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

With the wide application of face recognition systems, there is risingconcern that original face images could be exposed to malicious intents andconsequently cause personal privacy breaches. This paper presents DuetFace, anovel privacy-preserving face recognition method that employs collaborativeinference in the frequency domain. Starting from a counterintuitive discoverythat face recognition can achieve surprisingly good performance with onlyvisually indistinguishable high-frequency channels, this method designs acredible split of frequency channels by their cruciality for visualization andoperates the server-side model on non-crucial channels. However, the modeldegrades in its attention to facial features due to the missing visualinformation. To compensate, the method introduces a plug-in interactive blockto allow attention transfer from the client-side by producing a feature mask.The mask is further refined by deriving and overlaying a facial region ofinterest (ROI). Extensive experiments on multiple datasets validate theeffectiveness of the proposed method in protecting face images from undesiredvisual inspection, reconstruction, and identification while maintaining hightask availability and performance. Results show that the proposed methodachieves a comparable recognition accuracy and computation cost to theunprotected ArcFace and outperforms the state-of-the-art privacy-preservingmethods. The source code is available athttps://github.com/Tencent/TFace/tree/master/recognition/tasks/duetface.

DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain