{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:25:06Z","timestamp":1779294306451,"version":"3.51.4"},"publisher-location":"Cham","reference-count":79,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732539","type":"print"},{"value":"9783031732546","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73254-6_16","type":"book-chapter","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T07:20:18Z","timestamp":1732692018000},"page":"270-288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Boosting 3D Single Object Tracking with\u00a02D Matching Distillation and\u00a03D Pre-training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3847-7838","authenticated-orcid":false,"given":"Qiangqiang","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5298-748X","authenticated-orcid":false,"given":"Yan","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8198-1629","authenticated-orcid":false,"given":"Jia","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2886-2513","authenticated-orcid":false,"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Anthes, C., Garc\u00eda-Hern\u00e1ndez, R.J., Wiedemann, M., Kranzlm\u00fcller, D.: State of the art of virtual reality technology. In: 2016 IEEE Aerospace Conference, pp. 1\u201319. IEEE (2016)","DOI":"10.1109\/AERO.2016.7500674"},{"key":"16_CR2","unstructured":"Ben-Baruch, E., Karklinsky, M., Biton, Y., Ben-Cohen, A., Lawen, H., Zamir, N.: It\u2019s all in the head: representation knowledge distillation through classifier sharing (2022). arXiv:2201.06945"},{"key":"16_CR3","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":"16_CR4","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: ICCV, pp. 6182\u20136191 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"16_CR6","unstructured":"Chang, A.X., et\u00a0al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: CVPR, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"16_CR8","unstructured":"Cui, Y., Fang, Z., Shan, J., Gu, Z., Zhou, S.: 3D object tracking with transformer. arXiv preprint arXiv:2110.14921 (2021)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., Wu, G.: MixFormer: end-to-end tracking with iterative mixed attention. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ECO: efficient convolution operators for tracking. In: CVPR, pp. 21\u201326 (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"16_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2010)"},{"key":"16_CR12","unstructured":"Duong, C.N., Luu, K., Quach, K.G., Le, N.: ShrinkTeaNet: million-scale lightweight face recognition via shrinking teacher-student networks (2019). arXiv:1905.10620"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Fan, H., Lin, L., Yang, F.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: CVPR, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H.: Siamese cascaded region proposal networks for real-time visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7952\u20137961 (2019)","DOI":"10.1109\/CVPR.2019.00814"},{"issue":"4","key":"16_CR15","doi-asserted-by":"publisher","first-page":"4995","DOI":"10.1109\/JSEN.2020.3033034","volume":"21","author":"Z Fang","year":"2020","unstructured":"Fang, Z., Zhou, S., Cui, Y., Scherer, S.: 3D-SiamRPN: an end-to-end learning method for real-time 3D single object tracking using raw point cloud. IEEE Sens. J. 21(4), 4995\u20135011 (2020)","journal-title":"IEEE Sens. J."},{"issue":"12","key":"16_CR16","doi-asserted-by":"publisher","first-page":"8066","DOI":"10.1109\/LRA.2023.3325715","volume":"8","author":"S Feng","year":"2023","unstructured":"Feng, S., Liang, P., Gao, J., Cheng, E.: Multi-correlation siamese transformer network with dense connection for 3D single object tracking. IEEE Robot. Autom. Lett. 8(12), 8066\u20138073 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Galoogahi, H., Fagg, A., Lucey, S.: Learning background-aware correlation filters for visual tracking. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.129"},{"issue":"11","key":"16_CR18","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Giancola, S., Zarzar, J., Ghanem, B.: Leveraging shape completion for 3D siamese tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1359\u20131368 (2019)","DOI":"10.1109\/CVPR.2019.00145"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"16_CR21","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/978-3-031-20047-2_6","volume-title":"European Conference on Computer Vision 2022","author":"Z Guo","year":"2022","unstructured":"Guo, Z., Mao, Y., Zhou, W., Wang, M., Li, H.: CMT: context-matching-guided transformer for 3D tracking in point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 95\u2013111. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_6"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"3","key":"16_CR23","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2015","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 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR24","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). arXiv:1503.02531"},{"issue":"5","key":"16_CR25","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang, L., Zhao, X., Huang, K.: GOT-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR26","unstructured":"Hui, L., Wang, L., Cheng, M., Xie, J., Yang, J.: 3D siamese voxel-to-BEV tracker for sparse point clouds. In: Advances in Neural Information Processing Systems 34, pp. 28714\u201328727 (2021)"},{"key":"16_CR27","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-031-20086-1_17","volume-title":"European Conference on Computer Vision 2022","author":"L Hui","year":"2022","unstructured":"Hui, L., Wang, L., Tang, L., Lan, K., Xie, J., Yang, J.: 3D siamese transformer network for single object tracking on point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 293\u2013310. