mlsanityData to 7 Oct 2026

TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition

arXiv 2512.11503 ↗First posted 12 Dec 2025cs.CVcited by 0

On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models

Abstract (arXiv)

Skeleton-based action recognition has garnered significant attention in the computer vision community. Inspired by the recent success of the selective state-space model (SSM) Mamba in modeling 1D temporal sequences, we propose TSkel-Mamba, a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics. In particular, our approach leverages Spatial Transformer for spatial feature learning while utilizing Mamba for temporal modeling. Mamba, however, employs separate SSM blocks for individual channels, which inherently limits its ability to model inter-channel dependencies. To better adapt Mamba for skeleton data and enhance Mamba`s ability to model temporal dependencies, we introduce a Temporal Dynamic Modeling (TDM) block, which is a versatile plug-and-play component that integrates a novel Multi-scale Temporal Interaction (MTI) module. The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition. Extensive experiments on NTU-RGB+D 60, NTU-RGB+D 120, NW-UCLA and UAV-Human datasets demonstrate that TSkel-Mamba achieves state-of-the-art performance while maintaining low inference time, making it both efficient and highly effective.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 52 of its 68 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

52 of 68 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting25 Mar
  2. 2024Motion Mamba: Efficient and Long Sequence Motion Generation12 Mar
  3. 2024VideoMamba: State Space Model for Efficient Video Understanding11 Mar

Other references · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  4. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  5. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  6. 2024VMamba: Visual State Space Modelcited by 955
  7. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  8. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  9. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 600
  10. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  11. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 418
  12. 2022Decoupled Knowledge Distillationcited by 380
37 more
  1. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  2. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  3. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  4. 2018Human Action Recognition and Prediction: A Surveycited by 226
  5. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
  6. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  7. 2020Human Action Recognition from Various Data Modalities: A Reviewcited by 162
  8. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  9. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 142
  10. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  11. 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
  12. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  13. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  14. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 95
  15. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  16. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  17. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  18. 2020Spatial Temporal Transformer Network for Skeleton-based Action Recognitioncited by 76
  19. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  20. 2018Global Second-order Pooling Convolutional Networkscited by 66
  21. 2017Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalizationcited by 65
  22. 2023Learning Discriminative Representations for Skeleton Based Action Recognitioncited by 62
  23. 2022Generative Action Description Prompts for Skeleton-based Action Recognitioncited by 43
  24. 2024MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selectioncited by 40
  25. 2022Hypergraph Transformer for Skeleton-based Action Recognitioncited by 36
  26. 2022IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognitioncited by 31
  27. 2021Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognitioncited by 29
  28. 2023Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognitioncited by 23
  29. 2024DVMSR: Distillated Vision Mamba for Efficient Super-Resolutioncited by 23
  30. 2020Feedback Graph Convolutional Network for Skeleton-based Action Recognitioncited by 22
  31. 2024Vim4Path: Self-Supervised Vision Mamba for Histopathology Imagescited by 19
  32. 2022Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognitioncited by 18
  33. 2018CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Mapscited by 13
  34. 2022Skeleton-based Action Recognition via Temporal-Channel Aggregationcited by 13
  35. 2022Skeleton-based Action Recognition via Adaptive Cross-Form Learningcited by 12
  36. 2024EM-Net: Efficient Channel and Frequency Learning with Mamba for 3D Medical Image Segmentationcited by 12
  37. 2023InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognitioncited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos
  2. 2025MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos
  3. 20253D Skeleton-Based Action Recognition: A Review
  4. 2026T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition
  5. 2024SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders
  6. 2024Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
  7. 2025MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition
  8. 2026LLM Enhanced Action Recognition via Hierarchical Global-Local Skeleton-Language Model