mlsanityData to 14 Oct 2026

Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness

arXiv 2305.11468 ↗First posted 19 May 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-based action recognition, leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjacency matrix. However, an inherent flaw has come to light in these cutting-edge models: they tend to optimize the adjacency matrix jointly with the model weights. This process, while seemingly efficient, causes a gradual decay of bone connectivity data, culminating in a model indifferent to the very topology it sought to map. As a remedy, we propose a threefold strategy: (1) We forge an innovative pathway that encodes bone connectivity by harnessing the power of graph distances. This approach preserves the vital topological nuances often lost in conventional GCNs. (2) We highlight an oft-overlooked feature - the temporal mean of a skeletal sequence, which, despite its modest guise, carries highly action-specific information. (3) Our investigation revealed strong variations in joint-to-joint relationships across different actions. This finding exposes the limitations of a single adjacency matrix in capturing the variations of relational configurations emblematic of human movement, which we remedy by proposing an efficient refinement to Graph Convolutions (GC) - the BlockGC. This evolution slashes parameters by a substantial margin (above 40%), while elevating performance beyond original GCNs. Our full model, the BlockGCN, establishes new standards in skeleton-based action recognition for small model sizes. Its high accuracy, notably on the large-scale NTU RGB+D 120 dataset, stand as compelling proof of the efficacy of BlockGCN.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 34 of its 46 references that are in the map. First posted on arXiv 19 May 2023.

Builds on

34 of 46 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  9. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  10. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  11. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  12. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
22 more
  1. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  2. 2018Self-Attention with Relative Position Representationscited by 1,120
  3. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  4. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  5. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  6. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 339
  7. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  8. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  9. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 207
  10. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  11. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  12. 2016An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Datacited by 126
  13. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 126
  14. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  15. 2020Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognitioncited by 91
  16. 2021Constructing Stronger and Faster Baselines for Skeleton-based Action Recognitioncited by 87
  17. 2020Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognitioncited by 82
  18. 2020Spatial Temporal Transformer Network for Skeleton-based Action Recognitioncited by 77
  19. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  20. 2020Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognitioncited by 21
  21. 2023Graph Contrastive Learning for Skeleton-based Action Recognitioncited by 17
  22. 2022SP-ViT: Learning 2D Spatial Priors for Vision Transformerscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 1; 2026: 1.

8 papers.

  1. 2023Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognitioncited by 27
  2. 2023PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimationcited by 12
  3. 2023KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilaterationcited by 3
  4. 2024KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognitioncited by 3
  5. 2024POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Searchcited by 2
  6. 2025Content-Distortion High-Order Interaction for Blind Image Quality Assessmentcited by 2
  7. 2026KGS-GCN: Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Skeleton-Based Action Recognitioncited by 2
  8. 2023Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimationcited by 0