A dataset and framework that unifies two gesture corpora into HumanML3D format and demonstrates improved spatially controlled pointing gestures via fine-tuned OmniControl.
GestureDiffu- CLIP: Gesture diffusion model with CLIP latents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Grounded Gesture Generation: Language, Motion, and Space
A dataset and framework that unifies two gesture corpora into HumanML3D format and demonstrates improved spatially controlled pointing gestures via fine-tuned OmniControl.