AI Paper Atlas

Research map / 3D vision / Human pose estimation

Poseur: Direct Human Pose Regression with Transformers

Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang, Anton van den Hengel

ECCV 2022 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 147 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
initialize keypoint queries from coarse proposal instead of Deformable DETR reference points (ablation)Poseur · COCO valAP: 72.3 -> 72.9Improved
add noisy reference point sampling during training (ablation)Poseur · COCO valAP: 73.7 -> 74.3Improved
use proposed uncertainty score instead of RLE score (ablation)Poseur · COCO valAP: 73.6 -> 74.7Improved
add proposed uncertainty estimation re-scoring (ablation)Poseur · COCO valAP: +4.7 APImproved
feed more backbone feature levels (1 to 4) (ablation)Poseur · COCO valAP: 73.7 -> 74.7Improved
increase decoder layers from 3 to 4 (ablation)Poseur · COCO valAP: 74.7 -> 75.3Improved
increase decoder layers from 4 to 6 (ablation)Poseur · COCO valAP: 75.3 -> 75.4No clear effect
replace SimpleBaseline heatmap with Poseur at 64x64 inputResNet-50 · COCO valAP: 31.4 -> 47.9Improved
replace SimpleBaseline heatmap with Poseur on MobileNet-V2MobileNet-V2 · COCO valAP: 65.9 -> 71.9Improved
replace heatmap keypoint head in Mask R-CNN with PoseurMask R-CNN ResNet-101 · COCO valAP: 66.0 -> 68.6Improved
replace SimpleBaseline with Poseur on ResNet-50ResNet-50 · COCO valAP: 72.4 -> 75.4Improved

Later papers that compared with this method

6 later accepted papers report Poseur as a baseline in their results tables; 4 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