Show simple item record

dc.contributor.authorChen, G.
dc.contributor.authorWang, W.
dc.contributor.authorHe, Z.
dc.contributor.authorWang, L.
dc.contributor.authorYuan, Y.
dc.contributor.authorZhang, D.
dc.contributor.authorZhang, J.
dc.contributor.authorZhu, P.
dc.contributor.authorGool, L. V.
dc.contributor.authorHan, J.
dc.contributor.authorHoi, S.
dc.contributor.authorHu, Q.
dc.contributor.authorLiu, M.
dc.contributor.authorSciarrone, A.
dc.contributor.authorSun, C.
dc.contributor.authorGaribotto, C.
dc.contributor.authorTran, D. N. N.
dc.contributor.authorLavagetto, F.
dc.contributor.authorHaleem, H.
dc.contributor.authorMotorcu, Hakkı
dc.contributor.authorAteş, H. F.
dc.contributor.authorJeon, H. J.
dc.contributor.authorBisio, I.
dc.contributor.authorJeon, J. W.
dc.contributor.authorLi, J.
dc.contributor.authorPham, J. H.
dc.contributor.authorJeon, M.
dc.contributor.authorFeng, Q.
dc.contributor.authorLi, S.
dc.contributor.authorTran, T. H. P.
dc.contributor.authorPan, X.
dc.contributor.authorSong, Y. M.
dc.contributor.authorYao, Y.
dc.contributor.authorDu, Y.
dc.contributor.authorXu, Z.
dc.contributor.authorLuo, Z.
dc.date.accessioned2023-05-03T10:46:22Z
dc.date.available2023-05-03T10:46:22Z
dc.date.issued2021
dc.identifier.issn1550-5499en_US
dc.identifier.urihttp://hdl.handle.net/10679/8170
dc.identifier.urihttps://ieeexplore.ieee.org/document/9607797
dc.description.abstractVision Meets Drone: Multiple Object Tracking (VisDrone-MOT2021) challenge - the forth annual activity organized by the VisDrone team - focuses on benchmarking UAV MOT algorithms in realistic challenging environments. It is held in conjunction with ICCV 2021. VisDrone-MOT2021 contains 96 video sequences in total, including 56 sequences (~24K frames) for training, 7 sequences (~3K frames) for validation and 33 sequences (~13K frames) for testing. Bounding-box annotations for novel object categories are provided every frame and temporally consistent instance IDs are also given. Additionally, occlusion ratio and truncation ratio are provided as extra useful annotations. The results of eight state-of-the-art MOT algorithms are reported and discussed. We hope that our VisDrone-MOT2021 challenge will facilitate future research and applications in the field of UAV vision.en_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.ispartof2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
dc.rightsrestrictedAccess
dc.titleVisDrone-MOT2021: The vision meets drone multiple object tracking challenge resultsen_US
dc.typeConference paperen_US
dc.publicationstatusPublisheden_US
dc.contributor.departmentÖzyeğin University
dc.identifier.startpage2839en_US
dc.identifier.endpage2846en_US
dc.identifier.wosWOS:000739651102102
dc.identifier.doi10.1109/ICCVW54120.2021.00318en_US
dc.subject.keywordsBenchmarken_US
dc.subject.keywordsChallengeen_US
dc.subject.keywordsDroneen_US
dc.subject.keywordsMulti-object trackingen_US
dc.subject.keywordsVisDroneen_US
dc.identifier.scopusSCOPUS:2-s2.0-85122776407
dc.contributor.ozugradstudentMotorcu, Hakkı
dc.relation.publicationcategoryConference Paper - International - Institutional Graduate Student


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record


Share this page