{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T08:01:43Z","timestamp":1759564903149,"version":"3.37.3"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission (ITC)'s InnoHK","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.01292","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:30:52Z","timestamp":1692725452000},"page":"13445-13454","source":"Crossref","is-referenced-by-count":21,"title":["MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training"],"prefix":"10.1109","author":[{"given":"Runsen","family":"Xu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Tai","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"NTU,S-Lab"}]},{"given":"Runjian","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Jinkun","family":"Cao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Masked autoencoders as spatiotemporal learners","author":"feichtenhofer","year":"2022","journal-title":"ArXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref11","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"ICLRE"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"ref50","article-title":"Ssn: Shape signature networks for multi-class object detection from point clouds","author":"zhu","year":"0","journal-title":"ECCV"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_27"},{"key":"ref48","article-title":"Self pre-training with masked autoencoders for medical image analysis","author":"zhou","year":"2022","journal-title":"ArXiv"},{"key":"ref47","article-title":"ibot: Image bert pre-training with online tokenizer","author":"zhou","year":"2021","journal-title":"ArXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref44","article-title":"Point-m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training","author":"zhang","year":"2022","journal-title":"ArXiv"},{"key":"ref43","article-title":"Position prediction as an effective pretraining strategy","author":"zhai","year":"0","journal-title":"ICML"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref8","article-title":"Improved baselines with momentum contrastive learning","author":"chen","year":"2020","journal-title":"ArXiv"},{"key":"ref7","article-title":"Context autoencoder for self-supervised representation learning","author":"chen","year":"2022","journal-title":"ArXiv"},{"journal-title":"MMDetection3D Open-MMLab Next-generation Platform for General 3D Object Detection","year":"2020","key":"ref9"},{"key":"ref4","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"caron","year":"0","journal-title":"NeurIPS"},{"key":"ref3","article-title":"nuscenes: A multi-modal dataset for autonomous driving","author":"caesar","year":"2019","journal-title":"ArXiv"},{"key":"ref6","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"ICML"},{"key":"ref5","article-title":"CO3: Cooperative unsupervised 3d representation learning for autonomous driving","author":"chen","year":"0","journal-title":"ICLRE"},{"key":"ref40","article-title":"Proposal-contrast: Unsupervised pre-training for lidar-based 3d object detection","author":"yin","year":"0","journal-title":"ECCV"},{"key":"ref35","article-title":"Pointcontrast: Unsupervised pretraining for 3d point cloud understanding","author":"xie","year":"0","journal-title":"ECCV"},{"key":"ref34","article-title":"Balanced chamfer distance as a comprehensive metric for point cloud completion","author":"wu","year":"0","journal-title":"NeurIPS"},{"key":"ref37","article-title":"Masked autoencoders that listen","author":"xu","year":"2022","journal-title":"ArXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref31","article-title":"Swformer: Sparse window transformer for 3d object detection in point clouds","author":"sun","year":"0","journal-title":"ECCV"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref33","article-title":"Reconfigurable voxels: A new representation for lidar-based point clouds","author":"wang","year":"0","journal-title":"CoRL"},{"key":"ref32","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"tong","year":"0","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"brown","year":"0","journal-title":"NeurIPS"},{"key":"ref1","article-title":"Beit: Bert pre-training of image transformers","author":"bao","year":"2021","journal-title":"ArXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.3390\/s18103337","article-title":"Second: Sparsely embedded convolutional detection","author":"yan","year":"2018","journal-title":"SENSORS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref26","article-title":"Masked autoencoders for point cloud self-supervised learning","author":"pang","year":"0","journal-title":"ECCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00328"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","article-title":"Masked discrimination for self-supervised learning on point clouds","author":"liu","year":"0","journal-title":"ECCV"},{"key":"ref28","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref27","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"qi","year":"0","journal-title":"NeurIPS"},{"key":"ref29","article-title":"Self-supervised deep learning on point clouds by reconstructing space","author":"sauder","year":"0","journal-title":"NeurIPS"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2023,6,17]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10203646.pdf?arnumber=10203646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:59:21Z","timestamp":1694455161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10203646\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/cvpr52729.2023.01292","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}