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

Presentation attacks are recurrent threats to biometric systems, whereimpostors attempt to bypass these systems. Humans often use backgroundinformation as contextual cues for their visual system. Yet, regardingface-based systems, the background is often discarded, since face presentationattack detection (PAD) models are mostly trained with face crops. This workpresents a comparative study of face PAD models (including multi-task learning,adversarial training and dynamic frame selection) in two settings: with andwithout crops. The results show that the performance is consistently betterwhen the background is present in the images. The proposed multi-taskmethodology beats the state-of-the-art results on the ROSE-Youtu dataset by alarge margin with an equal error rate of 0.2%. Furthermore, we analyze themodels' predictions with Grad-CAM++ with the aim to investigate to what extentthe models focus on background elements that are known to be useful for humaninspection. From this analysis we can conclude that the background cues are notrelevant across all the attacks. Thus, showing the capability of the model toleverage the background information only when necessary.

Myope Models -- Are face presentation attack detection models short-sighted?