Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation (2019-11-24T00:00:00.000000Z)

TL;DR

A well-known bottom-up approach for multi-person pose estimation is rethink and an improved one is proposed which outperforms the baseline by about 15% in average precision and is comparable to the state of the art on the MS-COCO test-dev dataset.

Abstract

We rethink a well-known bottom-up approach for multi-person pose estimation and propose an improved one. The improved approach surpasses the baseline significantly thanks to (1) an intuitional yet more sensible representation, which we refer to as body parts to encode the connection information between keypoints, (2) an improved stacked hourglass network with attention mechanisms, (3) a novel focal L2 loss which is dedicated to “hard” keypoint and keypoint association (body part) mining, and (4) a robust greedy keypoint assignment algorithm for grouping the detected keypoints into individual poses. Our approach not only works straightforwardly but also outperforms the baseline by about 15% in average precision and is comparable to the state of the art on the MS-COCO test-dev dataset. The code and pre-trained models are publicly available on our project page1.

Authors

Jia Li

1 papers

Wen Su

1 papers

Zengfu Wang

1 papers

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

TL;DR

Abstract

Authors

References29 items

PifPaf: Composite Fields for Human Pose Estimation

Deep High-Resolution Representation Learning for Human Pose Estimation

Rethinking on Multi-Stage Networks for Human Pose Estimation

CornerNet: Detecting Objects as Paired Keypoints

Magnify-Net for Multi-Person 2D Pose Estimation

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

Integral Human Pose Regression

Cascaded Pyramid Network for Multi-person Pose Estimation

Squeeze-and-Excitation Networks

Focal Loss for Dense Object Detection

Multi-context Attention for Human Pose Estimation

Towards Accurate Multi-person Pose Estimation in the Wild

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

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

Multi-person Pose Estimation with Local Joint-to-Person Associations

Densely Connected Convolutional Networks

Stacked Hourglass Networks for Human Pose Estimation

Convolutional Pose Machines

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

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

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

Microsoft COCO: Common Objects in Context

DeepPose: Human Pose Estimation via Deep Neural Networks

Pictorial structures revisited: People detection and articulated pose estimation

The Representation and Matching of Pictorial Structures

Field of Study

Venue Information

Name

Type

URL

Alternate Names