{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:21:54Z","timestamp":1780572114617,"version":"3.54.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFB1004600"],"award-info":[{"award-number":["2018YFB1004600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61733007"],"award-info":[{"award-number":["61733007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018619","name":"National Program for Support of Top-notch Young Professionals","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018619","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for HUST Academic Frontier Youth Team","award":["2017QYTD08"],"award-info":[{"award-number":["2017QYTD08"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,2,1]]},"DOI":"10.1109\/tpami.2019.2937086","type":"journal-article","created":{"date-parts":[[2019,8,27]],"date-time":"2019-08-27T00:02:31Z","timestamp":1566864151000},"page":"532-548","source":"Crossref","is-referenced-by-count":185,"title":["Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2583-4314","authenticated-orcid":false,"given":"Minghui","family":"Liao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3153-8519","authenticated-orcid":false,"given":"Pengyuan","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6564-4796","authenticated-orcid":false,"given":"Cong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.143"},{"key":"ref72","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"wang","year":"2012","journal-title":"Proc 21st Int Conf Pattern Recognit"},{"key":"ref71","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref70","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","volume":"abs 1601 7140","author":"veit","year":"2016","journal-title":"CoRR"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_22"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/458"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.245"},{"key":"ref78","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref32","article-title":"Deep structured output learning for unconstrained text recognition","author":"jaderberg","year":"2015","journal-title":"Int Conf on Learning Representations"},{"key":"ref31","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","volume":"abs 1406 2227","author":"jaderberg","year":"2014","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_33"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"ref34","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0793-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.529"},{"key":"ref67","first-page":"35","article-title":"Accurate scene text recognition based on recurrent neural network","author":"su","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.016"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"ref2","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.331"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref25","first-page":"3501","article-title":"Reading scene text in deep convolutional sequences","author":"he","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00788"},{"key":"ref59","first-page":"569","article-title":"Recognizing text with perspective distortion in natural scenes","author":"quy phan","year":"2013","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref58","first-page":"127","article-title":"E2E-MLT-An unconstrained end-to-end method for multi-language scene text","author":"busta","year":"2018","journal-title":"Proc ACCV Workshops"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496234"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref55","first-page":"770","article-title":"A method for text localization and recognition in real-world images","author":"neumann","year":"2010","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref10","first-page":"935","article-title":"Total-text: A comprehensive dataset for scene text detection and recognition","author":"chng","year":"2017","journal-title":"Proc IAPR Int Conf Document Anal Recog"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546066"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref14","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref81","article-title":"DeepText: A unified framework for text proposal generation and text detection in natural images","volume":"abs 1605 7314","author":"zhong","year":"2016","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.04.027"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298914"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2878899"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00163"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.242"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref45","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref42","first-page":"4161","article-title":"TextBoxes: A fast text detector with a single deep neural network","author":"liao","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00619"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9317867\/08812908.pdf?arnumber=8812908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:21Z","timestamp":1652194161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8812908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,1]]},"references-count":82,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2937086","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,1]]}}}