{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T23:24:46Z","timestamp":1781047486741,"version":"3.54.1"},"reference-count":80,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62032006,62472098"],"award-info":[{"award-number":["62032006,62472098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["24511103100"],"award-info":[{"award-number":["24511103100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01973","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21243-21253","source":"Crossref","is-referenced-by-count":2,"title":["Aid: Adapting Image2video Diffusion Models for Instruction-Guided Video Prediction"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Xing","sequence":"first","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dai","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zejia","family":"Weng","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","volume-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref8","article-title":"Adversarial video generation on complex datasets","author":"Clark","year":"2019","journal-title":"arxiv preprint arxiv"},{"key":"ref9","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"Damen","year":"2018","journal-title":"ECCV"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref12","article-title":"Empowering dynamics-aware text-to-video diffusion with large language models","author":"Fei","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref16","article-title":"Making llama see and draw with seed tokenizer","author":"Ge","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref19","article-title":"Seer: Language instructed video prediction with latent diffusion models","author":"Gu","year":"2024","journal-title":"ICLR"},{"key":"ref20","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref21","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref22","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arxiv preprint arxiv"},{"key":"ref23","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref24","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref25","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1138"},{"issue":"4","key":"ref28","article-title":"Estimation of nonnormalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Kuaishou","year":"2024","journal-title":"Kling"},{"key":"ref31","article-title":"Pika Lab","year":"2023","journal-title":"Pika"},{"key":"ref32","article-title":"Stochastic adversarial video prediction","author":"Lee","year":"2018","journal-title":"arxiv preprint arxiv"},{"key":"ref33","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01126"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3485472"},{"key":"ref36","article-title":"Vstar: Generative temporal nursing for longer dynamic video synthesis","volume-title":"arxiv preprint arxiv","author":"Li","year":"2024"},{"key":"ref37","article-title":"Llm-grounded video diffusion models","author":"Lian","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref38","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Flowzero: Zero-shot text-to-video synthesis with 11 m-driven dynamic scene syntax","volume-title":"arxiv preprint arxiv","author":"Lu","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00150"},{"key":"ref42","article-title":"Sdedit: Image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng","year":"2022"},{"key":"ref43","article-title":"OpenAI","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref44","article-title":"OpenAI","year":"2024","journal-title":"Sora"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612012"},{"key":"ref46","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref47","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref50","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2023","journal-title":"ICLR"},{"key":"ref51","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"ref55","article-title":"Motionfollower: Editing video motion via lightweight score-guided diffusion","author":"Tu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01965"},{"key":"ref57","article-title":"Stableanimator++: Overcoming pose misalignment and face distortion for human image animation","author":"Tu","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref58","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arxiv preprint arxiv"},{"key":"ref59","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","article-title":"Mcvd-masked conditional video diffusion for prediction, generation, and interpolation","author":"Voleti","year":"2022","journal-title":"NeurIPS"},{"key":"ref62","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00804"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3456"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref66","article-title":"Next-gpt: Any-to-any multimodal 11 m","author":"Wu","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01804"},{"key":"ref69","article-title":"Vidiff: Translating videos via multi-modal instructions with diffusion models","author":"Xing","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"ref72","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arxiv preprint arxiv"},{"key":"ref73","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00845"},{"key":"ref76","article-title":"Adadiff: Adaptive step selection for fast diffusion","author":"Zhang","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref77","article-title":"Creatilayout: Siamese multimodal diffusion transformer for creative layout-to-image generation","author":"Zhang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01203"},{"key":"ref79","article-title":"Creatidesign: A unified multi-conditional diffusion transformer for creative graphic design","author":"Zhang","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445055.pdf?arnumber=11445055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:08Z","timestamp":1777613468000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01973","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}