{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:25:25Z","timestamp":1792513525941,"version":"4.5.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222616","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T13:58:31Z","timestamp":1694440711000},"page":"995-999","source":"Crossref","is-referenced-by-count":8,"title":["Training-Free Location-Aware Text-to-Image Synthesis"],"prefix":"10.1109","author":[{"given":"Jiafeng","family":"Mao","sequence":"first","affiliation":[{"name":"The University of Tokyo,Dept. of Information and Communication Eng."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueting","family":"Wang","sequence":"additional","affiliation":[{"name":"CyberAgent, Inc.,AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","author":"balaji","year":"2022"},{"key":"ref12","article-title":"Benchmark for compositional text-to-image synthesis","author":"park","year":"2021","journal-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)"},{"key":"ref15","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015 18th International Conference Munich Germany October 5-9 2015 Proceedings Part III 18"},{"key":"ref14","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Prompt-to-prompt image editing with cross attention control","author":"hertz","year":"2022"},{"key":"ref10","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"feng","year":"2022"},{"key":"ref2","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref16","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Computer Vision–ECCV 2014 13th European Conference Zurich Switzerland September 6-12 2014 Proceedings Part V 13"},{"key":"ref19","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"You only learn one representation: Unified network for multiple tasks","author":"wang","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref7","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"nichol","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref9","article-title":"Imagic: Text-based real image editing with diffusion models","author":"kawar","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","article-title":"Denoising diffusion implicit models","author":"song","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref6","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","author":"nichol","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"Hierarchical text-conditional image generation with clip latents","author":"ramesh","year":"2022"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222616.pdf?arnumber=10222616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T11:06:00Z","timestamp":1701255960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222616","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}