Recently, skeleton-based human action recognition has been receiving significant attention
from various research communities due to the availability of depth sensors and real-time …

In this paper, we develop an approach to exploiting kernel methods with manifold-valued
data. In many computer vision problems, the data can be naturally represented as points on …

With the rapid development of digital imaging and communication technologies, image set-
based face recognition (ISFR) is becoming increasingly important. One key issue of ISFR is …

In this paper, we propose a novel binary local representation for RGB-D video data fusion
with a structure-preserving projection. Our contribution consists of two aspects. To acquire a …

Abstract Recently, a particular paradigm [9] in the domain adaptation field has received
considerable attention by introducing novel and important insights to the problem. In this …

We present a novel approach for learning a finite mixture model on a Riemannian manifold
in which Euclidean metrics are not applicable and one needs to resort to geodesic distances …

Media streaming is the killer application in current Internet. There are a variety of media
streaming techniques in today's Internet, such as RTSP, HTTP live streaming and Adobe …

Modeling data as points on non-linear Riemannian manifolds has attracted increasing
attentions in many computer vision tasks, especially visual recognition. Learning an …

For image-set based classification, sparse coding and collaborative representation have
gained a lot of attention due to their robustness and effectiveness. However, most existing …

Reformulating computer vision problems over Riemannian manifolds has demonstrated
superior performance in various computer vision applications. This is because visual data …