{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:22Z","timestamp":1778048302035,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00419","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4305-4314","source":"Crossref","is-referenced-by-count":0,"title":["DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy"],"prefix":"10.1109","author":[{"given":"Jaewoo","family":"Song","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jooyoung","family":"Choi","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanghyun","family":"Baek","sequence":"additional","affiliation":[{"name":"IPAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangyub","family":"Lee","sequence":"additional","affiliation":[{"name":"IPAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daemin","family":"Park","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungroh","family":"Yoon","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref3","article-title":"Training-free regional prompting for diffusion transformers","author":"Chen","year":"2024"},{"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":"10.1007\/978-3-031-72630-9_25"},{"key":"ref7","article-title":"Textcrafter: Accurately rendering multiple texts in complex visual scenes","author":"Du","year":"2025"},{"key":"ref8","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref10","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01228"},{"key":"ref12","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref13","article-title":"Flux.1-dev","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.900"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_21"},{"key":"ref16","article-title":"Glyph-byt5-v2: A strong aesthetic baseline for accurate multilingual visual text rendering","author":"Liu","year":"2024"},{"key":"ref17","article-title":"Glyphdraw: Seamlessly rendering text with intricate spatial structures in text-to-image generation","author":"Ma","year":"2023"},{"key":"ref18","article-title":"Paddleocr","year":"2023"},{"key":"ref19","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"140","key":"ref21","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0157"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref26","article-title":"Anytext: Multilingual visual text generation and editing","author":"Tuo","year":"2023"},{"key":"ref27","article-title":"Textmastero: Mastering high-quality scene text editing in diverse languages and styles","author":"Wang","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02659"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02659"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01947"},{"key":"ref31","article-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels","author":"Wu","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1912"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4396"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_13"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01552"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11491999.pdf?arnumber=11491999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:35Z","timestamp":1778046815000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00419","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}