Skip to content

Latest commit

 

History

History
20 lines (17 loc) · 1.04 KB

README.md

File metadata and controls

20 lines (17 loc) · 1.04 KB

ICCV2017 - Predicting Human Activities Using Stochastic Grammar.

Files in the repository:

  • cpp: grammar induction code. Instructions for running the code can be find here: https://github.com/SiyuanQi/madios
  • matlab: scripts mainly used for skeleton processing and feature extraction.
  • python: files for low-level classifiers and grammar inference.

Important notes

  • The cpp folder contains code for learning grammar. For parsing/inference, most grammar related code are in python/grammarutils.py.
  • If you want to use the code for future prediction, you need to modify the nltk library according to the instructions here.

If you find this code useful, please cite our work with the following bibtex:

@inproceedings{qi2017predicting,
    title={Predicting Human Activities Using Stochastic Grammar},
    author={Qi, Siyuan and Huang, Siyuan and Wei, Ping and Zhu, Song-Chun},
    booktitle={International Conference on Computer Vision (ICCV)},
    year={2017}
}