Evaluating the Feasibility of Deep Learning for Action Recognition in Small Datasets
Juarez Monteiro, Roger Granada, Jotao Paulo Aires, Rodrigo Coelho Barros · 2018
Action recognition is the computer vision task of identifying what action is happening in a given sequence of frames. Traditional approaches rely on handcrafted features and domain-specific image processing algorithms, often resulting in limited accuracy. The substantial advances in deep learning and the availability of larger datasets have allowed techniques that yield much better performance without domain-specific knowledge to recognize actions being performed based on the raw information from video sequences, a strategy called representation learning. However, deep neural networks usually require very large labeled datasets for training and properly generalizing, and due to their high capacity, they often overfit small data, hence providing suboptimal results. This work aims to check the real feasibility of employing deep learning in the context of smallsized action recognition datasets. Our goal is to verify whether deep learning approaches can provide improved performance in cases in which labeled data is not abundant. In order to do so, we perform a thorough empirical analysis in which we investigate distinct network architectures with hyperparameter optimization, as well as different data pre-processing techniques and fusion methods.