search

Walter0807 / MotionBERT

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"
Apache License 2.0
1k stars 120 forks source link

What is the third channel for 2D pose input? #93

Closed pha123661 closed 10 months ago

pha123661 commented 11 months ago

Thanks for your great work! I would like to know what the third channel of 2D pose input stands for? Is it the output confidence score of the pose estimators?

x: 2D skeletons 
    type = <class 'torch.Tensor'>
    shape = [batch size * frames * joints(17) * channels(3)]
Walter0807 commented 10 months ago

Thanks for your interest! It is the confidence of the 2D joint.