Activity-Based Early Autism Diagnosis Using a Multi-Dataset Supervised Contrastive Learning Approach

Authors: Asha Rani & Yashaswi Verma

Venue: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 — CORE A

We propose a multi-dataset supervised contrastive learning framework for activity-based early diagnosis of Autism Spectrum Disorder. By leveraging activity videos across multiple datasets, the model learns discriminative representations that generalize across data distributions.

Presented at WACV 2024, Waikoloa, Hawaii.

[Paper]