---
license: mit
metrics:
- recall
pipeline_tag: video-classification
tags:
- FER
- Image Classification
library_name: PyTorch
---

# Static and dynamic facial emotion recognition using the Emo-AffectNet model

[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/in-search-of-a-robust-facial-expressions/facial-expression-recognition-on-affectnet)](https://paperswithcode.com/paper/in-search-of-a-robust-facial-expressions)
[![App](https://img.shields.io/badge/🤗-DEMO--Facial%20Expressions%20Recognition-FFD21F.svg)](https://huggingface.co/spaces/ElenaRyumina/Facial_Expression_Recognition)

This is Emo-AffectNet model for facial emotion recognition by videos / images. 

To see the emotion detected by webcam, you should run ``run_webcam``. Webcam result:

<p align="center">
    <img width="50%" src="https://github.com/ElenaRyumina/EMO-AffectNetModel/blob/main/gif/result_2.gif?raw=true" alt="result"/>
</p>

For more information see [GitHub](https://github.com/ElenaRyumina/EMO-AffectNetModel).

### Citation

If you are using EMO-AffectNet model in your research, please consider to cite research [paper](https://www.sciencedirect.com/science/article/pii/S0925231222012656). Here is an example of BibTeX entry:

<div class="highlight highlight-text-bibtex notranslate position-relative overflow-auto" dir="auto"><pre><span class="pl-k">@article</span>{<span class="pl-en">RYUMINA2022</span>,
  <span class="pl-s">title</span>        = <span class="pl-s"><span class="pl-pds">{</span>In Search of a Robust Facial Expressions Recognition Model: A Large-Scale Visual Cross-Corpus Study<span class="pl-pds">}</span></span>,
  <span class="pl-s">author</span>       = <span class="pl-s"><span class="pl-pds">{</span>Elena Ryumina and Denis Dresvyanskiy and Alexey Karpov<span class="pl-pds">}</span></span>,
  <span class="pl-s">journal</span>      = <span class="pl-s"><span class="pl-pds">{</span>Neurocomputing<span class="pl-pds">}</span></span>,
  <span class="pl-s">year</span>         = <span class="pl-s"><span class="pl-pds">{</span>2022<span class="pl-pds">}</span></span>,
  <span class="pl-s">doi</span>          = <span class="pl-s"><span class="pl-pds">{</span>10.1016/j.neucom.2022.10.013<span class="pl-pds">}</span></span>,
  <span class="pl-s">url</span>          = <span class="pl-s"><span class="pl-pds">{</span>https://www.sciencedirect.com/science/article/pii/S0925231222012656<span class="pl-pds">}</span></span>,
}</div>