Name
Abstract | ||
|---|---|---|
AbstractTo generate human motions with various specific attributes is a difficult task because of high dimensionality and complexity of human motions. This paper presents a novel human motion model for generating and editing motions with multiple factors. A set of motions performed by several actors with various styles was captured for constructing a well-structured motion database. Subsequently, MICA multilinear independent component analysis model that combines ICA and conventional multilinear framework was adopted for the construction of a multifactor model. With this model, new motions can be synthesized by interpolation and through solving optimization problems for the specific factors. Our method offers a practical solution to edit stylistic human motions in a parametric space learnt with MICA model. We demonstrated the power of our method by generating and editing sideways stepping, reaching, and striding over obstructions using different actors with various styles. The experimental results show that our method can be used for interactive stylistic motion synthesis and editing. Copyright © 2011 John Wiley & Sons, Ltd. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1002/cav.424 | Periodicals |
Keywords | Field | DocType |
motion,multifactor,multilinear independent components analysis,tensor | Computer vision,Tensor,Simulation,Computer science,Interpolation,Human motion,Curse of dimensionality,Parametric statistics,Independent component analysis,Artificial intelligence,Multilinear map,Optimization problem | Journal |
Volume | Issue | ISSN |
22 | 4 | 1546-4261 |
Citations | PageRank | References |
2 | 0.38 | 17 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gengdai Liu | 1 | 44 | 7.88 |
| Mingliang Xu | 2 | 372 | 54.07 |
| Zhigeng Pan | 3 | 25 | 4.37 |
| Abdennour El Rhalibi | 4 | 338 | 49.07 |