{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:56:30Z","timestamp":1781538990218,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":89,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Guangxi Science and Technology Program","award":["2025AB25069309"],"award-info":[{"award-number":["2025AB25069309"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810700","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"2597-2606","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Modal 3D Object Detection in Autonomous Driving: A New Survey"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1314-085X","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4110-8989","authenticated-orcid":false,"given":"Xin","family":"Lin","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01467"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802675"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"e_1_3_3_1_6_2","unstructured":"Saket\u00a0S Chaturvedi Lan Zhang Wenbin Zhang Pan He and Xiaoyong Yuan. 2024. BadFusion: 2D-oriented backdoor attacks against 3D object detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.03884 (2024)."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02078"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00771"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422147"},{"key":"e_1_3_3_1_11_2","unstructured":"Tanmoy Dam Sanjay\u00a0Bhargav Dharavath Sameer Alam Nimrod Lilith Aniruddha Maiti Supriyo Chakraborty and Mir Feroskhan. 2025. SaViD: Spectravista Aesthetic Vision Integration for Robust and Discerning 3D Object Detection in Challenging Environments. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20614 (2025)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02069"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32278"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636724"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Andreas Geiger Philip Lenz Christoph Stiller and Raquel Urtasun. 2013. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research 32 11 (2013) 1231\u20131237.","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_3_1_16_2","unstructured":"Keli Huang Botian Shi Xiang Li Xin Li Siyuan Huang and Yikang Li. 2022. Multi-modal sensor fusion for auto driving perception: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2202.02703 (2022)."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Xinyu Huang Peng Wang Xinjing Cheng Dingfu Zhou Qichuan Geng and Ruigang Yang. 2019. The apolloscape open dataset for autonomous driving and its application. IEEE transactions on pattern analysis and machine intelligence 42 10 (2019) 2702\u20132719.","DOI":"10.1109\/TPAMI.2019.2926463"},{"key":"e_1_3_3_1_19_2","unstructured":"Mingqian Ji Jian Yang and Shanshan Zhang. 2025. Enhancing Pseudo-Boxes via Data-Level LiDAR-Camera Fusion for Unsupervised 3D Object Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.20530 (2025)."},{"key":"e_1_3_3_1_20_2","first-page":"110","volume-title":"European Conference on Computer Vision","author":"Jiang Zheng","year":"2024","unstructured":"Zheng Jiang, Jinqing Zhang, Yanan Zhang, Qingjie Liu, Zhenghui Hu, Baohui Wang, and Yunhong Wang. 2024. Fsd-bev: Foreground self-distillation for multi-view 3d object detection. In European Conference on Computer Vision. Springer, 110\u2013126."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"e_1_3_3_1_22_2","first-page":"3172","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Jo Wonjun","year":"2024","unstructured":"Wonjun Jo, Kwon Byung-Ki, Kim Ji-Yeon, Hawook Jeong, Kyungdon Joo, and Tae-Hyun Oh. 2024. The Devil is in the Details: Simple Remedies for Image-to-LiDAR Representation Learning. In Proceedings of the Asian Conference on Computer Vision. 3172\u20133188."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547891"},{"key":"e_1_3_3_1_24_2","unstructured":"Ajinkya Khoche Laura\u00a0Pereira S\u00e1nchez Nazre Batool Sina\u00a0Sharif Mansouri and Patric Jensfelt. 2023. Fully Sparse Long Range 3D Object Detection Using Range Experts and Multimodal Virtual Points. