Training dataset: A dataset containing the images and their corresponding ground-truth saliency maps and scan-paths, so you can train and tune your algorithms as necessary. Tools to appropriately parse the data are also provided.

To cite the dataset: H. Duan, G. Zhai, X. Min, Z. Che, Y. Fang, X. Yang, J. Gutiérrez, P. Le Callet, “A Dataset of Eye Movements for the Children with Autism Spectrum Disorder”, ACM Multimedia Systems Conference (MMSys’19), Jun. 2019.

You can download the datasets from here. If you have any questions please send an email to: