Stacked Hourglass Networks for Human Pose Estimation

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

• Publication year

  2016

• Venue

  European Conference on Computer Vision

• Publication date

  2016-03-22

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1007/978-3-319-46484-8_29arXiv 1603.06937
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep learning for human part discovery in images

  2016cited by this paper
• Convolutional Pose Machines

  2016cited by this paper
• Semi-supervised Learning with Ladder Networks

  2015cited by this paper
• Holistically-Nested Edge Detection

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

  2015cited by this paper
• Deep multi-scale video prediction beyond mean square error

  2015cited by this paper
• Learning Deconvolution Network for Semantic Segmentation

  2015cited by this paper
• Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis

  2015cited by this paper
• Flowing ConvNets for Human Pose Estimation in Videos

  2015cited by this paper
• Human Pose Estimation with Iterative Error Feedback

  2015influential reference
• Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians

  2015cited by this paper
• Deep Reflectance Maps

  2015cited by this paper
• Stacked What-Where Auto-encoders

  2015cited by this paper
• DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

  2015cited by this paper
• Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation

  2015cited by this paper
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Fully convolutional networks for semantic segmentation

  2014influential reference
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

  2014influential reference
• DeepEdge: A multi-scale bifurcated deep network for top-down contour detection

  2014cited by this paper
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

  2014cited by this paper
• Recurrent Convolutional Neural Networks for Scene Labeling

  2014cited by this paper
• Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

  2014cited by this paper
• Parsing occluded people by flexible compositions

  2014cited by this paper
• Hypercolumns for object segmentation and fine-grained localization

  2014cited by this paper
• Pose Machines: Articulated Pose Estimation via Inference Machines

  2014cited by this paper
• MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation

  2014cited by this paper
• Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture

  2014cited by this paper
• 2D Human Pose Estimation: New Benchmark and State of the Art Analysis

  2014cited by this paper
• Going deeper with convolutions

  2014cited by this paper
• Efficient object localization using Convolutional Networks

  2014cited by this paper
• DeepPose: Human Pose Estimation via Deep Neural Networks

  2013influential reference
• MODEC: Multimodal Decomposable Models for Human Pose Estimation

  2013influential reference
• Strong Appearance and Expressive Spatial Models for Human Pose Estimation

  2013cited by this paper
• Learning Hierarchical Features for Scene Labeling

  2013cited by this paper
• Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation

  2013cited by this paper
• Indoor Semantic Segmentation using depth information

  2013cited by this paper
• Articulated Human Detection with Flexible Mixtures of Parts

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Learning effective human pose estimation from inaccurate annotation

  2011cited by this paper
• Real-time human pose recognition in parts from single depth images

  2011cited by this paper
• Torch7: A Matlab-like Environment for Machine Learning

  2011cited by this paper
• Deconvolutional networks

  2010cited by this paper
• Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation

  2010cited by this paper
• Poselets: Body part detectors trained using 3D human pose annotations

  2009cited by this paper
• A discriminatively trained, multiscale, deformable part model

  2008cited by this paper
• Progressive search space reduction for human pose estimation

  2008cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper

• HPPRNet: Human parsing enabled pose refinement network for human activity recognition

  2026cites this paper
• YOLD: You Only Look Denseness for Tiny Object Detection in Aerial Images

  2026cites this paper
• A Cross Self-Attention Feature Fusion Module for 2D Multiple Human Pose Estimation

  2026cites this paper
• Sit‐to‐Stand Power From 2D Pose Estimation as an Indicator of Muscle Strength in Older Adults

  2026cites this paper
• Double-Chain Graph Convolution Transformer for 3D Human Pose Estimation

  2026cites this paper
• ECCFNet: enhanced context-aware cross-resolution fusion network for human pose estimation

  2026influential citation
• Automated Extraction of 3-D Windows From MVS Point Clouds by Comprehensive Fusion of Multitype Features

  2026cites this paper
• Shadow vanishing point detection via combined human/shadow adaptive modulation

  2026cites this paper
• Camera-Space Hand Mesh Reconstruction from a Monocular Image via Pseudo Stereo Perception

  2026cites this paper
• Improving generative adversarial network generalization for facialexpression synthesis

  2026cites this paper
• Exploiting Class-agnostic Visual Prior for Few-shot Keypoint Detection

  2026cites this paper
• Real-Time Rat Pose Estimation System via Miniature Stereo Vision for Robot-Rat Interaction

  2026cites this paper
• GS-UNet: ConvNeXt-based keypoint-driven visual servoing with cross-hierarchical attention gating for high-precision robotic assembly

  2026cites this paper
• Differentiable Neural Architecture Search for medical image segmentation: A systematic review and field audit.

