AI Paper Atlas

Research map / 3D vision / Human pose estimation

Few-Shot Adaptive Gaze Estimation

Seonwook Park, Shalini De Mello, Pavlo Molchanov, Umar Iqbal, Otmar Hilliges, Jan Kautz

ICCV 2019 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 245 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 MAML instead of naive fine-tuning for the person-specific gaze estimator (ablation)AE features gaze estimator · MPIIGaze (train on GazeCapture)gaze error (degrees): 7.17 -> 6.61 (k=1)Improved
replace autoencoder with rotation-aware disentangling DT-ED (ablation)MAML gaze estimator · MPIIGaze (k=9)gaze error (degrees): 5.62 -> 4.87Improved
add gaze supervision loss to reconstruction loss (ablation)DT-ED · MPIIGaze (k=9)gaze error (degrees): 4.87 -> 3.60Improved
add person-specific embedding consistency loss to reconstruction loss (ablation)DT-ED · MPIIGaze (k=9)gaze error (degrees): 4.87 -> 3.32Improved
combine reconstruction, gaze and embedding consistency losses (ablation)DT-ED · MPIIGaze (k=9)gaze error (degrees): 4.87 -> 3.14Improved
use person-independent embedding consistency (also minimize inter-person differences) instead of person-specific (ablation)DT-ED · MPIIGazegaze error (degrees)Hurt
add triplet loss maximizing inter-person feature differences (ablation)DT-ED embedding consistency · MPIIGazegaze error (degrees)Hurt
use FAZE (DT-ED + MAML) instead of DenseNet/VGG-16 CNN trained on gaze objective + MAMLMAML gaze estimator · MPIIGazegaze error (degrees)Improved
use FAZE instead of Liu et al. differential gaze re-implementationgaze personalization · MPIIGaze (k=9)gaze error (degrees): 3.53 -> 3.14Improved
use FAZE instead of polynomial fit to PoRgaze personalization · MPIIGaze (k=9)gaze error (degrees): 4.19 -> 3.14Improved
use FAZE in within-MPIIGaze leave-one-person-out vs Liu et al.gaze personalization · MPIIGaze (within-dataset, k=9)gaze error (degrees): 4.67 -> 3.88Improved
set latent gaze code dimension F_g=2 rather than 16 or 3 (ablation)FAZE · GazeCapture test and MPIIGazegaze error (degrees)Improved

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