{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:50:15Z","timestamp":1767084615477,"version":"3.40.2"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"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":[[2024,9,24]]},"DOI":"10.1109\/itsc58415.2024.10920077","type":"proceedings-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T19:00:11Z","timestamp":1742583611000},"page":"3982-3988","source":"Crossref","is-referenced-by-count":1,"title":["Improved Single Camera BEV Perception Using Multi-Camera Training"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Busch","sequence":"first","affiliation":[{"name":"University of Wuppertal,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ido","family":"Freeman","sequence":"additional","affiliation":[{"name":"APTIV"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Meyes","sequence":"additional","affiliation":[{"name":"University of Wuppertal,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"Meisen","sequence":"additional","affiliation":[{"name":"University of Wuppertal,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"BEVFormer: Learning Bird\u2019s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers","volume-title":"Computer Vision ECCV 2022","author":"Li","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01710"},{"issue":"3","key":"ref3","doi-asserted-by":"crossref","first-page":"4867","DOI":"10.1109\/LRA.2020.3004325","article-title":"Cross-view Semantic Segmentation for Sensing Surroundings","volume":"5","author":"Pan","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"key":"ref4","first-page":"1042","article-title":"PolarFormer: Multi-Camera 3D Object Detection with Polar Transformer","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Jiang"},{"key":"ref5","first-page":"6896","article-title":"FB-BEV: BEV Representation from Forward-Backward View Transformations","volume-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Li"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2759","DOI":"10.1109\/ICRA48891.2023.10160831","article-title":"Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?","volume-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","author":"Harley","year":"2023"},{"issue":"1","key":"ref7","doi-asserted-by":"crossref","first-page":"2489","DOI":"10.1109\/TIV.2023.3319430","article-title":"BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for Multi-View BEV 3D Object Detection","volume":"9","author":"Li","year":"2024","journal-title":"IEEE Transactions on Intelligent Vehicle"},{"key":"ref8","first-page":"8437","article-title":"Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang"},{"issue":"4","key":"ref9","doi-asserted-by":"crossref","first-page":"2151","DOI":"10.1109\/TPAMI.2023.3333838","article-title":"Delving Into the Devils of Birds-Eye-View Perception: A Review, Evaluation and Recipe","volume":"46","author":"Li","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01164"},{"key":"ref11","first-page":"11135","article-title":"Predicting Semantic Map Representations From Images Using Pyramid Occupancy Networks","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Roddick"},{"key":"ref12","article-title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","volume-title":"Proceedings of the 40 th International Conference on Machine Learning","volume":"40","author":"Baevski"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1503","DOI":"10.1109\/ITSC48978.2021.9564667","article-title":"BEV-MODNet: Monocular Camera based Bird\u2019s Eye View Moving Object Detection for Autonomous Driving","volume-title":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","author":"Rashed","year":"2021"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/978-3-031-19769-7_8","article-title":"Lidar Point Cloud Guided Monocular 3D Object Detection","volume-title":"Computer Vision ECCV 2022","volume":"13661","author":"Peng","year":"2022"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"9200","DOI":"10.1109\/ICRA46639.2022.9811901","article-title":"Translating Images into Maps","volume-title":"2022 International Conference on Robotics and Automation (ICRA)","author":"Saha","year":"2022"},{"key":"ref16","article-title":"Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception","author":"Han","year":"2023","journal-title":"arXiv"},{"key":"ref17","article-title":"Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection","volume-title":"The Eleventh International Conference on Learning Representations","volume":"11","author":"Park","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00302"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/978-3-031-19812-0_31","article-title":"PETR: Position Embedding Transformation for Multi-view 3D Object Detection","volume-title":"Computer Vision ECCV 2022","volume":"13687","author":"Liu","year":"2022"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep Residual Learning for Image Recognition","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"ref23","article-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Zhu","year":"2021"},{"key":"ref24","volume-title":"BEVFormer_segmentation_detection","year":"2023"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"16133","DOI":"10.1109\/CVPR52729.2023.01548","article-title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Woo","year":"2023"},{"key":"ref26","article-title":"Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality","author":"Li","year":"2022","journal-title":"arXiv"},{"key":"ref27","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/wacv.2017.58"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"event":{"name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","location":"Edmonton, AB, Canada","start":{"date-parts":[[2024,9,24]]},"end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10919469\/10919190\/10920077.pdf?arnumber=10920077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T21:07:12Z","timestamp":1742591232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10920077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/itsc58415.2024.10920077","relation":{},"subject":[],"published":{"date-parts":[[2024,9,24]]}}}