Research
My research focuses on the theory and application of Deep Learning, Computer Vision, and Multimodal AI.
In fundamental research, I am particularly interested in creating intelligent algorithms that are both accurate and computationally efficient. In applied research, I am interested in bridging theory and real-world applications by leveraging various data modalities, including images, videos, and text.
Below are the main themes of my research. Each theme will be expanded with ongoing projects, datasets, and publications.
Research themes
-
Deep Learning for Computer Vision
Classical and modern deep learning methods for understanding visual data such as images and videos.
In preparation
-
Multimodal AI
Models that combine several modalities (image, text, possibly audio or video).
In preparation
-
Human Activity Recognition
In preparation