Non-Negative Kernel Sparse Coding for the Analysis of Motion Data

Bibliographic Metadata

Title
Non-Negative Kernel Sparse Coding for the Analysis of Motion Data
Author
Hosseini, Babak ; Hülsmann, Felix ; Botsch, Mario ; Hammer, Barbara
Editor
E.P. Villa, Alessandro ; Masulli, Paolo ; Javier Pons Rivero, Antonio
Published
2016
Language
English
Document type
Conference Proceedings
Keywords
Kernel sparse coding / Motion analysis / Classification / Interpretable models / Dynamic time warping
ISBN
978-3-319-44780-3
URN
urn:nbn:de:0070-pub-29044695
DOI
10.1007/978-3-319-44781-0_60

Restriction-Information

Links

Files

Classification

Abstract

We are interested in the decomposition of motion data into a sparse linear combination of base functions which enable efficient data processing. We combine two prominent frameworks: dynamic time warping (DTW), which offers particularly successful pairwise motion data comparison, and sparse coding (SC), which enables an automatic decomposition of vectorial data into a sparse linear combination of base vectors. We enhance SC as follows: an efficient kernelization which extends its application domain to general similarity data such as offered by DTW, and its restriction to non-negative linear representations of signals and base vectors in order to guarantee a meaningful dictionary. Empirical evaluations on motion capture benchmarks show the effectiveness of our framework regarding interpretation and discrimination concerns.

Stats