Simple Baseline for Single Human Motion Forecasting

Chenxi Wang, Yunfeng Wang, Zixuan Huang, Zhiwen Chen

ICCVW 2021 pp. 2260-2265

doi:10.1109/ICCVW54120.2021.00255 /iccvw/2021/wang2021iccvw-simple/

Abstract

Global human motion forecasting is important in many fields, which is the combination of global human trajectory prediction and local human pose prediction. Visual and social information are often used to boost model performance, however, they may consume too much computational resources. In this paper, we establish a simple but effective baseline for single human motion forecasting without visual and social information, equipped with useful training tricks. Our method "futuremotion_ICCV21" outperforms existing methods by a large margin on SoMoF benchmark1. We hope our work provide new ideas for future research.

PDF ICCVW Semantic Scholar

Cite

Text

Wang et al. "Simple Baseline for Single Human Motion Forecasting." IEEE/CVF International Conference on Computer Vision Workshops, 2021. doi:10.1109/ICCVW54120.2021.00255

Markdown

[Wang et al. "Simple Baseline for Single Human Motion Forecasting." IEEE/CVF International Conference on Computer Vision Workshops, 2021.](https://mlanthology.org/iccvw/2021/wang2021iccvw-simple/) doi:10.1109/ICCVW54120.2021.00255

BibTeX

@inproceedings{wang2021iccvw-simple,
  title     = {{Simple Baseline for Single Human Motion Forecasting}},
  author    = {Wang, Chenxi and Wang, Yunfeng and Huang, Zixuan and Chen, Zhiwen},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2021},
  pages     = {2260-2265},
  doi       = {10.1109/ICCVW54120.2021.00255},
  url       = {https://mlanthology.org/iccvw/2021/wang2021iccvw-simple/}
}