{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T14:58:28Z","timestamp":1772549908665,"version":"3.50.1"},"reference-count":67,"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"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","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.2021.3120261","type":"journal-article","created":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T09:32:29Z","timestamp":1634290349000},"page":"143138-143149","source":"Crossref","is-referenced-by-count":8,"title":["3D Object Detection With Multi-Frame RGB-Lidar Feature Alignment"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-0475","authenticated-orcid":false,"given":"Emec","family":"Ercelik","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3103-6052","authenticated-orcid":false,"given":"Ekim","family":"Yurtsever","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00653"},{"key":"ref38","article-title":"AB3DMOT: A baseline for 3D multi-object tracking and new evaluation metrics","author":"weng","year":"2020","journal-title":"arXiv 2008 08063"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref30","article-title":"You only watch once: A unified CNN architecture for real-time spatiotemporal action localization","author":"k\u00f6p\u00fckl\u00fc","year":"2019","journal-title":"arXiv 1911 06644"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813779"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00634"},{"key":"ref35","first-page":"2454","article-title":"AerialMPTNet: Multi-pedestrian tracking in aerial imagery using temporal and graphical features","author":"kraus","year":"2021","journal-title":"Proc Int Conf Pattern Recognit (ICPR)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00245"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00376"},{"key":"ref61","first-page":"11784","article-title":"Center-based 3D object detection and tracking","author":"yin","year":"2021","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref63","article-title":"Yolo4d: A spatio-temporal approach for real-time multi-object detection and classification from LiDAR point clouds","author":"el sallab","year":"2018","journal-title":"Proc NIPS Workshop MLITS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050867"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.5220\/0009340004320439"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref66","article-title":"Temp-Frustum Net: 3D object detection with temporal fusion","author":"er\u00e7elik","year":"2021","journal-title":"Proc IEEE Intell Vehicles Symp (IV)"},{"key":"ref29","first-page":"1604","article-title":"Video object detection using object’s motion context and spatio-temporal feature aggregation","author":"kim","year":"2021","journal-title":"Proc Int Conf Pattern Recognit (ICPR)"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00208"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00678"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00985"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.257"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.44"},{"key":"ref26","first-page":"331","article-title":"Object detection in video with spatiotemporal sampling networks","author":"bertasius","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00596"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00549"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref56","article-title":"PV-RCNN++: Point-voxel feature set abstraction with local vector representation for 3D object detection","author":"shi","year":"2021","journal-title":"arXiv 2102 00463"},{"key":"ref55","article-title":"Deformable PV-RCNN: Improving 3D object detection with learned deformations","author":"bhattacharyya","year":"2020","journal-title":"arXiv 2008 08766"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref53","first-page":"5105","article-title":"PointNet++ deep hierarchical feature learning on point sets in a metric space","author":"qi","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191134"},{"key":"ref12","first-page":"3772","article-title":"Cross-modality 3D object detection","author":"zhu","year":"2021","journal-title":"Proc IEEE\/CVF Winter Conf Appl Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref14","first-page":"10386","article-title":"CLOCs: Camera-LiDAR object candidates fusion for 3D object detection","author":"pang","year":"2020","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"ref18","article-title":"Faraway-frustum: Dealing with LiDAR sparsity for 3D object detection using fusion","author":"zhang","year":"2020","journal-title":"arXiv 2011 01404"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.101"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"ref5","article-title":"Voxel R-CNN: Towards high performance voxel-based 3D object detection","author":"deng","year":"2020","journal-title":"arXiv 2012 15712"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"SECOND: Sparsely embedded convolutional detection","volume":"18","author":"yan","year":"2018","journal-title":"SENSORS"},{"key":"ref9","article-title":"IPOD: Intensive point-based object detector for point cloud","author":"yang","year":"2018","journal-title":"arXiv 1812 05276"},{"key":"ref46","article-title":"MOTR: End-to-end multiple-object tracking with transformer","author":"zeng","year":"2021","journal-title":"arXiv 2105 03247"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref47","article-title":"TransMOT: Spatial-temporal graph transformer for multiple object tracking","author":"chu","year":"2021","journal-title":"arXiv 2104 00194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01151"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_16"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09570375.pdf?arnumber=9570375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T21:08:10Z","timestamp":1640639290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9570375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3120261","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}