{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:44:52Z","timestamp":1765547092552,"version":"3.37.3"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Vietnam Ministry of Science and Technology","award":["NDT\/AT\/22\/09"],"award-info":[{"award-number":["NDT\/AT\/22\/09"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3288027","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T17:33:30Z","timestamp":1687282410000},"page":"64170-64184","source":"Crossref","is-referenced-by-count":1,"title":["MonoIS3DLoc: Simulation to Reality Learning Based Monocular Instance Segmentation to 3D Objects Localization From Aerial View"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7443-9102","authenticated-orcid":false,"given":"Dinh Tuan","family":"Tran","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University, Shiga, Kusatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8535-8820","authenticated-orcid":false,"given":"Dung Duc","family":"Tran","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5091-7401","authenticated-orcid":false,"given":"Minh Anh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quyen","family":"Van Pham","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1100-087X","authenticated-orcid":false,"given":"Nobutaka","family":"Shimada","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University, Shiga, Kusatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1015-5615","authenticated-orcid":false,"given":"Joo-Ho","family":"Lee","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University, Shiga, Kusatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4198-4208","authenticated-orcid":false,"given":"Anh Quang","family":"Nguyen","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018851"},{"key":"ref12","article-title":"Objects as points","author":"zhou","year":"2019","journal-title":"arXiv 1904 07850"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00217"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00394"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803397"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01214"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018409"},{"key":"ref19","article-title":"PoseCNN: A convolutional neural network for 6D object pose estimation in cluttered scenes","author":"xiang","year":"2017","journal-title":"arXiv 1711 00199"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref48","article-title":"Unsupervised monocular depth estimation with left-right consistency","author":"godard","year":"2016","journal-title":"arXiv 1609 03677"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref44","article-title":"Pyramid scene parsing network","author":"zhao","year":"2016","journal-title":"arXiv 1612 01105"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01371"},{"key":"ref49","article-title":"3D object proposals using stereo imagery for accurate object class detection","author":"chen","year":"2016","journal-title":"arXiv 1608 07711 [cs]"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00696"},{"key":"ref3","article-title":"You only look once: Unified, real-time object detection","author":"redmon","year":"2015","journal-title":"arXiv 1506 02640"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00108"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01225"},{"key":"ref40","article-title":"Deformable ConvNets v2: More deformable, better results","author":"zhu","year":"2018","journal-title":"arXiv 1811 11168"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2019.8870934"},{"key":"ref37","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref36","article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","author":"bronstein","year":"2021","journal-title":"arXiv 2104 13478"},{"key":"ref31","article-title":"Flightmare: A flexible quadrotor simulator","author":"song","year":"2020","journal-title":"arXiv 2009 00563"},{"key":"ref30","article-title":"AirSim: High-fidelity visual and physical simulation for autonomous vehicles","author":"shah","year":"2017","journal-title":"arXiv 1705 05065"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_23"},{"key":"ref32","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Proc 1st Annu Conf Robot Learn"},{"key":"ref2","first-page":"1","article-title":"DisNet: A novel method for distance estimation from monocular camera","author":"haseeb","year":"2018","journal-title":"Proc 10th Planning Perception Navigat Intell Vehicles (PPNIV)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298800"},{"key":"ref39","article-title":"Bag of tricks for image classification with convolutional neural networks","author":"he","year":"2018","journal-title":"arXiv 1812 01187"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00439"},{"key":"ref24","first-page":"8404","article-title":"The earth ain’t flat: Monocular reconstruction of vehicles on steep and graded roads from a moving camera","author":"ansari","year":"2018","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.198"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE50850.2020.9310796"},{"key":"ref25","article-title":"Bayesian domain randomization for sim-to-real transfer","author":"muratore","year":"2020","journal-title":"arXiv 2003 02471"},{"key":"ref20","article-title":"ConvPoseCNN: Dense convolutional 6D object pose estimation","author":"capellen","year":"2019","journal-title":"arXiv 1912 07333"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref21","first-page":"1","article-title":"Real-time monocular object instance 6D pose estimation","author":"do","year":"2019","journal-title":"Proc 29th Brit Mach Vis Conf (BMVC)"},{"key":"ref28","article-title":"Meta reinforcement learning for sim-to-real domain adaptation","author":"arndt","year":"2019","journal-title":"arXiv 1909 12906"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11436"},{"key":"ref29","article-title":"Continual reinforcement learning deployed in real-life using policy distillation and sim2real transfer","author":"traor\u00e9","year":"2019","journal-title":"arXiv 1906 04452"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10156844.pdf?arnumber=10156844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:55:19Z","timestamp":1689616519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10156844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3288027","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}