{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:15:30Z","timestamp":1756167330380,"version":"3.44.0"},"reference-count":50,"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\/itsc58415.2024.10919575","type":"proceedings-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T15:00:11Z","timestamp":1742569211000},"page":"2405-2412","source":"Crossref","is-referenced-by-count":0,"title":["QuadBEV: An Efficient Quadruple-Task Perception Framework via Birds'-Eye-View Representation"],"prefix":"10.1109","author":[{"given":"Yuxin","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengying","family":"Yu","sequence":"additional","affiliation":[{"name":"Desay SV Automotive Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihang","family":"Huang","sequence":"additional","affiliation":[{"name":"Desay SV Automotive Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Wu","sequence":"additional","affiliation":[{"name":"Desay SV Automotive Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaikiat","family":"Yeo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore"}],"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":"European Conference on Computer Vision (ECCV)","volume":"13669","author":"L.","year":"2022"},{"key":"ref2","article-title":"Lift, splat, shoot:Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d","volume-title":"European Conference on Computer Vision (ECCV)","author":"P.","year":"2020"},{"key":"ref3","first-page":"531","article-title":"PETR: position embedding transformation for multi-view 3d object detection","volume-title":"European Conference on Computer Vision (ECCV)","volume":"13687","author":"Y.","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500547"},{"key":"ref5","article-title":"Maptr: Structured modeling and learning for online vectorized HD map construction","volume-title":"International Conference on Learning Representations","author":"L","year":"2023"},{"key":"ref6","volume":"abs\/2311.12058","author":"Y.","year":"2023","journal-title":"Flashocc: Fast and memory-efficient occupancy prediction via channel-to-height plugin"},{"journal-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","year":"2021","author":"Huang","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref9","volume":"abs\/2206.01256","author":"L.","year":"2022","journal-title":"Petrv2: A unified framework for 3d perception from multi-camera images"},{"key":"ref10","volume":"abs\/2203.17054","author":"H.","year":"2022","journal-title":"Bevdet4d: Exploit temporal cues in multi-camera 3d object detection"},{"key":"ref11","volume":"abs\/2206.10092","author":"L.","year":"2022","journal-title":"Bevdepth: Acquisition of reliable depth for multi-view 3d object detection"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00350"},{"key":"ref13","volume":"abs\/2211.10581","author":"L.","year":"2022","journal-title":"Sparse4d: Multi-view 3d object detection with sparse spatial-temporal fusion"},{"key":"ref14","volume":"abs\/2303.10209","author":"X.","year":"2023","journal-title":"CAPE: camera view position embedding for multi-view 3d object detection"},{"key":"ref15","first-page":"4628","article-title":"Hdmapnet: An online HD map construction and evalu-ation framework","volume-title":"2022 International Conference on Robotics and Automation, ICRA","author":"L.","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00588"},{"key":"ref17","first-page":"22352","article-title":"Vectormapnet: End-to-end vectorized HD map learning","volume-title":"International Conference on Machine Learning, ICML, ser. Pro-ceedings of Machine Learning Research","volume":"202","author":"L.","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00103"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01674"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref21","first-page":"9399","article-title":"Occformer: Dual-path transformer for vision-based 3d se-mantic occupancy prediction","volume-title":"IEEE\/CVF International Conference on Computer Vision, ICCV","author":"Z.","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref23","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR. Computer Vision Foundation lIEEE Computer Society","author":"K.","year":"2018"},{"key":"ref24","first-page":"793","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"International Conference on Machine Learning, ICML","volume":"80","author":"C.","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.126"},{"key":"ref27","article-title":"Branched multi-task networks: Deciding what layers to share","volume-title":"British Machine Vision Conference, BMVC","author":"V.","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"journal-title":"Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","year":"2022","author":"Wang","key":"ref29"},{"key":"ref30","first-page":"784","article-title":"Center-based 3d object detection and tracking","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR. Computer Vision Foundation \/ IEEE","volume":"11","author":"Y.","year":"2021"},{"journal-title":"nuscenes: A multimodal dataset for autonomous driving","year":"2020","author":"C.","key":"ref31"},{"key":"ref32","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"The Conference on Robot Learning (CoRL)","author":"Wang","year":"2021"},{"key":"ref33","article-title":"Tig-bev: Multi-view BEV 3d object detection via target inner-geometry learning","author":"H.","year":"2022","journal-title":"vol. abs\/2212.13979"},{"key":"ref34","volume":"abs\/2210.02443","author":"P.","year":"2022","journal-title":"Time will tell: New outlooks and A baseline for temporal multi-view 3d object detection"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref37","first-page":"129","article-title":"Learning ego 3d representation as ray tracing","volume-title":"IEEE\/CVF European Conference on Computer Vision, ECCV, ser. Lecture Notes in Computer Science","volume":"13686","author":"L.","year":"2022"},{"key":"ref38","first-page":"12697","article-title":"Pointpillars: Fast encoders for object detection from point clouds","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"L.","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00301"},{"key":"ref40","first-page":"550","article-title":"Persformer: 3d lane detection via perspective transformer and the openlane benchmark","volume-title":"IEEE\/ CVF European Conference on Computer Vision, ECCV","volume":"13698","author":"C.","year":"2022"},{"key":"ref41","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","author":"T.","year":"2023","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref42","volume":"abs\/2309.09502","author":"P.","year":"2023","journal-title":"Renderocc: Vision-centric 3d occupancy prediction with 2d rendering supervision"},{"key":"ref43","volume":"abs\/2306.10013","author":"W.","year":"2023","journal-title":"Panoocc: Unified occupancy representation for camera-based 3d panoptic segmentation"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"journal-title":"P. e. a. Sun","year":"2020","key":"ref46"},{"key":"ref47","article-title":"Openlane-v2: A topology reasoning benchmark for uni-fied 3d HD mapping","author":"W.","year":"2023","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"volume-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","year":"2020","author":"Contributors","key":"ref48"},{"key":"ref49","volume":"abs\/1908.09492","author":"Z.","year":"2019","journal-title":"Class-balanced grouping and sampling for point cloud 3d object detection"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"}],"event":{"name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","start":{"date-parts":[[2024,9,24]]},"location":"Edmonton, AB, Canada","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\/10919575.pdf?arnumber=10919575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:13:19Z","timestamp":1756152799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10919575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/itsc58415.2024.10919575","relation":{},"subject":[],"published":{"date-parts":[[2024,9,24]]}}}