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 adversarial attack can force a CNN-based model to produce an incorrectoutput by craftily manipulating human-imperceptible input. Exploring suchperturbations can help us gain a deeper understanding of the vulnerability ofneural networks, and provide robustness to deep learning against miscellaneousadversaries. Despite extensive studies focusing on the robustness of image,audio, and NLP, works on adversarial examples of visual object tracking --especially in a black-box manner -- are quite lacking. In this paper, wepropose a novel adversarial attack method to generate noises for single objecttracking under black-box settings, where perturbations are merely added oninitial frames of tracking sequences, which is difficult to be noticed from theperspective of a whole video clip. Specifically, we divide our algorithm intothree components and exploit reinforcement learning for localizing importantframe patches precisely while reducing unnecessary computational queriesoverhead. Compared to existing techniques, our method requires fewer queries oninitialized frames of a video to manipulate competitive or even better attackperformance. We test our algorithm in both long-term and short-term datasets,including OTB100, VOT2018, UAV123, and LaSOT. Extensive experiments demonstratethe effectiveness of our method on three mainstream types of trackers:discrimination, Siamese-based, and reinforcement learning-based trackers.

DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking