Towards a model of nonverbal leadership in unstructured joint physical activity

Abstract

In this paper, we propose a set of algorithms to compute the cues of the nonverbal leadership in an unstructured joint full-body physical activity, i.e., the joint activity of two or more interacting persons who perform some movements without a predefined sequence and without a predefined leader. An example of such activity can be a contact dance improvisation. The paper is composed of three parts: cue set, dataset and algorithms. First, we propose a cue set of nonverbal leadership which is grounded on existing literature and studies. It is composed of eight cues that characterize the nonverbal behaviors of the leader in a joint full-body physical activity. In this paper we also introduce a new dataset. It consists of multimodal data (video, MoCap) of contact dance improvisations. Additionally, sensory deprivation conditions (vision and/or touch restraint) were introduced to collect the evidences of the various strategies used by leaders and followers during improvisation. The dataset was annotated by twenty-seven persons who carried out continuous annotation of leadership in the recorded material. In the last part of the paper, we propose a set of algorithms that works on positional 3D data (i.e., joints' positions obtained from motion capture data of dancers). Each algorithm models one among the discussed cues of the nonverbal leadership.