Temporal Dynamics Decoupling with Inverse Processing for Enhancing Human Motion Prediction
This addresses motion prediction for human behavior modeling, appearing to be an incremental improvement over existing methods that incorporate reconstruction as an auxiliary task.
The paper tackles the problem of conflicts between reconstruction and prediction tasks in human motion prediction by proposing Temporal Decoupling Decoding with Inverse Processing (TD²IP), which separates these processes with distinct decoders and uses inverse processing to leverage bidirectional temporal correlations, though no concrete performance numbers are provided in the abstract.
Exploring the bridge between historical and future motion behaviors remains a central challenge in human motion prediction. While most existing methods incorporate a reconstruction task as an auxiliary task into the decoder, thereby improving the modeling of spatio-temporal dependencies, they overlook the potential conflicts between reconstruction and prediction tasks. In this paper, we propose a novel approach: Temporal Decoupling Decoding with Inverse Processing (\textbf{$TD^2IP$}). Our method strategically separates reconstruction and prediction decoding processes, employing distinct decoders to decode the shared motion features into historical or future sequences. Additionally, inverse processing reverses motion information in the temporal dimension and reintroduces it into the model, leveraging the bidirectional temporal correlation of human motion behaviors. By alleviating the conflicts between reconstruction and prediction tasks and enhancing the association of historical and future information, \textbf{$TD^2IP$} fosters a deeper understanding of motion patterns. Extensive experiments demonstrate the adaptability of our method within existing methods.