Identification of Narrative Peaks in Video Clips: Text Features Perform Best

A methodology is proposed to identify narrative peaks in video clips. Three basic clip properties are evaluated which reflect on video, audio and text related features in the clip. Furthermore, the expected distribution of narrative peaks throughout the clip is determined and exploited for future predictions. Results show that only the text related feature, related to the usage of distinct words throughout the clip, and the expected peak-distribution are of use when finding the peaks. On the training set, our best detector had an accuracy of 47% in finding narrative peaks. On the test set, this accuracy dropped to 24%.

• Type: Journal
• Year: 2009
• Where: CLEF
• Authors: Joep J. M. Kierkels, Mohammad Soleymani, Thierry Pun
• Keywords: Basic Clip Properties, CLEF 2009, Information Technology, Narrative Peaks, Text Related Feature