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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bermuth, Daniel, Poeppel, Alexander, Reif, Wolfgang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914586604601344
author Bermuth, Daniel
Poeppel, Alexander
Reif, Wolfgang
author_facet Bermuth, Daniel
Poeppel, Alexander
Reif, Wolfgang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23231
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Skarimva: Skeleton-based Action Recognition is a Multi-view Application
Bermuth, Daniel
Poeppel, Alexander
Reif, Wolfgang
Computer Vision and Pattern Recognition
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.
title Skarimva: Skeleton-based Action Recognition is a Multi-view Application
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.23231