An Extensible Deep Architecture for Action Recognition Problem
Isaac Wilfried Sanou, Donatello Conte, Hubert Cardot · 2019
Human action Recognition has been extensively addressed by deep learning. However, the problem is still open and many deep learning architectures show some limits, such as extracting redundant spatio-temporal informations, using hand-crafted features, and instability of proposed networks on different datasets. In this paper, we present a general method of deep learning for the human action recognition. This model fits on any type of database and we apply it on CAD-120 which is a complex dataset. Our model thus clearly improves in two aspects. The first aspect is on the redundant informations and the second one is the generality and the multi-functionality application of our deep architecture. Our model uses only raw data for human action recognition and the approach achieves state-of-the-art action classification performance. Figure 1: Pipline of human action recognition using deep learning method extracted from (TEIVAS, 2017). The upper box shows the training phase and the lower one the testing phase.