The AMGA attack, built from an ensemble of image classifiers trained with momentum, Gaussian smoothing, and a meta-learning-style update, substantially reduces the accuracy of seven visual trackers on three benchmarks in black-box settings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Adaptive Meta-Gradient Adversarial Examples for Visual Tracking
The AMGA attack, built from an ensemble of image classifiers trained with momentum, Gaussian smoothing, and a meta-learning-style update, substantially reduces the accuracy of seven visual trackers on three benchmarks in black-box settings.