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

• URL: http://arxiv.org/abs/2512.11503v1
• Date: Fri, 12 Dec 2025 11:55:16 GMT
• Title: TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition
• Authors: Yanan Liu, Jun Liu, Hao Zhang, Dan Xu, Hossein Rahmani, Mohammed Bennamoun, Qiuhong Ke,
• Abstract summary: TSkel-Mamba is a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics.<n>The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition.
• Score: 59.99922360648663
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis [22.768341734517815]
  Transformer-based models suffer from computational complexity and high memory overhead.<n>Mamba has emerged as a promising linear-time alternative with high expressiveness.<n>DeMa is a dual-path delay-aware Mamba backbone.
  arXiv  Detail & Related papers  (2026-01-09T04:54:56Z)
• MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection [94.12444452690329]
  This paper presents MambaTAD, a new state-space TAD model that introduces long-range modeling and global feature detection capabilities.<n>MambaTAD achieves superior TAD performance consistently across multiple public benchmarks.
  arXiv  Detail & Related papers  (2025-11-22T06:04:29Z)
• Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection [88.47928738482719]
  Linear State Space Models (SSMs) offer remarkable performance gains in sequence modeling.<n>Recent advances, such as Mamba, further enhance SSMs with input-dependent gating and hardware-aware implementations.<n>We introduce Routing Mamba (RoM), a novel approach that scales SSM parameters using sparse mixtures of linear projection experts.
  arXiv  Detail & Related papers  (2025-06-22T19:26:55Z)
• STNMamba: Mamba-based Spatial-Temporal Normality Learning for Video Anomaly Detection [48.997518615379995]
  Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems.<n>Most existing methods based on CNNs and transformers still suffer from substantial computational burdens.<n>We propose a lightweight and effective Mamba-based network named STNMamba to enhance the learning of spatial-temporal normality.
  arXiv  Detail & Related papers  (2024-12-28T08:49:23Z)
• MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking [51.28485682954006]
  We propose a pure Mamba-based framework (MambaVT) to fully exploit intrinsic-temporal contextual modeling for robust visible-thermal tracking. Specifically, we devise the long-range cross-frame integration component to globally adapt to target appearance variations. Experiments show the significant potential of vision Mamba for RGB-T tracking, with MambaVT achieving state-of-the-art performance on four mainstream benchmarks.
  arXiv  Detail & Related papers  (2024-08-15T02:29:00Z)
• Mamba-Spike: Enhancing the Mamba Architecture with a Spiking Front-End for Efficient Temporal Data Processing [4.673285689826945]
  Mamba-Spike is a novel neuromorphic architecture that integrates a spiking front-end with the Mamba backbone to achieve efficient temporal data processing. The architecture consistently outperforms state-of-the-art baselines, achieving higher accuracy, lower latency, and improved energy efficiency.
  arXiv  Detail & Related papers  (2024-08-04T14:10:33Z)
• RSCaMa: Remote Sensing Image Change Captioning with State Space Model [29.945966783242337]
  Remote Sensing Image Change Captioning (RSICC) aims to describe surface changes between multi-temporal remote sensing images in language. This poses challenges to spatial and temporal modeling of bi-temporal features. We propose a novel RSCaMa model, which achieves efficient joint spatial-temporal modeling through multiple CaMa layers.
  arXiv  Detail & Related papers  (2024-04-29T17:31:00Z)
• MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection [5.37935922811333]
  MambaMixer is a new architecture with data-dependent weights that uses a dual selection mechanism across tokens and channels. As a proof of concept, we design Vision MambaMixer (ViM2) and Time Series MambaMixer (TSM2) architectures based on the MambaMixer block.
  arXiv  Detail & Related papers  (2024-03-29T00:05:13Z)
• Slow-Fast Visual Tempo Learning for Video-based Action Recognition [78.3820439082979]
  Action visual tempo characterizes the dynamics and the temporal scale of an action. Previous methods capture the visual tempo either by sampling raw videos with multiple rates, or by hierarchically sampling backbone features. We propose a Temporal Correlation Module (TCM) to extract action visual tempo from low-level backbone features at single-layer remarkably.
  arXiv  Detail & Related papers  (2022-02-24T14:20:04Z)

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.