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

Very low-resolution face recognition (VLRFR) poses unique challenges, such astiny regions of interest and poor resolution due to extreme standoff distanceor wide viewing angle of the acquisition devices. In this paper, we studyprincipled approaches to elevate the recognizability of a face in the embeddingspace instead of the visual quality. We first formulate a robust learning-basedface recognizability measure, namely recognizability index (RI), based on twocriteria: (i) proximity of each face embedding against the unrecognizable facescluster center and (ii) closeness of each face embedding against its positiveand negative class prototypes. We then devise an index diversion loss to pushthe hard-to-recognize face embedding with low RI away from unrecognizable facescluster to boost the RI, which reflects better recognizability. Additionally, aperceptibility attention mechanism is introduced to attend to the mostrecognizable face regions, which offers better explanatory and discriminativetraits for embedding learning. Our proposed model is trained end-to-end andsimultaneously serves recognizability-aware embedding learning and face qualityestimation. To address VLRFR, our extensive evaluations on three challenginglow-resolution datasets and face quality assessment demonstrate the superiorityof the proposed model over the state-of-the-art methods.

Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation