Table 3 Cross-validation results of different models under different data sets.
From: Basketball technique action recognition using 3D convolutional neural networks
Dataset | NTURGB + D Dataset | Basketball-Action-Dataset | B3D Dataset | |||
|---|---|---|---|---|---|---|
Evaluation metric | Accuracy | F1 score | Accuracy | F1 score | Accuracy | F1 Score |
MIFD-1 | 0.79 | 0.78 | 0.73 | 0.72 | 0.77 | 0.76 |
MIFD-2 | 0.71 | 0.70 | 0.75 | 0.74 | 0.79 | 0.78 |
MOF-1 | 0.78 | 0.77 | 0.72 | 0.71 | 0.76 | 0.75 |
MOF-2 | 0.70 | 0.79 | 0.74 | 0.73 | 0.78 | 0.77 |
CNN-1 | 0.92 | 0.91 | 0.87 | 0.86 | 0.91 | 0.90 |
CNN-2 | 0.89 | 0.88 | 0.83 | 0.82 | 0.87 | 0.86 |
