{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:17:49Z","timestamp":1780463869280,"version":"3.54.1"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32341012,62172103"],"award-info":[{"award-number":["32341012,62172103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01622","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17464-17473","source":"Crossref","is-referenced-by-count":1,"title":["TextSSR: Diffusion-Based Data Synthesis for Scene Text Recognition"],"prefix":"10.1109","author":[{"given":"Xingsong","family":"Ye","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongkun","family":"Du","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunbo","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhineng","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00313"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2753"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref7","article-title":"An image is worth $16\\times 16$ words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/124"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3545453"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3525526"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01874"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1916"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00512"},{"key":"ref18","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","volume-title":"Workshop on Deep Learning, NeurIPS","author":"Jaderberg","year":"2014"},{"key":"ref19","article-title":"Improving diffusion models for scene text editing with dual encoders","author":"Ji","year":"2024","journal-title":"TMLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01878"},{"key":"ref21","first-page":"1484","article-title":"ICDAR2013 robust reading competition","author":"Karatzas","year":"2013","journal-title":"ICDAR"},{"key":"ref22","first-page":"1156","article-title":"ICDAR2015 competition on robust reading","author":"Karatzas","year":"2015","journal-title":"ICDAR"},{"key":"ref23","article-title":"PP-OCRv3: More attempts for the improvement of ultra lightweight ocr system","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"ref25","article-title":"Unrealtext: Synthesizing realistic scene text images from the unreal world","volume-title":"CVPR","author":"Long","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25305"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01479"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00130"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.233"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"ref41","article-title":"AnyText: Multilingual visual text generation and editing","volume-title":"ICLR","author":"Tuo","year":"2024"},{"key":"ref42","article-title":"COCO-Text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2011.6126402"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3197981"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02659"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28402"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350929"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02676"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01471"},{"key":"ref50","first-page":"44050","article-title":"GlyphControl: Glyph conditional control for visual text generation","author":"Yang","year":"2023","journal-title":"NeurIPS"},{"key":"ref51","first-page":"138569","article-title":"TextCtrl: Diffusion-based scene text editing with prior guidance control","author":"Zeng","year":"2024","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3005-5_43"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_16"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3017632"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28575"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_13"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01880-0"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01368"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_6"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444647.pdf?arnumber=11444647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:41Z","timestamp":1777611221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01622","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}