mlsanityData to 7 Oct 2026

HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation

arXiv 2301.07322 ↗First posted 18 Jan 2023cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Transformer-based approaches have been successfully proposed for 3D human pose estimation (HPE) from 2D pose sequence and achieved state-of-the-art (SOTA) performance. However, current SOTAs have difficulties in modeling spatial-temporal correlations of joints at different levels simultaneously. This is due to the poses' spatial-temporal complexity. Poses move at various speeds temporarily with various joints and body-parts movement spatially. Hence, a cookie-cutter transformer is non-adaptable and can hardly meet the "in-the-wild" requirement. To mitigate this issue, we propose Hierarchical Spatial-Temporal transFormers (HSTFormer) to capture multi-level joints' spatial-temporal correlations from local to global gradually for accurate 3D HPE. HSTFormer consists of four transformer encoders (TEs) and a fusion module. To the best of our knowledge, HSTFormer is the first to study hierarchical TEs with multi-level fusion. Extensive experiments on three datasets (i.e., Human3.6M, MPI-INF-3DHP, and HumanEva) demonstrate that HSTFormer achieves competitive and consistent performance on benchmarks with various scales and difficulties. Specifically, it surpasses recent SOTAs on the challenging MPI-INF-3DHP dataset and small-scale HumanEva dataset, with a highly generalized systematic approach. The code is available at: https://github.com/qianxiaoye825/HSTFormer.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 18 Jan 2023.

Builds on

26 of 39 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  7. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  8. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  11. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  12. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
14 more
  1. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  2. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  3. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  4. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  5. 2020TransPose: Keypoint Localization via Transformercited by 126
  6. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  7. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  8. 2017Exploiting temporal information for 3D pose estimationcited by 89
  9. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  10. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  11. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  12. 2019Modeling Human Motion with Quaternion-based Neural Networkscited by 45
  13. 2019Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimationcited by 30
  14. 2022Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localizationcited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 3; 2026: 1.

9 papers.

  1. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
  2. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  3. 2024HumMUSS: Human Motion Understanding using State Space Modelscited by 6
  4. 2025HGMamba: Enhancing 3D Human Pose Estimation with a HyperGCN-Mamba Networkcited by 4
  5. 2024Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusioncited by 3
  6. 2024STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Videocited by 2
  7. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
  8. 2025Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimationcited by 1
  9. 2023Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimationcited by 0