{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:38:48Z","timestamp":1777657128878,"version":"3.51.4"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729669","type":"print"},{"value":"9783031729676","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-72967-6_12","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:03:17Z","timestamp":1730574197000},"page":"200-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Ray Denoising: Depth-Aware Hard Negative Sampling for\u00a0Multi-view 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Feng","family":"Liu","sequence":"first","affiliation":[]},{"given":"Tengteng","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Qianjing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Haotian","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Fang","family":"Wan","sequence":"additional","affiliation":[]},{"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Yanzhao","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3D-RPN: monocular 3D region proposal network for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9287\u20139296 (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"12_CR2","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":"12_CR3","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"},{"issue":"9","key":"12_CR4","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2009","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"11","key":"12_CR5","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"issue":"1","key":"12_CR6","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2015","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 142\u2013158 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR7","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"},{"key":"12_CR8","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"12_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":"12_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: Polarformer: multi-camera 3D object detection with polar transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1042\u20131050 (2023)","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Lee, Y., Hwang, J.W., Lee, S., Bae, Y., Park, J.: An energy and GPU-computation efficient backbone network for real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"12_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"12_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":"12_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":"12_CR15","series-title":"LNCS","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":"12_CR16","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICCV.2017.324"},{"key":"12_CR17","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4D: multi-view 3D object detection with sparse spatial-temporal fusion. arXiv preprint arXiv:2211.10581 (2022)"},{"key":"12_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":"12_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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18580\u201318590 (2023)","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"12_CR20","unstructured":"Liu, S., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR. arXiv preprint arXiv:2201.12329 (2022)"},{"key":"12_CR21","series-title":"LNCS","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":"12_CR22","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"12_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Delving into localization errors for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4721\u20134730 (2021)","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"12_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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3142\u20133152 (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"12_CR26","unstructured":"Park, J., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3D object detection. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"12_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":"12_CR28","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, pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 761\u2013769 (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"12_CR30","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3580\u20133589 (2023)","DOI":"10.1109\/ICCV51070.2023.00331"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1991\u20131999 (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"issue":"1","key":"12_CR33","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/34.655648","volume":"20","author":"KK Sung","year":"1998","unstructured":"Sung, K.K., Poggio, T.: Example-based learning for view-based human face detection. IEEE Trans. Pattern Anal. Mach. Intell. 20(1), 39\u201351 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR34","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3621\u20133631 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"12_CR35","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":"12_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"12_CR37","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":"12_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Z., Huang, Z., Fu, J., Wang, N., Liu, S.: Object as query: lifting any 2D object detector to 3D detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3791\u20133800 (2023)","DOI":"10.1109\/ICCV51070.2023.00351"},{"key":"12_CR39","unstructured":"Wilson, B., et al.: Argoverse 2: next generation datasets for self-driving perception and forecasting. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Yan, J., et al.: Cross modal transformer: towards fast and robust 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18268\u201318278 (2023)","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"12_CR41","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"12_CR42","unstructured":"Zhang, H., et al.: Dino: DETR with improved denoising anchor boxes for end-to-end object detection. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"12_CR43","unstructured":"Zhang, H., et al.: Introducing depth into transformer-based 3D object detection. arXiv preprint arXiv:2302.13002 (2023)"},{"key":"12_CR44","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"},{"key":"12_CR45","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":"12_CR46","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Zong, Z., et al.: Temporal enhanced training of multi-view 3D object detector via historical object prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3781\u20133790 (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\/978-3-031-72967-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T18:17:35Z","timestamp":1732990655000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72967-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031729669","9783031729676"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72967-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 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"}}]}}