Human Motion Anticipation with Symbolic Label

TL;DR

This paper introduces a method that anticipates human motion by first predicting symbolic action labels, which simplifies the forecasting process and improves accuracy for both short-term and long-term predictions.

Contribution

The work proposes a novel two-step approach combining symbolic label prediction with motion generation, enhancing long-term human motion forecasting capabilities.

Findings

Achieves state-of-the-art results in human motion forecasting

Effective anticipation of motion changes over many steps

Improves long-term prediction accuracy

Abstract

Anticipating human motion depends on two factors: the past motion and the person's intention. While the first factor has been extensively utilized to forecast short sequences of human motion, the second one remains elusive. In this work we approximate a person's intention via a symbolic representation, for example fine-grained action labels such as walking or sitting down. Forecasting a symbolic representation is much easier than forecasting the full body pose with its complex inter-dependencies. However, knowing the future actions makes forecasting human motion easier. We exploit this connection by first anticipating symbolic labels and then generate human motion, conditioned on the human motion input sequence as well as on the forecast labels. This allows the model to anticipate motion changes many steps ahead and adapt the poses accordingly. We achieve state-of-the-art results on short-term as well as on long-term human motion forecasting.