A human motion feature based on semi-supervised learning of GMM.

Qi, T., Feng, Y., Xiao, J., Zhang, H., Zhuang, Y., Yang, X. and Zhang, J. J., 2017. A human motion feature based on semi-supervised learning of GMM. Multimedia Systems, 23 (1), 85 - 93.

Full text available as:

[img]
Preview
PDF (OPEN ACCESS ARTICLE- SPRINGER COMPACT)
art_10.1007_s00530-014-0429-2.pdf - Published Version
Available under License Creative Commons Attribution.

1MB

DOI: 10.1007/s00530-014-0429-2

Abstract

Using motion capture to create naturally looking motion sequences for virtual character animation has become a standard procedure in the games and visual effects industry. With the fast growth of motion data, the task of automatically annotating new motions is gaining an importance. In this paper, we present a novel statistic feature to represent each motion according to the pre-labeled categories of key-poses. A probabilistic model is trained with semi-supervised learning of the Gaussian mixture model (GMM). Each pose in a given motion could then be described by a feature vector of a series of probabilities by GMM. A motion feature descriptor is proposed based on the statistics of all pose features. The experimental results and comparison with existing work show that our method performs more accurately and efficiently in motion retrieval and annotation.

Item Type:Article
ISSN:0942-4962
Uncontrolled Keywords:Human motion feature; Semi-supervised learning; Probabilistic model; Motion retrieval; Motion classification
Group:Faculty of Media & Communication
ID Code:28146
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:20 Mar 2017 15:37
Last Modified:20 Mar 2017 15:37

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -