Visual Question Answering

Co-Attention Mechanism with Multi-Modal Factorized Bilinear Pooling for Medical Image Question Answering
A follow-up to our VQA-Med work, exploring co-attention and factorized bilinear pooling for fusing image and text representations in medical VQA.
Visual Question Answering in the Medical Domain (VQA-Med)
A project on visual question answering for medical images, combining vision and language models to answer clinical questions.