UMons at MediaEval 2015 Affective Impact of Movies Task including Violent Scenes Detection

In this paper, we present the work done at UMons regarding
the MediaEval 2015 Affective Impact of Movies Task
(including Violent Scenes Detection). This task can be divided
into two subtasks. On the one hand, Violent Scene
Detection, which means automatically finding scenes that
are violent in a set if videos. And on the other hand, evaluate
the affective impact of the video, through an estimation
of the valence and arousal. In order to offer a solution for
both detection and classification subtasks, we investigate different
visual and auditory feature extraction methods. An
i-vector approach is applied for the audio, and optical
flow maps processed through a deep convolutional neural network
are tested for extracting features from the video. Classifiers
based on probabilistic linear discriminant analysis and fully
connected feed-forward neural networks are then used.