AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Hybrid-Domain Adaptative Representation Learning for Gaze Estimation

Qida Tan, Hongyu Yang, Wenchao Du

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 0 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 UDA loss (LUDA) (ablation)dual-branch baseline · Cross-domain Gaze360->EyeDiapMAE: 12.56 -> 9.49Improved
add UDA loss (LUDA) (ablation)dual-branch baseline · EyeDiap in-domainMAE: 5.54 -> 5.42Improved
add head-pose encoder (EPose) (ablation)dual-branch baseline · Cross-domain Gaze360->MPIIFaceMAE: 11.97 -> 9.69Improved
add sparse-graph fusion (SGF) (ablation)dual-branch baseline · Cross-domain Gaze360->EyeDiapMAE: 12.56 -> 11.08Improved
add SGF to LUDA + EPose (ablation)HARL · Cross-domain Gaze360->MPIIFaceMAE: 8.08 -> 7.49Improved
add UDA loss to EPose + SGF (ablation)HARL · Cross-domain Gaze360->EyeDiapMAE: 8.65 -> 7.63Improved
add EPose to LUDA + SGF (ablation)HARL · EyeDiap in-domainMAE: 5.17 -> 5.02Improved
add per-dimension subgraph in SGF (ablation)HARL · EyeDiap in-domainMAE: 5.55 -> 5.13Improved
use top-1 instead of top-3 edges in subgraph (ablation)HARL · EyeDiap in-domainMAE: 5.22 -> 5.02Improved
use HARL instead of CLIP-Gazecross-domain gaze estimation · Cross-domain Gaze360->MPIIFaceMAE: 6.89 -> 7.49Hurt

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