{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:35:35Z","timestamp":1787013335639,"version":"build-2736575974"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62522105"],"award-info":[{"award-number":["62522105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176038"],"award-info":[{"award-number":["62176038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3599520","type":"journal-article","created":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T18:20:42Z","timestamp":1755282042000},"page":"11834-11847","source":"Crossref","is-referenced-by-count":6,"title":["Remote Sensing Image Generation via Object Text Decoupling"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7463-6103","authenticated-orcid":false,"given":"Wenda","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhepu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4826-2769","authenticated-orcid":false,"given":"Fan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Physics and Electronic Technology, Liaoning Normal University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4201-1122","authenticated-orcid":false,"given":"Haipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Unit 92728 of PLA, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6111-340X","authenticated-orcid":false,"given":"You","family":"He","sequence":"additional","affiliation":[{"name":"Research Institute of Information Fusion, Naval Aviation University, Yantai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"ref3","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref5","article-title":"Controllable generation with text-to-image diffusion models: A survey","author":"Cao","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3383473"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3367349"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3369178"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363054"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3453414"},{"key":"ref14","article-title":"DiffusionSat: A generative foundation model for satellite imagery","author":"Khanna"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3507010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00051"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3323799"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3068391"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3268331"},{"key":"ref20","article-title":"SatDM: Synthesizing realistic satellite image with semantic layout conditioning using diffusion models","author":"Baghirli","year":"2023"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-10363-3"},{"key":"ref24","article-title":"Hopfield networks is all you need","author":"Ramsauer","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00342"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref28","first-page":"30105","article-title":"StyleGAN-T: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sauer"},{"key":"ref29","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref30","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref31","first-page":"16890","article-title":"CogView2: Faster and better text-to-image generation via hierarchical transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref32","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref33","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305243"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298721"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3331275"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00187"},{"key":"ref43","article-title":"Compose and conquer: Diffusion-based 3D depth aware composable image synthesis","author":"Lee","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00455"},{"key":"ref46","first-page":"30146","article-title":"BLIP-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref50","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref51","article-title":"CC-Diff: Enhancing contextual coherence in remote sensing image synthesis","author":"Zhang","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref55","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref56","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref58","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3378777"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3347329"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11126950.pdf?arnumber=11126950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:21Z","timestamp":1762455201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11126950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":61,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3599520","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}