Skip to content

Latest commit

 

History

History
75 lines (62 loc) · 3.06 KB

README.md

File metadata and controls

75 lines (62 loc) · 3.06 KB

Preparing Skeleton Dataset

@misc{duan2021revisiting,
      title={Revisiting Skeleton-based Action Recognition},
      author={Haodong Duan and Yue Zhao and Kai Chen and Dian Shao and Dahua Lin and Bo Dai},
      year={2021},
      eprint={2104.13586},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Introduction

We release the skeleton annotations used in Revisiting Skeleton-based Action Recognition. By default, we use Faster-RCNN with ResNet50 backbone for human detection and HRNet-w32 for single person pose estimation. For FineGYM, we use Ground-Truth bounding boxes for the athlete instead of detection bounding boxes. Currently, we release the skeleton annotations for FineGYM and NTURGB-D Xsub split. Other annotations will be soo released.

Prepare Annotations

Currently, we support one dataset: FineGYM. You can execute following scripts to prepare the annotations.

bash download_annotations.sh ${DATASET}

PS: Due to Conditions of Use of the NTURGB-D dataset, we can not directly release the annotations used in our experiments. We will prepare a script for pose annotation generation ASAP. Once accomplished, you can use this script to generate all pose annotations used in our experiments.

Visualization

For skeleton data visualization, you need also to prepare the RGB videos. Please refer to visualize_heatmap_volume for detailed process. Here we provide some visualization examples from NTU-60 and FineGYM.

Pose Estimation Results


Keypoint Heatmap Volume Visualization


Limb Heatmap Volume Visualization


TODO:

  • FineGYM
  • NTU60_XSub
  • NTU120_XSub
  • NTU60_XView
  • NTU120_XSet
  • Kinetics