Single Person Pose Estimation: A Survey
Not on the map. Why?
Abstract (arXiv)
Human pose estimation in unconstrained images and videos is a fundamental computer vision task. To illustrate the evolutionary path in technique, in this survey we summarize representative human pose methods in a structured taxonomy, with a particular focus on deep learning models and single-person image setting. Specifically, we examine and survey all the components of a typical human pose estimation pipeline, including data augmentation, model architecture and backbone, supervision representation, post-processing, standard datasets, evaluation metrics. To envisage the future directions, we finally discuss the key unsolved problems and potential trends for human pose estimation.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 61 of its 95 references that are in the map. First posted on arXiv 21 Sep 2021.
Builds on
61 of 95 references.
References · 61
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
- 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
- 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
- 2016Convolutional Pose Machinescited by 325
- 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
- 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
- 2017Integral Human Pose Regressioncited by 255
38 more
- 2014Efficient Object Localization Using Convolutional Networkscited by 226
- 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
- 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
- 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
- 2017Compositional Human Pose Regressioncited by 124
- 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
- 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
- 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
- 2018Numerical Coordinate Regression with Convolutional Neural Networkscited by 72
- 2018Fast Human Pose Estimationcited by 68
- 2017Multi-Context Attention for Human Pose Estimationcited by 66
- 2020Monocular Human Pose Estimation: A Survey of Deep Learning-based Methodscited by 59
- 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
- 2015Flowing ConvNets for Human Pose Estimation in Videoscited by 55
- 2016Human pose estimation via Convolutional Part Heatmap Regressioncited by 51
- 2020UniPose: Unified Human Pose Estimation in Single Images and Videoscited by 49
- 2017Benchmarking and Error Diagnosis in Multi-Instance Pose Estimationcited by 48
- 2017Pose Invariant Embedding for Deep Person Re-identificationcited by 47
- 2018PoseFix: Model-agnostic General Human Pose Refinement Networkcited by 47
- 2018Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimationcited by 44
- 2017Joint Multi-Person Pose Estimation and Semantic Part Segmentationcited by 41
- 2017RGB-D-based Human Motion Recognition with Deep Learning: A Surveycited by 37
- 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37
- 2017Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimationcited by 35
- 2019Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Informationcited by 35
- 2020Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinementcited by 33
- 2016Convolutional Neural Fabricscited by 32
- 2016Recurrent Human Pose Estimationcited by 27
- 2014Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relationscited by 24
- 2020Adversarial Semantic Data Augmentation for Human Pose Estimationcited by 22
- 2019Human Pose Estimation with Spatial Contextual Informationcited by 21
- 2018Learning to Refine Human Pose Estimationcited by 19
- 2017Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimationcited by 18
- 2016Structured Feature Learning for Pose Estimationcited by 17
- 2016Chained Predictions Using Convolutional Neural Networkscited by 15
- 2015Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimationcited by 14
- 2016Human Pose Estimation using Deep Consensus Votingcited by 14
- 2013Learning Human Pose Estimation Features with Convolutional Networkscited by 11
50 most cited of 61 All 61 (JSON)
Built on by
Citing papers per year: 2023: 2; 2024: 0; 2025: 2.
4 papers.
- 2025Towards Robust and Realistic Human Pose Estimation via WiFi Signalscited by 5
- 2023Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementiacited by 2
- 2025GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Networkcited by 1
- 2023Augmenting Vision-Based Human Pose Estimation with Rotation Matrixcited by 0
- 2025GraphEnet: Event-driven Human Pose Estimation with a Graph Neural Network9 Oct 2025
- 2025Towards Robust and Realistic Human Pose Estimation via WiFi Signals16 Jan 2025
- 2023Augmenting Vision-Based Human Pose Estimation with Rotation Matrix9 Oct 2023
- 2023Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementia22 Aug 2023