Abstract
Autism spectrum disorder (ASD) is one of the common diseases that affects the language and even the behavior of the subjects. Since the large variations in the symptoms and severities of ASD, the diagnosis becomes a challenging problem. It has been witnessed that deep neural networks have been widely used and achieve good performance in various applications of visual data analysis. In this paper, we propose SP-ASDNet which utilizes both convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to classify whether an observer is typical developed (TD) or has ASD, based on the scanpath of the corresponding observer's gaze at the given image. The proposed SP-ASDNet is submitted to 2019 Saliency4ASD grand challenge and achieves 74.22% accuracy for validation.
