A new 150K-video 2D skeleton dataset with text captions and a diffusion model for single- and double-character motion generation, though the claimed FID-rewarded RL training is misrepresented.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Toward Rich Video Human-Motion2D Generation
A new 150K-video 2D skeleton dataset with text captions and a diffusion model for single- and double-character motion generation, though the claimed FID-rewarded RL training is misrepresented.