The dataset Dancer99 consists of solo dance videos of 99 subjects, with different choreography and background music, providing a robust evaluation of the proposed method’s...
The dataset Dancer101 consists of solo dance videos of 101 subjects from the public domain, providing a benchmark to prompt the development of HMT methods.
Human motion transfer (HMT) aims to generate a video clip for the target subject by imitating the source subject’s motion. Although previous methods have achieved good results...
