{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:32:56Z","timestamp":1777570376398,"version":"3.51.4"},"publisher-location":"Cham","reference-count":80,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200854","type":"print"},{"value":"9783031200861","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\/978-3-031-20086-1_17","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:31:55Z","timestamp":1668076315000},"page":"293-310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["3D Siamese Transformer Network for\u00a0Single Object Tracking on\u00a0Point Clouds"],"prefix":"10.1007","author":[{"given":"Le","family":"Hui","sequence":"first","affiliation":[]},{"given":"Lingpeng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Linghua","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Kaihao","family":"Lan","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"17_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850\u2013865. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Bibi, A., Zhang, T., Ghanem, B.: 3D part-based sparse tracker with automatic synchronization and registration. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.160"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. arXiv preprint arXiv:1903.11027 (2019)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"17_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Chiu, H.k., Prioletti, A., Li, J., Bohg, J.: Probabilistic 3D multi-object tracking for autonomous driving. arXiv preprint arXiv:2001.05673 (2020)","DOI":"10.1109\/ICRA48506.2021.9561754"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Comport, A.I., Marchand, \u00c9., Chaumette, F.: Robust model-based tracking for robot vision. In: IROS (2004)","DOI":"10.1163\/156855305774662226"},{"key":"17_CR9","unstructured":"Cui, Y., Fang, Z., Shan, J., Gu, Z., Sifan, Z.: 3D object tracking with Transformer. In: BMVC (2021)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Shahbaz Khan, F., Felsberg, M.: ECO: efficient convolution operators for tracking. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Hager, G., Shahbaz Khan, F., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.490"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Shahbaz Khan, F., Felsberg, M., Van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.143"},{"key":"17_CR14","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"17_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR16","unstructured":"Fan, H., Yang, Y., Kankanhalli, M.: Point 4D Transformer networks for spatio-temporal modeling in point cloud videos. In: CVPR"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Feng, T., Jiao, L., Zhu, H., Sun, L.: A novel object re-track framework for 3D point clouds. In: ACM MM (2020)","DOI":"10.1145\/3394171.3413742"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Giancola, S., Zarzar, J., Ghanem, B.: Leveraging shape completion for 3D Siamese tracking. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00145"},{"issue":"5","key":"17_CR20","first-page":"1","volume":"830","author":"N Gordon","year":"2004","unstructured":"Gordon, N., Ristic, B., Arulampalam, S.: Beyond the Kalman filter: particle filters for tracking applications. Artech House, London 830(5), 1\u20134 (2004)","journal-title":"Artech House, London"},{"key":"17_CR21","unstructured":"Guo, M.H., Cai, J.X., Liu, Z.N., Mu, T.J., Martin, R.R., Hu, S.M.: PCT: point cloud transformer. arXiv preprint arXiv:2012.09688 (2020)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Guo, Q., Feng, W., Zhou, C., Huang, R., Wan, L., Wang, S.: Learning dynamic Siamese network for visual object tracking. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.196"},{"key":"17_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/978-3-319-46448-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"D Held","year":"2016","unstructured":"Held, D., Thrun, S., Savarese, S.: Learning to track at 100 FPS with deep regression networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 749\u2013765. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_45"},{"key":"17_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1007\/978-3-642-33765-9_50","volume-title":"Computer Vision \u2013 ECCV 2012","author":"JF Henriques","year":"2012","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 702\u2013715. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33765-9_50"},{"issue":"3","key":"17_CR25","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2014","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583\u2013596 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR26","unstructured":"Hui, L., Wang, L., Cheng, M., Xie, J., Yang, J.: 3D Siamese voxel-to-BEV tracker for sparse point clouds. In: NeurIPS (2021)"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Hui, L., Yang, H., Cheng, M., Xie, J., Yang, J.: Pyramid point cloud Transformer for large-scale place recognition. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00604"},{"key":"17_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1007\/978-3-030-11009-3_8","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"U Kart","year":"2019","unstructured":"Kart, U., K\u00e4m\u00e4r\u00e4inen, J.-K., Matas, J.: How to make an RGBD tracker? In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11129, pp. 148\u2013161. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11009-3_8"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Kart, U., Lukezic, A., Kristan, M., K\u00e4m\u00e4r\u00e4inen, J., Matas, J.: Object tracking by reconstruction with view-specific discriminative correlation filters. