{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:18:03Z","timestamp":1778051883169,"version":"3.51.4"},"reference-count":41,"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"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001869","name":"Academia Sinica","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001869","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00746","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7730-7739","source":"Crossref","is-referenced-by-count":0,"title":["KMOPS: Keypoint-Driven Method for Multi-Object Pose and Metric Size Estimation from Stereo Images"],"prefix":"10.1109","author":[{"given":"Ying-Kun","family":"Wu","sequence":"first","affiliation":[{"name":"University of Minnesota,Twin Cities"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzuhsuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"I-Sheng","family":"Fang","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-Cheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00296"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00277"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160780"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s24041076"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811799"},{"key":"ref12","article-title":"Poet: Pose estimation transformer for single-view, multi-object 6d pose estimation","author":"Jantos","year":"2023","journal-title":"CoRL. PMLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01086"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00191"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812299"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01380"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01069"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref24","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"ref26","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res., 2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989233"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_32"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref33","first-page":"180","article-title":"DETR3D: 3d object detection from multi-view images via 3d-to-2d queries","author":"Wang","year":"2021","journal-title":"CoRL"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00875"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_19"},{"key":"ref37","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2023","journal-title":"ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00480"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_12"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref41","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","author":"Zhu","year":"2021","journal-title":"ICLR"}],"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\/11492358.pdf?arnumber=11492358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:31:46Z","timestamp":1778049106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00746","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}