The main research directions are machine vision, machine learning, deep learning, pattern recognition.
· Cross-modal Understanding and Reasoning
· Audio-Visual Event Understanding and Parsing
· Image/Video Captioning and Explanation
· Temporal Action Detection / Video Grounding
· Vison-based Sign Language Recognition and Translation)
· Vision-based Physiological Measurement
Characteristic research
· Visual Affective Computing
· Visual Sign Language Machine Translation
· Video Semantic Analysis and Grounding
· Visual Chatbot