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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Unconstrained remote gaze tracking using off-the-shelf cameras is achallenging problem. Recently, promising algorithms for appearance-based gazeestimation using convolutional neural networks (CNN) have been proposed.Improving their robustness to various confounding factors including variablehead pose, subject identity, illumination and image quality remain openproblems. In this work, we study the effect of variable head pose on machinelearning regressors trained to estimate gaze direction. We propose a novelbranched CNN architecture that improves the robustness of gaze classifiers tovariable head pose, without increasing computational cost. We also presentvarious procedures to effectively train our gaze network including transferlearning from the more closely related task of object viewpoint estimation andfrom a large high-fidelity synthetic gaze dataset, which enable our ten timesfaster gaze network to achieve competitive accuracy to its currentstate-of-the-art direct competitor.

Light-weight Head Pose Invariant Gaze Tracking