AI Paper Atlas

Research map / 3D vision / Human pose estimation

Gaze360: Physically Unconstrained Gaze Estimation in the Wild

Petr Kellnhofer, Adria Recasens, Simon Stent, Wojciech Matusik, Antonio Torralba

ICCV 2019 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 508 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 temporal input (LSTM over 7 frames) instead of single frame (ablation)Pinball loss model · Gaze360 test (all 360 deg)mean angular error (deg): 15.6 -> 13.5Improved
use bidirectional LSTM instead of TRN for temporal aggregation (ablation)Pinball loss model · Gaze360 test (all 360 deg)mean angular error (deg): 14.1 -> 13.5Improved
add pinball loss quantile regression instead of MSE (ablation)LSTM model · Gaze360 test (all 360 deg)mean angular error (deg): 14.1 -> 13.5Improved
add pinball loss instead of MSE (ablation)Static model · Gaze360 test (all 360 deg)mean angular error (deg): 15.8 -> 15.6Improved
pinball uncertainty instead of MSE+Drop dropout variance (ablation)LSTM model · Gaze360 test (uncertainty correlation)Spearman uncertainty correlation: 0.31 -> 0.45Improved
pinball uncertainty instead of crop augmentation variance (ablation)LSTM model · Gaze360 test (uncertainty correlation)Spearman uncertainty correlation: 0.37 -> 0.45Improved
pinball uncertainty instead of crop augmentation (ablation)LSTM model · Gaze360 test (front facing)mean angular error (deg): 11.2 -> 11.1Improved
train on Gaze360 instead of ColumbiaStatic model · Cross-dataset test on MPIIFaceGazemean angular error (deg): 12.3 -> 12.1Improved
train on Gaze360 instead of RT-GENEStatic model · Cross-dataset test on Columbiamean angular error (deg): 24.2 -> 9.0Improved
add self-supervised domain adaptation (discriminator and flip-symmetry loss) (ablation)Gaze360 Static · Cross-dataset test on Columbiamean angular error (deg): 9.0 -> 8.1Improved
add self-supervised domain adaptation (ablation)Gaze360 Static · Cross-dataset test on MPIIFaceGazemean angular error (deg): 12.1 -> 9.9Improved
add self-supervised domain adaptation (ablation)Gaze360 Static · Cross-dataset test on RT-GENEmean angular error (deg): 23.4 -> 21.9Improved

Later papers that compared with this method

4 later accepted papers report Gaze360 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