{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:33:26Z","timestamp":1772120006771,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T00:00:00Z","timestamp":1744761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T00:00:00Z","timestamp":1744761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s11760-025-03976-1","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T09:52:45Z","timestamp":1744797165000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A multi-level multi-attention mechanism millimeter-wave radar and camera fusion method for 3D object detection"],"prefix":"10.1007","volume":"19","author":[{"given":"Zehua","family":"Miao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinbei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zizhuo","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuliang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,16]]},"reference":[{"key":"3976_CR1","doi-asserted-by":"crossref","unstructured":"Fung, M.L., Chen, M.Z., Chen, Y.H.: Sensor fusion: A review of methods and applications. In: 2017 29th Chinese Control And Decision Conference (CCDC), pp. 3853\u20133860 (2017). IEEE","DOI":"10.1109\/CCDC.2017.7979175"},{"key":"3976_CR2","doi-asserted-by":"crossref","unstructured":"Ma, J., Huang, P., Xu, X.: A coordinated control strategy for rotating motion of the hub-spoke tethered space robot formation system. In: The 26th Chinese Control and Decision Conference (2014 CCDC), pp. 4628\u20134633 (2014). IEEE","DOI":"10.1109\/CCDC.2014.6852999"},{"key":"3976_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"9","key":"3976_CR4","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3976_CR5","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3976_CR6","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: Single shot multibox detector. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337 (2016). Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3976_CR7","doi-asserted-by":"crossref","unstructured":"Tang, Y., Dorn, S., Savani, C.: Center3d: Center-based monocular 3d object detection with joint depth understanding. In: DAGM German Conference on Pattern Recognition, pp. 289\u2013302 (2020). Springer","DOI":"10.1007\/978-3-030-71278-5_21"},{"key":"3976_CR8","doi-asserted-by":"crossref","unstructured":"Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A.: Is pseudo-lidar needed for monocular 3d object detection? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3142\u20133152 (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"3976_CR9","doi-asserted-by":"crossref","unstructured":"Jia, X., Hu, Z., Guan, H.: A new multi-sensor platform for adaptive driving assistance system (adas). In: 2011 9th World Congress on Intelligent Control and Automation, pp. 1224\u20131230 (2011). IEEE","DOI":"10.1109\/WCICA.2011.5970711"},{"issue":"2","key":"3976_CR10","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1109\/TITS.2020.3023541","volume":"23","author":"Y Cui","year":"2021","unstructured":"Cui, Y., Chen, R., Chu, W., Chen, L., Tian, D., Li, Y., Cao, D.: Deep learning for image and point cloud fusion in autonomous driving: A review. IEEE Trans. Intell. Transp. Syst. 23(2), 722\u2013739 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3976_CR11","doi-asserted-by":"crossref","unstructured":"Shin, K., Kwon, Y.P., Tomizuka, M.: Roarnet: A robust 3d object detection based on region approximation refinement. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 2510\u20132515 (2019). IEEE","DOI":"10.1109\/IVS.2019.8813895"},{"key":"3976_CR12","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3d proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1\u20138 (2018). IEEE","DOI":"10.1109\/IROS.2018.8594049"},{"key":"3976_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"3976_CR14","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"3976_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, Q., Zhang, L., Meng, D.: Target detection algorithm based on mmw radar and camera fusion. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 1\u20136 (2019). IEEE","DOI":"10.1109\/ITSC.2019.8917504"},{"key":"3976_CR16","doi-asserted-by":"crossref","unstructured":"Chadwick, S., Maddern, W., Newman, P.: Distant vehicle detection using radar and vision. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 8311\u20138317 (2019). IEEE","DOI":"10.1109\/ICRA.2019.8794312"},{"key":"3976_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3976_CR18","doi-asserted-by":"crossref","unstructured":"John, V., Mita, S.: Rvnet: Deep sensor fusion of monocular camera and radar for image-based obstacle detection in challenging environments. In: Image and Video Technology: 9th Pacific-Rim Symposium, PSIVT 2019, Sydney, NSW, Australia, November 18\u201322, 2019, Proceedings 9, pp. 351\u2013364 (2019). Springer","DOI":"10.1007\/978-3-030-34879-3_27"},{"issue":"18","key":"3976_CR19","doi-asserted-by":"publisher","first-page":"3690","DOI":"10.3390\/rs13183690","volume":"13","author":"T Zhang","year":"2021","unstructured":"Zhang, T., Zhang, X., Li, J., Xu, X., Wang, B., Zhan, X., Xu, Y., Ke, X., Zeng, T., Su, H., et al.: Sar ship detection dataset (ssdd): official release and comprehensive data analysis. Remote Sens. 13(18), 3690 (2021)","journal-title":"Remote Sens."},{"key":"3976_CR20","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhang, X., Zhang, T., Zhang, W., Shi, J., Wei, S., Shao, Z., Xu, Y., Zeng, T.: Distribution-based anchor assignment and comprehensive score voting with distance-penalty iou loss for sar remote sensing ship detection. IEEE Trans. Instrum. Meas. (2024)","DOI":"10.1109\/TIM.2024.3480276"},{"issue":"7","key":"3976_CR21","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1109\/TITS.2016.2533542","volume":"17","author":"X Wang","year":"2016","unstructured":"Wang, X., Xu, L., Sun, H., Xin, J., Zheng, N.: On-road vehicle detection and tracking using mmw radar and monovision fusion. IEEE Trans. Intell. Transp. Syst. 17(7), 2075\u20132084 (2016)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3976_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J.