{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:13:13Z","timestamp":1778051593582,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00153","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1512-1521","source":"Crossref","is-referenced-by-count":0,"title":["MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions"],"prefix":"10.1109","author":[{"given":"Kaen","family":"Kogashi","sequence":"first","affiliation":[{"name":"Mitsubishi Electric,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anoop","family":"Cherian","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Labs,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng-Yu Jennifer","family":"Kuo","sequence":"additional","affiliation":[{"name":"Nara Women’s University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00173"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-01984-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2782743"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00176"},{"key":"ref11","article-title":"MMHOI: Modeling complex 3D multi-human multi-object interactions","author":"Kogashi","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00370"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00172"},{"key":"ref15","article-title":"Language segment-anything","volume-title":"GitHub repository","author":"Luca"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2976014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2572685"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00973"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5244\/c.24.50"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00069"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.529"},{"key":"ref26","article-title":"Freecad","author":"Riegel","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17711-8_28"},{"key":"ref28","journal-title":"Get the mean of the rotations"},{"key":"ref29","author":"Smaira","year":"2020","journal-title":"A short note on the kinetics-700-2020 human action dataset"},{"key":"ref30","article-title":"Extrinsic calibration for multiple azure kinect cameras","volume-title":"GitHub repository","author":"Song"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11839-0_9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00956"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref36","article-title":"Neural-dome: A neural modeling pipeline on multi-view human-object interactions","volume-title":"CVPR","author":"Zhang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00056"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492250.pdf?arnumber=11492250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:41Z","timestamp":1778048321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00153","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}