{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:52Z","timestamp":1779948112621,"version":"3.53.1"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00087","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"860-870","source":"Crossref","is-referenced-by-count":0,"title":["Predicting 4D Hand Trajectory from Monocular Videos"],"prefix":"10.1109","author":[{"given":"Yufei","family":"Ye","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Feng","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omid","family":"Taheri","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiwen","family":"Feng","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubham","family":"Tulsiani","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael J.","family":"Black","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610288"},{"key":"ref2","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"ArXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s21082667"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref8","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00623"},{"key":"ref10","article-title":"Project Aria: A new tool for egocentric multi-modal AI research","author":"Engel","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3222784"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02157"},{"key":"ref14","article-title":"Cat3d: Create anything in 3D with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01276"},{"key":"ref17","article-title":"Pace: Physics-based animation and control of expressive 3D characters","author":"Gartner","year":"2022","journal-title":"CVPR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"ref20","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024","journal-title":"COLM"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00926"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00576"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2022.3195968"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_28"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00068"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"ref34","article-title":"Omnihands: Towards robust 4 d hand mesh recovery via a versatile transformer","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01445"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref39","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS56176.2022.9959207"},{"key":"ref41","article-title":"I21-meshnet: Image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single rgb image","author":"Moon","year":"2020","journal-title":"ECCV"},{"key":"ref42","article-title":"Interhand 2.6 m: A dataset and baseline for 3D interacting hand pose estimation from a single rgb image","author":"Moon","year":"2020","journal-title":"ECCV"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00155"},{"key":"ref44","article-title":"Learning to imitate object interactions from internet videos","author":"Patel","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00154"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501898"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref53","article-title":"Mvdream: Multi-view diffusion for 3D generation","author":"Shi","year":"2023","journal-title":"ICLR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.494"},{"key":"ref56","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"ICLR"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"ref58","article-title":"Trace: Monocular global human trajectory estimation in the wild","author":"Sun","year":"2023","journal-title":"CVPR"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01149"},{"key":"ref60","article-title":"Epic Fields: Marrying 3D geometry and video understanding","author":"Tschernezki","year":"2024","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687703"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531369"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01122"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02033"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00187"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00663"},{"key":"ref70","article-title":"Slahmr: Simultaneous localization and human mesh recovery","year":"2023","journal-title":"CVPR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480504"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02581"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00175"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00244"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00136"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00090"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533308.pdf?arnumber=11533308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:46Z","timestamp":1779944566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00087","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}