{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T16:14:01Z","timestamp":1780503241748,"version":"3.54.1"},"reference-count":55,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T00:00:00Z","timestamp":1722988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shanghai Sailing Program","award":["22YF1400500"],"award-info":[{"award-number":["22YF1400500"]}]},{"name":"Shanghai Sailing Program","award":["2232022D-11"],"award-info":[{"award-number":["2232022D-11"]}]},{"name":"Shanghai Sailing Program","award":["2232023G-06"],"award-info":[{"award-number":["2232023G-06"]}]},{"name":"Shanghai Sailing Program","award":["62001064"],"award-info":[{"award-number":["62001064"]}]},{"name":"Shanghai Sailing Program","award":["62201371"],"award-info":[{"award-number":["62201371"]}]},{"name":"Shanghai Sailing Program","award":["2023NSFSC1382"],"award-info":[{"award-number":["2023NSFSC1382"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["22YF1400500"],"award-info":[{"award-number":["22YF1400500"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2232022D-11"],"award-info":[{"award-number":["2232022D-11"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2232023G-06"],"award-info":[{"award-number":["2232023G-06"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["62001064"],"award-info":[{"award-number":["62001064"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["62201371"],"award-info":[{"award-number":["62201371"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2023NSFSC1382"],"award-info":[{"award-number":["2023NSFSC1382"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22YF1400500"],"award-info":[{"award-number":["22YF1400500"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2232022D-11"],"award-info":[{"award-number":["2232022D-11"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2232023G-06"],"award-info":[{"award-number":["2232023G-06"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001064"],"award-info":[{"award-number":["62001064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201371"],"award-info":[{"award-number":["62201371"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2023NSFSC1382"],"award-info":[{"award-number":["2023NSFSC1382"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["22YF1400500"],"award-info":[{"award-number":["22YF1400500"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2232022D-11"],"award-info":[{"award-number":["2232022D-11"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2232023G-06"],"award-info":[{"award-number":["2232023G-06"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["62001064"],"award-info":[{"award-number":["62001064"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["62201371"],"award-info":[{"award-number":["62201371"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2023NSFSC1382"],"award-info":[{"award-number":["2023NSFSC1382"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>In smart transportation, assisted driving relies on data integration from various sensors, notably LiDAR and cameras. However, their optical performance can degrade under adverse weather conditions, potentially compromising vehicle safety. Millimeter-wave radar, which can overcome these issues more economically, has been re-evaluated. Despite this, developing an accurate detection model is challenging due to significant noise interference and limited semantic information. To address these practical challenges, this paper presents the TC\u2013Radar model, a novel approach that synergistically integrates the strengths of transformer and the convolutional neural network (CNN) to optimize the sensing potential of millimeter-wave radar in smart transportation systems. The rationale for this integration lies in the complementary nature of CNNs, which are adept at capturing local spatial features, and transformers, which excel at modeling long-range dependencies and global context within data. This hybrid approach allows for a more robust and accurate representation of radar signals, leading to enhanced detection performance. A key innovation of our approach is the introduction of the Cross-Attention (CA) module, which facilitates efficient and dynamic information exchange between the encoder and decoder stages of the network. This CA mechanism ensures that critical features are accurately captured and transferred, thereby significantly improving the overall network performance. In addition, the model contains the dense information fusion block (DIFB) to further enrich the feature representation by integrating different high-frequency local features. This integration process ensures thorough incorporation of key data points. Extensive tests conducted on the CRUW and CARRADA datasets validate the strengths of this method, with the model achieving an average precision (AP) of 83.99% and a mean intersection over union (mIoU) of 45.2%, demonstrating robust radar sensing capabilities.