{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T20:28:46Z","timestamp":1773260926936,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["11971024"],"award-info":[{"award-number":["11971024"]}],"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":["11901443"],"award-info":[{"award-number":["11901443"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["CCSS-2348046"],"award-info":[{"award-number":["CCSS-2348046"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3382484","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T19:05:48Z","timestamp":1711652748000},"page":"8811-8823","source":"Crossref","is-referenced-by-count":25,"title":["MMGInpainting: Multi-Modality Guided Image Inpainting Based on Diffusion Models"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4986-5484","authenticated-orcid":false,"given":"Cong","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Mathematics, School of Science, Wuhan University of Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3005-5224","authenticated-orcid":false,"given":"Wenxia","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Mathematics, School of Science, Wuhan University of Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2067-2763","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science at the University at Albany, State University of New York, Albany, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6334-4738","authenticated-orcid":false,"given":"Huan","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Mathematics, School of Science, Wuhan University of Technology, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref4","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref7","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. Int. Conf. Learn. Representations, 2023","author":"Couairon"},{"key":"ref8","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng","year":"2022"},{"key":"ref9","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref10","article-title":"DiffuseVAE: Efficient, controllable and high-fidelity generation from low-dimensional latents","volume-title":"Trans. Mach. Learn. Res.","author":"Pandey","year":"2022"},{"key":"ref11","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref15","article-title":"eDiffi: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref16","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao","year":"2021"},{"key":"ref17","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Song","year":"2020"},{"key":"ref18","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3174413"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146774"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2023.115330"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189245"},{"key":"ref24","article-title":"MaGIC: Multi-modality guided image completion","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Yu","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00029"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00736","article-title":"LeftRefill: Filling right canvas based on left reference through generalized text-to-image diffusion model","author":"Cao","year":"2024"},{"key":"ref27","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Machine Learning","author":"Nichol","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02152"},{"key":"ref32","article-title":"DiffFaceSketch: High-fidelity face image synthesis with sketch-guided latent diffusion model","author":"Peng","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00581"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2831636"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00408"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01387"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01371"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3106124"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106789"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3111491"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/9953198"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref53","article-title":"Diffusion models already have a semantic latent space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kwon","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref56","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_47"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref60","article-title":"Pretraining is all you need for image-to-image translation","author":"Wang","year":"2022"},{"key":"ref61","article-title":"Understanding diffusion models: a unified perspective","author":"Bound","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01119"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00169"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01753"},{"key":"ref65","first-page":"8857","article-title":"Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rasul","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref68","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref70","first-page":"6629","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref72","article-title":"Large scale image completion via co-modulated generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2020"},{"key":"ref73","first-page":"36652","article-title":"Pick-a-Pic: An open dataset of user preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kirstain","year":"2023"},{"key":"ref74","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.250"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6046\/10384483\/10480591-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10480591.pdf?arnumber=10480591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T06:26:23Z","timestamp":1731651983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10480591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3382484","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}