Self-Stimulatory Behaviours in the Wild for Autism Diagnosis

摘要: Autism Spectrum Disorders (ASD), often referred to as autism, are neurological disorders characterised by deficits in cognitive skills, social and communicative behaviours. A common way of diagnosing ASD is studying behavioural cues expressed the children. We introduce a new publicly-available dataset children videos exhibiting self-stimulatory (stimming) behaviours commonly used for autism diagnosis. These videos, posted parents/caregivers public domain websites, collected annotated stimming extremely challenging automatic behaviour analysis they recorded uncontrolled natural settings. The contains 75 with an average duration 90 seconds per video, grouped under three categories behaviours: arm flapping, head banging spinning. also provide baseline results tests conducted on this using standard bag words approach human action recognition. To best our knowledge, first attempt publicly making available Self-Stimulatory Behaviour Dataset (SSBD)