mlsanityData to 7 Oct 2026

Pose Recognition with Cascade Transformers

arXiv 2104.06976 ↗First posted 14 Apr 2021cs.CVcited by 99

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject to various heuristic designs (not end-to-end mostly), whereas regression-based approaches attain relatively lower accuracy but they have less intermediate non-differentiable steps. Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches. We demonstrate the keypoint hypothesis (query) refinement process across different self-attention layers to reveal the recursive self-attention mechanism in Transformers. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). Builds on 34 of its 44 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

34 of 44 references.

References · 34

  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. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017Mask R-CNNcited by 7,259
  8. 2015Spatial Transformer Networkscited by 1,423
  9. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  10. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  11. 2019Objects as Pointscited by 1,172
  12. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
22 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  2. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  3. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  4. 2016Convolutional Pose Machinescited by 325
  5. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  6. 2017Integral Human Pose Regressioncited by 255
  7. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  8. 2019Analyzing the Structure of Attention in a Transformer Language Modelcited by 241
  9. 2019Visualizing and Measuring the Geometry of BERTcited by 215
  10. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  11. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  12. 2015End-to-end people detection in crowded scenescited by 140
  13. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  14. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  15. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  16. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  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. 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
  20. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  21. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  22. 2019Locality-constrained Spatial Transformer Network for Video Crowd Countingcited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 30; 2023: 28; 2024: 17; 2025: 11; 2026: 1.

99 papers.

Sort:

By area:

  1. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  2. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  3. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  4. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  5. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  6. 2022DETRs with Hybrid Matchingcited by 149
  7. 2021Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstructioncited by 110
  8. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  9. 2022Text Spotting Transformerscited by 70
  10. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  11. 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
  12. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
38 more
  1. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  2. 2023Rank-DETR for High Quality Object Detectioncited by 49
  3. 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
  4. 2023Human Pose as Compositional Tokenscited by 45
  5. 2022Flow-Guided Sparse Transformer for Video Deblurringcited by 43
  6. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  7. 2022EDTER: Edge Detection with Transformercited by 35
  8. 2022Multi-Task Learning with Multi-Query Transformer for Dense Predictioncited by 34
  9. 2021Test-Time Personalization with a Transformer for Human Pose Estimationcited by 33
  10. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  11. 2023Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Viewscited by 32
  12. 2022Towards Accurate Facial Landmark Detection via Cascaded Transformerscited by 31
  13. 2022VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformercited by 27
  14. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  15. 2023Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimationcited by 26
  16. 2022Efficient Human Pose Estimation via 3D Event Point Cloudcited by 25
  17. 2022RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmarkcited by 24
  18. 20222D Human Pose Estimation: A Surveycited by 21
  19. 2023X-Pose: Detecting Any Keypointscited by 21
  20. 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
  21. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  22. 2023End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenoncited by 16
  23. 2021CMTR: Cross-modality Transformer for Visible-infrared Person Re-identificationcited by 15
  24. 2021Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimationcited by 14
  25. 2021Ice hockey player identification via transformers and weakly supervised learningcited by 14
  26. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  27. 2022QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Querycited by 13
  28. 2022KPE: Keypoint Pose Encoding for Transformer-based Image Generationcited by 12
  29. 2022Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Taskscited by 12
  30. 2023DistilPose: Tokenized Pose Regression with Heatmap Distillationcited by 12
  31. 2023Neural Interactive Keypoint Detectioncited by 12
  32. 2024TCFormer: Visual Recognition via Token Clustering Transformercited by 12
  33. 2022Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectorscited by 10
  34. 2023On the Calibration of Human Pose Estimationcited by 10
  35. 2024Video-Based Human Pose Regression via Decoupled Space-Time Aggregationcited by 10
  36. 2022FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERcited by 9
  37. 2023GaitRef: Gait Recognition with Refined Sequential Skeletonscited by 9
  38. 2023Scene-aware Human Pose Generation using Transformercited by 9

50 most cited of 99 All 99 (JSON)