Video Classification on EPIC-KITCHENS 100
70.7Verb AccuracyMTCN
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MTCNModality=Multi-modal2022.01 | 70.7 | 62.1 | 49.6 | |
| OMNIVORE (Swin-B)Modality=RGB-only2022.01 | 69.5 | 61.7 | 49.9 | |
| ORVITModality=RGB-only2022.01 | 68.4 | 58.7 | 45.7 | |
| VideoSwin-BModality=RGB-only2022.01 | 67.8 | 57 | 46.1 | |
| MFormer-LModality=RGB-only2022.01 | 67.1 | 57.6 | 44.1 | |
| ViViT-LModality=RGB-only2022.01 | 66.4 | 56.8 | 44 | |
| TARModality=RGB-only2022.01 | 66 | 53.4 | 45.3 | |
| SlowFastModality=RGB-only2022.01 | 65.6 | 50 | 38.5 |