mlsanityData to 7 Oct 2026

Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition

arXiv 2107.12213 ↗First posted 26 Jul 2021cs.CVcited by 317

Not on the map. Why?

Abstract (arXiv)

Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. In GCNs, graph topology dominates feature aggregation and therefore is the key to extracting representative features. In this work, we propose a novel Channel-wise Topology Refinement Graph Convolution (CTR-GC) to dynamically learn different topologies and effectively aggregate joint features in different channels for skeleton-based action recognition. The proposed CTR-GC models channel-wise topologies through learning a shared topology as a generic prior for all channels and refining it with channel-specific correlations for each channel. Our refinement method introduces few extra parameters and significantly reduces the difficulty of modeling channel-wise topologies. Furthermore, via reformulating graph convolutions into a unified form, we find that CTR-GC relaxes strict constraints of graph convolutions, leading to stronger representation capability. Combining CTR-GC with temporal modeling modules, we develop a powerful graph convolutional network named CTR-GCN which notably outperforms state-of-the-art methods on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.

Key facts. Cited by 317 papers in the map (data through 7 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 26 Jul 2021.

Builds on

25 of 36 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  5. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  6. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  7. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  8. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  9. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  10. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  11. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  12. 2016Learning Convolutional Neural Networks for Graphscited by 314
13 more
  1. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  2. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  3. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  4. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 142
  5. 2018Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNNcited by 142
  6. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  7. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  8. 2018Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregationcited by 106
  9. 2020Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognitioncited by 91
  10. 2020Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognitioncited by 82
  11. 2017Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networkscited by 62
  12. 2015Differential Recurrent Neural Networks for Action Recognitioncited by 39
  13. 2020Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 38; 2023: 80; 2024: 71; 2025: 66; 2026: 58.

317 papers.

Sort:

By area:

  1. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  2. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  3. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  4. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  5. 2023MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensingcited by 77
  6. 2023Learning Discriminative Representations for Skeleton Based Action Recognitioncited by 62
  7. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
  8. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  9. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 46
  10. 2022Generative Action Description Prompts for Skeleton-based Action Recognitioncited by 43
  11. 2022STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognitioncited by 43
  12. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 42
38 more
  1. 2023Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognitioncited by 41
  2. 2023SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-trainingcited by 41
  3. 2023Masked Motion Predictors are Strong 3D Action Representation Learnerscited by 41
  4. 20233Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognitioncited by 40
  5. 2022CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillationcited by 38
  6. 2022Hypergraph Transformer for Skeleton-based Action Recognitioncited by 36
  7. 2024LLMs are Good Action Recognizerscited by 36
  8. 2022IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognitioncited by 31
  9. 2022Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentationscited by 31
  10. 2023Gloss-Free End-to-End Sign Language Translationcited by 31
  11. 2021Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognitioncited by 29
  12. 2024Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognitioncited by 29
  13. 2022Holistic Interaction Transformer Network for Action Detectioncited by 28
  14. 2022A Survey on Video Action Recognition in Sports: Datasets, Methods and Applicationscited by 27
  15. 2023Motion Question Answering via Modular Motion Programscited by 27
  16. 2023Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognitioncited by 27
  17. 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 27
  18. 2022Versatile Multi-Modal Pre-Training for Human-Centric Perceptioncited by 26
  19. 2022DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognitioncited by 26
  20. 2023Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classificationcited by 24
  21. 2022FLAG3D: A 3D Fitness Activity Dataset with Language Instructioncited by 23
  22. 2023Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognitioncited by 23
  23. 2024Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognitioncited by 23
  24. 2022ViA: View-invariant Skeleton Action Representation Learning via Motion Retargetingcited by 22
  25. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  26. 2024Prototypical Calibrating Ambiguous Samples for Micro-Action Recognitioncited by 22
  27. 2021ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpointscited by 20
  28. 2022Cross-Modal Learning with 3D Deformable Attention for Action Recognitioncited by 20
  29. 2023DVANet: Disentangling View and Action Features for Multi-View Action Recognitioncited by 19
  30. 2024Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognitioncited by 19
  31. 2025HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generationcited by 19
  32. 2022Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognitioncited by 18
  33. 2024UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editingcited by 18
  34. 2023Ancilia: Scalable Intelligent Video Surveillance for the Artificial Intelligence of Thingscited by 17
  35. 2023Graph Contrastive Learning for Skeleton-based Action Recognitioncited by 17
  36. 2023Navigating Open Set Scenarios for Skeleton-based Action Recognitioncited by 17
  37. 2024Prototype Learning for Micro-gesture Classificationcited by 17
  38. 2023Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognitioncited by 16

50 most cited of 317 All 317 (JSON)