# Active Learning for GCN-based Action Recognition

arXiv: https://arxiv.org/abs/2511.21625 · HTML: https://mlsanity.com/paper/2511.21625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 131 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Builds on (most cited first, 30 of 35)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [A Riemannian Network for SPD Matrix Learning](https://mlsanity.com/paper/1608.04233/) (2016)
- [Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition](https://mlsanity.com/paper/1607.07043/) (2016)
- [Contextual Diversity for Active Learning](https://mlsanity.com/paper/2008.05723/) (2020)
- [Building Deep Networks on Grassmann Manifolds](https://mlsanity.com/paper/1611.05742/) (2016)
- [Active Learning Principles for In-Context Learning with Large Language Models](https://mlsanity.com/paper/2305.14264/) (2023)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [Batch Active Learning Using Determinantal Point Processes](https://mlsanity.com/paper/1906.07975/) (2019)
- [Rethinking deep active learning: Using unlabeled data at model training](https://mlsanity.com/paper/1911.08177/) (2019)
- [Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition](https://mlsanity.com/paper/2411.18941/) (2024)
- [In Defense of Core-set: A Density-aware Core-set Selection for Active Learning](https://mlsanity.com/paper/2206.04838/) (2022)
- [MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition](https://mlsanity.com/paper/2405.02077/) (2024)
- [Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition](https://mlsanity.com/paper/2406.13327/) (2024)
- [A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding](https://mlsanity.com/paper/1807.00676/) (2018)
- [Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.11166/) (2023)
- [Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2112.03328/) (2021)
- [Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection](https://mlsanity.com/paper/1607.02737/) (2016)
- [Referring Atomic Video Action Recognition](https://mlsanity.com/paper/2407.01872/) (2024)
- [DeepGRU: Deep Gesture Recognition Utility](https://mlsanity.com/paper/1810.12514/) (2018)
- [Teaching an Active Learner with Contrastive Examples](https://mlsanity.com/paper/2110.14888/) (2021)
- [Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition](https://mlsanity.com/paper/2311.15619/) (2023)
- [TiDAL: Learning Training Dynamics for Active Learning](https://mlsanity.com/paper/2210.06788/) (2022)
- [A Comprehensive Review of Few-shot Action Recognition](https://mlsanity.com/paper/2407.14744/) (2024)
- [Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation](https://mlsanity.com/paper/2406.18011/) (2024)
- [3D Skeleton-Based Action Recognition: A Review](https://mlsanity.com/paper/2506.00915/) (2025)
- [Exploring Explainability in Video Action Recognition](https://mlsanity.com/paper/2404.09067/) (2024)
- [Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond](https://mlsanity.com/paper/2406.02978/) (2024)

## Abstract (arXiv)

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.