mlsanityData to 7 Oct 2026

HDFormer: High-order Directed Transformer for 3D Human Pose Estimation

arXiv 2302.01825 ↗First posted 3 Feb 2023cs.CV cs.AIcited by 23

Not on the map. Why?

Abstract (arXiv)

Human pose estimation is a challenging task due to its structured data sequence nature. Existing methods primarily focus on pair-wise interaction of body joints, which is insufficient for scenarios involving overlapping joints and rapidly changing poses. To overcome these issues, we introduce a novel approach, the High-order Directed Transformer (HDFormer), which leverages high-order bone and joint relationships for improved pose estimation. Specifically, HDFormer incorporates both self-attention and high-order attention to formulate a multi-order attention module. This module facilitates first-order "jointleftrightarrowjoint", second-order "boneleftrightarrowjoint", and high-order "hyperboneleftrightarrowjoint" interactions, effectively addressing issues in complex and occlusion-heavy situations. In addition, modern CNN techniques are integrated into the transformer-based architecture, balancing the trade-off between performance and efficiency. HDFormer significantly outperforms state-of-the-art (SOTA) models on Human3.6M and MPI-INF-3DHP datasets, requiring only 1/10 of the parameters and significantly lower computational costs. Moreover, HDFormer demonstrates broad real-world applicability, enabling real-time, accurate 3D pose estimation. The source code is in https://github.com/hyer/HDFormer

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 26 of its 47 references that are in the map. First posted on arXiv 3 Feb 2023.

Builds on

26 of 47 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  4. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  5. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  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. 2019Learnable Triangulation of Human Posecited by 160
  10. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  11. 2021CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 139
  12. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
14 more
  1. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  2. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  3. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  4. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  5. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  6. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  7. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  8. 2022Hypergraph Transformer for Skeleton-based Action Recognitioncited by 36
  9. 2019Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimationcited by 30
  10. 2017Multi-View Image Generation from a Single-Viewcited by 27
  11. 2022GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinementcited by 20
  12. 2020Generating Person Images with Appearance-aware Pose Stylizercited by 13
  13. 2019An Adaptive and Momental Bound Method for Stochastic Learningcited by 11
  14. 2022CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 1; 2025: 12; 2026: 2.

23 papers.

Sort:

By area:

  1. 2023MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Networkcited by 62
  2. 2023Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognitioncited by 27
  3. 2023Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimationcited by 15
  4. 2023DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Drivingcited by 12
  5. 2023PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimationcited by 12
  6. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  7. 2024HumMUSS: Human Motion Understanding using State Space Modelscited by 6
  8. 2025H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformerscited by 5
  9. 2025HGMamba: Enhancing 3D Human Pose Estimation with a HyperGCN-Mamba Networkcited by 4
  10. 2023KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilaterationcited by 3
  11. 2025A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mambacited by 3
  12. 2025SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimationcited by 2
11 more
  1. 2025A Spatio-temporal Continuous Network for Stochastic 3D Human Motion Predictioncited by 2
  2. 2025Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimationcited by 1
  3. 2025StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusioncited by 1
  4. 2025SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimationcited by 1
  5. 2023Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimationcited by 0
  6. 2025HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimationcited by 0
  7. 2025Learning Pyramid-structured Long-range Dependencies for 3D Human Pose Estimationcited by 0
  8. 2025Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruningcited by 0
  9. 2025PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimationcited by 0
  10. 2026Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimationcited by 0
  11. 2026L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimationcited by 0