It's not totally clear to me what you're trying to achieve. If you have just one video of a person and you'd like to generate more videos like that conditioned on some pose, why don't you use Everybody Dance Now or a similar work?
The point of our work is to be able to animate a diverse set of objects in an unsupervised manner, if you're interested in animating a particular object, supervised methods should be preferred.
It's not totally clear to me what you're trying to achieve. If you have just one video of a person and you'd like to generate more videos like that conditioned on some pose, why don't you use Everybody Dance Now or a similar work?
The point of our work is to be able to animate a diverse set of objects in an unsupervised manner, if you're interested in animating a particular object, supervised methods should be preferred.