{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:24:24Z","timestamp":1766298264147,"version":"3.37.3"},"reference-count":64,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Project for New Generation of AI","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61703049"],"award-info":[{"award-number":["61703049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province of China","doi-asserted-by":"publisher","award":["2019CFA022"],"award-info":[{"award-number":["2019CFA022"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3124313","type":"journal-article","created":{"date-parts":[[2021,11,5]],"date-time":"2021-11-05T19:20:58Z","timestamp":1636140058000},"page":"9321-9331","source":"Crossref","is-referenced-by-count":15,"title":["Video Text Tracking With a Spatio-Temporal Complementary Model"],"prefix":"10.1109","volume":"30","author":[{"given":"Yuzhe","family":"Gao","sequence":"first","affiliation":[]},{"given":"Xing","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jiajian","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6674-6484","authenticated-orcid":false,"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2560-0179","authenticated-orcid":false,"given":"Dian","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shenggao","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00956"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00788"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"ref31","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref30","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 (AAAI)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.87"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.371"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2797181"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2068553"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2015.06.002"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2198129"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.93"},{"key":"ref64","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.95"},{"key":"ref29","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2465169"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038520"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00102"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2695104"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351093"},{"key":"ref26","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 (ACCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.157"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref51","first-page":"1","article-title":"Siamese neural networks for one-shot image recognition","author":"koch","year":"2015","journal-title":"Proc ICML Deep Learn Workshop"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333727"},{"journal-title":"ICDAR Text in Video","year":"2020","author":"iwamura","key":"ref58"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref56","first-page":"17","article-title":"Performance measures and a data set for multi-target, multi-camera tracking","author":"ristani","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref55","article-title":"In defense of the triplet loss for person re-identification","author":"hermans","year":"2017","journal-title":"arXiv 1703 07737"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078516"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.527"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01044"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107901"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2554321"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0879-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/83.817607"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15702-8_36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4377101"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206051"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116563"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196577"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2666039"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2011.5711545"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001414550015"},{"key":"ref49","article-title":"Exploring simple Siamese representation learning","author":"chen","year":"2020","journal-title":"arXiv 2011 10566"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3026636"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2942506"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2839886"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2959256"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09605219.pdf?arnumber=9605219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:14Z","timestamp":1652194214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9605219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3124313","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2021]]}}}