Abstract: Very limited training samples pose significant challenges for hyperspectral image (HSI) classification. To address this issue, small-sample learning methods based on classical machine ...
Abstract: Autonomous driving systems critically depend on accurately classifying traffic signs, a task that is jeopardized by adversarial attacks. This paper focuses on the relatively unexplored ...
MotionEdit is a novel dataset and benchmark for motion-centric image editing. We also propose MotionNFT (Motion-guided Negative-aware FineTuning), a post-training framework with motion alignment ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback