{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:13:40Z","timestamp":1778184820980,"version":"3.51.4"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019048","name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","doi-asserted-by":"publisher","award":["JYB2025XDXM504"],"award-info":[{"award-number":["JYB2025XDXM504"]}],"id":[{"id":"10.13039\/501100019048","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62373298"],"award-info":[{"award-number":["62373298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["U24A20252"],"award-info":[{"award-number":["U24A20252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100019054","name":"Nansha Key Science and Technology Project","doi-asserted-by":"publisher","award":["2023ZD006"],"award-info":[{"award-number":["2023ZD006"]}],"id":[{"id":"10.13039\/501100019054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3654118","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:41:30Z","timestamp":1768423290000},"page":"5815-5827","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Modal Decouple and Recouple Network for Robust 3D Object Detection"],"prefix":"10.1109","volume":"36","author":[{"given":"Rui","family":"Ding","sequence":"first","affiliation":[{"name":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaonian","family":"Kuang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhe","family":"Ji","sequence":"additional","affiliation":[{"name":"Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0525-5059","authenticated-orcid":false,"given":"Meng","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9898-5543","authenticated-orcid":false,"given":"Xinhu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9522-6157","authenticated-orcid":false,"given":"Gang","family":"Hua","sequence":"additional","affiliation":[{"name":"Multimodal Experiences Research Laboratory, Dolby Laboratories, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith"},{"issue":"1","key":"ref2","first-page":"795","article-title":"Algorithms for learning kernels based on centered alignment","volume":"13","author":"Cortes","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0052"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475314"},{"key":"ref7","article-title":"DualBEV: CNN is all you need in view transformation","author":"Li","year":"2024","journal-title":"arXiv:2403.05402"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3352808"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952201"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3201469"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3427701"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3463409"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3430473"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189778"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270638"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410117"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3145663"},{"key":"ref18","first-page":"1992","article-title":"DeepInteraction: 3D object detection via modality interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3146017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00801"},{"key":"ref24","article-title":"CrossFusion: Interleaving cross-modal complementation for noise-resistant 3D object detection","author":"Yang","year":"2023","journal-title":"arXiv:2304.09694"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3366664"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01830"},{"key":"ref28","article-title":"RoboBEV: Towards robust Bird\u2019s eye view perception under corruptions","author":"Xie","year":"2023","journal-title":"arXiv:2304.06719"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref33","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3333225"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180210"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3245359"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275366"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304054"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3405992"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3628019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3600527"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00105"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00321"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3216611"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_20"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"ref49","first-page":"1272","article-title":"RoboFusion: Towards robust multi-modal 3D object detection via SAM","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"Song"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref51","article-title":"WeatherDG: LLM-assisted diffusion model for procedural weather generation in domain-generalized semantic segmentation","author":"Qian","year":"2024","journal-title":"arXiv:2410.12075"},{"key":"ref52","article-title":"Image augmentation agent for weakly supervised semantic segmentation","author":"Wu","year":"2024","journal-title":"arXiv:2412.20439"},{"key":"ref53","article-title":"Prompt categories cluster for weakly supervised semantic segmentation","author":"Wu","year":"2024","journal-title":"arXiv:2412.13823"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111154"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref56","first-page":"63529","article-title":"Achieving cross modal generalization with multimodal unified representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xia"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.27055"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358850"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111200"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102025"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272734"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref64","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref66","article-title":"3D dual-fusion: Dual-domain dual-query camera-LiDAR fusion for 3D object detection","author":"Kim","year":"2022","journal-title":"arXiv:2211.13529"},{"key":"ref67","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":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref69","first-page":"18442","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref73","volume-title":"MMDetection3D: OpenMMLab Next-Generation Platform for General 3D Object Detection","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3542993"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11352951.pdf?arnumber=11352951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:56:01Z","timestamp":1778183761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11352951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":74,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3654118","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}