AI Paper Atlas

Research map / 3D vision / Human pose estimation

Rethinking Pose Estimation in Crowds: Overcoming the Detection Information Bottleneck and Ambiguity

Mu Zhou, Lucas Stoffl, Mackenzie Weygandt Mathis, Alexander Mathis

ICCV 2023 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 36 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
use bottom-up detections plus pose proposals instead of an object detector with plain top-downBUCTD · CrowdPose testAP: 70.0 -> 78.5Improved
add CTD conditional top-down refinement to HigherHRNet-W32 detectionsHigherHRNet-W32 · CrowdPose testAP: 65.7 -> 71.4Improved
use CoAM conditioning instead of preNet (ablation)CTD · CrowdPose testAP: 69.5 -> 71.4Improved
inject conditions earlier in the network (stage 1 vs stage 4) (ablation)BUCTD-CoAM-W32 · CrowdPose testAP: 68.3 -> 71.2Improved
train with conditions from 15 checkpoints rather than one (ablation)CTD-CoAM-W32 · CrowdPose testAP: 68.8 -> 71.4Improved
use generative sampling for training conditions (ablation)CTD-CoAM-W32 · CrowdPose testAP: 71.4 -> 72.3Improved
use generative sampling on fish data (ablation)BUCTD · SchoolingFishAP: 88.7 -> 81.9Hurt
use bottom-up detections instead of object-detector boxes (ablation)CTD · Marmosets hard framesAP_H: 52.4 -> 89.4Improved
iteratively refine by feeding predictions back as conditions (3x) (ablation)BUCTD · OCHuman testAP: 47.4 -> 48.5Improved
apply BUCTD refinement on COCO with few overlapping peoplePETR · COCO valAP: 73.1 -> 77.8Improved

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