{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:30:14Z","timestamp":1780392614914,"version":"3.54.1"},"reference-count":83,"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\/iccv51701.2025.01013","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10886-10897","source":"Crossref","is-referenced-by-count":1,"title":["Humoto: A 4D Dataset of Mocap Human Object Interactions"],"prefix":"10.1109","author":[{"given":"Jiaxin","family":"Lu","sequence":"first","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Hao Paul","family":"Huang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uttaran","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qixing","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref2","article-title":"AvatarGO: Zero-shot 4d human-object interaction generation and animation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Cao"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0284-3"},{"key":"ref6","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360697"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196754"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01244"},{"key":"ref12","article-title":"Motion policy networks","volume-title":"Proceedings of the 6th Conference on Robot Learning (CoRL)","author":"Fishman"},{"key":"ref13","article-title":"Mobile aloha: Learning bimanual mobile manipulation with lowcost whole-body teleoperation","author":"Fu","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587495"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206755"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2532"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00072"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201399"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591525"},{"key":"ref26","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456161"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_18"},{"key":"ref29","article-title":"Mixamo","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687595"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.07.010"},{"key":"ref35","article-title":"Parahome: Parameterizing everyday home activities towards 3d generative modeling of human-object interactions","author":"Kim","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2593780"},{"key":"ref37","article-title":"Motion capture dataset for practical use of ai-based motion editing and stylization","author":"Kobayashi","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566605"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0746"},{"key":"ref42","article-title":"Sam-6d: Segment anything model meets zero-shot 6d object pose estimation","author":"Lin","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.02054","article-title":"Taco: Benchmarking generalizable bimanual tool-action-object understanding","author":"Liu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661273"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_24"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref48","article-title":"HOI4ABOT: Human-object interaction anticipation for hu-man intention reading collaborative roBOTs","volume-title":"7th Annual Conference on Robot Learning","author":"Mascaro"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00973"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref51","article-title":"Hoi-diff: Text-driven synthesis of 3d human-object interactions using diffusion models","author":"Peng","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref53","article-title":"Smartsuit pro ii","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1949.232969"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356505"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126338"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.13"},{"key":"ref60","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","author":"Tremblay","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151614"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00360"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160982"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_27"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530103"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref67","article-title":"Human-object interaction from human-level instructions","author":"Wu","year":"2024"},{"key":"ref68","article-title":"Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes","author":"Xiang","year":"2017"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_8"},{"key":"ref70","article-title":"Rhobin challenge: Reconstruction of human object interaction","author":"Xie","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1675"},{"key":"ref73","article-title":"HOI-swap: Swapping objects in videos with hand-object interaction awareness","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Xue"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02153"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00955"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00853"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00056"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_3"},{"key":"ref80","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20065-6_30","article-title":"Couch: Towards controllable human-chair interactions","author":"Zhang","year":"2022"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00076"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01845"}],"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\/11445768.pdf?arnumber=11445768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:09Z","timestamp":1777530129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445768\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01013","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}