# Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation

arXiv: https://arxiv.org/abs/1707.05388 · HTML: https://mlsanity.com/paper/1707.05388/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2017.

## Built on by (most cited first, 30 of 48)

- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Occluded Human Mesh Recovery](https://mlsanity.com/paper/2203.13349/) (2022)
- [SuperAnimal pretrained pose estimation models for behavioral analysis](https://mlsanity.com/paper/2203.07436/) (2022)
- [Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking](https://mlsanity.com/paper/2106.03772/) (2021)
- [Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation](https://mlsanity.com/paper/2101.11223/) (2021)
- [SportsPose -- A Dynamic 3D sports pose dataset](https://mlsanity.com/paper/2304.01865/) (2023)
- [Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation](https://mlsanity.com/paper/2111.08557/) (2021)
- [Learning to Track Instances without Video Annotations](https://mlsanity.com/paper/2104.00287/) (2021)
- [Measuring Annotator Agreement Generally across Complex Structured, Multi-object, and Free-text Annotation Tasks](https://mlsanity.com/paper/2212.09503/) (2022)
- [Dance with You: The Diversity Controllable Dancer Generation via Diffusion Models](https://mlsanity.com/paper/2308.13551/) (2023)
- [Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity](https://mlsanity.com/paper/2306.07879/) (2023)
- [Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion](https://mlsanity.com/paper/2307.13463/) (2023)
- [Neural Interactive Keypoint Detection](https://mlsanity.com/paper/2308.10174/) (2023)
- [DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes](https://mlsanity.com/paper/2112.00627/) (2021)
- [Demystifying Unsupervised Semantic Correspondence Estimation](https://mlsanity.com/paper/2207.05054/) (2022)
- [Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation](https://mlsanity.com/paper/2208.03704/) (2022)
- [On the Calibration of Human Pose Estimation](https://mlsanity.com/paper/2311.17105/) (2023)
- [Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room](https://mlsanity.com/paper/2108.11801/) (2021)
- [AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regression](https://mlsanity.com/paper/2210.04014/) (2022)
- [Few-shot Geometry-Aware Keypoint Localization](https://mlsanity.com/paper/2303.17216/) (2023)
- [Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods](https://mlsanity.com/paper/2406.17382/) (2024)
- [Rethink Sparse Signals for Pose-guided Text-to-image Generation](https://mlsanity.com/paper/2506.20983/) (2025)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognition](https://mlsanity.com/paper/2503.20436/) (2025)
- [Real-time Pose Estimation from Images for Multiple Humanoid Robots](https://mlsanity.com/paper/2107.02675/) (2021)
- [Bias-Compensated Integral Regression for Human Pose Estimation](https://mlsanity.com/paper/2301.10431/) (2023)
- [The Influence of Faulty Labels in Data Sets on Human Pose Estimation](https://mlsanity.com/paper/2409.03887/) (2024)
- [Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association](https://mlsanity.com/paper/2111.12892/) (2021)
- [Human keypoint detection for close proximity human-robot interaction](https://mlsanity.com/paper/2207.07742/) (2022)

## 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.