Learning Delicate Local Representations for Multi-Person Pose Estimation

by   Yuanhao Cai, et al.
Tsinghua University

In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatialsize (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in pre-cise keypoint localization. In addition, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to further refine the keypointlocations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN


page 2

page 10

page 13


Towards Accurate Multi-person Pose Estimation in the Wild

We propose a method for multi-person detection and 2-D pose estimation t...

Cascaded Pyramid Network for Multi-Person Pose Estimation

The topic of multi-person pose estimation has been largely improved rece...

Human Keypoint Detection by Progressive Context Refinement

Human keypoint detection from a single image is very challenging due to ...

Bi-directional Graph Structure Information Model for Multi-Person Pose Estimation

In this paper, we propose a novel multi-stage network architecture with ...

Modeling Multi-Destination Trips with Sketch-Based Model

The recently proposed EMDE (Efficient Manifold Density Estimator) model ...

Towards High Performance Human Keypoint Detection

Human keypoint detection from a single image is very challenging due to ...

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement

Finding local features that are repeatable across multiple views is a co...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset