Stacked Hourglass Networks for Human Pose Estimation (2016-03-22T00:00:00.000000Z)

TL;DR

This work introduces a novel convolutional network architecture for the task of human pose estimation that is described as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions.

Abstract

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.

Authors

Jia Deng

20 papers

Alejandro Newell

4 papers

Kaiyu Yang

5 papers

TL;DR

Abstract

Authors

References50 items

Deep learning for human part discovery in images

Convolutional Pose Machines

Deep Residual Learning for Image Recognition

Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis

DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

Deep multi-scale video prediction beyond mean square error

Deep Reflectance Maps

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Human Pose Estimation with Iterative Error Feedback

Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians

Semi-supervised Learning with Ladder Networks

Flowing ConvNets for Human Pose Estimation in Videos

Stacked What-Where Auto-encoders

Learning Deconvolution Network for Semantic Segmentation

Combining local appearance and holistic view: Dual-Source Deep Neural Networks for human pose estimation

Holistically-Nested Edge Detection

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Parsing occluded people by flexible compositions

DeepEdge: A multi-scale bifurcated deep network for top-down contour detection

Hypercolumns for object segmentation and fine-grained localization

Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture

Efficient object localization using Convolutional Networks

Fully convolutional networks for semantic segmentation

MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation

Going deeper with convolutions

Pose Machines: Articulated Pose Estimation via Inference Machines

Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

Recurrent Convolutional Neural Networks for Scene Labeling

Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

2D Human Pose Estimation: New Benchmark and State of the Art Analysis

DeepPose: Human Pose Estimation via Deep Neural Networks

Strong Appearance and Expressive Spatial Models for Human Pose Estimation

Articulated Human Detection with Flexible Mixtures of Parts

Learning Hierarchical Features for Scene Labeling

MODEC: Multimodal Decomposable Models for Human Pose Estimation

Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation

Indoor Semantic Segmentation using depth information

ImageNet classification with deep convolutional neural networks

Learning effective human pose estimation from inaccurate annotation

Real-time human pose recognition in parts from single depth images

Deconvolutional networks

Poselets: Body part detectors trained using 3D human pose annotations

A discriminatively trained, multiscale, deformable part model

Progressive search space reduction for human pose estimation

Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude

Torch7: A Matlab-like Environment for Machine Learning

Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation

Learning to parse images of articulated objects

Gradient-based learning applied to document recognition

Field of Study

Venue Information

Name

Type

URL

Alternate Names