{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T02:16:58Z","timestamp":1781662618352,"version":"3.54.5"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/iv55152.2023.10186768","type":"proceedings-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T17:20:05Z","timestamp":1690478405000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["DeepSTEP - Deep Learning-Based Spatio-Temporal End-To-End Perception for Autonomous Vehicles"],"prefix":"10.1109","author":[{"given":"Sebastian","family":"Huch","sequence":"first","affiliation":[{"name":"Technical University of Munich,Institute of Automotive Technology, School of Engineering & Design,Garching,Germany,85748"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Sauerbeck","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Institute of Automotive Technology, School of Engineering & Design,Garching,Germany,85748"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Betz","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Professorship Autonomous Vehicle Systems,Garching,Germany,85748"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018409"},{"key":"ref12","article-title":"Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving","author":"wang","year":"2018"},{"key":"ref15","article-title":"Pointpillars: Fast encoders for object detection from point clouds","author":"lang","year":"2018"},{"key":"ref14","article-title":"Pointrcnn: 3d object proposal generation and detection from point cloud","author":"shi","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref16","article-title":"Pv-rcnn: Point-voxel feature set abstraction for 3d object detection","author":"shi","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref18","article-title":"An LSTM approach to temporal 3d object detection in lidar point clouds","author":"huang","year":"2020","journal-title":"CoRR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-22050-1_12"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00465"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3251650"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01157"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s21041039"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref43","article-title":"Hybridnets: End-to-end perception network","author":"vu","year":"2022"},{"key":"ref49","article-title":"Rst-modnet: Real-time spatio-temporal moving object detection for autonomous driving","author":"ramzy","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00520-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref4","article-title":"Frustum pointnets for 3d object detection from rgb-d data","author":"qi","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s20082180"},{"key":"ref6","article-title":"A deep learning-based radar and camera sensor fusion architecture for object detection","author":"nobis","year":"2020"},{"key":"ref5","article-title":"Multi-task multi-sensor fusion for 3d object detection","author":"liang","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00288"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"ref34","article-title":"Cloner: Camera-lidar fusion for occupancy grid-aided neural representations","author":"carlson","year":"2022"},{"key":"ref37","article-title":"Loc-nerf: Monte carlo localization using neural radiance fields","author":"maggio","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_7"},{"key":"ref31","article-title":"Delving into the devils of bird’s-eye-view perception: A review, evaluation and recipe","author":"li","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/s20154220"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/machines5010006"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"ref38","article-title":"Nerf-slam: Real-time dense monocular slam with neural radiance fields","author":"rosinol","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594450"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561663"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_23"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16180"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00190"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"ref21","article-title":"3d object detection for autonomous driving: A review and new outlooks","author":"mao","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref27","article-title":"M2bev: Multi-camera joint 3d detection and segmentation with unified birds-eye view representation","author":"xie","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561169"}],"event":{"name":"2023 IEEE Intelligent Vehicles Symposium (IV)","location":"Anchorage, AK, USA","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,7]]}},"container-title":["2023 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10186382\/10186383\/10186768.pdf?arnumber=10186768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T17:36:21Z","timestamp":1692034581000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10186768\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iv55152.2023.10186768","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}