Publication

Abstract : Multimedia event recognition is one of the most important tasks with a wide range of applications from individual to group events. The standard literature on video event recognition relies on visual modality and does not consider the relevant information in the audio modality. In this paper, we present a comprehensive analysis of the state-of-the-art methods available to fuse audiovisual information for successful recognition. Then, we analyze the different types of audiovisual features and modeling techniques involved in different multimedia event recognition applications. We also provide a summary of audiovisual fusion systems and identify future directions.