Score: 0

Active Learning for GCN-based Action Recognition

Published: November 26, 2025 | arXiv ID: 2511.21625v1

By: Hichem Sahbi

Potential Business Impact:

Teaches computers to recognize actions with less training.

Business Areas:
Image Recognition Data and Analytics, Software

Despite the notable success of graph convolutional networks (GCNs) in skeleton-based action recognition, their performance often depends on large volumes of labeled data, which are frequently scarce in practical settings. To address this limitation, we propose a novel label-efficient GCN model. Our work makes two primary contributions. First, we develop a novel acquisition function that employs an adversarial strategy to identify a compact set of informative exemplars for labeling. This selection process balances representativeness, diversity, and uncertainty. Second, we introduce bidirectional and stable GCN architectures. These enhanced networks facilitate a more effective mapping between the ambient and latent data spaces, enabling a better understanding of the learned exemplar distribution. Extensive evaluations on two challenging skeleton-based action recognition benchmarks reveal significant improvements achieved by our label-efficient GCNs compared to prior work.

Page Count
17 pages

Category
Computer Science:
CV and Pattern Recognition