AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deep High-Resolution Representation Learning for Visual Recognition

Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Sheng Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, Bin Xiao

TPAMI 2020 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 5,375 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add across-stage fusion units (ablation)HRNetV1-W32 · COCO val poseAP: 70.8 -> 71.9Improved
add within-stage fusion units on top of across-stage (ablation)HRNetV1-W32 · COCO val poseAP: 71.9 -> 73.4Improved
add across-stage fusion units (ablation)HRNetV2-W48 · Cityscapes valmIoU: 74.8 -> 75.4Improved
add within-stage fusion units on top of across-stage (ablation)HRNetV2-W48 · Cityscapes valmIoU: 75.4 -> 76.4Improved
use strided convolution instead of bilinear downsampling in fusion (ablation)HRNet · COCO val poseAP: 72.6 -> 73.4Improved
use strided convolution instead of bilinear downsampling in fusion (ablation)HRNet · Cityscapes valmIoU: 74.2 -> 76.4Improved
use sum instead of multiplication for fusion (ablation)HRNet · COCO val poseAP: 54.7 -> 73.4Improved
use sum instead of multiplication for fusion (ablation)HRNet · Cityscapes valmIoU: 66.0 -> 76.4Improved
start with high-to-low streams added gradually instead of all four at the beginning (ablation)HRNetV1-W32 · COCO val poseAP: 72.5 -> 73.4Improved
start with high-to-low streams added gradually instead of all four at the beginning (ablation)HRNetV2-W48 · Cityscapes valmIoU: 75.7 -> 76.4Improved
use HRNetV2 (aggregate low-resolution streams) instead of HRNetV1 for pose (ablation)HRNet-W32 from scratch · COCO val poseAP: 73.4 -> 73.6No clear effect
add ImageNet pretrainingHRNetV1-W32 · COCO val pose (256x192)AP: 73.4 -> 74.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy