mlsanityData to 7 Oct 2026

Skeleton-based Action Recognition via Temporal-Channel Aggregation

arXiv 2205.15936 ↗First posted 31 May 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Skeleton-based action recognition methods are limited by the semantic extraction of spatio-temporal skeletal maps. However, current methods have difficulty in effectively combining features from both temporal and spatial graph dimensions and tend to be thick on one side and thin on the other. In this paper, we propose a Temporal-Channel Aggregation Graph Convolutional Networks (TCA-GCN) to learn spatial and temporal topologies dynamically and efficiently aggregate topological features in different temporal and channel dimensions for skeleton-based action recognition. We use the Temporal Aggregation module to learn temporal dimensional features and the Channel Aggregation module to efficiently combine spatial dynamic channel-wise topological features with temporal dynamic topological features. In addition, we extract multi-scale skeletal features on temporal modeling and fuse them with an attention mechanism. Extensive experiments show that our model results outperform state-of-the-art methods on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 51 of its 67 references that are in the map. First posted on arXiv 31 May 2022.

Builds on

51 of 67 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  10. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  11. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  12. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
38 more
  1. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  2. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  3. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  4. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  5. 2016Learning Convolutional Neural Networks for Graphscited by 314
  6. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  7. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  8. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 142
  9. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  10. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  11. 2016An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Datacited by 126
  12. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 125
  13. 2020Attentional Feature Fusioncited by 115
  14. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  15. 2020Skeleton-based Action Recognition via Spatial and Temporal Transformer Networkscited by 98
  16. 2020Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognitioncited by 91
  17. 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 88
  18. 2021Constructing Stronger and Faster Baselines for Skeleton-based Action Recognitioncited by 87
  19. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  20. 2020Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognitioncited by 82
  21. 2019LanczosNet: Multi-Scale Deep Graph Convolutional Networkscited by 73
  22. 2019Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searchingcited by 70
  23. 2019Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networkscited by 62
  24. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  25. 2016Going Deeper into Action Recognition: A Surveycited by 55
  26. 2017Skeleton-based Action Recognition with Convolutional Neural Networkscited by 54
  27. 2019Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Predictioncited by 50
  28. 2015Differential Recurrent Neural Networks for Action Recognitioncited by 39
  29. 2020Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognitioncited by 36
  30. 2021TAda! Temporally-Adaptive Convolutions for Video Understandingcited by 36
  31. 2018Glimpse Clouds: Human Activity Recognition from Unstructured Feature Pointscited by 33
  32. 2017Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnncited by 26
  33. 2021Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognitioncited by 25
  34. 2017Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognitioncited by 23
  35. 2020Feedback Graph Convolutional Network for Skeleton-based Action Recognitioncited by 22
  36. 2021Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognitioncited by 22
  37. 2019Skeleton-Based Online Action Prediction Using Scale Selection Networkcited by 20
  38. 2019Richly Activated Graph Convolutional Network for Action Recognition with Incomplete Skeletonscited by 12

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 7; 2024: 2; 2025: 4.

13 papers.

Sort:

By area:

  1. 2023Learning Discriminative Representations for Skeleton Based Action Recognitioncited by 62
  2. 2023Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognitioncited by 23
  3. 2024Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognitioncited by 12
  4. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  5. 2024Two-Person Interaction Augmentation with Skeleton Priorscited by 5
  6. 2023Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognitioncited by 4
  7. 2023A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognitioncited by 3
  8. 2025SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregationcited by 3
  9. 2023Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognitioncited by 2
  10. 2025Action Recognition in Real-World Ambient Assisted Living Environmentcited by 2
  11. 2025Learning Adaptive Node Selection with External Attention for Human Interaction Recognitioncited by 1
  12. 2023Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognitioncited by 0
1 more
  1. 2025TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognitioncited by 0