Feature Extractors for Evaluation

[yahshibu]

Hello, great work! And, thank you for sharing your code.

I'd like to train several motion generation models on Motion-X and evaluate them. Your paper says

We pretrain a motion feature extractor and a text feature extractor for the new motion presentation with contrastive loss to map the text and motion into feature space and then evaluate the distance between the text-motion pairs.

I'd like to use your pretrained feature extractors (motion and text) and evaluation code. Do you have a plan to make them publicly available?

[linjing7]

Hi, thanks for your interest. We have recently improved our text labels and we will release it next week. After that, we will train a new feature extractor with this version and release for evaluation.

[yahshibu]

Thank you for your response! I got it. I look forward to the release. Thanks!

[luomingshuang]

@linjing7 , hi, thanks for your excellent work. At present, I am using motion-x for some works. Can you share your feature extractors ?

[luomingshuang]

I want to know how to compare my new results with the public results on Motion-x if the evaluator models (feature extractors) are different.