{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:01:29Z","timestamp":1780444889489,"version":"3.54.1"},"reference-count":438,"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"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2024C01065"],"award-info":[{"award-number":["2024C01065"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2025C01061"],"award-info":[{"award-number":["2025C01061"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/comst.2025.3599596","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:50:49Z","timestamp":1755546649000},"page":"3478-3520","source":"Crossref","is-referenced-by-count":20,"title":["Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7275-0810","authenticated-orcid":false,"given":"Kun","family":"Shi","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Nanyang, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1505-6766","authenticated-orcid":false,"given":"Shibo","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Shi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2865-0710","authenticated-orcid":false,"given":"Anjun","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4440-941X","authenticated-orcid":false,"given":"Zehui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Pillar of Information Systems Technology and Design, Singapore University of Technology and Design, Tampines, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3155-3145","authenticated-orcid":false,"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7036-5158","authenticated-orcid":false,"given":"Jun","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Nanyang, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3336917"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3145856"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3298300"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221952"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2023.3334269"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3353265"},{"key":"ref7","article-title":"OmniDrive: A holistic LLM-agent framework for autonomous driving with 3-D perception, reasoning and planning","author":"Wang","year":"2024","journal-title":"arXiv:2405.01533"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/s20247283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3312382"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3409556"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02293-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.087"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3096854"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108796"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3317372"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01790-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962554"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046478"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103448"},{"key":"ref23","volume-title":"A tutorial on multiple extended object tracking","author":"Granstr\u00f6m","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12020308"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023541"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.20"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3041615"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3398004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/s22072542"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186647"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/su14095114"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2021.3093379"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3307157"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3166911"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3073032"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3371482"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2533542"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794312"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3059674"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592517"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.006.2200730"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2023.3283864"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21924\/cst.1.1.2016.7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1117\/12.883775"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2021.3128825"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CONECCT55679.2022.9865707"},{"key":"ref48","article-title":"Key technologies and application for radar and smart video fusion in perimeter intrusion alarm system","author":"Fu","year":"2023","journal-title":"arXiv:2308.14252"},{"key":"ref49","first-page":"1","article-title":"An efficient intrusion detecting method using multiple sensors and edge computing","volume":"13","author":"Lee","year":"2023","journal-title":"Human Centric Comput. Inf. Sci."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023957"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2019.2929974"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3084891"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561275"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/jmse9111199"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341432"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/rs13173364"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICKII51822.2021.9574744"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3217537"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3322851"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MetroAeroSpace57412.2023.10189934"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/RadarConf2351548.2023.10149552"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160681"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01498"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01077"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3415772"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3390\/jmse11091794"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3550325"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1177\/0954407020912137"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3390\/s23084159"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/SECON55815.2022.9918553"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3628453"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.3390\/s24010172"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3288850"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3180632"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3011809"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT58465.2023.10143104"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT46573.2021.9453703"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3253906"},{"key":"ref79","volume-title":"Principles of Modern Radar","author":"Richards","year":"2010"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3182652"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483267"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3397321"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483258"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3197416"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796905"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196884"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231160195"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197298"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562089"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION49465.2021.9627037"},{"key":"ref92","first-page":"129","article-title":"Automotive radar dataset for deep learning based 3-D object detection","volume-title":"Proc. Eur. Radar Conf. (EuRAD)","author":"Meyer"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3061270"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00055"},{"key":"ref95","first-page":"3819","article-title":"K-Radar: 