DAI Lab at MediaEval 2012 Affect Task: The Detection of Violent Scenes using Affective Features
We propose an approach to detect violence in movies at video shot level using low-level and mid-level features. We use audio energy, pitch and Mel-Frequency Cepstral Coefficients (MFCC) features to represent the affective audio content of movies. For the affective visual content, we extract average motion information. To learn a model for violence detection, we choose a discriminative classification approach and use a two-class support vector machine (SVM). Within this task, we investigate whether affect-related features provide good representation of violence and also whether making abstractions from low-level features are better than directly using low-level data for the task.