Active Generation Network of Human Skeleton for Action Recognition

TL;DR

This paper introduces an active generative network that enhances skeleton-based human action recognition by adaptively generating diverse, temporally consistent actions from limited data through motion style transfer and uncertainty-guided sampling.

Contribution

The proposed AGN combines motion style transfer with an uncertainty metric network to generate diverse and temporally consistent actions from minimal data, improving data augmentation for recognition tasks.

Findings

Effective generation of diverse actions from few samples.

Improved action recognition accuracy with augmented data.

Temporal consistency maintained in generated actions.

Abstract

Data generation is a data augmentation technique for enhancing the generalization ability for skeleton-based human action recognition. Most existing data generation methods face challenges to ensure the temporal consistency of the dynamic information for action. In addition, the data generated by these methods lack diversity when only a few training samples are available. To solve those problems, We propose a novel active generative network (AGN), which can adaptively learn various action categories by motion style transfer to generate new actions when the data for a particular action is only a single sample or few samples. The AGN consists of an action generation network and an uncertainty metric network. The former, with ST-GCN as the Backbone, can implicitly learn the morphological features of the target action while preserving the category features of the source action. The latter guides generating actions. Specifically, an action recognition model generates prediction vectors for each action, which is then scored using an uncertainty metric. Finally, UMN provides the uncertainty sampling basis for the generated actions.