Dynamically occluded samples via adversarial learning for person re-identification in sensor networks
Sign Up to like & getrecommendations! Published in 2021 at "Ad Hoc Networks"
DOI: 10.1016/j.adhoc.2020.102316
Abstract: Abstract In this paper, we propose a novel data augmentation method to dynamically learn occluded samples via adversarial learning for person re-identification (re-ID) in sensor networks. Specifically, we design two CNN models to learn original-image… read more here.
Keywords: image features; occluded samples; samples via; image ... See more keywords