Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,9 @@ pipeline_tag: other
|
|
| 14 |
|
| 15 |
# CaReDiff — Causal Reaction Diffusion (REACT 2026)
|
| 16 |
|
|
|
|
|
|
|
|
|
|
| 17 |
Model checkpoints for **CaReDiff**, a submission to the [REACT 2026 Challenge](https://sites.google.com/view/react2026/home) (ACM MM 2026, Multiple Appropriate Facial Reaction Generation).
|
| 18 |
|
| 19 |
Given speaker behaviour (audio, video, 3DMM coefficients, facial attributes), CaReDiff generates multiple appropriate listener facial reactions (25-d: 15 AUs + valence/arousal + 8 expressions) with an auxiliary EEG prediction head.
|
|
|
|
| 14 |
|
| 15 |
# CaReDiff — Causal Reaction Diffusion (REACT 2026)
|
| 16 |
|
| 17 |
+
|
| 18 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65fdba70f485b5180897c642/q5J2ScpexbMFlRiEllA4p.png" alt="react_challenge_figure" width="600">
|
| 19 |
+
|
| 20 |
Model checkpoints for **CaReDiff**, a submission to the [REACT 2026 Challenge](https://sites.google.com/view/react2026/home) (ACM MM 2026, Multiple Appropriate Facial Reaction Generation).
|
| 21 |
|
| 22 |
Given speaker behaviour (audio, video, 3DMM coefficients, facial attributes), CaReDiff generates multiple appropriate listener facial reactions (25-d: 15 AUs + valence/arousal + 8 expressions) with an auxiliary EEG prediction head.
|