fabro66 / GAST-Net-3DPoseEstimation

A Graph Attention Spatio-temporal Convolutional Networks for 3D Human Pose Estimation in Video (GAST-Net)
MIT License
311 stars 70 forks source link

How to not fix joint point 0 #53

Open PJJie opened 2 years ago

PJJie commented 2 years ago

In the case of a single person, it seems that the 0-off node is fixed. For example, when a single person walks, the generated skeleton always walks in place, which reduces the accuracy of the action recognition task. How can I not fix 0 off node? Thank you for your answer!