{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:13:23Z","timestamp":1778530403852,"version":"3.51.4"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2023YFF0905400"],"award-info":[{"award-number":["2023YFF0905400"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376102"],"award-info":[{"award-number":["62376102"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3656228","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:41:28Z","timestamp":1768941688000},"page":"7050-7064","source":"Crossref","is-referenced-by-count":0,"title":["SceneVTG++: Controllable Multilingual Visual Text Generation in the Wild"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6100-4000","authenticated-orcid":false,"given":"Jiawei","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3206-5347","authenticated-orcid":false,"given":"Feiyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2343-7750","authenticated-orcid":false,"given":"Zhibo","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyang","family":"Lin","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6732-7823","authenticated-orcid":false,"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4582-7488","authenticated-orcid":false,"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref6","article-title":"UnrealText: Synthesizing realistic scene text images from the unreal world","author":"Long","year":"2020","journal-title":"arXiv:2003.10608"},{"key":"ref7","first-page":"14205","article-title":"Denoising diffusion implicit models","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref8","article-title":"TextDiffuser-2: Unleashing the power of language models for text rendering","author":"Chen","year":"2023","journal-title":"arXiv:2311.16465"},{"key":"ref9","first-page":"20307","article-title":"AnyText: Multilingual visual text generation and editing","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Tuo"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2963663"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00999"},{"key":"ref13","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3326685"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/692"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615028"},{"key":"ref21","first-page":"43852","article-title":"LayoutPrompter: Awaken the design ability of large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref22","article-title":"PosterLlama: Bridging design ability of langauge model to contents-aware layout generation","author":"Seol","year":"2024","journal-title":"arXiv:2404.00995"},{"key":"ref23","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv:1411.1784"},{"key":"ref24","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sohn"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref27","first-page":"13753","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref28","first-page":"44050","article-title":"GlyphControl: Glyph conditional control for visual text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_21"},{"key":"ref30","article-title":"Glyph-ByT5-v2: A strong aesthetic baseline for accurate multilingual visual text rendering","author":"Liu","year":"2024","journal-title":"arXiv:2406.10208"},{"key":"ref31","article-title":"How control information influences multilingual text image generation and editing?","author":"Zhang","year":"2024","journal-title":"arXiv:2407.11502"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3151477"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28482"},{"key":"ref34","first-page":"14324","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Couairon"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3382484"},{"key":"ref36","article-title":"Lenna: Language enhanced reasoning detection assistant","author":"Wei","year":"2023","journal-title":"arXiv:2312.02433"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref39","article-title":"PP-OCRv3: More attempts for the improvement of ultra lightweight OCR system","author":"Li","year":"2022","journal-title":"arXiv:2206.03001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018859"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.233"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_24"},{"key":"ref48","article-title":"DiffBIR: Towards blind image restoration with generative diffusion prior","author":"Lin","year":"2023","journal-title":"arXiv:2308.15070"},{"key":"ref49","article-title":"Detecting curve text in the wild: New dataset and new solution","author":"Liu","year":"2017","journal-title":"arXiv:1712.02170"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00334-z"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41679-8_28"},{"key":"ref55","first-page":"1","article-title":"Uber-text: A large-scale dataset for optical character recognition from street-level imagery","volume-title":"Proc. SUNw, Scene Understand. Workshop (CVPR)","author":"Zhang"},{"key":"ref56","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":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref59","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11359242.pdf?arnumber=11359242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:57Z","timestamp":1778528937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":62,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3656228","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}