SST-Sal: A Spherical Spatio-Temporal Approach for Saliency Prediction in 360º Videos

Abstract

We present a deep learning approach to visual attention prediction in 360º videos. We resort to recurrent neural networks to model the inherent spatio-temporal features of visual behavior, while tailoring our model to the particularities of 360º content. Our model outperforms previous state-of-the-art works by a large margin.