{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:16:19Z","timestamp":1781018179489,"version":"3.54.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031314346","type":"print"},{"value":"9783031314353","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-31435-3_23","type":"book-chapter","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T07:03:12Z","timestamp":1682492592000},"page":"341-358","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["RadarFormer: Lightweight and\u00a0Accurate Real-Time Radar Object Detection Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1488-4794","authenticated-orcid":false,"given":"Yahia","family":"Dalbah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0315-6484","authenticated-orcid":false,"given":"Jean","family":"Lahoud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8230-9065","authenticated-orcid":false,"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","unstructured":"Angelov, A., Robertson, A., Murray-Smith, R., Fioranelli, F.: Practical classification of different moving targets using automotive radar and deep neural networks. IET Radar Sonar Navig. 12(10), 1082\u20131089 (2018). https:\/\/doi.org\/10.1049\/iet-rsn.2018.0103. https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/abs\/10.1049\/iet-rsn.2018.0103","DOI":"10.1049\/iet-rsn.2018.0103"},{"key":"23_CR2","doi-asserted-by":"publisher","unstructured":"Bansal, K., Rungta, K., Bharadia, D.: RadSegNet: a reliable approach to radar camera fusion (2022). https:\/\/doi.org\/10.48550\/ARXIV.2208.03849. https:\/\/arxiv.org\/abs\/2208.03849","DOI":"10.48550\/ARXIV.2208.03849"},{"issue":"8\u20139","key":"23_CR3","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1177\/02783649211006735","volume":"40","author":"J Behley","year":"2021","unstructured":"Behley, J., et al.: Towards 3D LiDAR-based semantic scene understanding of 3D point cloud sequences: the SemanticKITTI Dataset. Int. J. Robot. Res. 40(8\u20139), 959\u2013967 (2021). https:\/\/doi.org\/10.1177\/02783649211006735","journal-title":"Int. J. Robot. Res."},{"key":"23_CR4","doi-asserted-by":"publisher","unstructured":"Cao, P., Xia, W., Ye, M., Zhang, J., Zhou, J.: Radar-ID: human identification based on radar micro-doppler signatures using deep convolutional neural networks. IET Radar Sonar Navig. 12(7), 729\u2013734 (2018). https:\/\/doi.org\/10.1049\/iet-rsn.2017.0511. https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/abs\/10.1049\/iet-rsn.2017.0511","DOI":"10.1049\/iet-rsn.2017.0511"},{"key":"23_CR5","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-3-319-75608-0_9","volume-title":"Traffic Mining Applied to Police Activities","author":"S Capobianco","year":"2018","unstructured":"Capobianco, S., Facheris, L., Cuccoli, F., Marinai, S.: Vehicle classification based on convolutional networks applied to FMCW radar signals. In: Leuzzi, F., Ferilli, S. (eds.) TRAP 2017. AISC, vol. 728, pp. 115\u2013128. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-75608-0_9"},{"key":"23_CR6","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoatNet: marrying convolution and attention for all data sizes. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=dUk5Foj5CLf"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"D\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., Sagun, L.: ConViT: improving vision transformers with soft convolutional inductive biases. In: Internation Conference on Machine Learning, pp. 2286\u20132296 (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"23_CR8","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2020). https:\/\/doi.org\/10.48550\/ARXIV.2010.11929. https:\/\/arxiv.org\/abs\/2010.11929","DOI":"10.48550\/ARXIV.2010.11929"},{"issue":"3","key":"23_CR9","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2021","unstructured":"Feng, D., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans. Intell. Transp. Syst. 22(3), 1341\u20131360 (2021). https:\/\/doi.org\/10.1109\/TITS.2020.2972974","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"23_CR10","doi-asserted-by":"publisher","unstructured":"Hassanin, M., Anwar, S., Radwan, I., Khan, F.S., Mian, A.: Visual attention methods in deep learning: An in-depth survey (2022). https:\/\/doi.org\/10.48550\/ARXIV.2204.07756. https:\/\/arxiv.org\/abs\/2204.07756","DOI":"10.48550\/ARXIV.2204.07756"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et al.: UNETR: transformers for 3D medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"23_CR12","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR13","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR abs\/1704.04861 (2017). http:\/\/arxiv.org\/abs\/1704.04861"},{"key":"23_CR14","doi-asserted-by":"publisher","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. ACM Comput. Surv. 54(10s), 1\u201341 (2022). https:\/\/doi.org\/10.1145\/3505244. https:\/\/doi.org\/10.1145\/3505244","DOI":"10.1145\/3505244"},{"key":"23_CR15","unstructured":"Lahoud, J., et al.: 3D vision with transformers: a survey. arXiv preprint arXiv:2208.04309 (2022)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MViTv 2: improved multiscale vision transformers for classification and detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"23_CR17","unstructured":"Lim, T.Y., et al.: Radar and camera early fusion for vehicle detection in advanced driver assistance systems. In: NeurIPS Machine Learning for Autonomous Driving Workshop (2019)"},{"issue":"4","key":"23_CR18","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1109\/JSTSP.2021.3061270","volume":"15","author":"TY Lim","year":"2021","unstructured":"Lim, T.Y., Markowitz, S.A., Do, M.N.: Radical: A synchronized FMCW radar, depth, IMU and RGB camera data dataset with low-level FMCW radar signals. IEEE J. Select. Top. Sig. Process. 15(4), 941\u2013953 (2021). https:\/\/doi.org\/10.1109\/JSTSP.2021.3061270","journal-title":"IEEE J. Select. Top. Sig. Process."},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer v2: Scaling up capacity and resolution. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR21","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=Skq89Scxx"},{"key":"23_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked Hourglass Networks for Human Pose Estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Ouaknine, A., Newson, A., P\u00e9rez, P., Tupin, F., Rebut, J.: Multi-view radar semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15671\u201315680 (2021)","DOI":"10.1109\/ICCV48922.2021.01538"},{"key":"23_CR24","doi-asserted-by":"publisher","unstructured":"Ouaknine, A., Newson, A., Rebut, J., Tupin, F., P\u00e9rez, P.: Carrada dataset: camera and automotive radar with range- angle- doppler annotations. