This is a deep network model. It features in bridging the “semantic gap” in predicting where people look.
Try it out!

Upload an image or choose one from below, and check out how our model predicts!

SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
X. Huang, C. Shen, X. Boix, and Q. Zhao
ICCV 2015