Co-Attention Mechanism with Multi-Modal Factorized Bilinear Pooling for Medical Image Question Answering

Abstract

Explores a co-attention mechanism combined with multi-modal factorized bilinear pooling to fuse image and question representations for medical image question answering.

Jeremiah Fadugba (Jerofad)

Data Scientist | Machine Learning Engineer

My current research interests include Medical Imaging, Machine Learning, Deep Learning, and Trustworthy ML.