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00143"},{"key":"17_CR30","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive Transformers with linear attention. In: ICML (2020)"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Kim, A., O\u0161ep, A., Leal-Taix\u00e9, L.: EagerMOT: 3D multi-object tracking via sensor fusion. arXiv preprint arXiv:2104.14682 (2021)","DOI":"10.1109\/ICRA48506.2021.9562072"},{"key":"17_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1007\/978-3-319-48881-3_54","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"M Kristan","year":"2016","unstructured":"Kristan, M., et al.: The visual object tracking VOT2016 challenge results. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 777\u2013823. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_54"},{"issue":"11","key":"17_CR33","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1109\/TPAMI.2016.2516982","volume":"38","author":"M Kristan","year":"2016","unstructured":"Kristan, M., Matas, J., Leonardis, A., Voj\u00ed\u0159, T., Pflugfelder, R., Fernandez, G., Nebehay, G., Porikli, F., \u010cehovin, L.: A novel performance evaluation methodology for single-target trackers. IEEE Trans. Pattern Anal. Mach. Intell. 38(11), 2137\u20132155 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"17_CR34","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1109\/TMM.2015.2455418","volume":"17","author":"KH Lee","year":"2015","unstructured":"Lee, K.H., Hwang, J.N.: On-road pedestrian tracking across multiple driving recorders. IEEE Trans. Multimedia 17(9), 1429\u20131438 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"17_CR35","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. arXiv preprint arXiv:1703.03130 (2017)"},{"issue":"3","key":"17_CR36","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TMM.2018.2863604","volume":"21","author":"Y Liu","year":"2018","unstructured":"Liu, Y., Jing, X.Y., Nie, J., Gao, H., Liu, J., Jiang, G.P.: Context-aware three-dimensional mean-shift with occlusion handling for robust object tracking in RGB-D videos. IEEE Trans. Multimedia 21(3), 664\u2013677 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"6","key":"17_CR38","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TCST.2016.2518618","volume":"24","author":"Z Liu","year":"2016","unstructured":"Liu, Z., Chen, W., Lu, J., Wang, H., Wang, J.: Formation control of mobile robots using distributed controller with sampled-data and communication delays. IEEE Trans. Control Syst. Technol. 24(6), 2125\u20132132 (2016)","journal-title":"IEEE Trans. Control Syst. Technol."},{"issue":"2","key":"17_CR39","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/MRA.2020.2977290","volume":"27","author":"Z Liu","year":"2020","unstructured":"Liu, Z., Suo, C., Liu, Y., Shen, Y., Qiao, Z., Wei, H., Zhou, S., Li, H., Liang, X., Wang, H., et al.: Deep learning-based localization and perception systems: approaches for autonomous cargo transportation vehicles in large-scale, semiclosed environments. IEEE Robot. Autom. Mag. 27(2), 139\u2013150 (2020)","journal-title":"IEEE Robot. Autom. Mag."},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Luber, M., Spinello, L., Arras, K.O.: People tracking in RGB-D data with on-line boosted target models. In: IROS (2011)","DOI":"10.1109\/IROS.2011.6095075"},{"key":"17_CR41","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00376"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"L\u00fcscher, C., et al.: RWTH ASR Systems for LibriSpeech: Hybrid vs attention-w\/o data augmentation. arXiv preprint arXiv:1905.03072 (2019)","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Voxel Transformer for 3D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Pan, X., Xia, Z., Song, S., Li, L.E., Huang, G.: 3D object detection with pointformer. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Pang, Z., Li, Z., Wang, N.: Model-free vehicle tracking and state estimation in point cloud sequences. In: IROS (2021)","DOI":"10.1109\/IROS51168.2021.9636202"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Pieropan, A., Bergstr\u00f6m, N., Ishikawa, M., Kjellstr\u00f6m, H.: Robust 3D tracking of unknown objects. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 2410\u20132417. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7139520"},{"key":"17_CR47","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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"17_CR48","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR (2017)"},{"key":"17_CR49","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Qi, H., Feng, C., Cao, Z., Zhao, F., Xiao, Y.: P2B: point-to-box network for 3D object tracking in point clouds. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00636"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Scheidegger, S., Benjaminsson, J., Rosenberg, E., Krishnan, A., Granstr\u00f6m, K.: Mono-camera 3D multi-object tracking using deep learning detections and PMBM filtering. In: IV (2018)","DOI":"10.1109\/IVS.2018.8500454"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Shan, J., Zhou, S., Fang, Z., Cui, Y.: PTT: point-track-Transformer module for 3D single object tracking in point clouds. In: IROS (2021)","DOI":"10.1109\/IROS51168.2021.9636821"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Shenoi, A., et al.: JRMOT: a real-time 3D multi-object tracker and a new large-scale dataset. