# High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation

arXiv: https://arxiv.org/abs/2510.11017 · HTML: https://mlsanity.com/paper/2510.11017/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 48 of its 58 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections](https://mlsanity.com/paper/2008.07669/) (2020)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [Long Range Language Modeling via Gated State Spaces](https://mlsanity.com/paper/2206.13947/) (2022)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [PoseTrack: A Benchmark for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1710.10000/) (2017)
- [PifPaf: Composite Fields for Human Pose Estimation](https://mlsanity.com/paper/1903.06593/) (2019)
- [TokenPose: Learning Keypoint Tokens for Human Pose Estimation](https://mlsanity.com/paper/2104.03516/) (2021)
- [Lite-HRNet: A Lightweight High-Resolution Network](https://mlsanity.com/paper/2104.06403/) (2021)
- [Pose Flow: Efficient Online Pose Tracking](https://mlsanity.com/paper/1802.00977/) (2018)
- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [Combining detection and tracking for human pose estimation in videos](https://mlsanity.com/paper/2003.13743/) (2020)
- [MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network](https://mlsanity.com/paper/1807.04067/) (2018)
- [PoseTrack: Joint Multi-Person Pose Estimation and Tracking](https://mlsanity.com/paper/1611.07727/) (2016)
- [Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos](https://mlsanity.com/paper/1703.10898/) (2017)

## Built on by (most cited first, 4 of 4)

- [MambaVF: State Space Model for Efficient Video Fusion](https://mlsanity.com/paper/2602.06017/) (2026)
- [Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation](https://mlsanity.com/paper/2603.05929/) (2026)
- [NCSTR: Node-Centric Decoupled Spatio-Temporal Reasoning for Video-based Human Pose Estimation](https://mlsanity.com/paper/2603.20323/) (2026)
- [IMPose: Interactive Multi-person Pose Estimation with Dynamic Correction Propagation](https://mlsanity.com/paper/2606.04480/) (2026)

## Abstract (arXiv)

Modeling high-resolution spatiotemporal representations, including both global dynamic contexts (e.g., holistic human motion tendencies) and local motion details (e.g., high-frequency changes of keypoints), is essential for video-based human pose estimation (VHPE). Current state-of-the-art methods typically unify spatiotemporal learning within a single type of modeling structure (convolution or attention-based blocks), which inherently have difficulties in balancing global and local dynamic modeling and may bias the network to one of them, leading to suboptimal performance. Moreover, existing VHPE models suffer from quadratic complexity when capturing global dependencies, limiting their applicability especially for high-resolution sequences. Recently, the state space models (known as Mamba) have demonstrated significant potential in modeling long-range contexts with linear complexity; however, they are restricted to 1D sequential data. In this paper, we present a novel framework that extends Mamba from two aspects to separately learn global and local high-resolution spatiotemporal representations for VHPE. Specifically, we first propose a Global Spatiotemporal Mamba, which performs 6D selective space-time scan and spatial- and temporal-modulated scan merging to efficiently extract global representations from high-resolution sequences. We further introduce a windowed space-time scan-based Local Refinement Mamba to enhance the high-frequency details of localized keypoint motions. Extensive experiments on four benchmark datasets demonstrate that the proposed model outperforms state-of-the-art VHPE approaches while achieving better computational trade-offs.