{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:56:12Z","timestamp":1779346572914,"version":"3.51.4"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["19K12033"],"award-info":[{"award-number":["19K12033"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["22H00540"],"award-info":[{"award-number":["22H00540"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3326685","type":"journal-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T18:08:28Z","timestamp":1698430108000},"page":"5837-5851","source":"Crossref","is-referenced-by-count":10,"title":["A Scene-Text Synthesis Engine Achieved Through Learning From Decomposed Real-World Data"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2011-8105","authenticated-orcid":false,"given":"Zhengmi","family":"Tang","sequence":"first","affiliation":[{"name":"Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5205-0542","authenticated-orcid":false,"given":"Tomo","family":"Miyazaki","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7706-9995","authenticated-orcid":false,"given":"Shinichiro","family":"Omachi","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00077"},{"key":"ref15","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"ref58","first-page":"234","article-title":"Adversarial Image Composition with Auxiliary Illumination","author":"zhan","year":"2020","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref52","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume":"4","author":"kingma","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.157"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2273672"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01080"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86337-1_8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3125260"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01471"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350929"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00924"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.06.023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00033"},{"key":"ref49","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"wang","year":"2012","journal-title":"Proc Int Conf Pattern Recognit (ICPR)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19318-7_60"},{"key":"ref7","first-page":"366","article-title":"Detecting and reading text in natural scenes","author":"chen","year":"2004","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.226"},{"key":"ref4","first-page":"5488","article-title":"UnrealText: Synthesizing realistic scene text images from the unreal world","author":"long","year":"2020","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2737-0"},{"key":"ref6","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1","article-title":"A learning-based text synthesis engine for scene text detection","author":"yang","year":"2019","journal-title":"Proc 30th Br Mach Vis Conf"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.299"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00985"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778862"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00377"},{"key":"ref36","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141934"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2016.163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0579-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185578"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_16"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00861"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01555-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5424"},{"key":"ref67","first-page":"935","article-title":"Total-text: A comprehensive dataset for scene text detection and recognition","volume":"1","author":"ch\u2019ng","year":"2017","journal-title":"Proc 14th IAPR Int Conf Document Anal Recognit (ICDAR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3167919"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref63","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1179352.1141933"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/38.946629"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185580"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018859"},{"key":"ref61","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"arXiv 1405 0312"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10299591.pdf?arnumber=10299591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:43:53Z","timestamp":1700509433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10299591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3326685","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}