Skarimva: Skeleton-based Action Recognition is a Multi-view Application

TL;DR

This paper shows that using multi-view camera triangulation to improve 3D skeleton data significantly enhances the performance of action recognition models, advocating multi-view setups as standard practice.

Contribution

It demonstrates the importance of input data quality and advocates for multi-view triangulation to improve skeleton-based action recognition accuracy.

Findings

Multi-view triangulation improves recognition accuracy.

Input data quality limits current model performance.

Multi-camera setups are cost-effective for practical applications.

Abstract

Human action recognition plays an important role when developing intelligent interactions between humans and machines. While there is a lot of active research on improving the machine learning algorithms for skeleton-based action recognition, not much attention has been given to the quality of the input skeleton data itself. This work demonstrates that by making use of multiple camera views to triangulate more accurate 3D~skeletons, the performance of state-of-the-art action recognition models can be improved significantly. This suggests that the quality of the input data is currently a limiting factor for the performance of these models. Based on these results, it is argued that the cost-benefit ratio of using multiple cameras is very favorable in most practical use-cases, therefore future research in skeleton-based action recognition should consider multi-view applications as the standard setup.