Action Recognition on HMDB51 (train-test)
88.1Top-1 AccuracyVideoMAE V2
Evaluation Results
| Method | Links | |
|---|---|---|
| VideoMAE V2Evaluation Protocol=Non-interpretable2025.09 | 88.1 | |
| MoTIFBackbone=PE-G/142025.09 | 83 | |
| MoTIF-STBackbone=PE-G/142025.09 | 82.1 | |
| MoTIFBackbone=PE-L/142025.09 | 81.8 | |
| MoTIF-STBackbone=PE-L/142025.09 | 80.8 | |
| PE-G/14Evaluation Protocol=Global CBM, Backbone=G/142025.09 | 77.8 | |
| PE-L/14Evaluation Protocol=Global CBM, Backbone=L/142025.09 | 76.4 | |
| MoTIFBackbone=ViT-L/142025.09 | 76.1 | |
| MoTIF-STBackbone=ViT-L/142025.09 | 75.8 | |
| TSMEvaluation Protocol=Non-interpretable2025.09 | 73.5 | |
| No frame left behindEvaluation Protocol=Non-interpretable2025.09 | 73.4 | |
| CLIP-ViT-L/14Evaluation Protocol=Global CBM, Backbone=ViT-L/142025.09 | 71 | |
| MoTIFBackbone=ViT-B/322025.09 | 68.5 | |
| MoTIFBackbone=RN/502025.09 | 66.2 | |
| CLIP-ViT-B/32Evaluation Protocol=Global CBM, Backbone=ViT-B/322025.09 | 62.6 | |
| CLIP-RN/50Evaluation Protocol=Global CBM, Backbone=RN/502025.09 | 61.8 | |
| PE-G/14Evaluation Protocol=Zero-shot, Backbone=G/142025.09 | 60.7 | |
| PE-L/14Evaluation Protocol=Zero-shot, Backbone=L/142025.09 | 56.7 | |
| CLIP-ViT-L/14Evaluation Protocol=Zero-shot, Backbone=ViT-L/142025.09 | 45.7 | |
| CLIP-ViT-B/32Evaluation Protocol=Zero-shot, Backbone=ViT-B/322025.09 | 38.1 | |
| CLIP-RN/50Evaluation Protocol=Zero-shot, Backbone=RN/502025.09 | 29.8 |