<\/jats:p>","DOI":"10.3390\/rs16162881","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T11:33:52Z","timestamp":1723030432000},"page":"2881","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["TC\u2013Radar: Transformer\u2013CNN Hybrid Network for Millimeter-Wave Radar Object Detection"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4870-8473","authenticated-orcid":false,"given":"Fengde","family":"Jia","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Donghua University, Shanghai 201620, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Donghua University, Shanghai 201620, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8365-811X","authenticated-orcid":false,"given":"Siyi","family":"Bi","sequence":"additional","affiliation":[{"name":"Shanghai Frontier Science Research Center for Modern Textiles, College of Textiles, Donghua University, Shanghai 201620, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8017-725X","authenticated-orcid":false,"given":"Junhui","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Microelectronic and Communication Engineering, Chongqing University, Chongqing 400044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leizhe","family":"Wei","sequence":"additional","affiliation":[{"name":"Shanghai Wellplan Technology Co., Ltd., Shanghai 200030, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohao","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Sichuan University, Chengdu 610207, China"},{"name":"Sichuan Provincial Key Laboratory of Robotics Satellites, Chengdu 610207, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,8,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/MITS.2023.3283864","article-title":"Multi-Sensor Fusion and Cooperative Perception for Autonomous Driving: A Review","volume":"15","author":"Xiang","year":"2023","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.inffus.2020.11.002","article-title":"Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy","volume":"68","author":"Fernandes","year":"2021","journal-title":"Inf. Fusion"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1109\/TIV.2022.3167733","article-title":"Millimeter Wave FMCW RADARs for Perception, Recognition and Localization in Automotive Applications: A Survey","volume":"7","author":"Venon","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, L., Zhao, H., L\u00f3pez-Ben\u00edtez, M., Yu, L., and Yue, Y. (2022). Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges. Sensors, 22.","DOI":"10.3390\/s22114208"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ignatious, H.A., El-Sayed, H., and Kulkarni, P. (2023). Multilevel Data and Decision Fusion Using Heterogeneous Sensory Data for Autonomous Vehicles. Remote Sens., 15.","DOI":"10.3390\/rs15092256"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1109\/TAES.1983.309350","article-title":"Radar CFAR Thresholding in Clutter and Multiple Target Situations","volume":"AES-19","author":"Rohling","year":"1983","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"6964","DOI":"10.1109\/JSEN.2022.3154980","article-title":"Camera, LiDAR, and Radar Sensor Fusion Based on Bayesian Neural Network (CLR-BNN)","volume":"22","author":"Ravindran","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, Y., Deng, J., Li, Y., Hu, J., Liu, C., Zhang, Y., Ji, J., Ouyang, W., and Zhang, Y. (2023, January 17\u201324). Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01287"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Monta\u00f1ez, O.J., Suarez, M.J., and Fernandez, E.A. (2023). Application of Data Sensor Fusion Using Extended Kalman Filter Algorithm for Identification and Tracking of Moving Targets from LiDAR\u2013Radar Data. Remote Sens., 15.","DOI":"10.3390\/rs15133396"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, Z., Miao, X., Huang, Z., and Luo, H. (2021). Research of Target Detection and Classification Techniques Using Millimeter-Wave Radar and Vision Sensors. Remote Sens., 13.","DOI":"10.3390\/rs13061064"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yang, Y., Wang, X., Wu, X., Lan, X., Su, T., and Guo, Y. (2024). A Robust Target Detection Algorithm Based on the Fusion of Frequency-Modulated Continuous Wave Radar and a Monocular Camera. Remote Sens., 16.","DOI":"10.3390\/rs16122225"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, A., Nowruzi, F.E., and Laganiere, R. (2021, January 26\u201328). RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users. Proceedings of the 2021 18th Conference on Robots and Vision (CRV), Burnaby, BC, Canada.","DOI":"10.1109\/CRV52889.2021.00021"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5119","DOI":"10.1109\/JSEN.2020.3036047","article-title":"RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition","volume":"21","author":"Gao","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, R., Cheng, L., Wang, S., Lou, Y., Gao, Y., Wu, W., and