mlsanityData to 7 Oct 2026

Fast Human Pose Estimation

arXiv 1811.05419 ↗First posted 13 Nov 2018cs.CVcited by 68

Not on the map. Why?

Abstract (arXiv)

Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we investigate the under-studied but practically critical pose model efficiency problem. To this end, we present a new Fast Pose Distillation (FPD) model learning strategy. Specifically, the FPD trains a lightweight pose neural network architecture capable of executing rapidly with low computational cost. It is achieved by effectively transferring the pose structure knowledge of a strong teacher network. Extensive evaluations demonstrate the advantages of our FPD method over a broad range of state-of-the-art pose estimation approaches in terms of model cost-effectiveness on two standard benchmark datasets, MPII Human Pose and Leeds Sports Pose.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 8; 2023: 21; 2024: 12; 2025: 3; 2026: 4.

68 papers.

Sort:

By area:

  1. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  2. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  3. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  4. 2021Online Knowledge Distillation for Efficient Pose Estimationcited by 55
  5. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  6. 2021When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarkscited by 41
  7. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  8. 2021Data-Free Knowledge Transfer: A Surveycited by 31
  9. 2023Human Pose Estimation in Extremely Low-Light Conditionscited by 27
  10. 2023Teacher-Student Architecture for Knowledge Distillation: A Surveycited by 26
  11. 2022Efficient Human Pose Estimation via 3D Event Point Cloudcited by 25
  12. 2023Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?cited by 21
38 more
  1. 2023Cumulative Spatial Knowledge Distillation for Vision Transformerscited by 18
  2. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
  3. 2022Fast Object Placement Assessmentcited by 12
  4. 2023DistilPose: Tokenized Pose Regression with Heatmap Distillationcited by 12
  5. 2023Learning to "Segment Anything" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIRcited by 11
  6. 2023SHaRPose: Sparse High-Resolution Representation for Human Pose Estimationcited by 11
  7. 2023Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Modulecited by 10
  8. 2024A Survey on Symbolic Knowledge Distillation of Large Language Modelscited by 9
  9. 2023AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesiscited by 8
  10. 2024Real World Federated Learning with a Knowledge Distilled Transformer for Cardiac CT Imagingcited by 8
  11. 2021Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating roomcited by 7
  12. 2024FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditionscited by 7
  13. 2021Estimating and Maximizing Mutual Information for Knowledge Distillationcited by 6
  14. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  15. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  16. 2021SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimationcited by 5
  17. 2022LACV-Net: Semantic Segmentation of Large-Scale Point Cloud Scene via Local Adaptive and Comprehensive VLADcited by 5
  18. 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Modelscited by 5
  19. 2023POISE: Pose Guided Human Silhouette Extraction under Occlusionscited by 5
  20. 2021Students are the Best Teacher: Exit-Ensemble Distillation with Multi-Exitscited by 4
  21. 2021WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotationscited by 4
  22. 2021Single Person Pose Estimation: A Surveycited by 4
  23. 2023Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillationcited by 4
  24. 2023Exploring Event-based Human Pose Estimation with 3D Event Representationscited by 4
  25. 2024Human Modelling and Pose Estimation Overviewcited by 4
  26. 2021Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Trainingcited by 3
  27. 2024Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breedingcited by 3
  28. 2021ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphonescited by 2
  29. 2022Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local Descriptorscited by 2
  30. 2023MixBCT: Towards Self-Adapting Backward-Compatible Trainingcited by 2
  31. 2024Fine-tuning a Multiple Instance Learning Feature Extractor with Masked Context Modelling and Knowledge Distillationcited by 2
  32. 2025Soft Knowledge Distillation with Multi-Dimensional Cross-Net Attention for Image Restoration Models Compressioncited by 2
  33. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
  34. 2021Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimationcited by 1
  35. 2021Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Bettercited by 1
  36. 2021Joint 3D Human Shape Recovery and Pose Estimation from a Single Image with Bilayer Graphcited by 1
  37. 2022Repainting and Imitating Learning for Lane Detectioncited by 1
  38. 2023GoalieNet: A Multi-Stage Network for Joint Goalie, Equipment, and Net Pose Estimation in Ice Hockeycited by 1

50 most cited of 68 All 68 (JSON)