{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T18:37:24Z","timestamp":1775932644603,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61411136002"],"award-info":[{"award-number":["61411136002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61633021"],"award-info":[{"award-number":["61633021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/tip.2018.2855399","type":"journal-article","created":{"date-parts":[[2018,7,12]],"date-time":"2018-07-12T19:05:00Z","timestamp":1531422300000},"page":"5406-5419","source":"Crossref","is-referenced-by-count":96,"title":["Multi-Oriented and Multi-Lingual Scene Text Detection With Direct Regression"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-5720","authenticated-orcid":false,"given":"Wenhao","family":"He","sequence":"first","affiliation":[]},{"given":"Xu-Yao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.528"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref32","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2010.5651862"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.04.002"},{"key":"ref36","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.233"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/TIP.2010.2070803","article-title":"A hybrid approach to detect and localize texts in natural scene images","volume":"20","author":"pan","year":"2011","journal-title":"IEEE Trans Image Process"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116200"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref20","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref21","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.368"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref26","author":"ma","year":"2017","journal-title":"Arbitrary-oriented scene text detection via rotation proposals"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref51","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","volume":"8693","author":"zitnick","year":"2014","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2547588"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.156"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref13","author":"huang","year":"2015","journal-title":"Densebox Unifying landmark localization with end to end object detection"},{"key":"ref14","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.514"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.98"},{"key":"ref4","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.388"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2300479"},{"key":"ref8","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref49","author":"zhong","year":"2016","journal-title":"Deeptext A unified framework for text proposal generation and text detection in natural images"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","article-title":"Robust text detection in natural scene images","volume":"36","author":"yin","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388210"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298871"},{"key":"ref42","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"yao","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.04.005"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref43","author":"yao","year":"2016","journal-title":"Scene text detection via holistic multi-channel prediction"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8421670\/08410577.pdf?arnumber=8410577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:29:26Z","timestamp":1642004966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8410577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":51,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tip.2018.2855399","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}