Violence Video Detection by Discriminative Slow Feature Analysis

Nowadays, Internet makes it easy for us to share all kinds of information. However, violent content in web has harmful influence on those who lack proper judgment, especially teenagers. This paper presents an approach for detecting violence in videos, where Discriminative Slow Feature Analysis (D-SFA) is introduced to learn slow feature functions from dense trajectories derived from videos. Afterwards, with the learnt slow feature functions, the Accumulated Squared Derivative (ASD) features are extracted to represent videos. Finally, a linear support vector machine (SVM) is trained for classification. We also construct a Violence Video (VV) dataset which includes 200 violence samples and 200 non-violence samples collected from Internet and movies. The experimental results on the newly established dataset demonstrate the effectiveness of the proposed method.