AI Paper Atlas

Research map / 3D vision / Human pose estimation

SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation

Yanjie Li, Sen Yang, Peidong Liu, Shoukui Zhang, Yunxiao Wang, Zhicheng Wang, Wankou Yang, Shu-Tao Xia

ECCV 2022 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 291 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
replace 2D heatmap with SimCC coordinate classificationHRNet-W48 · COCO val2017 (64x64)AP: 48.5 -> 59.7Improved
replace 2D heatmap with SimCC coordinate classificationHRNet-W48 · COCO val2017 (256x192)AP: 75.1 -> 75.9Improved
replace DARK post-processing with SimCCTokenPose-S · COCO val2017 (64x64)AP: 57.1 -> 62.8Improved
add refinement post-processing (DARK) to heatmap (ablation)TokenPose-S · COCO val2017 (64x64)AP: 35.9 -> 57.1Improved
remove deconvolution upsampling layers via SimCCSimpleBaseline-R50 · COCO val2017 (256x192)AP: 70.4 -> 70.8Improved
add deconvolution upsampling modules to SimCC (ablation)SimpleBaseline-R50 · COCO val2017 (256x192)AP: 70.8 -> 71.4Improved
add deconvolution upsampling modules to SimCC (ablation)SimpleBaseline-R50 · COCO val2017 (128x128)AP: 62.6 -> 62.6No clear effect
add deconvolution upsampling modules to SimCC (ablation)SimpleBaseline-R50 · COCO val2017 (64x64)AP: 39.3 -> 40.8Improved
add equal label smoothing (ablation)SimCC SimBa-R50 · COCO val2017 (384x288)AP: 71.3 -> 73.0Improved
use Gaussian instead of equal label smoothing (ablation)SimCC SimBa-R50 · COCO val2017 (384x288)AP: 73.0 -> 73.4Improved
use Laplace instead of equal label smoothing (ablation)SimCC SimBa-R50 · COCO val2017 (384x288)AP: 73.0 -> 73.0No clear effect
replace 2D heatmap with 1D heatmap regressionSimpleBaseline-R50 · COCO val2017 (256x256)AP: 68.8 -> 68.5Hurt

Later papers that compared with this method

2 later accepted papers report SimCC as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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