JihoonChoi commited on
Commit
25d4f36
·
verified ·
1 Parent(s): 2e6dc6d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
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.