Visualizing Gaze Direction to Support Video Coding of Social Attention for Children with Autism Spectrum Disorder

This paper presents a novel interface to support video coding of social attention in assessment for children with Autism Spectrum Disorder. Video-based evaluation of social attention in therapeutic activity poses efforts for observers to find target behaviors while handling the ambiguity of attention. Despite the recent advances in computer vision-based gaze estimation methods, fully automatic recognition of social attention under diverse environments is still challenging. The goal of this work is to investigate an approach using automatic video analysis in a supportive manner for guiding human judgement. The proposed interface displays visualization of gaze estimation results on videos, and provides GUI supports to allow users to define social attention labels in the video timeline for facilitating agreements within observers. Throughout user studies and expert reviews, we show how the interface helps observers to perform video coding of social attention and how it can be improved for more efficient support.