Press Enter to search, or Escape to close.
Faculty, researchers, and students working together at MHUG.
Computer Vision
Vision and Language, Motion Understanding, Video Understanding
Learning on hyperbolic space
Open-world visual perception
Geometric Deep Learning
Image Generation
Vision and Language
Video and Language
Video Generation
Novel Class Discovery
Few-Shot Learning
Compositional Generalization
TinyML
Continual Learning
Generative Models
Multimodal Generation
Physics-Based Deep Learning
Vision and Language, Large Multimodal Models, Video Understanding
Interpretability
Autonomous Driving
Motion & Language
Tracking, Vison and Language
Sign Language Video Generation
Brain-to-image Decoding
Image Segmentation
University of Electronic Science and Technology of China
FBK