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.04800 (2023)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611449"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Jisong Kim Minjae Seong and Jun\u00a0Won Choi. 2024. CRT-Fusion: Camera Radar Temporal Fusion Using Motion Information for 3D Object Detection. Advances in Neural Information Processing Systems 37 (2024) 108625\u2013108648.","DOI":"10.52202\/079017-3449"},{"key":"e_1_3_3_1_27_2","first-page":"19","volume-title":"European Conference on Computer Vision","author":"Kim Sanmin","year":"2024","unstructured":"Sanmin Kim, Youngseok Kim, Sihwan Hwang, Hyeonjun Jeong, and Dongsuk Kum. 2024. LabelDistill: Label-Guided Cross-Modal Knowledge Distillation for Camera-Based 3D Object Detection. In European Conference on Computer Vision. Springer, 19\u201337."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01615"},{"key":"e_1_3_3_1_29_2","first-page":"13343","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Klingner Marvin","year":"2023","unstructured":"Marvin Klingner, Shubhankar Borse, Varun\u00a0Ravi Kumar, Behnaz Rezaei, Venkatraman Narayanan, Senthil Yogamani, and Fatih Porikli. 2023. X3KD: Knowledge distillation across modalities, tasks and stages for multi-camera 3d object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13343\u201313353."},{"key":"e_1_3_3_1_30_2","unstructured":"Zhihao Lai Chuanhao Liu Shihui Sheng and Zhiqiang Zhang. 2024. KAN-RCBEVDepth: A multi-modal fusion algorithm in object detection for autonomous driving. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.02088 (2024)."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Duy\u00a0Tho Le Hengcan Shi Hamid Rezatofighi and Jianfei Cai. 2022. Accurate and real-time 3D pedestrian detection using an efficient attentive pillar network. IEEE Robotics and Automation Letters 8 2 (2022) 1159\u20131166.","DOI":"10.1109\/LRA.2022.3233234"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128369"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Han Li Yukai Ma Yuehao Huang Yaqing Gu Weihua Xu Yong Liu and Xingxing Zuo. 2024. Riders: radar-infrared depth estimation for robust sensing. IEEE Transactions on Intelligent Transportation Systems (2024).","DOI":"10.1109\/TITS.2024.3432996"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Yiheng Li Yang Yang and Zhen Lei. 2025. CoreNet: Conflict Resolution Network for point-pixel misalignment and sub-task suppression of 3D LiDAR-camera object detection. Information Fusion 118 (2025) 102896.","DOI":"10.1016\/j.inffus.2024.102896"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32535"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01414"},{"key":"e_1_3_3_1_38_2","unstructured":"Yueting Liu Hanshi Wang Yunfei Lei Zhengjun Zha Weiming Hu and Jin Gao. 2025. PFSD: A Multi-Modal Pedestrian-Focus Scene Dataset for Rich Tasks in Semi-Structured Environments. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.15342 (2025)."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Zhe Liu Tengteng Huang Bingling Li Xiwu Chen Xi Wang and Xiang Bai. 2022. EPNet++: Cascade bi-directional fusion for multi-modal 3D object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022).","DOI":"10.1109\/TPAMI.2022.3228806"},{"key":"e_1_3_3_1_40_2","unstructured":"Zhijian Liu Haotian Tang Alexander Amini Xinyu Yang Huizi Mao Daniela Rus and Song Han. 2022. BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird\u2019s-Eye View Representation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.13542 (2022)."},{"key":"e_1_3_3_1_41_2","unstructured":"Yukai Ma Jianbiao Mei Xuemeng Yang Licheng Wen Weihua Xu Jiangning Zhang Xingxing Zuo Botian Shi and Yong Liu. 2024. Licrocc: Teach radar for accurate semantic occupancy prediction using lidar and camera. IEEE Robotics and Automation Letters (2024)."},{"key":"e_1_3_3_1_42_2","unstructured":"Jiageng Mao Minzhe Niu Chenhan Jiang Hanxue Liang Jingheng Chen Xiaodan Liang Yamin Li Chaoqiang Ye Wei Zhang Zhenguo Li et\u00a0al. 2021. One million scenes for autonomous driving: Once dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.11037 (2021)."},{"key":"e_1_3_3_1_43_2","volume-title":"8th Annual Conference on Robot Learning","author":"Mohan Rohit","year":"2024","unstructured":"Rohit Mohan, Daniele Cattaneo, Florian Drews, and Abhinav Valada. 2024. Progressive Multi-Modal Fusion for Robust 3D Object Detection. In 8th Annual Conference on Robot Learning."