{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T23:09:21Z","timestamp":1783552161818,"version":"3.55.0"},"reference-count":79,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tits.2026.3651273","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T20:51:29Z","timestamp":1768596689000},"page":"6027-6039","source":"Crossref","is-referenced-by-count":1,"title":["CrossRay3D: Geometry and Distribution Guidance for Efficient Multimodal 3D Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3485-937X","authenticated-orcid":false,"given":"Huiming","family":"Yang","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhuo","family":"Liu","sequence":"additional","affiliation":[{"name":"Division of Energy-Mobility Convergence, Beijing Institute of Technology, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3790-6400","authenticated-orcid":false,"given":"Yicheng","family":"Qiao","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1800-6892","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianzhu","family":"Zeng","sequence":"additional","affiliation":[{"name":"Division of Energy-Mobility Convergence, Beijing Institute of Technology, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9325-2391","authenticated-orcid":false,"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7071-199X","authenticated-orcid":false,"given":"Zhiwei","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Chemical Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6038-5155","authenticated-orcid":false,"given":"Zijian","family":"Zeng","sequence":"additional","affiliation":[{"name":"Institute of Computer Science and Digital Innovation, UCSI University, Kuala Lumpur, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8840-7056","authenticated-orcid":false,"given":"Zhiying","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beijing University of Chemical Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4042-6044","authenticated-orcid":false,"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2744-1191","authenticated-orcid":false,"given":"Kunfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Chemical Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892405"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref3","article-title":"Multi-modal fusion technology based on vehicle information: A survey","author":"Gong","year":"2022","journal-title":"arXiv:2211.06080"},{"key":"ref4","article-title":"MIPD: A multi-sensory interactive perception dataset for embodied intelligent driving","author":"Li","year":"2024","journal-title":"arXiv:2411.05881"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02102"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3303334"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107575"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/drones9040300"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3411486"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3728308"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130918"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05552-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"ref18","first-page":"18442","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref20","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref21","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv:2203.03605"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IHMSC66529.2025.00020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref25","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":"ref26","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0026"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3328929"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref35","article-title":"Submanifold sparse convolutional networks","author":"Graham","year":"2017","journal-title":"arXiv:1706.01307"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3568418"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3266727"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3429139"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref42","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref45","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-024-00296-x"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3325360"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3319547"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3394550"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3323036"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00644"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS57906.2023.10156162"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3556852"},{"key":"ref58","article-title":"TEM3-learning: Time-efficient multimodal multi-task learning for advanced assistive driving","author":"Liu","year":"2025","journal-title":"arXiv:2506.18084"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3332608"},{"key":"ref62","article-title":"Sparse DETR: Efficient end-to-end object detection with learnable sparsity","author":"Roh","year":"2021","journal-title":"arXiv:2111.14330"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref64","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023","journal-title":"arXiv:2301.00493"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref67","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019","journal-title":"arXiv:1908.09492"},{"key":"ref68","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref71","first-page":"16494","article-title":"Multimodal virtual point 3D detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Yin"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21428\/594757db.d733a905"},{"key":"ref74","first-page":"1992","article-title":"DeepInteraction: 3D object detection via modality interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00105"},{"key":"ref78","article-title":"PoIFusion: Multi-modal 3D object detection via fusion at points of interest","author":"Deng","year":"2024","journal-title":"arXiv:2403.09212"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3392303"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11512109\/11355997.pdf?arnumber=11355997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:42:11Z","timestamp":1778269331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11355997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":79,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tits.2026.3651273","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}