(A Double-feature Double-motion Network)

JHMDB

SHREC-14

Updating code to current Keras environment.

Thanks for @muxizju, @pengfeiZhao1993, and @YLTsai0609 helped to fix bugs in this code. After fixing bugs, the performance is further improved - JHMDB 82-83% and SHREC-14 96-97 %.

Thanks for Nightwatch, who made a pytorch version DD-Net. You can check it at Pytorch DD-Net

A lightweight network for body/hand action recognition, implemented by keras tensorflow backend. It also could be the simplest tutorial code to start skeleton-based action recognition.

git clone https://github.com/fandulu/DD-Net.git

Note: You can download the raw data and use our code to preprocess them, or, directly use our preprocessed data under /data.

JHMDB raw data download link:   http://jhmdb.is.tue.mpg.de/challenge/JHMDB/datasets
SHREC raw data download link:   http://www-rech.telecom-lille.fr/shrec2017-hand/

Note: if you want to test the speed, please try to run the model.predict() at leat twice and do not take the speed of first run, the model initialization takes extra time.

If you find this code is helpful, thanks for citing our work as,

@inproceedings{yang2019ddnet,
  title={Make Skeleton-based Action Recognition Model Smaller, Faster and Better},
  author={Fan Yang, Sakriani Sakti, Yang Wu, and Satoshi Nakamura},
  booktitle={ACM International Conference on Multimedia in Asia},
  year={2019}
}

Hey, come take a look