{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T05:39:50Z","timestamp":1780983590247,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CPS 1931867"],"award-info":[{"award-number":["CPS 1931867"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"gift from Qualcomm Technologies, Inc."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tits.2024.3433591","type":"journal-article","created":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T18:03:47Z","timestamp":1722881027000},"page":"18537-18546","source":"Crossref","is-referenced-by-count":18,"title":["BEV-TP: End-to-End Visual Perception and Trajectory Prediction for Autonomous Driving"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0586-3783","authenticated-orcid":false,"given":"Bo","family":"Lang","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1007-1000","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research, Qualcomm Technologies, Inc., San Diego, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0117-0621","authenticated-orcid":false,"given":"Mooi Choo","family":"Chuah","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01157"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00465"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01140"},{"key":"ref4","first-page":"947","article-title":"IntentNet: Learning to predict intention from raw sensor data","volume-title":"Proc. Conf. Robot Learn.","author":"Casas"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_29"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref11","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Wang"},{"key":"ref12","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref15","article-title":"SimpleTrack: Understanding and rethinking 3D multi-object tracking","author":"Pang","year":"2021","journal-title":"arXiv:2111.09621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00500"},{"key":"ref21","article-title":"GRIP++: Enhanced graph-based interaction-aware trajectory prediction for autonomous driving","author":"Li","year":"2019","journal-title":"arXiv:1907.07792"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00865"},{"key":"ref23","article-title":"Stochastic prediction of multi-agent interactions from partial observations","author":"Sun","year":"2019","journal-title":"arXiv:1902.09641"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"ref25","first-page":"895","article-title":"TNT: Target-driven trajectory prediction","volume-title":"Proc. Conf. Robot Learn.","author":"Zhao"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"ref27","article-title":"Stepwise goal-driven networks for trajectory prediction","author":"Wang","year":"2021","journal-title":"arXiv:2103.14107"},{"key":"ref28","first-page":"910","article-title":"Towards capturing the temporal dynamics for trajectory prediction: A coarse-to-fine approach","volume-title":"Proc. Conf. Robot Learn.","author":"Jia"},{"key":"ref29","first-page":"203","article-title":"Multimodal trajectory prediction conditioned on lane-graph traversals","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Deo"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298301"},{"key":"ref31","first-page":"1434","article-title":"Multi-agent trajectory prediction by combining egocentric and allocentric views","volume-title":"Proc. Conf. Robot Learn.","author":"Jia"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00376"},{"key":"ref33","article-title":"ViP3D: End-to-end visual trajectory prediction via 3D agent queries","author":"Gu","year":"2022","journal-title":"arXiv:2208.01582"},{"key":"ref34","article-title":"Perceive, interact, predict: Learning dynamic and static clues for end-to-end motion prediction","author":"Jiang","year":"2022","journal-title":"arXiv:2212.02181"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref36","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref42","article-title":"Tracking the trackers: An analysis of the state of the art in multiple object tracking","author":"Leal-Taix\u00e9","year":"2017","journal-title":"arXiv:1704.02781"},{"key":"ref43","first-page":"1","article-title":"The CLEAR 2006 evaluation","volume-title":"Proc. Int. Eval. Workshop Classification Events, Activities Relationships","author":"Stiefelhagen"},{"key":"ref44","article-title":"3D multi-object tracking: A baseline and new evaluation metrics","author":"Weng","year":"2019","journal-title":"arXiv:1907.03961"},{"key":"ref45","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref46","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019","journal-title":"arXiv:1908.09492"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"ref51","article-title":"DEFT: Detection embeddings for tracking","author":"Chaabane","year":"2021","journal-title":"arXiv:2102.02267"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00683"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6979\/10742224\/10623523-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10742224\/10623523.pdf?arnumber=10623523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:47:44Z","timestamp":1733885264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10623523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":53,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3433591","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}