mlsanityData to 7 Oct 2026

Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance

arXiv 2204.10312 ↗First posted 21 Apr 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel end-to-end method for the problem of skeleton-based unsupervised human action recognition. We propose a new architecture with a convolutional autoencoder that uses graph Laplacian regularization to model the skeletal geometry across the temporal dynamics of actions. Our approach is robust towards viewpoint variations by including a self-supervised gradient reverse layer that ensures generalization across camera views. The proposed method is validated on NTU-60 and NTU-120 large-scale datasets in which it outperforms all prior unsupervised skeleton-based approaches on the cross-subject, cross-view, and cross-setup protocols. Although unsupervised, our learnable representation allows our method even to surpass a few supervised skeleton-based action recognition methods. The code is available in: www.github.com/IIT-PAVIS/UHAR_Skeletal_Laplacian

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 21 Apr 2022.

Builds on

20 of 34 references.

References · 20

  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  2. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  3. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  4. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  5. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  6. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  7. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 142
  8. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  9. 20213D Human Action Representation Learning via Cross-View Consistency Pursuitcited by 105
  10. 2020MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognitioncited by 92
  11. 2019PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognitioncited by 90
  12. 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 88
8 more
  1. 2020Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognitioncited by 59
  2. 2017Skeleton-based Action Recognition with Convolutional Neural Networkscited by 54
  3. 2018Unsupervised Learning of View-invariant Action Representationscited by 32
  4. 2014Histogram of Oriented Principal Components for Cross-View Action Recognitioncited by 27
  5. 2018Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifoldcited by 26
  6. 2020Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognitioncited by 25
  7. 2020Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruningcited by 6
  8. 2017Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machinescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 2; 2024: 1; 2025: 2; 2026: 2.

10 papers.

  1. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 42
  2. 2022Multimodal Across Domains Gaze Target Detectioncited by 22
  3. 2022Multimodal Emotion Recognition with Modality-Pairwise Unsupervised Contrastive Losscited by 7
  4. 2022Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Surveycited by 6
  5. 2023Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognitioncited by 6
  6. 2025Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentationcited by 6
  7. 2024Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyondcited by 5
  8. 2025Feature Hallucination for Self-supervised Action Recognitioncited by 3
  9. 2026Unsupervised Skeleton-Based Action Segmentation via Hierarchical Spatiotemporal Vector Quantizationcited by 0
  10. 2026TReViS: Temporal Repetition Structure Aware Video Synthesis for Self-supervised Repetitive Action Countingcited by 0