4-D radar object detection for autonomous driving in various weather conditions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Paek"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3147324"},{"key":"ref97","article-title":"Dual radar: A multi-modal dataset with dual 4-D radar for autononous driving","author":"Zhang","year":"2023","journal-title":"arXiv:2310.07602"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2011.08.001"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3187138"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01170"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413181"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00058"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CRV52889.2021.00021"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01651"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3373310"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00214"},{"key":"ref107","volume-title":"All-in-one drive: A large-scale comprehensive perception dataset with high-density long-range point clouds","author":"Weng","year":"2020"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/itsc55140.2022.9922539"},{"key":"ref109","article-title":"Aimotive dataset: A multimodal dataset for robust autonomous driving with long-range perception","author":"Matuszka","year":"2022","journal-title":"arXiv:2211.09445"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01232"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50115-4_41"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00121"},{"key":"ref113","first-page":"6","article-title":"Density-based spatial clustering of applications with noise","volume-title":"Proc. Int. Conf. Knowl. Disc. Data Min.","volume":"240","author":"Ester"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/APSCON56343.2023.10101274"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803392"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191046"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/SDF.2019.8916629"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.3390\/s20040956"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01615"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3240287"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/S0262-8856(97)00093-0"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.09.003"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref126","article-title":"BEVDet: High-performance multi-camera 3-D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.920469"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334537"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.3390\/s110908992"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.03.080"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS.2017.8204237"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139473"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.023"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2018.8581329"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794186"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/EuRAD48048.2021.00079"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3061364"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2020.1819874"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3268866.3268868"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3033698"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561938"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3311680"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593693"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917135"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1117\/12.2587994"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340866"},{"key":"ref149","first-page":"366","article-title":"Joint radar alignment and odometry calibration","volume-title":"Proc. 18th Int. Conf. Inf. Fusion (Fusion)","author":"Kellner"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.23919\/ENC48637.2020.9317343"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1145\/3649447"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096835"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref155","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref156","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3-D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422593"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICMIM.2015.7117922"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34879-3_27"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10040424"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68780-9_24"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-39770-8_11"},{"key":"ref165","article-title":"YOdar: Uncertainty-based sensor fusion for vehicle detection with camera and radar sensors","author":"Kowol","year":"2020","journal-title":"arXiv:2010.03320"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00895"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/RadarConf2351548.2023.10149729"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3167251"},{"key":"ref169","first-page":"7","article-title":"Radar and camera early fusion for vehicle detection in advanced driver assistance systems","volume-title":"Proc. Mach. Learn. Auton. Driving Workshop 33rd Conf. Neural Inf. Process. Syst.","volume":"2","author":"Lim"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564904"},{"key":"ref171","article-title":"RadSegNet: A reliable approach to radar camera fusion","author":"Bansal","year":"2022","journal-title":"arXiv:2208.03849"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3280525"},{"key":"ref174","first-page":"1","article-title":"Echoes beyond points: Unleashing the power of raw radar data in multi-modality fusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref176","first-page":"180","article-title":"DETR3-D: 3-D object detection from multi-view images via 3-D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25198"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161329"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341793"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3507538"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3357775"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP48669.2020.9320985"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453532"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02103"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341177"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_6"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2200299"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430776"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCC55723.2022.9984358"},{"key":"ref194","article-title":"Unleashing HyDRa: Hybrid fusion, depth consistency and radar for unified 3-D perception","author":"Wolters","year":"2024","journal-title":"arXiv:2403.07746"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3380244"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00134"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01589"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610929"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413682"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3387700"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref207","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref208","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Dai"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref212","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref214","article-title":"YOLOX: Exceeding Yolo series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.02976"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref218","article-title":"DSSD: Deconvolutional single shot