{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:14:22Z","timestamp":1778530462581,"version":"3.51.4"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62227808"],"award-info":[{"award-number":["62227808"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tencent Foundation\/Xplorer Prize"},{"DOI":"10.13039\/501100001809","name":"Major Key Project of Peng Cheng Laboratory","doi-asserted-by":"publisher","award":["PCL2024A05"],"award-info":[{"award-number":["PCL2024A05"]}],"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":[[2026,5]]},"DOI":"10.1109\/tcsvt.2025.3645812","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:35:33Z","timestamp":1766082933000},"page":"7020-7034","source":"Crossref","is-referenced-by-count":0,"title":["Customized Multi-Subject Text-to-Image Generation With Causal Tuning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3614-9371","authenticated-orcid":false,"given":"Chaoyang","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1346-2437","authenticated-orcid":false,"given":"Lingzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8355-0969","authenticated-orcid":false,"given":"Ning","family":"Hu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1012-5301","authenticated-orcid":false,"given":"Qing","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref5","first-page":"57500","article-title":"Customizable image synthesis with multiple subjects","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref6","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref7","first-page":"1","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref8","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref9","article-title":"Unified multi-modal latent diffusion for joint subject and text conditional image generation","author":"Ma","year":"2023","journal-title":"arXiv:2303.09319"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612524"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613832"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3485236"},{"key":"ref15","article-title":"Textual localization: Decomposing multi-concept images for subject-driven text-to-image generation","author":"Shentu","year":"2024","journal-title":"arXiv:2402.09966"},{"key":"ref16","first-page":"1","article-title":"DisenBooth: Identity-preserving disentangled tuning for subject-driven text-to-image generation","volume-title":"Proc. Int. Conf. Learn. Representat.","author":"Chen"},{"key":"ref17","first-page":"21548","article-title":"Cones: Concept neurons in diffusion models for customized generation","volume-title":"Proc. Int. Conf. Mach. Learning(ICML)","author":"Liu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00761"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274228"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3532685"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref22","first-page":"30105","article-title":"StyleGAN-t: Unlocking the power of GANs for fast large-scale text-to-image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Sauer"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00377"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358086"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217384"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3278992"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3347971"},{"key":"ref29","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":"ref30","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref31","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref32","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref33","first-page":"7009","article-title":"Image generation with shortest path diffusion","volume-title":"Proc. Int. Conf. Mach. Learning(ICML)","author":"Das"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00979"},{"key":"ref35","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","first-page":"1","article-title":"Re-imagen: Retrieval-augmented text-to-image generator","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref39","first-page":"1737","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learning(ICML)","author":"Bar-Tal"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3506992"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00416"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3618322"},{"key":"ref45","first-page":"1","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gal"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613806"},{"key":"ref47","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with C-LoRA","author":"Smith","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531917"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00877"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32210"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00648"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02286"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00868"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00848"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3200"},{"key":"ref62","first-page":"1","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref64","article-title":"DreamStory: Open-domain story visualization by LLM-guided multi-subject consistent diffusion","author":"He","year":"2024","journal-title":"arXiv:2407.12899"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00280"},{"key":"ref66","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref67","first-page":"15861","article-title":"On the relationship between explanation and prediction: A causal view","volume-title":"Proc. Int. Conf. Mach. Learning","author":"Karimi"},{"key":"ref68","first-page":"3076","article-title":"Estimating individual treatment effect: Generalization bounds and algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shalit"},{"key":"ref69","first-page":"3020","article-title":"Learning representations for counterfactual inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Johansson"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014846"},{"key":"ref71","first-page":"10220","article-title":"CXPlain: Causal explanations for model interpretation under uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Schwab"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref73","article-title":"Diffusers: State-of-the-art diffusion models","author":"Von Platen","year":"2022"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref75","first-page":"1","article-title":"Demystifying MMD GANs","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Binkowski"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref77","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Podell"},{"key":"ref78","first-page":"1","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11303933.pdf?arnumber=11303933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:50Z","timestamp":1778528930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11303933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":79,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3645812","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}