{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T14:31:50Z","timestamp":1780669910756,"version":"3.54.1"},"reference-count":83,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2047359"],"award-info":[{"award-number":["2047359"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02553","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27498-27509","source":"Crossref","is-referenced-by-count":1,"title":["Self-Supervised Sparse Sensor Fusion for Long Range Perception"],"prefix":"10.1109","author":[{"given":"Edoardo","family":"Palladin","sequence":"first","affiliation":[{"name":"Torc Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"Brucker","sequence":"additional","affiliation":[{"name":"Torc Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Filippo","family":"Ghilotti","sequence":"additional","affiliation":[{"name":"Torc Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praveen","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Torc Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario","family":"Bijelic","sequence":"additional","affiliation":[{"name":"Torc Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Heide","sequence":"additional","affiliation":[{"name":"Torc Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01373"},{"key":"ref2","article-title":"Depth pro: Sharp monocular metric depth in less than a second","author":"Bochkovskii","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01293"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","article-title":"Bevfusion4d: Learning lidar-camera fusion under bird\u2019s-eye-view via crossmodality guidance and temporal aggregation","author":"Cai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref9","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00890"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_22"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00731"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref23","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2018.00013"},{"key":"ref26","first-page":"12697","article-title":"Pointpillars: Fast encoders for object detection from point clouds","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Alex","year":"2019"},{"key":"ref27","article-title":"Hdmapnet: An online HD map construction and evaluation framework","author":"Li","year":"2021","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1340"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3392303"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref37","volume-title":"One million scenes for autonomous driving: Once dataset","author":"Mao","year":"2021"},{"key":"ref38","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_27"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00588"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3040528"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01424"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/785"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01273"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref56","volume-title":"Distillnerf: Perceiving 3d scenes from single-glance images by distilling neural fields and foundation model features","author":"Wang","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref60","volume-title":"Inverting the pose forecasting pipeline with spf2: Sequential pointcloud forecasting for sequential pose forecasting","author":"Weng","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_32"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"ref63","volume-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01443"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0145"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"ref72","first-page":"16494","article-title":"Multimodal virtual point 3d detection","volume":"34","author":"Yin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01161"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00500"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01777"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-016-1006-2"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref81","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref82","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_5"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445672.pdf?arnumber=11445672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:21Z","timestamp":1777613541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445672\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02553","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}