Multimodal Deep Generative Models for Remote Medical Applications
Keywords:Biometrics, Thermal, Facial Emotion Recognition, Generative Adversarial Network, Multimodal Machine Learning
AbstractVisible-to-Thermal (VT) face translation is an under-studied problem of image-to-image translation that offers an AI-enabled alternative to traditional thermal sensors. Over three phases, my Doctoral Proposal explores developing multimodal deep generative solutions that can be applied towards telemedicine applications. These include the contribution of a novel Thermal Face Contrastive GAN (TFC-GAN), exploration of hybridized diffusion-GAN models, application on real clinical thermal data at the National Institutes of Health, and exploration of strategies for Federated Learning (FL) in heterogenous data settings.
How to Cite
Ordun, C. (2023). Multimodal Deep Generative Models for Remote Medical Applications. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16127-16128. https://doi.org/10.1609/aaai.v37i13.26924
AAAI Doctoral Consortium Track