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 5068\u20135075 (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9413181","DOI":"10.1109\/ICPR48806.2021.9413181"},{"key":"23_CR25","unstructured":"Pan, Z., Cai, J., Zhuang, B.: Fast vision transformers with HiLo attention. In: NeurIPS (2022)"},{"key":"23_CR26","doi-asserted-by":"publisher","unstructured":"Peiris, H., Hayat, M., Chen, Z., Egan, G., Harandi, M.: A robust volumetric transformer for accurate 3D tumor segmentation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2022. MICCAI 2022. LNCS, vol. 13435, pp. 162\u2013172. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16443-9_16","DOI":"10.1007\/978-3-031-16443-9_16"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. CoRR abs\/1506.02640 (2015). http:\/\/arxiv.org\/abs\/1506.02640","DOI":"10.1109\/CVPR.2016.91"},{"key":"23_CR28","unstructured":"Schumann, O., et al.: RadarScenes: a real-world radar point cloud data set for automotive applications. CoRR abs\/2104.02493 (2021). https:\/\/arxiv.org\/abs\/2104.02493"},{"key":"23_CR29","unstructured":"Shaker, A., Maaz, M., Rasheed, H., Khan, S., Yang, M.H., Khan, F.S.: UNETR++: delving into efficient and accurate 3D medical image segmentation. arXiv:2212.04497 (2022)"},{"key":"23_CR30","doi-asserted-by":"publisher","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"23_CR31","doi-asserted-by":"publisher","unstructured":"Tu, Z., et al.: MaxViT: Multi-axis vision transformer. In: Avidan, S., Brostow, G., Farinella, G.M., Hassner, T. (eds) Computer Vision\u2013ECCV 2022. ECCV 2022. LNCS, vol. 13684. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_27","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"23_CR32","doi-asserted-by":"publisher","unstructured":"Vogginger, B., et al.: Automotive radar processing with spiking neural networks: Concepts and challenges. Front. Neurosci. 16, 851774 (2022). https:\/\/doi.org\/10.3389\/fnins.2022.851774. https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2022.851774","DOI":"10.3389\/fnins.2022.851774"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Huang, Y.T., Hwang, J.N.: Monocular visual object 3D localization in road scenes. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 917\u2013925. ACM (2019)","DOI":"10.1145\/3343031.3350924"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Rod 2021 challenge: a summary for radar object detection challenge for autonomous driving applications. In: Proceedings of the 2021 International Conference on Multimedia Retrieval, pp. 553\u2013559 (2021)","DOI":"10.1145\/3460426.3463658"},{"key":"23_CR35","doi-asserted-by":"publisher","unstructured":"Wang, Y., Jiang, Z., Gao, X., Hwang, J.N., Xing, G., Liu, H.: RODNet: radar object detection using cross-modal supervision. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 504\u2013513 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00055","DOI":"10.1109\/WACV48630.2021.00055"},{"key":"23_CR36","unstructured":"Wang, Y., Guizilini, V., Zhang, T., Wang, Y., Zhao, H., Solomon, J.M.: DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: The Conference on Robot Learning (CoRL) (2021)"},{"key":"23_CR37","first-page":"30392","volume":"34","author":"T Xiao","year":"2021","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.: Early convolutions help transformers see better. Adv. Neural. Inf. Process. Syst. 34, 30392\u201330400 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR38","doi-asserted-by":"publisher","unstructured":"Yan, X., et al.: Sparse single sweep lidar point cloud segmentation via learning contextual shape priors from scene completion. Proceed. AAAI Conf. Artif. Intell. 35(4), 3101\u20133109 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i4.16419. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16419","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"23_CR39","doi-asserted-by":"publisher","unstructured":"Ye, D., et al.: LidarMultiNet: unifying lidar semantic segmentation, 3D object detection, and panoptic segmentation in a single multi-task network (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.11428. https:\/\/arxiv.org\/abs\/2206.11428","DOI":"10.48550\/ARXIV.2206.11428"},{"key":"23_CR40","unstructured":"Yuan, Y., et al.: HRFormer: high-resolution transformer for dense prediction. In: NeurIPS (2021)"},{"issue":"4","key":"23_CR41","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.1109\/TCSVT.2021.3082763","volume":"32","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z., Song, X., Bai, L., Wang, Z., Ouyang, W.: Temporal-channel transformer for 3D lidar-based video object detection for autonomous driving. IEEE Trans. Circuits Syst. Video Technol. 32(4), 2068\u20132078 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3082763","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"23_CR42","doi-asserted-by":"publisher","unstructured":"Zhang, A., Nowruzi, F.E., Laganiere, R.: RADDet: range-azimuth-doppler based radar object detection for dynamic road users. In: 2021 18th Conference on Robots and Vision (CRV), pp. 95\u2013102 (2021). https:\/\/doi.org\/10.1109\/CRV52889.2021.00021","DOI":"10.1109\/CRV52889.2021.00021"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Zhang, Y., Foroosh, H.: Panoptic-PolarNet: proposal-free lidar point cloud panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01299"}],"container-title":["Lecture Notes in Computer Science","Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-31435-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T18:05:13Z","timestamp":1685383513000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-31435-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031314346","9783031314353"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-31435-3_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SCIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Scandinavian Conference on Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lapland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"scia2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/scia2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT 3","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"108","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}