  2026cites this paper
• MSPNet: A Multiscale Pyramid Network for Semantic Segmentation of Urban-Scale Photogrammetric Point Clouds

  2026cites this paper
• Graph-Based and Multi-Stage Constraints for Hand–Object Reconstruction

  2026cites this paper
• HEViTPose: towards high-accuracy and efficient 2D human pose estimation with cascaded group spatial reduction attention

  2026influential citation
• Learning Structural Relations for Robust Chest X-Ray Landmark Detection

  2026cites this paper
• Local-Global Feature Fusion for Enhancing 3D Human Pose Estimation

  2026cites this paper
• Automatic localization of cross sections corresponding to standard transesophageal echocardiographic views on computed tomography volume

  2026cites this paper
• A Study on Real-time Object Detection using Deep Learning

  2026cites this paper
• From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction

  2026cites this paper
• Measurement of Echocardiographic Parameters in Various Cardiac Phases: A Comparative Study of Deep Learning Models and Keypoint Representations

  2026cites this paper
• DSVTformer: Dual-stream Spatial-View-Temporal Transformer for multi-view 3D human pose estimation

  2026cites this paper
• Pose Under Covers: In-Bed Human Pose Estimation Using Multisensor Image Fusion and Graph Convolutional Network

  2026cites this paper
• GHGPSE-Net: a method towards spaceborne automated extraction of greenhouse-gas point sources using point-object-detection deep neural network

  2026cites this paper
• 3D landmark detection on human point clouds: A benchmark and a dual cascade point transformer framework

  2026cites this paper
• RePose: A Real-Time 3D Human Pose Estimation and Biomechanical Analysis Framework for Rehabilitation

  2026cites this paper
• PECC: Position Encoding Coordinate Classification System Design for Human Pose Estimation

  2026cites this paper
• Balancing Speed and Accuracy: A Mouth-Eye 3D Keypoints Alignment Framework for Large Poses

  2026cites this paper
• Co-HSC: Complementary image-mesh fusion for dense human-scene contact estimation

  2026cites this paper
• Accurate urban solar potential estimation empowered by multimodal 3-D building reconstruction: a case study in Landshut, Germany

  2026cites this paper
• Aligning Computer Vision with Expert Assessment: An Adaptive Hybrid Framework for Real-Time Fatigue Assessment in Smart Manufacturing

  2026cites this paper
• K-nearest neighbor-enhanced Residual Learning Framework for image restoration

  2026cites this paper
• Multi-Modal Multi-Stage Multi-Task Learning for Occlusion-Aware Facial Landmark Localisation

  2026cites this paper
• MSTPFormer: Mamba-driven spatiotemporal bidirectional dual-stream parallel transformer for 3D human pose estimation

  2026cites this paper
• Deep learning for object detection: state of the art, challenges, and future directions

  2026cites this paper
• HyT-Pose: Accurate Pose Estimation by Iteratively Fusing Global and Local Context

  2026cites this paper
• Advancing depth-based semi-supervised three-dimensional hand pose estimation with consistency training

  2026cites this paper
• OccFace: Unified Occlusion-Aware Facial Landmark Detection with Per-Point Visibility

  2026cites this paper
• Development of a Novel Deep Learning-Based Gaze Estimation Method for Detecting Strabismus

  2026cites this paper
• HandFS: Wavelet-guided Frequency-Spatial Domain Feature Decoupling Network for 3D Hand Pose Estimation Under Occlusion

  2026cites this paper
• SPRITETOMESH: Automatic Mesh Generation for 2D Skeletal Animation Using Learned Segmentation and Contour-Aware Vertex Placement

  2026cites this paper
• Transformers Outperform ConvNets for Root Segmentation: A Systematic Comparison Across Nine Datasets

  2026cites this paper
• Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement

  2026cites this paper
• ROM-Pose: restoring occluded mask image for 2D human pose estimation

  2025cites this paper
• Partition Map-Based Fast Block Partitioning for VVC Inter Coding

  2025cites this paper
• 3D Human Pose Estimation via Spatial Graph Order Attention and Temporal Body Aware Transformer

  2025cites this paper
• InLite-HRNet: efficient band convolution network for human pose estimation

  2025cites this paper
• Action Recognition via Multi-View Perception Feature Tracking for Human-Robot Interaction

  2025cites this paper
• BR-Pose: enhancing human pose estimation through Bi-level routing attention and multi-level weight fusion

  2025cites this paper
• Healthy and Unhealthy Oil Palm Tree Detection Using Deep Learning Method

  2025cites this paper
• Low-resolution human pose estimation and action recognition via pose-driven super-resolution reconstruction

  2025influential citation
• AcuSim: A Synthetic Dataset for Cervicocranial Acupuncture Points Localisation

  2025cites this paper
• SKAD: A Unified Framework Guided by Structural Knowledge for Anomaly Detection of Dampers in Transmission Lines

