AI Paper Atlas

Research map / 3D vision / Human pose estimation

Cross-Encoder for Unsupervised Gaze Representation Learning

Yunjia Sun, Jiabei Zeng, Shiguang Shan, Xilin Chen

ICCV 2021 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 39 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 gaze-similar pair training in addition to eye-consistent pairs (ablation)Cross-Encoder · UTMultiview 100-shot, w/ head poseangular error (deg): 10.6 -> 8.0Improved
add gaze-similar pair training in addition to eye-consistent pairs (ablation)Cross-Encoder · Columbia 100-shot, w/ head poseangular error (deg): 7.6 -> 6.6Improved
add residual loss (ablation)Cross-Encoder · Columbia 100-shot, w/ head poseangular error (deg): 6.7 -> 6.6Improved
add residual loss (ablation)Cross-Encoder · UTMultiview 100-shot, w/ head poseangular error (deg): 7.4 -> 8.0Hurt
add residual loss (ablation)Cross-Encoder · MPIIGaze 100-shot, w/ head poseangular error (deg): 7.2 -> 7.5Hurt
use gaze feature instead of eye feature (ablation)Cross-Encoder · UTMultiview 100-shot, w/ head poseangular error (deg): 15.5 -> 8.0Improved
swap features (Cross-Encoder) instead of equal feature constraint (ablation)auto-encoder · Columbia 100-shot, w/ head poseangular error (deg): 9.2 -> 6.6Improved
swap features (Cross-Encoder) instead of plain auto-encoder (ablation)auto-encoder · UTMultiview 100-shot, w/ head poseangular error (deg): 18.0 -> 8.0Improved
vary gaze feature dimension dg from 9 to 15 (ablation)Cross-Encoder · Columbia 100-shot, w/ head poseangular error (deg): 6.7 -> 6.4No clear effect
increase eye feature dimension from 16 to 64 (ablation)Cross-Encoder · Columbia 100-shot, w/ head poseangular error (deg): 6.7 -> 6.5No clear effect
add more unlabeled data (XGaze, TabletGaze, FreeGaze union) instead of XGaze alone (ablation)Cross-Encoder cross-dataset · Columbia 100-shot cross-datasetangular error (deg): 7.76 -> 7.09Improved
use Cross-Encoder instead of SimCLR/BYOL (ablation)gaze representation · UTMultiview 50-shotangular error (deg): 14.4 -> 8.8Improved

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