NII-UIT at MediaEval 2015 Affective Impact of Movies Task

Affective Impact of Movies task aims to detect violent videos and affective impact on viewers of that videos [9]. This is a challenging task not only because of the diversity of video content but also due to the subjectiveness of human emotion. In this paper, we present a unified framework that can be applied to both subtasks: (i) induce affect detection, and (ii) violence detection. This framework is based on our previous year’s Violent Scene Detection (VSD) framework. We extended it to support affect detection by training different valence/arousal classes independently and combine them to make the final decision. Besides using internal features from three different modalities: audio, image, and motion, in this year, we also incorporate deep learning features into our framework. Experimental results show that our unified framework can detect violent videos and its affective impact with a reasonable accuracy. Moreover, using deep features can significantly improve the detection performance of both subtasks.