{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T14:20:48Z","timestamp":1783088448704,"version":"3.54.6"},"reference-count":68,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010852","name":"Institute of Computing Technology Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["E561090"],"award-info":[{"award-number":["E561090"]}],"id":[{"id":"10.13039\/501100010852","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.jvcir.2026.104828","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T15:53:26Z","timestamp":1779206006000},"page":"104828","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["IDFreq: Identity-preserved human video generation via frequency-based decomposition"],"prefix":"10.1016","volume":"118","author":[{"given":"Zhang","family":"Wan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1331-5020","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104828_b1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104828_b2","series-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104828_b3","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"47","key":"10.1016\/j.jvcir.2026.104828_b4","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jvcir.2026.104828_b5","series-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104828_b6","doi-asserted-by":"crossref","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.jvcir.2026.104828_b7","series-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104828_b8","series-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104828_b9","doi-asserted-by":"crossref","unstructured":"N. Tumanyan, M. Geyer, S. Bagon, T. Dekel, Plug-and-play diffusion features for text-driven image-to-image translation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1921\u20131930.","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"10.1016\/j.jvcir.2026.104828_b10","doi-asserted-by":"crossref","unstructured":"Z. Wan, S. Tang, J. Wei, R. Zhang, J. Cao, DragEntity: Trajectory Guided Video Generation using Entity and Positional Relationships, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 108\u2013116.","DOI":"10.1145\/3664647.3681567"},{"key":"10.1016\/j.jvcir.2026.104828_b11","doi-asserted-by":"crossref","unstructured":"L. Hu, Animate anyone: Consistent and controllable image-to-video synthesis for character animation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 8153\u20138163.","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"10.1016\/j.jvcir.2026.104828_b12","series-title":"Controlnext: Powerful and efficient control for image and video generation","author":"Peng","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b13","doi-asserted-by":"crossref","unstructured":"T. Wang, L. Li, K. Lin, Y. Zhai, C.-C. Lin, Z. Yang, H. Zhang, Z. Liu, L. Wang, Disco: Disentangled control for realistic human dance generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 9326\u20139336.","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"10.1016\/j.jvcir.2026.104828_b14","doi-asserted-by":"crossref","unstructured":"Z. Xu, J. Zhang, J.H. Liew, H. Yan, J.-W. Liu, C. Zhang, J. Feng, M.Z. Shou, Magicanimate: Temporally consistent human image animation using diffusion model, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 1481\u20131490.","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"10.1016\/j.jvcir.2026.104828_b15","series-title":"Genrec: Unifying video generation and recognition with diffusion models","author":"Weng","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b16","doi-asserted-by":"crossref","first-page":"16222","DOI":"10.52202\/075280-0714","article-title":"Diffusion self-guidance for controllable image generation","volume":"36","author":"Epstein","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104828_b17","doi-asserted-by":"crossref","first-page":"16240","DOI":"10.52202\/079017-0518","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","volume":"37","author":"Kuang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104828_b18","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104828_b19","doi-asserted-by":"crossref","unstructured":"A. Siarohin, O.J. Woodford, J. Ren, M. Chai, S. Tulyakov, Motion representations for articulated animation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13653\u201313662.","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"10.1016\/j.jvcir.2026.104828_b20","series-title":"Unianimate: Taming unified video diffusion models for consistent human image animation","author":"Wang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b21","series-title":"Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance","author":"Zhang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b22","series-title":"European Conference on Computer Vision","first-page":"145","article-title":"Champ: Controllable and consistent human image animation with 3d parametric guidance","author":"Zhu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b23","series-title":"StableAnimator: High-quality identity-preserving human image animation","author":"Tu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b24","doi-asserted-by":"crossref","first-page":"36777","DOI":"10.52202\/079017-1159","article-title":"Pulid: Pure and lightning id customization via contrastive alignment","volume":"37","author":"Guo","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104828_b25","series-title":"Consistentid: Portrait generation with multimodal fine-grained identity preserving","author":"Huang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b26","series-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b27","series-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104828_b28","series-title":"FaceFusion","author":"Henry","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b29","doi-asserted-by":"crossref","unstructured":"F. Bao, S. Nie, K. Xue, Y. Cao, C. Li, H. Su, J. Zhu, All are worth words: A vit backbone for diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22669\u201322679.","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"10.1016\/j.jvcir.2026.104828_b30","series-title":"European Conference on Computer Vision","first-page":"421","article-title":"Rethinking video deblurring with wavelet-aware dynamic transformer and diffusion model","author":"Rao","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b31","series-title":"Identity-preserving text-to-video generation by frequency decomposition","author":"Yuan","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b32","doi-asserted-by":"crossref","unstructured":"C. Si, Z. Huang, Y. Jiang, Z. Liu, Freeu: Free lunch in diffusion u-net, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 4733\u20134743.","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"10.1016\/j.jvcir.2026.104828_b33","series-title":"Promptfix: You prompt and we fix the photo","author":"Yu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b34","series-title":"Bayesian Brain: Probabilistic Approaches To Neural Coding","first-page":"268","article-title":"Optimal control theory","author":"Todorov","year":"2006"},{"issue":"3","key":"10.1016\/j.jvcir.2026.104828_b35","doi-asserted-by":"crossref","first-page":"B48","DOI":"10.1115\/1.1470675","article-title":"Optimal control: An introduction","volume":"55","author":"Locatelli","year":"2002","journal-title":"Appl. Mech. Rev."