ViPER-VT

(Vision Text)

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

For more information on how to use this model please refer to the following repository

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