A forest of two-node graphs over corresponding parent-child face components, combined with a gradually introduced center loss, reports state-of-the-art accuracy on KinFaceW-II.
IEEE Transactions on Pattern Analysis and Machine Intelligence 44(8), 4432–4453 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Kinship Verification through a Forest Neural Network
A forest of two-node graphs over corresponding parent-child face components, combined with a gradually introduced center loss, reports state-of-the-art accuracy on KinFaceW-II.