TY - GEN
T1 - Style translation filter to change attribute of motion
AU - Yamaguchi, Akihiko
AU - Sato, Shiori
AU - Takemura, Kentaro
AU - Takamatsu, Jun
AU - Ogasawara, Tsukasa
PY - 2012
Y1 - 2012
N2 - In this paper, we propose a style translation filter that changes the attribute (style) of the motion coming from the actors' ages, genders, and so on. Using this filter, we can diversify the motions. Specifically, this filter is modeled by the Gaussian process regression that estimates the difference of pose (joint angles) between a neutral motion and the motion of a target attribute. In learning this filter, a key technique is to find pairs of corresponding posed from the sample motions. We solve this problem by employing the Multifactor Gaussian Process Model (MGPM) proposed by Wang et al. [1]. In the experiments, we constructed multiple style translation filters from several attributes of walking motions, such as genders, ages, and emotions. The obtained filters were applied to some kinds of testing motions, such as walking, jumping, kicking, and dancing. The acquired motions were verified by a questionnaire study; the most of their attributes were changed to the filters' target attributes.
AB - In this paper, we propose a style translation filter that changes the attribute (style) of the motion coming from the actors' ages, genders, and so on. Using this filter, we can diversify the motions. Specifically, this filter is modeled by the Gaussian process regression that estimates the difference of pose (joint angles) between a neutral motion and the motion of a target attribute. In learning this filter, a key technique is to find pairs of corresponding posed from the sample motions. We solve this problem by employing the Multifactor Gaussian Process Model (MGPM) proposed by Wang et al. [1]. In the experiments, we constructed multiple style translation filters from several attributes of walking motions, such as genders, ages, and emotions. The obtained filters were applied to some kinds of testing motions, such as walking, jumping, kicking, and dancing. The acquired motions were verified by a questionnaire study; the most of their attributes were changed to the filters' target attributes.
UR - http://www.scopus.com/inward/record.url?scp=84891117169&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84891117169&partnerID=8YFLogxK
U2 - 10.1109/HUMANOIDS.2012.6651590
DO - 10.1109/HUMANOIDS.2012.6651590
M3 - Conference contribution
AN - SCOPUS:84891117169
SN - 9781467313698
T3 - IEEE-RAS International Conference on Humanoid Robots
SP - 660
EP - 665
BT - 2012 12th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2012
T2 - 2012 12th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2012
Y2 - 29 November 2012 through 1 December 2012
ER -