Human Motion Anticipation with Symbolic Label
This work addresses the problem of predicting human motion for applications like robotics or surveillance, but it is incremental as it builds on existing methods by incorporating symbolic labels.
The paper tackles human motion anticipation by approximating a person's intention using symbolic labels like action types, which simplifies forecasting and improves accuracy. It achieves state-of-the-art results in both short-term and long-term motion forecasting.
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.