{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T17:00:32Z","timestamp":1790960432130,"version":"4.1.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668584","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:20:44Z","timestamp":1790277644000},"page":"6365-6377","source":"Crossref","is-referenced-by-count":1,"title":["SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6798-1083","authenticated-orcid":false,"given":"Yiheng","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory, Institute of Computing Technology, Chinese Academy of Sciences (CAS)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[{"name":"independent researcher, resides in Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-208X","authenticated-orcid":false,"given":"Zehao","family":"Huang","sequence":"additional","affiliation":[{"name":"independent researcher, resides in Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2668-0070","authenticated-orcid":false,"given":"Hong","family":"Chang","sequence":"additional","affiliation":[{"name":"State Key Laboratory, Institute of Computing Technology, Chinese Academy of Sciences (CAS)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0526-3331","authenticated-orcid":false,"given":"Naiyan","family":"Wang","sequence":"additional","affiliation":[{"name":"independent researcher, resides in Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BEVDet: High-performance multi-camera 3D object detection in Bird-Eye-View","author":"Huang","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00351"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3502456"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588783"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00625"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189778"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0026"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref15","first-page":"6664","article-title":"Cluster-Former: Cluster-based transformer for 3D object detection in point clouds","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Pei","year":"2023"},{"key":"ref16","first-page":"923","article-title":"End-to-end multi-view fusion for 3D object detection in LiDAR point clouds","volume-title":"Proc. Conf. Robot Learn.","author":"Zhou","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00122"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref24","article-title":"M2BEV: Multi-camera joint 3D detection and segmentation with unified Birds-Eye View representation","author":"Xie","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3414835"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref27","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","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref29","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00801"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref35","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wilson","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref38","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","author":"Qi","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304054"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2309"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1733"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275366"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00310"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01901"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01441"},{"key":"ref48","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref50","first-page":"146","article-title":"OPEN: Object-wise position embedding for multi-view 3D object detection","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Hou","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref52","article-title":"FusionFormer: A multi-sensory fusion in Birds-Eye-View and temporal consistent transformer for 3D objection","author":"Hu","year":"2023"},{"key":"ref53","article-title":"EA-LSS: Edge-aware lift-splat-shot framework for 3D BEV object detection","author":"Hu","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref58","article-title":"BEVPoolv2: A cutting-edge implementation of BEVDET toward deployment","author":"Huang","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3392303"},{"key":"ref64","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019"},{"key":"ref65","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00103"},{"key":"ref67","article-title":"BEVDET4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3401172"},{"key":"ref69","article-title":"BEVFusion4D: Learning LiDAR-camera fusion under birds-eye-view via cross-modality guidance and temporal aggregation","author":"Cai","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00301"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_32"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01674"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00730"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00768"},{"key":"ref75","article-title":"M$^{2}$-3DLaneNet: Exploring multi-modal 3D lane detection","author":"Luo","year":"2022"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11709506.pdf?arnumber=11709506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T04:49:06Z","timestamp":1790398146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11709506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668584","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}