Generative Data Augmentation for Skeleton Action Recognition

TL;DR

This paper introduces a Transformer-based generative pipeline for augmenting skeleton action recognition data, improving model performance especially in low-data scenarios.

Contribution

It presents a novel conditional generative method with a Transformer architecture to synthesize diverse, high-fidelity skeleton sequences for better action recognition.

Findings

Improves recognition accuracy in low-data settings.

Enhances model generalization with synthetic skeleton data.

Validates effectiveness on multiple datasets.

Abstract

Skeleton-based human action recognition is a powerful approach for understanding human behaviour from pose data, but collecting large-scale, diverse, and well-annotated 3D skeleton datasets is both expensive and labor-intensive. To address this challenge, we propose a conditional generative pipeline for data augmentation in skeleton action recognition. Our method learns the distribution of real skeleton sequences under the constraint of action labels, enabling the synthesis of diverse and high-fidelity data. Even with limited training samples, it can effectively generate skeleton sequences and achieve competitive recognition performance in low-data scenarios, demonstrating strong generalisation in downstream tasks. Specifically, we introduce a Transformer-based encoder-decoder architecture, combined with a generative refinement module and a dropout mechanism, to balance fidelity and diversity during sampling. Experiments on HumanAct12 and the refined NTU-RGBD (NTU-VIBE) dataset show that our approach consistently improves the accuracy of multiple skeleton-based action recognition models, validating its effectiveness in both few-shot and full-data settings. The source code can be found at here.