Multi-Mode Tensor Representation of Motion Data

J. Herder (Editors)
In: Journal of Virtual Reality and Broadcasting (July 2008), 5:5
Presented at 2nd International Conference on Computer Graphics Theory and Applications (GRAPP 2007)
 

Abstract

In this paper, we investigate how a multilinear model can be used to represent human motion data. Based on technical modes (referring to degrees of freedom and number of frames) and natural modes that typically appear in the context of a motion capture session (referring to actor, style, and repetition), the motion data is encoded in form of a high-order tensor. This tensor is then reduced by using N-mode singular value decomposition. Our experiments show that the reduced model approximates the original motion better then previously introduced PCA-based approaches. Furthermore, we discuss how the tensor representation may be used as a valuable tool for the synthesis of new motions.

Images

Download Paper

Download Paper

Additional Material

  • Video (AVI video, 8.4 MB)

Bibtex

@ARTICLE{krueger-2008-multi,
      author = {Kr{\"u}ger, Bj{\"o}rn and Tautges, Jochen and M{\"u}ller, M. and Weber, Andreas},
      editor = {Herder, J.},
       title = {Multi-Mode Tensor Representation of Motion Data},
     journal = {Journal of Virtual Reality and Broadcasting},
      volume = {5},
      number = {5},
        year = {2008},
       month = jul,
    abstract = {In this paper, we investigate how a multilinear model
                              can be used to represent human motion data. Based
                              on technical modes (referring to degrees of freedom
                              and number of frames) and natural modes that typically
                              appear in the context of a motion capture session
                              (referring to actor, style, and repetition), the motion
                              data is encoded in form of a high-order tensor.
                              This tensor is then reduced by using N-mode singular
                              value decomposition. Our experiments show that the
                              reduced model approximates the original motion better
                              then previously introduced PCA-based approaches.
                              Furthermore, we discuss how the tensor representation
                              may be used as a valuable tool for the synthesis of new
                              motions.},
        issn = {1860-2037},
  conference = {2nd International Conference on Computer Graphics Theory and Applications (GRAPP 2007)}
}