Skeleton-Based Activity Recognition for Children with Autism Using Graph Convolutional Networks
Preprint
- 24 June 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Movement-based and physical activity programs are central tools in autism intervention, so recognizing the activities a child performs during therapy is valuable for objective progress tracking. Manual monitoring of these sessions is time-consuming and subjective, and raw video raises privacy concerns because it shows identifiable children. We address autism therapy activity recognition from privacy-preserving 2D skeletons, and we focus on the practical difficulty that several therapy activities differ only in subtle motion details. As a backbone we adopt ProtoGCN, a graph convolutional network that represents each action as a combination of learnable motion prototypes. This contrastive backbone organizes all classes at once, however, so it does not enforce a margin between the few pairs that remain entangled after training. We therefore introduce a Refine-Confusable (RC) module, a training-only regularizer that pushes apart the empirically most-confused class pairs using a hinge-margin loss over momentum-updated class centroids. The module changes neither the backbone nor the inference cost. On the MMASD dataset restricted to the ten-class 2D-skeleton configuration, the RC module improves the base model under both splitting regimes, with a gain of 1.21 points of pooled accuracy on the stricter subject-independent split. Under the protocol-matched holdout it reaches 96.30% accuracy with 0.959 macro-F1, which surpasses recent 2D-skeleton baselines while it keeps a lightweight and privacy-preserving modality. A per-fold analysis shows that this gain is consistent across folds rather than tied to a single split, and t-SNE and prototype visualizations show that the learned representation is discriminative and interpretable.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Modeling the Heterogeneous Movements of ASD via Fine-Grained Skeleton Representation LearningIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2026
- Improving Early Detection of Learning Disabilities Using Graph Convolutional Networks (GCN) and Multi-Modal DataInternational Journal of Artificial Intelligence and Machine Learning, 2026
- Early Diagnosis of Autism: A Review of Video-Based Motion Analysis and Deep Learning TechniquesIEEE Access, 2025
- ARAIS-Activity Recognition of Autism Children During Intervention Sessions2024
- Physics Augmented Tuple Transformer for Autism Severity-Level DetectionIEEE Sensors Journal, 2024
- Early Diagnosis of Autism Spectrum Disorder: A Review and Analysis of the Risks and BenefitsCureus, 2023
- Evaluation of an artificial intelligence-based medical device for diagnosis of autism spectrum disordernpj Digital Medicine, 2022
- Using 2D video-based pose estimation for automated prediction of autism spectrum disorders in young childrenScientific Reports, 2021
- The DREAM Dataset: Supporting a data-driven study of autism spectrum disorder and robot enhanced therapyPLOS ONE, 2020
- Improving Physical Fitness in Individuals with Autism Spectrum with Game Console Physical Activity ProgramJournal of Physical Education and Sports Studies, 2019