{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T17:57:42Z","timestamp":1787594262200,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729065","type":"print"},{"value":"9783031729072","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72907-2_17","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"286-302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["DualBEV: Unifying Dual View Transformation with\u00a0Probabilistic Correspondences"],"prefix":"10.1007","author":[{"given":"Peidong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wancheng","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dixiao","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., Barnard, K.: Attentional feature fusion. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Fang, Z., Li, J., Ambrus, R., Fragkiadaki, K.: Simple-BEV: what really matters for multi-sensor BEV perception? In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR5","unstructured":"Huang, J., Huang, G.: BEVPoolv2: a cutting-edge implementation of BEVDet toward deployment (2022). arXiv:2211.17111"},{"key":"17_CR6","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection (2023). arXiv:2307.11477"},{"key":"17_CR7","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view (2021). arXiv:2112.11790"},{"key":"17_CR8","unstructured":"Huang, P., et al.: TiG-BEV: multi-view BEV 3D object detection via target inner-geometry learning (2022). arXiv:2212.13979"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: PolarFormer: multi-camera 3D object detection with polar transformers. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"17_CR10","unstructured":"Jinqing, Z., Yanan, Z., Qingjie, L., Yunhong, W.: SA-BEV: generating semantic-aware bird\u2019s-eye-view feature for multi-view 3D object detection. In: ICCV (2023)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J.: CenterMask: real-time anchor-free instance segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"17_CR12","unstructured":"Li, Y., Chen, Y., Qi, X., Li, Z., Sun, J., Jia, J.: Unifying voxel-based representation with transformer for 3D object detection. In: NeurIPS (2022)"},{"key":"17_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 dynamic temporal stereo. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"17_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., Yu, Z., Wang, W., Anandkumar, A., Lu, T., Alvarez, J.M.: FB-BEV: BEV representation from forward-backward view transformations. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"17_CR17","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4D: multi-view 3D object detection with sparse spatial-temporal fusion (2022). arXiv:2211.10581"},{"key":"17_CR18","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: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"17_CR19","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/978-3-031-19812-0_31","volume-title":"ECCV 2022","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: PETR: position embedding transformation for multi-view 3D object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 531\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: PETRv2: a unified framework for 3D perception from multi-camera images. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"17_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"17_CR25","unstructured":"Park, J., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3D object detection. In: ICLR (2023)"},{"key":"17_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","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: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"17_CR28","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3D object detection. In: BMVC (2019)"},{"key":"17_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"17_CR30","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: CoRL (2022)"},{"key":"17_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Wu, Y., Li, R., Qin, Z., Zhao, X., Li, X.: HeightFormer: explicit height modeling without extra data for camera-only 3D object detection in bird\u2019s eye view (2023). arXiv:2307.13510","DOI":"10.1109\/TIP.2024.3427701"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"17_CR34","unstructured":"Xiaowei, C., et al.: BEV-SAN: accurate BEV 3D object detection via slice attention networks. In: CVPR (2023)"},{"key":"17_CR35","unstructured":"Xie, E., et al.: M$$^2$$BEV: multi-camera joint 3D detection and segmentation with unified birds-eye view representation (2022). arXiv:2204.05088"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Xiong, K., et al.: CAPE: camera view position embedding for multi-view 3D object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: BEVFormer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, H., Ge, Z., Li, Z., Zhang, X.: MatrixVT: efficient multi-camera to BEV transformation for 3D perception. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00785"},{"key":"17_CR39","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection (2019). arXiv:1908.09492"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72907-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:33:03Z","timestamp":1730302383000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72907-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729065","9783031729072"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72907-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","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"}}]}}