{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:14:46Z","timestamp":1783527286969,"version":"3.55.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733468","type":"print"},{"value":"9783031733475","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-73347-5_9","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"146-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["OPEN: Object-Wise Position Embedding for\u00a0Multi-view 3D Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6555-4038","authenticated-orcid":false,"given":"Jinghua","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4173-3994","authenticated-orcid":false,"given":"Tong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3268-880X","authenticated-orcid":false,"given":"Xiaoqing","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2513-2662","authenticated-orcid":false,"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0845-9578","authenticated-orcid":false,"given":"Shi","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9162-8570","authenticated-orcid":false,"given":"Xiao","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1867-5378","authenticated-orcid":false,"given":"Errui","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: A multimodal dataset for autonomous driving. In: CVPR, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"9_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel r-cnn: towards high performance voxel-based 3d object detection. In: AAAI, vol.\u00a035, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of detr with spatially modulated co-attention. In: ICCV, pp. 3621\u20133630 (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"He, C., Li, R., Li, S., Zhang, L.: Voxel set transformer: a set-to-set approach to 3d object detection from point clouds. In: CVPR, pp. 8417\u20138427 (2022)","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"He, C., Zeng, H., Huang, J., Hua, X.S., Zhang, L.: Structure aware single-stage 3d object detection from point cloud. In: CVPR, pp. 11873\u201311882 (2020)","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR8","unstructured":"Huang, J., Huang, G.: Bevdet4d: exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"9_CR9","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":"9_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: Far3d: expanding the horizon for surround-view 3d object detection. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"9_CR11","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. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: Dn-detr: accelerate detr training by introducing query denoising. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Dfa3d: 3d deformable attention for 2d-to-3d feature lifting. In: ICCV, pp. 6684\u20136693 (2023)","DOI":"10.1109\/ICCV51070.2023.00615"},{"key":"9_CR14","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: AAAI, vol.\u00a037, pp. 1486\u20131494 (2023)","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Bevdepth: acquisition of reliable depth for multi-view 3d object detection. In: AAAI, vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"9_CR16","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: ECCV, pp. 1\u201318. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"9_CR18","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4d v2: recurrent temporal fusion with sparse model. arXiv preprint arXiv:2305.14018 (2023)"},{"key":"9_CR19","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, pp. 18580\u201318590 (2023)","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"9_CR20","unstructured":"Liu, S., et al.: Dab-detr: dynamic anchor boxes are better queries for detr. In: ICLR (2022)"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: position embedding transformation for multi-view 3d object detection. In: ECCV 2022, pp. 531\u2013548. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Petrv2: a unified framework for 3d perception from multi-camera images. In: ICCV, pp. 3262\u20133272 (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"9_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional detr for fast training convergence. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A.: Is pseudo-lidar needed for monocular 3d object detection? In: ICCV, pp. 3142\u20133152 (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"9_CR26","unstructured":"Park, J., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3d object detection. In: ICLR (2022)"},{"key":"9_CR27","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":"9_CR28","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3d object detection in point clouds. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"9_CR29","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: CVPR, pp. 652\u2013660 (2017)"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: Pv-rcnn: point-voxel feature set abstraction for 3d object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"9_CR31","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","volume":"131","author":"S Shi","year":"2021","unstructured":"Shi, S., et al.: Pv-rcnn++: point-voxel feature set abstraction with local vector representation for 3d object detection. IJCV 131, 531\u2013551 (2021)","journal-title":"IJCV"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Shu, C., Deng, J., Yu, F., Liu, Y.: 3dppe: 3d point positional encoding for transformer-based multi-camera 3d object detection. In: ICCV, pp. 3580\u20133589 (2023)","DOI":"10.1109\/ICCV51070.2023.00331"},{"key":"9_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol.\u00a030 (2017)"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, Y., Wang, T., Li, Y., Zhang, X.: Exploring object-centric temporal modeling for efficient multi-view 3d object detection. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3d: fully convolutional one-stage monocular 3d object detection. In: ICCV, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor detr: query design for transformer-based detector. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Xiong, K., et al.: Cape: camera view position embedding for multi-view 3d object detection. In: CVPR.=, pp. 21570\u201321579 (2023)","DOI":"10.1109\/CVPR52729.2023.02066"},{"issue":"10","key":"9_CR39","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: Bevformer v2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: CVPR, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3dssd: point-based 3d single stage object detector. In: CVPR, pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"9_CR42","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. In: CVPR, pp. 1951\u20131960 (2019)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"9_CR43","unstructured":"Zhang, H., et al.: Dino: detr with improved denoising anchor boxes for end-to-end object detection. In: ICLR (2023)"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., Guo, Y.: Not all points are equal: learning highly efficient point-based detectors for 3d lidar point clouds. In: CVPR, pp. 18953\u201318962 (2022)","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3d object detection. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"9_CR46","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492 (2019)"},{"key":"9_CR47","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. In: ICLR (2021)"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Zong, Z., et al.: Temporal enhanced training of multi-view 3d object detector via historical object prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00350"}],"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\/978-3-031-73347-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:47:02Z","timestamp":1730108822000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73347-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031733468","9783031733475"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73347-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}