-G., Chen, S.J., Zhou, L.-B., Wan, K.-W., Yau, W.-Y.: Vehicle detection and width estimation in rain by fusing radar and vision. In: 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), pp. 1063\u20131068 (2018). IEEE","DOI":"10.1109\/ICARCV.2018.8581246"},{"key":"3976_CR23","doi-asserted-by":"crossref","unstructured":"Nobis, F., Geisslinger, M., Weber, M., Betz, J., Lienkamp, M.: A deep learning-based radar and camera sensor fusion architecture for object detection. In: 2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF), pp. 1\u20137 (2019). IEEE","DOI":"10.1109\/SDF.2019.8916629"},{"key":"3976_CR24","doi-asserted-by":"crossref","unstructured":"Nabati, R., Qi, H.: Centerfusion: Center-based radar and camera fusion for 3d object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1527\u20131536 (2021)","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"3976_CR25","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., Darrell, T.: Deep layer aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2403\u20132412 (2018)","DOI":"10.1109\/CVPR.2018.00255"},{"key":"3976_CR26","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"3976_CR27","doi-asserted-by":"crossref","unstructured":"Wang, R., Shivanna, R., Cheng, D., Jain, S., Lin, D., Hong, L., Chi, E.: Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems. In: Proceedings of the Web Conference 2021, pp. 1785\u20131797 (2021)","DOI":"10.1145\/3442381.3450078"},{"key":"3976_CR28","doi-asserted-by":"crossref","unstructured":"Stergiou, A., Poppe, R., Kalliatakis, G.: Refining activation downsampling with softpool. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10357\u201310366 (2021)","DOI":"10.1109\/ICCV48922.2021.01019"},{"key":"3976_CR29","first-page":"1","volume":"19","author":"M Zha","year":"2022","unstructured":"Zha, M., Qian, W., Yang, W., Xu, Y.: Multifeature transformation and fusion-based ship detection with small targets and complex backgrounds. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"3976_CR30","doi-asserted-by":"crossref","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., Barnard, K.: Attentional feature fusion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3560\u20133569 (2021)","DOI":"10.1109\/WACV48630.2021.00360"},{"issue":"10","key":"3976_CR31","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1021\/ml500239m","volume":"5","author":"GH Goetz","year":"2014","unstructured":"Goetz, G.H., Philippe, L., Shapiro, M.J.: Epsa: a novel supercritical fluid chromatography technique enabling the design of permeable cyclic peptides. ACS Med. Chem. Lett. 5(10), 1167\u20131172 (2014)","journal-title":"ACS Med. Chem. Lett."},{"issue":"12","key":"3976_CR32","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.3390\/e23121587","volume":"23","author":"M Zha","year":"2021","unstructured":"Zha, M., Qian, W., Yi, W., Hua, J.: A lightweight yolov4-based forestry pest detection method using coordinate attention and feature fusion. Entropy 23(12), 1587 (2021)","journal-title":"Entropy"},{"key":"3976_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"3976_CR34","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., Beijbom, O.: nuscenes: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"3976_CR35","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1991\u20131999 (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"3976_CR36","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"3976_CR37","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3d: Fully convolutional one-stage monocular 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"3976_CR38","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: Fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"3976_CR39","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"3976_CR40","doi-asserted-by":"crossref","unstructured":"Wang, R., Lu, N.: Mwrc3d: 3d object detection with millimeter-wave radar and camera fusion. In: 2024 7th International Conference on Advanced Algorithms and Control Engineering (ICAACE), pp. 384\u2013389 (2024). IEEE","DOI":"10.1109\/ICAACE61206.2024.10549596"},{"key":"3976_CR41","doi-asserted-by":"crossref","unstructured":"Zha, M., Pei, Y., Wang, G., Li, T., Yang, Y., Qian, W., Shen, H.T.: Weakly-supervised mirror detection via scribble annotations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 6953\u20136961 (2024)","DOI":"10.1609\/aaai.v38i7.28521"},{"key":"3976_CR42","doi-asserted-by":"crossref","unstructured":"Zha, M., Fu, F., Pei, Y., Wang, G., Li, T., Tang, X., Yang, Y., Shen, H.T.: Dual domain perception and progressive refinement for mirror detection. IEEE Trans. Circuits Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2024.3426673"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03976-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03976-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03976-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T06:38:32Z","timestamp":1747636712000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03976-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,16]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["3976"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03976-1","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4648522\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,16]]},"assertion":[{"value":"27 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest that might be perceived to influence the results and\/or discussion reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"490"}}