arXiv preprint / 6D位姿

VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network

作者：Zepeng Yang, Junxuan Bai, Hao Li, Ju Dai, Junjun Pan, Yongfeng Yin, Bin Li, Chinese Academy of Sciences · 单位：Beihang University, Peng Cheng Laboratory, Capital University of Physical Education and Sports, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2026-05-08

6D位姿估计人体姿态
新标签打开 AlphaXiv新标签打开 Code
VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network figure
AlphaXiv 中文概览（可滚动查看）