{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:22Z","timestamp":1777865422175,"version":"3.51.4"},"reference-count":50,"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":["6243000159,62102416,62450001,62476008"],"award-info":[{"award-number":["6243000159,62102416,62450001,62476008"]}],"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\/iccv51701.2025.01139","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12253-12262","source":"Crossref","is-referenced-by-count":0,"title":["MotionCtrl: A Real-Time Controllable Vision-Language-Motion Model"],"prefix":"10.1109","author":[{"given":"Bin","family":"Cao","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}]},{"given":"Sipeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}]},{"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence"}]},{"given":"Lujie","family":"Xia","sequence":"additional","affiliation":[{"name":"Renmin University of China"}]},{"given":"Qianshan","family":"Wei","sequence":"additional","affiliation":[{"name":"Southeast University"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University"}]},{"given":"Zongqing","family":"Lu","sequence":"additional","affiliation":[{"name":"BeingBeyond"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00581"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3627546\/mm1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3407570"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01239"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref16","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02589"},{"key":"ref18","article-title":"Motion-x: A largescale 3d expressive whole-body human motion dataset","author":"Lin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","article-title":"llamacpp","volume-title":"https:\/\/github.com\/ggml-org\/llama.cpp","year":"2024"},{"key":"ref22","author":"Lu","year":"2023","journal-title":"Humantomato: Text-aligned whole-body motion generation"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02595"},{"key":"ref24","author":"Luo","year":"2024","journal-title":"M3 gpt: An advanced multimodal, multitask framework for motion comprehension and generation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref27","author":"Mentzer","year":"2023","journal-title":"Finite scalar quantization: Vq-vae made simple"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"ref32","author":"Team","year":"2024","journal-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context"},{"key":"ref33","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref34","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref35","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"ref37","author":"Wang","year":"2024","journal-title":"Motiongpt-2: A general-purpose motionlanguage model for motion generation and understanding"},{"key":"ref38","author":"Wang","year":"2024","journal-title":"Quo vadis, motion generation? from large language models to large motion models"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6911"},{"key":"ref40","author":"Wu","year":"2024","journal-title":"Motionllm: Multimodal motion-language learning with large language models"},{"key":"ref41","author":"Xu","year":"2024","journal-title":"Motionbank: A large-scale video motion benchmark with disentangled rule-based annotations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1190"},{"key":"ref43","author":"Yu","year":"2023","journal-title":"Language model beats diffusion-tokenizer is key to visual generation"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414\/mm2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_23"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref49","author":"Zhang","year":"2024","journal-title":"Video instruction tuning with synthetic data"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"}],"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\/11445803.pdf?arnumber=11445803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:31:05Z","timestamp":1777530665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01139","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}