{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:34:43Z","timestamp":1780079683599,"version":"3.54.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3070379","type":"journal-article","created":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T19:43:37Z","timestamp":1617306217000},"page":"51710-51721","source":"Crossref","is-referenced-by-count":61,"title":["RoIFusion: 3D Object Detection From LiDAR and Vision"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4928-8880","authenticated-orcid":false,"given":"Can","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6269-5280","authenticated-orcid":false,"given":"Luca Zanotti","family":"Fragonara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3966-7633","authenticated-orcid":false,"given":"Antonios","family":"Tsourdos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref38","article-title":"PV-RCNN: Point-voxel feature set abstraction for 3D object detection","author":"shi","year":"2019","journal-title":"arXiv 1912 13192"},{"key":"ref33","article-title":"Submanifold sparse convolutional networks","author":"graham","year":"2017","journal-title":"arXiv 1706 01307"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI48845.2019.8965844"},{"key":"ref30","article-title":"PointPainting: Sequential fusion for 3D object detection","author":"vora","year":"2019","journal-title":"arXiv 1911 10150"},{"key":"ref37","article-title":"TANet: Robust 3D object detection from point clouds with triple attention","author":"liu","year":"2019","journal-title":"arXiv 1912 05163"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00987"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00033"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref1","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref24","first-page":"197","article-title":"Complex-YOLO: An Euler-region-proposal for real-time 3D object detection on point clouds","author":"simon","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref10","article-title":"More diverse means better: Multimodal deep learning meets remote-sensing imagery classification","author":"hong","year":"2020","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.06.014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00783"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.10.006"},{"key":"ref13","first-page":"1","article-title":"ImageNet classification with deep convolutional neural","author":"krizhevsky","year":"2014","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref15","first-page":"5099","article-title":"PointNet: Deep hierarchical feature learning on point sets in a metric space","author":"qi","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref18","article-title":"GAPNet: Graph attention based point neural network for exploiting local feature of point cloud","author":"chen","year":"2019","journal-title":"arXiv 1905 08705"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app10072391"},{"key":"ref4","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2856821"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2933224"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref45","article-title":"Patch refinement–localized 3D object detection","author":"lehner","year":"2019","journal-title":"arXiv 1910 04093"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref47","article-title":"IPOD: Intensive point-based object detector for point cloud","author":"yang","year":"2018","journal-title":"arXiv 1812 05276"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"ref44","first-page":"202","article-title":"VoteNet: A deep learning label fusion method for multi-atlas segmentation","author":"ding","year":"2019","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref43","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09393330.pdf?arnumber=9393330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T09:25:06Z","timestamp":1643189106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9393330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3070379","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}