Text-conditioned Video Prediction on EGO4D
301.7FVDSeer
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SeerEvaluation Mode=Zero-shot, Training Dataset=Something Something-V22023.03 | 301.7 | 0.55 | |
| VideoFusionEvaluation Mode=Zero-shot, Training Dataset=Something Something-V22023.03 | 618.6 | 1.85 |