{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:04Z","timestamp":1777890184766,"version":"3.51.4"},"reference-count":84,"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\/100004316","name":"IBM","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004316","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"publisher","award":["HR00112390059"],"award-info":[{"award-number":["HR00112390059"]}],"id":[{"id":"10.13039\/100000185","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\/iccv51701.2025.00686","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7306-7317","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion-Based 3D Hand Motion Recovery with Intuitive Physics"],"prefix":"10.1109","author":[{"given":"Yufei","family":"Zhang","sequence":"first","affiliation":[{"name":"Rensselaer Polytechnic Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijun","family":"Cui","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey O.","family":"Kephart","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Ji","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00616"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376550"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3216899"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.7287\/peerj.preprints.3080v1","article-title":"Hand posture comparison in synergy space","volume-title":"PeerJ PrePrints","author":"Bhatt","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01363"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01989"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_45"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01992"},{"key":"ref14","article-title":"Hamba: Single-view 3d hand reconstruction with graph-guided bi-scanning mamba","volume-title":"arXiv","author":"Dong","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00623"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02157"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547828"},{"key":"ref18","article-title":"Intuitive physics understanding emerges from self-supervised pretraining on natural videos","volume-title":"arXiv preprint arXiv","author":"Garrido","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01109"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2018.8446250"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27979"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00065"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"arXiv preprint arXiv","author":"Jang","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00080"},{"key":"ref28","article-title":"Consistency trajectory models: Learning probability flow ode trajectory of diffusion","volume-title":"arXiv preprint arXiv","author":"Kim","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00504"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1272"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00057"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00278"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00068"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01445"},{"key":"ref37","article-title":"Geneoh diffusion: Towards generalizable hand-object interaction denoising via denoising diffusion","volume-title":"arXiv preprint arXiv","author":"Liu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02054"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"arXiv preprint arXiv","author":"Loshchilov","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00227"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_44"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00013"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00155"},{"key":"ref44","article-title":"Reconstructing hands in 3d with transformers","volume-title":"arXiv preprint arXiv","author":"Pavlakos","year":"2023"},{"key":"ref45","article-title":"Wilor: End-to-end 3d hand localization and reconstruction in-the-wild","volume-title":"arXiv preprint arXiv","author":"Potamias","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00989"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196104"},{"key":"ref48","article-title":"End-toend weakly-supervised single-stage multiple 3d hand mesh reconstruction from a single rgb image","volume-title":"arXiv preprint arXiv","author":"Ren","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00736"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2013.00023"},{"key":"ref52","article-title":"Denoising diffusion implicit models","volume-title":"arXiv preprint arXiv","author":"Song","year":"2020"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58520-4_13","article-title":"Weakly supervised 3d hand pose estimation via biomechanical constraints","volume-title":"arXiv preprint arXiv","author":"Spurr","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01104"},{"key":"ref55","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00457"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00171"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247907"},{"key":"ref59","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012429"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00062"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00231"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01635"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00968"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00242"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00277"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00187"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(95)00020-E"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01245"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00060"},{"key":"ref72","article-title":"Resshift: Efficient diffusion model for image super-resolution by residual shifting","volume":"36","author":"Yue","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01116"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00244"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00224"},{"key":"ref76","article-title":"Weaklysupervised 3d hand reconstruction with knowledge prior and uncertainty guidance","volume-title":"arXiv preprint arXiv","author":"Zhang","year":"2024"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508412"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_1"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00136"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00136"},{"key":"ref81","volume-title":"Get a grip: Reconstructing hand-object stable grasps in egocentric videos","author":"Zhu","year":"2024"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00073"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00831"}],"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\/11445852.pdf?arnumber=11445852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:52Z","timestamp":1777613572000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00686","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}