Results of ACA and HACA
Abstract
This page shows the resulting segmentation of 14 sequences performed by subject 86 in Carnegie Mellon University Motion Capture
database. We compared clustering performance of three methods: Aligned Cluster Analysis (ACA) [1], Hierarchical Aligned Cluster Analysis (HACA) [2] and GMM
[3]. The ground truth label is available here.
- [1] F. Zhou, F. de la Torre, and J. K. Hodgins, "Aligned cluster analysis for temporal segmentation of human motion," in
International Conference on Automatic Face and Gesture Recognition (FG), 2008.
- [2] F. Zhou, F. de la Torre, and J. K. Hodgins, "Hierarchical Aligned cluster analysis for temporal segmentation of human motion," submitted to
IEEE Transactions on Pattern Analysis & Machine Intelligence (PAMI), 2010.
- [3] J. Barbic, A. Safonova, J.-Y. Pan, C. Faloutsos, J. K. Hodgins, and N. S. Pollard, "Segmenting motion capture data into
distinct behaviors," in Graphics Interface (GI), 2004.
Code
The experiments can be repeated by using the code here.
Accuracy
Results
