A hierarchical multi-modal approach to story segmentation in news video

Abstract

This research presents a multi-modal two-level framework for news story segmentation. We divide our system into two levels: shot level that classifies the input video shots into one of the predefined categories using a hybrid of heuristic and learning based approaches; and story level that performs story segmentation using two different machine-learning approaches based on the output of shot level and other temporal features. The first machine-learning approach employs a statistical method called Hidden Markov Models (HMM) whereas the second approach uses a rule induction technique. We test the two approaches on over 120 hours of news video provided by TRECVID 2003. The results show that we could achieve an accuracy of over 77% for the HMM framework and over 75% for the rule induction approach. The results demonstrate that our 2-level machine-learning framework is effective and is adequate to cope with large scale practical problems.