Hello author, you used the tex_mot_match model in text-to-motion during the evaluation, but the structure of the model in the first stage is not the same, and the method of text feature extraction is also different. Why use the verification model of text-to-motion?
Hello author, you used the tex_mot_match model in text-to-motion during the evaluation, but the structure of the model in the first stage is not the same, and the method of text feature extraction is also different. Why use the verification model of text-to-motion?