Pinned Repositories
RTPCA
PCformer
MixSTE
Official implementation of CVPR 2022 paper(MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video)
XViTSTR
PyTorch code of my paper Orthogonality constrained multihead self-attention for scene text recognition (cjig.cn) (XViTSTR)
MotionAGFormer
Official implementation of the paper "MotionAGFormer: Enhancing 3D Pose Estimation with a Transformer-GCNFormer Network" (WACV 2024).
IGANet
IGANet, single-frame based 3D human pose estimation
liuxing007's Repositories
liuxing007 doesn’t have any repository yet.