E-React generates diverse two-person reaction motions conditioned on an actor's movement and a specified emotion using a learned Gaussian emotion prior inside a symmetrical actor-reactor diffusion model.
In 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), 1–8
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
E-React: Towards Emotionally Controlled Synthesis of Human Reactions
E-React generates diverse two-person reaction motions conditioned on an actor's movement and a specified emotion using a learned Gaussian emotion prior inside a symmetrical actor-reactor diffusion model.