Ng, D.W.K. (2024). Integrated Sensing and Communication with Massive MIMO: A Unified Tensor Approach for Channel and Target Parameter Estimation. IEEE Trans. Wirel. Commun., 1.","DOI":"10.1109\/TWC.2024.3351856"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/TIV.2023.3322353","article-title":"Semantic Segmentation-Based Occupancy Grid Map Learning with Automotive Radar Raw Data","volume":"9","author":"Jin","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5028712","DOI":"10.1109\/TIM.2023.3320761","article-title":"Superimposed Mask-Guided Contrastive Regularization for Multiple Targets Echo Separation on Range\u2013Doppler Maps","volume":"72","author":"Xu","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., and Rambach, K. (2023, January 1\u20134). Histogram-based Deep Learning for Automotive Radar. Proceedings of the 2023 IEEE Radar Conference (RadarConf23), San Antonio, TX, USA.","DOI":"10.1109\/RadarConf2351548.2023.10149688"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4878","DOI":"10.1109\/LRA.2024.3377562","article-title":"mmPlace: Robust Place Recognition with Intermediate Frequency Signal of Low-Cost Single-Chip Millimeter Wave Radar","volume":"9","author":"Meng","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ouaknine, A., Newson, A., P\u00e9rez, P., Tupin, F., and Rebut, J. (2021, January 11\u201317). Multi-View Radar Semantic Segmentation. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01538"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zou, H., Xie, Z., Ou, J., and Gao, Y. (June, January 29). TransRSS: Transformer-based Radar Semantic Segmentation. Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK.","DOI":"10.1109\/ICRA48891.2023.10161200"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1109\/JSTSP.2021.3058895","article-title":"RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization","volume":"15","author":"Wang","year":"2021","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ju, B., Yang, W., Jia, J., Ye, X., Chen, Q., Tan, X., Sun, H., Shi, Y., and Ding, E. (2021, January 30). DANet: Dimension Apart Network for Radar Object Detection. Proceedings of the 2021 International Conference on Multimedia Retrieval, New York, NY, USA. ICMR \u201921.","DOI":"10.1145\/3460426.3463656"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Decourt, C., VanRullen, R., Salle, D., and Oberlin, T. (2024). A Recurrent CNN for Online Object Detection on Raw Radar Frames. IEEE Trans. Intell. Transp. Syst., 1\u201310.","DOI":"10.1109\/TITS.2024.3404076"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Jia, F., Tan, J., Lu, X., and Qian, J. (2023). Radar Timing Range\u2013Doppler Spectral Target Detection Based on Attention ConvLSTM in Traffic Scenes. Remote Sens., 15.","DOI":"10.3390\/rs15174150"},{"key":"ref_26","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Attention is All you Need. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"4297","DOI":"10.1109\/JSTARS.2022.3177235","article-title":"A CNN-Transformer Network With Multiscale Context Aggregation for Fine-Grained Cropland Change Detection","volume":"15","author":"Liu","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"10990","DOI":"10.1109\/JSTARS.2021.3119654","article-title":"STransFuse: Fusing Swin Transformer and Convolutional Neural Network for Remote Sensing Image Semantic Segmentation","volume":"14","author":"Gao","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1109\/JSTARS.2020.3037893","article-title":"DASNet: Dual Attentive Fully Convolutional Siamese Networks for Change Detection in High-Resolution Satellite Images","volume":"14","author":"Chen","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yang, C., Kong, Y., Wang, X., and Cheng, Y. (2024). Hyperspectral Image Classification Based on Adaptive Global\u2013Local Feature Fusion. Remote Sens., 16.","DOI":"10.3390\/rs16111918"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3012","DOI":"10.1109\/TIV.2023.3234583","article-title":"Cross-Modal Supervision-Based Multitask Learning with Automotive Radar Raw Data","volume":"8","author":"Jin","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1038\/s42256-020-00288-6","article-title":"High-resolution radar road segmentation using weakly supervised learning","volume":"3","author":"Orr","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"9435","DOI":"10.1109\/TVT.2022.3182411","article-title":"Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications","volume":"71","author":"Grimm","year":"2022","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3999","DOI":"10.1109\/JSEN.2023.3339651","article-title":"Effective mmWave Radar Object Detection Pretraining Based on Masked Image Modeling","volume":"24","author":"Zhuang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Schumann, O., Hahn, M., Scheiner, N., Weishaupt, F., Tilly, J.F., Dickmann, J., and W\u00f6hler, C. (2021, January 1\u20134). RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications. Proceedings of the 2021 IEEE 24th International Conference on Information Fusion (FUSION), Sun City, South Africa.","DOI":"10.23919\/FUSION49465.2021.9627037"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Fang, S., Zhu, H., Bisla, D., Choromanska, A., Ravindran, S., Ren, D., and Wu, R. (June, January 29). ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals. Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK.","DOI":"10.1109\/ICRA48891.2023.10160343"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, X., Zhang, Y., Guo, Y., Chen, Y., Huang, X., and Ma, Z. (2023, January 17\u201324). PeakConv: Learning Peak Receptive Field for Radar Semantic Segmentation. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01686"},{"key":"ref_38","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., Bischof, H., Brox, T., and Frahm, J.M. (2020, January 23\u201328). End-to-End Object Detection with Transformers. Proceedings of the Computer Vision\u2014ECCV 2020, Glasgow, UK.","DOI":"10.1007\/978-3-030-58604-1"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1109\/LRA.2022.3226030","article-title":"Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data","volume":"8","author":"Zeller","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kim, Y., Kim, S., Choi, J.W., and Kum, D. (2023, January 7\u201314). CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i1.25198"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., and Hassner, T. (2022, January 23\u201327). CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection. Proceedings of the Computer Vision\u2014ECCV 2022, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20059-5"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Lo, C.C., and Vandewalle, P. (2023, January 4\u201310). RCDPT: Radar-Camera Fusion Dense Prediction Transformer. Proceedings of the ICASSP 2023\u20142023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece.","DOI":"10.1109\/ICASSP49357.2023.10096129"},{"key":"ref_44","first-page":"1","article-title":"T-RODNet: Transformer for Vehicular Millimeter-Wave Radar Object Detection","volume":"72","author":"Jiang","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_45","unstructured":"Gade, R., Felsberg, M., and K\u00e4m\u00e4r\u00e4inen, J.K. (2023). RadarFormer: Lightweight and Accurate Real-Time Radar Object Detection Model. Proceedings of the Image Analysis, Springer."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 10\u201317). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Agarwal, A., and Arora, C. (2023, January 2\u20137). Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention. Proceedings of the 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H.R., and Xu, D. (2022, January 2\u20137). UNETR: Transformers for 3D Medical Image Segmentation. Proceedings of the 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref_50","unstructured":"Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., and Vaughan, J.W. (2021, January 6\u201314). HRFormer: High-Resolution Vision Transformer for Dense Predict. Proceedings of the Advances in Neural Information Processing Systems, Online."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Navab, N., Hornegger, J., Wells, W.M., and Frangi, A.F. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Munich, Germany.","DOI":"10.1007\/978-3-319-24571-3"},{"key":"ref_53","unstructured":"Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018, January 8\u201314). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the Computer Vision\u2014ECCV 2018, Munich, Germany."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Kaul, P., de Martini, D., Gadd, M., and Newman, P. (November, January 19). RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radar. Proceedings of the 2020 IEEE Intelligent Vehicles Symposium (IV), Las Vegas, NV, USA.","DOI":"10.1109\/IV47402.2020.9304674"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"3330","DOI":"10.1109\/TIV.2023.3342296","article-title":"LQCANet: Learnable-Query-Guided Multi-Scale Fusion Network Based on Cross-Attention for Radar Semantic Segmentation","volume":"9","author":"Zhuang","year":"2024","journal-title":"IEEE Trans. Intell. Veh."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/16\/2881\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:31:21Z","timestamp":1760110281000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/16\/2881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,7]]},"references-count":55,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["rs16162881"],"URL":"https:\/\/doi.org\/10.3390\/rs16162881","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,7]]}}}