Simple Baseline for Single Human Motion Forecasting

Chenxi Wang, Yunfeng Wang, Zixuan Huang, Zhiwen Chen; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 2260-2265

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 benchmark. We hope our work provide new ideas for future research.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2021_ICCV, author = {Wang, Chenxi and Wang, Yunfeng and Huang, Zixuan and Chen, Zhiwen}, title = {Simple Baseline for Single Human Motion Forecasting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2260-2265} }