Dense interest features for video processing
Roeland De Geest, Tinne Tuytelaars · 2014
We propose two novel feature detection methods for action recognition, based on the dense interest points described by Tuytelaars [1]. The first one is an extension of dense interest points to three dimensions. In the second one, trajectories are constructed starting from dense interest points. We present an analysis of the properties of these methods and conclude that both give higher classification accuracies than dense sampling when less features are used.