Multiple Feature Fusion Based on Co-Training Approach and Time Regularization for Place Classification in Wearable Video
Figure 9
Effect of supervision level on the CO-DAS performance and optimal parameters. (a) Accuracy for CO-DAS and single feature approaches. (b) Optimal amount of selected samples for the Co-Training feedback loop. (c) Selected DAS parameter for late fusion. (IDOL2 dataset, random setup).
