Verb Recognition on Epic-Kitchens (EK)
53.02Top-1 AccX-MIC+DINO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| X-MIC+DINOTemporal Attention=true, Trained on=Epic-Kitchens, Visual Encoder=CLIP + DINO2024.03 | 53.02 | 24.6 | |
| X-MICTemporal Attention=true, Trained on=Epic-Kitchens2024.03 | 50.01 | 26.58 | |
| Vita-CLIPTemporal Attention=true, Trained on=Epic-Kitchens2024.03 | 48.78 | 21.11 | |
| CLIP-Adapter*Temporal Attention=true, Trained on=Epic-Kitchens2024.03 | 48.69 | 23.54 | |
| A5Temporal Attention=true, Trained on=Epic-Kitchens2024.03 | 46.05 | 25.81 | |
| CLIP-AdapterTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 36.7 | 22.37 | |
| Co-CoOpTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 34.16 | 20.03 | |
| CoOpTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 30.91 | 18.64 | |
| X-MIC+DINOTemporal Attention=true, Trained on=Ego4D, Visual Encoder=CLIP + DINO2024.03 | 29.49 | 28.86 | |
| X-MICTemporal Attention=true, Trained on=Ego4D2024.03 | 26.48 | 27.65 | |
| Vita-CLIPTemporal Attention=true, Trained on=Ego4D2024.03 | 25.81 | 24.13 | |
| A5Temporal Attention=true, Trained on=Ego4D2024.03 | 22.77 | 24.41 | |
| CLIP-Adapter*Temporal Attention=true, Trained on=Ego4D2024.03 | 22.28 | 24.54 | |
| CoOpTemporal Attention=false, Trained on=Ego4D2024.03 | 20.42 | 21.44 | |
| CLIP-AdapterTemporal Attention=false, Trained on=Ego4D2024.03 | 19.94 | 21.28 | |
| Co-CoOpTemporal Attention=false, Trained on=Ego4D2024.03 | 12.99 | 16.14 | |
| TARAZero-shot=true2025.12 | 6.1 | — | |
| ZS CLIPTemporal Attention=false, Trained on=Zero-shot2024.03 | 4.25 | 2.88 | |
| CaReZero-shot=true2025.12 | 3.6 | — | |
| CLIPZero-shot=true2025.12 | 1.8 | — | |
| DINO.txtZero-shot=true2025.12 | 1.4 | — | |
| ChanceZero-shot=true2025.12 | 0.03 | — |