Thumbnail
Access Restriction
Open

Author Sidenbladh, Hedvig ♦ Black, Michael J. ♦ Sigal, Leonid
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword High Dimensional Nature ♦ Texture Synthesis ♦ Treat Image ♦ Explicit Probabilistic Model ♦ Human Motion ♦ Training Data ♦ Large Database ♦ Similar Instance ♦ Implicit Probabilistic Model ♦ Efficient Search ♦ Large Training Set ♦ Texture Pattern ♦ Implicit Empirical Distribution ♦ Example Motion ♦ Available Training Data ♦ Temporal Data ♦ Tracking Hedvig Sidenblen
Description 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
In European Conference on Computer Vision
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2002-01-01