# SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation

arXiv: https://arxiv.org/abs/2504.11749 · HTML: https://mlsanity.com/paper/2504.11749/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 56 references that are in the map.
- First posted on arXiv 16 Apr 2025.

## Builds on (most cited first, 30 of 32)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [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)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [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)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose](https://mlsanity.com/paper/1611.07828/) (2016)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2208.10741/) (2022)
- [Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks](https://mlsanity.com/paper/1707.05740/) (2017)
- [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)
- [A Survey on Data Synthesis and Augmentation for Large Language Models](https://mlsanity.com/paper/2410.12896/) (2024)
- [DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition](https://mlsanity.com/paper/2210.05895/) (2022)
- [Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition](https://mlsanity.com/paper/2012.13823/) (2020)
- [Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition](https://mlsanity.com/paper/2210.16820/) (2022)
- [Uncertainty-DTW for Time Series and Sequences](https://mlsanity.com/paper/2211.00005/) (2022)
- [SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition](https://mlsanity.com/paper/2004.11085/) (2020)
- [One-shot action recognition in challenging therapy scenarios](https://mlsanity.com/paper/2102.08997/) (2021)
- [Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions](https://mlsanity.com/paper/2202.11423/) (2022)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)
- [One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching](https://mlsanity.com/paper/2307.07286/) (2023)
- [CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner](https://mlsanity.com/paper/2403.10082/) (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, 3 of 3)

- [Skarimva: Skeleton-based Action Recognition is a Multi-view Application](https://mlsanity.com/paper/2602.23231/) (2026)
- [SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition](https://mlsanity.com/paper/2606.03610/) (2026)
- [StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring](https://mlsanity.com/paper/2608.01643/) (2026)

## Abstract (arXiv)

While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. These challenges are particularly pronounced when facing new action categories, diverse performers, and varied skeleton layouts, leading to significant performance degeneration. Additionally, the high cost and difficulty of collecting skeleton data make large-scale data collection impractical. This paper studies one-shot and limited-scale learning settings to enable efficient adaptation with minimal data. Existing approaches often overlook the rich mutual information between labeled samples, resulting in sub-optimal performance in low-data scenarios. To boost the utility of labeled data, we identify the variability among performers and the commonality within each action as two key attributes. We present SkeletonX, a lightweight training pipeline that integrates seamlessly with existing GCN-based skeleton action recognizers, promoting effective training under limited labeled data. First, we propose a tailored sample pair construction strategy on two key attributes to form and aggregate sample pairs. Next, we develop a concise and effective feature aggregation module to process these pairs. Extensive experiments are conducted on NTU RGB+D, NTU RGB+D 120, and PKU-MMD with various GCN backbones, demonstrating that the pipeline effectively improves performance when trained from scratch with limited data. Moreover, it surpasses previous state-of-the-art methods in the one-shot setting, with only 1/10 of the parameters and much fewer FLOPs. The code and data are available at: https://github.com/zzysteve/SkeletonX