{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T07:11:14Z","timestamp":1760339474064,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031962387"},{"type":"electronic","value":"9783031962394"}],"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\/978-3-031-96239-4_19","type":"book-chapter","created":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T02:03:23Z","timestamp":1750471403000},"page":"258-271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GaussBEV: Multi-head Gaussian Feature Grouping for\u00a0Multi-view 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Junjie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanping","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinpeng","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingwen","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: 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":"19_CR2","unstructured":"Chen, S., Wang, X., Cheng, T., Zhang, Q., Huang, C., Liu, W.: Polar parametrization for vision-based surround-view 3D detection. arXiv preprint arXiv:2206.10965 (2022)"},{"key":"19_CR3","doi-asserted-by":"publisher","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.236","DOI":"10.1109\/cvpr.2016.236"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chi, X., et al.: BEV-SAN: accurate BEV 3D object detection via slice attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17461\u201317470 (2023)","DOI":"10.1109\/CVPR52729.2023.01675"},{"key":"19_CR5","unstructured":"Chong, Z., et al.: MonoDistill: Learning spatial features for monocular 3D object detection. arXiv preprint arXiv:2201.10830 (2022)"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Feng, C., Jie, Z., Zhong, Y., Chu, X., Ma, L.: AeDet: azimuth-invariant multi-view 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21580\u201321588 (2023)","DOI":"10.1109\/CVPR52729.2023.02067"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Han, C., et al.: Exploring recurrent long-term temporal fusion for multi-view 3d perception. arXiv preprint arXiv:2303.05970 (2023)","DOI":"10.1109\/LRA.2024.3401172"},{"key":"19_CR8","unstructured":"Huang, B., Li, Y., et al.: Fast-BEV: Towards real-time on-vehicle bird\u2019s-eye view perception. arXiv preprint arXiv:2301.07870 (2023)"},{"key":"19_CR9","unstructured":"Huang, J., Huang, G.: BEVDet4D: Exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"19_CR10","unstructured":"Huang, J., Huang, G.: BEVPoolv2: A cutting-edge implementation of BEVDet toward deployment. arXiv preprint arXiv:2211.17111 (2022)"},{"key":"19_CR11","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: BEVDet: High-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: Far3D: expanding the horizon for surround-view 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 2561\u20132569 (2024)","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Bao, H., Ge, Z., Yang, J., Sun, J., Li, Z.: BEVStereo: enhancing depth estimation in multi-view 3D object detection with temporal stereo. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a037, pp. 1486\u20131494 (2023)","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: European Conference on Computer Vision, pp. 1\u201318. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Liu, H., Teng, Y., Lu, T., Wang, H., Wang, L.: SparseBEV: high-performance sparse 3d object detection from multi-camera videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18580\u201318590 (2023)","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"19_CR17","doi-asserted-by":"publisher","unstructured":"Liu, Z., Zhou, D., Lu, F., Fang, J., Zhang, L.: AutoShape: real-time shape-aware monocular 3D object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021). https:\/\/doi.org\/10.1109\/iccv48922.2021.01535","DOI":"10.1109\/iccv48922.2021.01535"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Geometry uncertainty projection network for monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3111\u20133121 (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16, pp. 194\u2013210. Springer (2020)","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., Lopez-Antequera, M., Kontschieder, P.: Disentangling monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"19_CR23","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":"19_CR24","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Weng, X., Kitani, K.: Monocular 3D object detection with pseudo-lidar point cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Xu, B., Chen, Z.: Multi-level fusion based 3D object detection from monocular images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Yang, J., Liu, S., Li, Z., Li, X., Sun, J.: StreamYOLO: Real-time object detection for streaming perception. arXiv preprint arXiv:2207.10433 (2022)","DOI":"10.1109\/CVPR52688.2022.00531"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: flexible monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3289\u20133298 (2021)","DOI":"10.1109\/CVPR46437.2021.00330"}],"container-title":["IFIP Advances in Information and Communication Technology","Artificial Intelligence Applications and Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-96239-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T06:37:52Z","timestamp":1760337472000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-96239-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031962387","9783031962394"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-96239-4_19","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1868-422X"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"22 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Artificial Intelligence Applications and Innovations","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ifipaiai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}