Researchers have developed a new 3D temporal analysis framework using DECA to screen for Autism Spectrum Disorder (ASD) in school-aged children. This method extracts detailed head pose and facial expression parameters, outperforming traditional 2D analysis. A GRU-based model achieved 83.9% accuracy using head pose features and 81.4% with facial features, with multimodal fusion reaching 84.6% accuracy. AI
IMPACT Establishes a foundation for objective, automated screening tools for ASD, potentially improving early diagnosis and intervention.
RANK_REASON The cluster contains an academic paper detailing a new methodology and benchmark results. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →