Research Article
Deep Ensemble Learning for Human Action Recognition in Still Images
Table 7
Results for DELVS in Li’s action dataset.
| | Model | Strategy | Sensitivity for each class | Overall | | Phoning | P.Guitar | R.Bike | R.Horse | Running | Shooting | Acc |
| | DELVS1 | Hard | 1 | 0.95 | 0.9 | 1 | 1 | 0.95 | 0.9667 | | Soft | 1 | 0.95 | 0.9 | 1 | 1 | 0.95 | 0.9667 | | Tuning | 1 | 1 | 0.9 | 0.95 | 1 | 1 | 0.975 |
| | DELVS2 | Hard | 1 | 0.95 | 0.95 | 1 | 1 | 0.95 | 0.975 | | Soft | 1 | 0.95 | 0.95 | 1 | 1 | 1 | 0.9833 | | Tuning | 1 | 1 | 0.95 | 1 | 1 | 1 | 0.9917 |
| | DELVS3 | Hard | 1 | 0.95 | 0.9 | 1 | 1 | 0.95 | 0.9667 | | Soft | 1 | 0.95 | 0.9 | 1 | 1 | 1 | 0.975 | | Tuning | 1 | 1 | 0.95 | 1 | 1 | 1 | 0.9917 |
|
|
