{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:49:32Z","timestamp":1784821772657,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0115803"],"award-info":[{"award-number":["2022ZD0115803"]}]},{"name":"Natural Science Basic Research Plan in Shaanxi Province of China","award":["2023-JC-JQ-51"],"award-info":[{"award-number":["2023-JC-JQ-51"]}]},{"name":"Key Research and Development Project in Shaanxi Province","award":["2023-ZDLNY-65"],"award-info":[{"award-number":["2023-ZDLNY-65"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2024.3366664","type":"journal-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:25:02Z","timestamp":1708111502000},"page":"5753-5764","source":"Crossref","is-referenced-by-count":96,"title":["Toward Robust LiDAR-Camera Fusion in BEV Space via Mutual Deformable Attention and Temporal Aggregation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4091-2165","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"first","affiliation":[{"name":"Shaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology, School of Information and Communications Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7566-1634","authenticated-orcid":false,"given":"Fan","family":"Li","sequence":"additional","affiliation":[{"name":"Shaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology, School of Information and Communications Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"An","sequence":"additional","affiliation":[{"name":"Shaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology, School of Information and Communications Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2772-2700","authenticated-orcid":false,"given":"Xuchong","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2153-2906","authenticated-orcid":false,"given":"Hongbin","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3296583"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00023"},{"key":"ref5","article-title":"Vision-centric BEV perception: A survey","author":"Ma","year":"2022","journal-title":"arXiv:2208.02797"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref9","first-page":"10421","article-title":"BEVFusion: A simple and robust LiDAR-camera fusion framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref11","first-page":"877","article-title":"Towards robust LiDAR-based perception in autonomous driving: General black-box adversarial sensor attack and countermeasures","volume-title":"Proc. 29th USENIX Secur. Symp. (USENIX Secur.)","author":"Sun"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01588"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00321"},{"key":"ref14","article-title":"On the adversarial robustness of camera-based 3D object detection","author":"Xie","year":"2023","journal-title":"arXiv:2301.10766"},{"key":"ref15","article-title":"Benchmarking bird\u2019s eye view detection robustness to real-world corruptions","volume-title":"Proc. Int. Conf. Learn. Represent. Workshop Scene Represent. Auton. Driving","author":"Xie"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02069"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197212"},{"key":"ref18","article-title":"3D object detection for autonomous driving: A comprehensive survey","author":"Mao","year":"2022","journal-title":"arXiv:2206.09474"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3260115"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100848"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref29","first-page":"16494","article-title":"Multimodal virtual point 3D detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Yin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00158"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00752"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248656"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3268849"},{"key":"ref47","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019","journal-title":"arXiv:1908.09492"},{"key":"ref48","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Qi"},{"key":"ref49","first-page":"1","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref51","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref53","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref56","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Wang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref59","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref60","volume-title":"MMDetection3D: OpenMMLab Next-generation Platform for General 3D Object Detection","author":"Contributors","year":"2020"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10438483.pdf?arnumber=10438483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:13:13Z","timestamp":1736453593000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10438483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":60,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3366664","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}