Action Recognition In Videos On Ava V2 2
评估指标
mAP (Val)
评测结果
各个模型在此基准测试上的表现结果
模型名称 | mAP (Val) | Paper Title | Repository |
|---|---|---|---|
| VideoMAE V2 | 18.24 | VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking | |
| YOWO+LFB* | 20.2 | You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization | - |
0 of 2 row(s) selected.