The bag-of-visual-words (BOVW) approaches are widely used in human action recognition. Usually, large vocabulary size of the BOVW is more discriminative for inter-class action clas...
In this paper we propose an approach for action recognition based on a vocabulary forest of local motionappearance features. Large numbers of features with associated motion vecto...
3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...