{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:16:46Z","timestamp":1765520206409,"version":"3.48.0"},"reference-count":50,"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\/iros60139.2025.11246949","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"11797-11804","source":"Crossref","is-referenced-by-count":0,"title":["OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB"],"prefix":"10.1109","author":[{"given":"Yunzhi","family":"Lin","sequence":"first","affiliation":[{"name":"Meta"}]},{"given":"Yipu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Meta"}]},{"given":"Fu-Jen","family":"Chu","sequence":"additional","affiliation":[{"name":"Meta"}]},{"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta"}]},{"given":"Weiyao","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"Meta"}]},{"given":"Patricio A.","family":"Vela","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Matt","family":"Feiszli","sequence":"additional","affiliation":[{"name":"Meta"}]},{"given":"Kevin","family":"Liang","sequence":"additional","affiliation":[{"name":"Meta"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353536"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.23"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3056043"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196679"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01296"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811720"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"ref8","article-title":"MegaPose: 6D pose estimation of novel objects via render & compare","author":"Labb\u00e9","year":"2023","journal-title":"CoRL"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_18"},{"key":"ref10","article-title":"OnePose++: Keypoint-free one-shot object pose estimation without CAD models","author":"He","year":"2022","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635991"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00063"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref17","article-title":"TAP-Vid: A benchmark for tracking any point in a video","author":"Doersch","year":"2022","journal-title":"NeurIPS Datasets Track"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Track anything: Segment anything meets videos","year":"2023","author":"Yang","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2013.6696485"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696810"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487184"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.86"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341314"},{"article-title":"GenPose: Generative category-level object pose estimation via diffusion models","year":"2023","author":"Zhang","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00670"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161117"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_41"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04901"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"article-title":"Shapenet: An information-rich 3D model repository","year":"2015","author":"Chang","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906903"},{"key":"ref42","article-title":"Blender - a 3D modelling and rendering package","author":"Community","year":"2018","journal-title":"Blender Foundation, Stichting Blender Foundation, Amsterdam"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02040"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref46","article-title":"DROID-SLAM: Deep visual slam for monocular, stereo, and RGB-D cameras","author":"Teed","year":"2021","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9197374"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref50"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246949.pdf?arnumber=11246949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:14:08Z","timestamp":1765520048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246949","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}