{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:11:10Z","timestamp":1743073870977,"version":"3.40.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council of Taiwan","doi-asserted-by":"publisher","award":["NSTC-112-2628-E-002-033-MY4,NSTC-113-2634-F-002-001-MBK"],"award-info":[{"award-number":["NSTC-112-2628-E-002-033-MY4,NSTC-113-2634-F-002-001-MBK"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006477","name":"National Taiwan University","doi-asserted-by":"publisher","award":["114L900901\/114L900902\/114L900903"],"award-info":[{"award-number":["114L900901\/114L900902\/114L900903"]}],"id":[{"id":"10.13039\/501100006477","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,11]]},"DOI":"10.1109\/icce63647.2025.10929885","type":"proceedings-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:16:58Z","timestamp":1743041818000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["A Taiwanese Street Scene Data Augmentation Method Based on Diffusion Model for Layout - to- Image Generation"],"prefix":"10.1109","author":[{"given":"Rou-An","family":"Chen","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Huang","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv","author":"Podell","year":"2023"},{"key":"ref5","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv"},{"key":"ref6","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"I CML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3447239"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240546"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2557642.2563669"},{"key":"ref13","article-title":"Realcompo: Dynamic equilibrium between realism and compositionality improves text-to-image diffusion models","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref14","article-title":"Self-correcting 11m-controlled diffusion models","author":"Wu","year":"2024","journal-title":"CVPR"},{"key":"ref15","article-title":"LIm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2023","journal-title":"ar Xiv"},{"key":"ref16","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms","author":"Yang","year":"2024","journal-title":"ICML"},{"key":"ref17","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","author":"Feng","year":"2024","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref19","article-title":"Layoutllm-t2i: Eliciting layout guidance from 11m for text-to-image generation","author":"Qu","year":"2023","journal-title":"ACM MM"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-016-0151-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_17"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3657282"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28696"},{"key":"ref24","article-title":"Defect spectrum: A granular look of large-scale defect datasets with rich semantics","author":"Yang","year":"2023","journal-title":"arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"event":{"name":"2025 IEEE International Conference on Consumer Electronics (ICCE)","start":{"date-parts":[[2025,1,11]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2025,1,14]]}},"container-title":["2025 IEEE International Conference on Consumer Electronics (ICCE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10929765\/10929768\/10929885.pdf?arnumber=10929885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:12:07Z","timestamp":1743070327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10929885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icce63647.2025.10929885","relation":{},"subject":[],"published":{"date-parts":[[2025,1,11]]}}}