AI-empowered Multimedia Content Understanding and Generation

Lead  Prof. CHEN Changwen

Department of Computing

In recent years there has been an exponential growth in multimedia content and video understanding remains a fundamental challenge. The research team led by Prof. Chen Changwen have developed paradigm-shifting AI technologies that bridge computer vision, natural language processing and communications for understanding true semantics conveyed by visual data.

The research outcomes have become new benchmarks in visual computing, and helped share the advancement through open-source releases. Beyond scientific advances, these innovations have been successfully adopted for industrial-scale applications in collaboration with global tech leaders. For example, application to encyclopedia content production—delivering engaging knowledge to millions of users while saving more than HK$45M in production costs.

Discover More: Research Behind Impact