A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
Recently, multi-resolution networks (such as Hourglass, CPN, HRNet, etc.) have achieved significant performance on the task of human pose estimation by combining features from various resolutions. In this paper, we propose a novel type of attention module, namely De-Normalized Attention (DNA) to deal with the feature attenuations of conventional attention modules. Our method extends the original HRNet with spatial, channel-wise and resolution-wise DNAs, which aims at evaluating the importancearXiv:1909.05090v3 fatcat:lhyfltnsxnfxphs5n3rzbvhic4