{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T11:10:17Z","timestamp":1778238617487,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570836","type":"print"},{"value":"9789819570843","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-7084-3_38","type":"book-chapter","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T10:23:04Z","timestamp":1778235784000},"page":"548-557","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning 3D Proposals in\u00a0Spatio-Temporal Transformer for\u00a0Multi-camera Driving Scene Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8238-1117","authenticated-orcid":false,"given":"Wenxuan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7955-0782","authenticated-orcid":false,"given":"Qin","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"38_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":"38_CR2","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: ECCV, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: Homography loss for monocular 3D object detection. In: CVPR, pp. 1080\u20131089 (2022)","DOI":"10.1109\/CVPR52688.2022.00115"},{"key":"38_CR4","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)"},{"issue":"1\u20132","key":"38_CR5","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Nav. Res. Logist. Q."},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Li, W., Zhou, J., Chen, C., Yu, H., Du, B., Zou, Q.: Bevfix: deep feature enhancement for robust 3D object detection. Neural Netw. 107675 (2025)","DOI":"10.1016\/j.neunet.2025.107675"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Co-Fix3D: enhancing 3D object detection with collaborative refinement. IEEE RA-L 211\u2013219 (2025)","DOI":"10.1109\/LRA.2025.3555859"},{"key":"38_CR8","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":"38_CR9","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":"38_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: PETR: position embedding transformation for multi-view 3D object detection. In: ECCV, pp. 531\u2013548. Springer (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"38_CR11","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":"38_CR12","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: CVPR, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Sun, Y., Hariharan, B.: Dynamo-depth: fixing unsupervised depth estimation for dynamical scenes. NIPS 36, 54987\u201355005 (2023)","DOI":"10.52202\/075280-2399"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Tao, R., Han, W., Qiu, Z., Xu, C.z., Shen, J.: Weakly supervised monocular 3D object detection using multi-view projection and direction consistency. In: CVPR, pp. 17482\u201317492 (2023)","DOI":"10.1109\/CVPR52729.2023.01677"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Tseng, C.Y., Chen, Y.R., Lee, H.Y., Wu, T.H., Chen, W.C., Hsu, W.H.: Crossdtr: cross-view and depth-guided transformers for 3D object detection. In: ICRA, pp. 4850\u20134857 (2023)","DOI":"10.1109\/ICRA48891.2023.10161451"},{"key":"38_CR16","unstructured":"Wang, T., Xinge, Z., Pang, J., Lin, D.: Probabilistic and geometric depth: detecting objects in perspective. In: CoRL, pp. 1475\u20131485 (2022)"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: FCOS3D: fully convolutional one-stage monocular 3D object detection. In: CVPR, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"38_CR18","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, pp. 180\u2013191 (2022)"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: CVPR, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"38_CR20","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv:1908.09492 (2019)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7084-3_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T10:23:13Z","timestamp":1778235793000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7084-3_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570836","9789819570843"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7084-3_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","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":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}