首页> 外文会议>International Conference on Transdisciplinary AI >A-HRNet: Attention Based High Resolution Network for Human pose estimation
【24h】

A-HRNet: Attention Based High Resolution Network for Human pose estimation

机译:A-HRNet:基于注意力的高分辨率人体姿势估计网络

获取原文

摘要

Recently, human pose estimation has received much attention in the research community due to its broad range of application scenarios. Most architectures for human pose estimation use multiple resolution networks, such as Hourglass, CPN, HRNet, etc. High Resolution Network (HRNet) is the latest SOTA architecture improved from Hourglass. In this paper, we propose a novel attention block that leverages a special Channel-Attention branch. We use this attention block as the building block and adopt the architecture of HRNet to build our Attention Based HRNet (A-HRNet). Experiments show that our model can consistently outperform HRNet on different datasets. Moreover, our model achieves the state-of-the-art performance on the COCO keypoint detection val2017 dataset (77.7 AP)1.
机译:近年来,人体姿势估计由于其广泛的应用场景而在研究界引起了很多关注。大多数用于人体姿势估计的体系结构都使用多分辨率网络,例如Hourglass,CPN,HRNet等。高分辨率网络(HRNet)是Hourglass改进的最新SOTA体系结构。在本文中,我们提出了一种新颖的注意力块,它利用了特殊的Channel-Attention分支。我们将这个注意力模块用作构建模块,并采用HRNet的体系结构来构建我们的基于注意力的HRNet(A-HRNet)。实验表明,我们的模型在不同的数据集上可以始终胜过HRNet。此外,我们的模型在COCO关键点检测val2017数据集(77.7 AP)上实现了最先进的性能 1

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号