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_17"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Jin, X., Peng, B., Wu, Y., Liu, Y., Liu, J.: Knowledge distillation via route constrained optimization. In: IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00143"},{"key":"16_CR29","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"issue":"6","key":"16_CR30","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2021","unstructured":"Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909\u20134926 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"11","key":"16_CR31","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1109\/TPAMI.2016.2516982","volume":"38","author":"M Kristan","year":"2016","unstructured":"Kristan, M., et al.: 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."},{"key":"16_CR32","unstructured":"Kristan, M., Matas, J., Danelljan, M.: The first visual object tracking segmentation VOTS2023 challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Lan, K., Jiang, H., Xie, J.: Temporal-aware siamese tracker: integrate temporal context for 3D object tracking. In: Proceedings of the Asian Conference on Computer Vision, pp. 399\u2013414 (2022)","DOI":"10.1007\/978-3-031-26319-4_2"},{"key":"16_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/978-3-030-01231-1_21","volume-title":"Computer Vision \u2013 ECCV 2018","author":"SH Lee","year":"2018","unstructured":"Lee, S.H., Kim, D.H., Song, B.C.: Self-supervised knowledge distillation using singular value decomposition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 339\u2013354. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_21"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: SiamRPN++: evolution of siamese visual tracking with very deep networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4282\u20134291 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8971\u20138980 (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Rethinking feature-based knowledge distillation for face recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01930"},{"key":"16_CR38","unstructured":"Lin, L., Fan, H., Zhang, Z., Xu, Y., Ling, H.: SwinTrack: a simple and strong baseline for transformer tracking, pp. 16743\u201316754 (2022)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liang, Y., Wu, Q., Zhang, L., Wang, H.: A new framework for multiple deep correlation filters based object tracking. In: ICASSP (2022)","DOI":"10.1109\/ICASSP43922.2022.9747821"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Muller, M., Bibi, A., Giancola, S.: TrackingNet: a large-scale dataset and benchmark for object tracking in the wild. In: ECCV, pp. 300\u2013317 (2018)","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Osep, A., Mehner, W., Mathias, M., Leibe, B.: Combined image-and world-space tracking in traffic scenes. In: IEEE International Conference on Robotics and Automation, pp. 1988\u20131995. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989230"},{"key":"16_CR42","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1007\/978-3-031-20086-1_35","volume-title":"European Conference on Computer Vision 2022","author":"Y Pang","year":"2022","unstructured":"Pang, Y., Wang, W., Tay, F.E., Liu, W., Tian, Y., Yuan, L.: Masked autoencoders for point cloud self-supervised learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 604\u2013621. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_35"},{"key":"16_CR43","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":"16_CR44","unstructured":"Peng, B., et al.: Self-supervised knowledge distillation using singular value decomposition. In: IEEE\/CVF International Conference on Computer Vision (2019)"},{"key":"16_CR45","unstructured":"Peng, B., et al.: ShrinkTeaNet: million-scale lightweight face recognition via shrinking teacher-student networks. In: IEEE\/CVF International Conference on Computer Vision (2019)"},{"key":"16_CR46","unstructured":"Qi, C., Su, H., Mo, K., Guibas, L.: PointNet: deep learning on point sets for 3D classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)"},{"key":"16_CR47","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6329\u20136338 (2020)","DOI":"10.1109\/CVPR42600.2020.00636"},{"key":"16_CR48","unstructured":"Qi, Z., et al.: Contrast with reconstruct: contrastive 3D representation learning guided by generative pretraining (2023)"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Ran, T., Gavves, E., Smeulders, A.W.: Siamese instance search for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1420\u20131429 (2016)","DOI":"10.1109\/CVPR.2016.158"},{"key":"16_CR50","unstructured":"Romero, A., Ballas, N.: FitNets: hints for thin deep nets (2014). arXiv:1412.6550"},{"key":"16_CR51","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. arXiv preprint arXiv:2108.06455 (2021)","DOI":"10.1109\/IROS51168.2021.9636821"},{"key":"16_CR52","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":"16_CR53","unstructured":"Tao, F., Wang, M.: Response-based distillation for incremental object detection (2021). arXiv:2110.13471"},{"key":"16_CR54","unstructured":"Tao, F., Wang, M., Yuan, H.: Overcoming catastrophic forgetting in incremental object detection via elastic response distillation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Wang, N., Song, Y., Ma, C.: Unsupervised deep tracking. In: CVPR, pp. 3708\u20131317 (2019)","DOI":"10.1109\/CVPR.2019.00140"},{"key":"16_CR56","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3101\u20133110 (2021)","DOI":"10.1109\/ICCV48922.2021.00309"},{"key":"16_CR57","unstructured":"Wang, Z., Yu, X., Rao, Y., Zhou, J., Lu, J.: P2P: tuning pre-trained image models for point cloud analysis with point-to-pixel prompting. In: Advances in Neural Information Processing Systems 35, pp. 14388\u201314402 (2022)"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Wu, Q., Chan, A.: Meta-graph adaptation for visual object tracking. In: ICME (2021)","DOI":"10.1109\/ICME51207.2021.9428441"},{"key":"16_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/978-3-030-20873-8_8","volume-title":"Computer Vision \u2013 ACCV 2018","author":"Q Wu","year":"2019","unstructured":"Wu, Q., Yan, Y., Liang, Y., Liu, Y., Wang, H.: DSNet: deep and shallow feature learning for efficient visual tracking. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11365, pp. 119\u2013134. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20873-8_8"},{"key":"16_CR60","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wan, J., Chan, A.B.: Progressive unsupervised learning for visual object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2993\u20133002 (2021)","DOI":"10.1109\/CVPR46437.2021.00301"},{"key":"16_CR61","doi-asserted-by":"crossref","unstructured":"Wu, Q., Yang, T., Liu, Z., Wu, B., Shan, Y., Chan, A.B.: DropMAE: masked autoencoders with spatial-attention dropout for tracking tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14561\u201314571 (2023)","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"16_CR62","doi-asserted-by":"crossref","unstructured":"Wu, Q., Yang, T., Wu, W., Chan, A.B.: Scalable video object segmentation with simplified framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01276"},{"issue":"1","key":"16_CR63","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1109\/LRA.2022.3221313","volume":"8","author":"Q Wu","year":"2022","unstructured":"Wu, Q., Sun, C., Wang, J.: Multi-level structure-enhanced network for 3D single object tracking in sparse point clouds. IEEE Robot. Autom. Lett. 8(1), 9\u201316 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"16_CR64","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR, pp. 2411\u20132418 (2013)","DOI":"10.1109\/CVPR.2013.312"},{"key":"16_CR65","doi-asserted-by":"crossref","unstructured":"Xia, Y., et al.: CASSPR: cross attention single scan place recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8461\u20138472 (2023)","DOI":"10.1109\/ICCV51070.2023.00777"},{"key":"16_CR66","doi-asserted-by":"crossref","unstructured":"Xia, Y., Shi, L., Ding, Z., Henriques, J.F., Cremers, D.: Text2Loc: 3D point cloud localization from natural language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14958\u201314967 (2024)","DOI":"10.1109\/CVPR52733.2024.01417"},{"issue":"5","key":"16_CR67","doi-asserted-by":"publisher","first-page":"5543","DOI":"10.1109\/TITS.2023.3243470","volume":"24","author":"Y Xia","year":"2023","unstructured":"Xia, Y., Wu, Q., Li, W., Chan, A.B., Stilla, U.: A lightweight and detector-free 3D single object tracker on point clouds. IEEE Trans. Intell. Transp. Syst. 24(5), 5543\u20135554 (2023)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"16_CR68","doi-asserted-by":"crossref","unstructured":"Xu, T.X., Guo, Y.C., Lai, Y.K., Zhang, S.H.: CXTrack: improving 3D point cloud tracking with contextual information. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1084\u20131093 (2023)","DOI":"10.1109\/CVPR52729.2023.00111"},{"key":"16_CR69","doi-asserted-by":"crossref","unstructured":"Xu, T.X., Guo, Y.C., Lai, Y.K., Zhang, S.H.: MBPTrack: improving 3D point cloud tracking with memory networks and box priors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9911\u20139920 (2023)","DOI":"10.1109\/ICCV51070.2023.00909"},{"key":"16_CR70","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: ICCV, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"Yang, T., Chan, A.B.: Learning dynamic memory networks for object tracking. In: Proceedings of the European Conference on Computer Vision, pp. 152\u2013167 (2018)","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"16_CR72","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/978-3-031-20047-2_20","volume-title":"European Conference on Computer Vision 2022","author":"B Ye","year":"2022","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., Chen, X.: Joint feature learning and relation modeling for tracking: a one-stream framework. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 341\u2013357. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_20"},{"key":"16_CR73","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"16_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, L., Gonzalez-Garcia, A., Van De Weijer, J., Danelljan, M., Khan, F.S.: Learning the model update for siamese trackers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4010\u20134019 (2019)","DOI":"10.1109\/ICCV.2019.00411"},{"key":"16_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H.: Deeper and wider siamese networks for real-time visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4591\u20134600 (2019)","DOI":"10.1109\/CVPR.2019.00472"},{"key":"16_CR76","doi-asserted-by":"crossref","unstructured":"Zheng, C., et al.: Box-aware feature enhancement for single object tracking on point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13199\u201313208 (2021)","DOI":"10.1109\/ICCV48922.2021.01295"},{"key":"16_CR77","doi-asserted-by":"crossref","unstructured":"Zheng, C., et al.: Beyond 3D siamese tracking: a motion-centric paradigm for 3D single object tracking in point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8111\u20138120 (2022)","DOI":"10.1109\/CVPR52688.2022.00794"},{"key":"16_CR78","doi-asserted-by":"crossref","unstructured":"Zhou, C., et al.: PTTR: relational 3D point cloud object tracking with transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8531\u20138540 (2022)","DOI":"10.1109\/CVPR52688.2022.00834"},{"key":"16_CR79","unstructured":"Zhou, H., Song, L., Chen, J., Zhou, Y., Wang, G.: Rethinking soft labels for knowledge distillation: a bias-variance tradeoff perspective (2021). arXiv:2102.00650"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73254-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T08:10:34Z","timestamp":1732695034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73254-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"ISBN":["9783031732539","9783031732546"],"references-count":79,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73254-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"28 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}