Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

PyTorch version should be 0.3! For PyTorch0.4 or higher, the codes need to be modified.

• Download the raw data from NTU-RGB D and Skeleton-Kinetics. Then put them under the data directory:

   -data\  
     -kinetics_raw\  
       -kinetics_train\
         ...
       -kinetics_val\
         ...
       -kinetics_train_label.json
       -keintics_val_label.json
     -nturgbd_raw\  
       -nturgb d_skeletons\
         ...
       -samples_with_missing_skeletons.txt
  

• Preprocess the data with

  python data_gen/ntu_gendata.py

  python data_gen/kinetics-gendata.py.

• Generate the bone data with:

  python data_gen/gen_bone_data.py

Change the config file depending on what you want.

`python main.py --config ./config/nturgbd-cross-view/train_joint.yaml`

`python main.py --config ./config/nturgbd-cross-view/train_bone.yaml`

To ensemble the results of joints and bones, run test firstly to generate the scores of the softmax layer.

`python main.py --config ./config/nturgbd-cross-view/test_joint.yaml`

`python main.py --config ./config/nturgbd-cross-view/test_bone.yaml`

Then combine the generated scores with:

`python ensemble.py` --datasets ntu/xview

Please cite the following paper if you use this repository in your reseach.

@inproceedings{2sagcn2019cvpr,  
  title     = {Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition},  
  author    = {Lei Shi and Yifan Zhang and Jian Cheng and Hanqing Lu},  
  booktitle = {CVPR},  
  year      = {2019},  
}

For any questions, feel free to contact: [email protected]