Neighbor similarity and soft-label adaptation for unsupervised cross-dataset person re-identification
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2019.12.115
Abstract: Abstract Most of the existing person re-identification algorithms rely on supervised model learning from a large number of labeled training data per-camera-pair. However, the manual annotations often require expensive human labor, which limits the application… read more here.
Keywords: neighbor similarity; soft label; identification; domain ... See more keywords