AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking

Shuai Jia, Yibing Song, Chao Ma, Xiaokang Yang

CVPR 2021 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 78 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use IoU Attack instead of clean inputsSiamRPN++ · VOT2019EAO: 0.287 to 0.124Hurt
Use IoU Attack instead of random noisetrackers · NFS30success: 22.6% decrease; 8.4% decrease with random noiseHurt
Add temporal IoU score (ablation)IoU Attack · VOT2018 and VOT2016EAO: 0.149 -> 0.129; 0.189 -> 0.183 (SiamRPN++); 0.257 -> 0.248; 0.275 -> 0.256 (DiMP); 0.147 -> 0.120; 0.184 -> 0.170 (LTMU)Improved
Transfer previous-frame perturbation to initialize subsequent frames (ablation)IoU Attack · VOT2018 and VOT2016EAO: 0.134 -> 0.129; 0.190 -> 0.183 (SiamRPN++); 0.261 -> 0.248; 0.295 -> 0.256 (DiMP); 0.150 -> 0.120; 0.189 -> 0.170 (LTMU)Improved
Use IoU Attack instead of SPARKSiamRPN++ · OTB100success drop: 6.6 -> 19.6Improved
Use IoU Attack instead of UAP perturbationsSiamRPN++ · OTB100success drop: 2.7 -> 19.6Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy