{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T23:09:22Z","timestamp":1783552162090,"version":"3.55.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["2022ZD0160604"],"award-info":[{"award-number":["2022ZD0160604"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176194"],"award-info":[{"award-number":["62176194"]}],"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":["62272357"],"award-info":[{"award-number":["62272357"]}],"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":["62202348"],"award-info":[{"award-number":["62202348"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Hubei Province","award":["2024BAB030"],"award-info":[{"award-number":["2024BAB030"]}]},{"name":"Key Research and Development Program of Hubei Province","award":["2022BAA052"],"award-info":[{"award-number":["2022BAA052"]}]},{"name":"Project of Sanya Yazhou Bay Science and Technology City","award":["SCKJ-JYRC-2022-76"],"award-info":[{"award-number":["SCKJ-JYRC-2022-76"]}]},{"name":"Project of Sanya Yazhou Bay Science and Technology City","award":["SKJC-2022-PTDX-031"],"award-info":[{"award-number":["SKJC-2022-PTDX-031"]}]},{"name":"Project of Sanya Science and Education Innovation Park of Wuhan University of Technology","award":["2021KF0031"],"award-info":[{"award-number":["2021KF0031"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["104972024JYS0066"],"award-info":[{"award-number":["104972024JYS0066"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Knowledge Innovation Program of Wuhan-Shuguang Project","award":["2023010201020323"],"award-info":[{"award-number":["2023010201020323"]}]},{"name":"Hubei Provincial Natural Science Foundation of China","award":["2023AFB697"],"award-info":[{"award-number":["2023AFB697"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tits.2025.3599015","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:46:05Z","timestamp":1758563165000},"page":"21257-21270","source":"Crossref","is-referenced-by-count":1,"title":["HybridBEV: Hybrid Encode and Distillation for Improved BEV 3D Object Detection"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5845-3615","authenticated-orcid":false,"given":"Junyin","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7275-5064","authenticated-orcid":false,"given":"Chenghu","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3727-9397","authenticated-orcid":false,"given":"Huikai","family":"Liu","sequence":"additional","affiliation":[{"name":"VOYAH Automobile Technology Company Ltd., Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8295-8359","authenticated-orcid":false,"given":"Zhenchang","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8403-1776","authenticated-orcid":false,"given":"Bingyi","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4006-7029","authenticated-orcid":false,"given":"Shengwu","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3253554"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"ref5","article-title":"M2BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation","author":"Xie","year":"2022","journal-title":"arXiv:2204.05088"},{"key":"ref6","article-title":"HFT: Lifting perspective representations via hybrid feature transformation","author":"Zou","year":"2022","journal-title":"arXiv:2204.05068"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_40"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01528"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref12","article-title":"UniBEV: Multi-modal 3D object detection with uniform BEV encoders for robustness against missing sensor modalities","author":"Wang","year":"2023","journal-title":"arXiv:2309.14516"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref14","article-title":"Fast-BEV: Towards real-time on-vehicle bird\u2019s-eye view perception","author":"Huang","year":"2023","journal-title":"arXiv:2301.07870"},{"key":"ref15","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00310"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72907-2_17"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref20","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial\u2013temporal fusion","author":"Lin","year":"2022","journal-title":"arXiv:2211.10581"},{"key":"ref21","first-page":"64318","article-title":"Occ3D: A large-scale 3D occupancy prediction benchmark for autonomous driving","volume-title":"Proc. NIPS","author":"Tian"},{"key":"ref22","first-page":"8406","article-title":"Scene as occupancy","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Sima"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3394550"},{"key":"ref24","article-title":"EA-BEV: Edge-aware bird\u2019s-eye-view projector for 3D object detection","author":"Hu","year":"2023","journal-title":"arXiv:2303.17895"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref29","article-title":"BEV-LGKD: A unified LiDAR-guided knowledge distillation framework for BEV 3D object detection","author":"Li","year":"2022","journal-title":"arXiv:2212.00623"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28577"},{"key":"ref32","article-title":"TiG-BEV: Multi-view BEV 3D object detection via target inner-geometry learning","author":"Huang","year":"2022","journal-title":"arXiv:2212.13979"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00495"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01282"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3319430"},{"key":"ref37","first-page":"87","article-title":"STXD: Structural and temporal cross-modal distillation for multi-view 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jang"},{"key":"ref38","article-title":"BEVDistill: Cross-modal BEV distillation for multi-view 3D object detection","author":"Chen","year":"2022","journal-title":"arXiv:2211.09386"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_23"},{"key":"ref43","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":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"ref48","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. NIPS","author":"Chen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00139"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00314"},{"key":"ref51","article-title":"Towards efficient 3D object detection with knowledge distillation","author":"Yang","year":"2022","journal-title":"arXiv:2205.15156"},{"key":"ref52","article-title":"Unifying voxel-based representation with transformer for 3D object detection","author":"Li","year":"2022","journal-title":"arXiv:2206.00630"},{"key":"ref53","article-title":"BEVerse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","author":"Zhang","year":"2022","journal-title":"arXiv:2205.09743"},{"key":"ref54","article-title":"EA-LSS: Edge-aware lift-splat-shot framework for 3D BEV object detection","author":"Hu","year":"2023","journal-title":"arXiv:2303.17895"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611436"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00102"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_38"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01901"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3520814"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00098"},{"key":"ref65","article-title":"Leveraging vision-centric multi-modal expertise for 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Huang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00793"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_2"},{"key":"ref68","article-title":"MonoTAKD: Teaching assistant knowledge distillation for monocular 3D object detection","author":"Liu","year":"2024","journal-title":"arXiv:2404.04910"},{"key":"ref69","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. ICCV","author":"Kaiming"},{"key":"ref70","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019","journal-title":"arXiv:1908.09492"},{"key":"ref71","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref73","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":"ref74","article-title":"Using effective dimension to analyze feature transformations in deep neural networks","volume-title":"Proc. ICML, Workshop Identifying Understand. Deep Learn. Phenomena","author":"Ravichandran"},{"key":"ref75","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref76","article-title":"HybriMap: Hybrid clues utilization for effective vectorized HD map construction","author":"Zhang","year":"2024","journal-title":"arXiv:2404.11155"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11241045\/11175584.pdf?arnumber=11175584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T18:43:37Z","timestamp":1762973017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11175584\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":76,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3599015","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}