},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Zhiwei Ning Zhaojiang Liu Xuanang Gao Yifan Zuo Jie Yang Yuming Fang and Wei Liu. 2025. CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Prediction. IEEE Transactions on Circuits and Systems for Video Technology (2025).","DOI":"10.1109\/TCSVT.2025.3600527"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Dong-Hee Paek Seung-Hyun Kong and Kevin\u00a0Tirta Wijaya. 2022. K-radar: 4d radar object detection for autonomous driving in various weather conditions. Advances in Neural Information Processing Systems 35 (2022) 3819\u20133829.","DOI":"10.52202\/068431-0276"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00327"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Andras Palffy Ewoud Pool Srimannarayana Baratam Julian\u00a0FP Kooij and Dariu\u00a0M Gavrila. 2022. Multi-class road user detection with 3+ 1d radar in the view-of-delft dataset. IEEE Robotics and Automation Letters 7 2 (2022) 4961\u20134968.","DOI":"10.1109\/LRA.2022.3147324"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00380"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887748"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801398"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO64047.2024.10907310"},{"key":"e_1_3_3_1_53_2","first-page":"339","volume-title":"European Conference on Computer Vision","author":"Sgaravatti Carlo","year":"2024","unstructured":"Carlo Sgaravatti, Roberto Basla, Riccardo Pieroni, Matteo Corno, Sergio\u00a0M Savaresi, Luca Magri, and Giacomo Boracchi. 2024. A multimodal hybrid late-cascade fusion network for enhanced 3d object detection. In European Conference on Computer Vision. Springer, 339\u2013356."},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Yucheng Sheng Hao Ye Le Liang Shi Jin and Geoffrey\u00a0Ye Li. 2024. Semantic communication for cooperative perception based on importance map. Journal of the Franklin Institute 361 6 (2024) 106739.","DOI":"10.1016\/j.jfranklin.2024.106739"},{"key":"e_1_3_3_1_55_2","unstructured":"Yu Sheng Lu Zhang Xingchen Li Yifan Duan Yanyong Zhang Yu Zhang and Jianmin Ji. 2024. Rendering-enhanced automatic image-to-point cloud registration for roadside scenes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.05164 (2024)."},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611436"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"crossref","unstructured":"Yang Song and Lin Wang. 2024. BiCo-Fusion: Bidirectional complementary LiDAR-camera fusion for semantic-and spatial-aware 3D object detection. IEEE Robotics and Automation Letters (2024).","DOI":"10.1109\/LRA.2024.3518845"},{"key":"e_1_3_3_1_58_2","first-page":"347","volume-title":"European Conference on Computer Vision","author":"Song Ziying","year":"2024","unstructured":"Ziying Song, Lei Yang, Shaoqing Xu, Lin Liu, Dongyang Xu, Caiyan Jia, Feiyang Jia, and Li Wang. 2024. Graphbev: Towards robust bev feature alignment for multi-modal 3d object detection. In European Conference on Computer Vision. Springer, 347\u2013366."},{"key":"e_1_3_3_1_59_2","first-page":"178","volume-title":"DAGM German Conference on Pattern Recognition","author":"St\u00e4cker Lukas","year":"2023","unstructured":"Lukas St\u00e4cker, Shashank Mishra, Philipp Heidenreich, Jason Rambach, and Didier Stricker. 2023. RC-BEVFusion: A plug-in module for radar-camera bird\u2019s eye view feature fusion. In DAGM German Conference on Pattern Recognition. Springer, 178\u2013194."},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588584"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588475"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161451"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"e_1_3_3_1_65_2","unstructured":"Beibei Wang Shuang Meng Lu Zhang Chenjie Wang Jingjing Huang Yao Li Haojie Ren Yuxuan Xiao Yuru Peng Jianmin Ji et\u00a0al. 2024. CORP: A Multi-Modal Dataset for Campus-Oriented Roadside Perception Tasks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.03191 (2024)."},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"crossref","unstructured":"Hanshi Wang Jin Gao Weiming Hu and Zhipeng Zhang. 