search

lawrence-cj / ARKitTrack

PyTorch implementation of ARKitTrack for CVPR'2023 paper "ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data", by Haojie Zhao, Junsong Chen, Lijun Wang, Huchuan Lu. Code will be released here.
MIT License
43 stars 4 forks source link

vot train dataset #6

Open ShangGaoG opened 12 months ago

ShangGaoG commented 12 months ago

Hi, thank you for your outstanding contribution. Is the image‘s naming format in the vot.zip the final version?

lawrence-cj commented 12 months ago

Yes, correctOn Sep 14, 2023, at 23:59, ShangGaoG @.***> wrote: Hi, thank you for your outstanding contribution. Is the image‘s naming format in the vot.zip the final version?

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you are subscribed to this thread.Message ID: @.***>

ShangGaoG commented 12 months ago

Thanks for your reply. But it looks like the code provided can't read this naming format correctly, like 760577.250899.jpg. By the way, why are there multiple truth box files, like "groundtruth_1.txt, groundtruth_2.txt'?

lawrence-cj commented 12 months ago

I’ll check the code. Different truth box indicates different object. There may be multiple objects in one video. On Sep 15, 2023, at 10:18, ShangGaoG @.***> wrote: Thanks for your reply. But it looks like the code provided can't read this naming format correctly, like 760577.250899.jpg. By the way, why are there multiple truth box files, like "groundtruth_1.txt, groundtruth_2.txt'?

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you commented.Message ID: @.***>