AI Paper Atlas

Research map / 3D vision / Human pose estimation

OpenMonkeyChallenge: Dataset and Benchmark Challenges for Pose Estimation of Non-human Primates

Yuan Yao, Praneet Bala, Abhiraj Mohan, Eliza Bliss‐Moreau, Kristine Coleman, Sienna M. Freeman, Christopher J. Machado, Jessica Raper, Jan Zimmermann, Benjamin Y. Hayden, Hyun Soo Park

IJCV 2022 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 45 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
train on OpenMonkeyChallenge instead of retraining nothing (COCO human model)CPM · OpenMonkeyChallenge testMPJPE: 0.197 -> 0.074Improved
train on OpenMonkeyChallenge instead of COCO human modelCPM · OpenMonkeyChallenge testPCK@0.2: 0.265 -> 0.761Improved
primate model vs human model on its own domain (gap)CPM · PCK@0.2PCK@0.2: 0.849 -> 0.761Hurt
increase training data from 20% to 100% (ablation)CPM · OpenMonkeyChallenge testPCK@0.2: 15% gain at PCK@0.2Improved
train on OpenMonkeyChallenge instead of MacaquePose/OpenMonkeyPoseCPM · cross-dataset (OMC, MacaquePose, OpenMonkeyPose tests)MPJPEImproved
train on OpenMonkeyPose (lab data) instead of OpenMonkeyChallengeCPM · OpenMonkeyChallenge and MacaquePose testsMPJPEHurt
use top-down model instead of bottom-upHRNet-W48 vs HigherHRNet-W48 · OpenMonkeyChallenge testmean MPJPE: 0.092 -> 0.064Improved
increase backbone width from W32 to W48 (ablation)HRNet · OpenMonkeyChallenge testAP: 70.7 -> 76.5Improved
increase backbone width from W32 to W48 (ablation)HigherHRNet · OpenMonkeyChallenge testAP: 59.1 -> 65.3Improved
increase depth from ResNet101 to ResNet152 (ablation)SimpleBaseline · OpenMonkeyChallenge testmean PCK@0.2: 0.863 -> 0.901Improved
choice among top CNN architecturespose estimators · OpenMonkeyChallenge testmean PCK@0.2: 0.890 to 0.903No clear effect

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