A Strict Pyramidal Deep Neural Network for Action Recognition

A human action recognition method is reported in which pose representation is based on the contour points of the human silhouette and actions are learned by a strict 3d pyramidal neural network (3DPyraNet) model which is based on convolutional neural networks and the image pyramids concept. 3DPyraNet extracts features from both spatial and temporal dimensions by keeping biological structure, thereby it is capable to capture the motion information encoded in multiple adjacent frames. One outlined advantage of 3DPyraNet is that it maintains spatial topology of the input image and presents a simple connection scheme with lower computational and memory costs compared to other neural networks. Encouraging results are reported for recognizing human actions in real-world environments.