# Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition

arXiv: https://arxiv.org/abs/2302.02316 · HTML: https://mlsanity.com/paper/2302.02316/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 99 references that are in the map.
- First posted on arXiv 5 Feb 2023.

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [A Survey of Transformers](https://mlsanity.com/paper/2106.04554/) (2021)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition](https://mlsanity.com/paper/1607.07043/) (2016)
- [Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN](https://mlsanity.com/paper/1803.04831/) (2018)
- [Cross-view Action Modeling, Learning and Recognition](https://mlsanity.com/paper/1405.2941/) (2014)
- [A New Representation of Skeleton Sequences for 3D Action Recognition](https://mlsanity.com/paper/1703.03492/) (2017)
- [Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation](https://mlsanity.com/paper/1804.06055/) (2018)

## Built on by (most cited first, 17 of 17)

- [PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2304.07230/) (2023)
- [Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction](https://mlsanity.com/paper/2311.17408/) (2023)
- [BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction](https://mlsanity.com/paper/2502.14676/) (2025)
- [A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation](https://mlsanity.com/paper/2312.05830/) (2023)
- [DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition](https://mlsanity.com/paper/2302.12007/) (2023)
- [Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2308.12609/) (2023)
- [Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition](https://mlsanity.com/paper/2307.07791/) (2023)
- [CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer](https://mlsanity.com/paper/2307.13310/) (2023)
- [Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding](https://mlsanity.com/paper/2410.23570/) (2024)
- [EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis](https://mlsanity.com/paper/2506.10002/) (2025)
- [Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization](https://mlsanity.com/paper/2303.08463/) (2023)
- [A Generically Contrastive Spatiotemporal Representation Enhancement for 3D Skeleton Action Recognition](https://mlsanity.com/paper/2312.15144/) (2023)
- [Grid-Reg: Detector-Free Gridized Feature Learning and Matching for Large-Scale SAR-Optical Image Registration](https://mlsanity.com/paper/2507.04233/) (2025)
- [DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition](https://mlsanity.com/paper/2512.11941/) (2025)
- [Single Image Reflection Removal with Patch Reflectance Prior](https://mlsanity.com/paper/2312.03798/) (2023)
- [BC-GAN: A Generative Adversarial Network for Synthesizing a Batch of Collocated Clothing](https://mlsanity.com/paper/2502.01080/) (2025)
- [Adaptive Interaction Network for Human Motion Prediction During Human-Robot Collaboration](https://mlsanity.com/paper/2610.16624/) (2026)

## Abstract (arXiv)

Contrastive learning has been successfully leveraged to learn action representations for addressing the problem of semi-supervised skeleton-based action recognition. However, most contrastive learning-based methods only contrast global features mixing spatiotemporal information, which confuses the spatial- and temporal-specific information reflecting different semantic at the frame level and joint level. Thus, we propose a novel Spatiotemporal Decouple-and-Squeeze Contrastive Learning (SDS-CL) framework to comprehensively learn more abundant representations of skeleton-based actions by jointly contrasting spatial-squeezing features, temporal-squeezing features, and global features. In SDS-CL, we design a new Spatiotemporal-decoupling Intra-Inter Attention (SIIA) mechanism to obtain the spatiotemporal-decoupling attentive features for capturing spatiotemporal specific information by calculating spatial- and temporal-decoupling intra-attention maps among joint/motion features, as well as spatial- and temporal-decoupling inter-attention maps between joint and motion features. Moreover, we present a new Spatial-squeezing Temporal-contrasting Loss (STL), a new Temporal-squeezing Spatial-contrasting Loss (TSL), and the Global-contrasting Loss (GL) to contrast the spatial-squeezing joint and motion features at the frame level, temporal-squeezing joint and motion features at the joint level, as well as global joint and motion features at the skeleton level. Extensive experimental results on four public datasets show that the proposed SDS-CL achieves performance gains compared with other competitive methods.