Saved in:
Bibliographic Details
Main Authors: Yu, Dongyang, Xie, Yunshi, An, Wangpeng, Zhang, Li, Yao, Yufeng
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2307.01004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916213037203456
author Yu, Dongyang
Xie, Yunshi
An, Wangpeng
Zhang, Li
Yao, Yufeng
author_facet Yu, Dongyang
Xie, Yunshi
An, Wangpeng
Zhang, Li
Yao, Yufeng
contents We introduce a novel one-stage end-to-end multi-person 2D pose estimation algorithm, known as Joint Coordinate Regression and Association (JCRA), that produces human pose joints and associations without requiring any post-processing. The proposed algorithm is fast, accurate, effective, and simple. The one-stage end-to-end network architecture significantly improves the inference speed of JCRA. Meanwhile, we devised a symmetric network structure for both the encoder and decoder, which ensures high accuracy in identifying keypoints. It follows an architecture that directly outputs part positions via a transformer network, resulting in a significant improvement in performance. Extensive experiments on the MS COCO and CrowdPose benchmarks demonstrate that JCRA outperforms state-of-the-art approaches in both accuracy and efficiency. Moreover, JCRA demonstrates 69.2 mAP and is 78\% faster at inference acceleration than previous state-of-the-art bottom-up algorithms. The code for this algorithm will be publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2307_01004
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approach
Yu, Dongyang
Xie, Yunshi
An, Wangpeng
Zhang, Li
Yao, Yufeng
Computer Vision and Pattern Recognition
Machine Learning
We introduce a novel one-stage end-to-end multi-person 2D pose estimation algorithm, known as Joint Coordinate Regression and Association (JCRA), that produces human pose joints and associations without requiring any post-processing. The proposed algorithm is fast, accurate, effective, and simple. The one-stage end-to-end network architecture significantly improves the inference speed of JCRA. Meanwhile, we devised a symmetric network structure for both the encoder and decoder, which ensures high accuracy in identifying keypoints. It follows an architecture that directly outputs part positions via a transformer network, resulting in a significant improvement in performance. Extensive experiments on the MS COCO and CrowdPose benchmarks demonstrate that JCRA outperforms state-of-the-art approaches in both accuracy and efficiency. Moreover, JCRA demonstrates 69.2 mAP and is 78\% faster at inference acceleration than previous state-of-the-art bottom-up algorithms. The code for this algorithm will be publicly available.
title Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approach
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2307.01004