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

The large domain discrepancy between faces captured in polarimetric (orconventional) thermal and visible domain makes cross-domain face recognitionquite a challenging problem for both human-examiners and computer visionalgorithms. Previous approaches utilize a two-step procedure (visible featureestimation and visible image reconstruction) to synthesize the visible imagegiven the corresponding polarimetric thermal image. However, these are regardedas two disjoint steps and hence may hinder the performance of visible facereconstruction. We argue that joint optimization would be a better way toreconstruct more photo-realistic images for both computer vision algorithms andhuman-examiners to examine. To this end, this paper proposes a GenerativeAdversarial Network-based Visible Face Synthesis (GAN-VFS) method to synthesizemore photo-realistic visible face images from their corresponding polarimetricimages. To ensure that the encoded visible-features contain more semanticallymeaningful information in reconstructing the visible face image, a guidancesub-network is involved into the training procedure. To achieve photo realisticproperty while preserving discriminative characteristics for the reconstructedoutputs, an identity loss combined with the perceptual loss are optimized inthe framework. Multiple experiments evaluated on different experimentalprotocols demonstrate that the proposed method achieves state-of-the-artperformance.

Generative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faces