Multimodal News Story Segmentation
IHCI(2009)
摘要
In this paper, we describe a multi-modal approach to segmenting news video based on the perceived shift in content. We divide up a video document into logically coherent semantic units known as stories. We investigate the effectiveness of a number of multimedia features which serve as potential indicators of a story boundary. The results show an improvement of performance over current state of the art story segmenters.
更多查看译文
关键词
video segmentation,story detection.,feature extraction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要