Age , Gender and Race Estimation from Unconstrained Face Images

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Gender Classification by Deep Learning on Millions of Weakly Labelled Images (2016, methodology): “Han [16] used biologically inspired features (BIF) and SVM on all the faces from GROUPS and achieved an accuracy of 87.1%.”
Improving Confidence Estimates for Unfamiliar Examples (2018, methodology): “Gender recognition: The extended Labeled Faces in the Wild (LFW+) dataset [14] with 15,699 faces is used.”
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach (2017, background): “Some of the preliminary work is described in [34], [35].”
What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics (2016, background): “That is why traits such as age, gender and ethnicity are often treated and categorized simultaneously (see [189], [207]–[209]) - an approach that is in line with the perceived correlation of these soft biometric traits.”
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification (2018, background): “5% White (Han and Jain, 2014).”