{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:45:32Z","timestamp":1787161532813,"version":"build-2736575974"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2042"],"award-info":[{"award-number":["U21B2042"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836014"],"award-info":[{"award-number":["61836014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2035 Innovation Program of CAS"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tpami.2025.3568120","type":"journal-article","created":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T13:38:22Z","timestamp":1746711502000},"page":"7021-7035","source":"Crossref","is-referenced-by-count":2,"title":["Uncertain Object Representation for Image-Based 3D Object Perception"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2191-9988","authenticated-orcid":false,"given":"Qitai","family":"Wang","sequence":"first","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9555-1897","authenticated-orcid":false,"given":"Yuntao","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref3","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","author":"Wang","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00280"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref9","first-page":"351","article-title":"Fully sparse 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan","year":"2022"},{"key":"ref10","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_42"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"ref20","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Proc. Conf. Robot Learn.","author":"Wang","year":"2022"},{"key":"ref21","article-title":"MonoDistill: Learning spatial features for monocular 3D object detection","author":"Chong","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref23","article-title":"Pseudo-LiDAR++: Accurate depth for 3D object detection in autonomous driving","author":"You","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00592"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref26","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"ref29","first-page":"2294","article-title":"CC-3DT: Panoramic 3D object tracking via cross-camera fusion","volume-title":"Proc. Mach. Learn. Res.","author":"Fischer","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3168781"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00496"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00500"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01719"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3096854"},{"key":"ref35","first-page":"5574","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30: Annu. Conf. Neural Inf. Process. Syst.","author":"Kendall","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460700"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917494"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793821"},{"key":"ref39","first-page":"42","article-title":"Benchmarking sampling-based probabilistic object detectors","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Miller","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196544"},{"key":"ref41","article-title":"Uncertainty in deep learning","author":"Gal","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295387"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00355"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00281"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01296"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462978"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25460"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"ref49","article-title":"SRCN3D: Sparse R-CNN 3D surround-view camera object detection and tracking for autonomous driving","author":"Shi","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25056-9_43"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref54","article-title":"A baseline for 3D multi-object tracking","author":"Weng","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref57","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref58","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"ref61","article-title":"Immortal tracker: Tracklet never dies","author":"Wang","year":"2021"},{"key":"ref62","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","volume":"164","author":"Wang","year":"2021"},{"key":"ref63","first-page":"18442","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00493"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105438"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11068886\/10993323.pdf?arnumber=10993323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T13:50:49Z","timestamp":1751637049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10993323\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":68,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3568120","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}