A Novel Video Parsing Algorithm Utilizing the Pleasure-Arousal-Dominance Emotional Information

摘要

One of the major problems faced when designing a high level video parsing system is that viewers usually have doubts about the exact boundaries of an episode. Moreover, due to the different emotional states that viewers have while viewing a video, it is very difficult to improve the performance of these algorithms using convention methods. To solve this problem, this paper presents a novel spectral clustering based high level video parsing algorithm that utilizes the Pleasure-Arousal-Dominance (P-A-D) [1, 2] emotional content of the video.