{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:39:34Z","timestamp":1757608774998,"version":"3.44.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC62088102"],"award-info":[{"award-number":["NSFC62088102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007128","name":"Natural Science Foundation of Shaanxi Province","doi-asserted-by":"publisher","award":["2022JM-366"],"award-info":[{"award-number":["2022JM-366"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128845","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"15740-15746","source":"Crossref","is-referenced-by-count":0,"title":["Towards Accurate Semi-Supervised BEV 3D Object Detection with Depth-Aware Refinement and Denoising-Aided Alignment"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Yang","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications,Xi'an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinan","family":"Shi","sequence":"additional","affiliation":[{"name":"school of computation information and technology, Technical Unversity of Munich,Munich,Germany,80333"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangtong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications,Xi'an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longjun","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, the National Engineering Research Center for Visual Information and Applications,Xi'an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref4","first-page":"180","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref6","article-title":"Detr4d: Direct multi-view 3d object detection with sparse attention","author":"Luo","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref9","article-title":"Bevdet4d: Exploit temporal cues in multi-camera 3d object detection","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Bevfusion4d: Learning lidar-camera fusion under bird\u2019s-eye-view via cross-modality guidance and temporal aggregation","author":"Cai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref12","article-title":"Pscudo-lidar++: Accurate depth for 3d object detection in autonomous driving","author":"You","year":"2019","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref15","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"Tarvainen","year":"2017","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00712"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3270728"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_41"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01601"},{"key":"ref21","first-page":"49100","article-title":"Diffusion-ss3d: Diffusion model for semi-supervised 3d object detection","volume":"36","author":"Ho","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3220219"},{"key":"ref23","article-title":"Learning with noisy labels","volume":"26","author":"Natarajan","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","volume-title":"arXiv preprint","author":"Zhang","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref26","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"arXiv preprint","author":"Wilson","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128845.pdf?arnumber=11128845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:33:41Z","timestamp":1756881221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128845","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}