Towards learning emotional subspace

We introduce a model designed to predict emotional impact of movies through affective video content analysis. Specifically, our approach utilizes a two-stage learning framework, which first conducts subspace learning using emotion preserving embedding (EPE) or biased discriminant embedding (BDE) to uncover the informative subspace from the original feature space according to the continuous or discrete emotional labels, respectively, and then carries out the prediction utilizing the support vector machine (SVM). Experimentation on a movie dataset validates the effectiveness of our learning framework. Copyright held by the owner/author(s).