IEEE

Quad-Rotor Helicopter Visual Attack Based on Attention Mechanism Grad-CAM++ and Mask-PGD

Abstract: In order to explore security vulnerabilities in unmanned aerial vehicle (UAV) target tracking processes, a quad-rotor helicopter visual adversarial sample attack method based on Grad-CAM++ ...

Elephants know when you're watching—how they recognize human visual attention

With their massive flapping ears and long trunks, it isn't hard to believe that elephants tend to rely on acoustic and ...
IEEE

Enhancing Medical Visual Question Answering with a Multimodal Feature Fusion Network Based on Densely Connected Attention Streams

Abstract: Medical Visual Question Answering (MVQA) is a specialized task developed from Visual Question Answering (VQA) and is specifically tailored to the medical domain. The goal of MVQA is to ...