{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T20:29:03Z","timestamp":1783628943622,"version":"3.55.0"},"reference-count":59,"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":[{"name":"National Key R&D Program of China","award":["2017YFC0803700"],"award-info":[{"award-number":["2017YFC0803700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61602459"],"award-info":[{"award-number":["61602459"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61572138"],"award-info":[{"award-number":["61572138"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"crossref","award":["17511101902"],"award-info":[{"award-number":["17511101902"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"crossref","award":["16JC1420400"],"award-info":[{"award-number":["16JC1420400"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/tmm.2018.2818020","type":"journal-article","created":{"date-parts":[[2018,3,23]],"date-time":"2018-03-23T18:15:44Z","timestamp":1521828944000},"page":"3111-3122","source":"Crossref","is-referenced-by-count":1243,"title":["Arbitrary-Oriented Scene Text Detection via Rotation Proposals"],"prefix":"10.1109","volume":"20","author":[{"given":"Jianqi","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5939-4708","authenticated-orcid":false,"given":"Weiyuan","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5590-9292","authenticated-orcid":false,"given":"Yingbin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2547588"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2004.02.006"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref31","first-page":"3304","article-title":"End-to-end text recognition with\n convolutional neural networks","author":"wang","year":"0","journal-title":"Proc Int Conf Pattern Recognit"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.19"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.388"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472154"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.296"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.1109\/TPAMI.2003.1251157","article-title":"Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift\n algorithm","volume":"25","author":"kim","year":"2003","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref29","first-page":"366","article-title":"Detecting and reading text in natural scenes","volume":"2","author":"chen","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref2","article-title":"Integrating scene text and visual appearance for\n fine-grained image classification with convolutional neural networks","author":"bai","year":"2017","journal-title":"arXiv 1704 04613"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2638622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref21","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"yao","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref24","article-title":"A survey of text detection and recognition in images and videos","author":"chen","year":"2000"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1007\/978-0-85729-859-1_28","article-title":"Text localization and recognition in images and video","author":"uchida","year":"2014","journal-title":"Handbook of Document Image Processing and Recognition"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2003.10.012"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.210"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.368"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388210"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.514"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","article-title":"Robust text detection in natural scene\n images","volume":"36","author":"yin","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"ref10","first-page":"512","article-title":"Deep\n features for text spotting","author":"jaderberg","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref11","first-page":"497","article-title":"Robust scene\n text detection with convolution neural network induced MSER trees","author":"huang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443556"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.528"},{"key":"ref14","article-title":"Improving text proposals for scene images with\n fully convolutional networks","author":"bazazian","year":"2017","journal-title":"arXiv 1702 05089"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2625259"},{"key":"ref16","first-page":"4161","article-title":"Textboxes: A fast text detector with a single deep neural network","author":"liao","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref18","article-title":"Scene text detection via holistic, multi-channel prediction","author":"yao","year":"2016","journal-title":"arXiv 1606 09002"},{"key":"ref19","article-title":"Accurate text localization in natural image with\n cascaded convolutional text network","author":"he","year":"2016","journal-title":"arXiv 1603 09423"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2177646"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2554321"},{"key":"ref6","first-page":"366","article-title":"Detecting and reading text in natural scenes","author":"chen","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2154317"},{"key":"ref8","first-page":"770","article-title":"A method for text localization and recognition in real-world images","volume":"6494","author":"neumann","year":"0","journal-title":"Proc 10th Asian Conf Comp Vis LNCS"},{"key":"ref7","first-page":"591","article-title":"Word spotting in the wild","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0196-6774(87)90020-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref46","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019461"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref47","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref42","first-page":"56","article-title":"Detecting text in natural image with connectionist text proposal network","author":"tian","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref44","article-title":"Face detection with the faster R-CNN","author":"jiang","year":"2016","journal-title":"arXiv 1606 03473"},{"key":"ref43","article-title":"Deeptext: A unified framework for text\n proposal generation and text detection in natural images","author":"zhong","year":"2016","journal-title":"arXiv 1605 07314"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8491746\/08323240.pdf?arnumber=8323240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T22:07:06Z","timestamp":1643234826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8323240\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":59,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2818020","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}