Photo of Zhengjun Zha

Artificial intelligence & robotics

Zhengjun Zha

Overcoming the semantic gap and intention gap

Year Honored


In multimedia analysis and search, there exist two challenges: Semantic Gap and Intention Gap. The former refers to the gap between the underlying features of the image and high-level semantics, while the latter refers to the gap between the user’s intention and the expressed search request. But while they may have stumped other researchers, for Zhengjun Zha, they are quite “simple."

To address these gaps, Zhengjun published 3 different solutions: an image and video analysis method integrating context information, an image and video key retrieval technology based on user intention, and key technologies for image and video analysis and retrieval for complex queries.

These results have greatly contributed to the development of the multimedia analysis and search field. They can significantly improve the accuracy of content analysis and retrieval, while Zhengjun’s research on the intention gap can satisfy the user’s demand for complex information. All of these have a wide range of application potential.

With an extensive academic background, Zhengjun has a long list of titles: Professor at the School of Information Science and Technology at the University of Science and Technology of China, Research Fellow at the Chinese Academy of Sciences, and Deputy Director of China’s National Engineering Laboratory for Brain-inspired Intelligence Technology and Application. He has published over 100 papers, among them, 40 are ACM/IEEE conference papers or recognized as Class A conference papers by the Chinese Computer Society.

Going beyond academia, Zhengjun’s research is also being recognized by the industry and being used in iFlytek’s image search and audio surveillance products.