RoleNet: treat a movie as a small society

Chung-Yi Weng, Wei-Ta Chu, Ja-Ling Wu

Abstract: We present a brave new way to analyze movie content, from the perspectives of the relationships between roles rather than low-level audiovisual features. Interactions between roles in a movie resemble human behaviors in a society. Roles' actions lead the story and make viewers understand what directors want to present. In this paper, we introduce the idea of social network analysis to model the relationships of actors/actresses as a network, called RoleNet. Through analyzing this network, the proposed approach automatically determines the leading roles and the communities embedded in movies. We also describe an implementation framework to realize the proposed model. The experimental results show that the proposed methods can effectively capture social characteristics in movies. It's believed that this idea provides a different way to approach movie understanding.