Salicon Dataset

• “10,000 images for training and 5000 images for validation”
• “Each image was viewed by 60 observers”
• this dataset Different from other fixation datasets, is large-scale mouse-tracking data through Amazon Mechanical Turk
• Although this dataset is not the fixation dataset, it is well known that the distribution of mouse tracking points is similar to the distribution of fixations and that the parameters of the model trained on Salicon dataset are useful for saliency map estimation