Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks

Understand

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for image recognition problems.

• Nevertheless, it is not trivial when utilizing a CNN for learning spatio-temporal video representation.
• A few studies have shown that performing 3D convolutions is a rewarding approach to capture both spatial and temporal dimensions in videos.
• However, the development of a very deep 3D CNN from scratch results in expensive computational cost and memory demand.