Over the last decade, there have been many studies that focus on modeling driver behavior, and in particular detecting and overcoming driver distraction in an effort to reduce accidents caused by driver negligence. Such studies assume that the entire onus of avoiding accidents are on the driver alone. In this study, we adopt a different stance and study the behavior of pedestrians instead. In particular, we focus on detecting pedestrians who are engaged in secondary activities involving their cellphones and similar hand-held multimedia devices from a purely vision-based standpoint. To achieve this objective, we propose a pipeline incorporating articulated human pose estimation, and the use gradient based image features to detect the presence/absence of a device in either hand of a pedestrian. Information from different streams and their dependencies on one another are encoded by a belief network. This network is then used to predict a probability score suggesting the involvement of a subject with his/her device.