Using visual attention estimation on videos for automated prediction of autism spectrum disorder and symptom severity in preschool children
Fig 1
Overview of the proposed feature learning/extraction, classification and symptom severity prediction approach.
(a) Given a video input, per-frame features are learned using an end-to-end approach to predict the difference of fixation (DoF) maps. (b) Extracted features at fixated pixels from each fixation stage are cascaded and passed on to an SVM to identify individuals with ASD and predict the level of ASD-related symptoms.