{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:35:57Z","timestamp":1771014957971,"version":"3.50.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC3602601"],"award-info":[{"award-number":["2022YFC3602601"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Zhejiang Province of China","doi-asserted-by":"publisher","award":["2021C02037"],"award-info":[{"award-number":["2021C02037"]}],"id":[{"id":"10.13039\/501100019091","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tcsvt.2024.3454331","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:32:43Z","timestamp":1725474763000},"page":"534-546","source":"Crossref","is-referenced-by-count":4,"title":["A Bilingual, Open World Video Text Dataset and Real-Time Video Text Spotting With Contrastive Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-7212","authenticated-orcid":false,"given":"Weijia","family":"Wu","sequence":"first","affiliation":[{"name":"College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3870-4275","authenticated-orcid":false,"given":"Zhuang","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8041-012X","authenticated-orcid":false,"given":"Yuanqiang","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1314-8883","authenticated-orcid":false,"given":"Hong","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7681-2166","authenticated-orcid":false,"given":"Mike","family":"Zheng Shou","sequence":"additional","affiliation":[{"name":"Department of Electrical & Computer Engineering, National University of Singapore, Queenstown, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01369-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2003.10.012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2011.21"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.378"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110818"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00956"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3871897"},{"key":"ref14","article-title":"TextCohesion: Detecting text for arbitrary shapes","author":"Wu","year":"2019","journal-title":"arXiv:1904.12640"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897699"},{"key":"ref16","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. 32nd Int. Conf. Int. Conf. Mach. Learn","volume":"37","author":"Srivastava"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2008.922938"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2305515"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3110990"},{"key":"ref21","article-title":"Contrastive learning of semantic and visual representations for text tracking","author":"Li","year":"2021","journal-title":"arXiv:2112.14976"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00174"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.207"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038520"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351093"},{"key":"ref26","article-title":"A bilingual, OpenWorld video text dataset and end-to-end video text spotter with transformer","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Wu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2695104"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443556"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2014.6836024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196577"},{"key":"ref32","article-title":"BDD100K: A diverse driving dataset for heterogeneous multitask learning","author":"Yu","year":"2018","journal-title":"arXiv:1805.04687"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_18"},{"key":"ref39","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst","volume":"28","author":"Ren"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095916"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2554321"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2198129"},{"key":"ref43","article-title":"End-to-end video text spotting with transformer","author":"Wu","year":"2022","journal-title":"arXiv:2203.10539"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.841653"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2014.6890248"},{"key":"ref46","article-title":"ICDAR 2015 text reading in the wild competition","author":"Zhou","year":"2015","journal-title":"arXiv:1506.03184"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/76.999203"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116563"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00262"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41679-8_23"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110177"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref55","article-title":"Semi-TCL: Semi-supervised track contrastive representation learning","author":"Li","year":"2021","journal-title":"arXiv:2107.02396"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225754"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00229"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083257"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076097"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref67","first-page":"54683","article-title":"DatasetDM: Synthesizing data with perception annotations using diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"36","author":"Wu"},{"key":"ref68","article-title":"Paragraph-to-image generation with information-enriched diffusion model","author":"Wu","year":"2023","journal-title":"arXiv:2311.14284"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048680"},{"key":"ref70","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref76","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Annu. Conf. Neural Inf. Process. Syst","volume":"28","author":"Jaderberg"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2249082"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3124313"},{"key":"ref79","first-page":"334","article-title":"Gated recurrent convolution neural network for OCR","volume-title":"Proc. Neural Inf. Process. Syst","author":"Wang"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10857816\/10664465.pdf?arnumber=10664465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T05:46:20Z","timestamp":1738215980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10664465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":79,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3454331","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}