# SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition

arXiv: https://arxiv.org/abs/2209.02399 · HTML: https://mlsanity.com/paper/2209.02399/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 51 references that are in the map.
- First posted on arXiv 1 Sep 2022.

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1611.06067/) (2016)
- [3D Human Action Representation Learning via Cross-View Consistency Pursuit](https://mlsanity.com/paper/2104.14466/) (2021)
- [MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition](https://mlsanity.com/paper/2010.05599/) (2020)
- [Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition](https://mlsanity.com/paper/2112.03590/) (2021)
- [Interpretable 3D Human Action Analysis with Temporal Convolutional Networks](https://mlsanity.com/paper/1704.04516/) (2017)

## Built on by (most cited first, 29 of 29)

- [SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training](https://mlsanity.com/paper/2307.08476/) (2023)
- [Masked Motion Predictors are Strong 3D Action Representation Learners](https://mlsanity.com/paper/2308.07092/) (2023)
- [Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning](https://mlsanity.com/paper/2308.03975/) (2023)
- [MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion](https://mlsanity.com/paper/2409.10473/) (2024)
- [Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning](https://mlsanity.com/paper/2405.20606/) (2024)
- [Foundation Model for Skeleton-Based Human Action Understanding](https://mlsanity.com/paper/2508.12586/) (2025)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Deep Learning Approaches for Seizure Video Analysis: A Review](https://mlsanity.com/paper/2312.10930/) (2023)
- [Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond](https://mlsanity.com/paper/2406.02978/) (2024)
- [Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition](https://mlsanity.com/paper/2411.05692/) (2024)
- [Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2505.23012/) (2025)
- [STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences](https://mlsanity.com/paper/2407.10935/) (2024)
- [Towards Efficient General Feature Prediction in Masked Skeleton Modeling](https://mlsanity.com/paper/2509.03609/) (2025)
- [Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence](https://mlsanity.com/paper/2401.00921/) (2024)
- [Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning](https://mlsanity.com/paper/2407.01397/) (2024)
- [FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition](https://mlsanity.com/paper/2412.20621/) (2024)
- [A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion](https://mlsanity.com/paper/2603.25283/) (2026)
- [Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/2605.07140/) (2026)
- [Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition](https://mlsanity.com/paper/2409.17951/) (2024)
- [SPAR: Self-supervised Placement-Aware Representation Learning for Distributed Sensing](https://mlsanity.com/paper/2505.16936/) (2025)
- [MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation](https://mlsanity.com/paper/2508.12948/) (2025)
- [ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning](https://mlsanity.com/paper/2602.06251/) (2026)
- [Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning](https://mlsanity.com/paper/2602.22791/) (2026)
- [Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models](https://mlsanity.com/paper/2603.05963/) (2026)
- [Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors](https://mlsanity.com/paper/2604.17914/) (2026)
- [Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition](https://mlsanity.com/paper/2609.02510/) (2026)
- [One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation Learning](https://mlsanity.com/paper/2609.07078/) (2026)
- [SignMimic: Robust High-Quality Sign Language Motion Generation via Human-Shape-Oblivious Pose Transfer Guidance](https://mlsanity.com/paper/2609.14122/) (2026)
- [DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2609.35444/) (2026)

## Abstract (arXiv)

Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised skeleton-based action recognition has attracted more attention. With utilizing the unlabeled data, more generalizable features can be learned to alleviate the overfitting problem and reduce the demand of massive labeled training data. Inspired by the MAE, we propose a spatial-temporal masked autoencoder framework for self-supervised 3D skeleton-based action recognition (SkeletonMAE). Following MAE's masking and reconstruction pipeline, we utilize a skeleton-based encoder-decoder transformer architecture to reconstruct the masked skeleton sequences. A novel masking strategy, named Spatial-Temporal Masking, is introduced in terms of both joint-level and frame-level for the skeleton sequence. This pre-training strategy makes the encoder output generalizable skeleton features with spatial and temporal dependencies. Given the unmasked skeleton sequence, the encoder is fine-tuned for the action recognition task. Extensive experiments show that our SkeletonMAE achieves remarkable performance and outperforms the state-of-the-art methods on both NTU RGB+D and NTU RGB+D 120 datasets.