Active Learning for GCN-based Action Recognition

• URL: http://arxiv.org/abs/2511.21625v1
• Date: Wed, 26 Nov 2025 17:51:59 GMT
• Title: Active Learning for GCN-based Action Recognition
• Authors: Hichem Sahbi,
• Abstract summary: We propose a novel label-efficient graph convolutional network (GCN) model.<n>We develop a novel acquisition function that employs an adversarial strategy to identify a compact set of informative exemplars for labeling.<n>These enhanced networks facilitate a more effective mapping between the ambient and latent data spaces.
• Score: 14.061680807550722
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks [14.061680807550722]
  This paper devises a novel, label-efficient method for skeleton-based action recognition using graph convolutional networks (GCNs)<n>The contribution of the proposed method resides in learning a novel acquisition function -- scoring the most informative subsets for labeling.<n>We also extend this approach by learning the most informative subsets using an invertible GCN which allows mapping data from ambient to latent spaces.
  arXiv  Detail & Related papers  (2025-11-21T16:06:53Z)
• Degree-Conscious Spiking Graph for Cross-Domain Adaptation [51.58506501415558]
  Spiking Graph Networks (SGNs) have demonstrated significant potential in graph classification.<n>We introduce a novel framework named Degree-Consicious Spiking Graph for Cross-Domain Adaptation (DeSGraDA)<n>DeSGraDA enhances generalization across domains with three key components.
  arXiv  Detail & Related papers  (2024-10-09T13:45:54Z)
• Structure-Aware Consensus Network on Graphs with Few Labeled Nodes [7.438140196173472]
  Graph node classification with few labeled nodes presents significant challenges due to limited supervision. Conventional methods often exploit the graph in a transductive learning manner. We introduce a Structure-Aware Consensus Network (SACN) to overcome these issues.
  arXiv  Detail & Related papers  (2024-07-02T11:46:07Z)
• Dual-stream contrastive predictive network with joint handcrafted feature view for SAR ship classification [9.251342335645765]
  We propose a novel dual-stream contrastive predictive network (DCPNet) The first task is to construct positive sample pairs, guiding the core encoder to learn more general representations. The second task is to encourage adaptive capture of the correspondence between deep features and handcrated features, achieving knowledge transfer within the model, and effectively improving the redundancy caused by the feature fusion.
  arXiv  Detail & Related papers  (2023-11-26T05:47:01Z)
• NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning [77.95710025273218]
  We propose a unified framework called NICE that can jointly learn two panoptic narrative recognition tasks. By linking PNS and PND in series with the barycenter of segmentation as the anchor, our approach naturally aligns the two tasks. NICE surpasses all existing methods by a large margin, achieving 4.1% for PND and 2.9% for PNS over the state-of-the-art.
  arXiv  Detail & Related papers  (2023-10-17T03:42:12Z)
• Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition [65.78703941973183]
  We propose a novel correlation-driven joint-bone fusion graph convolutional network (CD-JBF-GCN) as an encoder and use a pose prediction head as a decoder. Specifically, the CD-JBF-GC can explore the motion transmission between the joint stream and the bone stream. The pose prediction based auto-encoder in the self-supervised training stage allows the network to learn motion representation from unlabeled data.
  arXiv  Detail & Related papers  (2022-02-08T16:03:15Z)
• Meta Propagation Networks for Graph Few-shot Semi-supervised Learning [39.96930762034581]
  We propose a novel network architecture equipped with a novel meta-learning algorithm to solve this problem. In essence, our framework Meta-PN infers high-quality pseudo labels on unlabeled nodes via a meta-learned label propagation strategy. Our approach offers easy and substantial performance gains compared to existing techniques on various benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-18T00:11:56Z)
• Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation [78.28390172958643]
  We identify two key aspects that can help to alleviate multiple domain-shifts in the multi-target domain adaptation (MTDA) We propose Curriculum Graph Co-Teaching (CGCT) that uses a dual classifier head, with one of them being a graph convolutional network (GCN) which aggregates features from similar samples across the domains. When the domain labels are available, we propose Domain-aware Curriculum Learning (DCL), a sequential adaptation strategy that first adapts on the easier target domains, followed by the harder ones.
  arXiv  Detail & Related papers  (2021-04-01T23:41:41Z)
• On the Equivalence of Decoupled Graph Convolution Network and Label Propagation [60.34028546202372]
  Some work shows that coupling is inferior to decoupling, which supports deep graph propagation better. Despite effectiveness, the working mechanisms of the decoupled GCN are not well understood. We propose a new label propagation method named propagation then training Adaptively (PTA), which overcomes the flaws of the decoupled GCN.
  arXiv  Detail & Related papers  (2020-10-23T13:57:39Z)
• Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition [75.44233392355711]
  KGGR framework exploits prior knowledge of statistical label correlations with deep neural networks. It first builds a structured knowledge graph to correlate different labels based on statistical label co-occurrence. Then, it introduces the label semantics to guide learning semantic-specific features. It exploits a graph propagation network to explore graph node interactions.
  arXiv  Detail & Related papers  (2020-09-20T15:05:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.