Header logo is

Characteristic Kernels on Structured Domains Excel in Robotics and Human Action Recognition

2010

Conference Paper

ei


Embedding probability distributions into a sufficiently rich (characteristic) reproducing kernel Hilbert space enables us to take higher order statistics into account. Characterization also retains effective statistical relation between inputs and outputs in regression and classification. Recent works established conditions for characteristic kernels on groups and semigroups. Here we study characteristic kernels on periodic domains, rotation matrices, and histograms. Such structured domains are relevant for homogeneity testing, forward kinematics, forward dynamics, inverse dynamics, etc. Our kernel-based methods with tailored characteristic kernels outperform previous methods on robotics problems and also on a widely used benchmark for recognition of human actions in videos.

Author(s): Danafar, S. and Gretton, A. and Schmidhuber, J.
Book Title: Machine Learning and Knowledge Discovery in Databases, LNCS Vol. 6321
Pages: 264--279
Year: 2010
Day: 0
Editors: JL Balcázar and F Bonchi and A Gionis and M Sebag
Publisher: Springer

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1007/978-3-642-15880-3_23
Event Name: ECML PKDD 2010
Event Place: Barcelona, Spain

Address: Berlin, Germany
Digital: 0

BibTex

@inproceedings{DanafarGSFAM2010,
  title = {Characteristic Kernels on Structured Domains Excel in Robotics and Human Action Recognition},
  author = {Danafar, S. and Gretton, A. and Schmidhuber, J.},
  booktitle = {Machine Learning and Knowledge Discovery in Databases, LNCS Vol. 6321},
  pages = {264--279},
  editors = {JL Balcázar and F Bonchi and A Gionis and M Sebag},
  publisher = {Springer},
  address = {Berlin, Germany},
  year = {2010},
  doi = {10.1007/978-3-642-15880-3_23}
}