Identification of Emergent Leaders in a Meeting Scenario Using Multiple Kernel Learning

In this paper, an eective framework for detection of emer- gent leaders in small group is presented. In this scope, the combination of dierent types of nonverbal visual features; the visual focus of attention, head activity and body activity based features are utilized. Using them together ensued sig- nicant results. For the rst time, multiple kernel learning (MKL) was applied for the identication of the most and the least emergent leaders. Taking the advantage of MKL's capability to use dierent kernels which corresponds to dif- ferent feature subsets having dierent notions of similarity, signicantly improved results compared to the state of the art methods were obtained. Additionally, high correlations between the majority of the features and the social psy- chology questionnaires which are designed to estimate the leadership or dominance were demonstrated.