Video Recognition on Kinetics-600 (test)
81.1AccuracyOpen-VCLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| Open-VCLIPEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.10 | 81.1 | |
| MoTEEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.10 | 78.4 | |
| DiSTEncoder=ViT-L/14, Frames=32, Protocol=Zero-shot2024.10 | 75 | |
| Open-VCLIPEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.10 | 73 | |
| Text4VisEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.10 | 72.1 | |
| MAXIEncoder=ViT-B/16, Frames=16/32, Protocol=Zero-shot2024.10 | 71.5 | |
| ViFi-CLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.10 | 71.2 | |
| OTIEncoder=ViT-L/14, Frames=8, Protocol=Zero-shot2024.10 | 70.6 | |
| MoTEEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.10 | 70.2 | |
| X-FlorenceEncoder=Florence, Frames=32, Protocol=Zero-shot2024.10 | 68.8 | |
| ActionCLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.10 | 67.7 | |
| Vita-CLIPEncoder=ViT-B/16, Frames=8/32, Protocol=Zero-shot2024.10 | 67.4 | |
| OTIEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.10 | 66.9 | |
| X-CLIPEncoder=ViT-B/16, Frames=32, Protocol=Zero-shot2024.10 | 65.2 | |
| ST-AdapterEncoder=ViT-B/16, Frames=8, Protocol=Zero-shot2024.10 | 60.2 |