[Paper] Active Learning for GCN-based Action Recognition
Source: arXiv
Abstract
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.
Subjects
- Computer Vision and Pattern Recognition (cs.CV)
Citation
- arXiv: 2511.21625 (cs.CV)
- DOI: https://doi.org/10.48550/arXiv.2511.21625
Submission History
- v1 – Wed, 26 Nov 2025 17:51:59 UTC (25 KB) – Author: Hichem Sahbi