what is the difference between PostText and Text description in the readme of the dataset

[hdjsjyl]

Hi author,
I got text description in terms of the ReadMe.
In the issue, I found you release the "whole-body" description.
What is the difference between them? If I want to train a model of generating whole-body motion, no face, no hand. Which data I should use for training? Thanks

[linjing7]

Hi, you should use the semantic label. Text description provided in README is frame-level pose descriptions.

[chenmingTHU]

Hi, you should use the semantic label. Text description provided in README is frame-level pose descriptions.

Thanks for your work! Is the motionx_seq_text.zip the same with semantic labels? I find no semantic_labels in Zip files provided.

[Infinitywxh]

Hi, you should use the semantic label. Text description provided in README is frame-level pose descriptions.

Hi, I can't find the directory 'semantic_labels' in the zip files from the provided urls. Could you elaborate the location of it? Thanks!