Action Recognition on Ego-Exo4D Cooking
55.74Top-1 AccuracyTIME + VideoMAEv2
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TIME + VideoMAEv22026.05 | 55.74 | 12.78 | |
| TIME + V-JEPA 22026.05 | 48.52 | 13.96 | |
| TIME + CLIPframes=4f2026.05 | 43.27 | 17.28 | |
| TIME + DINOv3frames=4f2026.05 | 43.27 | 18.01 | |
| TIME + RVM2026.05 | 39.66 | 14.56 |