InterventionLens: A Multi-Agent Framework for Detecting ASD Intervention Strategies in Parent-Child Shared Reading
This work addresses the costly and time-intensive reliance on expert annotation for analyzing ASD interventions in home settings, offering a scalable automated solution.
The paper tackles the problem of automatically detecting and segmenting caregiver intervention strategies in parent-child shared reading videos for children with autism spectrum disorder (ASD), achieving an overall F1 score of 79.44%, which outperforms the baseline by 19.72%.
Home-based interventions like parent-child shared reading provide a cost-effective approach for supporting children with autism spectrum disorder (ASD). However, analyzing caregiver intervention strategies in naturalistic home interactions typically relies on expert annotation, which is costly, time-intensive, and difficult to scale. To address this challenge, we propose InterventionLens, an end-to-end multi-agent system for automatically detecting and temporally segmenting caregiver intervention strategies from shared reading videos. Without task-specific model training or fine-tuning, InterventionLens uses a collaborative multi-agent architecture to integrate multimodal interaction content and perform fine-grained strategy analysis. Experiments on the ASD-HI dataset show that InterventionLens achieves an overall F1 score of 79.44\%, outperforming the baseline by 19.72\%. These results suggest that InterventionLens is a promising system for analyzing caregiver intervention strategies in home-based ASD shared reading settings. Additional resources will be released on the project page.