Skip to content

Latest commit

 

History

History
16 lines (13 loc) · 761 Bytes

README.md

File metadata and controls

16 lines (13 loc) · 761 Bytes
Raw

In this work, we present Recursive Joint Cross-Modal Attention across audio, visual and text modalities for dimensional emotion recognition. We submitted our results on test set for Valence-arousal challenge of 6th ABAW competition.

References

If you find this work useful in your research, please consider citing our work 📝 and giving a star 🌟 :

@article{praveen2024recursive,
  title={Recursive Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognition},
  author={Praveen, R Gnana and Alam, Jahangir},
  journal={arXiv preprint arXiv:2403.13659},
  year={2024}
}

Acknowledgements

The code for preprocessing and the coding framework for the proposed model is based on (https://github.com/sucv/ABAW3).