Function and shape data analysis are old topics in statistics, studied off and on over the last
several decades. However, the early years of the new millennium saw a renewed focus and …

Although surveillance video cameras are now widely used, their effectiveness is
questionable. Here, we focus on the challenging task of monitoring crowded events for …

Recognizing human actions in 3-D video sequences is an important open problem that is
currently at the heart of many research domains including surveillance, natural interfaces …

We study the problem of classifying actions of human subjects using depth movies
generated by Kinect or other depth sensors. Representing human body as dynamical …

In this paper we address the problem of modeling and analyzing human motion by focusing
on 3D body skeletons. Particularly, our intent is to represent skeletal motion in a geometric …

In this paper, we propose a novel space-time geometric representation of human landmark
configurations and derive tools for comparison and classification. We model the temporal …

The attention paid to matrix manifolds has grown considerably in the computer vision
community in recent years. There are a wide range of important applications including face …

Action videos are multidimensional data and can be naturally represented as data tensors.
While tensor computing is widely used in computer vision, the geometry of tensor space is …

Representing 3-D motion-capture sensor data with 2-D color-coded joint distance maps
(JDMs) as input to a deep neural network has been shown to be effective for 3-D skeletal …

Abstract 3D human action recognition is an important current challenge at the heart of many
research areas lying to the modeling of the spatio-temporal information. In this paper, we …