{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T09:09:15Z","timestamp":1778576955820,"version":"3.51.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02363","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25474-25484","source":"Crossref","is-referenced-by-count":2,"title":["ForeSight: Multi-View Streaming Joint Object Detection and Trajectory Forecasting"],"prefix":"10.1109","author":[{"given":"Sandro","family":"Papais","sequence":"first","affiliation":[{"name":"University of Toronto"}]},{"given":"Letian","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Toronto"}]},{"given":"Brian","family":"Cheong","sequence":"additional","affiliation":[{"name":"University of Toronto"}]},{"given":"Steven L.","family":"Waslander","sequence":"additional","affiliation":[{"name":"University of Toronto"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref2","first-page":"947","article-title":"Intentnet: Learning to predict intention from raw sensor data","volume-title":"Conference on Robot Learning","author":"Casas","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_19"},{"key":"ref4","article-title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","author":"Chai","year":"2019","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793868"},{"key":"ref8","first-page":"203","article-title":"Multimodal trajectory prediction conditioned on lane-graph traversals","volume-title":"Conference on Robot Learning","author":"Deo","year":"2022"},{"key":"ref9","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160296"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_24"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3401172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref19","article-title":"Bevdet4d: Exploit temporal cues in multi-camera 3d object detection","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Bevpoolv2: A cutting-edge implementation of bevdet toward deployment","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982283"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01655"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref26","article-title":"Scenarionet: Open-source platform for large-scale traffic scenario simulation and modeling","volume":"36","author":"Li","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610204"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00900"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01157"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref35","article-title":"Sparse4d v2: Recurrent temporal fusion with sparse model","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref38","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00376"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01719"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611067"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref44","article-title":"Time will tell: New outlooks and a baseline for temporal multiview 3d object detection","volume-title":"The Eleventh International Conference on Learning Representations","author":"Park","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"ref48","first-page":"726","article-title":"Safety-enhanced autonomous driving using inter-pretable sensor fusion transformer","volume-title":"Conference on Robot Learning","author":"Shao","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01319"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0473"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812107"},{"key":"ref54","article-title":"Attention is all you need. In Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017","journal-title":"Curran Associates, Inc."},{"key":"ref55","article-title":"Hierarchical adaptable and transferable networks (hatn) for driving behavior prediction","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061350"},{"key":"ref57","article-title":"Transferable and adaptable driving behavior prediction","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.102"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3332608"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02106"},{"key":"ref62","first-page":"180","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00646"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827273"},{"key":"ref65","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610201"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160788"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01447"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01713"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445643.pdf?arnumber=11445643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:39:14Z","timestamp":1777531154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02363","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}