CVApr 16, 2025

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

arXiv:2504.11749v11 citationsh-index: 32Has CodeIEEE transactions on multimedia
Originality Incremental advance
AI Analysis

This work addresses the problem of data-efficient adaptation for skeleton action recognition, which is incremental as it builds on existing GCN-based methods to enhance low-data performance.

The paper tackles the challenge of adapting skeleton-based action recognition models to new scenarios with limited data by proposing SkeletonX, a lightweight pipeline that improves performance in one-shot and limited-scale settings, achieving state-of-the-art results with only 1/10 of the parameters and fewer FLOPs.

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

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes