{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:42:32Z","timestamp":1782405752943,"version":"3.54.5"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031917660","type":"print"},{"value":"9783031917677","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-91767-7_23","type":"book-chapter","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T13:44:27Z","timestamp":1748267067000},"page":"339-356","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Multimodal Hybrid Late-Cascade Fusion Network for\u00a0Enhanced 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Carlo","family":"Sgaravatti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Basla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riccardo","family":"Pieroni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matteo","family":"Corno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio M.","family":"Savaresi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Magri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giacomo","family":"Boracchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"23_CR1","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Improving object detection with one line of code. CoRR abs\/1704.04503 (2017). arxiv:1704.04503"},{"key":"23_CR2","doi-asserted-by":"publisher","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. Information 11(2) (2020). https:\/\/doi.org\/10.3390\/info11020125, https:\/\/www.mdpi.com\/2078-2489\/11\/2\/125","DOI":"10.3390\/info11020125"},{"key":"23_CR3","unstructured":"Chen, K., et al.: MMDetection: open mmlab detection toolbox and benchmark. arXiv:1906.07155 (2019)"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3d object detection for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. CoRR abs\/1611.07759 (2016). arxiv:1611.07759","DOI":"10.1109\/CVPR.2017.691"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.T., Shi, J., Ye, Z., Mertz, C., Ramanan, D., Kong, S.: Multimodal object detection via probabilistic ensembling. In: European Conference on Computer Vision, pp. 139\u2013158. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_9"},{"key":"23_CR7","unstructured":"Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection (2020). https:\/\/github.com\/open-mmlab\/mmdetection3d"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"23_CR9","doi-asserted-by":"publisher","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"23_CR10","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"},{"issue":"4","key":"23_CR11","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/BF02278710","volume":"38","author":"R Jonker","year":"1987","unstructured":"Jonker, R., Volgenant, A.: A shortest augmenting path algorithm for dense and sparse linear assignment problems. Computing 38(4), 325\u2013340 (1987). https:\/\/doi.org\/10.1007\/BF02278710","journal-title":"Computing"},{"key":"23_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. CoRR abs\/1712.02294 (2017). arxiv:1712.02294","DOI":"10.1109\/IROS.2018.8594049"},{"key":"23_CR13","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. CoRR abs\/1812.05784 (2018). arxiv:1812.05784","DOI":"10.1109\/CVPR.2019.01298"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., et\u00a0al.: Logonet: towards accurate 3d object detection with local-to-global cross-modal fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17524\u201317534 (2023)","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"23_CR15","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. CoRR abs\/1612.03144 (2016). arxiv:1612.03144"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Lin, Z., Shen, Y., Zhou, S., Chen, S., Zheng, N.: Mlf-det: multi-level fusion for cross-modal 3d object detection. In: International Conference on Artificial Neural Networks, pp. 136\u2013149. Springer (2023)","DOI":"10.1007\/978-3-031-44195-0_12"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Bevfusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2774\u20132781. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"23_CR18","unstructured":"Ma, Y., et al.: Long-tailed 3d detection via 2d late fusion. arXiv preprint arXiv:2312.10986 (2023)"},{"issue":"8","key":"23_CR19","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.1007\/s11263-023-01790-1","volume":"131","author":"J Mao","year":"2023","unstructured":"Mao, J., Shi, S., Wang, X., Li, H.: 3d object detection for autonomous driving: a comprehensive survey. Int. J. Comput. Vis. 131(8), 1909\u20131963 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J.: 3d bounding box estimation using deep learning and geometry. CoRR abs\/1612.00496 (2016), arxiv:1612.00496","DOI":"10.1109\/CVPR.2017.597"},{"key":"23_CR21","doi-asserted-by":"publisher","unstructured":"Paigwar, A., Sierra-Gonzalez, D., Erkent, O., Laugier, C.: Frustum-pointpillars: A multi-stage approach for 3d object detection using RGB camera and lidar. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 2926\u20132933 (2021). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00327","DOI":"10.1109\/ICCVW54120.2021.00327"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., Radha, H.: Clocs: camera-lidar object candidates fusion for 3d object detection. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10386\u201310393. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"23_CR23","unstructured":"Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621 (2017)"},{"key":"23_CR24","unstructured":"Peri, N., Dave, A., Ramanan, D., Kong, S.: Towards long-tailed 3d detection. In: Conference on Robot Learning, pp. 1904\u20131915. PMLR (2023)"},{"key":"23_CR25","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from RGB-D data. CoRR abs\/1711.08488 (2017), arxiv:1711.08488"},{"key":"23_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108796","volume":"130","author":"R Qian","year":"2022","unstructured":"Qian, R., Lai, X., Li, X.: 3d object detection for autonomous driving: a survey. Pattern Recogn. 