Action Recognition in the Frequency Domain
This addresses the problem of sensitivity to motion and viewpoint changes in action recognition for computer vision applications, but it is incremental as it applies an existing frequency-based approach to known features.
The paper tackles variability in temporal data for human action recognition by focusing on long-term frequency domain features, achieving good and robust results on the KTH Actions dataset with a simple forest classifier.
In this paper, we describe a simple strategy for mitigating variability in temporal data series by shifting focus onto long-term, frequency domain features that are less susceptible to variability. We apply this method to the human action recognition task and demonstrate how working in the frequency domain can yield good recognition features for commonly used optical flow and articulated pose features, which are highly sensitive to small differences in motion, viewpoint, dynamic backgrounds, occlusion and other sources of variability. We show how these frequency-based features can be used in combination with a simple forest classifier to achieve good and robust results on the popular KTH Actions dataset.