Action Recognition In Videos On Kinetics 400 1
評価指標
Top-1 Accuracy
Top-5 Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Top-1 Accuracy | Top-5 Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| Florence | 86.5 | 97.3 | Florence: A New Foundation Model for Computer Vision | |
| ActionCLIP (ViT-B/16) | 83.8 | - | ActionCLIP: A New Paradigm for Video Action Recognition | |
| Frozen Backbone, SwinV2-G-ext22K (Video-Swin) | 81.7 | - | Could Giant Pretrained Image Models Extract Universal Representations? | - |
0 of 3 row(s) selected.