mlsanityData to 7 Oct 2026

TFPose: Direct Human Pose Estimation with Transformers

arXiv 2103.15320 ↗First posted 29 Mar 2021cs.CVcited by 42

Not on the map. Why?

Abstract (arXiv)

We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-the-art methods, we formulate the pose estimation task into a sequence prediction problem that can effectively be solved by transformers. Our framework is simple and direct, bypassing the drawbacks of the heatmap-based pose estimation. Moreover, with the attention mechanism in transformers, our proposed framework is able to adaptively attend to the features most relevant to the target keypoints, which largely overcomes the feature misalignment issue of previous regression-based methods and considerably improves the performance. Importantly, our framework can inherently take advantages of the structured relationship between keypoints. Experiments on the MS-COCO and MPII datasets demonstrate that our method can significantly improve the state-of-the-art of regression-based pose estimation and perform comparably with the best heatmap-based pose estimation methods.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 42 of its 53 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

42 of 53 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2017Mask R-CNNcited by 7,259
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
30 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  2. 2020Pre-Trained Image Processing Transformercited by 891
  3. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  4. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  5. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  6. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  7. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  8. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  9. 2017Integral Human Pose Regressioncited by 255
  10. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  11. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  12. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  13. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  14. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  15. 2017Compositional Human Pose Regressioncited by 124
  16. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  17. 2019Single-Stage Multi-Person Pose Machinescited by 95
  18. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  19. 2018Numerical Coordinate Regression with Convolutional Neural Networkscited by 72
  20. 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
  21. 2017Multi-Context Attention for Human Pose Estimationcited by 66
  22. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  23. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  24. 2016Human pose estimation via Convolutional Part Heatmap Regressioncited by 51
  25. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  26. 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37
  27. 2019Human Pose Estimation with Spatial Contextual Informationcited by 21
  28. 2015Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussianscited by 14
  29. 2016Human Pose Estimation using Deep Consensus Votingcited by 14
  30. 2018Facial Landmarks Detection by Self-Iterative Regression based Landmarks-Attention Networkcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 14; 2023: 9; 2024: 5; 2025: 3.

42 papers.

Sort:

By area:

  1. 2022DETRs with Hybrid Matchingcited by 149
  2. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 140
  3. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
  4. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  5. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  6. 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
  7. 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
  8. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  9. 2021TransCrowd: weakly-supervised crowd counting with transformerscited by 61
  10. 2021Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Predictioncited by 57
  11. 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
  12. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
30 more
  1. 2021Test-Time Personalization with a Transformer for Human Pose Estimationcited by 33
  2. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  3. 2022Towards Accurate Facial Landmark Detection via Cascaded Transformerscited by 31
  4. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  5. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  6. 2021Generative Transformer for Accurate and Reliable Salient Object Detectioncited by 18
  7. 2021Temporal Action Proposal Generation with Transformerscited by 17
  8. 2023A Graph-Based Approach for Category-Agnostic Pose Estimationcited by 16
  9. 2023Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguitycited by 13
  10. 2023DistilPose: Tokenized Pose Regression with Heatmap Distillationcited by 12
  11. 2023SHaRPose: Sparse High-Resolution Representation for Human Pose Estimationcited by 11
  12. 2021Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Netcited by 9
  13. 2021PE-former: Pose Estimation Transformercited by 7
  14. 2023Lightweight Super-Resolution Head for Human Pose Estimationcited by 7
  15. 2022IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimationcited by 6
  16. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  17. 2024GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimationcited by 6
  18. 2024Referring Human Pose and Mask Estimation in the Wildcited by 6
  19. 2022Video based Object 6D Pose Estimation using Transformerscited by 5
  20. 2022An Energy-Based Prior for Generative Saliencycited by 3
  21. 2022VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimationcited by 3
  22. 2022DPIT: Dual-Pipeline Integrated Transformer for Human Pose Estimationcited by 3
  23. 2024DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimationcited by 2
  24. 2022Location-free Human Pose Estimationcited by 1
  25. 2024GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolutioncited by 1
  26. 2024MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detectioncited by 1
  27. 2023Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimationcited by 0
  28. 2025Leveraging 2D Masked Reconstruction for Domain Adaptation of 3D Pose Estimationcited by 0
  29. 2025LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimationcited by 0
  30. 2025A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Networkcited by 0