2025. MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.04369 (2025).","DOI":"10.1109\/ICCV51701.2025.02475"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01287"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"crossref","unstructured":"Yingjie Wang Qiuyu Mao Hanqi Zhu Jiajun Deng Yu Zhang Jianmin Ji Houqiang Li and Yanyong Zhang. 2023. Multi-modal 3d object detection in autonomous driving: a survey. International Journal of Computer Vision (2023) 1\u201331.","DOI":"10.1007\/s11263-023-01784-z"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25370"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610545"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02074"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00534"},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161329"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32966"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"crossref","unstructured":"Shanliang Yao Runwei Guan Xiaoyu Huang Zhuoxiao Li Xiangyu Sha Yong Yue Eng\u00a0Gee Lim Hyungjoon Seo Ka\u00a0Lok Man Xiaohui Zhu et\u00a0al. 2023. Radar-camera fusion for object detection and semantic segmentation in autonomous driving: A comprehensive review. IEEE Transactions on Intelligent Vehicles 9 1 (2023) 2094\u20132128.","DOI":"10.1109\/TIV.2023.3307157"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72335-3_8"},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"crossref","unstructured":"Haibao Yu Yingjuan Tang Enze Xie Jilei Mao Ping Luo and Zaiqing Nie. 2023. Flow-based feature fusion for vehicle-infrastructure cooperative 3d object detection. Advances in Neural Information Processing Systems 36 (2023) 34493\u201334503.","DOI":"10.52202\/075280-1497"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889148"},{"key":"e_1_3_3_1_83_2","first-page":"109","volume-title":"European Conference on Computer Vision","author":"Zhang Hongcheng","year":"2024","unstructured":"Hongcheng Zhang, Liu Liang, Pengxin Zeng, Xiao Song, and Zhe Wang. 2024. SparseLIF: High-performance sparse LiDAR-camera fusion for 3D object detection. In European Conference on Computer Vision. Springer, 109\u2013128."},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33078"},{"key":"e_1_3_3_1_85_2","doi-asserted-by":"crossref","unstructured":"Xinyu Zhang Li Wang Jian Chen Cheng Fang Guangqi Yang Yichen Wang Lei Yang Ziying Song Lin Liu Xiaofei Zhang et\u00a0al. 2025. Dual radar: A multi-modal dataset with dual 4d radar for autononous driving. Scientific data 12 1 (2025) 439.","DOI":"10.1038\/s41597-025-04698-2"},{"key":"e_1_3_3_1_86_2","unstructured":"Yifan Zhang Qijian Zhang Junhui Hou Yixuan Yuan and Guoliang Xing. 2023. Bidirectional Propagation for Cross-Modal 3D Object Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.09077 (2023)."},{"key":"e_1_3_3_1_87_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01465"},{"key":"e_1_3_3_1_88_2","doi-asserted-by":"crossref","unstructured":"Walter Zimmer Christian Cre\u00df Huu\u00a0Tung Nguyen and Alois\u00a0C Knoll. 2023. A9 Intersection Dataset: All You Need for Urban 3D Camera-LiDAR Roadside Perception. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.09266 (2023).","DOI":"10.1109\/ITSC57777.2023.10422289"},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"crossref","unstructured":"Walter Zimmer Ross Greer Daniel Lehmberg Marc Pavel Holger Caesar Xingcheng Zhou Ahmed Ghita Mohan Trivedi Rui Song Hu Cao et\u00a0al. 2025. Towards Vision Zero: The Accid3nD Dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.12095 (2025).","DOI":"10.1109\/ICCVW69036.2025.00093"},{"key":"e_1_3_3_1_90_2","unstructured":"Walter Zimmer Ross Greer Xingcheng Zhou Rui Song Marc Pavel Daniel Lehmberg Ahmed Ghita Akshay Gopalkrishnan Mohan Trivedi and Alois Knoll. 2025. Enhancing highway safety: Accident detection on the a9 test stretch using roadside sensors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.00402 (2025)."}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:26:33Z","timestamp":1781537193000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810700"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":89,"alternative-id":["10.1145\/3805622.3810700","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810700","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}