mlsanityData to 7 Oct 2026

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

arXiv 2602.23231 ↗First posted 26 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 26 Feb 2026.

Builds on

27 of 39 references.

References · 27

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  3. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  4. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  5. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  6. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  7. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  8. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  9. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  10. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 46
  11. 20233Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognitioncited by 40
  12. 2024LLMs are Good Action Recognizerscited by 36
15 more
  1. 2024Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognitioncited by 29
  2. 2023Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognitioncited by 27
  3. 2022DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognitioncited by 26
  4. 2020Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognitioncited by 23
  5. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  6. 2020SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognitioncited by 18
  7. 2021One-shot action recognition in challenging therapy scenarioscited by 15
  8. 2023One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matchingcited by 12
  9. 2021NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actionscited by 11
  10. 2024Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connectionscited by 11
  11. 2024Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognitioncited by 5
  12. 2024VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimationcited by 3
  13. 2025SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregationcited by 3
  14. 2025RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecondcited by 2
  15. 2025SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognitioncited by 1

Built on by

Not cited yet.