# Motion-Adaptive Multi-Scale Temporal Modelling with Skeleton-Constrained Spatial Graphs for Efficient 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2604.03652 · HTML: https://mlsanity.com/paper/2604.03652/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth](https://mlsanity.com/paper/2103.03404/) (2021)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2303.17472/) (2023)
- [P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.07628/) (2022)
- [MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network](https://mlsanity.com/paper/2310.16288/) (2023)
- [GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/2307.05853/) (2023)
- [KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2404.00658/) (2024)
- [Unsupervised Pre-training for Temporal Action Localization Tasks](https://mlsanity.com/paper/2203.13609/) (2022)
- [TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation](https://mlsanity.com/paper/2501.01770/) (2025)
- [Unified Spatial-Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2502.02504/) (2025)
- [H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers](https://mlsanity.com/paper/2509.06956/) (2025)
- [HGMamba: Enhancing 3D Human Pose Estimation with a HyperGCN-Mamba Network](https://mlsanity.com/paper/2504.06638/) (2025)
- [ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2511.12214/) (2025)

## Built on by (most cited first, 2 of 2)

- [Sparse Multi-Stage Expert-Agent Routing for Complex Clinical Reasoning](https://mlsanity.com/paper/2608.21948/) (2026)
- [HSTGFormer: Hyper Spatial-Temporal Graph Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2608.12187/) (2026)

## Abstract (arXiv)

Accurate 3D human pose estimation from monocular videos requires effective modelling of complex spatial and temporal dependencies. However, existing methods often face challenges in efficiency and adaptability when modelling spatial and temporal dependencies, particularly under dense attention or fixed modelling schemes. In this work, we propose MASC-Pose, a Motion-Adaptive multi-scale temporal modelling framework with Skeleton-Constrained spatial graphs for efficient 3D human pose estimation. Specifically, it introduces an Adaptive Multi-scale Temporal Modelling (AMTM) module to adaptively capture heterogeneous motion dynamics at different temporal scales, together with a Skeleton-constrained Adaptive GCN (SAGCN) for joint-specific spatial interaction modelling. By jointly enabling adaptive temporal reasoning and efficient spatial aggregation, our method achieves strong accuracy with high computational efficiency. Extensive experiments on Human3.6M and MPI-INF-3DHP datasets demonstrate the effectiveness of our approach.