mlsanityData to 7 Oct 2026

Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation

arXiv 2111.08557 ↗First posted 16 Nov 2021cs.CV cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

In keypoint estimation tasks such as human pose estimation, heatmap-based regression is the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer from quantization error and require excessive computation to generate and post-process. Motivated to find a more efficient solution, we propose to model individual keypoints and sets of spatially related keypoints (i.e., poses) as objects within a dense single-stage anchor-based detection framework. Hence, we call our method KAPAO (pronounced "Ka-Pow"), for Keypoints And Poses As Objects. KAPAO is applied to the problem of single-stage multi-person human pose estimation by simultaneously detecting human pose and keypoint objects and fusing the detections to exploit the strengths of both object representations. In experiments, we observe that KAPAO is faster and more accurate than previous methods, which suffer greatly from heatmap post-processing. The accuracy-speed trade-off is especially favourable in the practical setting when not using test-time augmentation. Source code: https://github.com/wmcnally/kapao.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 72 of its 83 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

72 of 83 references.

References · 72

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Mask R-CNNcited by 7,259
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Fast R-CNNcited by 2,930
  9. 2018YOLOv3: An Incremental Improvementcited by 2,652
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  11. 2015Variational Inference with Normalizing Flowscited by 2,161
  12. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
38 more
  1. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  3. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  4. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  7. 2019Objects as Pointscited by 1,172
  8. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  9. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  10. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  11. 2017Focal Loss for Dense Object Detectioncited by 749
  12. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  13. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  14. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  15. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  16. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  17. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  18. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  19. 2016Convolutional Pose Machinescited by 325
  20. 2016Dynamic Filter Networkscited by 318
  21. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  22. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  23. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  24. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  25. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  26. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  27. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  28. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  29. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  30. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  31. 2019Adaptive Wing Loss for Robust Face Alignment via Heatmap Regressioncited by 127
  32. 2020TransPose: Keypoint Localization via Transformercited by 126
  33. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  34. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  35. 2018Unsupervised Learning of Object Landmarks through Conditional Image Generationcited by 113
  36. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  37. 2018Hand Pose Estimation via Latent 2.5D Heatmap Regressioncited by 111
  38. 2021Pose Recognition with Cascade Transformerscited by 99

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 7; 2025: 3; 2026: 2.

20 papers.

Sort:

By area:

  1. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  2. 2022FenceNet: Fine-grained Footwork Recognition in Fencingcited by 12
  3. 2024YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systemscited by 6
  4. 2024Referring Human Pose and Mask Estimation in the Wildcited by 6
  5. 2024Underground Mapping and Localization Based on Ground-Penetrating Radarcited by 5
  6. 20253D Plant Root Skeleton Detection and Extractioncited by 5
  7. 2024Occluded Human Pose Estimation based on Limb Joint Augmentationcited by 3
  8. 2022A View Independent Classification Framework for Yoga Posturescited by 2
  9. 2023Single-stage Multi-human Parsing via Point Sets and Center-based Offsetscited by 2
  10. 2023BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimationcited by 2
  11. 2024SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillationcited by 1
  12. 2024GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolutioncited by 1
8 more
  1. 2024MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detectioncited by 1
  2. 2025DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypointscited by 1
  3. 2025Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computingcited by 1
  4. 2022Entropy-driven Unsupervised Keypoint Representation Learning in Videoscited by 0
  5. 2023Hybrid model for Single-Stage Multi-Person Pose Estimationcited by 0
  6. 2023Non-Contact Breathing Rate Detection Using Optical Flowcited by 0
  7. 2026FlyPose: Towards Robust Human Pose Estimation From Aerial Viewscited by 0
  8. 2026ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose Estimationcited by 0