Action Recognition on SSv2 (train-test)
76.8Top-1 AccuracyVideoMAE V2
Evaluation Results
| Method | Links | |
|---|---|---|
| VideoMAE V2Evaluation Protocol=Non-interpretable2025.09 | 76.8 | |
| No frame left behindEvaluation Protocol=Non-interpretable2025.09 | 62.7 | |
| TSMEvaluation Protocol=Non-interpretable2025.09 | 61.7 | |
| MoTIF-STBackbone=PE-G/142025.09 | 41.9 | |
| MoTIFBackbone=PE-G/142025.09 | 40.4 | |
| MoTIF-STBackbone=PE-L/142025.09 | 39.6 | |
| MoTIFBackbone=PE-L/142025.09 | 37.3 | |
| PE-G/14Evaluation Protocol=Global CBM, Backbone=G/142025.09 | 33.6 | |
| PE-L/14Evaluation Protocol=Global CBM, Backbone=L/142025.09 | 31.3 | |
| MoTIF-STBackbone=ViT-L/142025.09 | 27.7 | |
| MoTIFBackbone=ViT-L/142025.09 | 25.8 | |
| CLIP-ViT-L/14Evaluation Protocol=Global CBM, Backbone=ViT-L/142025.09 | 22 | |
| MoTIFBackbone=ViT-B/322025.09 | 20.7 | |
| MoTIFBackbone=RN/502025.09 | 20 | |
| CLIP-ViT-B/32Evaluation Protocol=Global CBM, Backbone=ViT-B/322025.09 | 18.2 | |
| CLIP-RN/50Evaluation Protocol=Global CBM, Backbone=RN/502025.09 | 17 | |
| PE-L/14Evaluation Protocol=Zero-shot, Backbone=L/142025.09 | 2.2 | |
| PE-G/14Evaluation Protocol=Zero-shot, Backbone=G/142025.09 | 2.2 | |
| CLIP-ViT-B/32Evaluation Protocol=Zero-shot, Backbone=ViT-B/322025.09 | 0.9 | |
| CLIP-ViT-L/14Evaluation Protocol=Zero-shot, Backbone=ViT-L/142025.09 | 0.9 | |
| CLIP-RN/50Evaluation Protocol=Zero-shot, Backbone=RN/502025.09 | 0.8 |