A Novel Dataset for Video-Based Neurodivergent Classification Leveraging Extra-Stimulatory Behavior
This work addresses ASD classification for medical professionals by providing a more affordable video-based alternative to expensive MRI methods, though it is incremental as it focuses on dataset creation and basic testing.
The authors tackled the problem of classifying autism spectrum disorder (ASD) by introducing a new video-based dataset to capture behavioral differences, achieving effective generalization in understanding distinct movements in children. They also tested foundation models to highlight performance issues due to movement noise and data limitations.
Facial expressions and actions differ among different individuals at varying degrees of intensity given responses to external stimuli, particularly among those that are neurodivergent. Such behaviors affect people in terms of overall health, communication, and sensory processing. Deep learning can be responsibly leveraged to improve productivity in addressing this task, and help medical professionals to accurately understand such behaviors. In this work, we introduce the Video ASD dataset-a dataset that contains video frame convolutional and attention map feature data-to foster further progress in the task of ASD classification. Unlike many recent studies in ASD classification with MRI data, which require expensive specialized equipment, our method utilizes a powerful but relatively affordable GPU, a standard computer setup, and a video camera for inference. Results show that our model effectively generalizes and understands key differences in the distinct movements of the children. Additionally, we test foundation models on this data to showcase how movement noise affects performance and the need for more data and more complex labels.