Semantically Consistent Text-to-Motion with Unsupervised Styles

Text-to-stylized human motion generation leverages text descriptions for motion generation with fine-grained style control with respect to a reference motion. However, existing approaches typically rely on supervised style learning with labeled datasets, constraining their adaptability and generalization for effective diverse style control. Additionally, they have not fully explored the temporal correlations between motion, textual descriptions, and style, making it challenging to generate semantically consistent motion with for profit or commercial advantage and that copies bear this notice and the full citation on the first page.