TR2020-073

Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction


    •  Li, M., Chen, S., Zhao, Y., Zhang, Y., Wang, Y., Tia, Q., "Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
      BibTeX TR2020-073 PDF
      • @inproceedings{Li2020jun,
      • author = {Li, Maosen and Chen, Sihen and Zhao, Yangheng and Zhang, Ya and Wang, Yanfeng and Tia, Qi},
      • title = {Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2020,
      • month = jun,
      • url = {https://www.merl.com/publications/TR2020-073}
      • }
  • MERL Contact:
  • Research Areas:

    Artificial Intelligence, Computer Vision, Signal Processing

We propose novel dynamic multiscale graph neural networks (DMGNN) to predict 3D skeleton-based human motions. The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning. This multiscale graph is adaptive during training and dynamic across network layers. Based on this graph, we propose a multiscale graph computational unit (MGCU) to extract features at individual scales and fuse features across scales. The entire model is action-category-agnostic and follows an encoder-decoder framework. The encoder consists of a sequence of MGCUs to learn motion features. The decoder uses a proposed graph-based gate recurrent unit to generate future poses. Extensive experiments show that the proposed DMGNN outperforms state-of-the-art methods in both short and long-term predictions on the datasets of Human 3.6M and CMU Mocap. We further investigate the learned multiscale graphs for the interpretability. The codes could be downloaded from https://github.com/limaosen0/DMGNN

 

  • Related News & Events