{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T14:42:59Z","timestamp":1730212979456,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T00:00:00Z","timestamp":1718582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T00:00:00Z","timestamp":1718582400000},"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":[[2024,6,17]]},"DOI":"10.1109\/cvprw63382.2024.00205","type":"proceedings-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:27:42Z","timestamp":1727461662000},"page":"1997-2006","source":"Crossref","is-referenced-by-count":0,"title":["RGB-D Cube R-CNN: 3D Object Detection with Selective Modality Dropout"],"prefix":"10.1109","author":[{"given":"Jens","family":"Piekenbrinck","sequence":"first","affiliation":[{"name":"RWTH Aachen University"}]},{"given":"Alexander","family":"Hermans","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}]},{"given":"Narunas","family":"Vaskevicius","sequence":"additional","affiliation":[{"name":"Robert Bosch GmbH"}]},{"given":"Timm","family":"Linder","sequence":"additional","affiliation":[{"name":"Robert Bosch GmbH"}]},{"given":"Bastian","family":"Leibe","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}]}],"member":"263","reference":[{"article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning","author":"Baevski","key":"ref1"},{"article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","volume-title":"International Conference on Machine Learning","author":"Baevski","key":"ref2"},{"key":"ref3","article-title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","author":"Baruch","year":"2021","journal-title":"Advances in Neural Information Processing Systems Datasets and Benchmarks Track"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190858"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref8"},{"article-title":"Point-gcc : Universal self-supervised 3d scene pre-training via geometry-color contrast","year":"2023","author":"Fan","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01298"},{"article-title":"Perceiver: General Perception with Iterative Attention","volume-title":"International Conference on Machine Learning","author":"Jaegle","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812299"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196899"},{"article-title":"P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding","year":"2020","author":"Liu","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Decoupled Weight Decay Regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341029"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00446"},{"article-title":"Accelerating 3D Deep Learning with PyTorch3D","year":"2020","author":"Ravi","key":"ref28"},{"key":"ref29","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222644"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"article-title":"How to train your vit? data, augmentation, and regularization in vision transformers","year":"2021","author":"Steiner","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341422"},{"key":"ref36","first-page":"29975","article-title":"Cagroup3d: Class-aware grouping for 3d object detection on point clouds","volume":"35","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Pytorch image models","year":"2019","author":"Wightman","key":"ref37"},{"article-title":"Detectron2","year":"2019","author":"Wu","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"article-title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","volume-title":"International Conference on Machine Learning","author":"Zbontar","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"article-title":"Objects as points","year":"2019","author":"Zhou","key":"ref43"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","start":{"date-parts":[[2024,6,17]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2024,6,18]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10677511\/10677844\/10678259.pdf?arnumber=10678259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T04:02:58Z","timestamp":1727582578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10678259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,17]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/cvprw63382.2024.00205","relation":{},"subject":[],"published":{"date-parts":[[2024,6,17]]}}}