Adaptive Multi-Order Graph Neural Networks for Human Motion Prediction | IEEE Conference Publication | IEEE Xplore

Adaptive Multi-Order Graph Neural Networks for Human Motion Prediction


Abstract:

Human motion prediction aims at capturing the hidden temporal correlations between historical motion and future poses. Various graph convolution networks have been presen...Show More

Abstract:

Human motion prediction aims at capturing the hidden temporal correlations between historical motion and future poses. Various graph convolution networks have been presented for encoding the spatial dependencies between joints. Empirically, the crucial shortcoming of these methods is that they fail to extract enough spatially relevant information. In this paper, we propose an adaptive multi-order context fusion architecture that consists of two components. A novel message propagation module encodes the interaction between joints, while highlighting contexts from closely related joints. An adaptive aggregation module fuses various information from different-order joint features. Our model is evaluated on Human 3.6 Million dataset. Extensive experiments show that our method achieves state-of-the-art performance on short-term and long-term predictions.
Date of Conference: 18-22 July 2022
Date Added to IEEE Xplore: 26 August 2022
ISBN Information:

ISSN Information:

Conference Location: Taipei, Taiwan

Funding Agency:


References

References is not available for this document.