{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T01:33:31Z","timestamp":1773452011891,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376060"],"award-info":[{"award-number":["62376060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tpami.2025.3565194","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T17:31:40Z","timestamp":1745947900000},"page":"6749-6763","source":"Crossref","is-referenced-by-count":9,"title":["DeepInteraction++: Multi-Modality Interaction for Autonomous Driving"],"prefix":"10.1109","volume":"47","author":[{"given":"Zeyu","family":"Yang","sequence":"first","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}]},{"given":"Nan","family":"Song","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9284-2955","authenticated-orcid":false,"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1031-5420","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0259-5732","authenticated-orcid":false,"given":"Philip H.S.","family":"Torr","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref3","first-page":"16494","article-title":"Multimodal virtual point 3D detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yin"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00119"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160968"},{"key":"ref9","article-title":"BEVFusion: A simple and robust LiDAR-Camera fusion framework","author":"Liang","year":"2022"},{"key":"ref10","first-page":"1992","article-title":"Deepinteraction: 3D object detection via modality interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref11","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"ref27","article-title":"Range conditioned dilated convolutions for scale invariant 3D object detection","author":"Bewley","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01574"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00827"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref33","first-page":"20745","article-title":"Object DGCNN: 3D object detection using dynamic graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01515"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00446"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_25"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00625"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref42","article-title":"SparseFusion: Efficient sparse multi-modal fusion framework for long-range 3D perception","author":"Li","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00570"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330866"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2018.00013"},{"key":"ref52","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dao"},{"key":"ref53","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023"},{"key":"ref54","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref55","first-page":"68","article-title":"Stand-alone self-attention in vision models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ramachandran"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_20"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3392303"},{"key":"ref62","first-page":"351","article-title":"Fully sparse 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref65","article-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref70","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_21"},{"key":"ref75","article-title":"GPT-driver: Learning to drive with GPT","author":"Mao","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11068886\/10980037.pdf?arnumber=10980037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T22:57:23Z","timestamp":1751929043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10980037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":75,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3565194","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":[[2025,8]]}}}