Prediction of Human Eye Fixation by a Single Filter

Saliency modeling has played an important part in computer vision studies over the past 30 years. Many state-of-the-art models adopted complex mathematical and machine learning theories. In this paper, a simple and effective visual attention model is proposed. We find that a single fixed template is enough for saliency map generation; this idea is inspired by the receptive field of the human visual system. All that is needed is to convolve the input image with this template with additional post-processing. Experiments show that our model is extremely fast and performs better than state-of-the-art models in human eye fixation prediction.