Recognizing human activities from video sequences or still images is a challenging task due
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …

Vision-based human action and activity recognition has an increasing importance among
the computer vision community with applications to visual surveillance, video retrieval and …

In recent years, there has been a proliferation of works on human action classification from
depth sequences. These works generally present methods and/or feature representations …

We propose a function-based temporal pooling method that captures the latent structure of
the video sequence data-eg, how frame-level features evolve over time in a video. We show …

Human activity recognition is central to many practical applications, ranging from visual
surveillance to gaming interfacing. Most approaches addressing this problem are based on …

In this paper we propose a new framework to compare and classify temporal sequences.
The proposed approach captures the underlying dynamics of the data while avoiding …

Most popular deep models for action recognition split video sequences into short sub-
sequences consisting of a few frames; frame-based features are then pooled for recognizing …

In this paper, we propose a new supervised classification method based on a modified
sparse model for action recognition. The main contributions are three-fold. First, a novel …

Sparsity-based representations have recently led to notable results in various visual
recognition tasks. In a separate line of research, Riemannian manifolds have been shown …

Abstract Human Action Recognition (HAR) has achieved a remarkable milestone in the field
of computer vision. Apart from its varied applications in human–computer interactions …