mlsanityData to 7 Oct 2026

Skeleton-Based Human Action Recognition with Noisy Labels

arXiv 2403.09975 ↗First posted 15 Mar 2024cs.CV cs.RO eess.IVcited by 8

Not on the map. Why?

Abstract (arXiv)

Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of activity sequences is time-consuming and the resulting labels are often noisy. If not effectively addressed, label noise negatively affects the model's training, resulting in lower recognition quality. Despite its importance, addressing label noise for skeleton-based action recognition has been overlooked so far. In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark. Observations reveal that these baselines yield only marginal performance when dealing with sparse skeleton data. Consequently, we introduce a novel methodology, NoiseEraSAR, which integrates global sample selection, co-teaching, and Cross-Modal Mixture-of-Experts (CM-MOE) strategies, aimed at mitigating the adverse impacts of label noise. Our proposed approach demonstrates better performance on the established benchmark, setting new state-of-the-art standards. The source code for this study is accessible at https://github.com/xuyizdby/NoiseEraSAR.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 15 Mar 2024.

Builds on

32 of 48 references.

References · 32

  1. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  2. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  3. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  4. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  5. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  6. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  7. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  8. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  9. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  10. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  11. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  12. 2019Learning From Noisy Labels By Regularized Estimation Of Annotator Confusioncited by 126
20 more
  1. 2019Meta Label Correction for Noisy Label Learningcited by 108
  2. 2022Robust Training under Label Noise by Over-parameterizationcited by 93
  3. 2020A Second-Order Approach to Learning with Instance-Dependent Label Noisecited by 90
  4. 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 88
  5. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  6. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  7. 2020Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognitioncited by 82
  8. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  9. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  10. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  11. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  12. 2022STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognitioncited by 43
  13. 2016Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networkscited by 32
  14. 2020Weakly Supervised Learning with Side Information for Noisy Labeled Imagescited by 30
  15. 2022Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Featurescited by 27
  16. 2021Mitigating Memorization of Noisy Labels via Regularization between Representationscited by 26
  17. 2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 21
  18. 2021Adaptive Sample Selection for Robust Learning under Label Noisecited by 20
  19. 2023Navigating Open Set Scenarios for Skeleton-based Action Recognitioncited by 17
  20. 2019Self-Attention Network for Skeleton-based Human Action Recognitioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 4.

8 papers.

  1. 2024Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalizationcited by 6
  2. 2024Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activationscited by 3
  3. 2025Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognitioncited by 3
  4. 2026IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Constructioncited by 2
  5. 2025EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labelscited by 1
  6. 2026BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognitioncited by 0
  7. 2026From Skeletons to Semantics: Design and Deployment of a Hybrid Edge-Based Action Detection System for Public Safetycited by 0
  8. 2026IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 20253D Skeleton-Based Action Recognition: A Review
  2. 2023Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition
  3. 2026T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition
  4. 2025SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition
  5. 2026Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition
  6. 2025Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment
  7. 2024SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders
  8. 2024Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition