Video Classification on HMDB-51 (val)
64.2Top-1 AccuracyTACO
Evaluation Results
| Method | Links | |
|---|---|---|
| TACOEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.06 | 64.2 | |
| MoTEEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.06 | 61.4 | |
| TACOEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.06 | 60 | |
| OTIEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.06 | 59.3 | |
| Open-VCLIPEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.06 | 59 | |
| DiSTEncoder=ViT-L/14, Frames=32, Zero-shot=true2026.06 | 57.5 | |
| MoTEEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.06 | 55.8 | |
| OSTEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.06 | 54.9 | |
| FROSTEREncoder=ViT-B/16, Frames=8, Zero-shot=true2026.06 | 54.8 | |
| Open-MeDeEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.06 | 54.6 | |
| Open-VCLIPEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.06 | 53.9 | |
| Text4VisEncoder=ViT-L/14, Frames=8, Zero-shot=true2026.06 | 52.4 | |
| MAXIEncoder=ViT-B/16, Frames=16/32, Zero-shot=true2026.06 | 52.3 | |
| ST-AdapterEncoder=ViT-B/16, Frames=8, Zero-shot=true2026.06 | 51.5 | |
| ViFi-CLIPEncoder=ViT-B/16, Frames=32, Zero-shot=true2026.06 | 51.3 | |
| Vita-CLIPEncoder=ViT-B/16, Frames=8/32, Zero-shot=true2026.06 | 48.6 | |
| X-FlorenceEncoder=Florence, Frames=32, Zero-shot=true2026.06 | 48.4 | |
| X-CLIPEncoder=ViT-B/16, Frames=32, Zero-shot=true2026.06 | 44.6 | |
| ActionCLIPEncoder=ViT-B/16, Frames=32, Zero-shot=true2026.06 | 40.8 |