{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:46:38Z","timestamp":1780494398858,"version":"3.54.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":"crossref","award":["62225208"],"award-info":[{"award-number":["62225208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62450046"],"award-info":[{"award-number":["62450046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62406304"],"award-info":[{"award-number":["62406304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176260"],"award-info":[{"award-number":["62176260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"General Program of China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M743442"],"award-info":[{"award-number":["2023M743442"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZB20240730"],"award-info":[{"award-number":["GZB20240730"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3616376","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:37Z","timestamp":1759772197000},"page":"1-16","source":"Crossref","is-referenced-by-count":2,"title":["CC-Diff++: Spatially Controllable Text-to-Image Synthesis for Remote Sensing With Enhanced Contextual Coherence"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0642-761X","authenticated-orcid":false,"given":"Mu","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8929-4866","authenticated-orcid":false,"given":"Yunfan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2425-6786","authenticated-orcid":false,"given":"Yuzhong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00257"},{"key":"ref2","first-page":"47706","article-title":"Do generated data always help contrastive learning?","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01290"},{"key":"ref4","article-title":"AeroGen: Enhancing remote sensing object detection with diffusion-driven data generation","author":"Tang","year":"2024","journal-title":"arXiv:2411.15497"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3323799"},{"key":"ref6","first-page":"19539","article-title":"Diffusionsat: A generative foundation model for satellite imagery","volume-title":"Proc. ICLR","author":"Khanna"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3453414"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-10363-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3268331"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3556386"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3556276"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01547"},{"key":"ref16","first-page":"8815","article-title":"Samrs: Scaling-up remote sensing segmentation dataset with segment anything model","volume-title":"Proc. NeurIPS","volume":"36","author":"Wang"},{"key":"ref17","first-page":"73299","article-title":"What a mess: Multi-domain evaluation of zero-shot semantic segmentation","volume-title":"Proc. NeurIPS","volume":"36","author":"Blumenstiel"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref21","article-title":"MIGC+: Advanced multi-instance generation controller for image synthesis","author":"Zhou","year":"2024","journal-title":"arXiv:2407.02329"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2016.2565705"},{"key":"ref25","article-title":"CC-diff: Enhancing contextual coherence in remote sensing image synthesis","author":"Zhang","year":"2024","journal-title":"arXiv:2412.08464"},{"key":"ref26","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. ICML","author":"Reed"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref29","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. ICML","author":"Ramesh"},{"key":"ref30","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. NeurIPS","volume":"34","author":"Ding"},{"key":"ref31","first-page":"1","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume-title":"Proc. TMLR","author":"Yu"},{"key":"ref32","first-page":"4055","article-title":"Muse: Text-to-image generation via masked generative transformers","volume-title":"Proc. ICML","volume":"202","author":"Chang"},{"key":"ref33","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref34","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref35","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref37","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"issue":"140","key":"ref38","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. ICML","volume":"162","author":"Nichol"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01063"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078577"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref47","first-page":"846","article-title":"Geodiffusion: Text-prompted geometric control for object detection data generation","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref48","article-title":"IFAdapter: Instance feature control for grounded text-to-image generation","author":"Wu","year":"2024","journal-title":"arXiv:2409.08240"},{"key":"ref49","first-page":"1","article-title":"Generate your own scotland: Satellite image generation conditioned on maps","volume-title":"Proc. NeurIPS Workshop","author":"Espinosa"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00051"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3578309"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00340"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3407111"},{"key":"ref58","volume-title":"Chatgpt","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612012"},{"key":"ref60","first-page":"6048","article-title":"Visual programming for step-by-step text-to-image generation and evaluation","volume-title":"Proc. NeurIPS","volume":"36","author":"Cho"},{"key":"ref61","article-title":"Zero-shot text-guided infinite image synthesis with LLM guidance","author":"Kwon","year":"2024","journal-title":"arXiv:2407.12642"},{"key":"ref62","article-title":"Divide and conquer: Language models can plan and self-correct for compositional text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv:2401.15688"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref64","first-page":"1","article-title":"LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","volume-title":"Proc. TMLR","author":"Lian"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref66","first-page":"1","article-title":"Dinov2: Learning robust visual features without supervision","volume":"1","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res. J."},{"key":"ref67","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32831"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref71","first-page":"4061","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref72","first-page":"1","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NeurIPS","volume":"30","author":"Heusel"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref74","volume-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01271"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01300"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11187367.pdf?arnumber=11187367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:40:06Z","timestamp":1760463606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11187367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3616376","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}