mlsanityData to 7 Oct 2026

STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Video

arXiv 2407.10099 ↗First posted 14 Jul 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

The current methods of video-based 3D human pose estimation have achieved significant progress.However, they still face pressing challenges, such as the underutilization of spatiotemporal bodystructure features in transformers and the inadequate granularity of spatiotemporal interaction modeling in graph convolutional networks, which leads to pervasive depth ambiguity in monocular 3D human pose estimation. To address these limitations, this paper presents the Spatio-Temporal GraphFormer framework (STGFormer) for 3D human pose estimation in videos. First, we introduce a Spatio-Temporal criss-cross Graph (STG) attention mechanism, designed to more effectively leverage the inherent graph priors of the human body within continuous sequence distributions while capturing spatiotemporal long-range dependencies. Next, we present a dual-path Modulated Hop-wise Regular GCN (MHR-GCN) to independently process temporal and spatial dimensions in parallel, preserving features rich in temporal dynamics and the original or high-dimensional representations of spatial structures. Furthermore, the module leverages modulation to optimize parameter efficiency and incorporates spatiotemporal hop-wise skip connections to capture higher-order information. Finally, we demonstrate that our method achieves state-of-the-art performance on the Human3.6M and MPIINF-3DHP datasets.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 31 of its 47 references that are in the map. First posted on arXiv 14 Jul 2024.

Builds on

31 of 47 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  5. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  6. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  7. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  8. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  9. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  10. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  11. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  12. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
19 more
  1. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  2. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  3. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
  4. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  5. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  6. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  7. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
  8. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  9. 2021Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Drivingcited by 39
  10. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  11. 2022Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformerscited by 33
  12. 2019Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modelingcited by 32
  13. 2021Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Networkcited by 13
  14. 2020HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimationcited by 12
  15. 2023Regular Splitting Graph Network for 3D Human Pose Estimationcited by 11
  16. 2021GraFormer: Graph Convolution Transformer for 3D Pose Estimationcited by 10
  17. 2019Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinatescited by 9
  18. 2023HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimationcited by 9
  19. 2023HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Imagescited by 0
  2. 2026STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecastingcited by 0