AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning To Adversarially Blur Visual Object Tracking

Qing Guo, Ziyi Cheng, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Yang Liu, Jianjun Zhao

ICCV 2021 · Detection and segmentation › Tracking · approach: Foundation-model and correlation-filter tracking · 65 citations (OpenAlex)

Read the paperCheck 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
tune accumulation weights A_t in addition to motion W_t (ablation)OS-ABA · OTB100 (SiamRPN++ ResNet50)success rate drop: 5.5 -> 28.1Improved
tune accumulation weights A_t in addition to motion W_t (ablation)OP-ABA · OTB100 (SiamRPN++ ResNet50)success rate drop: 15.0 -> 31.2Improved
tune motion ratios W_t in addition to accumulation A_t (ablation)OP-ABA · OTB100 (SiamRPN++ ResNet50)success rate drop: 25.6 -> 31.2Improved
tune motion ratios W_t in addition to accumulation A_t (ablation)OS-ABA · OTB100 (SiamRPN++ ResNet50)success rate drop: 24.9 -> 28.1Improved
tune motion ratios W_t in addition to accumulation A_t (ablation)OS-ABA · OTB100 (SiamRPN++ ResNet50)precision drop: 29.5 -> 32.5Improved
use adversarial blur instead of normal (Norm-Blur) blurSiamRPN++ ResNet50 · OTB100success rate drop: 1.2 -> 31.2Improved
use iterative optimization (OP-ABA) instead of one-step network (OS-ABA)adversarial blur attack · OTB100 (SiamRPN++ ResNet50)precision drop: 32.5 -> 41.7Improved
use one-step JAMANet (OS-ABA) instead of optimization (OP-ABA) for speedadversarial blur attack · OTB100 (SiamRPN++ ResNet50)attack FPS: 6.79 -> 17.62Improved
use lighter backbone MobileNetv2 instead of ResNet50 as targetOP-ABA · OTB100precision drop: 41.7 -> 49.6Mixed
use OS-ABA instead of OP-ABA for transfer to KYSSiamRPN++ ResNet50 guided attack · OTB100 (transfer)precision drop: 7.9 -> 12.3Improved
use OS-ABA instead of CSA for transfer to DiMP50SiamRPN++ ResNet50 guided attack · OTB100 (transfer)precision drop: 3.4 -> 10.7Improved
use OS-ABA instead of OP-ABA for transfer to SiamRPN++ MobileNetv2SiamRPN++ ResNet50 guided attack · OTB100 (transfer)precision drop: 2.5 -> 0.2Hurt

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