Upcoming events

Regular countable second countable (CSC) spaces admit rather nice characterizations and can easily be formalized in second order arithmetic. It is natural to ask what set existence axioms are needed to ensure regular CSC spaces remain nice. It turns out many theorems which characterize regular CSC are equivalent to one of the big five subsystems of second order arithmetic.

In the era of increasing reliance on multimedia, accurately assessing image quality has become crucial for a wide range of applications, from entertainment to medical imaging. Saliency-based approaches, which stimulate human visual attention, provide powerful tools to bridge the gap between computational assessment and human perception. This talk explores the role of saliency in image and video quality assessment, highlighting state-of-the-art techniques that integrate saliency modelling with AI-driven quality assessment frameworks. I will demonstrate how these methods enhance the precision and reliability of quality assessments. The discussion will cover recent advancements, challenges, and future directions in the field.

Historical parchment scrolls are fragile, and consequently many such scrolls cannot be unrolled, so that their contents have remained hidden for centuries. I will describe several stages in the development of our method to perform a “virtual unrolling” of such documents from their X-ray tomographic scans. A critical element is the segmentation of the images in order to separate the parchment from the background, which is complicated by both holes in the parchment and the fusing of adjacent rolled layers. Since this causes standard segmentation algorithms to produce errors, we have devised several new algorithms to cope with such data. Once segmentation is achieved, the parchment is virtually flattened, and the ink density recovered to produce a reconstruction of the parchment surface. An example of our results are shown on the previously unseen fifteenth century Bressingham scroll.

Video analysis is a challenging task due to its high dimensionality and the complex, entangled spatio-temporal context. Applying this understanding to healthcare applications requires AI to align with humans’ expectations and values, i.e., making them responsible. In this seminar, I will introduce high-level geometric features, such as bounding boxes and human skeletal representations, for video analysis and explain how they reduce computational complexity, improve model generalizability, and facilitate the extraction of clinically relevant motion patterns. Furthermore, I will explore how incorporating geometric concepts enhances the interpretability, privacy, and fairness of deep learning models, fostering responsible AI. This is demonstrated through predicting Parkinson’s disease and cerebral palsy, as well as analyzing surgery videos.