# ViPER-VATF 
## (Vision Audio Text FAU)

This repository contains the checkpoints for the ViPER model. 
It is a Perceiver-based model finetuned on the concatenation of visual, acoustic, textual and FAU-related features.

For more information on how to use this model please refer to the following [repository](https://github.com/VaianiLorenzo/ViPER)

If you find this useful please cite:
```
@inproceedings{vaiani2022viper,
  title={ViPER: Video-based Perceiver for Emotion Recognition},
  author={Vaiani, Lorenzo and La Quatra, Moreno and Cagliero, Luca and Garza, Paolo},
  booktitle={Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge},
  pages={67--73},
  year={2022}
}
```

For any other question feel free to contact me at lorenzo.vaiani@polito.it