Open Source Page of HAVPR Group @ Wuhan University
Paper with Code
We open source code of papers here. All paper list can be browsed in publication page
Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry, Neural motion retargeting model that can preserve the source motion semantics and avoid interpenetration in the target motion, CVPR 2023, Code
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video, 3D Human pose estimation method from monocular data using Transformer, CVPR 2022, Code
Motion-driven Visual Tempo Learning for Video-based Action Recognition, Video action recognition method via motion representation learning, TIP 2022, Code
Dataset
We list our published datasets and correspondng project pages here.
FADE, The first one for FAlling object DEtection dataset around buildings, Project Page
EBPersons, The first one for Person Detection at the Edges of Buildings, Project Page
Dark-48, A dark video dataset for action recognition in the dark., Project Page
