,171,178],"in":[6,19,50,95,165],"an":[7],"end-to-end":[8,54,92,169],"training":[9],"fashion":[10],"has":[11],"become":[12],"a":[13,76,81,88,112],"new":[14],"trend":[15],"for":[16,143,196],"reading":[17],"the":[20,36,66,72,120,126,177],"wild,":[21],"as":[22,59],"these":[23],"two":[24],"tasks":[25],"are":[26],"highly":[27],"relevant":[28],"complementary.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,174],"investigate":[35,176],"problem":[37],"of":[38,75,140,180],"scene":[39,197],"spotting,":[41],"which":[42,96,184],"aims":[43],"at":[44],"simultaneous":[45],"natural":[51],"images.":[52],"An":[53],"trainable":[55],"neural":[56],"network":[57,79],"named":[58],"Mask":[60,85],"TextSpotter":[61,86],"is":[62,116],"presented.":[63],"Different":[64],"from":[65,105,125],"previous":[67],"spotters":[69],"that":[70],"follow":[71],"pipeline":[73],"consisting":[74],"proposal":[77],"generation":[78],"sequence-to-sequence":[82],"network,":[84],"enjoys":[87],"simple":[89],"smooth":[91],"learning":[93],"procedure,":[94],"both":[97,131,166,190],"can":[101],"be":[102],"achieved":[103],"directly":[104],"two-dimensional":[106,128],"space":[107],"via":[108],"semantic":[109],"segmentation.":[110],"Further,":[111],"spatial":[113],"attention":[114],"module":[115,179],"proposed":[117,127],"to":[118],"enhance":[119],"performance":[121,161],"universality.":[123],"Benefiting":[124],"representation":[129],"on":[130,150,189],"recognition,":[134],"it":[135,149],"easily":[136],"handles":[137],"instances":[139],"irregular":[141,193],"shapes,":[142],"instance,":[144],"curved":[145],"text.":[146],"We":[147],"evaluate":[148],"four":[151],"English":[152],"datasets":[153,195],"one":[155],"multi-language":[156],"dataset,":[157],"achieving":[158],"consistently":[159],"superior":[160],"over":[162],"state-of-the-art":[163,187],"methods":[164,188],"tasks.":[172],"Moreover,":[173],"further":[175],"our":[181],"method":[182],"separately,":[183],"significantly":[185],"outperforms":[186],"regular":[191],"recognition.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":39},{"year":2021,"cited_by_count":71},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":7}],"updated_date":"2026-06-04T09:04:59.091469","created_date":"2025-10-10T00:00:00"}