{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:30:43Z","timestamp":1778081443046,"version":"3.51.4"},"reference-count":66,"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\/iccv51701.2025.00515","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5426-5436","source":"Crossref","is-referenced-by-count":1,"title":["Generative Modeling of Shape-Dependent Self-Contact Human Poses"],"prefix":"10.1109","author":[{"given":"Takehiko","family":"Ohkawa","sequence":"first","affiliation":[{"name":"Codec Avatars Lab, Meta"}]},{"given":"Jihyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Codec Avatars Lab, Meta"}]},{"given":"Shunsuke","family":"Saito","sequence":"additional","affiliation":[{"name":"Codec Avatars Lab, Meta"}]},{"given":"Jason","family":"Saragih","sequence":"additional","affiliation":[{"name":"Codec Avatars Lab, Meta"}]},{"given":"Fabian","family":"Prada","sequence":"additional","affiliation":[{"name":"Codec Avatars Lab, Meta"}]},{"given":"Yichen","family":"Xu","sequence":"additional","affiliation":[{"name":"Codec Avatars Lab, Meta"}]},{"given":"Shoou-I","family":"Yu","sequence":"additional","affiliation":[{"name":"Codec Avatars Lab, Meta"}]},{"given":"Ryosuke","family":"Furuta","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Yoichi","family":"Sato","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}]},{"given":"Takaaki","family":"Shiratori","sequence":"additional","affiliation":[{"name":"Codec Avatars Lab, Meta"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref3","article-title":"Demystifying MMD GANs","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net","author":"Binkowski","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0506"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01640"},{"key":"ref6","article-title":"Emosign: A multimodal dataset for understanding emotions in american sign language","author":"Chua","year":"2025","journal-title":"CoRR, abs\/2505.17090"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16223"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00152"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0277-9536(85)90193-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1111\/j.1559-1816.1991.tb00538.x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Heusel","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2671015.2671020"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2020"},{"key":"ref20","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"CoRR, abs\/2207.12598"},{"key":"ref21","article-title":"Expressive gaussian human avatars from monocular RGB video","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Hu","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01292"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref25","article-title":"Harmony4D: A video dataset for in-the-wild close human interactions","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Khirodkar","year":"2024"},{"key":"ref26","article-title":"Auto-encoding variational bayes","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Kingma","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00057"},{"key":"ref28","article-title":"Hybrik-x: Hybrid analytical-neural inverse kinematics for whole-body mesh recovery","author":"Li","year":"2023","journal-title":"CoRR, abs\/2304.05690"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01243"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02027"},{"key":"ref33","article-title":"Simhand: Mining similar hands for large-scale 3d hand pose pre-training","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Lin","year":"2025"},{"key":"ref34","article-title":"Unified generation, reconstruction, and representation: Generalized diffusion with adaptive latent encoding-decoding","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Liu","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00071"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2640"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw56347.2022.00257"},{"key":"ref39","article-title":"Expressive wholebody 3d gaussian avatar","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Moon","year":"2024"},{"key":"ref40","first-page":"548","article-title":"Lee. InterHand2.6M: A dataset and baseline for 3D interacting hand pose estimation from a single RGB image","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Moon","year":"2020"},{"key":"ref41","first-page":"9990","article-title":"Black","volume-title":"On self-contact and human pose. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"M\u00fcller","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00925"},{"key":"ref43","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","volume":"139","author":"Nichol","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01856-0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01249"},{"key":"ref46","article-title":"Black. Expressive body capture: 3d hands, face, and body from a single image","author":"Pavlakos","year":"2019","journal-title":"CVPR"},{"key":"ref47","article-title":"The definitive book of body language: The hidden meaning behind people\u2019s gestures and expressions","author":"Pease","year":"2008","journal-title":"Bantam"},{"key":"ref48","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR). OpenReview","author":"Poole","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01333"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref52","first-page":"5234","article-title":"Assessing generative models via precision and recall","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)","author":"Sajjadi","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3618329"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417768"},{"key":"ref55","article-title":"Denoising diffusion implicit models","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Song","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref58","article-title":"Human motion diffusion model","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Tevet","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1264"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00073"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"}],"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\/11445611.pdf?arnumber=11445611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:33Z","timestamp":1777611753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00515","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}