# Foundation Model for Skeleton-Based Human Action Understanding

arXiv: https://arxiv.org/abs/2508.12586 · HTML: https://mlsanity.com/paper/2508.12586/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 74 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Builds on (most cited first, 30 of 47)

- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Whitening for Self-Supervised Representation Learning](https://mlsanity.com/paper/2007.06346/) (2020)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [BEVT: BERT Pretraining of Video Transformers](https://mlsanity.com/paper/2112.01529/) (2021)
- [Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition](https://mlsanity.com/paper/1607.07043/) (2016)
- [Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks](https://mlsanity.com/paper/2008.07404/) (2020)
- [UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles](https://mlsanity.com/paper/2104.00946/) (2021)
- [MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition](https://mlsanity.com/paper/2010.05599/) (2020)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Large Motion Model for Unified Multi-Modal Motion Generation](https://mlsanity.com/paper/2404.01284/) (2024)
- [Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks](https://mlsanity.com/paper/1704.02581/) (2017)
- [HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations](https://mlsanity.com/paper/2303.06242/) (2023)
- [Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition](https://mlsanity.com/paper/2303.10904/) (2023)
- [SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training](https://mlsanity.com/paper/2307.08476/) (2023)
- [Masked Motion Predictors are Strong 3D Action Representation Learners](https://mlsanity.com/paper/2308.07092/) (2023)
- [CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation](https://mlsanity.com/paper/2208.12448/) (2022)
- [Encouraging LSTMs to Anticipate Actions Very Early](https://mlsanity.com/paper/1703.07023/) (2017)
- [LLMs are Good Action Recognizers](https://mlsanity.com/paper/2404.00532/) (2024)
- [Contrastive Positive Mining for Unsupervised 3D Action Representation Learning](https://mlsanity.com/paper/2208.03497/) (2022)
- [Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations](https://mlsanity.com/paper/2211.13466/) (2022)
- [Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning](https://mlsanity.com/paper/2207.09644/) (2022)
- [Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning](https://mlsanity.com/paper/2212.02082/) (2022)
- [SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition](https://mlsanity.com/paper/2209.02399/) (2022)
- [Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning](https://mlsanity.com/paper/2312.03703/) (2023)

## Built on by (most cited first, 11 of 11)

- [ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment](https://mlsanity.com/paper/2511.19217/) (2025)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [FineXtrol: Controllable Motion Generation via Fine-Grained Text](https://mlsanity.com/paper/2511.18927/) (2025)
- [iMiGUE-3K: A Large-Scale Benchmark for Micro-Gesture Analysis with Self-Supervised Learning](https://mlsanity.com/paper/2605.17179/) (2026)
- [MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation](https://mlsanity.com/paper/2603.27185/) (2026)
- [Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning](https://mlsanity.com/paper/2508.21363/) (2025)
- [LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation](https://mlsanity.com/paper/2603.24097/) (2026)
- [Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition](https://mlsanity.com/paper/2604.17090/) (2026)
- [Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors](https://mlsanity.com/paper/2604.17914/) (2026)
- [Zero-Shot Skeleton-Based Action Anticipation](https://mlsanity.com/paper/2608.14243/) (2026)
- [De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift](https://mlsanity.com/paper/2609.32454/) (2026)

## Abstract (arXiv)

Human action understanding serves as a foundational pillar in the field of intelligent motion perception. Skeletons serve as a modality- and device-agnostic representation for human modeling, and skeleton-based action understanding has potential applications in humanoid robot control and interaction. REDHowever, existing works often lack the scalability and generalization required to handle diverse action understanding tasks. There is no skeleton foundation model that can be adapted to a wide range of action understanding tasks. This paper presents a Unified Skeleton-based Dense Representation Learning (USDRL) framework, which serves as a foundational model for skeleton-based human action understanding. USDRL consists of a Transformer-based Dense Spatio-Temporal Encoder (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT). The DSTE module adopts two parallel streams to learn temporal dynamic and spatial structure features. The MG-FD module collaboratively performs feature decorrelation across temporal, spatial, and instance domains to reduce dimensional redundancy and enhance information extraction. The MPCT module employs both multi-view and multi-modal self-supervised consistency training. The former enhances the learning of high-level semantics and mitigates the impact of low-level discrepancies, while the latter effectively facilitates the learning of informative multimodal features. We perform extensive experiments on 25 benchmarks across across 9 skeleton-based action understanding tasks, covering coarse prediction, dense prediction, and transferred prediction. Our approach significantly outperforms the current state-of-the-art methods. We hope that this work would broaden the scope of research in skeleton-based action understanding and encourage more attention to dense prediction tasks.