Jeremiah Fadugba
Jeremiah Fadugba
Home
Posts
Projects
Talks
Publications
CV
Light
Dark
Automatic
4
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.
V. S. Mfogo
,
Georgia Gkioxari
,
X. Chen
,
Jeremiah Fadugba (Jerofad)
Locally-Run Interpretable Breast Cancer Diagnosis from Histology Images
An interpretable, locally-run web app for classifying breast cancer histology images.
Jeremiah Fadugba (Jerofad)
,
O. Y. Sanni
,
M. O. Yekinni
Source Document
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.
V. S. Mfogo
,
X. Chen
,
Jeremiah Fadugba (Jerofad)
,
Georgia Gkioxari
Cite
×