The Dynamic Ordinal Classification (DOC) Toolbox

 

                                                      

The Dynamic Ordinal Classification (DOC) Toolbox contains different sequence classification methods including Conditional Ordinal Random Fields (CORF), Hidden Conditional Ordinal Random Fields (HCORF), Conditional Random Fields (CRF) , Hidden Conditional Random Fields (HCRF) and Variable State Latent Conditional Random Fields (VSL-CRF).

  

This Toolbox is a collection of open source functions implemented in Matlab.
Download code here. Please follow the instructions in the README file. 

 

Code released as is **for research purposes only** 
Feel free to modify/distribute but please cite the papers:

 

[1] R. WaleckiO. Rudovic, V. Pavlovic, M. Pantic. "Variable-state Latent Conditional Random Fields for Facial Expression Recognition and Action Unit Detection" Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition (FG'15)Ljubljana, Slovenia, pp. 1 - 8, May 2015. (pdf)

[2] O. Rudovic, V. Pavlovic, M. Pantic. "Multi-output Laplacian Dynamic Ordinal Regression for Facial Expression Recognition and Intensity Estimation" Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012)Providence, USA, pp. 2634 - 2641, June 2012. (pdf)

 

contact:  orudovic@imperial.ac.uk