| Benchmark | Model | Rank | Results |
|---|---|---|---|
| action-classification-on-moments-in-time | VTN | #9 | Top 1 Accuracy: 37.4Top 5 Accuracy: 65.4 |
| action-classification-on-kinetics-400 | ViT-B-VTN+ ImageNet-21K (84.0 [10]) | #100 | Acc@1: 79.8 |
| action-classification-on-kinetics-400 | ViT-B-VTN (3 layers, ImageNet pretrain) | #117 | Acc@1: 78.6Acc@5: 93.7 |
| action-classification-on-kinetics-400 | ViT-B-VTN+ ImageNet-21K (84.0 [10]) | #191 | Acc@5: 94.2 |
| action-classification-on-kinetics-400 | ViT-B-VTN (1 layer, ImageNet pretrain) | #193 | Acc@5: 93.4 |