Motion retrieval using Isomap
Ning Suo, Qian Xu · 2010
In this paper, we propose a new learning method in human motion data analysis. We use Isomap algorithm to reduce high dimensionality of motion's features data. And Support Vector Machine (SVM) for clustering and handling new data. Then data driven decision trees based on multiple instance are automatically constructed to reflect the influence of each point during the comparison of motion similarity. The experimental results show that algorithm is effective.