Efficient Metric Learning for the Analysis of Motion Data

Hosseini B, Hammer B (2015)
Presented at the Data Science and Advanced Analytics (DSAA), Paris, France.

Download
OA 350.02 KB
Conference Paper | Published | English
Abstract
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 neighbours 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 regularisation can be transferred from the vectorial case to component-wise DTW in a similar way. We illustrate, that metric regularisation constitutes a crucial prerequisite for the interpretation of the resulting relevance profiles.
Publishing Year
Conference
Data Science and Advanced Analytics (DSAA)
Location
Paris, France
Conference Date
2015-10-19 – 2015-10-21
PUB-ID

Cite this

Hosseini B, Hammer B. Efficient Metric Learning for the Analysis of Motion Data. Presented at the Data Science and Advanced Analytics (DSAA), Paris, France.
Hosseini, B., & Hammer, B. (2015). Efficient Metric Learning for the Analysis of Motion Data. Presented at the Data Science and Advanced Analytics (DSAA), Paris, France.
Hosseini, B., and Hammer, B. (2015).“Efficient Metric Learning for the Analysis of Motion Data”. Presented at the Data Science and Advanced Analytics (DSAA), Paris, France.
Hosseini, B., & Hammer, B., 2015. Efficient Metric Learning for the Analysis of Motion Data. Presented at the Data Science and Advanced Analytics (DSAA), Paris, France.
B. Hosseini and B. Hammer, “Efficient Metric Learning for the Analysis of Motion Data”, Presented at the Data Science and Advanced Analytics (DSAA), Paris, France, 2015.
Hosseini, B., Hammer, B.: Efficient Metric Learning for the Analysis of Motion Data. Presented at the Data Science and Advanced Analytics (DSAA), Paris, France (2015).
Hosseini, Babak, and Hammer, Barbara. “Efficient Metric Learning for the Analysis of Motion Data”. Presented at the Data Science and Advanced Analytics (DSAA), Paris, France, 2015.
Main File(s)
File Name
Access Level
OA Open Access
Last Uploaded
2016-09-13T13:26:37Z

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar
ISBN Search