MUCOS

Detecting Common Actions in Motion Capture Data and Videos

This code is a simple implementation of OF COMMONALITY DETECTION METHOD PROPOSED IN [1]
Given an distance matrix (D) of two action sequences, our method discovers all pairs of similar subsequences, i.e. subsequences that represent the same action.
This is achieved in a completely unsupervised manner, i.e., without any prior knowledge of the type of actions, their number and their duration. These common subsequences (commonalities) may be located anywhere in the original sequences, may differ in duration and may be performed under different conditions e.g., by a different actor.

We will appreciate if you cite our papers [1, 2] in your work:

More details can be found in https://sites.google.com/site/costaspanagiotakis/research/mucos

[1] Panagiotakis, C., Papoutsakis, K., & Argyros, A. (2018). A graph-based approach for detecting common actions
in motion capture data and videos. Pattern Recognition, 79, 1-11.

[2] K. Papoutsakis, C. Panagiotakis and A.A. Argyros, "Temporal Action Co-Segmentation in 3D Motion Capture Data and Videos", In IEEE Computer Vision and Pattern Recognition (CVPR 2017), IEEE, Honolulu, Hawaii, USA, July 2017.