{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T20:57:22Z","timestamp":1767646642130,"version":"3.48.0"},"reference-count":64,"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":["62302246"],"award-info":[{"award-number":["62302246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LQ23F010008"],"award-info":[{"award-number":["LQ23F010008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3587757","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:49:53Z","timestamp":1752169793000},"page":"12238-12250","source":"Crossref","is-referenced-by-count":0,"title":["Canvas: Compositional Generation for Art Painting With Seamless Subject-Driven Infusion"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5480-4587","authenticated-orcid":false,"given":"Yunnan","family":"Wang","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China"}]},{"given":"Ziqiang","family":"Li","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3090-255X","authenticated-orcid":false,"given":"Wenyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University (SJTU), Shanghai, China"}]},{"given":"Lexiang","family":"Lv","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University (HNU), Changsha, China"}]},{"given":"Zequn","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, China"}]},{"given":"Xiaoyu","family":"Shen","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1820-8358","authenticated-orcid":false,"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT), Ningbo, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3295115"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3361799"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3298811"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343733"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01100"},{"key":"ref6","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref9","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref13","article-title":"InstantStyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv:2404.02733"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680848"},{"key":"ref22","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref25","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv:2011.13456"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326293"},{"key":"ref27","first-page":"11287","article-title":"Score-based generative modeling in latent space","volume-title":"Proc. NIPS","author":"Vahdat"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Oord","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","article-title":"EDiff-I: Text-to-Image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv:2211.01324"},{"key":"ref32","article-title":"Re-imagen: Retrieval-augmented text-to-image generator","author":"Chen","year":"2022","journal-title":"arXiv:2209.14491"},{"key":"ref33","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref34","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"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":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref40","first-page":"23104","article-title":"DisenBooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref41","first-page":"15890","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Gu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref45","article-title":"Taming encoder for zero fine-tuning image customization with text-to-image diffusion models","author":"Jia","year":"2023","journal-title":"arXiv:2304.02642"},{"key":"ref46","first-page":"30146","article-title":"BLIP-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"key":"ref47","article-title":"InstantBooth: Personalized text-to-image generation without test-time finetuning","author":"Shi","year":"2023","journal-title":"arXiv:2304.03411"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref49","article-title":"FastComposer: Tuning-free multi-subject image generation with localized attention","author":"Xiao","year":"2023","journal-title":"arXiv:2305.10431"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3338459"},{"key":"ref53","article-title":"Pretraining is all you need for image-to-image translation","author":"Wang","year":"2022","journal-title":"arXiv:2205.12952"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286841"},{"key":"ref57","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv:2208.01626"},{"key":"ref58","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"L\u00fc"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref60","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv:2210.11427"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"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. (NeurIPS)","author":"Heusel","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11077416.pdf?arnumber=11077416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:04Z","timestamp":1767638464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11077416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":64,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3587757","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}