# Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?

arXiv: https://arxiv.org/abs/2505.10679 · HTML: https://mlsanity.com/paper/2505.10679/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 55 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 30 of 34)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [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)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [The Lottery Ticket Hypothesis for Pre-trained BERT Networks](https://mlsanity.com/paper/2007.12223/) (2020)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [Comparing Rewinding and Fine-tuning in Neural Network Pruning](https://mlsanity.com/paper/2003.02389/) (2020)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask](https://mlsanity.com/paper/1905.01067/) (2019)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [A New Representation of Skeleton Sequences for 3D Action Recognition](https://mlsanity.com/paper/1703.03492/) (2017)
- [A Unified Lottery Ticket Hypothesis for Graph Neural Networks](https://mlsanity.com/paper/2102.06790/) (2021)
- [Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1912.06971/) (2019)
- [PYSKL: Towards Good Practices for Skeleton Action Recognition](https://mlsanity.com/paper/2205.09443/) (2022)
- [Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks](https://mlsanity.com/paper/1707.05740/) (2017)
- [VPN: Learning Video-Pose Embedding for Activities of Daily Living](https://mlsanity.com/paper/2007.03056/) (2020)
- [Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning](https://mlsanity.com/paper/1805.02335/) (2018)
- [Playing Lottery Tickets with Vision and Language](https://mlsanity.com/paper/2104.11832/) (2021)
- [SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition](https://mlsanity.com/paper/1907.13025/) (2019)
- [STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition](https://mlsanity.com/paper/2210.07503/) (2022)
- [Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition](https://mlsanity.com/paper/2008.03791/) (2020)

## Built on by (most cited first, 5 of 5)

- [DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions](https://mlsanity.com/paper/2605.20680/) (2026)
- [Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition](https://mlsanity.com/paper/2604.17090/) (2026)
- [An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories](https://mlsanity.com/paper/2605.09231/) (2026)
- [EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration](https://mlsanity.com/paper/2607.04472/) (2026)
- [De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift](https://mlsanity.com/paper/2609.32454/) (2026)

## Abstract (arXiv)

Spatial-temporal graph convolutional networks (ST-GCNs) showcase impressive performance in skeleton-based human action recognition (HAR). However, despite the development of numerous models, their recognition performance does not differ significantly after aligning the input settings. With this observation, we hypothesize that ST-GCNs are over-parameterized for HAR, a conjecture subsequently confirmed through experiments employing the lottery ticket hypothesis. Additionally, a novel sparse ST-GCNs generator is proposed, which trains a sparse architecture from a randomly initialized dense network while maintaining comparable performance levels to the dense components. Moreover, we generate multi-level sparsity ST-GCNs by integrating sparse structures at various sparsity levels and demonstrate that the assembled model yields a significant enhancement in HAR performance. Thorough experiments on four datasets, including NTU-RGB+D 60(120), Kinetics-400, and FineGYM, demonstrate that the proposed sparse ST-GCNs can achieve comparable performance to their dense components. Even with 95% fewer parameters, the sparse ST-GCNs exhibit a degradation of <1% in top-1 accuracy. Meanwhile, the multi-level sparsity ST-GCNs, which require only 66% of the parameters of the dense ST-GCNs, demonstrate an improvement of >1% in top-1 accuracy. The code is available at https://github.com/davelailai/Sparse-ST-GCN.