Affective Level Video Segmentation by Utilizing the Pleasure-Arousal-Dominance Information

In this paper, we offer an entirely new view to the problem of high level video parsing. We developed a novel computation method for affective level video segmentation. Its function was to extract emotional segments from videos. Its design was based on the pleasure-arousal-dominance (P-A-D) model of affect representation , which in principle can represent a large number of emotions. Our method had two stages. The first P-A-D estimation stage was defined within framework of the dynamic Bayesian networks (DBNs). A spectral clustering algorithm was applied in the final stage to determine the emotional segments of the video. The performance of our method was compared with the time adaptive clustering (TAC) algorithm and an accelerated version of it which we had developed. According to Vendrig , the TAC algorithm was the best segmentation method. Experiment results will show the feasibility of our method.