Simple Baseline for Single Human Motion Forecasting.

IEEE International Conference on Computer Vision(2021)

引用 18|浏览14
暂无评分
摘要
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.
更多
查看译文
关键词
global human trajectory prediction,visual information,social information,single human motion forecasting,global human motion forecasting,local human pose prediction,SoMoF benchmark,SoMoF benchmark,futuremotion_ICCV21
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要