English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Conventional feature-based and model-based gaze estimation methods haveproven to perform well in settings with controlled illumination and specializedcameras. In unconstrained real-world settings, however, such methods aresurpassed by recent appearance-based methods due to difficulties in modelingfactors such as illumination changes and other visual artifacts. We present anovel learning-based method for eye region landmark localization that enablesconventional methods to be competitive to latest appearance-based methods.Despite having been trained exclusively on synthetic data, our method exceedsthe state of the art for iris localization and eye shape registration onreal-world imagery. We then use the detected landmarks as input to iterativemodel-fitting and lightweight learning-based gaze estimation methods. Ourapproach outperforms existing model-fitting and appearance-based methods in thecontext of person-independent and personalized gaze estimation.

Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings