Contextual Face Recognition with a Nested-Hierarchical Nonparametric Identity Model
arXiv: Computer Vision and Pattern Recognition, Volume abs/1811.07753, 2018.
Current face recognition systems typically operate via classification into known identities obtained from supervised identity annotations. There are two problems with this paradigm: (1) current systems are unable to benefit from often abundant unlabelled data; and (2) they equate successful recognition with labelling a given input image. ...More
Full Text (Upload PDF)
PPT (Upload PPT)