# Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networks

arXiv: https://arxiv.org/abs/2301.11495 · HTML: https://mlsanity.com/paper/2301.11495/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 60 references that are in the map.
- First posted on arXiv 27 Jan 2023.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Audio-Visual Scene Analysis with Self-Supervised Multisensory Features](https://mlsanity.com/paper/1804.03641/) (2018)
- [Learning Convolutional Neural Networks for Graphs](https://mlsanity.com/paper/1605.05273/) (2016)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Unsupervised Representation Learning by Sorting Sequences](https://mlsanity.com/paper/1708.01246/) (2017)
- [End-to-End Dense Video Captioning with Masked Transformer](https://mlsanity.com/paper/1804.00819/) (2018)
- [Recurrent Neural Network Regularization](https://mlsanity.com/paper/1409.2329/) (2014)
- [Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition](https://mlsanity.com/paper/1607.07043/) (2016)
- [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)
- [3D Human Action Representation Learning via Cross-View Consistency Pursuit](https://mlsanity.com/paper/2104.14466/) (2021)
- [Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks](https://mlsanity.com/paper/2008.07404/) (2020)
- [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)
- [Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition](https://mlsanity.com/paper/2112.03590/) (2021)

## Built on by (most cited first, 9 of 9)

- [Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2305.12398/) (2023)
- [A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation](https://mlsanity.com/paper/2312.05830/) (2023)
- [GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition](https://mlsanity.com/paper/2401.10039/) (2024)
- [An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2406.00639/) (2024)
- [Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition](https://mlsanity.com/paper/2307.07791/) (2023)
- [Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows](https://mlsanity.com/paper/2404.17381/) (2024)
- [Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis](https://mlsanity.com/paper/2503.00371/) (2025)
- [Learning Adaptive Node Selection with External Attention for Human Interaction Recognition](https://mlsanity.com/paper/2507.03936/) (2025)
- [Learning Pyramid-structured Long-range Dependencies for 3D Human Pose Estimation](https://mlsanity.com/paper/2506.02853/) (2025)

## Abstract (arXiv)

For pursuing accurate skeleton-based action recognition, most prior methods use the strategy of combining Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete graph, resulting in less variations between different actions (e.g., the connection between the elbow and head in action ``clapping hands''). For this, we propose a novel Contrastive GCN-Transformer Network (ConGT) which fuses the spatial and temporal modules in a parallel way. The ConGT involves two parallel streams: Spatial-Temporal Graph Convolution stream (STG) and Spatial-Temporal Transformer stream (STT). The STG is designed to obtain action representations maintaining the natural topology structure of the human skeleton. The STT is devised to acquire action representations containing the global relationships among joints. Since the action representations produced from these two streams contain different characteristics, and each of them knows little information of the other, we introduce the contrastive learning paradigm to guide their output representations of the same sample to be as close as possible in a self-supervised manner. Through the contrastive learning, they can learn information from each other to enrich the action features by maximizing the mutual information between the two types of action representations. To further improve action recognition accuracy, we introduce the Cyclical Focal Loss (CFL) which can focus on confident training samples in early training epochs, with an increasing focus on hard samples during the middle epochs. We conduct experiments on three benchmark datasets, which demonstrate that our model achieves state-of-the-art performance in action recognition.