{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T22:06:49Z","timestamp":1780956409072,"version":"3.54.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100020717","name":"Center for High Performance Computing, Shanghai Jiao Tong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020717","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003444","name":"Beijing University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003444","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113778","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T06:52:16Z","timestamp":1776754336000},"page":"113778","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["RCACF: 4D Radar-Camera Adaptive and Cooperative Fusion for 3D detection"],"prefix":"10.1016","volume":"179","author":[{"given":"Shihao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyan","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhuo","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyu","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.patcog.2026.113778_b1","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.3390\/rs17081465","article-title":"Moving-least-squares-enhanced 3d object detection for 4d millimeter-wave radar","volume":"17","author":"Shi","year":"2025","journal-title":"Remote Sens."},{"issue":"2","key":"10.1016\/j.patcog.2026.113778_b2","doi-asserted-by":"crossref","first-page":"366","DOI":"10.3390\/rs16020366","article-title":"Louvain-based traffic object detection for roadside 4d millimeter-wave radar","volume":"16","author":"Gong","year":"2024","journal-title":"Remote Sens."},{"key":"10.1016\/j.patcog.2026.113778_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108796","article-title":"3D object detection for autonomous driving: A survey","volume":"130","author":"Qian","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113778_b4","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Lidar light scattering augmentation (lisa): Physics-based simulation of adverse weather conditions for 3d object detection","author":"Kilic","year":"2025"},{"key":"10.1016\/j.patcog.2026.113778_b5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1016\/j.patcog.2019.02.005","article-title":"Mapnet: Multi-modal attentive pooling network for rgb-d indoor scene classification","volume":"90","author":"Li","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113778_b6","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4603","article-title":"Pointpainting: Sequential fusion for 3d object detection","author":"Vora","year":"2020"},{"key":"10.1016\/j.patcog.2026.113778_b7","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20432","article-title":"Ipod: Implicit field learning with point diffusion for generalizable 3d object reconstruction from single rgb-d images","author":"Wu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113778_b8","series-title":"2019 Sensor Data Fusion: Trends, Solutions, Applications","first-page":"1","article-title":"A deep learning-based radar and camera sensor fusion architecture for object detection","author":"Nobis","year":"2019"},{"key":"10.1016\/j.patcog.2026.113778_b9","first-page":"301","article-title":"Very deep convolutional networks for large-scale image recognition vol 12 issue 08","volume":"12","author":"Publication","year":"2012","journal-title":"SSRN Electron. J."},{"issue":"6","key":"10.1016\/j.patcog.2026.113778_b10","doi-asserted-by":"crossref","first-page":"8641","DOI":"10.1109\/TITS.2025.3554313","article-title":"Mssf: A 4d radar and camera fusion framework with multi-stage sampling for 3d object detection in autonomous driving","volume":"26","author":"Liu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patcog.2026.113778_b11","series-title":"2019 IEEE International Conference on Image Processing","first-page":"3093","article-title":"Rrpn: Radar region proposal network for object detection in autonomous vehicles","author":"Nabati","year":"2019"},{"key":"10.1016\/j.patcog.2026.113778_b12","series-title":"2021 IEEE Winter Conference on Applications of Computer Vision","first-page":"1526","article-title":"Centerfusion: Center-based radar and camera fusion for 3d object detection","author":"Nabati","year":"2021"},{"key":"10.1016\/j.patcog.2026.113778_b13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2023.3322473","article-title":"Rcfusion: Fusing 4-d radar and camera with bird\u2019s-eye view features for 3-d object detection","volume":"72","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.patcog.2026.113778_b14","doi-asserted-by":"crossref","unstructured":"Y. Dalbah, J. Lahoud, H. Cholakkal, Transradar: Adaptive-directional transformer for real-time multi-view radar semantic segmentation, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV, 2024, pp. 353\u2013362.","DOI":"10.1109\/WACV57701.2024.00042"},{"key":"10.1016\/j.patcog.2026.113778_b15","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"172","article-title":"Futr3d: A unified sensor fusion framework for 3d detection","author":"Chen","year":"2023"},{"key":"10.1016\/j.patcog.2026.113778_b16","series-title":"2014 9th IEEE International Conference on Networking, Architecture, and Storage","first-page":"33","article-title":"Raflow: Read ahead accelerated i\/o flow through multiple virtual layers","author":"Zhang","year":"2014"},{"key":"10.1016\/j.patcog.2026.113778_b17","article-title":"A cnn-transformer-convlstm-crf hybrid network for sleep stage classification","author":"Zhang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.patcog.2026.113778_b18","doi-asserted-by":"crossref","first-page":"101589","DOI":"10.52202\/079017-3222","article-title":"Radarocc: Robust 3d occupancy prediction with 4d imaging