{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:13:29Z","timestamp":1781885609550,"version":"3.54.5"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100017677","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["GJHZ20220913142600001"],"award-info":[{"award-number":["GJHZ20220913142600001"]}],"id":[{"id":"10.13039\/501100017677","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation Youth Basic Research Program","doi-asserted-by":"publisher","award":["623B2100"],"award-info":[{"award-number":["623B2100"]}],"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":[[2025,6]]},"DOI":"10.1109\/tcsvt.2025.3532495","type":"journal-article","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:29:30Z","timestamp":1737484170000},"page":"6059-6073","source":"Crossref","is-referenced-by-count":6,"title":["UniAdapter: All-in-One Control for Flexible Video Generation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2448-3352","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen Campus, Guangming, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panwen","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong at Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanfan","family":"Guo","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6201-9503","authenticated-orcid":false,"given":"Jiaxi","family":"Gu","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9519-612X","authenticated-orcid":false,"given":"Xiao","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai Campus, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Han","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen Campus, Guangming, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Video Generation Models As World Simulators","author":"Brooks","year":"2024"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","volume-title":"arXiv:2311.15127","author":"Blattmann","year":"2023"},{"key":"ref3","article-title":"I2 VGen-XL: High-quality image-to-video synthesis via cascaded diffusion models","volume-title":"arXiv:2311.04145","author":"Zhang","year":"2023"},{"key":"ref4","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","volume-title":"arXiv:2310.19512","author":"Chen","year":"2023"},{"key":"ref5","first-page":"1","article-title":"VideoComposer: Compositional video synthesis with motion controllability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref7","article-title":"Breathing life into sketches using text-to-video priors","volume-title":"arXiv:2311.13608","author":"Gal","year":"2023"},{"key":"ref8","article-title":"Sketching the future (STF): Applying conditional control techniques to text-to-video models","volume-title":"arXiv:2305.05845","author":"Dhesikan","year":"2023"},{"key":"ref9","article-title":"AnimateDiff: Animate your personalized text-to-Image diffusion models without specific tuning","volume-title":"arXiv:2307.04725","author":"Guo","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref11","article-title":"ControlVideo: Training-free controllable text-to-video generation","volume-title":"arXiv:2305.13077","author":"Zhang","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref15","first-page":"1","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3441713"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326293"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407131"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3404256"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409184"},{"key":"ref21","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"arXiv:2112.10741","author":"Nichol","year":"2021"},{"key":"ref22","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","first-page":"613","article-title":"Generating videos with scene dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vondrick"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.09.016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5220\/0010241801010112"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00979"},{"key":"ref31","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","volume-title":"arXiv:2104.10157","author":"Yan","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867934"},{"key":"ref33","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"arXiv:2209.14792","author":"Singer","year":"2022"},{"key":"ref34","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"arXiv:2205.15868","author":"Hong","year":"2022"},{"key":"ref35","article-title":"Imagen video: High definition video generation with diffusion models","volume-title":"arXiv:2210.02303","author":"Ho","year":"2022"},{"key":"ref36","article-title":"MagicVideo: Efficient video generation with latent diffusion models","volume-title":"arXiv:2211.11018","author":"Zhou","year":"2022"},{"key":"ref37","article-title":"Reuse and diffuse: Iterative denoising for text-to-video generation","volume-title":"arXiv:2309.03549","author":"Gu","year":"2023"},{"key":"ref38","article-title":"Modelscope text-to-video technical report","volume-title":"arXiv:2308.06571","author":"Wang","year":"2023"},{"key":"ref39","article-title":"Emu video: Factorizing text-to-video generation by explicit image conditioning","volume-title":"arXiv:2311.10709","author":"Girdhar","year":"2023"},{"key":"ref40","article-title":"Swap attention in spatiotemporal diffusions for text-to-video generation","volume-title":"arXiv:2305.10874","author":"Wang","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref45","article-title":"LAVIE: High-quality video generation with cascaded latent diffusion models","volume-title":"arXiv:2309.15103","author":"Wang","year":"2023"},{"key":"ref46","article-title":"Movie gen: A cast of media foundation models","volume-title":"arXiv:2410.13720","author":"Polyak","year":"2024"},{"key":"ref47","article-title":"Open-sora plan: Open-source large video generation model","volume-title":"arXiv:2412.00131","author":"Lin","year":"2024"},{"key":"ref48","article-title":"Pyramidal flow matching for efficient video generative modeling","volume-title":"arXiv:2410.05954","author":"Jin","year":"2024"},{"key":"ref49","article-title":"CogVideoX: Text-to-Video diffusion models with an expert transformer","volume-title":"arXiv:2408.06072","author":"Yang","year":"2024"},{"key":"ref50","article-title":"Latte: Latent diffusion transformer for video generation","volume-title":"arXiv:2401.03048","author":"Ma","year":"2024"},{"key":"ref51","article-title":"Allegro: Open the black box of commercial-level video generation model","volume-title":"arXiv:2410.15458","author":"Zhou","year":"2024"},{"key":"ref52","first-page":"31769","article-title":"Generating long videos of dynamic scenes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brooks"},{"key":"ref53","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref54","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume-title":"arXiv:2204.06125","author":"Ramesh","year":"2022"},{"key":"ref55","article-title":"Latent video diffusion models for high-fidelity long video generation","volume-title":"arXiv:2211.13221","author":"He","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01462"},{"key":"ref57","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","volume-title":"arXiv:2304.08477","author":"An","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083257"},{"key":"ref59","article-title":"MagDiff: Multi-alignment diffusion for high-fidelity video generation and editing","volume-title":"arXiv:2311.17338","author":"Zhao","year":"2023"},{"key":"ref60","article-title":"AtomoVideo: High fidelity image-to-video generation","volume-title":"arXiv:2403.01800","author":"Gong","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref62","article-title":"Animate-a-story: Storytelling with retrieval-augmented video generation","volume-title":"arXiv:2307.06940","author":"He","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00662"},{"key":"ref64","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/11758501_76"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925972"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3132703"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref72","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref73","article-title":"Classifier-free diffusion guidance","volume-title":"arXiv:2207.12598","author":"Ho","year":"2022"},{"key":"ref74","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv:2307.019520","author":"Podell","year":"2023"},{"key":"ref75","volume-title":"Corran\/pexelvideos","year":"2022"},{"key":"ref76","first-page":"1","article-title":"FVD: A new metric for video generation","volume-title":"Proc. Deep Generative Models Highly Structured Data, (ICLR) Workshop","author":"Unterthiner"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3569219.3569352"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11027896\/10848181.pdf?arnumber=10848181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T05:10:25Z","timestamp":1749532225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":81,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3532495","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}