Research Group

Research Orientation

The Faculty of Computer Science currently has three main research orientations: Knowledge Technology and Machine Learning, Natural Language Processing, and Computer Vision and Multimedia.

Knowledge Technology and Machine Learning

This research group focuses on the theoretical basis of Knowledge Technology, Knowledge Representation, and issues related to automated reasoning, thereby developing intelligent applications across various fields such as e-learning, e-government, and e-commerce.
Some representative research directions include:

  • Knowledge Representation and Reasoning.
  • Knowledge Bases, Expert Systems, Intelligent Problem Solving Systems.
    Knowledge Management Systems, Semantic Document Management.
  • Data Mining and Knowledge Discovery.
  • Some applications of the research group that have been applied in practice:
  • Automated reasoning systems for Euclidean geometry, spatial geometry, and analytical geometry.
  • Intelligent problem-solving systems in physics and chemistry.
  • Semantic-based learning resource management systems.
  • Information retrieval and aggregation systems based on semantics in online news.

Natural Language Processing

The Natural Language Processing research group is developing multiple research directions, both theoretical and applied, focusing on:

  • Syntax analysis.
  • Text summarization, question-answering systems.
  • Understanding and generating natural language.
  • Information retrieval and extraction.
  • Speech recognition and synthesis, etc.

Research is conducted through various approaches, based on formal computational methods and statistical machine learning theories.

Computer Vision and Multimedia

This research group addresses issues related to Computer Vision, Multimedia Content Analysis, Multimedia Information Retrieval, Virtual Reality & Augmented Reality, specifically:

  • Face detection, recognition, and searching in video.
  • Event detection in videos.
  • Detection of violent content in videos.
  • Image and video searching in large databases.
  • Image classification in large datasets.
  • Crowd behavior analysis through surveillance video.
  • Gesture recognition and action recognition in 2D and 3D videos.
  • Smart traffic systems (traffic monitoring, sign recognition, etc.).
  • Optical character recognition.