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341635"},{"key":"17_CR54","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"17_CR55","doi-asserted-by":"crossref","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. (2020)","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"17_CR56","doi-asserted-by":"crossref","unstructured":"Spinello, L., Arras, K., Triebel, R., Siegwart, R.: A layered approach to people detection in 3D range data. In: AAAI (2010)","DOI":"10.1609\/aaai.v24i1.7728"},{"key":"17_CR57","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"17_CR58","unstructured":"Synnaeve, G., et al.: End-to-end ASR: from supervised to semi-supervised learning with modern architectures. arXiv preprint arXiv:1911.08460 (2019)"},{"key":"17_CR59","doi-asserted-by":"crossref","unstructured":"Tang, S., Andriluka, M., Andres, B., Schiele, B.: Multiple people tracking by lifted multicut and person re-identification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.394"},{"key":"17_CR60","doi-asserted-by":"crossref","unstructured":"Tao, R., Gavves, E., Smeulders, A.W.: Siamese instance search for tracking. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.158"},{"key":"17_CR61","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J., Vedaldi, A., Torr, P.H.: End-to-end representation learning for correlation filter based tracking. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.531"},{"key":"17_CR62","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"17_CR63","unstructured":"Wang, Q., Gao, J., Xing, J., Zhang, M., Hu, W.: DCFNet: discriminant correlation filters network for visual tracking. arXiv preprint arXiv:1704.04057 (2017)"},{"key":"17_CR64","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision Transformer: a versatile backbone for dense prediction without convolutions. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"17_CR65","doi-asserted-by":"crossref","unstructured":"Wang, Y., Weng, X., Kitani, K.: Joint detection and multi-object tracking with graph neural networks. arXiv preprint arXiv:2006.13164 (2020)","DOI":"10.1109\/ICRA48506.2021.9561110"},{"key":"17_CR66","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph cnn for learning on point clouds. arXiv preprint arXiv:1801.07829 (2018)","DOI":"10.1145\/3326362"},{"key":"17_CR67","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xie, Q., Lai, Y.K., Wu, J., Long, K., Wang, J.: MLVSNet: multi-level voting Siamese network for 3D visual tracking. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00309"},{"key":"17_CR68","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, J., Held, D., Kitani, K.: 3D multi-object tracking: a baseline and new evaluation metrics. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"17_CR69","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, Y., Man, Y., Kitani, K.M.: GNN3DMOT: graph neural network for 3D multi-object tracking with 2D\u20133D multi-feature learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00653"},{"key":"17_CR70","doi-asserted-by":"crossref","unstructured":"Weng, X., Yuan, Y., Kitani, K.: Joint 3D tracking and forecasting with graph neural network and diversity sampling. arXiv preprint arXiv:2003.07847 (2020)","DOI":"10.1109\/LRA.2021.3068925"},{"key":"17_CR71","doi-asserted-by":"crossref","unstructured":"Wu, H., Han, W., Wen, C., Li, X., Wang, C.: 3D multi-object tracking in point clouds based on prediction confidence-guided data association. IEEE Trans. Intell. Transp. Syst. (2021)","DOI":"10.1109\/TITS.2021.3055616"},{"key":"17_CR72","doi-asserted-by":"crossref","unstructured":"Xing, J., Ai, H., Lao, S.: Multiple human tracking based on multi-view upper-body detection and discriminative learning. In: ICPR (2010)","DOI":"10.1109\/ICPR.2010.420"},{"key":"17_CR73","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., Le, Q.V.: XLNet: Generalized autoregressive pretraining for language understanding. arXiv preprint arXiv:1906.08237 (2019)"},{"key":"17_CR74","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"17_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, M., Xing, J., Gao, J., Shi, X., Wang, Q., Hu, W.: Joint scale-spatial correlation tracking with adaptive rotation estimation. In: ICCV Workshops (2015)","DOI":"10.1109\/ICCVW.2015.81"},{"key":"17_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhou, H., Sun, S., Wang, Z., Shi, J., Loy, C.C.: Robust multi-modality multi-object tracking. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00245"},{"key":"17_CR77","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P., Koltun, V.: Point transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"17_CR78","doi-asserted-by":"crossref","unstructured":"Zheng, C., et al.: Box-aware feature enhancement for single object tracking on point clouds. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01295"},{"key":"17_CR79","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"17_CR80","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/978-3-030-01240-3_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Zhu","year":"2018","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware siamese networks for visual object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 103\u2013119. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_7"}],"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\/978-3-031-20086-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:55:57Z","timestamp":1668077757000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20086-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200854","9783031200861"],"references-count":80,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20086-1_17","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":"11 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)"}}]}}