{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T18:06:09Z","timestamp":1790705169895,"version":"4.1.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200762","type":"print"},{"value":"9783031200779","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20077-9_12","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"193-209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["INT: Towards Infinite-Frames 3D Detection with\u00a0an\u00a0Efficient Framework"],"prefix":"10.1007","author":[{"given":"Jianyun","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenwei","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyu","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peihan","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongmin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"12_CR1","unstructured":"Bewley, A., Sun, P., Mensink, T., Anguelov, D., Sminchisescu, C.: Range conditioned dilated convolutions for scale invariant 3d object detection. arXiv preprint arXiv:2005.09927 (2020)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"12_CR3","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)","DOI":"10.1109\/CVPR.2017.691"},{"key":"12_CR4","unstructured":"Chong, Z., et al.: MonodiStill: learning spatial features for monocular 3d object detection. arXiv preprint arXiv:2201.10830 (2022)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4d spatio-temporal convnets: Minkowski convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Fan, L., Xiong, X., Wang, F., Wang, N., Zhang, Z.: Rangedet:in defense of range view for lidar-based 3d object detection. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Feng, Y., Ma, L., Liu, W., Luo, J.: Spatio-temporal video re-localization by warp LSTM. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1288\u20131297 (2019)","DOI":"10.1109\/CVPR.2019.00138"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: M3DeTR: multi-representation, multi-scale, mutual-relation 3d object detection with transformers. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (2021)","DOI":"10.1109\/WACV51458.2022.00235"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"He, L., et al.: End-to-end video object detection with spatial-temporal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1507\u20131516 (2021)","DOI":"10.1145\/3474085.3475285"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Afdetv2: rethinking the necessity of the second stage for object detection from point clouds. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v36i1.19980"},{"key":"12_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1007\/978-3-030-58523-5_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Huang","year":"2020","unstructured":"Huang, R., et al.: An LSTM approach to temporal 3d object detection in LiDAR point clouds. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 266\u2013282. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_16"},{"key":"12_CR12","unstructured":"Jaderberg, M., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems., vol. 28 (2015)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Kang, K., et al.: Object detection in videos with tubelet proposal networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 727\u2013735 (2017)","DOI":"10.1109\/CVPR.2017.101"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Ku, J., Pon, A.D., Waslander, S.L.: Monocular 3d object detection leveraging accurate proposals and shape reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11867\u201311876 (2019)","DOI":"10.1109\/CVPR.2019.01214"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"12_CR16","unstructured":"Li, B., Zhang, T., Xia, T.: Vehicle detection from 3d lidar using fully convolutional network. arXiv preprint arXiv:1608.07916 (2016)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Li, B., Ouyang, W., Sheng, L., Zeng, X., Wang, X.: Gs3d: an efficient 3d object detection framework for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1019\u20131028 (2019)","DOI":"10.1109\/CVPR.2019.00111"},{"key":"12_CR18","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 Conference on Computer Vision and Pattern Recognition, pp. 7345\u20137353 (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Meyer, G.P., Laddha, A., Kee, E., Vallespi-Gonzalez, C., Wellington, C.K.: LaserNet: an efficient probabilistic 3d object detector for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12677\u201312686 (2019)","DOI":"10.1109\/CVPR.2019.01296"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Miao, Z., et al.: PVGNet: a bottom-up one-stage 3d object detector with integrated multi-level features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3279\u20133288 (2021)","DOI":"10.1109\/CVPR46437.2021.00329"},{"key":"12_CR21","unstructured":"Ngiam, J., Caine, B., Han, W., Yang, B., Vasudevan, V.: StarNet: targeted computation for object detection in point clouds. arXiv preprint arXiv:1908.11069 (2019)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Piergiovanni, A., Casser, V., Ryoo, M.S., Angelova, A.: 4d-net for learned multi-modal alignment. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01515"},{"key":"12_CR23","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: Proceedings of the IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"12_CR24","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)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"12_CR25","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Li, H.: PV-RCNN: point-voxel feature set abstraction for 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"12_CR27","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 Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Sun, P.,et al.: RSN: range sparse net for efficient, accurate lidar 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"12_CR30","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 Conference on Computer Vision and Pattern Recognition, pp. 4604\u20134612 (2020)","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W.L., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8445\u20138453 (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Wu, P., Chen, S., Metaxas, D.N.: MotionNet: joint perception and motion prediction for autonomous driving based on bird\u2019s eye view maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11385\u201311395 (2020)","DOI":"10.1109\/CVPR42600.2020.01140"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Xiao, F., Lee, Y.J.: Video object detection with an aligned spatial-temporal memory. In: European Conference on Computer Vision, pp. 485\u2013501 (2018)","DOI":"10.1007\/978-3-030-01237-3_30"},{"key":"12_CR34","unstructured":"Xu, J., Tang, X., Dou, J., Shu, X., Zhu, Y.: CenterAtt: Fast 2-stage center attention network. arXiv preprint arXiv:2106.10493 (2021)"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Xu, J., Zhang, R., Dou, J., Zhu, Y., Sun, J., Pu, S.: RPVNet: a deep and efficient range-point-voxel fusion network for lidar point cloud segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 16024\u201316033 (2021)","DOI":"10.1109\/ICCV48922.2021.01572"},{"issue":"10","key":"12_CR36","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":"12_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhou, Y., Chen, Z., Ngiam, J.: 3d-man: 3d multi-frame attention network for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1863\u20131872 (2021)","DOI":"10.1109\/CVPR46437.2021.00190"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Yin, J., Shen, J., Guan, C., Zhou, D., Yang, R.: Lidar-based online 3d video object detection with graph-based message passing and spatiotemporal transformer attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01151"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3d object detection and tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"12_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1007\/978-3-030-58583-9_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JH Yoo","year":"2020","unstructured":"Yoo, J.H., Kim, Y., Kim, J., Choi, J.W.: 3D-CVF: generating joint camera and LiDAR features using cross-view spatial feature fusion for 3d object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 720\u2013736. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58583-9_43"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et al.: Lift: Learning 4d lidar image fusion transformer for 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 17172\u201317181 (2022)","DOI":"10.1109\/CVPR52688.2022.01666"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"12_CR43","unstructured":"Zhou, Y., et al.: End-to-end multi-view fusion for 3d object detection in lidar point clouds. In: Conference on Robot Learning, pp. 923\u2013932. PMLR (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20077-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:10:11Z","timestamp":1667866211000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"6 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}