My current research mainly lies in the areas of machine learning and computer vision, with particular focus on developing models/methods that analyze structured data (usually Non-Euclidean and Non-Grid alike) by, for example, characterizing invariance and equivalence among them. Those types of data that I have coped with include but are not limited to:
Graphs: graph representation learning, graph neural networks;
Videos: motion representation learning, event captioning, image2video translation, action classification and detection, imitation learning from videos;
Subspaces: infinite Grassmannian (modeled by linear dynamical systems);