作者: M. De Santo , G. Percannella , C. Sansone , M. Vento
DOI: 10.1007/11494683_40
关键词:
摘要: In this paper we propose an innovative combination strategy for a system using video and audio stream of news to automatically segment it into stories. our approach, the segmentation is performed in two steps: first, shots are classified by combining three different anchor shot detection algorithms information only. Then, classification improved novel method based on features extracted from track. Experimental results demonstrate that combined use allows perform better than approaches only terms both story segmentation.