{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:44Z","timestamp":1777865384510,"version":"3.51.4"},"reference-count":47,"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\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072386"],"award-info":[{"award-number":["62072386"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["242300420680"],"award-info":[{"award-number":["242300420680"]}],"id":[{"id":"10.13039\/501100006407","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\/iccv51701.2025.01850","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19893-19902","source":"Crossref","is-referenced-by-count":2,"title":["OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography"],"prefix":"10.1109","author":[{"given":"Caoshuo","family":"Li","sequence":"first","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zengmao","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer & Information Engineering, Anyang Normal University,Key Laboratory of Oracle Bone Inscriptions Information Processing, Ministry of Education of China,Anyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobin","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer & Information Engineering, Anyang Normal University,Key Laboratory of Oracle Bone Inscriptions Information Processing, Ministry of Education of China,Anyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghao","family":"Luo","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"AndyPian","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent Digital Culture Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Digital Culture Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taisong","family":"Jin","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"SevenShu","sequence":"additional","affiliation":[{"name":"Tencent Digital Culture Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunsheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongge","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer & Information Engineering, Anyang Normal University,Key Laboratory of Oracle Bone Inscriptions Information Processing, Ministry of Education of China,Anyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230302"},{"key":"ref5","article-title":"Obi-bench: Can lmms aid in study of ancient script on oracle bones?","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Region-aware text-to-image generation via hard binding and soft refinement","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"issue":"793\u2013800","key":"ref7","first-page":"1","article-title":"Sur la sphere vide. Izv. Akad. Nauk SSSR","volume":"7","author":"Delaunay","year":"1934","journal-title":"Otdelenie Matematicheskii i Estestvennyka Nauk"},{"key":"ref8","article-title":"Textcrafter: Accurately rendering multiple texts in complex visual scenes","author":"Du","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref10","author":"Feng","year":"2023","journal-title":"Layoutgpt: Compositional visual planning and generation with large language models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0376"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/sym14040743"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.831"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref15","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_44"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16446-0_38"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_23"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3592123"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00027"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612534"},{"key":"ref24","author":"Li","year":"2022","journal-title":"Does unsupervised grammar induction need pixels?"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_16"},{"key":"ref26","first-page":"1","article-title":"Differentiable vector graphics rasterization for editing and learning","author":"Li","year":"2020","journal-title":"ACM Transactions on Graphics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref28","author":"Lian","journal-title":"Llm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models"},{"key":"ref29","author":"Nichol","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref31","author":"Poole","journal-title":"Dreamfusion: Text-to3d using 2d diffusion"},{"key":"ref32","author":"Poole","journal-title":"Dreamfusion: Text-to3d using 2d diffusion"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01203"},{"key":"ref34","author":"Ramesh","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.17816\/ptors34150-21621"},{"key":"ref37","author":"Saharia","journal-title":"Photorealistic text-to-image diffusion models with deep language understanding"},{"key":"ref38","article-title":"Align and surpass human camouflaged perception: Visual refocus reinforcement fine-tuning","author":"Shen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00041"},{"key":"ref40","volume-title":"Chinese pictograph dictionary","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3165989"},{"key":"ref42","author":"Xie","journal-title":"Visorgpt: Learning visual prior via generative pretraining"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0698"},{"key":"ref45","author":"Zhang","journal-title":"Controllable text-to-image generation with gpt-4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/357994.358023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i28.35383"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01742"}],"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\/11444851.pdf?arnumber=11444851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:28Z","timestamp":1777530208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01850","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}