2D

[caochengchen]

If my dataset stores frame-by-frame images in each folder, with images containing only upper body movements, and each folder represents an action sequence with a corresponding text description. How should I use your code for such a dataset? Also, which part of your code is related to text-motion alignment? I couldn't find it, please point it out. Thank you. If I have only extracted the 2D skeletal keypoints of human images, how do I use your code?

[LinghaoChan]

Please refer to the OpenTMA part. I think you can easily transfer the code with simply changing the vector dimension.