{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:15:06Z","timestamp":1777889706344,"version":"3.51.4"},"reference-count":59,"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":["62472104"],"award-info":[{"award-number":["62472104"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01607","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17302-17311","source":"Crossref","is-referenced-by-count":2,"title":["AnyI2V: Animating Any Conditional Image with Motion Control"],"prefix":"10.1109","author":[{"given":"Ziye","family":"Li","sequence":"first","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Luo","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba group,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xincheng","family":"Shuai","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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\/ICCV48922.2021.01144"},{"key":"ref4","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref8","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref10","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref11","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref12","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref14","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arxiv preprint arxiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1408"},{"key":"ref16","article-title":"Videocontrolnet: A motion-guided video-to-video translation framework by using diffusion model with controlnet","author":"Hu","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref20","article-title":"Diffblender: Scalable and composable multimodal text-to-image diffusion models","author":"Kim","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref21","article-title":"Compose and conquer: Diffusion-based 3d depth aware composable image synthesis","author":"Lee","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32533"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4596-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687652"},{"key":"ref25","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability","volume":"1","author":"MacQueen","year":"1967"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"ref28","article-title":"Sg-i2v: Self-guided trajectory control in image-to-video generation","author":"Namekata","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591500"},{"key":"ref31","article-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref32","article-title":"Freetraj: Tuning-free trajectory control in video diffusion models","author":"Qiu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref36","article-title":"A survey of multimodal-guided image editing with text-to-image diffusion models","author":"Shuai","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01157"},{"key":"ref38","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref39","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Song","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref42","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref43","article-title":"Boximator: Generating rich and controllable motions for video synthesis","author":"Wang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref44","article-title":"CharaConsist: Finegrained consistent character generation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Wang","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02810-6"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref50","article-title":"Motionbooth: Motion-aware customized text-to-video generation","author":"Wu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref52","article-title":"Video diffusion models are training-free motion interpreter and controller","author":"Xiao","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref55","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref57","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref58","article-title":"Tora: Trajectory-oriented diffusion transformer for video generation","author":"Zhang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33167"}],"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\/11445352.pdf?arnumber=11445352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:23Z","timestamp":1777612703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01607","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}