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

Recent deep learning based face recognition methods have achieved greatperformance, but it still remains challenging to recognize very low-resolutionquery face like 28x28 pixels when CCTV camera is far from the captured subject.Such face with very low-resolution is totally out of detail information of theface identity compared to normal resolution in a gallery and hard to findcorresponding faces therein. To this end, we propose a Resolution InvariantModel (RIM) for addressing such cross-resolution face recognition problems,with three distinct novelties. First, RIM is a novel and unified deeparchitecture, containing a Face Hallucination sub-Net (FHN) and a HeterogeneousRecognition sub-Net (HRN), which are jointly learned end to end. Second, FHN isa well-designed tri-path Generative Adversarial Network (GAN) whichsimultaneously perceives facial structure and geometry prior information, i.e.landmark heatmaps and parsing maps, incorporated with an unsupervisedcross-domain adversarial training strategy to super-resolve very low-resolutionquery image to its 8x larger ones without requiring them to be well aligned.Third, HRN is a generic Convolutional Neural Network (CNN) for heterogeneousface recognition with our proposed residual knowledge distillation strategy forlearning discriminative yet generalized feature representation. Quantitativeand qualitative experiments on several benchmarks demonstrate the superiorityof the proposed model over the state-of-the-arts. Codes and models will bereleased upon acceptance.

Cross-Resolution Face Recognition via Prior-Aided Face Hallucination and Residual Knowledge Distillation