Main navigation
- Programs
- Subjects
- Universities
- Destinations
- Advice
Our research focuses on creating innovative machine learning techniques for computer vision and natural language processing to address challenges in today's data-driven environment. These solutions must efficiently train massive models, typically deep neural networks or extensive probabilistic systems, demanding novel algorithmic strategies and precise execution on advanced computing systems.
Our team possesses specialized knowledge across multiple domains, including autonomous vehicles and urban intelligence (such as video-based object recognition, sensor integration, attention models, visual-to-text conversion, environmental comprehension, multimodal video condensation, and vehicle positioning), healthcare technologies (like surgical image analysis, diabetic eye disease identification, and remote elderly care through imaging and sensor data), earth observation applications (including agricultural monitoring and environmental issue detection), and scientific text analysis through natural language processing.