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/

Zendy Plus

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

Zendy Tools

Zendy Open

Although gaze estimation methods have been developed with deep learningtechniques, there has been no such approach as aim to attain accurateperformance in low-resolution face images with a pixel width of 50 pixels orless. To solve a limitation under the challenging low-resolution conditions, wepropose a high-frequency attentive super-resolved gaze estimation network,i.e., HAZE-Net. Our network improves the resolution of the input image andenhances the eye features and those boundaries via a proposed super-resolutionmodule based on a high-frequency attention block. In addition, our gazeestimation module utilizes high-frequency components of the eye as well as theglobal appearance map. We also utilize the structural location information offaces to approximate head pose. The experimental results indicate that theproposed method exhibits robust gaze estimation performance even inlow-resolution face images with 28x28 pixels. The source code of this work isavailable at https://github.com/dbseorms16/HAZE_Net/.

HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face Images