Implicit Probabilistic Models of Human Motion for Synthesis and Tracking Hedvig Sidenblen

DMCA

Implicit Probabilistic Models of Human Motion for Synthesis and Tracking Hedvig Sidenblen (2002)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Hedvig Sidenbladh , Michael J. Black , Leonid Sigal

Venue:	In European Conference on Computer Vision
Citations:	201 - 4 self

BibTeX

@INPROCEEDINGS{Sidenbladh02implicitprobabilistic,
    author = {Hedvig Sidenbladh and Michael J. Black and Leonid Sigal},
    title = {Implicit Probabilistic Models of Human Motion for Synthesis and Tracking Hedvig Sidenblen},
    booktitle = {In European Conference on Computer Vision},
    year = {2002},
    pages = {784--800}
}

OpenURL

Abstract

This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Given the high dimensional nature of human motion, learning an explicit probabilistic model from available training data is currently impractical. Instead we exploit methods from texture synthesis that treat images as representing an implicit empirical distribution . These methods replace the problem of representing the probability of a texture pattern with that of searching the training data for similar instances of that pattern. We extend this idea to temporal data representing 3D human motion with a large database of example motions. To make the method useful in practice, we must address the problem of efficient search in a large training set

Keyphrases

human motion tracking hedvig sidenblen implicit probabilistic model similar instance explicit probabilistic model training data available training data efficient search implicit empirical distribution large training set example motion texture pattern high dimensional nature treat image texture synthesis temporal data large database

DMCA