mlsanityData to 7 Oct 2026

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

arXiv 1801.07455 ↗First posted 23 Jan 2018cs.CVcited by 1,199

Not on the map. Why?

Abstract (arXiv)

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

Key facts. Cited by 1,199 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 210; 2022: 221; 2023: 218; 2024: 207; 2025: 192; 2026: 151.

1,199 papers.

Sort:

By area:

  1. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  2. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  3. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
  4. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  5. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 251
  6. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  7. 2022Vision GNN: An Image is Worth Graph of Nodescited by 185
  8. 2021Graph Learning: A Surveycited by 140
  9. 2021Hyperbolic Deep Neural Networks: A Surveycited by 138
  10. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  11. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 116
  12. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
38 more
  1. 2021GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognitioncited by 114
  2. 20213D Human Action Representation Learning via Cross-View Consistency Pursuitcited by 105
  3. 2021Skeleton Aware Multi-modal Sign Language Recognitioncited by 101
  4. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
  5. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
  6. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  7. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  8. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 95
  9. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  10. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  11. 2022Towards Diverse and Natural Scene-aware 3D Human Motion Synthesiscited by 91
  12. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 89
  13. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  14. 2021Constructing Stronger and Faster Baselines for Skeleton-based Action Recognitioncited by 87
  15. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  16. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  17. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  18. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  19. 2021Graph Representation Learning in Biomedicinecited by 79
  20. 2022ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generationcited by 77
  21. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
  22. 2021Group-aware Contrastive Regression for Action Quality Assessmentcited by 75
  23. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  24. 2021Scene-aware Generative Network for Human Motion Synthesiscited by 70
  25. 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
  26. 2021Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecastingcited by 67
  27. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  28. 2022UDE: A Unified Driving Engine for Human Motion Generationcited by 67
  29. 2022Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Predictioncited by 66
  30. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  31. 2022Motion Puzzle: Arbitrary Motion Style Transfer by Body Partcited by 64
  32. 2022When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learningcited by 64
  33. 2021iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysiscited by 63
  34. 2021A Review of Graph Neural Networks and Their Applications in Power Systemscited by 62
  35. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  36. 2023Learning Discriminative Representations for Skeleton Based Action Recognitioncited by 62
  37. 2021Temporal Knowledge Graph Forecasting with Neural ODEcited by 61
  38. 2021SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognitioncited by 59

50 most cited of 1,199 All 1,199 (JSON)