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

Action recognition has been heavily employed in many applications such asautonomous vehicles, surveillance, etc, where its robustness is a primaryconcern. In this paper, we examine the robustness of state-of-the-art actionrecognizers against adversarial attack, which has been rarely investigated sofar. To this end, we propose a new method to attack action recognizers thatrely on 3D skeletal motion. Our method involves an innovative perceptual lossthat ensures the imperceptibility of the attack. Empirical studies demonstratethat our method is effective in both white-box and black-box scenarios. Itsgeneralizability is evidenced on a variety of action recognizers and datasets.Its versatility is shown in different attacking strategies. Its deceitfulnessis proven in extensive perceptual studies. Our method shows that adversarialattack on 3D skeletal motions, one type of time-series data, is significantlydifferent from traditional adversarial attack problems. Its success raisesserious concern on the robustness of action recognizers and provides insightson potential improvements.

Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack