{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T18:09:09Z","timestamp":1785694149946,"version":"3.56.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726576","type":"print"},{"value":"9783031726583","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T00:00:00Z","timestamp":1727827200000},"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\/978-3-031-72658-3_6","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T03:32:37Z","timestamp":1727839957000},"page":"90-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["MapTracker: Tracking with\u00a0Strided Memory Fusion for\u00a0Consistent Vector HD Mapping"],"prefix":"10.1007","author":[{"given":"Jiacheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuefan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasutaka","family":"Furukawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,2]]},"reference":[{"key":"6_CR1","unstructured":"Online hd map construction challenge for autonomous driving on cvpr 2023 workshop on end-to-end autonomous driving. https:\/\/github.com\/Tsinghua-MARS-Lab\/Online-HD-Map-Construction-CVPR2023 (2023)"},{"key":"6_CR2","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":"6_CR3","doi-asserted-by":"crossref","unstructured":"Cai, J., et al.: Memot: multi-object tracking with memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8090\u20138100 (2022)","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"6_CR4","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":"6_CR5","unstructured":"Chen, J., Deng, R., Furukawa, Y.: Polydiffuse: Polygonal shape reconstruction via guided set diffusion models. arXiv preprint arXiv:2306.01461 (2023)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Ding, W., Qiao, L., Qiu, X., Zhang, C.: Pivotnet: vectorized pivot learning for end-to-end hd map construction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3672\u20133682 (2023)","DOI":"10.1109\/ICCV51070.2023.00340"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Gao, R., Wang, L.: Memotr: long-term memory-augmented transformer for multi-object tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9901\u20139910 (2023)","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: Vip3d: end-to-end visual trajectory prediction via 3d agent queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5496\u20135506 (2023)","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Han, C., et al.: Exploring recurrent long-term temporal fusion for multi-view 3d perception. arXiv preprint arXiv:2303.05970 (2023)","DOI":"10.1109\/LRA.2024.3401172"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR12","unstructured":"Huang, J., Huang, G.: Bevdet4d: Exploit temporal cues in multi-camera 3d object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Li, E., Casas, S., Urtasun, R.: Memoryseg: online lidar semantic segmentation with a latent memory. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00075"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: Dn-detr: accelerate detr training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"6_CR15","unstructured":"Li, H., et\u00a0al.: Delving into the devils of bird\u2019s-eye-view perception: A review, evaluation and recipe. IEEE Trans. Pattern Analy. Mach. Intell. (2023)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Li, Q., Wang, Y., Wang, Y., Zhao, H.: Hdmapnet: an online hd map construction and evaluation framework. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 4628\u20134634. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"6_CR17","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: European conference on computer vision. pp. 1\u201318. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"6_CR18","unstructured":"Liao, B., et al.: Maptr: Structured modeling and learning for online vectorized hd map construction. arXiv preprint arXiv:2208.14437 (2022)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Liao, B., et al.: Maptrv2: An end-to-end framework for online vectorized hd map construction. arXiv preprint arXiv:2308.05736 (2023)","DOI":"10.1007\/s11263-024-02235-z"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Lilja, A., Fu, J., Stenborg, E., Hammarstrand, L.: Localization is all you evaluate: Data leakage in online mapping datasets and how to fix it. arXiv preprint arXiv:2312.06420 (2023)","DOI":"10.1109\/CVPR52733.2024.02091"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"6_CR22","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4d v2: Recurrent temporal fusion with sparse model. arXiv preprint arXiv:2305.14018 (2023)"},{"key":"6_CR23","unstructured":"Lin, X., Pei, Z., Lin, T., Huang, L., Su, Z.: Sparse4d v3: Advancing end-to-end 3d detection and tracking. arXiv preprint arXiv:2311.11722 (2023)"},{"key":"6_CR24","unstructured":"Liu, Y., Yuan, T., Wang, Y., Wang, Y., Zhao, H.: Vectormapnet: end-to-end vectorized hd map learning. In: International Conference on Machine Learning, pp. 22352\u201322369. PMLR (2023)"},{"key":"6_CR25","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam. ArXiv abs\/ arXiv: 1711.05101 (2017)"},{"key":"6_CR26","unstructured":"Ma, Y., et al.: Vision-centric bev perception: A survey. arXiv preprint arXiv:2208.02797 (2022)"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"6_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Qiao, L., Ding, W., Qiu, X., Zhang, C.: End-to-end vectorized hd-map construction with piecewise bezier curve. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13218\u201313228 (2023)","DOI":"10.1109\/CVPR52729.2023.01270"},{"key":"6_CR31","unstructured":"Qiao, L., et al.: Machmap: End-to-end vectorized solution for compact hd-map construction. arXiv preprint arXiv:2306.10301 (2023)"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Shan, T., Englot, B.: Lego-loam: lightweight and ground-optimized lidar odometry and mapping on variable terrain. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4758\u20134765. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594299"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Shan, T., Englot, B., Meyers, D., Wang, W., Ratti, C., Rus, D.: Lio-sam: tightly-coupled lidar inertial odometry via smoothing and mapping. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5135\u20135142. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341176"},{"key":"6_CR34","unstructured":"Sun, P., et al.: Transtrack: Multiple object tracking with transformer. arXiv preprint arXiv:2012.15460 (2020)"},{"key":"6_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"6_CR36","unstructured":"Wang, S., et al.: Stream query denoising for vectorized hd map construction. arXiv preprint arXiv:2401.09112 (2024)"},{"key":"6_CR37","unstructured":"Wilson, B., et\u00a0al.: Argoverse 2: Next generation datasets for self-driving perception and forecasting. arXiv preprint arXiv:2301.00493 (2023)"},{"key":"6_CR38","unstructured":"Xu, Z., Wong, K.K., Zhao, H.: Insightmapper: A closer look at inner-instance information for vectorized high-definition mapping. arXiv preprint arXiv:2308.08543 (2023)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: Bevformer v2: Adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. (CSUR) 38(4), 13\u2013es (2006)","DOI":"10.1145\/1177352.1177355"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Yuan, T., Liu, Y., Wang, Y., Wang, Y., Zhao, H.: Streammapnet: streaming mapping network for vectorized online hd map construction. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7356\u20137365 (2024)","DOI":"10.1109\/WACV57701.2024.00719"},{"key":"6_CR42","doi-asserted-by":"publisher","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., Wei, Y.: Motr: End-to-end multiple-object tracking with transformer. In: European Conference on Computer Vision, pp. 659\u2013675. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_38","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"6_CR43","unstructured":"Zhang, G., et al.: Online map vectorization for autonomous driving: A rasterization perspective. arXiv preprint arXiv:2306.10502 (2023)"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, J., Singh, S.: Loam: Lidar odometry and mapping in real-time. In: Robotics: Science and Systems (2014)","DOI":"10.15607\/RSS.2014.X.007"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, T., Zhang, X.: Motrv2: bootstrapping end-to-end multi-object tracking by pretrained object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22056\u201322065 (2023)","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, Y., Ding, X., Jin, F., Yue, X.: Online vectorized hd map construction using geometry. arXiv preprint arXiv:2312.03341 (2023)","DOI":"10.1007\/978-3-031-72967-6_5"},{"key":"6_CR47","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)"}],"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\/978-3-031-72658-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T23:53:07Z","timestamp":1732837987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72658-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,2]]},"ISBN":["9783031726576","9783031726583"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72658-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,2]]},"assertion":[{"value":"2 October 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"}}]}}