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).
|Journal||CEUR Workshop Proceedings|
|Publication status||Published - 2018|
|Event||2018 Working Notes Proceedings of the MediaEval Workshop, MediaEval 2018 - Sophia Antipolis, France|
Duration: 29 Oct 2018 → 31 Oct 2018
Scopus Subject Areas
- Computer Science(all)