# Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences

arXiv: https://arxiv.org/abs/2302.09018 · HTML: https://mlsanity.com/paper/2302.09018/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Builds on (most cited first, 27 of 27)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [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)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [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)
- [Learning Representations for Automatic Colorization](https://mlsanity.com/paper/1603.06668/) (2016)
- [A New Representation of Skeleton Sequences for 3D Action Recognition](https://mlsanity.com/paper/1703.03492/) (2017)
- [3D Human Action Representation Learning via Cross-View Consistency Pursuit](https://mlsanity.com/paper/2104.14466/) (2021)
- [View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1703.08274/) (2017)
- [MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition](https://mlsanity.com/paper/2010.05599/) (2020)
- [PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition](https://mlsanity.com/paper/1911.12409/) (2019)
- [Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition](https://mlsanity.com/paper/2010.09978/) (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)
- [Skeleton-Contrastive 3D Action Representation Learning](https://mlsanity.com/paper/2108.03656/) (2021)
- [Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2206.13028/) (2022)
- [Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition](https://mlsanity.com/paper/2008.00188/) (2020)
- [Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning](https://mlsanity.com/paper/1812.00329/) (2018)
- [Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network](https://mlsanity.com/paper/2105.10882/) (2021)

## Built on by (most cited first, 25 of 25)

- [SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training](https://mlsanity.com/paper/2307.08476/) (2023)
- [Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization](https://mlsanity.com/paper/2308.03950/) (2023)
- [Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding](https://mlsanity.com/paper/2311.03106/) (2023)
- [USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation](https://mlsanity.com/paper/2412.09220/) (2024)
- [Heterogeneous Skeleton-Based Action Representation Learning](https://mlsanity.com/paper/2506.03481/) (2025)
- [SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition](https://mlsanity.com/paper/2309.05834/) (2023)
- [Foundation Model for Skeleton-Based Human Action Understanding](https://mlsanity.com/paper/2508.12586/) (2025)
- [Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient](https://mlsanity.com/paper/2308.05681/) (2023)
- [Spatio-Temporal Branching for Motion Prediction using Motion Increments](https://mlsanity.com/paper/2308.01097/) (2023)
- [3D Skeleton-Based Action Recognition: A Review](https://mlsanity.com/paper/2506.00915/) (2025)
- [Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond](https://mlsanity.com/paper/2406.02978/) (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)
- [Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence](https://mlsanity.com/paper/2401.00921/) (2024)
- [DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation](https://mlsanity.com/paper/2509.05543/) (2025)
- [Attack-Augmentation Mixing-Contrastive Skeletal Representation Learning](https://mlsanity.com/paper/2304.04023/) (2023)
- [Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision](https://mlsanity.com/paper/2309.12009/) (2023)
- [Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition](https://mlsanity.com/paper/2512.21064/) (2025)
- [Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments](https://mlsanity.com/paper/2309.12029/) (2023)
- [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)
- [Toward Universal Skeleton-Based Action Recognition across Heterogeneous Skeletons and Open Vocabularies](https://mlsanity.com/paper/2604.17013/) (2026)
- [Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors](https://mlsanity.com/paper/2604.17914/) (2026)
- [One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation Learning](https://mlsanity.com/paper/2609.07078/) (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)

Self-supervised learning has demonstrated remarkable capability in representation learning for skeleton-based action recognition. Existing methods mainly focus on applying global data augmentation to generate different views of the skeleton sequence for contrastive learning. However, due to the rich action clues in the skeleton sequences, existing methods may only take a global perspective to learn to discriminate different skeletons without thoroughly leveraging the local relationship between different skeleton joints and video frames, which is essential for real-world applications. In this work, we propose a Partial Spatio-Temporal Learning (PSTL) framework to exploit the local relationship from a partial skeleton sequences built by a unique spatio-temporal masking strategy. Specifically, we construct a negative-sample-free triplet steam structure that is composed of an anchor stream without any masking, a spatial masking stream with Central Spatial Masking (CSM), and a temporal masking stream with Motion Attention Temporal Masking (MATM). The feature cross-correlation matrix is measured between the anchor stream and the other two masking streams, respectively. (1) Central Spatial Masking discards selected joints from the feature calculation process, where the joints with a higher degree of centrality have a higher possibility of being selected. (2) Motion Attention Temporal Masking leverages the motion of action and remove frames that move faster with a higher possibility. Our method achieves SOTA performance on NTU-60, NTU-120 and PKU-MMD under various downstream tasks. A practical evaluation is performed where some skeleton joints are lost in downstream tasks. In contrast to previous methods that suffer from large performance drops, our PSTL can still achieve remarkable results, validating the robustness of our method. Code: https://github.com/YujieOuO/PSTL.git.