{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:09:40Z","timestamp":1783930180855,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819235032","type":"print"},{"value":"9789819235049","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3504-9_25","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:36:56Z","timestamp":1783928216000},"page":"303-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DUG-VT: Depth and Uncertainty Guided View Transformer for Robust BEV Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Xiaolu","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiaoling","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1833-2009","authenticated-orcid":false,"given":"Yixin","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4971-0276","authenticated-orcid":false,"given":"Tongtong","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5865-7724","authenticated-orcid":false,"given":"Kai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"25_CR1","first-page":"1663","volume-title":"Conference on Robot Learning","author":"F Bartoccioni","year":"2023","unstructured":"Bartoccioni, F., Zablocki, \u00c9., Bursuc, A., P\u00e9rez, P., Cord, M., Alahari, K.: Lara: latents and rays for multi-camera bird\u2019s-eye-view semantic segmentation. In: Conference on Robot Learning, pp. 1663\u20131672. PMLR (2023)"},{"key":"25_CR2","first-page":"11621","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"H Caesar","year":"2020","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)"},{"key":"25_CR3","first-page":"15195","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Chambon","year":"2024","unstructured":"Chambon, L., Zablocki, E., Chen, M., Bartoccioni, F., P\u00e9rez, P., Cord, M.: Pointbev: a sparse approach for bev predictions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15195\u201315204 (2024)"},{"key":"25_CR4","first-page":"5496","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Gu","year":"2023","unstructured":"Gu, J., et al.: Vip3d: end-to-end visual trajectory prediction via 3d agent queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5496\u20135506 (2023)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Fang, Z., Li, J., Ambrus, R., Fragkiadaki, K.: Simplebev: what really matters for multi-sensor bev perception? arXiv preprint arXiv:2206.07959 (2022)","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"25_CR6","first-page":"15273","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"A Hu","year":"2021","unstructured":"Hu, A., et al.: Fiery: future instance prediction in bird\u2019s-eye view from surround monocular cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15273\u201315282 (2021)"},{"key":"25_CR7","first-page":"533","volume-title":"European Conference on Computer Vision","author":"S Hu","year":"2022","unstructured":"Hu, S., Chen, L., Wu, P., Li, H., Yan, J., Tao, D.: St-p3: end-to-end vision-based autonomous driving via spatial-temporal feature learning. In: European Conference on Computer Vision, pp. 533\u2013549. Springer (2022)"},{"key":"25_CR8","first-page":"17853","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Hu","year":"2023","unstructured":"Hu, Y., et al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)"},{"key":"25_CR9","volume-title":"Bevdet: High-Performance Multi-camera 3d Object Detection in Bird-Eye-View","author":"J Huang","year":"2021","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: Bevdet: High-Performance Multi-camera 3d Object Detection in Bird-Eye-View (2021)"},{"key":"25_CR10","first-page":"1477","volume":"37","author":"Y Li","year":"2023","unstructured":"Li, Y., et al.: Bevdepth: acquisition of reliable depth for multi-view 3d object detection. Proc. AAAI Conf. Artif. Intell. 37, 1477\u20131485 (2023)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. arXiv preprint arXiv:2203.17270 (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"25_CR12","first-page":"2980","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"TY Lin","year":"2017","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)"},{"key":"25_CR13","first-page":"3262","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Y Liu","year":"2023","unstructured":"Liu, Y., et al.: Petrv2: a unified framework for 3d perception from multi-camera images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3262\u20133272 (2023)"},{"key":"25_CR14","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"25_CR15","first-page":"17124","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"SW Lu","year":"2025","unstructured":"Lu, S.W., Tsai, Y.H., Chen, Y.T.: Toward real-world bev perception: depth uncertainty estimation via gaussian splatting. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17124\u201317133 (2025)"},{"key":"25_CR16","first-page":"9590","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"C Pan","year":"2023","unstructured":"Pan, C., He, Y., Peng, J., Zhang, Q., Sui, W., Zhang, Z.: Baeformer: bi-directional and early interaction transformers for bird\u2019s eye view semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9590\u20139599 (2023)"},{"key":"25_CR17","first-page":"194","volume-title":"European Conference on Computer Vision","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3d. In: European Conference on Computer Vision, pp. 194\u2013210. Springer (2020)"},{"key":"25_CR18","first-page":"6612","volume":"39","author":"S Qiu","year":"2025","unstructured":"Qiu, S., Li, X., Xue, X., Pu, J.: Pc-bev: an efficient polar-cartesian bev fusion framework for lidar semantic segmentation. Proc. AAAI Conf. Artif. Intell. 39, 6612\u20136620 (2025)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"25_CR19","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3d object detection. arXiv preprint arXiv:1811.08188 (2018)"},{"key":"25_CR20","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1109\/IROS58592.2024.10802147","volume-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"J Schramm","year":"2024","unstructured":"Schramm, J., et al.: Bevcar: camera-radar fusion for bev map and object segmentation. In: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1435\u20131442. IEEE (2024)"},{"key":"25_CR21","doi-asserted-by":"publisher","first-page":"53025","DOI":"10.52202\/075280-2307","volume":"36","author":"S Shao","year":"2023","unstructured":"Shao, S., Pei, Z., Wu, X., Liu, Z., Chen, W., Li, Z.: Iebins: iterative elastic bins for monocular depth estimation. Adv. Neural Inf. Process. Syst. 36, 53025\u201353037 (2023)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"25_CR22","first-page":"6105","volume-title":"International Conference on Machine Learning","author":"M Tan","year":"2019","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"25_CR23","unstructured":"Xie, E., et al.: M2bev: multi-camera joint 3d detection and segmentation with unified birds-eye view representation. arxiv 2022. arXiv preprint arXiv:2204.05088 (2022)"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Dual-bev nav: dual-layer bev-based heuristic path planning for robotic navigation in unstructured outdoor environments. arXiv preprint arXiv:2501.18351 (2025)","DOI":"10.1109\/ICRA55743.2025.11128157"},{"key":"25_CR25","first-page":"9960","volume":"39","author":"J Zhang","year":"2025","unstructured":"Zhang, J., Zhang, Y., Qi, Y., Fu, Z., Liu, Q., Wang, Y.: Geobev: learning geometric bev representation for multi-view 3d object detection. Adv. Neural Inf. Process. Syst. 39, 9960\u20139968 (2025)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"25_CR26","first-page":"13760","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"B Zhou","year":"2022","unstructured":"Zhou, B., Kr\u00e4henb\u00fchl, P.: Cross-view transformers for real-time map-view semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13760\u201313769 (2022)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3504-9_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:37:01Z","timestamp":1783928221000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3504-9_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819235032","9789819235049"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3504-9_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","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":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}