Deep High-Resolution Representation Learning for Human Pose Estimation (2019-02-25T00:00:00.000000Z)

TL;DR

This paper proposes a network that maintains high-resolution representations through the whole process of human pose estimation and empirically demonstrates the effectiveness of the network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset.

Abstract

In this paper, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. In addition, we show the superiority of our network in pose tracking on the PoseTrack dataset. The code and models have been publicly available at https://github.com/leoxiaobin/deep-high-resolution-net.pytorch.

Authors

Ke Sun

6 papers

Bin Xiao

6 papers

Dong Liu

2 papers

TL;DR

Abstract

Authors

References86 items

Deeply Learned Compositional Models for Human Pose Estimation

Pose Partition Networks for Multi-person Pose Estimation

Pose Proposal Networks

Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation

Quantized Densely Connected U-Nets for Efficient Landmark Localization

MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network

Human Pose Estimation with Parsing Induced Learner

IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks

NU-Net: Deep Residual Wide Field of View Convolutional Neural Network for Semantic Segmentation

Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation

Joint Flow: Temporal Flow Fields for Multi Person Tracking

Simple Baselines for Human Pose Estimation and Tracking

Interleaved Structured Sparse Convolutional Neural Networks

Multi-Scale Structure-Aware Network for Human Pose Estimation

PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model

Pose Flow: Efficient Online Pose Tracking

Detect-and-Track: Efficient Pose Estimation in Videos

Integral Human Pose Regression

Cascaded Pyramid Network for Multi-person Pose Estimation

AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding

PoseTrack: A Benchmark for Human Pose Estimation and Tracking

Human Pose Regression by Combining Indirect Part Detection and Contextual Information

Interleaved Group Convolutions

A Coarse-Fine Network for Keypoint Localization

Human Pose Estimation Using Global and Local Normalization

Learning Feature Pyramids for Human Pose Estimation

Residual Conv-Deconv Grid Network for Semantic Segmentation

Self Adversarial Training for Human Pose Estimation

Joint Multi-person Pose Estimation and Semantic Part Segmentation

Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation

Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation

Multi-Scale Dense Convolutional Networks for Efficient Prediction

Mask R-CNN

Multi-context Attention for Human Pose Estimation

Towards Accurate Multi-person Pose Estimation in the Wild

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Pyramid Scene Parsing Network

RMPE: Regional Multi-person Pose Estimation

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

Deep Convolutional Neural Networks with Merge-and-Run Mappings

PoseTrack: Joint Multi-person Pose Estimation and Tracking

Associative Embedding: End-to-End Learning for Joint Detection and Grouping

Human Pose Estimation via Convolutional Part Heatmap Regression

A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

End-to-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation

Convolutional Neural Fabrics

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Deeply-Fused Nets

Recurrent Human Pose Estimation

DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model

Chained Predictions Using Convolutional Neural Networks

Structured Feature Learning for Pose Estimation

Human Pose Estimation Using Deep Consensus Voting

Stacked Hourglass Networks for Human Pose Estimation

MOT16: A Benchmark for Multi-Object Tracking

Convolutional Pose Machines

Deep Residual Learning for Image Recognition

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

Interlinked Convolutional Neural Networks for Face Parsing

Human Pose Estimation with Iterative Error Feedback

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

Flowing ConvNets for Human Pose Estimation in Videos

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

Holistically-Nested Edge Detection

Adam: A Method for Stochastic Optimization

Locally Scale-Invariant Convolutional Neural Networks

Scale-Invariant Convolutional Neural Networks

Efficient object localization using Convolutional Networks

Deeply-Supervised Nets

Going deeper with convolutions

ImageNet Large Scale Visual Recognition Challenge

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

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

Multi-source Deep Learning for Human Pose Estimation

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