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

• URL: http://arxiv.org/abs/2602.23231v1
• Date: Thu, 26 Feb 2026 17:10:58 GMT
• Title: Skarimva: Skeleton-based Action Recognition is a Multi-view Application
• Authors: Daniel Bermuth, Alexander Poeppel, Wolfgang Reif,
• Abstract summary: This work demonstrates that by making use of multiple camera views to triangulate more accurate 3Dskeletons, the performance of state-of-the-art action recognition models can be improved significantly.
• Score: 44.79834103607383
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• 3D Skeleton-Based Action Recognition: A Review [60.0580120274659]
  3D skeleton-based action recognition has become a prominent topic in the field of computer vision.<n>Previous reviews have predominantly adopted a model-oriented perspective, often neglecting the fundamental steps involved in skeleton-based action recognition.<n>This review aims to address these limitations by presenting a comprehensive, task-oriented framework for understanding skeleton-based action recognition.
  arXiv  Detail & Related papers  (2025-06-01T09:04:12Z)
• Action Recognition Utilizing YGAR Dataset [5.922172844641853]
  The scarcity of high quality actions video data is a bottleneck in the research and application of action recognition. We present a new 3D actions data simulation engine and generate 3 sets of sample data to demonstrate its current functionalities.
  arXiv  Detail & Related papers  (2023-10-02T00:43:45Z)
• SkeleTR: Towrads Skeleton-based Action Recognition in the Wild [86.03082891242698]
  SkeleTR is a new framework for skeleton-based action recognition. It first models the intra-person skeleton dynamics for each skeleton sequence with graph convolutions. It then uses stacked Transformer encoders to capture person interactions that are important for action recognition in general scenarios.
  arXiv  Detail & Related papers  (2023-09-20T16:22:33Z)
• The Impact of Different Backbone Architecture on Autonomous Vehicle Dataset [120.08736654413637]
  The quality of the features extracted by the backbone architecture can have a significant impact on the overall detection performance. Our study evaluates three well-known autonomous vehicle datasets, namely KITTI, NuScenes, and BDD, to compare the performance of different backbone architectures on object detection tasks.
  arXiv  Detail & Related papers  (2023-09-15T17:32:15Z)
• Robust Activity Recognition for Adaptive Worker-Robot Interaction using Transfer Learning [0.0]
  This paper proposes a transfer learning methodology for activity recognition of construction workers. The developed algorithm transfers features from a model pre-trained by the original authors and fine-tunes them for the downstream task of activity recognition. Results indicate that the fine-tuned model can recognize distinct MMH tasks in a robust and adaptive manner.
  arXiv  Detail & Related papers  (2023-08-28T19:03:46Z)
• Representation-Centric Survey of Skeletal Action Recognition and the ANUBIS Benchmark [43.00059447663327]
  3D skeleton-based human action recognition has emerged as a powerful alternative to traditional RGB and depth-based approaches.<n>Despite remarkable progress, current research remains fragmented across diverse input representations.<n>ANUBIS is a large-scale, challenging skeleton action dataset designed to address critical gaps in existing benchmarks.
  arXiv  Detail & Related papers  (2022-05-04T14:03:43Z)
• Muscle Vision: Real Time Keypoint Based Pose Classification of Physical Exercises [52.77024349608834]
  3D human pose recognition extrapolated from video has advanced to the point of enabling real-time software applications. We propose a new machine learning pipeline and web interface that performs human pose recognition on a live video feed to detect when common exercises are performed and classify them accordingly.
  arXiv  Detail & Related papers  (2022-03-23T00:55:07Z)
• Human Activity Recognition models using Limited Consumer Device Sensors and Machine Learning [0.0]
  Human activity recognition has grown in popularity with its increase of applications within daily lifestyles and medical environments. This paper presents the findings of different models that are limited to train using sensor data from smartphones and smartwatches. Results show promise for models trained strictly using limited sensor data collected from only smartphones and smartwatches coupled with traditional machine learning concepts and algorithms.
  arXiv  Detail & Related papers  (2022-01-21T06:54:05Z)
• A Benchmark for Gait Recognition under Occlusion Collected by Multi-Kinect SDAS [6.922350076348358]
  We collect a new gait database called OG RGB+D database, which breaks through the limitation of other gait databases. Azure Kinect DK can simultaneously collect multimodal data to support different types of gait recognition algorithms. We propose a gait recognition method SkeletonGait based on human dual skeleton model.
  arXiv  Detail & Related papers  (2021-07-19T16:01:18Z)
• Revisiting Skeleton-based Action Recognition [107.08112310075114]
  PoseC3D is a new approach to skeleton-based action recognition, which relies on a 3D heatmap instead stack a graph sequence as the base representation of human skeletons. On four challenging datasets, PoseC3D consistently obtains superior performance, when used alone on skeletons and in combination with the RGB modality.
  arXiv  Detail & Related papers  (2021-04-28T06:32:17Z)
• Sensor Data for Human Activity Recognition: Feature Representation and Benchmarking [27.061240686613182]
  The field of Human Activity Recognition (HAR) focuses on obtaining and analysing data captured from monitoring devices (e.g. sensors) We address the issue of accurately recognising human activities using different Machine Learning (ML) techniques.
  arXiv  Detail & Related papers  (2020-05-15T00:46:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.