Multiple Feature Fusion Based on Co-Training Approach and Time Regularization for Place Classification in Wearable Video

<table>Effect of the filter size in temporal accumulation. Plot of the accuracy as a function of the TA filter size. (IDOL2 dataset, SPH Level 3 features).</table>

Advances in Multimedia

fig7

Figure 7

Figure 7: Multiple Feature Fusion Based on Co-Training Approach and Time Regularization for Place Classification in Wearable Video 