{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:41:32Z","timestamp":1752982892999,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984343"},{"type":"electronic","value":"9789819984350"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8435-0_32","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"401-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["URFormer: Unified Representation LiDAR-Camera 3D Object Detection with\u00a0Transformer"],"prefix":"10.1007","author":[{"given":"Guoxin","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jun","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhepeng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Kuihe","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Ziying","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907\u20131915 (2017)","key":"32_CR1","DOI":"10.1109\/CVPR.2017.691"},{"doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, Y., Zhang, X., Sun, J., Jia, J.: Focal sparse convolutional networks for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5428\u20135437 (2022)","key":"32_CR2","DOI":"10.1109\/CVPR52688.2022.00535"},{"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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1201\u20131209 (2021)","key":"32_CR3","DOI":"10.1609\/aaai.v35i2.16207"},{"doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","key":"32_CR4","DOI":"10.1109\/CVPR.2012.6248074"},{"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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8417\u20138427 (2022)","key":"32_CR5","DOI":"10.1109\/CVPR52688.2022.00823"},{"doi-asserted-by":"crossref","unstructured":"Hu, M., Wang, S., Li, B., Ning, S., Fan, L., Gong, X.: Penet: towards precise and efficient image guided depth completion. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13656\u201313662. IEEE (2021)","key":"32_CR6","DOI":"10.1109\/ICRA48506.2021.9561035"},{"key":"32_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58555-6_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Huang","year":"2020","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: EPNet: enhancing point features with image semantics for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 35\u201352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_3"},{"doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., Urtasun, R.: Multi-task multi-sensor fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7345\u20137353 (2019)","key":"32_CR8","DOI":"10.1109\/CVPR.2019.00752"},{"doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Voxel transformer for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3164\u20133173 (2021)","key":"32_CR9","DOI":"10.1109\/ICCV48922.2021.00315"},{"doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., Radha, H.: Fast-clocs: fast camera-lidar object candidates fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 187\u2013196 (2022)","key":"32_CR10","DOI":"10.1109\/WACV51458.2022.00380"},{"doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3D object detection from RGB-D data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","key":"32_CR11","DOI":"10.1109\/CVPR.2018.00102"},{"doi-asserted-by":"crossref","unstructured":"Sheng, H., et al.: Improving 3D object detection with channel-wise transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2743\u20132752 (2021)","key":"32_CR12","DOI":"10.1109\/ICCV48922.2021.00274"},{"doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529\u201310538 (2020)","key":"32_CR13","DOI":"10.1109\/CVPR42600.2020.01054"},{"doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013779 (2019)","key":"32_CR14","DOI":"10.1109\/CVPR.2019.00086"},{"issue":"8","key":"32_CR15","first-page":"2647","volume":"43","author":"S Shi","year":"2020","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2647\u20132664 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Song, Z., Jia, C., Yang, L., Wei, H., Liu, L.: Graphalign++: an accurate feature alignment by graph matching for multi-modal 3D object detection. IEEE Trans. Circuits Syst. Video Technol. (2023)","key":"32_CR16","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"32_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3271020","volume":"61","author":"Z Song","year":"2023","unstructured":"Song, Z., Wei, H., Jia, C., Xia, Y., Li, X., Zhang, C.: Vp-net: voxels as points for 3-D object detection. IEEE Trans. Geosci. Remote Sens. 61, 1\u201312 (2023). https:\/\/doi.org\/10.1109\/TGRS.2023.3271020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"32_CR18"},{"doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., Beijbom, O.: Pointpainting: sequential fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4604\u20134612 (2020)","key":"32_CR19","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"32_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110080","volume":"259","author":"L Wang","year":"2023","unstructured":"Wang, L., et al.: SAT-GCN: self-attention graph convolutional network-based 3D object detection for autonomous driving. Knowl.-Based Syst. 259, 110080 (2023)","journal-title":"Knowl.-Based Syst."},{"doi-asserted-by":"publisher","unstructured":"Wang, L., et al.: Multi-modal 3D object detection in autonomous driving: a survey and taxonomy. IEEE Trans. Intell. Veh. 8(7), 3781\u20133798 . https:\/\/doi.org\/10.1109\/TIV.2023.3264658","key":"32_CR21","DOI":"10.1109\/TIV.2023.3264658"},{"doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Sparse fuse dense: towards high quality 3D detection with depth completion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5418\u20135427 (2022)","key":"32_CR22","DOI":"10.1109\/CVPR52688.2022.00534"},{"issue":"10","key":"32_CR23","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"},{"doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Bevheight: a robust framework for vision-based roadside 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21611\u201321620, June 2023","key":"32_CR24","DOI":"10.1109\/CVPR52729.2023.02070"},{"unstructured":"Yin, T., Zhou, X., Kr\u00e4henb\u00fchl, P.: Multimodal virtual point 3D detection. In: Advances in Neural Information Processing Systems, vol. 34, pp. 16494\u201316507 (2021)","key":"32_CR25"},{"key":"32_CR26","first-page":"1","volume":"72","author":"X Zhang","year":"2022","unstructured":"Zhang, X., et al.: Ri-fusion: 3D object detection using enhanced point features with range-image fusion for autonomous driving. IEEE Trans. Instrum. Meas. 72, 1\u201313 (2022)","journal-title":"IEEE Trans. Instrum. Meas."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8435-0_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:14:27Z","timestamp":1703319267000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8435-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984343","9789819984350"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8435-0_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}