Multimodal Violence Detection in Hollywood Movies: State-of-the-Art and Benchmarking

This paper introduces a benchmark evaluation targeting the detection of violent scenes in Hollywood movies. The evaluation was implemented in 2011 and 2012 as an affect task in the framework of the international MediaEval benchmark initiative. We report on these two years of evaluation, providing a detailed description of the dataset created, describing the state-of-the-art by studying the results achieved by participants and providing a detailed analysis of two of the best performing multimodal systems. We elaborate on the lessons learned after two years to provide insight on future work emphasizing multimodal modeling and fusion.