{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:11:04Z","timestamp":1777889464368,"version":"3.51.4"},"reference-count":91,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01327","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14305-14316","source":"Crossref","is-referenced-by-count":0,"title":["Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations"],"prefix":"10.1109","author":[{"given":"Ruoxi","family":"Guo","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaijin","family":"Pi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehong","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Shuai","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zechen","family":"Hu","sequence":"additional","affiliation":[{"name":"Deep Glint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhumei","family":"Wang","sequence":"additional","affiliation":[{"name":"Deep Glint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajiao","family":"Dong","sequence":"additional","affiliation":[{"name":"Deep Glint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taku","family":"Komura","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sida","family":"Peng","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"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Easymocap - make human motion capture easier","volume-title":"Github","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00916"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01381"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"ref6","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"ref9","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Brown","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00182"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01726"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref16","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref19","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1997.0547"},{"key":"ref24","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530094"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00192"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref29","article-title":"Noise-free score distillation","author":"Katzir","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01345"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref32","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00908"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00053"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02224"},{"key":"ref41","article-title":"Motion-x: A largescale 3d expressive whole-body human motion dataset","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"36","author":"Lin","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref43","article-title":"Plan, posture and go: Towards open-world text-to-motion generation","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"One-2-3-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"36","author":"Liu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref49","volume-title":"Introducing chatgpt","year":"2022"},{"key":"ref50","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","volume-title":"Optitrack"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01080"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01383"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref57","article-title":"DreamFusion: Text-to-3D using 2D Diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref59","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"issue":"1","key":"ref60","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref61","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Razavi","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref63","article-title":"Human motion diffusion as a generative prior","volume-title":"The Twelfth International Conference on Learning Representations (ICLR)","author":"Shafir"},{"key":"ref64","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"ref66","article-title":"Text-to-4d dynamic scene generation","author":"Singer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref70","article-title":"Human motion diffusion model","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Tevet","year":"2023"},{"key":"ref71","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"ref73","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"van den Oord","year":"2017"},{"key":"ref74","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"ref75","volume-title":"Vicon"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref77","article-title":"Holistic-motion2d: Scalable whole-body human motion generation in 2d space","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1088"},{"key":"ref79","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"36","author":"Wang","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00940"},{"key":"ref81","article-title":"Omnicontrol: Control any joint at any time for human motion generation","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Xie"},{"key":"ref82","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_14"},{"key":"ref84","article-title":"Text-to-3d with classifier score distillation","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_36"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01385"}],"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\/11445965.pdf?arnumber=11445965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:55Z","timestamp":1777612495000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01327","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}