no code implementations • 27 Apr 2024 • Yiming Bao, Xu Zhao, Dahong Qian
On Total Capture dataset, the pose estimation error is significantly decreased compared to the baseline method.
no code implementations • 24 Nov 2023 • Xiaoyue Wan, Zhuo Chen, Yiming Bao, Xu Zhao
This perception is injected by the Pose Transformer network and learned through a pre-training task that recovers iterative masked joints.
no code implementations • 25 Aug 2022 • Yiming Bao, Xu Zhao, Dahong Qian
On Total Capture dataset, KineFuse surpasses previous state-of-the-art which uses IMU only for testing by 8. 6\%.
Ranked #2 on 3D Human Pose Estimation on Total Capture
no code implementations • 7 May 2021 • Yiming Bao, Jun Wang, Tong Li, Linyan Wang, Jianwei Xu, Juan Ye, Dahong Qian
Specifically, the encoder of a DL model that is pre-trained on the source domain is used to initialize the encoder of a reconstruction model.