mlsanityData to 14 Oct 2026

Joint angle based learning to refine kinematic human pose estimation

arXiv 2507.11075 ↗First posted 15 Jul 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Marker-free human pose estimation (HPE) has found increasing applications in various fields. Current HPE suffers from occasional errors in keypoint recognition and random fluctuation in keypoint trajectories when analyzing kinematic human poses. The performance of existing deep learning-based models for HPE refinement is considerably limited by inaccurate training datasets in which the keypoints are manually annotated. This paper proposed a novel method to overcome the difficulty, in which the key techniques include: (i) A robust joint angle-based description of kinematic human poses; (ii) Approximating temporal variation of joint angles using high order Fourier series to get reliable "ground truth"; (iii) A bidirectional recurrent network is designed as a post-processing module to refine the estimation of single image-based HPE models. Trained with the high-quality dataset constructed using our method, the network demonstrates outstanding performance to correct wrongly recognized joints and smooth their spatiotemporal trajectories. Tests show that joint angle-based refinement (JAR) outperforms the state-of-the-art HPE refinement network in challenging cases like figure skating and breaking. JAR also demonstrates great potential to rectify existing datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 68 references that are in the map. First posted on arXiv 15 Jul 2025.

Builds on

33 of 68 references.

References · 33

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  7. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  8. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  9. 2016Convolutional Pose Machinescited by 325
  10. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  11. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  12. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 207
21 more
  1. 2020Whole-Body Human Pose Estimation in the Wildcited by 178
  2. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  3. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  4. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  5. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  6. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  7. 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
  8. 2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
  9. 2020UniPose: Unified Human Pose Estimation in Single Images and Videoscited by 49
  10. 2018PoseFix: Model-agnostic General Human Pose Refinement Networkcited by 47
  11. 2016PoseTrack: Joint Multi-Person Pose Estimation and Trackingcited by 44
  12. 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37
  13. 2021Skeletor: Skeletal Transformers for Robust Body-Pose Estimationcited by 26
  14. 2020Toward fast and accurate human pose estimation via soft-gated skip connectionscited by 22
  15. 2018Learning to Refine Human Pose Estimationcited by 19
  16. 2023Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registrationcited by 13
  17. 2020Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded Peoplecited by 8
  18. 2023All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletescited by 8
  19. 2020Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Eventscited by 7
  20. 2021Lower-limb kinematics and kinetics during continuously varying human locomotioncited by 7
  21. 2023TimeSQL: Improving Multivariate Time Series Forecasting with Multi-Scale Patching and Smooth Quadratic Losscited by 5

Built on by

Not cited yet.