| action-classification-on-charades | TubeViT-L | #2 | MAP: 66.2 |
| action-classification-on-kinetics-400 | TubeViT-H (ImageNet-1k) | #4 | Acc@1: 90.9Acc@5: 98.9FLOPs (G) x views: 176400x4x3… |
| action-classification-on-kinetics-400 | TubeVit-L (ImageNet-1k) | #7 | Acc@1: 90.2Acc@5: 98.6FLOPs (G) x views: 95300x4x3… |
| action-classification-on-kinetics-400 | TubeVit-B (ImageNet-1k) | #19 | Acc@1: 88.6Acc@5: 97.6FLOPs (G) x views: 8700x3x4… |
| action-classification-on-kinetics-600 | TubeVit-H | #2 | Top-1 Accuracy: 91.8Top-5 Accuracy: 98.9 |
| action-classification-on-kinetics-600 | TubeVit-L | #4 | Top-1 Accuracy: 91.5Top-5 Accuracy: 98.7 |
| action-classification-on-kinetics-600 | TubeVit-B | #6 | Top-1 Accuracy: 90.9Top-5 Accuracy: 97.3 |
| action-classification-on-kinetics-700 | TubeViT-L | #4 | Top-1 Accuracy: 83.8Top-5 Accuracy: 96.6 |
| action-recognition-in-videos-on-something | TubeViT-L | #8 | Top-1 Accuracy: 76.1Top-5 Accuracy: 95.2 |