AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deep Pictorial Gaze Estimation

Seonwook Park, Adrian Spurr, Otmar Hilliges

ECCV 2018 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 218 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
add gazemap intermediate supervision loss (ablation)Hourglass + DenseNet (k=32) · MPIIGazemean gaze error (degrees): 4.67 -> 4.56Improved
add gazemap intermediate supervision loss (ablation)Hourglass + DenseNet (k=32) · Columbia Gazemean gaze error (degrees): 3.78 -> 3.59Improved
add gazemap intermediate supervision loss (ablation)Hourglass + DenseNet (k=32) · EYEDIAPmean gaze error (degrees): 11.28 -> 10.63Improved
replace VGG-16 (single eye) with gazemap hourglass + light DenseNetsingle-eye gaze regression · MPIIGazemean gaze error (degrees): 5.4 -> 4.5Improved
replace GazeNet (eye plus head pose) with gazemap architecture using eye onlystate-of-the-art gaze estimator · MPIIGazemean gaze error (degrees): 5.5 -> 4.5Improved
replace VGG-16 with gazemap architecturesingle-eye gaze regression · Columbia Gazemean gaze error (degrees): 3.9 -> 3.8Improved
replace VGG-16 with gazemap architecturesingle-eye gaze regression · EYEDIAPmean gaze error (degrees): 11.2 -> 10.3Improved

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