Our beliefs about the world are generally not formed in isolation: the inherently social nature of human beings means that much of what we believe to know is based, at least in part, on information gained from others. Consequently, human knowledge and its acquisition cannot be fully understood by considering individuals alone. In this paper, we examine the belief dynamics in a group of networke...

In this work, we propose a compositional data-driven approach for the formal estimation of collision risks autonomous vehicles (AVs) with black-box dynamics while acting in stochastic multi-agent framework. The proposed is based on construction sub-barrier certificates each agent via set data collected from its trajectories providing an priori guaranteed confidence estimation. our setting, firs...

This paper presents a multi-task learning framework, called the dynamic information transfer network (DITN). We mainly focused on improving pose estimation with spatial relationship of adjacent joints. To benefit from explicit structural knowledge, we constructed two branches shared backbone to localize human joints and bones, respectively. Since related tasks share high-level representation, l...