2 papers
cs.CV2026
VAMAE: Vessel-Aware Masked Autoencoders for OCT Angiography
Ilerioluwakiiye Abolade, Prince Mireku, Kelechi Chibundu +4
Optical coherence tomography angiography (OCTA) provides non-invasive visualization of retinal microvasculature, but learning robust representations remains challenging due to spar…
cs.CL2025
AFRICAPTION: Establishing a New Paradigm for Image Captioning in African Languages
Mardiyyah Oduwole, Prince Mireku, Fatimo Adebanjo +3
Multimodal AI research has overwhelmingly focused on high-resource languages, hindering the democratization of advancements in the field. To address this, we present AfriCaption, a…