# A Survey on 3D Skeleton-Based Action Recognition Using Learning Method

arXiv: https://arxiv.org/abs/2002.05907 · HTML: https://mlsanity.com/paper/2002.05907/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2020.

## Built on by (most cited first, 30 of 47)

- [GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition](https://mlsanity.com/paper/2111.13089/) (2021)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning](https://mlsanity.com/paper/2407.05862/) (2024)
- [NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actions](https://mlsanity.com/paper/2101.11529/) (2021)
- [Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient](https://mlsanity.com/paper/2308.05681/) (2023)
- [STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition](https://mlsanity.com/paper/2312.03288/) (2023)
- [Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2209.10073/) (2022)
- [A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities](https://mlsanity.com/paper/2408.05436/) (2024)
- [HumanVLM: Foundation for Human-Scene Vision-Language Model](https://mlsanity.com/paper/2411.03034/) (2024)
- [An Efficient Framework for Few-shot Skeleton-based Temporal Action Segmentation](https://mlsanity.com/paper/2207.09925/) (2022)
- [Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack](https://mlsanity.com/paper/2211.11312/) (2022)
- [Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation](https://mlsanity.com/paper/2406.18011/) (2024)
- [3D Skeleton-Based Action Recognition: A Review](https://mlsanity.com/paper/2506.00915/) (2025)
- [MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition](https://mlsanity.com/paper/2404.10210/) (2024)
- [CityLoc: 6DoF Pose Distributional Localization for Text Descriptions in Large-Scale Scenes with Gaussian Representation](https://mlsanity.com/paper/2501.08982/) (2025)
- [HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition](https://mlsanity.com/paper/2502.05869/) (2025)
- [Transformers in Action Recognition: A Review on Temporal Modeling](https://mlsanity.com/paper/2302.01921/) (2022)
- [Enhancing Action Recognition from Low-Quality Skeleton Data via Part-Level Knowledge Distillation](https://mlsanity.com/paper/2404.18206/) (2024)
- [LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition](https://mlsanity.com/paper/2407.14655/) (2024)
- [Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics](https://mlsanity.com/paper/2408.01701/) (2024)
- [SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion](https://mlsanity.com/paper/2502.13385/) (2025)
- [A Generically Contrastive Spatiotemporal Representation Enhancement for 3D Skeleton Action Recognition](https://mlsanity.com/paper/2312.15144/) (2023)
- [PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection](https://mlsanity.com/paper/2408.14600/) (2024)
- [Evolving Skeletons: Motion Dynamics in Action Recognition](https://mlsanity.com/paper/2501.02593/) (2025)
- [Federated Action Recognition for Smart Worker Assistance Using FastPose](https://mlsanity.com/paper/2508.14113/) (2025)
- [Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework](https://mlsanity.com/paper/2508.17726/) (2025)
- [SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition](https://mlsanity.com/paper/2308.16018/) (2023)
- [Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space](https://mlsanity.com/paper/2407.08572/) (2024)
- [Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities](https://mlsanity.com/paper/2408.14585/) (2024)
- [A transition towards virtual representations of visual scenes](https://mlsanity.com/paper/2410.07987/) (2024)

## Abstract (arXiv)

3D skeleton-based action recognition (3D SAR) has gained significant attention within the computer vision community, owing to the inherent advantages offered by skeleton data. As a result, a plethora of impressive works, including those based on conventional handcrafted features and learned feature extraction methods, have been conducted over the years. However, prior surveys on action recognition have primarily focused on video or RGB data-dominated approaches, with limited coverage of reviews related to skeleton data. Furthermore, despite the extensive application of deep learning methods in this field, there has been a notable absence of research that provides an introductory or comprehensive review from the perspective of deep learning architectures. To address these limitations, this survey first underscores the importance of action recognition and emphasizes the significance of 3D skeleton data as a valuable modality. Subsequently, we provide a comprehensive introduction to mainstream action recognition techniques based on four fundamental deep architectures, i.e., Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), Graph Convolutional Network (GCN), and Transformers. All methods with the corresponding architectures are then presented in a data-driven manner with detailed discussion. Finally, we offer insights into the current largest 3D skeleton dataset, NTU-RGB+D, and its new edition, NTU-RGB+D 120, along with an overview of several top-performing algorithms on these datasets. To the best of our knowledge, this research represents the first comprehensive discussion of deep learning-based action recognition using 3D skeleton data.