# UniSTFormer: Unified Spatio-Temporal Lightweight Transformer for Efficient Skeleton-Based Action Recognition

arXiv: https://arxiv.org/abs/2508.08944 · HTML: https://mlsanity.com/paper/2508.08944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Builds on (most cited first, 12 of 12)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [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)
- [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)
- [Cross-view Action Modeling, Learning and Recognition](https://mlsanity.com/paper/1405.2941/) (2014)
- [Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks](https://mlsanity.com/paper/2008.07404/) (2020)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Learning Discriminative Representations for Skeleton Based Action Recognition](https://mlsanity.com/paper/2303.03729/) (2023)
- [SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition](https://mlsanity.com/paper/2403.09508/) (2024)
- [Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer](https://mlsanity.com/paper/2407.12322/) (2024)
- [FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition](https://mlsanity.com/paper/2412.20621/) (2024)

## Abstract (arXiv)

Skeleton-based action recognition (SAR) has achieved impressive progress with transformer architectures. However, existing methods often rely on complex module compositions and heavy designs, leading to increased parameter counts, high computational costs, and limited scalability. In this paper, we propose a unified spatio-temporal lightweight transformer framework that integrates spatial and temporal modeling within a single attention module, eliminating the need for separate temporal modeling blocks. This approach reduces redundant computations while preserving temporal awareness within the spatial modeling process. Furthermore, we introduce a simplified multi-scale pooling fusion module that combines local and global pooling pathways to enhance the model's ability to capture fine-grained local movements and overarching global motion patterns. Extensive experiments on benchmark datasets demonstrate that our lightweight model achieves a superior balance between accuracy and efficiency, reducing parameter complexity by over 58% and lowering computational cost by over 60% compared to state-of-the-art transformer-based baselines, while maintaining competitive recognition performance.