  2025cites this paper
• A Hierarchical Progressive Perception System for Autonomous Luggage Trolley Collection

  2025cites this paper
• Sparse and transferable three-dimensional dynamic vascular reconstruction for instantaneous diagnosis

  2025cites this paper
• Robust keypoint-based method for peduncle pose estimation in unstructured environments

  2025cites this paper
• Generation driven understanding of localized 3D scenes with 3D diffusion model

  2025cites this paper
• Uncertainty Quantification and Quality Control for Heatmap-Based Landmark Detection Models

  2025cites this paper
• VisualCent: Visual Human Analysis using Dynamic Centroid Representation

  2025cites this paper
• Crowd Detection Using Very-Fine-Resolution Satellite Imagery

  2025cites this paper
• Monocular 3D hand pose estimation based on high-resolution network

  2025cites this paper
• YOLO-RS: Remote Sensing Enhanced Crop Detection Methods

  2025cites this paper
• Self-supervised keypoint detection based on affine transformation

  2025cites this paper
• PFLO: a high-throughput pose estimation model for field maize based on YOLO architecture

  2025cites this paper
• AI Method for LAMOST Fiber Detection Based on Front Illumination

  2025cites this paper
• Fetal Cerebellum Landmark Detection Based on 3D MRI: Method and Benchmark

  2025cites this paper
• Adaptive Detection of Fast-moving Celestial Objects Using a Mixture-of-experts and Physical-inspired Neural Network

  2025cites this paper
• A Survey on Deep Learning-Based Lane Detection Algorithms for Camera and LiDAR

  2025cites this paper
• Multi-Person Pose Estimation with Feature Enhancement and Decoupling Based on Contrastive Learning

  2025cites this paper
• Calibrating the Principal Point of Vehicle-Mounted Fisheye Cameras Using Point-Oriented Representation

  2025cites this paper
• ListPose: Lightweight and Implicit Spatial-Temporal Modeling with TokenPose for Video-Based Pose Estimation

  2025cites this paper
• A Survey of the State of the Art in Monocular 3D Human Pose Estimation: Methods, Benchmarks, and Challenges

  2025cites this paper
• A review of transformer-based human pose estimation: Delving into the relation modeling

  2025cites this paper
• Anti-drift pose tracker (ADPT), a transformer-based network for robust animal pose estimation cross-species

  2025cites this paper
• Spatial–Temporal–Geometric Graph Convolutional Network for 3-D Human Pose Estimation From Multiview Video

  2025cites this paper
• YOLO-MousePose: A Novel Framework and Dataset for Mouse Pose Estimation From a Top–Down View

  2025cites this paper
• Artificial neural networks for finger vein recognition: A survey

  2025cites this paper
• OA-WinSeg: Occlusion-Aware Window Segmentation With Conditional Adversarial Training Guided by Structural Prior Information

  2025cites this paper
• Perception-Enhanced Network for Accurate Human Pose Estimation

  2025cites this paper
• DCFormer: Divide-and-Conquer in 3D Human Pose Estimation Tasks

  2025cites this paper
• Artificial Intelligence in Fitness: Pose Estimation and Movement Correction

  2025cites this paper
• Diffusion-Refinement Pose Estimation With Hybrid Representation

  2025influential citation
• WiPE: Privacy-Friendly WiFi-Based Human Pose Estimation on Consumer Platform

  2025cites this paper
• Enhanced Nighttime Vehicle Detection for On-Board Processing

  2025influential citation
• Occluded human pose estimation based on part-aware discrete diffusion priors

  2025cites this paper
• Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning

  2025cites this paper
• Advancing Active Speaker Detection for Egocentric Videos

  2025cites this paper
• MSANet: Mixed Spectral and Attention Network for Robust 3D Human Pose Estimation

  2025cites this paper
• Deep learning for recognition and detection of plant diseases and pests

  2025cites this paper
• Transformer-based weakly supervised 3D human pose estimation

  2025cites this paper
• Cricket Shot Analysis using Conditional Directed Spatio-Temporal Graph networks

  2025cites this paper
• VertexNet: a table structure recognition model based on key points for complex scenes

  2025cites this paper
• Single-Person 3D Human Pose Estimation Based on Deep Learning: A Review

  2025cites this paper
• Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation

  2025cites this paper
• Automatic Physical Examination Segmentation within Objective Structured Clinical Examination Videos

  2025cites this paper
• InfraEyeNet: Infrared eye landmark detection network with modified bottleneck module

  2025cites this paper
• HGMamba: Enhancing 3D Human Pose Estimation with a HyperGCN-Mamba Network

  2025influential citation
• Lightweight CA-YOLOv7-Based Badminton Stroke Recognition: A Real-Time and Accurate Behavior Analysis Method

  2025cites this paper