AI Paper Atlas

Research map / 3D vision / Human pose estimation

Group Pose: A Simple Baseline for End-to-End Multi-Person Pose Estimation

Huan Liu, Qiang Chen, Zichang Tan, Jiang-Jiang Liu, Jian Wang, Xiangbo Su, Xiaolong Li, Kun Yao, Junyu Han, Errui Ding, Yao Zhao, Jingdong Wang

ICCV 2023 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 61 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 standard self-attention with group self-attentions (within-instance then same-type across-instance) (ablation)GroupPose · MS COCO val2017AP: 69.4 -> 72.0Improved
use group self-attentions instead of standard self-attention with attention mask (ablation)GroupPose · MS COCO val2017AP: 70.7 -> 72.0Improved
add keypoint queries to instance queries (ablation)GroupPose · MS COCO val2017AP: 64.5 -> 72.0Improved
add instance queries for classification (ablation)GroupPose · MS COCO val2017AP: 71.2 -> 72.0Improved
add within-instance self-attention (ablation)GroupPose · MS COCO val2017AP: 67.4 -> 72.0Improved
add same-type across-instance self-attention (ablation)GroupPose · MS COCO val2017AP: 66.3 -> 72.0Improved
use separate parameters for the two group self-attentions (ablation)GroupPose · MS COCO val2017AP: 71.5 -> 72.0Improved
increase number of instances from 100 to 200 (ablation)GroupPose · MS COCO val2017AP: 72.0 -> 72.0No clear effect
increase number of instances from 50 to 100 (ablation)GroupPose · MS COCO val2017AP: 71.4 -> 72.0Improved
add human detection decoder layers to GroupPose (ablation)GroupPose · MS COCO val2017AP: 72.0 -> 72.2Improved
GroupPose with simple decoder, no box supervision, vs ED-Pose with box supervisionED-Pose · MS COCO val2017 (ResNet-50)AP: 71.6 -> 72.0Improved
GroupPose vs Poseur top-down on COCO val2017 ResNet-50Poseur · MS COCO val2017AP: 74.2 -> 72.0Hurt

Later papers that compared with this method

4 later accepted papers report GroupPose as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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