# LLM Enhanced Action Recognition via Hierarchical Global-Local Skeleton-Language Model

arXiv: https://arxiv.org/abs/2603.27103 · HTML: https://mlsanity.com/paper/2603.27103/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Unified Contrastive Learning in Image-Text-Label Space](https://mlsanity.com/paper/2204.03610/) (2022)
- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [Cross-view Action Modeling, Learning and Recognition](https://mlsanity.com/paper/1405.2941/) (2014)
- [Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks](https://mlsanity.com/paper/2008.07404/) (2020)
- [Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition](https://mlsanity.com/paper/2007.14690/) (2020)
- [Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2206.13028/) (2022)
- [STORM: Token-Efficient Long Video Understanding for Multimodal LLMs](https://mlsanity.com/paper/2503.04130/) (2025)
- [FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flow](https://mlsanity.com/paper/2003.05102/) (2020)
- [Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow](https://mlsanity.com/paper/2510.05836/) (2025)
- [From CNNs to Transformers in Multimodal Human Action Recognition: A Survey](https://mlsanity.com/paper/2405.15813/) (2024)
- [VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language Models](https://mlsanity.com/paper/2511.18823/) (2025)
- [Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model](https://mlsanity.com/paper/2105.11312/) (2021)

## Abstract (arXiv)

Skeleton-based human action recognition has achieved remarkable progress in recent years. However, most existing GCN-based methods rely on short-range motion topologies, which not only struggle to capture long-range joint dependencies and complex temporal dynamics but also limit cross-modal semantic alignment and understanding due to insufficient modeling of action semantics. To address these challenges, we propose a hierarchical global-local skeleton-language model (HocSLM), enabling the large action model be more representative of action semantics. First, we design a hierarchical global-local network (HGLNet) that consists of a composite-topology spatial module and a dual-path hierarchical temporal module. By synergistically integrating multi-level global and local modules, HGLNet achieves dynamically collaborative modeling at both global and local scales while preserving prior knowledge of human physical structure, significantly enhancing the model's representation of complex spatio-temporal relationships. Then, a large vision-language model (VLM) is employed to generate textual descriptions by passing the original RGB video sequences to this model, providing the rich action semantics for further training the skeleton-language model. Furthermore, we introduce a skeleton-language sequential fusion module by combining the features from HGLNet and the generated descriptions, which utilizes a skeleton-language model (SLM) for aligning skeletal spatio-temporal features and textual action descriptions precisely within a unified semantic space. The SLM model could significantly enhance the HGLNet's semantic discrimination capabilities and cross-modal understanding abilities. Extensive experiments demonstrate that the proposed HocSLM achieves the state-of-the-art performance on three mainstream benchmark datasets: NTU RGB+D 60, NTU RGB+D 120, and Northwestern-UCLA.