{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:38Z","timestamp":1757608718273,"version":"3.44.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127749","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"10095-10102","source":"Crossref","is-referenced-by-count":0,"title":["Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-Based Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Yichen","family":"Xie","sequence":"first","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongge","family":"Chen","sequence":"additional","affiliation":[{"name":"Cruise LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory P.","family":"Meyer","sequence":"additional","affiliation":[{"name":"Cruise LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Cruise LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric M.","family":"Wolff","sequence":"additional","affiliation":[{"name":"Cruise LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"University of California,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuning","family":"Chai","sequence":"additional","affiliation":[{"name":"Cruise LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Huang","sequence":"additional","affiliation":[{"name":"Cruise LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BEVDet: Highperformance multi-camera 3d object detection in bird-eye-view","volume-title":"arXiv:2112.11790","author":"Huang","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref4","article-title":"MapTR: Structured modeling and learning for online vectorized hd map construction","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liao","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref6","article-title":"Perceive, interact, predict: Learning dynamic and static clues for end-to-end motion prediction","volume-title":"arXiv:2212.02181","author":"Jiang","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00505"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref13","article-title":"DETR3D: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref17","article-title":"Bevdet4d: Exploit temporal cues in multicamera 3d object detection","volume-title":"arXiv:2203.17054","author":"Huang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref19","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","author":"Park","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01559"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00647"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref28","first-page":"27061","article-title":"Point-m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Bev-mae: Bird\u2019s eye view masked autoencoders for outdoor point cloud pre-training","volume-title":"arXiv:2212.05758","author":"Lin","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01304"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref32","article-title":"Occ-bev: Multi-camera unified pre-training via 3d scene reconstruction","volume-title":"arXiv:2305.18829","author":"Min","year":"2023"},{"key":"ref33","article-title":"Pre-training on synthetic driving data for trajectory prediction","volume-title":"arXiv:2309.10121","author":"Li","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref36","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pretraining","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref38","article-title":"Siamese masked autoencoders","volume-title":"arXiv:2305.14344","author":"Gupta","year":"2023"},{"key":"ref39","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume":"33","author":"Han","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","first-page":"19545","article-title":"Space-time correspondence as a contrastive random walk","volume":"33","author":"Jabri","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2010.5548059"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37456-2_14"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00505"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00508"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01607"},{"key":"ref49","article-title":"Calico: Self-supervised camera-lidar contrastive pre-training for bev perception","volume-title":"arXiv:2306.00349","author":"Sun","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127749.pdf?arnumber=11127749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:21Z","timestamp":1756880001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127749","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}