mlsanityData to 7 Oct 2026

HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation

arXiv 2302.14581 ↗First posted 28 Feb 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

2D-to-3D human pose lifting is fundamental for 3D human pose estimation (HPE), for which graph convolutional networks (GCNs) have proven inherently suitable for modeling the human skeletal topology. However, the current GCN-based 3D HPE methods update the node features by aggregating their neighbors' information without considering the interaction of joints in different joint synergies. Although some studies have proposed importing limb information to learn the movement patterns, the latent synergies among joints, such as maintaining balance are seldom investigated. We propose the Hop-wise GraphFormer with Intragroup Joint Refinement (HopFIR) architecture to tackle the 3D HPE problem. HopFIR mainly consists of a novel hop-wise GraphFormer (HGF) module and an intragroup joint refinement (IJR) module. The HGF module groups the joints by k-hop neighbors and applies a hopwise transformer-like attention mechanism to these groups to discover latent joint synergies. The IJR module leverages the prior limb information for peripheral joint refinement. Extensive experimental results show that HopFIR outperforms the SOTA methods by a large margin, with a mean per-joint position error (MPJPE) on the Human3.6M dataset of 32.67 mm. We also demonstrate that the state-of-the-art GCN-based methods can benefit from the proposed hop-wise attention mechanism with a significant improvement in performance: SemGCN and MGCN are improved by 8.9% and 4.5%, respectively.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 30 of its 52 references that are in the map. First posted on arXiv 28 Feb 2023.

Builds on

30 of 52 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2017Graph Attention Networkscited by 8,854
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  8. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  11. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  12. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
18 more
  1. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  2. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  3. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  4. 2017Integral Human Pose Regressioncited by 255
  5. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  6. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  7. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  8. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  9. 2017Compositional Human Pose Regressioncited by 124
  10. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  11. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  12. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  13. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  14. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  15. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  16. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  17. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  18. 2021Lifting 2D Human Pose to 3D with Domain Adapted 3D Body Conceptcited by 4

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 4.

7 papers.

  1. 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioningcited by 29
  2. 2025Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videoscited by 3
  3. 2024Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimationcited by 2
  4. 2024STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Videocited by 2
  5. 2025NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimationcited by 2
  6. 2025ExoGait-MS: Learning Periodic Dynamics with Multi-Scale Graph Network for Exoskeleton Gait Recognitioncited by 0
  7. 2025PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimationcited by 0