{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:23:09Z","timestamp":1777569789182,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730030","type":"print"},{"value":"9783031730047","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73004-7_24","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:05:45Z","timestamp":1730394345000},"page":"412-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Accelerating Online Mapping and\u00a0Behavior Prediction via\u00a0Direct BEV Feature Attention"],"prefix":"10.1007","author":[{"given":"Xunjiang","family":"Gu","sequence":"first","affiliation":[]},{"given":"Guanyu","family":"Song","sequence":"additional","affiliation":[]},{"given":"Igor","family":"Gilitschenski","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Pavone","sequence":"additional","affiliation":[]},{"given":"Boris","family":"Ivanovic","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: NuScenes: multimodal dataset for autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Can, Y.B., Liniger, A., Paudel, D.P., Gool, L.V.: Structured bird\u2019s-eye-view traffic scene understanding from onboard images. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01537"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Chang, M.F., et al.: Argoverse: 3D tracking and forecasting with rich maps. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00895"},{"key":"24_CR4","unstructured":"Deo, N., Wolff, E.M., Beijbom, O.: Multimodal trajectory prediction conditioned on lane-graph traversals. In: Conference on Robot Learning (2021)"},{"key":"24_CR5","unstructured":"Dong, H., et al.: SuperFusion: multilevel LiDAR-camera fusion for long-range HD map generation. arXiv preprint arXiv:2211.15656 (2022)"},{"key":"24_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Ettinger, S., et al.: Large scale interactive motion forecasting for autonomous driving: the WAYMO open motion dataset. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: VectorNet: encoding HD maps and agent dynamics from vectorized representation. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Gilles, T., Sabatini, S., Tsishkou, D., Stanciulescu, B., Moutarde, F.: HOME: heatmap output for future motion estimation. In: Proceedings of the IEEE International Conference on Intelligent Transportation Systems (2021)","DOI":"10.1109\/ITSC48978.2021.9564944"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Gilles, T., Sabatini, S., Tsishkou, D., Stanciulescu, B., Moutarde, F.: GOHOME: graph-oriented heatmap output for future motion estimation. In: Proceedings of the IEEE Conference on Robotics and Automation (2022)","DOI":"10.1109\/ICRA46639.2022.9812253"},{"key":"24_CR11","unstructured":"Gilles, T., Sabatini, S., Tsishkou, D., Stanciulescu, B., Moutarde, F.: THOMAS: trajectory heatmap output with learned multi-agent sampling. In: International Conference on Learning Representations (2022)"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Gu, J., Sun, C., Zhao, H.: DenseTNT: end-to-end trajectory prediction from dense goal sets. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Gu, X., Song, G., Gilitschenski, I., Pavone, M., Ivanovic, B.: Producing and leveraging online map uncertainty in trajectory prediction. In: IEEE Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01376"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Planning-oriented autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Ivanovic, B., Harrison, J., Pavone, M.: Expanding the deployment envelope of behavior prediction via adaptive meta-learning. In: Proceedings of the IEEE Conference on Robotics and Automation (2023). https:\/\/arxiv.org\/abs\/2209.11820","DOI":"10.1109\/ICRA48891.2023.10161155"},{"key":"24_CR17","unstructured":"Ivanovic, B., Song, G., Gilitschenski, I., Pavone, M.: Trajdata: a unified interface to multiple human trajectory datasets. In: Conference on Neural Information Processing Systems Datasets and Benchmarks Track. New Orleans, USA, December 2023. https:\/\/arxiv.org\/abs\/2307.13924"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, B., et al: VAD: vectorized scene representation for efficient autonomous driving. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Li, Q., Wang, Y., Wang, Y., Zhao, H.: HDMapNet: an online HD map construction and evaluation framework. In: Proceedings of the IEEE Conference on Robotics and Automation (2022)","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"24_CR20","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"24_CR21","doi-asserted-by":"publisher","unstructured":"Liang, M., et al.: Learning lane graph representations for motion forecasting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. LNCS, vol. 12347. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_32","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"24_CR22","unstructured":"Liao, B., et al.: MapTR: structured modeling and learning for online vectorized HD map construction. In: International Conference on Learning Representations (2023)"},{"key":"24_CR23","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":"24_CR24","unstructured":"Liu, Y., Yuantian, Y., Wang, Y., Wang, Y., Zhao, H.: VectorMapNet: end-to-end vectorized HD map learning. In: International Conference on Machine Learning. PMLR (2023)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, J., Fang, L., Jiang, Q., Zhou, B.: Multimodal motion prediction with stacked transformers. In: IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00749"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: Proceedings of the IEEE Conference on Robotics and Automation (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Phan-Minh, T., Grigore, E.C., Boulton, F.A., Beijbom, O., Wolff, E.M.: CoverNet: multimodal behavior prediction using trajectory sets. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01408"},{"key":"24_CR28","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":"24_CR29","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: IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01270"},{"issue":"8","key":"24_CR30","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1177\/0278364920917446","volume":"39","author":"A Rudenko","year":"2020","unstructured":"Rudenko, A., Palmieri, L., Herman, M., Kitani, K.M., Gavrila, D.M., Arras, K.O.: Human motion trajectory prediction: a survey. Int. J. Robot. Res. 39(8), 895\u2013935 (2020)","journal-title":"Int. J. Robot. Res."},{"key":"24_CR31","doi-asserted-by":"publisher","unstructured":"Salzmann, T., Ivanovic, B., Chakravarty, P., Pavone, M.: Trajectron++: dynamically-feasible trajectory forecasting with heterogeneous data. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 683\u2013700. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_40, https:\/\/arxiv.org\/abs\/2001.03093","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"24_CR32","unstructured":"Shin, J., Rameau, F., Jeong, H., Kum, D.: InstaGraM: instance-level graph modeling for vectorized HD map learning. arXiv preprint arXiv:2301.04470 (2023)"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Tong, W., et al.: Scene as occupancy. In: IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"24_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Conference on Neural Information Processing Systems (2017)"},{"key":"24_CR35","unstructured":"Wilson, B., et al.: Argoverse 2: next generation datasets for self-driving perception and forecasting. In: Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2021)"},{"key":"24_CR36","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":"24_CR37","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: IEEE Winter Conference on Applications of Computer Vision (2024)","DOI":"10.1109\/WACV57701.2024.00719"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Weng, X., Ou, Y., Kitani, K.M.: AgentFormer: agent-aware transformers for socio-temporal multi-agent forecasting. In: IEEE International Conference on Computer Vision, pp. 9813\u20139823 (2021)","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"24_CR39","unstructured":"Zhao, H., et al.: TNT: target-driveN trajectory prediction. In: Conference on Robot Learning (2020)"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Ye, L., Wang, J., Wu, K., Lu, K.: HiVT: hierarchical vector transformer for multi-agent motion prediction. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00862"}],"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\/978-3-031-73004-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:09:45Z","timestamp":1730394585000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73004-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031730030","9783031730047"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73004-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}