Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks
This work addresses the costly and time-consuming need for large labeled datasets in skeleton-based action recognition, offering a label-efficient solution that is incremental in improving existing GCN approaches.
The paper tackled the problem of label-efficient skeleton-based action recognition by proposing a novel acquisition function for selecting informative subsets for labeling, and extended it with an invertible GCN to capture data distributions better. The method outperformed related work on two challenging datasets, demonstrating effectiveness in reducing labeling costs.
Skeleton-based action recognition is a hotspot in image processing. A key challenge of this task lies in its dependence on large, manually labeled datasets whose acquisition is costly and time-consuming. This paper devises a novel, label-efficient method for skeleton-based action recognition using graph convolutional networks (GCNs). The contribution of the proposed method resides in learning a novel acquisition function -- scoring the most informative subsets for labeling -- as the optimum of an objective function mixing data representativity, diversity and uncertainty. We also extend this approach by learning the most informative subsets using an invertible GCN which allows mapping data from ambient to latent spaces where the inherent distribution of the data is more easily captured. Extensive experiments, conducted on two challenging skeleton-based recognition datasets, show the effectiveness and the outperformance of our label-frugal GCNs against the related work.