An improved valence-arousal emotion space for video affective content representation and recognition

To understand video affective content automatically, the primary task is to transform the abstract concept of emotion into the form which can be handled by the computer easily. An improved V-A emotion space is proposed to address this problem. It unifies the discrete and dimensional emotion model by introducing the typical fuzzy emotion subspace. Fuzzy C-mean clustering (FCM) algorithm is adopted to divide the V-A emotion space into the subspaces and Gaussian mixture model (GMM) is used to determine their membership functions. Based on the proposed emotion space, the maximum membership principle and the threshold principle are introduced to represent and recognize video affective content. A video affective content database is created to validate the proposed model. The experimental results show that the improved emotion space can be used as a solution to represent and recognize video affective content.