{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:56Z","timestamp":1777865336515,"version":"3.51.4"},"reference-count":82,"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":"NSFC","doi-asserted-by":"publisher","award":["62322207,U24B20154"],"award-info":[{"award-number":["62322207,U24B20154"]}],"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\/iccv51701.2025.01181","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12713-12724","source":"Crossref","is-referenced-by-count":0,"title":["Precise Action-to-Video Generation Through Visual Action Prompts"],"prefix":"10.1109","author":[{"given":"Yuang","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Wen","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sida","family":"Peng","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghan","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Xiangjiang Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Easymocap - make human motion capture easier","year":"2021","journal-title":"Github"},{"key":"ref2","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01163"},{"key":"ref4","article-title":"Diffusion for world modeling: Visual details matter in atari","author":"Alonso","year":"2025","journal-title":"NeurIPS"},{"key":"ref5","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref6","volume-title":"Introducing hot3d: An egocentric dataset for 3d hand and object tracking","author":"Banerjee","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276467"},{"key":"ref9","article-title":"Gen2act: Human video generation in novel scenarios enables generalizable robot manipulation","author":"Bharadhwaj","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Zeroshot robotic manipulation with pretrained image-editing diffusion models","author":"Black","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref12","article-title":"Genie: Generative interactive environments","author":"Bruce","year":"2024","journal-title":"ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208639"},{"key":"ref14","article-title":"Gamegen-x: Interactive open-world game video generation","author":"Che","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"Damen","year":"2018","journal-title":"ECCV"},{"key":"ref16","volume-title":"Oasis: A universe in a transformer","author":"Decart","year":"2024"},{"key":"ref17","article-title":"DeepMind","year":"2024","journal-title":"Genie 2: A large-scale foundation world model"},{"key":"ref18","volume-title":"Motion capture from internet videos. In ECCV","author":"Dong","year":"2020"},{"key":"ref19","volume-title":"Learning universal policies via text-guided video generation","author":"Du","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"ref21","article-title":"The matrix: Infinite-horizon world generation with real-time moving control","author":"Feng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01627"},{"key":"ref23","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2025","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref28","article-title":"Matchanything: Universal cross-modality image matching with large-scale pre-training","author":"He","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/027836499501400301"},{"key":"ref30","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00951"},{"key":"ref33","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","volume-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref36","article-title":"Sapiens: Foundation for human vision models","author":"Khirodkar","year":"2024","journal-title":"ECCV"},{"key":"ref37","article-title":"Learning to act from actionless videos through dense correspondences","author":"Ko","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596796"},{"key":"ref39","article-title":"Wonderland: Navigating 3d scenes from a single image","author":"Liang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02054"},{"key":"ref41","article-title":"The babyview dataset: High-resolution egocentric videos of infants\u2019 and young children\u2019s everyday experiences","author":"Long","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Mimo: Controllable character video synthesis with spatial decomposed modeling","author":"Men","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Do generative video models understand physical principles?","author":"Motamed","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14426"},{"key":"ref46","article-title":"OpenAI","year":"2023","journal-title":"Openai sora"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref48","article-title":"Rick Parent","year":"2012","journal-title":"Computer animation: algorithms and techniques"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref50","volume-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01143"},{"key":"ref52","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687565"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00627"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282250"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_24"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/70.34770"},{"key":"ref60","article-title":"Fvd: A new metric for video generation","volume-title":"ICLR workshop","author":"Unterthiner","year":"2019"},{"key":"ref61","article-title":"Diffusion models are real-time game engines","author":"Valevski","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","article-title":"Boximator: Generating rich and controllable motions for video synthesis","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730735"},{"key":"ref64","article-title":"Egovid-5m: A large-scale video-action dataset for egocentric video generation","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref67","article-title":"ivideogpt: Interactive videogpts are scalable world models","author":"Wu","year":"2025","journal-title":"NeurIPS"},{"key":"ref68","volume-title":"Samurai: Adapting segment anything model for zero-shot visual tracking with motion-aware memory","author":"Yang","year":"2024"},{"key":"ref69","article-title":"Learning interactive real-world simulators","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref70","volume-title":"Video as the new language for real-world decision making","author":"Yang","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref72","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref73","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":"ref74","article-title":"Gamefactory: Creating new games with generative interactive videos","author":"Yu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00050"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref78","article-title":"Mimicmotion: High-quality human motion video generation with confidenceaware pose guidance","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref79","article-title":"Tora: Trajectory-oriented diffusion transformer for video generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref80","volume-title":"Realisdance: Equip controllable character animation with realistic hands","author":"Zhou","year":"2024"},{"key":"ref81","article-title":"Irasim: Learning interactive realrobot action simulators","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref82","volume-title":"Champ: Controllable and consistent human image animation with 3d parametric guidance","author":"Zhu","year":"2024"}],"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\/11444679.pdf?arnumber=11444679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:03Z","timestamp":1777529823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01181","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}