{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T03:19:25Z","timestamp":1761621565069,"version":"3.37.3"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61772330","61533012","61876109"],"award-info":[{"award-number":["61772330","61533012","61876109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Key Laboratory of Crime Scene Evidence","award":["2017XCWZK01"],"award-info":[{"award-number":["2017XCWZK01"]}]},{"DOI":"10.13039\/501100004921","name":"Interdisciplinary Program of Shanghai Jiao Tong University","doi-asserted-by":"publisher","award":["YG2019QNA09"],"award-info":[{"award-number":["YG2019QNA09"]}],"id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3057108","type":"journal-article","created":{"date-parts":[[2021,2,6]],"date-time":"2021-02-06T01:21:27Z","timestamp":1612574487000},"page":"26431-26441","source":"Crossref","is-referenced-by-count":5,"title":["A Robust and Effective Text Detector Supervised by Contrastive Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1191-2972","authenticated-orcid":false,"given":"Ran","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaoyi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ze","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongtao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nengbin","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuejun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"DeepText: A unified framework for text proposal generation and text detection in natural images","author":"zhong","year":"2016","journal-title":"arXiv 1605 07314"},{"key":"ref38","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.95"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-015-4488-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-859-1_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref36","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref34","first-page":"512","article-title":"Deep features for text spotting","author":"jaderberg","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929819"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007351"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2999069"},{"key":"ref28","article-title":"Scene text detection via holistic, multi-channel prediction","author":"yao","year":"2016","journal-title":"arXiv 1606 09002"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.126"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"ref2","first-page":"489","article-title":"Locating characters in scene images using frequency features","author":"sin","year":"2002","journal-title":"Object Recognition Supported by User Interaction for Service Robots"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388210"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref24","first-page":"752","article-title":"Large-lexicon attribute-consistent text recognition in natural images","author":"novikova","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref25","first-page":"497","article-title":"Robust scene text detection with convolution neural network induced MSER trees","author":"huang","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.331"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.529"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref57","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":"ref56","first-page":"20","article-title":"Textsnake: A flexible representation for detecting text of arbitrary shapes","author":"long","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref55","article-title":"PixelLink: Detecting scene text via instance segmentation","volume":"32","author":"deng","year":"2018","journal-title":"Proc AAAI"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00853"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967274"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.368"},{"key":"ref11","article-title":"TextBoxes: A fast text detector with a single deep neural network","author":"liao","year":"2016","journal-title":"arXiv 1611 06779"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref14","first-page":"56","article-title":"Detecting text in natural image with connectionist text proposal network","author":"tian","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref19","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"arXiv 2002 05709"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.04.031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/34.845381"},{"key":"ref6","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.157"},{"key":"ref49","article-title":"R2CNN: Rotational region CNN for orientation robust scene text detection","author":"jiang","year":"2017","journal-title":"arXiv 1706 09579"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e89-d.3.1221"},{"key":"ref46","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2019","journal-title":"arXiv 1908 03265"},{"key":"ref45","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"arXiv 1912 01703"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref47","first-page":"9597","article-title":"Lookahead optimizer: K steps forward, 1 step back","author":"zhang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref41","first-page":"649","article-title":"Colorful image colorization","author":"zhang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref43","article-title":"Learning deep representations by mutual information estimation and maximization","author":"devon hjelm","year":"2018","journal-title":"arXiv 1808 06670"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09347431.pdf?arnumber=9347431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T15:48:08Z","timestamp":1643212088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9347431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3057108","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}