{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:24Z","timestamp":1774420044539,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888619","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["LocRef-Diffusion:Tuning-Free Layout and Appearance-Guided Generation"],"prefix":"10.1109","author":[{"given":"Fan","family":"Deng","sequence":"first","affiliation":[{"name":"MetaX,China"}]},{"given":"Yaguang","family":"Wu","sequence":"additional","affiliation":[{"name":"MetaX,China"}]},{"given":"Xinyang","family":"Yu","sequence":"additional","affiliation":[{"name":"MetaX,China"}]},{"given":"Xiangjun","family":"Huang","sequence":"additional","affiliation":[{"name":"MetaX,China"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"MetaX,China"}]},{"given":"Guangyu","family":"Yan","sequence":"additional","affiliation":[{"name":"MetaX,China"}]},{"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[{"name":"MetaX,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","author":"Schuhmann","year":"2021"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00355","article-title":"Adding Conditional Control to Text-to-Image Diffusion Models","author":"Zhang","year":"2023"},{"key":"ref3","article-title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","author":"Dahary","year":"2024"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00692","article-title":"DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception","author":"Wang","year":"2024"},{"key":"ref5","article-title":"Training-Free Layout Control with Cross-Attention Guidance","author":"Chen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28111"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref9","article-title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","author":"Ye","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref11","article-title":"InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation","author":"Wang","year":"2024"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00733","article-title":"High-fidelity Person-centric Subject-to-Image Synthesis","author":"Wang","year":"2024"},{"key":"ref13","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020"},{"key":"ref14","article-title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","author":"Ramesh","year":"2022"},{"key":"ref15","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01042","article-title":"High-Resolution Image Synthesis with Latent Diffusion Models","author":"Rombach","year":"2022"},{"key":"ref17","article-title":"In Proceedings of the 31st International Conference on International Conference on Machine Learning","author":"Rezende","year":"2014"},{"key":"ref18","article-title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","author":"Suvorov","year":"2021"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00651","article-title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","author":"Zhou","year":"2024"},{"key":"ref20","article-title":"StyleAlign: Analysis and Applications of Aligned StyleGAN Models","author":"Wu","year":"2022"},{"key":"ref21","article-title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","author":"Zheng","year":"2024"},{"key":"ref22","article-title":"GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation","author":"Chen","year":"2024"},{"key":"ref23","article-title":"Denoising Diffusion Implicit Models","author":"Song","year":"2022"},{"key":"ref24","article-title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","author":"Wang","year":"2024"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888619.pdf?arnumber=10888619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:06Z","timestamp":1774416366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888619","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}