{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:48:56Z","timestamp":1782334136237,"version":"3.54.5"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong Special Administrative Region","award":["ITS\/269\/24FP"],"award-info":[{"award-number":["ITS\/269\/24FP"]}]},{"name":"Kuaishou Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tvcg.2026.3693147","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:57:15Z","timestamp":1778788635000},"page":"7031-7045","source":"Crossref","is-referenced-by-count":0,"title":["MultiPaint: A Unified Framework for Multi-Task, Multi-Object, and Multi-Condition Video Inpainting"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8213-5803","authenticated-orcid":false,"given":"Shiyuan","family":"Yang","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9914-3922","authenticated-orcid":false,"given":"Zheng","family":"Gu","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Hou","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Tao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-565X","authenticated-orcid":false,"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1624-2680","authenticated-orcid":false,"given":"Xiaodong","family":"Chen","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-5377","authenticated-orcid":false,"given":"Jing","family":"Liao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref4","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3658136"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3235364"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3594004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3434386"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"ref11","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref12","article-title":"WAN: Open and advanced large-scale video generative models","author":"Wan","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref14","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3156949"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3550844"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2462368"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240625"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00606"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref23","article-title":"HD-Painter: High-resolution and prompt-faithful text-guided image inpainting with diffusion models","author":"Manukyan","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01763"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3658237"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02148"},{"key":"ref29","article-title":"Inst-Inpaint: Instructing to remove objects with diffusion models","author":"Yildirim","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3150"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref33","article-title":"Coherent and multi-modality image inpainting via latent space optimization","author":"Pan","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612200"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_42"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_22"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00961"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3003768"},{"key":"ref41","article-title":"Advanced video inpainting using optical flow-guided efficient diffusion","author":"Gu","year":"2024"},{"key":"ref42","article-title":"DiffuEraser: A diffusion model for video inpainting","author":"Li","year":"2025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01188"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref45","article-title":"VideoPoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00684"},{"key":"ref48","article-title":"CoCoCo: Improving text-guided video inpainting for better consistency, controllability and compatibility","author":"Zi","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730673"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref51","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022"},{"issue":"140","key":"ref52","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":"ref53","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bar-Tal"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref55","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2170"},{"key":"ref57","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref61","first-page":"8525","article-title":"Extract free dense labels from videos: A large-scale video image segmentation dataset and benchmark","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zhou"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325056"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2957464"},{"key":"ref65","article-title":"CogVLM2: Visual language models for image and video understanding","author":"Hong","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref73","article-title":"ModelScope text-to-video technical report","author":"Wang","year":"2023"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11575570\/11517540.pdf?arnumber=11517540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:50:02Z","timestamp":1782330602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11517540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":73,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3693147","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}