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