TR2020-073
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction
-
- "Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR42600.2020.00029, June 2020, pp. 211-220.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,
- pages = {211--220},
- month = jun,
- doi = {10.1109/CVPR42600.2020.00029},
- url = {https://www.merl.com/publications/TR2020-073}
- }
,
- "Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR42600.2020.00029, June 2020, pp. 211-220.
-
Research Areas:
Abstract:
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
-
NEWS MERL researchers presenting four papers and organizing two workshops at CVPR 2020 conference Date: June 14, 2020 - June 19, 2020
MERL Contacts: Anoop Cherian; Michael J. Jones; Toshiaki Koike-Akino; Tim K. Marks; Kuan-Chuan Peng; Ye Wang
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningBrief- MERL researchers are presenting four papers (two oral papers and two posters) and organizing two workshops at the IEEE/CVF Computer Vision and Pattern Recognition (CVPR 2020) conference.
CVPR 2020 Orals with MERL authors:
1. "Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction," by Maosen Li, Siheng Chen, Yangheng Zhao, Ya Zhang, Yanfeng Wang, Qi Tian
2. "Collaborative Motion Prediction via Neural Motion Message Passing," by Yue Hu, Siheng Chen, Ya Zhang, Xiao Gu
CVPR 2020 Posters with MERL authors:
3. "LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood," by Abhinav Kumar, Tim K. Marks, Wenxuan Mou, Ye Wang, Michael Jones, Anoop Cherian, Toshiaki Koike-Akino, Xiaoming Liu, Chen Feng
4. "MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird’s Eye View Maps," by Pengxiang Wu, Siheng Chen, Dimitris N. Metaxas
CVPR 2020 Workshops co-organized by MERL researchers:
1. Fair, Data-Efficient and Trusted Computer Vision
2. Deep Declarative Networks.
- MERL researchers are presenting four papers (two oral papers and two posters) and organizing two workshops at the IEEE/CVF Computer Vision and Pattern Recognition (CVPR 2020) conference.