mlsanityData to 7 Oct 2026

Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation

arXiv 1707.05388 ↗First posted 17 Jul 2017cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

We propose a new method to analyze the impact of errors in algorithms for multi-instance pose estimation and a principled benchmark that can be used to compare them. We define and characterize three classes of errors - localization, scoring, and background - study how they are influenced by instance attributes and their impact on an algorithm's performance. Our technique is applied to compare the two leading methods for human pose estimation on the COCO Dataset, measure the sensitivity of pose estimation with respect to instance size, type and number of visible keypoints, clutter due to multiple instances, and the relative score of instances. The performance of algorithms, and the types of error they make, are highly dependent on all these variables, but mostly on the number of keypoints and the clutter. The analysis and software tools we propose offer a novel and insightful approach for understanding the behavior of pose estimation algorithms and an effective method for measuring their strengths and weaknesses.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 10; 2023: 11; 2024: 4; 2025: 3; 2026: 5.

48 papers.

Sort:

  1. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  2. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  3. 2022Occluded Human Mesh Recoverycited by 52
  4. 2022SuperAnimal pretrained pose estimation models for behavioral analysiscited by 38
  5. 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
  6. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  7. 2023SportsPose -- A Dynamic 3D sports pose datasetcited by 26
  8. 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
  9. 2021Learning to Track Instances without Video Annotationscited by 18
  10. 2023Dance with You: The Diversity Controllable Dancer Generation via Diffusion Modelscited by 17
  11. 2022Measuring Annotator Agreement Generally across Complex Structured, Multi-object, and Free-text Annotation Taskscited by 16
  12. 2023Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguitycited by 13
36 more
  1. 2023Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotioncited by 12
  2. 2023Neural Interactive Keypoint Detectioncited by 12
  3. 2021DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenescited by 11
  4. 2022Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimationcited by 10
  5. 2023On the Calibration of Human Pose Estimationcited by 10
  6. 2022Demystifying Unsupervised Semantic Correspondence Estimationcited by 9
  7. 2021Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating roomcited by 7
  8. 2022AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regressioncited by 6
  9. 2023Few-shot Geometry-Aware Keypoint Localizationcited by 6
  10. 2024Automatic infant 2D pose estimation from videos: comparing seven deep neural network methodscited by 6
  11. 2025Rethink Sparse Signals for Pose-guided Text-to-image Generationcited by 5
  12. 2021Single Person Pose Estimation: A Surveycited by 4
  13. 2025Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognitioncited by 4
  14. 2021Real-time Pose Estimation from Images for Multiple Humanoid Robotscited by 3
  15. 2023Bias-Compensated Integral Regression for Human Pose Estimationcited by 3
  16. 2021Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Associationcited by 2
  17. 2022Human keypoint detection for close proximity human-robot interactioncited by 2
  18. 2023Robustness Evaluation in Hand Pose Estimation Models using Metamorphic Testingcited by 2
  19. 2024The Influence of Faulty Labels in Data Sets on Human Pose Estimationcited by 2
  20. 2021Learning Spatial Context with Graph Neural Network for Multi-Person Pose Groupingcited by 1
  21. 2022Black-box Error Diagnosis in Deep Neural Networks for Computer Vision: a Survey of Toolscited by 1
  22. 2022Location-free Human Pose Estimationcited by 1
  23. 2022Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hipcited by 1
  24. 2024Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revisioncited by 1
  25. 2024Whole-Herd Elephant Pose Estimation from Drone Data for Collective Behavior Analysiscited by 1
  26. 2021Greedy Offset-Guided Keypoint Grouping for Human Pose Estimationcited by 0
  27. 2021Adaptive Dilated Convolution For Human Pose Estimationcited by 0
  28. 2021Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimationcited by 0
  29. 2023Towards High Performance One-Stage Human Pose Estimationcited by 0
  30. 2023BundleMoCap: Efficient, Robust and Smooth Motion Capture from Sparse Multiview Videoscited by 0
  31. 2025MultiFormer: A Multi-Person Pose Estimation System Based on CSI and Attention Mechanismcited by 0
  32. 2026UnrealPose: Leveraging Game Engine Kinematics for Large-Scale Synthetic Human Pose Datacited by 0
  33. 2026OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025cited by 0
  34. 2026FISICA: A Deployed Service for Plantar-Pressure and Posture Assessment with Ontology-Grounded Recommendationcited by 0
  35. 2026A Black-Box Adversarial Attack on Human Pose Estimation and Keypoint-Based Action Recognition Modelscited by 0
  36. 2026Can 4D Foundation Models Remember?cited by 0