Haoyu Ma

The TokenPose has a linear projection layer to make different input produce the same number of tokens (i.e., 16 * 16). In contrast, the TransPose does not have it, which...

Thanks for your interest in our work. More details will be released soon in our paper. For multi-view pose estimation on the custom dataset, I suggest you fine-tune the multi-view...

Yes, your understanding is correct.

Same question. Besides, it seems that the provided bounding box is not a square bounding box. For example, the bounding box has a size of (1018 - 648, 553-48), i.e,...

Hi, thanks for your interests in this project. It may be available on Win10. Unfortunately, I don't have a device with Win10 to verify it at this time. The error...

You can keep the exp as a None value. i.e., if you don't pass the exp value, it will follow the original expression coefficient. The logic is here: https://github.com/HowieMa/CVTHead/blob/8f75b227fe35d3aec30920064ef7c9df5dcd8567/models/cvthead.py#L436

Oh you also need to keep the original jaw pose. In the flame model, the model is always closed if you keep the default jaw pose.

Hi, thanks for your interests in our work! I only trained it once and get these results, not "pick a good with many times". As for your results, there could...

Hi, unfortunately, I have graduated and cannot get the original training logs for resnet50+cifar100. I have posted a similar log for ResNext-29 + CIFAR-100 before (#14) before, and you can...