},{"key":"10.1016\/j.jvcir.2026.104828_b36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12532-018-0139-4","article-title":"Casadi: a software framework for nonlinear optimization and optimal control","volume":"11","author":"Andersson","year":"2019","journal-title":"Math. Program. Comput."},{"key":"10.1016\/j.jvcir.2026.104828_b37","series-title":"International Conference on Machine Learning","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104828_b38","series-title":"Vidiff: Translating videos via multi-modal instructions with diffusion models","author":"Xing","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104828_b39","first-page":"8","article-title":"Video generation models as world simulators","volume":"1","author":"Brooks","year":"2024","journal-title":"OpenAI Blog"},{"key":"10.1016\/j.jvcir.2026.104828_b40","series-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104828_b41","series-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104828_b42","doi-asserted-by":"crossref","unstructured":"S. Tu, Q. Dai, Z.-Q. Cheng, H. Hu, X. Han, Z. Wu, Y.-G. Jiang, Motioneditor: Editing video motion via content-aware diffusion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 7882\u20137891.","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"10.1016\/j.jvcir.2026.104828_b43","series-title":"Motionfollower: Editing video motion via lightweight score-guided diffusion","author":"Tu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b44","series-title":"Magicvideo-v2: Multi-stage high-aesthetic video generation","author":"Wang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b45","unstructured":"J.Z. Wu, Y. Ge, X. Wang, S.W. Lei, Y. Gu, Y. Shi, W. Hsu, Y. Shan, X. Qie, M.Z. Shou, Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 7623\u20137633."},{"key":"10.1016\/j.jvcir.2026.104828_b46","series-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b47","series-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104828_b48","series-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b49","doi-asserted-by":"crossref","unstructured":"W. Peebles, S. Xie, Scalable diffusion models with transformers, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 4195\u20134205.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"10.1016\/j.jvcir.2026.104828_b50","series-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104828_b51","doi-asserted-by":"crossref","unstructured":"L. Yu, Y. Cheng, K. Sohn, J. Lezama, H. Zhang, H. Chang, A.G. Hauptmann, M.-H. Yang, Y. Hao, I. Essa, et al., Magvit: Masked generative video transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 10459\u201310469.","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"10.1016\/j.jvcir.2026.104828_b52","series-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104828_b53","doi-asserted-by":"crossref","unstructured":"Z. Li, M. Cao, X. Wang, Z. Qi, M.-M. Cheng, Y. Shan, Photomaker: Customizing realistic human photos via stacked id embedding, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 8640\u20138650.","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"10.1016\/j.jvcir.2026.104828_b54","series-title":"UniPortrait: A unified framework for identity-preserving single-and multi-human image personalization","author":"He","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b55","doi-asserted-by":"crossref","unstructured":"J. Deng, J. Guo, N. Xue, S. Zafeiriou, Arcface: Additive angular margin loss for deep face recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4690\u20134699.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"10.1016\/j.jvcir.2026.104828_b56","series-title":"Imagine yourself: Tuning-free personalized image generation","author":"He","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b57","series-title":"Id-animator: Zero-shot identity-preserving human video generation","author":"He","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b58","unstructured":"Y. He, S. Yang, H. Chen, X. Cun, M. Xia, Y. Zhang, X. Wang, R. He, Q. Chen, Y. Shan, Scalecrafter: Tuning-free higher-resolution visual generation with diffusion models, in: The Twelfth International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.jvcir.2026.104828_b59","series-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","author":"Qiu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104828_b60","doi-asserted-by":"crossref","unstructured":"Y. Ma, Y. He, X. Cun, X. Wang, S. Chen, X. Li, Q. Chen, Follow your pose: Pose-guided text-to-video generation using pose-free videos, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 4117\u20134125.","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"10.1016\/j.jvcir.2026.104828_b61","series-title":"European Conference on Computer Vision","first-page":"330","article-title":"Sparsectrl: Adding sparse controls to text-to-video diffusion models","author":"Guo","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b62","series-title":"European Conference on Computer Vision","first-page":"273","article-title":"Motiondirector: Motion customization of text-to-video diffusion models","author":"Zhao","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104828_b63","doi-asserted-by":"crossref","unstructured":"L. Zhang, A. Rao, M. Agrawala, Adding conditional control to text-to-image diffusion models, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 3836\u20133847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"10.1016\/j.jvcir.2026.104828_b64","doi-asserted-by":"crossref","unstructured":"X. Chen, L. Huang, Y. Liu, Y. Shen, D. Zhao, H. Zhao, Anydoor: Zero-shot object-level image customization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 6593\u20136602.","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"10.1016\/j.jvcir.2026.104828_b65","doi-asserted-by":"crossref","unstructured":"Z. Huang, X. Han, J. Xu, T. Zhang, Few-shot human motion transfer by personalized geometry and texture modeling, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 2297\u20132306.","DOI":"10.1109\/CVPR46437.2021.00233"},{"key":"10.1016\/j.jvcir.2026.104828_b66","doi-asserted-by":"crossref","unstructured":"J. Zhao, H. Zhang, Thin-plate spline motion model for image animation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 3657\u20133666.","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"10.1016\/j.jvcir.2026.104828_b67","series-title":"HumanDiT: Pose-guided diffusion transformer for long-form human motion video generation","author":"Gan","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104828_b68","doi-asserted-by":"crossref","unstructured":"Y. Jafarian, H.S. Park, Learning high fidelity depths of dressed humans by watching social media dance videos, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12753\u201312762.","DOI":"10.1109\/CVPR46437.2021.01256"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001239?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001239?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T13:33:22Z","timestamp":1783085602000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326001239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":68,"alternative-id":["S1047320326001239"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104828","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"IDFreq: Identity-preserved human video generation via frequency-based decomposition","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104828","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104828"}}