| action-classification-on-charades | MViT-B-24, 32x3 (Kinetics-600 pretraining) | #10 | MAP: 47.7 |
| action-classification-on-charades | MViT-B, 32x3 (Kinetics-600 pretraining) | #12 | MAP: 47.1 |
| action-classification-on-charades | MViT-B-24, 32x3 (Kinetics-400 pretraining) | #13 | MAP: 46.3 |
| action-classification-on-charades | MViT-B, 32x3 (Kinetics-400 pretraining) | #16 | MAP: 44.3 |
| action-classification-on-charades | MViT-B, 16x4 (Kinetics-600 pretraining) | #18 | MAP: 43.9 |
| action-classification-on-charades | MViT-B, 16x4 (Kinetics-400 pretraining) | #24 | MAP: 40 |
| action-recognition-on-ava-v2-2 | MViT-B-24, 32x3 (Kinetics-600 pretraining) | #25 | mAP: 28.7 |
| action-recognition-on-ava-v2-2 | MViT-B, 32x3 (Kinetics-500 pretraining) | #27 | mAP: 27.5 |
| action-recognition-on-ava-v2-2 | MViT-B, 64x3 (Kinetics-400 pretraining) | #28 | mAP: 27.3 |
| action-recognition-on-ava-v2-2 | MViT-B, 32x3 (Kinetics-400 pretraining) | #30 | mAP: 26.8 |
| action-recognition-on-ava-v2-2 | MViT-B, 16x4 (Kinetics-600 pretraining) | #33 | mAP: 26.1 |
| action-recognition-on-ava-v2-2 | MViT-B, 16x4 (Kinetics-400 pretraining) | #34 | mAP: 24.5 |
| action-classification-on-kinetics-600 | MViT-B-24, 32x3 | #30 | Top-1 Accuracy: 83.8Top-5 Accuracy: 96.3 |
| action-classification-on-kinetics-600 | MViT-B, 32x3 | #33 | Top-1 Accuracy: 83.4Top-5 Accuracy: 96.3 |
| action-classification-on-kinetics-600 | MViT-B, 16x4 | #38 | Top-1 Accuracy: 82.1Top-5 Accuracy: 95.7 |
| action-recognition-in-videos-on-something-something-v2 | MViT-B-24, 32x3 | #46 | Top-1 Accuracy: 68.7Top-5 Accuracy: 91.5Parameters: 53.2M… |
| action-recognition-in-videos-on-something-something-v2 | MViT-B, 32x3(Kinetics600 pretrain) | #52 | Top-1 Accuracy: 67.8Top-5 Accuracy: 91.3Parameters: 36.6… |
| action-recognition-in-videos-on-something-something-v2 | MViT-B, 16x4 | #73 | Top-1 Accuracy: 66.2Top-5 Accuracy: 90.2 |
| action-classification-on-kinetics-400 | MViT-B, 64x3 | #79 | Acc@1: 81.2Acc@5: 95.1 |
| action-classification-on-kinetics-400 | MViT-B, 32x3 | #96 | Acc@1: 80.2Acc@5: 94.4 |
| action-classification-on-kinetics-400 | MViT-B, 16x4 | #118 | Acc@1: 78.4Acc@5: 93.5 |
| action-classification-on-kinetics-400 | MViT-S | #145 | Acc@1: 76Acc@5: 92.1 |
| image-classification-on-imagenet | MViT-B-24 | #304 | Top 1 Accuracy: 84.8%Number of params: 72.9MGFLOPs: 32.7 |
| image-classification-on-imagenet | MViT-B-16 | #508 | Top 1 Accuracy: 83.0%Number of params: 37MGFLOPs: 7.8 |