Mining Text and Visual Links to Browse TV Programs in a Web-Like Way

As the amount of recoded TV content is increasing rapidly, people need active and interactive browsing methods. In this paper, we use both text information from closed captions and visual information from video frames to generate links to enable one to explore not only the original video content but also augmented information from the Web. This solution especially shows its superiority when the video content cannot be well represented only by closed captions. A prototype system was implemented and some experiments were carried out to prove the effectiveness and efficiency.