2 papers
cs.CV2021
Adversarial Imaging Pipelines
Buu Phan, Fahim Mannan, Felix Heide
Adversarial attacks play an essential role in understanding deep neural network predictions and improving their robustness. Existing attack methods aim to deceive convolutional neu…
cs.CV2019
Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar
Nicolas Scheiner, Florian Kraus, Fangyin Wei +8
Conventional sensor systems record information about directly visible objects, whereas occluded scene components are considered lost in the measurement process. Non-line-of-sight (…