AI Paper Atlas

Research map / 3D vision / Human pose estimation

Appearance-Based Gaze Estimation With Deep Learning: A Review and Benchmark

Yihua Cheng, Haofei Wang, Yiwei Bao, Feng Lu

TPAMI 2024 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 308 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 CNN backbone to the transformer (Hybrid vs Pure)GazeTR · MPIIFaceGazeangular error: 4.74 -> 4.00Improved
add CNN backbone to the transformer (Hybrid vs Pure)GazeTR · Gaze360angular error: 13.58 -> 10.62Improved
use face-image input with AFF-Net instead of Itracker-style multi-inputItracker · MPIIGazeangular error: 7.25 -> 3.69Improved
Gaze360 vs Dilated-Net on in-the-wild dataDilated-Net · Gaze360angular error: 13.73 -> 11.04Improved
full-face CNN regression vs eye-image Mnist baselineMnist · MPIIGazeangular error: 6.27 -> 4.07Improved
AFF-Net vs Gaze360 on EyeDiap eye imagesGaze360 · EyeDiapangular error: 5.58 -> 6.75Hurt
RT-Gene vs Gaze360 on RT-Gene datasetRT-Gene · RT-Gene datasetangular error: 8.60 -> 7.06Improved

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