School of Computer Science and Statistics
BLIP-2 is a system which can create image captions from pictures. CLIP is a system which can compare captions to pictures allowing us to choose images from a dataset based on how well the captions match. This project is intended to look more deeply at this field and compare this approach to other image retrieval … Read more
Ever wondered who is related to who? Well some computer vision researchers have tried to determine this automatically and this project aims to investigate the area and hopefully come up with something new. The concept for this project is drawn from the paper “Kinship Verification with Custom Sampling and Hard Contrastive Loss” from VISAPP 2026 (See … Read more
This project is intended to develop a system which would use publicly available webcams, evaluate the current weather and automatically compare the current weather (e.g. precipitation, wind, sunshine) with the forecasted conditions (from various weather forecasting services). In this way we could get metrics on how well the different weather prediction services work!! The concept … Read more
Classifying dance style is an interesting problem and some work has been done using just video. I’m curious to know if we could use clothing classification and music recognition to help… The concept for this project is drawn from the paper “Dance Style Classification using Laban-Inspired and Frequency-Domain Motion Features” which was presented in VISAPP … Read more
Over the years I have found that many students who propose their own projects using computer vision have been very successful – probably because they are strongly motivated by the subject matter. So if you have an idea for a project in a field which interests you please contact me. The biggest issues are usually … Read more
Can we tell something about a person from the way they move, even when their appearance has been completely changed? In this project, the student will use selected interactions from Meta’s Seamless Interaction dataset to create animated MetaHuman characters in Unreal Engine 5. Real conversational motion will be transferred onto virtual characters whose appearance differs … Read more
Eye gaze plays a fundamental role in face-to-face communication, signalling attention, engagement, turn-taking and social intent. However, gaze is often studied from the perspective of only one participant. This project will create a new dataset of synchronised eye movements from pairs of people engaged in natural social interactions, using two wearable Pupil Labs eye-tracking headsets. … Read more
Recent advances in generative AI make it possible to realistically transform both a person’s face and voice while preserving their underlying behaviour. This project will develop an interactive AI virtual mirror in which participants see their face transformed into another photorealistic identity while their own facial expressions and head movements drive the generated face. The … Read more
There is no excerpt because this is a protected post.
Multimodal Learning for DeepFake Detection In recent years, the rise of deepfakes—videos that are digitally altered using artificial intelligence (AI) to convincingly depict false events or individuals has sparked significant concerns about the reliability of visual content captured by surveillance systems. This project is driven by the recognition that traditional methods of detecting video manipulation … Read more