Efficient Metric Learning for the Analysis of Motion Data
This work addresses the need for problem-adapted representations in motion data analysis, though it is incremental by extending existing methods to a new domain.
The paper tackles the problem of adapting metric learning to dynamic time warping (DTW) for motion capture data, resulting in enhanced classification accuracy in benchmarks.
We investigate metric learning in the context of dynamic time warping (DTW), the by far most popular dissimilarity measure used for the comparison and analysis of motion capture data. While metric learning enables a problem-adapted representation of data, the majority of methods has been proposed for vectorial data only. In this contribution, we extend the popular principle offered by the large margin nearest neighbors learner (LMNN) to DTW by treating the resulting component-wise dissimilarity values as features. We demonstrate that this principle greatly enhances the classification accuracy in several benchmarks. Further, we show that recent auxiliary concepts such as metric regularization can be transferred from the vectorial case to component-wise DTW in a similar way. We illustrate that metric regularization constitutes a crucial prerequisite for the interpretation of the resulting relevance profiles.