Video Recognition on UCF-101 (test)
88.7AccuracyMoTE
Evaluation Results
| Method | Links | |
|---|---|---|
| MoTEEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.10 | 88.7 | |
| OTIEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.10 | 88.1 | |
| Open-VCLIPEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.10 | 87.6 | |
| Open-VCLIPEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.10 | 83.4 | |
| MoTEEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.10 | 83.4 | |
| OTIEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.10 | 83.3 | |
| Text4VisEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.10 | 82.6 | |
| MAXIEncoder=ViT-B/16, Frames=16/32, Protocol=Zero-shot2024.10 | 78.2 | |
| ST-AdapterEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.10 | 76.9 | |
| ViFi-CLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.10 | 76.8 | |
| Vita-CLIPEncoder=ViT-B/16, Frames=8/32, Protocol=Zero-shot2024.10 | 75 | |
| DiSTEncoder=ViT-L/14, Frames=32, Protocol=Zero-shot2024.10 | 74.9 | |
| X-FlorenceEncoder=Florence, Frames=32, Protocol=Zero-shot2024.10 | 73.2 | |
| X-CLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.10 | 72 | |
| A5Encoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.10 | 69.3 | |
| ActionCLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.10 | 58.3 |