# LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition

arXiv: https://arxiv.org/abs/2407.14655 · HTML: https://mlsanity.com/paper/2407.14655/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 19 Jul 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [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)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Scatterbrain: Unifying Sparse and Low-rank Attention Approximation](https://mlsanity.com/paper/2110.15343/) (2021)
- [An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1611.06067/) (2016)
- [A New Representation of Skeleton Sequences for 3D Action Recognition](https://mlsanity.com/paper/1703.03492/) (2017)
- [The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction](https://mlsanity.com/paper/2312.13558/) (2023)
- [Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks](https://mlsanity.com/paper/2008.07404/) (2020)
- [Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2208.10741/) (2022)
- [A Survey on 3D Skeleton-Based Action Recognition Using Learning Method](https://mlsanity.com/paper/2002.05907/) (2020)
- [Hypergraph Transformer for Skeleton-based Action Recognition](https://mlsanity.com/paper/2211.09590/) (2022)
- [LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models](https://mlsanity.com/paper/2404.09695/) (2024)
- [STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition](https://mlsanity.com/paper/2312.03288/) (2023)

## Built on by (most cited first, 2 of 2)

- [SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders](https://mlsanity.com/paper/2411.19544/) (2024)
- [SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2604.02222/) (2026)

## Abstract (arXiv)

The complexity of state-of-the-art Transformer-based models for skeleton-based action recognition poses significant challenges in terms of computational efficiency and resource utilization. In this paper, we explore the application of Singular Value Decomposition (SVD) to effectively reduce the model sizes of these pre-trained models, aiming to minimize their resource consumption while preserving accuracy. Our method, LORTSAR (LOw-Rank Transformer for Skeleton-based Action Recognition), also includes a fine-tuning step to compensate for any potential accuracy degradation caused by model compression, and is applied to two leading Transformer-based models, "Hyperformer" and "STEP-CATFormer". Experimental results on the "NTU RGB+D" and "NTU RGB+D 120" datasets show that our method can reduce the number of model parameters substantially with negligible degradation or even performance increase in recognition accuracy. This confirms that SVD combined with post-compression fine-tuning can boost model efficiency, paving the way for more sustainable, lightweight, and high-performance technologies in human action recognition.