130, 108796 (2022)","journal-title":"Pattern Recogn."},{"key":"23_CR27","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR abs\/1506.01497 (2015), arxiv:1506.01497"},{"key":"23_CR28","doi-asserted-by":"publisher","unstructured":"Reuse, M., Simon, M., Sick, B.: About the ambiguity of data augmentation for 3d object detection in autonomous driving. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 979\u2013987 (2021). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00114","DOI":"10.1109\/ICCVW54120.2021.00114"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3d object detection. CoRR abs\/1912.13192 (2019), arXiv:1912.13192","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. CoRR abs\/1812.04244 (2018), arXiv:1812.04244","DOI":"10.1109\/CVPR.2019.00086"},{"issue":"8","key":"23_CR31","first-page":"2647","volume":"43","author":"S Shi","year":"2020","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2647\u20132664 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR32","unstructured":"Vora, S., Lang, A.H., Helou, B., Beijbom, O.: Pointpainting: sequential fusion for 3d object detection. CoRR abs\/1911.10150 (2019). arxiv:1911.10150"},{"key":"23_CR33","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":"23_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving. CoRR abs\/1812.07179 (2018). arxiv:1812.07179","DOI":"10.1109\/CVPR.2019.00864"},{"key":"23_CR35","unstructured":"Wang, Y., Mao, Q., Zhu, H., Zhang, Y., Ji, J., Zhang, Y.: Multi-modal 3d object detection in autonomous driving: a survey. CoRR abs\/2106.12735 (2021). arxiv:2106.12735"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., Jia, K.: Frustum convnet: sliding frustums to aggregate local point-wise features for amodal 3d object detection. CoRR abs\/1903.01864 (2019), arxiv:1903.01864","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"23_CR37","doi-asserted-by":"publisher","unstructured":"Wu, H., Wen, C., Li, W., Li, X., Yang, R., Wang, C.: Transformation-equivariant 3d object detection for autonomous driving. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 3, pp. 2795\u20132802 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i3.25380, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/25380","DOI":"10.1609\/aaai.v37i3.25380"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Wu, H., Wen, C., Shi, S., Li, X., Wang, C.: Virtual sparse convolution for multimodal 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21653\u201321662 (2023)","DOI":"10.1109\/CVPR52729.2023.02074"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Sparse fuse dense: towards high quality 3d detection with depth completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5418\u20135427 (2022)","DOI":"10.1109\/CVPR52688.2022.00534"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Xu, D., Anguelov, D., Jain, A.: Pointfusion: deep sensor fusion for 3d bounding box estimation. CoRR abs\/1711.10871 (2017), arXiv:1711.10871","DOI":"10.1109\/CVPR.2018.00033"},{"key":"23_CR41","doi-asserted-by":"publisher","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: Sparsely embedded convolutional detection. Sensors 18(10) (2018). https:\/\/doi.org\/10.3390\/s18103337, https:\/\/www.mdpi.com\/1424-8220\/18\/10\/3337","DOI":"10.3390\/s18103337"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3dssd: point-based 3d single stage object detector. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11037\u201311045 (2020). https:\/\/api.semanticscholar.org\/CorpusID:211259226","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: STD: sparse-to-dense 3d object detector for point cloud. CoRR abs\/1907.10471 (2019). arXiv:1907.10471","DOI":"10.1109\/ICCV.2019.00204"},{"key":"23_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, H., Yang, D., Yurtsever, E., Redmill, K.A., \u00d6zg\u00fcner, U.: Faraway-frustum: Dealing with lidar sparsity for 3d object detection using fusion. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 2646\u20132652 (2021). https:\/\/doi.org\/10.1109\/ITSC48978.2021.9564990","DOI":"10.1109\/ITSC48978.2021.9564990"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, J., Huang, D.: Cat-det: contrastively augmented transformer for multi-modal 3d object detection (2022). arXiv:2204.00325","DOI":"10.1109\/CVPR52688.2022.00098"},{"key":"23_CR46","unstructured":"Zheng, W., Tang, W., Chen, S., Jiang, L., Fu, C.: CIA-SSD: confident iou-aware single-stage object detector from point cloud. CoRR abs\/2012.03015 (2020). arXiv:2012.03015"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Jiang, L., Fu, C.W.: Se-ssd: self-ensembling single-stage object detector from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14494\u201314503 (2021)","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3d object detection. CoRR abs\/1711.06396 (2017), arXiv:1711.06396","DOI":"10.1109\/CVPR.2018.00472"},{"key":"23_CR49","unstructured":"Zhou, Y., Guo, C., Wang, X., Chang, Y., Wu, Y.: A survey on data augmentation in large model era. ArXiv abs\/2401.15422 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267311830"},{"key":"23_CR50","doi-asserted-by":"publisher","unstructured":"\u00c7aldiran, B.E., Acarman, T.: A late asymmetric fusion approach to eliminate false positives. In: 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), pp. 2080\u20132085 (2022). https:\/\/doi.org\/10.1109\/ITSC55140.2022.9922182","DOI":"10.1109\/ITSC55140.2022.9922182"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91767-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T15:36:28Z","timestamp":1757172988000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91767-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031917660","9783031917677"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91767-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}