{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:35:23Z","timestamp":1780054523284,"version":"3.54.0"},"reference-count":123,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0160102"],"award-info":[{"award-number":["2022ZD0160102"]}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MOE AcRF Tier 2","award":["MOE-T2EP20221-0012"],"award-info":[{"award-number":["MOE-T2EP20221-0012"]}]},{"name":"MOE AcRF Tier 2","award":["MOE-T2EP20223-0002"],"award-info":[{"award-number":["MOE-T2EP20223-0002"]}]},{"name":"Industry Alignment Fund – Industry Collaboration Projects (IAF-ICP) Funding Initiative","award":["RIE2020"],"award-info":[{"award-number":["RIE2020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3535960","type":"journal-article","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T18:52:31Z","timestamp":1738176751000},"page":"3878-3894","source":"Crossref","is-referenced-by-count":20,"title":["Benchmarking and Improving Bird\u2019s Eye View Perception Robustness in Autonomous Driving"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1358-3010","authenticated-orcid":false,"given":"Shaoyuan","family":"Xie","sequence":"first","affiliation":[{"name":"Donald Bren School of Information and Computer Sciences, University of California, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3884-2185","authenticated-orcid":false,"given":"Lingdong","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Computing, CNRS@CREATE, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2748-4514","authenticated-orcid":false,"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1950-5976","authenticated-orcid":false,"given":"Jiawei","family":"Ren","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1821-4296","authenticated-orcid":false,"given":"Liang","family":"Pan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref3","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref4","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"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159589"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3333838"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref10","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3063611"},{"key":"ref12","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3550011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3314512"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.153"},{"key":"ref16","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01388"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01373"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00076"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083288"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref26","article-title":"Adversarial patch","author":"Brown","year":"2017"},{"key":"ref27","article-title":"DPatch: An adversarial patch attack on object detectors","author":"Liu","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3349304"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02079"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3535625"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00313"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00507"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01980"},{"key":"ref38","first-page":"75896","article-title":"Towards label-free scene understanding by vision foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref39","first-page":"37193","article-title":"Segment any point cloud sequences by distilling vision foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref40","article-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","author":"Contributors","year":"2020"},{"key":"ref41","article-title":"An empirical study of training state-of-the-art LiDAR segmentation models","author":"Sun","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3449912"},{"key":"ref44","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref46","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019"},{"key":"ref47","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref49","article-title":"Delving into transferable adversarial examples and black-box attacks","author":"Liu","year":"2016"},{"key":"ref50","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref51","article-title":"BEVerse: Unified perception and prediction in bird\u2019s-eye-view for vision-centric autonomous driving","author":"Zhang","year":"2022"},{"key":"ref52","article-title":"ORA3D: Overlap region aware multi-view 3D object detection","author":"Roh","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref54","article-title":"SRCN3D: Sparse R-CNN 3D surround-view camera object detection and tracking for autonomous driving","author":"Shi","year":"2022"},{"key":"ref55","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref59","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref60","first-page":"9453","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Barbu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref62","article-title":"On the adversarial robustness of camera-based 3D object detection","author":"Xie","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref65","first-page":"1","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Park"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref67","article-title":"BEVFusion: A simple and robust LiDAR-camera fusion framework","author":"Liang","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref69","article-title":"AutoAlignV2: Deformable feature aggregation for dynamic multi-modal 3D object detection","author":"Chen","year":"2022"},{"key":"ref70","first-page":"539","article-title":"SurroundDepth: Entangling surrounding views for self-supervised multi-camera depth estimation","volume-title":"Proc. Conf. Robot Learn.","author":"Wei"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref73","first-page":"21 600","article-title":"Understanding the robustness of 3D object detection with bird\u2019s-eye-view representations in autonomous driving","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zhu"},{"key":"ref74","first-page":"1663","article-title":"Lara: Latents and rays for multi-camera bird\u2019s-eye-view semantic segmentation","volume-title":"Proc. Conf. Robot Learn.","author":"Bartoccioni"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01830"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref78","article-title":"Occ-BEV: Multi-camera unified pre-training via 3D scene reconstruction","author":"Min","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00801"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341473"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref82","article-title":"Exploring recurrent long-term temporal fusion for multi-view 3D perception","author":"Han","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref84","first-page":"18 442","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref85","first-page":"21298","article-title":"RoboDepth: Robust out-of-distribution depth estimation under corruptions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong"},{"key":"ref86","article-title":"The RoboDepth challenge: Methods and advancements towards robust depth estimation","author":"Kong","year":"2023"},{"key":"ref87","first-page":"18 559","article-title":"Benchmarking and analyzing point cloud classification under corruptions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01710-9"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"ref100","article-title":"PETRv2: A unified framework for 3D perception from multi-camera images","author":"Liu","year":"2022"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00028"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref104","article-title":"AMVNet: Assertion-based multi-view fusion network for LiDAR semantic segmentation","author":"Liong","year":"2020"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01572"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160410"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref112","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27880"},{"key":"ref114","first-page":"21 455","article-title":"Quality not quantity: On the interaction between dataset design and robustness of CLIP","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref115","first-page":"7721","article-title":"Accuracy on the line: On the strong correlation between out-of-distribution and in-distribution generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Miller"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref120","article-title":"Understanding the robustness of multi-modal contrastive learning to distribution shift","author":"Xue","year":"2023"},{"key":"ref121","first-page":"6216","article-title":"Data determines distributional robustness in contrastive language image pre-training (CLIP)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fang"},{"key":"ref122","first-page":"23 965","article-title":"Model soups: Averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wortsman"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01853"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10857618.pdf?arnumber=10857618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:13:28Z","timestamp":1744305208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10857618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":123,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3535960","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":[[2025,5]]}}}