Noun Recognition on Epic-Kitchens (EK)
44.07Top-1 AccX-MIC+DINO
Evaluation results
| Method | Links | ||
|---|---|---|---|
| X-MIC+DINOTemporal Attention=true, Trained on=Epic-Kitchens, Visual Encoder=CLIP + DINO2024.03 | 44.07 | 18.17 | |
| Vita-CLIPTemporal Attention=true, Trained on=Epic-Kitchens2024.03 | 34.41 | 14.91 | |
| CLIP-Adapter*Temporal Attention=true, Trained on=Epic-Kitchens2024.03 | 34.4 | 8.22 | |
| CLIP-AdapterTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 33.21 | 9.77 | |
| A5Temporal Attention=true, Trained on=Epic-Kitchens2024.03 | 32.04 | 5.99 | |
| X-MICTemporal Attention=true, Trained on=Epic-Kitchens2024.03 | 30.64 | 17.57 | |
| Co-CoOpTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 24.23 | 13.41 | |
| CoOpTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 21.56 | 13.06 | |
| X-MIC+DINOTemporal Attention=true, Trained on=Ego4D, Visual Encoder=CLIP + DINO2024.03 | 18.96 | 24.8 | |
| X-MICTemporal Attention=true, Trained on=Ego4D2024.03 | 15.35 | 21.06 | |
| CoOpTemporal Attention=false, Trained on=Ego4D2024.03 | 10.87 | 15.7 | |
| Vita-CLIPTemporal Attention=true, Trained on=Ego4D2024.03 | 10.61 | 16.11 | |
| CLIP-Adapter*Temporal Attention=true, Trained on=Ego4D2024.03 | 10 | 15.16 | |
| Co-CoOpTemporal Attention=false, Trained on=Ego4D2024.03 | 9.51 | 14.44 | |
| CLIP-AdapterTemporal Attention=false, Trained on=Ego4D2024.03 | 8.95 | 13.78 | |
| ZS CLIPTemporal Attention=false, Trained on=Zero-shot2024.03 | 8.74 | 7.03 | |
| A5Temporal Attention=true, Trained on=Ego4D2024.03 | 7.84 | 12.55 |