{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:35:08Z","timestamp":1782408908336,"version":"3.54.5"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","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\/978-3-031-20074-8_39","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"680-697","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["MPPNet: Multi-frame Feature Intertwining with\u00a0Proxy Points for\u00a03D Temporal Object Detection"],"prefix":"10.1007","author":[{"given":"Xuesong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoshuai","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ka Chun","family":"Cheung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"39_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/978-3-030-01258-8_21","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Bertasius","year":"2018","unstructured":"Bertasius, G., Torresani, L., Shi, J.: Object detection in video with spatiotemporal sampling networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 342\u2013357. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_21"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10337\u201310346 (2020)","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., Mei, T.: Relation distillation networks for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7023\u20137032 (2019)","DOI":"10.1109\/ICCV.2019.00712"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Detect to track and track to detect. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3038\u20133046 (2017)","DOI":"10.1109\/ICCV.2017.330"},{"key":"39_CR5","unstructured":"Ge, R., Ding, Z., Hu, Y., Wang, Y., Chen, S., Huang, L., Li, Y.: AFDet: anchor free one stage 3D object detection. arXiv preprint arXiv:2006.12671 (2020)"},{"key":"39_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-030-58589-1_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Han","year":"2020","unstructured":"Han, M., Wang, Y., Chang, X., Qiao, Yu.: Mining inter-video proposal relations for video object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 431\u2013446. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_26"},{"key":"39_CR7","unstructured":"Hetang, C., Qin, H., Liu, S., Yan, J.: Impression network for video object detection. arXiv preprint arXiv:1712.05896 (2017)"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: AFDetV2: rethinking the necessity of the second stage for object detection from point clouds. arXiv preprint arXiv:2112.09205 (2021)","DOI":"10.1609\/aaai.v36i1.19980"},{"issue":"8","key":"39_CR9","doi-asserted-by":"publisher","first-page":"3195","DOI":"10.1109\/TNNLS.2021.3053249","volume":"33","author":"L Jiao","year":"2021","unstructured":"Jiao, L., Zhang, R., Liu, F., Yang, S., Hou, B., Li, L., Tang, X.: New generation deep learning for video object detection: a survey. IEEE Trans. Neural Netw. Learn. Syst. 33(8), 3195\u20133215 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"39_CR10","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"},{"issue":"10","key":"39_CR11","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1109\/TCSVT.2017.2736553","volume":"28","author":"K Kang","year":"2017","unstructured":"Kang, K., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2896\u20132907 (2017)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, F., Wang, N.: LiDAR R-CNN: an efficient and universal 3D object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7546\u20137555 (2021)","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Luo, C., Yang, X., Yuille, A.: Exploring simple 3D multi-object tracking for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10488\u201310497 (2021)","DOI":"10.1109\/ICCV48922.2021.01032"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Luo, W., Yang, B., Urtasun, R.: Fast and furious: real time end-to-end 3D detection, tracking and motion forecasting with a single convolutional net. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3569\u20133577 (2018)","DOI":"10.1109\/CVPR.2018.00376"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Mao, J., Niu, M., Bai, H., Liang, X., Xu, H., Xu, C.: Pyramid R-CNN: towards better performance and adaptability for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2723\u20132732 (2021)","DOI":"10.1109\/ICCV48922.2021.00272"},{"key":"39_CR17","unstructured":"Ngiam, J., et al.: StarNet: targeted computation for object detection in point clouds. arXiv preprint arXiv:1908.11069 (2019)"},{"key":"39_CR18","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\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"39_CR19","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Zhou, Y., Najibi, M., Sun, P., Vo, K., Deng, B., Anguelov, D.: Offboard 3D object detection from point cloud sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6134\u20136144 (2021)","DOI":"10.1109\/CVPR46437.2021.00607"},{"key":"39_CR21","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":"39_CR22","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)","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"39_CR23","unstructured":"Shi, S., Guo, C., Yang, J., Li, H.: PV-RCNN: the top-performing lidar-only solutions for 3D detection\/3D tracking\/domain adaptation of Waymo open dataset challenges. arXiv preprint arXiv:2008.12599 (2020)"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN++: point-voxel feature set abstraction with local vector representation for 3D object detection. arXiv preprint arXiv:2102.00463 (2021)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"39_CR25","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)","DOI":"10.1109\/CVPR.2019.00086"},{"issue":"8","key":"39_CR26","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."},{"key":"39_CR27","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"},{"key":"39_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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5725\u20135734 (2021)","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"39_CR29","unstructured":"Tolstikhin, I.O., et al.: MLP-Mixer: an all-MLP architecture for vision. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"39_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"39_CR31","doi-asserted-by":"publisher","unstructured":"Wang, J., Chakraborty, R., Yu, S.X.: Spatial transformer for 3D point clouds. IEEE Trans. Pattern Anal. Mach. Intell. 1 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2021.3070341","DOI":"10.1109\/TPAMI.2021.3070341"},{"key":"39_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/978-3-030-01261-8_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Wang","year":"2018","unstructured":"Wang, S., Zhou, Y., Yan, J., Deng, Z.: Fully motion-aware network for video object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 557\u2013573. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_33"},{"key":"39_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58542-6_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Wang","year":"2020","unstructured":"Wang, Y., et al.: Pillar-based object detection for autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 18\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_2"},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9217\u20139225 (2019)","DOI":"10.1109\/ICCV.2019.00931"},{"key":"39_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-030-01237-3_30","volume-title":"Computer Vision \u2013 ECCV 2018","author":"F Xiao","year":"2018","unstructured":"Xiao, F., Lee, Y.J.: Video object detection with an aligned spatial-temporal memory. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 494\u2013510. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_30"},{"issue":"10","key":"39_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":"39_CR37","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., Urtasun, R.: PIXOR: real-time 3D object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7652\u20137660 (2018)","DOI":"10.1109\/CVPR.2018.00798"},{"key":"39_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: STD: sparse-to-dense 3D object detector for point cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1951\u20131960 (2019)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"39_CR39","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1863\u20131872 (2021)","DOI":"10.1109\/CVPR46437.2021.00190"},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"39_CR41","doi-asserted-by":"publisher","unstructured":"Yuan, Z., Song, X., Bai, L., Wang, Z., Ouyang, W.: Temporal-channel transformer for 3D lidar-based video object detection for autonomous driving. IEEE Trans. Circ. Syst. Video Technol. 1 (2021). https:\/\/doi.org\/10.1109\/TCSVT.2021.3082763","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"39_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, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"39_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"39_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2349\u20132358 (2017)","DOI":"10.1109\/CVPR.2017.441"}],"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\/978-3-031-20074-8_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:34:12Z","timestamp":1668198852000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_39","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":"12 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)"}}]}}