Multi-Person Extreme Motion Prediction
This addresses the challenge of multi-person motion prediction for collaborative tasks, which is incremental as it extends existing single-person methods to interactive scenarios.
The paper tackles the problem of predicting future 3D poses for two interacting humans, rather than single humans in isolation, by proposing a cross interaction attention mechanism and introducing the ExPI dataset of professional dancers. The method consistently outperforms state-of-the-art single-person motion prediction methods in both short- and long-term predictions on this new dataset.
Human motion prediction aims to forecast future poses given a sequence of past 3D skeletons. While this problem has recently received increasing attention, it has mostly been tackled for single humans in isolation. In this paper, we explore this problem when dealing with humans performing collaborative tasks, we seek to predict the future motion of two interacted persons given two sequences of their past skeletons. We propose a novel cross interaction attention mechanism that exploits historical information of both persons, and learns to predict cross dependencies between the two pose sequences. Since no dataset to train such interactive situations is available, we collected ExPI (Extreme Pose Interaction), a new lab-based person interaction dataset of professional dancers performing Lindy-hop dancing actions, which contains 115 sequences with 30K frames annotated with 3D body poses and shapes. We thoroughly evaluate our cross interaction network on ExPI and show that both in short- and long-term predictions, it consistently outperforms state-of-the-art methods for single-person motion prediction.