{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:56:21Z","timestamp":1759334181678,"version":"build-2065373602"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"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":[[2025,8,17]]},"DOI":"10.1109\/case58245.2025.11163793","type":"proceedings-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:24:07Z","timestamp":1758648247000},"page":"2881-2888","source":"Crossref","is-referenced-by-count":0,"title":["Unified Self-supervised Representation Learning for Multi-modal and Single-modal 3D Perception"],"prefix":"10.1109","author":[{"given":"Xiaohao","family":"Xu","sequence":"first","affiliation":[{"name":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Li","sequence":"additional","affiliation":[{"name":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA,15213"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinrong","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Johnson-Roberson","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA,15213"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaonan","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611485"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610896"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28141"},{"article-title":"Voxel-mae: Masked autoencoders for pre-training large-scale point clouds","year":"2022","author":"Min","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01293"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00907"},{"article-title":"Calico: Self-supervised camera-lidar contrastive pre-training for bev perception","volume-title":"ICLR","author":"Sun","key":"ref11"},{"article-title":"Bevdistill: Cross-modal bev distillation for multi-view 3d object detection","volume-title":"ICLR","author":"Chen","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_42"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"article-title":"ibot: Image bert pre-training with online tokenizer","year":"2021","author":"Zhou","key":"ref17"},{"article-title":"Data determines distributional robustness in contrastive language image pre-training (clip)","year":"2022","author":"Fang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_24"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00556"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01474"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00052"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref31","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","author":"Wang","year":"2022","journal-title":"CoRL"},{"article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","year":"2021","author":"Huang","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3401172"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610946"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref40","article-title":"End-to-end multi-view fusion for 3d object detection in lidar point clouds","author":"Zhou","year":"2020","journal-title":"CoRL"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref44","article-title":"Deepinteraction: 3d object detection via modality interaction","author":"Yang","year":"2022","journal-title":"NeurIPS"},{"key":"ref45","article-title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","author":"Liang","year":"2022","journal-title":"NeurIPS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01292"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00335"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/964965.808594"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Class-balanced grouping and sampling for point cloud 3d object detection","year":"2019","author":"Zhu","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"article-title":"3d object proposals for accurate object class detection","volume-title":"NeurIPS","author":"Chen","key":"ref55"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"year":"2020","key":"ref58","article-title":"Mmdetection3d: Open-mmlab next-generation platform for general 3d object detection"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00119"},{"article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","year":"2023","author":"Wilson","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_29"}],"event":{"name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2025,8,17]]},"location":"Los Angeles, CA, USA","end":{"date-parts":[[2025,8,21]]}},"container-title":["2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11163731\/11163732\/11163793.pdf?arnumber=11163793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:26:16Z","timestamp":1759238776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11163793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,17]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/case58245.2025.11163793","relation":{},"subject":[],"published":{"date-parts":[[2025,8,17]]}}}