mlsanityData to 7 Oct 2026

ProbPose: A Probabilistic Approach to 2D Human Pose Estimation

arXiv 2412.02254 ↗First posted 3 Dec 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Current Human Pose Estimation methods have achieved significant improvements. However, state-of-the-art models ignore out-of-image keypoints and use uncalibrated heatmaps as keypoint location representations. To address these limitations, we propose ProbPose, which predicts for each keypoint: a calibrated probability of keypoint presence at each location in the activation window, the probability of being outside of it, and its predicted visibility. To address the lack of evaluation protocols for out-of-image keypoints, we introduce the CropCOCO dataset and the Extended OKS (Ex-OKS) metric, which extends OKS to out-of-image points. Tested on COCO, CropCOCO, and OCHuman, ProbPose shows significant gains in out-of-image keypoint localization while also improving in-image localization through data augmentation. Additionally, the model improves robustness along the edges of the bounding box and offers better flexibility in keypoint evaluation. The code and models are available on https://mirapurkrabek.github.io/ProbPose/ for research purposes.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 28 of its 48 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

28 of 48 references.

References · 28

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  6. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  7. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  8. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  9. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  10. 2016From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classificationcited by 337
  11. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  12. 2017Integral Human Pose Regressioncited by 255
16 more
  1. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  2. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  3. 2019Adaptive Wing Loss for Robust Face Alignment via Heatmap Regressioncited by 127
  4. 2017Compositional Human Pose Regressioncited by 124
  5. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  6. 2017Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networkscited by 108
  7. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  8. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  9. 2022YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Losscited by 66
  10. 2017Human Pose Regression by Combining Indirect Part Detection and Contextual Informationcited by 52
  11. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  12. 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
  13. 2020Adversarial Semantic Data Augmentation for Human Pose Estimationcited by 22
  14. 2023On the Calibration of Human Pose Estimationcited by 10
  15. 2022Heatmap Distribution Matching for Human Pose Estimationcited by 9
  16. 2022AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regressioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 7.

9 papers.