{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:40:18Z","timestamp":1770846018673,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"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":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342862","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"6371-6376","source":"Crossref","is-referenced-by-count":0,"title":["RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Geon","family":"Park","sequence":"first","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seon Bin","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gunho","family":"Jung","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Ramesh"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.902945"},{"key":"ref6","article-title":"Text2Layer: Layered image generation using latent diffusion model","author":"Zhang","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref8","first-page":"2937","article-title":"Deep reinforcement learning in continuous action spaces: a case study in the game of simulated curling","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Lee"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00160"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00591"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3122969"},{"key":"ref14","article-title":"Auto-encoding variational bayes","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2007.01.033"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/5326.760572"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref22","first-page":"1737","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Bar-Tal"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref25","article-title":"Decoupled weight decay regularization","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref27","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":"Adv. Neural Inf. Process. Syst. (NeurIPS)"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342862.pdf?arnumber=11342862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:52:22Z","timestamp":1770843142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342862\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342862","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}