About the Project
GenV (Generalised Video Language Models through Alignment, Few-Shot Learning and Dynamic Ensembles) aims to uniquely study and reframe computer vision, advanced algorithmic search, and machine learning collectively via: a) Optimising Vision Language Models (VLMs) to better perform in recognizing human activities; b) Reducing the computational and data collection costs for training and deploying such models; c) Recognizing human motion and emotion across various scenarios and domains.
Project GenV is spearheaded by Institute of Digital Games, Malta and The Department of Artificial Intelligence, University of Malta and funded by Xjenza Malta.
Social Media