# FERT: Real-Time Facial Expression Recognition with Short-Range FMCW Radar

arXiv: https://arxiv.org/abs/2411.11619 · HTML: https://mlsanity.com/paper/2411.11619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 18 Nov 2024.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition](https://mlsanity.com/paper/2212.05463/) (2022)
- [MCROOD: Multi-Class Radar Out-Of-Distribution Detection](https://mlsanity.com/paper/2303.06232/) (2023)
- [Facial Expression Recognition Under Partial Occlusion from Virtual Reality Headsets based on Transfer Learning](https://mlsanity.com/paper/2008.05563/) (2020)
- [Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radar](https://mlsanity.com/paper/2302.14192/) (2023)
- [HAROOD: Human Activity Classification and Out-of-Distribution Detection with Short-Range FMCW Radar](https://mlsanity.com/paper/2312.08894/) (2023)
- [FOOD: Facial Authentication and Out-of-Distribution Detection with Short-Range FMCW Radar](https://mlsanity.com/paper/2406.04546/) (2024)
- [Unsupervised Deep Representations for Learning Audience Facial Behaviors](https://mlsanity.com/paper/1805.04136/) (2018)

## Abstract (arXiv)

This study proposes a novel approach for real-time facial expression recognition utilizing short-range Frequency-Modulated Continuous-Wave (FMCW) radar equipped with one transmit (Tx), and three receive (Rx) antennas. The system leverages four distinct modalities simultaneously: Range-Doppler images (RDIs), micro range-Doppler Images (micro-RDIs), range azimuth images (RAIs), and range elevation images (REIs). Our innovative architecture integrates feature extractor blocks, intermediate feature extractor blocks, and a ResNet block to accurately classify facial expressions into smile, anger, neutral, and no-face classes. Our model achieves an average classification accuracy of 98.91% on the dataset collected using a 60 GHz short-range FMCW radar. The proposed solution operates in real-time in a person-independent manner, which shows the potential use of low-cost FMCW radars for effective facial expression recognition in various applications.