detector","author":"Fu","year":"2017","journal-title":"arXiv:1701.06659"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref224","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref225","article-title":"Probabilistic two-stage detection","author":"Zhou","year":"2021","journal-title":"arXiv:2103.07461"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref228","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1002\/9780470283158"},{"key":"ref234","volume-title":"Fundamentals of Radar Signal Processing","author":"Richards","year":"2014"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3237494"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2491329"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952908"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2019.2893528"},{"key":"ref239","first-page":"1","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":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00327"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01180"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00738"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01710-9"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917000"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION45008.2020.9190261"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2022.100275"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294546"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION52260.2023.10224223"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3322729"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/RadarConf2147009.2021.9455172"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00023"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9048939"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00059"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3058895"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/563\/4\/042027"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207080"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827281"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967272"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3036047"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2006.888597"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/ICVES.2011.5983805"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/ChiCC.2016.7553978"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.3390\/en13010116"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917504"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746764"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1109\/IVWorkshops54471.2021.9669223"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575636"},{"key":"ref280","article-title":"HVDetFusion: A simple and robust camera-radar fusion framework","author":"Lei","year":"2023","journal-title":"arXiv:2307.11323"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3328953"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564627"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00183"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref286","first-page":"133","article-title":"Deep learning based 3-D object detection for automotive radar and camera","volume-title":"Proc. IEEE Eur. Radar Conf. (EuRAD)","author":"Meyer"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_23"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00022"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25270"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00325"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01414"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922457"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463654"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463655"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00316"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463653"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3229703"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.3390\/math11020361"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00901"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref309","first-page":"10421","article-title":"BEVFusion: A simple and robust LiDAR-camera fusion framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liang"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2003.809413"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/MAES.2004.1263228"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1109\/7.210087"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref318","article-title":"ByteTrackV2: 2-D and 3-D multi-object tracking by associating every detection box","author":"Zhang","year":"2023","journal-title":"arXiv:2303.15334"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25056-9_43"},{"key":"ref320","article-title":"TransTrack: Multiple object tracking with transformer","author":"Sun","year":"2020","journal-title":"arXiv:2012.15460"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00485"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225078"},{"key":"ref323","volume-title":"Statistical Multisource-Multitarget Information Fusion","volume":"685","author":"Mahler","year":"2007"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2946.001.0001"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1109\/78.782219"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1117\/12.280797"},{"key":"ref328","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.1970.310128"},{"key":"ref329","doi-asserted-by":"publisher","DOI":"10.1109\/MAES.2020.3002001"},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1109\/7.640267"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1109\/9.489270"},{"key":"ref332","doi-asserted-by":"publisher","DOI":"10.1109\/7.543865"},{"key":"ref333","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/428036"},{"key":"ref334","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.1985.310548"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2001.946220"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.2002.0440"},{"key":"ref337","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2017.2664598"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2003.1261119"},{"key":"ref339","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2013.2262753"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3298646"},{"key":"ref341","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2007.894241"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2007.4441756"},{"key":"ref343","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2012.6178085"},{"key":"ref344","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2257765"},{"key":"ref345","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2641392"},{"key":"ref346","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2853120"},{"key":"ref347","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.2007924"},{"key":"ref348","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3240740"},{"key":"ref349","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2946023"},{"key":"ref350","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2018.2805153"},{"key":"ref351","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294735"},{"key":"ref352","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917144"},{"key":"ref353","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION43075.2019.9011217"},{"key":"ref354","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588837"},{"key":"ref355","doi-asserted-by":"publisher","DOI":"10.1109\/7.625124"},{"key":"ref356","doi-asserted-by":"publisher","DOI":"10.1109\/ICIF.2010.5711956"},{"key":"ref357","first-page":"886","article-title":"The exact algorithm for multi-sensor asynchronous track-to-track fusion","volume-title":"Proc. IEEE 18th Int. Conf. Inf. Fusion (Fusion)","author":"Lu"},{"key":"ref358","doi-asserted-by":"publisher","DOI":"10.1109\/RoboMech.2016.7813156"},{"key":"ref359","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957663"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2094188"},{"key":"ref361","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2008.4621245"},{"key":"ref362","doi-asserted-by":"publisher","DOI":"10.1109\/NAECON46414.2019.9058168"},{"key":"ref363","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2018.8581246"},{"key":"ref364","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2009.2032769"},{"key":"ref365","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917238"},{"key":"ref366","doi-asserted-by":"publisher","DOI":"10.3390\/s21041116"},{"key":"ref367","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340932"},{"key":"ref368","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3325527"},{"key":"ref369","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00306"},{"key":"ref370","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3421339"},{"key":"ref371","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588514"},{"key":"ref372","doi-asserted-by":"publisher","DOI":"10.1109\/RadarConf2458775.2024.10548703"},{"key":"ref373","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00076"},{"key":"ref374","first-page":"1","article-title":"Exploring adversarial robustness of multi-sensor perception systems in self driving","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","author":"Tu"},{"key":"ref375","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref376","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161428"},{"key":"ref377","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.04.002"},{"key":"ref378","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230441"},{"key":"ref379","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref380","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref381","first-page":"12","article-title":"Robust human detection under visual degradation via thermal and mmWave radar fusion","volume-title":"Proc. Int. Conf. Embedded Wireless Syst. Netw.","author":"Cai"},{"key":"ref382","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref383","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10066-4"},{"key":"ref384","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01462"},{"key":"ref385","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.04.013"},{"key":"ref386","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2021.773142"},{"key":"ref387","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref388","first-page":"5","article-title":"Improving data augmentation for multi-modality 3-D object detection","volume-title":"Proc. Int. Conf. Learn. Rep. Workshop Scene Rep. Auton. Driving","author":"Zhang"},{"key":"ref389","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44851-5_45"},{"key":"ref390","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref391","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3398724"},{"key":"ref392","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref393","first-page":"1","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Dao"},{"key":"ref394","article-title":"Vl-mamba: Exploring state space models for multimodal learning","author":"Qiao","year":"2024","journal-title":"arXiv:2403.13600"},{"key":"ref395","article-title":"Cobra: Extending mamba to multi-modal large language model for efficient inference","author":"Zhao","year":"2024","journal-title":"arXiv:2403.14520"},{"key":"ref396","article-title":"CFMW: Cross-modality fusion mamba for Multispectral object detection under adverse weather conditions","author":"Li","year":"2024","journal-title":"arXiv:2404.16302"},{"key":"ref397","article-title":"Fusion-mamba for cross-modality object detection","author":"Dong","year":"2024","journal-title":"arXiv:2404.09146"},{"key":"ref398","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"ref399","article-title":"Sigma: Siamese mamba network for multi-modal semantic segmentation","author":"Wan","year":"2024","journal-title":"arXiv:2404.04256"},{"key":"ref400","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8858-3_1"},{"key":"ref401","article-title":"Exploring learning-based motion models in multi-object tracking","author":"Huang","year":"2024","journal-title":"arXiv:2403.10826"},{"key":"ref402","first-page":"1","article-title":"vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref403","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00752"},{"key":"ref404","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref405","article-title":"Achelous++: Power-oriented waterway multi-task panoptic perception framework based on vision-radar fusion","author":"Guana","year":"2023","journal-title":"arXiv:2312.08851"},{"key":"ref406","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421802"},{"key":"ref407","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588795"},{"key":"ref408","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref409","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01467"},{"key":"ref410","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00495"},{"key":"ref411","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01282"},{"key":"ref412","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01465"},{"key":"ref413","article-title":"Self-supervised learning for pre-training 3-D point clouds: A survey","author":"Fei","year":"2023","journal-title":"arXiv:2305.04691"},{"key":"ref414","first-page":"1","article-title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection","volume-title":"Proc. 12th Int. Conf. Learn. Rep.","author":"Zhou"},{"key":"ref415","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref416","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref417","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref418","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref419","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"ref420","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref421","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00512"},{"key":"ref422","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref423","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref424","first-page":"27061","article-title":"point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang"},{"key":"ref425","doi-asserted-by":"publisher","DOI":"10.3390\/s21010073"},{"key":"ref426","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298801"},{"key":"ref427","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref428","first-page":"9125","article-title":"DetCLIP: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yao"},{"key":"ref429","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00314"},{"key":"ref430","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref431","first-page":"1","article-title":"SimMMDG: A simple and effective framework for multi-modal domain Generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Dong"},{"key":"ref432","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00740"},{"key":"ref433","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01524"},{"key":"ref434","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29578"},{"key":"ref435","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref436","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3422241"},{"key":"ref437","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649348"},{"key":"ref438","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3381602"}],"container-title":["IEEE Communications Surveys &amp; Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9739\/11321210\/11127186.pdf?arnumber=11127186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:05:50Z","timestamp":1768255550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":438,"URL":"https:\/\/doi.org\/10.1109\/comst.2025.3599596","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}