Spatial Attention Adapted to a LSTM Architecture with Frame Selection for Human Action Recognition in Videos

Abstract

Action recognition in videos is currently a topic of interest in the area of computer vision, due to potential applications such as: multimedia indexing, surveillance in public spaces, among others. In this work we propose an attention mechanism adapted to a CNN–LSTM base architecture. To carry out the training and testing phases, we used the HMDB-51 and UCF-101 datasets. We evaluate the performance of our system using accuracy as the evaluation metric, obtaining 57.3% and 90.4% for HMDB-51 and UCF-101 respectively.