SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction

arXiv:2310.05370v2 Announce Type: replace
Abstract: Analyzing and forecasting trajectories of agents like pedestrians and cars in complex scenes has become more and more significant in many intelligent systems and applications. The diversity and uncertainty in socially interactive behaviors among a rich variety of agents make this task more challenging than other deterministic computer vision tasks. Researchers have made a lot of efforts to quantify the effects of these interactions on future trajectories through different mathematical models and network structures, but …

abstract agents applications arxiv become cars cs.cv diversity forecasting intelligent intelligent systems interactive pedestrian pedestrians prediction representation social systems trajectory type uncertainty