Our paper addresses the problem of enforcing constraints in human body tracking. A projection technique is derived to impose kinematic constraints on independent multi-body motion: we show that for small motions the multi-body articulated motion space can be approximated by a linear manifold estimated directly from the previous body pose. We propose a learning approach to model non-linear const...

This paper presents a novel double knowledge transferring method to solve the multi-culture facial attractiveness enhancement problem. The existing enhancement of facial attractiveness methods just focus on one particular culture and assume the beautification model learned in one culture could be used in other cultures without adaptation. However, for the people in different cultures who do not...

Quantitative detection of defects in structures is always a hot research topic the field guided wave inverse scattering. Research studies on how to effectively extract defect-related information encompassed multi-frequency and multi-modes scattered signals for reconstructions have been paid attention recent decades. In this paper, novel deep learning-based quantitative scattering technique has ...

In this paper, we present a novel dictionary learning framework for data lying on the manifold of square root densities and apply it to the reconstruction of diffusion propagator (DP) fields given a multi-shell diffusion MRI data set. Unlike most of the existing dictionary learning algorithms which rely on the assumption that the data points are vectors in some Euclidean space, our dictionary l...

In this paper, a novel deep manifold-to-manifold transforming network (DMT-Net) is proposed for action recognition, in which symmetric positive definite (SPD) matrix is adopted to describe the spatial-temporal information of action feature vectors. Since each SPD matrix is a point of the Riemannian manifold space, the proposed DMT-Net aims to learn more discriminative feature by hierarchically ...

In this chapter we discuss how to learn an optimal manifold presentation to regularize nonegative matrix factorization (NMF) for data representation problems. NMF, which tries to represent a nonnegative data matrix as a product of two low rank nonnegative matrices, has been a popular method for data representation due to its ability to explore the latent part-based structure of data. Recent stu...

Recognizing objects from different viewpoints is a challenging task. One approach for handling this task is to model the appearance of an object under different viewing conditions using a low dimensional subspace. Manifold learning describes the process by which this low dimensional embedding can be generated. However, manifold learning is an unsupervised method and thus gives poor results on c...