Action Recognition In Videos On Kinetics 400 1
评估指标
Top-1 Accuracy
Top-5 Accuracy
评测结果
各个模型在此基准测试上的表现结果
模型名称 | 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.