Noun Recognition on Ego4D
35.85Top-1 AccX-MIC+DINO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| X-MIC+DINOTemporal Attention=true, Trained on=Ego4D, Visual Encoder=CLIP + DINO2024.03 | 35.85 | 24.8 | |
| X-MICTemporal Attention=true, Trained on=Ego4D2024.03 | 33.54 | 21.06 | |
| Vita-CLIPTemporal Attention=true, Trained on=Ego4D2024.03 | 33.52 | 16.11 | |
| A5Temporal Attention=true, Trained on=Ego4D2024.03 | 31.39 | 12.55 | |
| CLIP-Adapter*Temporal Attention=true, Trained on=Ego4D2024.03 | 31.26 | 15.16 | |
| Co-CoOpTemporal Attention=false, Trained on=Ego4D2024.03 | 30 | 14.44 | |
| CLIP-AdapterTemporal Attention=false, Trained on=Ego4D2024.03 | 30 | 13.78 | |
| CoOpTemporal Attention=false, Trained on=Ego4D2024.03 | 28.22 | 15.7 | |
| X-MICTemporal Attention=true, Trained on=Epic-Kitchens2024.03 | 12.32 | 17.57 | |
| X-MIC+DINOTemporal Attention=true, Trained on=Epic-Kitchens, Visual Encoder=CLIP + DINO2024.03 | 11.45 | 18.17 | |
| Vita-CLIPTemporal Attention=true, Trained on=Epic-Kitchens2024.03 | 9.52 | 14.91 | |
| CoOpTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 9.37 | 13.06 | |
| Co-CoOpTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 9.27 | 13.41 | |
| ZS CLIPTemporal Attention=false, Trained on=Zero-shot2024.03 | 5.89 | 7.03 | |
| CLIP-AdapterTemporal Attention=false, Trained on=Epic-Kitchens2024.03 | 5.73 | 9.77 | |
| CLIP-Adapter*Temporal Attention=true, Trained on=Epic-Kitchens2024.03 | 4.67 | 8.22 | |
| A5Temporal Attention=true, Trained on=Epic-Kitchens2024.03 | 3.31 | 5.99 |