{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:11:22Z","timestamp":1788851482359,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370945","type":"print"},{"value":"9783032370952","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37095-2_15","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:05:12Z","timestamp":1788851112000},"page":"263-278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BeyondSight: Object Permanence for\u00a0End-to-End Autonomous Driving"],"prefix":"10.1007","author":[{"given":"Sandro","family":"Papais","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Letian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mudit","family":"Jain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Behnaz","family":"Rezaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven L.","family":"Waslander","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"15_CR1","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":"15_CR2","doi-asserted-by":"crossref","unstructured":"Cheong, B., Wang, L., Papais, S., Waslander, S.L.: Scatr: mitigating new instance suppression in lidar-based tracking-by-attention via second chance assignment and track query dropout. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3330\u20133339 (2026)","DOI":"10.1109\/WACV61042.2026.00325"},{"key":"15_CR3","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":"15_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/978-3-031-19839-7_31","volume-title":"Computer Vision \u2013 ECCV 2022","author":"S Hu","year":"2022","unstructured":"Hu, S., Chen, L., Wu, P., Li, H., Yan, J., Tao, D.: St-p3: end-to-end vision-based autonomous driving via spatial-temporal feature learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13698, pp. 533\u2013549. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_31"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Hu, Y., et\u00a0al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Jia, X., Gao, Y., Chen, L., Yan, J., Liu, P.L., Li, H.: DriveAdapter: breaking the coupling barrier of perception and planning in end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00731"},{"key":"15_CR7","unstructured":"Jia, X., You, J., Zhang, Z., Yan, J.: Drivetransformer: unified transformer for scalable end-to-end autonomous driving. arXiv preprint arXiv:2503.07656 (2025)"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Jiang, B., et al.: VAD: vectorized scene representation for efficient autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138350 (2023)","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"15_CR9","unstructured":"Li, P., Cui, D.: Navigation-guided sparse scene representation for end-to-end autonomous driving. arXiv preprint arXiv:2409.18341 (2024)"},{"key":"15_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Papais, S., Ren, R., Waslander, S.: Swtrack: multiple hypothesis sliding window 3D multi-object tracking. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 4939\u20134945. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10611067"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Papais, S., Wang, L., Cheong, B., Waslander, S.L.: Foresight: multi-view streaming joint object detection and trajectory forecasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 25474\u201325484 (2025)","DOI":"10.1109\/ICCV51701.2025.02363"},{"key":"15_CR13","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":"15_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58517-4_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Shamsian","year":"2020","unstructured":"Shamsian, A., Kleinfeld, O., Globerson, A., Chechik, G.: Learning object permanence from video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 35\u201350. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_3"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Shao, H., Wang, L., Chen, R., Waslander, S.L., Li, H., Liu, Y.: Reasonnet: end-to-end driving with temporal and global reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13723\u201313733 (2023)","DOI":"10.1109\/CVPR52729.2023.01319"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Song, Z., et al.: Don\u2019t shake the wheel: Momentum-aware planning in end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22432\u201322441 (2025)","DOI":"10.1109\/CVPR52734.2025.02089"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Sun, W., Lin, X., Shi, Y., Zhang, C., Wu, H., Zheng, S.: Sparsedrive: end-to-end autonomous driving via sparse scene representation. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 8795\u20138801. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11128800"},{"key":"15_CR18","unstructured":"Tokmakov, P., Jabri, A., Li, J., Gaidon, A.: Object permanence emerges in a random walk along memory. In: International Conference on Machine Learning, pp. 21506\u201321519. PMLR (2022)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Li, J., Burgard, W., Gaidon, A.: Learning to track with object permanence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10860\u201310869 (2021)","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Van Hoorick, B., Tokmakov, P., Stent, S., Li, J., Vondrick, C.: Tracking through containers and occluders in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13802\u201313812 (2023)","DOI":"10.1109\/CVPR52729.2023.01326"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Wang, L., et\u00a0al.: Trends in motion prediction toward deployable and generalizable autonomy: a revisit and perspectives. Found. Trends\u00ae Robot. 13(1-2), 1\u2013269 (2026)","DOI":"10.1108\/FTROB-05-2025-0079"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, Y., Wang, T., Li, Y., Zhang, X.: Exploring object-centric temporal modeling for efficient multi-view 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3621\u20133631 (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Xue, Z., Guo, M., Fan, H., Zhang, S., Zhang, Z.: Corrbev: multi-view 3D object detection by correlation learning with multi-modal prototypes. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 27413\u201327423 (2025)","DOI":"10.1109\/CVPR52734.2025.02553"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, B., Song, N., Jin, X., Zhang, L.: Bridging past and future: end-to-end autonomous driving with historical prediction and planning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6854\u20136863 (2025)","DOI":"10.1109\/CVPR52734.2025.00643"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37095-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:05:17Z","timestamp":1788851117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37095-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370945","9783032370952"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37095-2_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}