Action Recognition on Ego-Exo4D Cooking (test)
55.74Top-1 AccuracyTIME + VideoMAEv2
Evaluation results
| Method | Links | ||
|---|---|---|---|
| TIME + VideoMAEv2Model Strategy=TIME + VideoMAEv2, Evaluation Protocol=Video Probing2026.05 | 55.74 | 12.78 | |
| TIME + V-JEPA 2Model Strategy=TIME + V-JEPA 2, Evaluation Protocol=Video Probing2026.05 | 48.52 | 13.96 | |
| TIME + CLIPModel Strategy=TIME + CLIP (4f), Number of frames=4f, Evaluation Protocol=Video Probing2026.05 | 43.27 | 17.28 | |
| TIME + DINOv3Model Strategy=TIME + DINOv3 (4f), Number of frames=4f, Evaluation Protocol=Video Probing2026.05 | 43.27 | 18.01 | |
| VideoMAEv2Model Strategy=VideoMAEv2, Evaluation Protocol=Video Probing2026.05 | 42.96 | — | |
| TIME + RVMModel Strategy=TIME + RVM, Evaluation Protocol=Video Probing2026.05 | 39.66 | 14.56 | |
| V-JEPA 2Model Strategy=V-JEPA 2, Evaluation Protocol=Video Probing2026.05 | 34.56 | — | |
| CLIPModel Strategy=CLIP (4f), Number of frames=4f, Evaluation Protocol=Video Probing2026.05 | 25.99 | — | |
| DINOv3Model Strategy=DINOv3 (4f), Number of frames=4f, Evaluation Protocol=Video Probing2026.05 | 25.26 | — | |
| RVMModel Strategy=RVM, Evaluation Protocol=Video Probing2026.05 | 25.1 | — | |
| TIMEModel Strategy=TIME (Ours), Evaluation Protocol=Video Probing2026.05 | 17.13 | — |