mlsanityData to 14 Oct 2026

CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark

arXiv 1812.00324 ↗First posted 2 Dec 2018cs.CVcited by 214

Not on the map. Why?

Abstract (arXiv)

Multi-person pose estimation is fundamental to many computer vision tasks and has made significant progress in recent years. However, few previous methods explored the problem of pose estimation in crowded scenes while it remains challenging and inevitable in many scenarios. Moreover, current benchmarks cannot provide an appropriate evaluation for such cases. In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms. Our model consists of two key components: joint-candidate single person pose estimation (SPPE) and global maximum joints association. With multi-peak prediction for each joint and global association using graph model, our method is robust to inevitable interference in crowded scenes and very efficient in inference. The proposed method surpasses the state-of-the-art methods on CrowdPose dataset by 5.2 mAP and results on MSCOCO dataset demonstrate the generalization ability of our method. Source code and dataset will be made publicly available.

Key facts. Cited by 214 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 42; 2022: 47; 2023: 49; 2024: 34; 2025: 24; 2026: 18.

214 papers.

Sort:

By area:

  1. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  2. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 200
  3. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 175
  4. 2023InstructDiffusion: A Generalist Modeling Interface for Vision Taskscited by 164
  5. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 155
  6. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  7. 2024VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Taskscited by 137
  8. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  9. 2021AP-10K: A Benchmark for Animal Pose Estimation in the Wildcited by 123
  10. 2022Revealing the Dark Secrets of Masked Image Modelingcited by 117
  11. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  12. 2025Detect Anything via Next Point Predictioncited by 73
38 more
  1. 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3Dcited by 72
  2. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  3. 2023Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenescited by 68
  4. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 65
  5. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  6. 2022Normalizing Flows for Human Pose Anomaly Detectioncited by 60
  7. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
  8. 2022APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Trackingcited by 56
  9. 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
  10. 2022Occluded Human Mesh Recoverycited by 54
  11. 2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
  12. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 50
  13. 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
  14. 2021Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesiscited by 46
  15. 2023Human Pose as Compositional Tokenscited by 45
  16. 2021TFPose: Direct Human Pose Estimation with Transformerscited by 42
  17. 2021RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Imagescited by 39
  18. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  19. 2022Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detectioncited by 34
  20. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 34
  21. 2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 33
  22. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 32
  23. 2025SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimationcited by 32
  24. 2023UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detectioncited by 31
  25. 2024Harmony4D: A Video Dataset for In-The-Wild Close Human Interactionscited by 31
  26. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  27. 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
  28. 2022Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithmscited by 28
  29. 2023Human Pose Estimation in Extremely Low-Light Conditionscited by 27
  30. 2021ViPNAS: Efficient Video Pose Estimation via Neural Architecture Searchcited by 26
  31. 2023Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimationcited by 26
  32. 2022Efficient Human Pose Estimation via 3D Event Point Cloudcited by 25
  33. 2023Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfercited by 25
  34. 2024HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidancecited by 25
  35. 2021Shape-aware Multi-Person Pose Estimation from Multi-View Imagescited by 24
  36. 2022Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimationcited by 24
  37. 2023Sampling is Matter: Point-guided 3D Human Mesh Reconstructioncited by 24
  38. 2022ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wildcited by 23

50 most cited of 214 All 214 (JSON)