A Grid-based Representation for Human Action Recognition

TL;DR

This paper introduces GRAR, a novel grid-based method that encodes discriminative pose features for human action recognition, improving accuracy on benchmark datasets despite appearance variations and occlusions.

Contribution

The paper presents a new compact grid representation focusing on pose features, enhancing action recognition accuracy over existing methods.

Findings

Accurately recognizes actions despite appearance variations.

Effective in handling occlusions.

Demonstrates superior performance on benchmark datasets.

Abstract

Human action recognition (HAR) in videos is a fundamental research topic in computer vision. It consists mainly in understanding actions performed by humans based on a sequence of visual observations. In recent years, HAR have witnessed significant progress, especially with the emergence of deep learning models. However, most of existing approaches for action recognition rely on information that is not always relevant for this task, and are limited in the way they fuse the temporal information. In this paper, we propose a novel method for human action recognition that encodes efficiently the most discriminative appearance information of an action with explicit attention on representative pose features, into a new compact grid representation. Our GRAR (Grid-based Representation for Action Recognition) method is tested on several benchmark datasets demonstrating that our model can accurately recognize human actions, despite intra-class appearance variations and occlusion challenges.