{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:25:29Z","timestamp":1774679129557,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698622","type":"print"},{"value":"9789819698639","type":"electronic"}],"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\/978-981-96-9863-9_34","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T14:38:56Z","timestamp":1753281536000},"page":"401-412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-view 3D Object Detection by Using a Preluded 2D Detector"],"prefix":"10.1007","author":[{"given":"Songyan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoyi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Chai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"34_CR1","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. arXiv preprint (2021)"},{"key":"34_CR2","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. 3598\u20133608 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S., Lift, S.S.: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: European Conference on Computer Vision (ECCV). pp. 194\u2013210 (2020)","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. arXiv preprint (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: Petr: position embedding transformation for multi- view 3d object detection. In: European Conference on Computer Vision (ECCV), pp. 531\u2013548 (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to- end object detection with transformers. In: European Conference on Computer Vision (ECCV), pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"34_CR7","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 (ICCV), pp. 3791\u20133800 (2023)","DOI":"10.1109\/ICCV51070.2023.00351"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2016)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J.: You only look once: Unified, real-time object detection. In: CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., et al.: Ssd: single shot multibox detector. In: ECCV, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: a simple and strong anchor-free object detector. TPAMI, pp. 69\u201376 (2020)","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"34_CR14","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint (2019)"},{"key":"34_CR15","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":"34_CR16","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":"34_CR17","doi-asserted-by":"crossref","unstructured":"Lee, Y., Hwang, J., Lee, S., Bae, Y., Park, J.: An energy and GPU-computation efficient backbone network for real-time object detection. In: CVPR Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"34_CR18","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint (2020)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"34_CR20","unstructured":"Park, J., Xu, C., Yang, S., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3d object detection. arXiv preprint (2022)"},{"key":"34_CR21","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4d v2: recurrent temporal fusion with sparse model. arXiv preprint (2023)"},{"key":"34_CR22","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. 7132\u20137141 (2023)","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"34_CR23","unstructured":"Wang, J., Li, Z., Sun, K., Liu, X., Zhou, Y.: DVPE: Divided View Position Embedding for Multi-View 3D Object Detection. arXiv preprint (2024)"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Feng, C., Jie, Z., Zhong, Y., Chu, X., Ma, L.: AeDet: azimuth-invariant multi-view 3D object detection. In: CVPR, pp. 21580\u201321588 (2023)","DOI":"10.1109\/CVPR52729.2023.02067"},{"key":"34_CR25","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: PMLR, pp. 180\u2013191 (2022)"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yan, J., Jia, F., 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":"34_CR27","unstructured":"Li, P., Shen, W., Huang, Q., et al.: DualBEV: CNN is all you need in view transformation. arXiv preprint (2024)"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A. H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: CVPR, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"34_CR29","unstructured":"Wilson, B., Qi, W., Agarwal, T., et al.: Argoverse 2: next generation datasets for self- driving perception and forecasting. arXiv preprint. (2023)"},{"key":"34_CR30","unstructured":"Kingma, D. P.: Adam: a method for stochastic optimization. arXiv preprint (2014)"},{"key":"34_CR31","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint (2019)"},{"key":"34_CR32","unstructured":"Huang, J., Huang, G.: BEVPoolv2: a Cutting-edge Implementation of BEVDet Toward Deployment. arXiv preprint (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\/978-981-96-9863-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T04:10:16Z","timestamp":1774671016000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9863-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698622","9789819698639"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9863-9_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","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":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 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":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}