Abstract:

News videos constitute a huge volume of daily information. It has become necessary to provide viewers with a concise and chronological view of various news themes through story dependency threading and topical documentary. This article presents techniques in threading and autodocumenting news stories according to topic themes. Initially, we perform story clustering by exploiting the duality between stories and textual-visual concepts through a coclustering algorithm. The dependency among stories of a topic is tracked by exploring the textual-visual novelty and redundancy of stories. A novel topic structure that chains the dependencies of stories is then presented to facilitate the fast navigation of the news topic. By pruning the peripheral and redundant news stories in the topic structure, a main thread is extracted for autodocumentary.

Figures:


Figure 1: Framework.


Figure 2: A graphical view of the main thread of the "Arkansas school shooting.

Reference:

  • Xiao Wu, Chong-Wah Ngo and Qing Li
    Threading and Autodocumenting News Videos
    IEEE Signal Processing Magazine, volume 23, issue 2, pp. 59-68, March 2006.
    Full Text: [PDF, 1.61M]