Face Space Representations in Deep Convolutional Neural Networks

doi:10.1016/j.tics.2018.06.006

Paper

DOI: 10.1016/j.tics.2018.06.006

Face Space Representations in Deep Convolutional Neural Networks

Published Sep 1, 2018 · A. O’toole, C. Castillo, Connor J. Parde

Trends in Cognitive Sciences

Q1 SJR score

106

Citations

Influential Citations

Full text Semantic Scholar

Abstract

Abstract removed due to Elsevier request; this does not indicate any issues with the research. Click the full text link above to read the abstract and view the original source.

Highly Cited

Study Snapshot

Key takeawayDeep convolutional neural networks (DCNNs) provide a new class of visual representation for faces, allowing for generalized face recognition across variations in viewpoint, illumination, expression, and appearance.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Full text analysis coming soon...

References

DOI: 10.1073/pnas.1721355115

Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms

Collaboration among humans and machines, particularly forensic facial examiners and superrecognizers, can significantly improve face identification accuracy in forensic applications.

2018·286citations·P. Phillips et al.·Proceedings of the National Academy of Sciences of the United States of America

Proceedings of the National Academy of Sciences of the United States of America

DOI: 10.1016/j.tics.2017.11.007

Are We Face Experts?

We are, in effect, familiar face experts, as we show limited expertise with unfamiliar faces for identity recognition.

2018·169citations·A. Young et al.·Trends in Cognitive Sciences

Trends in Cognitive Sciences

DOI: 10.1016/j.neuroimage.2016.10.001

Seeing it all: Convolutional network layers map the function of the human visual system

Convolutional networks can accurately model human brain activity during image viewing, capturing universal representations of brain function across various experimental paradigms.

2017·307citations·Michael Eickenberg et al.·NeuroImage

NeuroImage

DOI: 10.1109/FG.2017.137

An All-In-One Convolutional Neural Network for Face Analysis

Our single deep convolutional neural network (CNN) effectively performs simultaneous face detection, alignment, pose estimation, genderrecognition, smile detection, age estimation, and face recognition tasks, achieving state-of-the-art results for most of these tasks.

2016·417citations·Rajeev Ranjan et al.·2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)

2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)

DOI: 10.1038/nn.4247

Explicit information for category-orthogonal object properties increases along the ventral stream

The inferior temporal visual area encodes all category-orthogonal object properties more explicitly and better predicts human performance patterns than earlier ventral stream areas.

2016·283citations·Ha Hong et al.·Nature Neuroscience

Nature Neuroscience

Citations

DOI: 10.48550/arXiv.2407.19072

Configural processing as an optimized strategy for robust object recognition in neural networks

Configural processing in neural networks provides more robust object recognition compared to local featural cues, especially when both features are available.

2024·0citations·Hojin Jang et al.·ArXiv

ArXiv

DOI: 10.3390/s24134347

A Multi-Scale-Enhanced YOLO-V5 Model for Detecting Small Objects in Remote Sensing Image Information

The I-YOLO-V5 model improves object detection in remote sensing images by 15.4% and reduces miss rates by 46.8% compared to existing advanced algorithms.

2024·0citations·Jing Li et al.·Sensors (Basel, Switzerland)

Sensors (Basel, Switzerland)

DOI: 10.48550/arXiv.2405.18302

Deep Network Pruning: A Comparative Study on CNNs in Face Recognition

Deep network pruning based on Taylor scores can reduce the size of deep Convolutional Neural Networks for face recognition, with minimal performance loss.

2024·1citation·F. Alonso-Fernandez et al.·ArXiv

ArXiv

DOI: 10.48550/arXiv.2402.15662

GiMeFive: Towards Interpretable Facial Emotion Classification

Our model, GiMeFive, outperforms previous methods in facial emotion recognition accuracy and provides explanations for layer activations and gradient-weighted class activation mapping.

2024·0citations·Jiawen Wang et al.·ArXiv

ArXiv

DOI: 10.3390/sym16020176

Assessing the Role of Facial Symmetry and Asymmetry between Partners in Predicting Relationship Duration: A Pilot Deep Learning Analysis of Celebrity Couples

Facial dissimilarity between partners does not significantly correlate with partnership duration in celebrity couples, suggesting other factors play a more critical role in relationship dynamics.

2024·1citation·V. Shavlokhova et al.·Symmetry

Symmetry