# Real-time Convolutional Neural Networks for Emotion and Gender Classification

arXiv: https://arxiv.org/abs/1710.07557 · HTML: https://mlsanity.com/paper/1710.07557/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2017.

## Built on by (most cited first, 24 of 24)

- [I Find Your Lack of Uncertainty in Computer Vision Disturbing](https://mlsanity.com/paper/2104.08188/) (2021)
- [Self-supervised Learning for Sonar Image Classification](https://mlsanity.com/paper/2204.09323/) (2022)
- [Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration](https://mlsanity.com/paper/2507.10293/) (2025)
- [The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts](https://mlsanity.com/paper/2505.17476/) (2025)
- [Pre-trained Models for Sonar Images](https://mlsanity.com/paper/2108.01111/) (2021)
- [Universal computational thermal imaging overcoming the ghosting effect](https://mlsanity.com/paper/2604.01542/) (2026)
- [Is Gender "In-the-Wild" Inference Really a Solved Problem?](https://mlsanity.com/paper/2105.05794/) (2021)
- [MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition](https://mlsanity.com/paper/2404.18327/) (2024)
- [A Multi-Task Deep Learning Framework for Real-Time Intelligent Video Surveillance with Temporal Event Validation](https://mlsanity.com/paper/2607.03131/) (2026)
- [Practical Digital Disguises: Leveraging Face Swaps to Protect Patient Privacy](https://mlsanity.com/paper/2204.03559/) (2022)
- [E-ffective: A Visual Analytic System for Exploring the Emotion and Effectiveness of Inspirational Speeches](https://mlsanity.com/paper/2110.14908/) (2021)
- [Lie-Sensor: A Live Emotion Verifier or a Licensor for Chat Applications using Emotional Intelligence](https://mlsanity.com/paper/2102.11318/) (2021)
- [Real-time Emotion and Gender Classification using Ensemble CNN](https://mlsanity.com/paper/2111.07746/) (2021)
- [ArcFace Knows the Gender, Too!](https://mlsanity.com/paper/2112.10101/) (2021)
- [Teaching Drones on the Fly: Can Emotional Feedback Serve as Learning Signal for Training Artificial Agents?](https://mlsanity.com/paper/2202.09634/) (2022)
- [Interpretability by design using computer vision for behavioral sensing in child and adolescent psychiatry](https://mlsanity.com/paper/2207.04724/) (2022)
- [On Developing Facial Stress Analysis and Expression Recognition Platform](https://mlsanity.com/paper/2209.07916/) (2022)
- [The Face of Populism: Examining Differences in Facial Emotional Expressions of Political Leaders Using Machine Learning](https://mlsanity.com/paper/2304.09914/) (2023)
- [Facial Emotion Recognition using CNN in PyTorch](https://mlsanity.com/paper/2312.10818/) (2023)
- [Customer Analytics using Surveillance Video](https://mlsanity.com/paper/2503.00452/) (2025)
- [Deep Learning based approach to detect Customer Age, Gender and Expression in Surveillance Video](https://mlsanity.com/paper/2503.00453/) (2025)
- [A Hybrid Deep Learning Framework for Emotion Recognition in Children with Autism During NAO Robot-Mediated Interaction](https://mlsanity.com/paper/2512.12208/) (2025)
- [Event-Level Emotion Recognition in the Wild Using Deep Facial Expression Analysis](https://mlsanity.com/paper/2609.13854/) (2026)
- [Quantum-Gated LiteSSD: A Parameter-Efficient Lightweight Hybrid Quantum-Classical Framework for Forward-Looking Sonar Object Detection](https://mlsanity.com/paper/2609.14025/) (2026)

## Abstract (arXiv)

In this paper we propose an implement a general convolutional neural network (CNN) building framework for designing real-time CNNs. We validate our models by creating a real-time vision system which accomplishes the tasks of face detection, gender classification and emotion classification simultaneously in one blended step using our proposed CNN architecture. After presenting the details of the training procedure setup we proceed to evaluate on standard benchmark sets. We report accuracies of 96% in the IMDB gender dataset and 66% in the FER-2013 emotion dataset. Along with this we also introduced the very recent real-time enabled guided back-propagation visualization technique. Guided back-propagation uncovers the dynamics of the weight changes and evaluates the learned features. We argue that the careful implementation of modern CNN architectures, the use of the current regularization methods and the visualization of previously hidden features are necessary in order to reduce the gap between slow performances and real-time architectures. Our system has been validated by its deployment on a Care-O-bot 3 robot used during RoboCup@Home competitions. All our code, demos and pre-trained architectures have been released under an open-source license in our public repository.