This project is to attach meaningful labels to videos by investigating novel video content analysis and machine learning techniques to facilitate visual information search.
Professor David Feng, Dr Zhiyong Wang.
N/A
With rapid growth of video data generated by a wide range of applications, it is increasingly crucial to provide users intelligent tools to efficiently access video data. Automatic Video Content Annotation is to generate meaningful video content representation to facilitate visual information search by exploring video shots, video objects and their attributes, events, and high level concepts (e.g, scenes and stories). This project aims to develop automated and efficient video content analysis by integrating techniques such as video segmentation, object extraction, story discovery, event detection, and novel machine learning.
The opportunity ID for this research opportunity is 322