| Benchmark | Model | Rank | Results |
|---|---|---|---|
| action-recognition-in-videos-on-something-something-v2 | ST-Adapter (ViT-L, CLIP) | #24 | Top-1 Accuracy: 72.3Top-5 Accuracy: 93.9GFLOPs: 8248 |
| action-classification-on-kinetics-400 | ST-Adapter (ViT-L, CLIP) | #34 | Acc@1: 87.2Acc@5: 97.6 |