{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:24:44Z","timestamp":1766298284563,"version":"3.37.3"},"reference-count":97,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2020.3038520","type":"journal-article","created":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T22:59:51Z","timestamp":1606172391000},"page":"822-837","source":"Crossref","is-referenced-by-count":24,"title":["FREE: A Fast and Robust End-to-End Video Text Spotter"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5732-1513","authenticated-orcid":false,"given":"Zhanzhan","family":"Cheng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7922-9921","authenticated-orcid":false,"given":"Jing","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Baorui","family":"Zou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4464-4644","authenticated-orcid":false,"given":"Liang","family":"Qiao","sequence":"additional","affiliation":[]},{"given":"Yunlu","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5269-7821","authenticated-orcid":false,"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Niu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1949-2768","authenticated-orcid":false,"given":"Shuigeng","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"335","article-title":"Gated recurrent convolution neural network for OCR","author":"wang","year":"2017","journal-title":"Proc NIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.368"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00619"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219861"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00150"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.529"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.12.011"},{"key":"ref29","article-title":"R2CNN: Rotational region CNN for orientation robust scene text detection","author":"jiang","year":"2017","journal-title":"arXiv 1706 09579"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601883"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.08.016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700788"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601835"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351044"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019070"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00922"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2554321"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333727"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116563"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.536"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4761548"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.243"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4377101"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.102"},{"key":"ref52","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 algorithm","volume":"25","author":"in kim","year":"2003","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00163"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.207"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351093"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref9","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00917"},{"key":"ref48","first-page":"83","article-title":"TextNet: Irregular text reading from images with an end-to-end trainable network","author":"sun","year":"2018","journal-title":"Proc ACCV"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00480"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00584"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443556"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_9"},{"key":"ref70","first-page":"2647","article-title":"Scene text detection in video by learning locally and globally","author":"tian","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.05.101"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00102"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.62"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00764-5_28"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2363167"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ASSPCC.2000.882463"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2273672"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3941-x"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2695104"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350868"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00299"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2011.5711545"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15702-8_36"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130221"},{"key":"ref2","first-page":"776","article-title":"Video text detection and recognition: Dataset and benchmark","author":"xuan nguyen","year":"2014","journal-title":"Proc IEEE Winter Conf Appl Comput Vis"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2014.6890248"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2013.0217"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref94","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"jaderberg","year":"2014","journal-title":"arXiv 1406 2227"},{"key":"ref93","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"veit","year":"2016","journal-title":"arXiv 1601 07140"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.57"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00335-y"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196577"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.110"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206051"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.06.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2068553"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2198129"},{"key":"ref14","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00562"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6864"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00128"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.009"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00248"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.09.010"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref89","first-page":"10","article-title":"A framework towards realtime detection and tracking of text","author":"merino","year":"2007","journal-title":"Proc CBDAR"},{"key":"ref85","first-page":"1","article-title":"Network in network","author":"lin","year":"2013","journal-title":"Proc ICLR"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09266586.pdf?arnumber=9266586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:58:22Z","timestamp":1642003102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9266586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":97,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.3038520","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2021]]}}}