Action Recognition on FineGym (val)
31.8Top-1 AccuracyTrackMAE
Evaluation results
| Method | Links | |
|---|---|---|
| TrackMAETarget=CLIP, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 31.8 | |
| SMILETarget=CLIP, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 30.2 | |
| SIGMATarget=DINO, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 30.1 | |
| TrackMAETarget=Pixel, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 29 | |
| MMETarget=HOG, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 29 | |
| MGMAETarget=Pixel, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 26.1 | |
| MGMTarget=Pixel, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 25.8 | |
| VideoMAETarget=Pixel, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 23.9 | |
| EVERESTTarget=Pixel, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 23.3 | |
| MVDTarget=Pixel, Evaluation Protocol=Linear probing, Backbone=ViT-B, Pre-trained Dataset=K4002026.03 | 22.7 |