ViCo
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Listening Head Generation | ViCo | FD (Expression)15.67 | 8 | |
| Listener Facial Motion Generation | ViCo (test) | FD Expression72.88 | 7 | |
| listening head generation | ViCo (test) | FD (Exp)39.02 | 6 | |
| Text-to-image personalization | ViCo (test) | IDINO70 | 6 | |
| Audio-driven facial animation | ViCo | Lip Sync Acc4.164 | 5 | |
| Listener head generation | ViCo out-of-domain (D_ood) | FD (exp)12.67 | 5 | |
| Listener head generation | ViCo (D_test) | FD (Expression)11.54 | 5 | |
| Listener Head Generation | ViCo (test) | SSIM0.6 | 5 |
Showing 8 of 8 rows