radar","volume":"37","author":"Ding","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113778_b19","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113778_b20","series-title":"Radar Signal Processing for Autonomous Driving","author":"Gamba","year":"2020"},{"key":"10.1016\/j.patcog.2026.113778_b21","series-title":"Crossover: 3d scene cross-modal alignment","author":"Sarkar","year":"2025"},{"key":"10.1016\/j.patcog.2026.113778_b22","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113778_b23","series-title":"Attention is all you need","author":"Vaswani","year":"2023"},{"key":"10.1016\/j.patcog.2026.113778_b24","doi-asserted-by":"crossref","unstructured":"H. Liu, Y. Teng, T. Lu, H. Wang, L. Wang, Sparsebev: High-performance sparse 3d object detection from multi-camera videos, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 18580\u201318590.","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"10.1016\/j.patcog.2026.113778_b25","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11779","article-title":"Center-based 3d object detection and tracking","author":"Yin","year":"2021"},{"key":"10.1016\/j.patcog.2026.113778_b26","series-title":"Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence","first-page":"9","article-title":"Craft: camera-radar 3d object detection with spatio-contextual fusion transformer","author":"Kim","year":"2023"},{"issue":"2","key":"10.1016\/j.patcog.2026.113778_b27","doi-asserted-by":"crossref","first-page":"1523","DOI":"10.1109\/TIV.2023.3240287","article-title":"Bridging the view disparity between radar and camera features for multi-modal fusion 3d object detection","volume":"8","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.patcog.2026.113778_b28","doi-asserted-by":"crossref","unstructured":"Z. Lin, Z. Liu, Z. Xia, X. Wang, Y. Wang, S. Qi, Y. Dong, N. Dong, L. Zhang, C. Zhu, Rcbevdet: radar-camera fusion in bird\u2019s eye view for 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 14928\u201314937.","DOI":"10.1109\/CVPR52733.2024.01414"},{"key":"10.1016\/j.patcog.2026.113778_b29","doi-asserted-by":"crossref","unstructured":"Y. Kim, J. Shin, S. Kim, I.-J. Lee, J.W. Choi, D. Kum, Crn: Camera radar net for accurate, robust, efficient 3d perception, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 17615\u201317626.","DOI":"10.1109\/ICCV51070.2023.01615"},{"key":"10.1016\/j.patcog.2026.113778_b30","doi-asserted-by":"crossref","unstructured":"Y. Li, Z. Ge, G. Yu, J. Yang, Z. Wang, Y. Shi, J. Sun, Z. Li, Bevdepth: Acquisition of reliable depth for multi-view 3d object detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2023, pp. 1477\u20131485.","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"10.1016\/j.patcog.2026.113778_b31","unstructured":"J. Park, C. Xu, S. Yang, K. Keutzer, K. Kitani, M. Tomizuka, W. Zhan, Time will tell: New outlooks and a baseline for temporal multi-view 3d object detection, in: International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.patcog.2026.113778_b32","doi-asserted-by":"crossref","unstructured":"S. Wang, Y. Liu, T. Wang, Y. Li, X. Zhang, Exploring object-centric temporal modeling for efficient multi-view 3d object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 3621\u20133631.","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"10.1016\/j.patcog.2026.113778_b33","series-title":"2023 IEEE\/CVF International Conference on Computer Vision","first-page":"17569","article-title":"Crn: Camera radar net for accurate, robust, efficient 3d perception","author":"Kim","year":"2023"},{"key":"10.1016\/j.patcog.2026.113778_b34","series-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IV","first-page":"474","article-title":"Tracking objects as points","author":"Zhou","year":"2020"},{"key":"10.1016\/j.patcog.2026.113778_b35","series-title":"2019 International Conference on Robotics and Automation","first-page":"7276","article-title":"Mvx-net: Multimodal voxelnet for 3d object detection","author":"Sindagi","year":"2019"},{"key":"10.1016\/j.patcog.2026.113778_b36","doi-asserted-by":"crossref","unstructured":"A.H. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang, O. Beijbom, Pointpillars: Fast encoders for object detection from point clouds, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 12697\u201312705.","DOI":"10.1109\/CVPR.2019.01298"},{"issue":"3","key":"10.1016\/j.patcog.2026.113778_b37","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1109\/LRA.2019.2921506","article-title":"Recurrent convolutional fusion for rgb-d object recognition","volume":"4","author":"Loghmani","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.patcog.2026.113778_b38","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"2774","article-title":"Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation","author":"Liu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113778_b39","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1477","article-title":"Bevdepth: Acquisition of reliable depth for multi-view 3d object detection","volume":"Vol. 37","author":"Li","year":"2023"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007430?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007430?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:48:52Z","timestamp":1780955332000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326007430"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":39,"alternative-id":["S0031320326007430"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113778","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RCACF: 4D Radar-Camera Adaptive and Cooperative Fusion for 3D detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113778","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113778"}}