{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:31:02Z","timestamp":1775745062036,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610545","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"16388-16394","source":"Crossref","is-referenced-by-count":13,"title":["EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection"],"prefix":"10.1109","author":[{"given":"Zhe","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Fan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoliang","family":"Huo","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongda","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilun","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya-Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for AI Industry Research (AIR),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Vision-centric bev perception: A survey","author":"Ma","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2023.3298534"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"ref4","first-page":"3474","article-title":"Dis-conet: Shapes learning on disconnected manifolds for 3d editing","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Mehr"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"ref6","article-title":"Cobevt: Cooperative bird\u2019s eye view semantic segmentation with sparse trans-formers","author":"Xu","year":"2022"},{"key":"ref7","first-page":"1195","article-title":"Learning to communicate and correct pose errors","volume-title":"Proceedings of the 2020 Conference on Robot Learning","volume":"155","author":"Vadivelu"},{"key":"ref8","article-title":"Vehicle-infrastructure cooperative 3d object detection via feature flow prediction","author":"Yu","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192802"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"ref11","article-title":"Where2comm: Communication-efficient collaborative perception via spatial confi-dence maps","author":"Hu","year":"2022"},{"key":"ref12","article-title":"Co\u02c6 3: Cooperative unsupervised 3d representation learning for autonomous driving","author":"Chen","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_36"},{"key":"ref14","article-title":"Quest: Query stream for vehicle-infrastructure cooperative perception","author":"Fan","year":"2023"},{"key":"ref15","article-title":"Model-agnostic multi-agent perception framework","author":"Chen","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"ref17","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"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref20","article-title":"Petrv2: A unified framework for 3d perception from multi-camera images","author":"Liu","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref23","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref24","article-title":"Bevdet4d: Exploit temporal cues in multi-camera 3d object detection","author":"Huang","year":"2022"},{"key":"ref25","article-title":"M\u02c6 2bev: Multi-camera joint 3d detection and segmentation with unified birds-eye view representation","author":"Xie","year":"2022"},{"key":"ref26","article-title":"Beverse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","author":"Zhang","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref29","article-title":"Bevdepth: Acquisition of reliable depth for multi-view 3d object detection","author":"Li","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00588"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01164"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00892"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00416"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610545.pdf?arnumber=10610545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T19:52:36Z","timestamp":1736365956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610545","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}