SEXNET: A Neural Network Identifies Sex From Human Faces

By Beatrice A. Golomb, D. T. Lawrence, Terrence J. Sejnowski. 1990

How researchers see this paper

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

Citations in the corpus

Defeating Image Obfuscation with Deep Learning (2016, background): “For example, Golomb et al. [11] used neural networks to identify the sex of human faces.”
A Study on Gait-Based Gender Classification (2009, background): “The SexNet proposed in [1] is pioneering work in gender recognition; it is a back-propagation neural network trained for face-based gender classification.”
Learning Gender with Support Faces (2002, unknown): “Ë Îûð ñZ óvÉSÎ ç Í Ê0Ç Ê(ÝhÉ /Ë ÝAÍ>Ý6 0Ó)Ëxä Ç ÓxË Æ"Ñ!”
Automated Facial Trait Judgment and Election Outcome Prediction: Social Dimensions of Face (2015, background): “The human face is a highly salient medium of human communication, carrying surprisingly rich information about the subject, including gender [12], ethnicity [14], age Figure 1.”
Human Attribute Recognition by Rich Appearance Dictionary (2013, methodology): “Earlier works used the facial images for classification of gender [9], age group [13], ethnicity [10], and so on, since the face is the most informative part for these attributes.”
Deep convolutional neural networks-based age and gender classification with facial images (2017, background): “Golomb [1] trained a 2-layer fully connected network.”
A Fast and Accurate Face Detector Based on Neural Networks (2001, methodology): “This model can be built with different methods: neural networks [6], [38], [12], [33], [20], [36], [29], [30], [13], [14], principal components analysis [35], [11], [15], [ 17 ], [18], [26], Kullback distance and maximum-likelihood method [10], Support Vector Machines [27], [28], etc.”
Visual Persuasion: Inferring Communicative Intents of Images (2014, background): “Our paper is related to studies in computer vision on human attribute recognition [8, 22, 16, 13], such as gender, race, or facial expression recognition.”
Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose (2016, background): “Early work focused on facial images since face is the most informative and distinct part of the body, and is the most suitable for estimating attributes such as gender [22], [23], [24], age [25], and some local attributes (e.”
Minimalistic CNN-based ensemble model for gender prediction from face images (2016, background): “For example, Golomb et al. (1990) trained a 2-layers fully-connected neural network and achieved 91.90% accuracy on a tiny test set of 90 images.”
Neural Network Approaches to Image Compression (1995, methodology): “[47] have used the above architecture to successfully compress and restore images of faces.”
Attribute and simile classifiers for face verification (2009, methodology): “Automatically determining the gender of a face has been an active area of research since at least 1990 [15, 9], and includes more recent work [24] using Support Vector Machines (SVMs) [8].”
Gender classification with support vector machines (2000, unknown): “[12] trained a fully connected two-layer neural network, SEXNET, to identify gender from 30-by30 face images.”
Describing people: A poselet-based approach to attribute classification (2011, background): “Gender recognition methods using neural networks date back to the early 1990s [8, 16].”
FaceTracer: A Search Engine for Large Collections of Images with Faces (2008, background): “Early works such as [3]used neural networks to perform gender classification on small datasets.”
The Misgendering Machines (2018, background): “A regular feature of facial recognition literature since 1990 [34], AGR research has many suggested applications.”