{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:37:18Z","timestamp":1772041038730,"version":"3.50.1"},"reference-count":69,"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":"publisher","award":["62125102"],"award-info":[{"award-number":["62125102"]}],"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":["623B2013"],"award-info":[{"award-number":["623B2013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JL23005"],"award-info":[{"award-number":["JL23005"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535343","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T14:20:10Z","timestamp":1738246810000},"page":"4494-4507","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Image Harmonization With Generative Model Prior"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0031-8417","authenticated-orcid":false,"given":"Jianqi","family":"Chen","sequence":"first","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3633-7038","authenticated-orcid":false,"given":"Yilan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1774-552X","authenticated-orcid":false,"given":"Zhengxia","family":"Zou","sequence":"additional","affiliation":[{"name":"Department of Guidance, Navigation and Control, School of Astronautics, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0483-1306","authenticated-orcid":false,"given":"Keyan","family":"Chen","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4772-3172","authenticated-orcid":false,"given":"Zhenwei","family":"Shi","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_20"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_18"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_40"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01792"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3207091"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69532-3_15"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00166"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3324591"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409107"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185580"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/38.946629"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.166"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778862"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01909"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00479"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.299"},{"key":"ref18","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goodfellow","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00861"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1128923.1128974"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.11.011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.926997"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.271"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995413"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(82)90007-X"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/j.0956-7976.2004.00719.x"},{"key":"ref29","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref30","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Gal","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3244398"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/rs13214441"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2188997"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601101"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260620"},{"key":"ref37","article-title":"Controlcom: Controllable image composition using diffusion model","author":"Zhang","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00574"},{"key":"ref39","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."},{"key":"ref40","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","article-title":"Zero-shot image restoration using denoising diffusion null-space model","volume-title":"Proc. 11th Int. Conf. Learn. Representations}","author":"Wang","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3480519"},{"key":"ref44","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref45","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref46","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"Proc. 11th Int. Conf. Learn. Representations}","author":"Hertz","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref48","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref49","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4v (ision)","author":"Yang","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref51","article-title":"Denoising diffusion implicit models","volume-title":"Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383198"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/4.996"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01610"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref59","article-title":"Decoupled weight decay regularization","volume-title":"Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref60","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00189"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref63","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref64","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding","year":"2021"},{"key":"ref65","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref66","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022"},{"key":"ref67","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3026740"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_26"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10858769.pdf?arnumber=10858769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T10:23:17Z","timestamp":1766053397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10858769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535343","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}