For my undergraduate, I studied Computer Science at The University of Salford. It was here I developed an interest in computer vision. For my final year project I developed an image captioning system similar to Facebook’s Automatic Alt Text generator.
Upon completion of my undergraduate I moved to The University of Liverpool to study on their MSc in Advanced Computer Science course, where I further specialised in machine learning. For my masters thesis I developed a 3D object detection system that fused both 2D image inputs and LiDAR data. Building on recent developments in the field, it implemented a Graph Neural Network to process the LiDAR data and predict object bounding boxes.
I’m currently a first year PhD student at Queen Mary University London supervised by Dr Luca Rossi and Greg Slabaugh. My PhD is in computer vision and I am investigating how Graph Neural Networks can be used to further develop scene understanding. This work focusses on the application of GNNs to vision tasks like image captioning and visual question answering (VQA).