Action Classification on Kinetics 600 (test)
90.3Top-1 AccMTV-H
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MTV-HIn-house labeled data=WTS, Resolution=280^2, Views=4 x 3, TFLOPs=73.572023.03 | 90.3 | 98.5 | |
| VideoMAE V2-gResolution=64 x 266^2, Views=2 x 3, TFLOPs=160.32023.03 | 89.9 | 98.5 | |
| VideoMAE V2-HResolution=32 x 384^2, Views=4 x 3, TFLOPs=184.242023.03 | 89.6 | 98.4 | |
| MTV-HIn-house labeled data=WTS, Views=4 x 3, TFLOPs=44.472023.03 | 89.6 | 98.3 | |
| VideoMAE V2-gViews=5 x 3, TFLOPs=38.162023.03 | 88.8 | 98.2 | |
| MaskFeatResolution=312p, Views=3 x 4, TFLOPs=33.942023.03 | 88.3 | 98 | |
| VideoMAE V2-HViews=5 x 3, TFLOPs=17.882023.03 | 88.3 | 98.1 | |
| MViTv2-LResolution=352p, Views=3 x 4, TFLOPs=45.482023.03 | 87.9 | 97.9 | |
| CoVeRIn-house labeled data=JFT-3B, Views=1 x 32023.03 | 87.9 | 97.8 | |
| MaskFeatViews=1 x 10, TFLOPs=3.772023.03 | 86.4 | 97.4 | |
| MViTv2-BViews=1 x 5, TFLOPs=1.032023.03 | 85.5 | 97.2 | |
| MViT-BViews=3 x 3, TFLOPs=4.12023.03 | 83.8 | 96.3 | |
| MTV-BViews=4 x 3, TFLOPs=4.792023.03 | 83.6 | 96.1 | |
| ViViT-L FEViews=1 x 3, TFLOPs=11.942023.03 | 82.9 | 94.6 | |
| TimeSformer-LViews=1 x 3, TFLOPs=7.142023.03 | 82.2 | 95.6 | |
| SlowFast R101-NLViews=10 x 3, TFLOPs=7.022023.03 | 81.8 | 95.1 |