Traditional dynamical systems used for motion tracking cannot effectively handle high dimensionality of the motion states and composite dynamics. In this paper, to address both is...
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...
Abstract. In this work, synthesis of facial animation is done by modelling the mapping between facial motion and speech using the shared Gaussian process latent variable model. Bot...
Supervised learning is difficult with high dimensional input spaces and very small training sets, but accurate classification may be possible if the data lie on a low-dimensional ...