Recognition of Group Actions from Individual Actions in Brainstorming Sessions

In this paper we show how an artificial intelligence system is able to recognize actions of a group of people during remote meetings. It is based on the combination of several basic detections. We explain why it is a very important task in order to help a coach manage teams. In particular, we explain how the recognition of discussions allows to measure the collaboration between participants or possibly their isolation. We detail the action of Eye Contact where two people look at each other during a discussion. We present the algorithm of the module of our system in charge of the recognition of an Eye Contact action and the difficulties raised by this module. We conclude with the heuristics rules that would allow to detect higher level of group actions from individual actions in brainstorming sessions.