/JointCrossAttentional-AV-Fusion

ABAW3 (CVPRW): A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition

Primary LanguagePython

JointCrossAttention for AV-Fusion

Code for our paper "A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition" submitted to ABAW3 challenge conducted with CVPR 2022.

Citation

If you find this code useful for your research, please cite our paper.

@INPROCEEDINGS{10095234,
  author={Praveen, R Gnana and de Melo, Wheidima Carneiro and Ullah, Nasib and Aslam, Haseeb and Zeeshan, Osama and Denorme, Théo and Pedersoli, Marco and Koerich, Alessandro L. and Bacon, Simon and Cardinal, Patrick and Granger, Eric},
  booktitle={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, 
  title={A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition}, 
  year={2022},
}

The proposed approach has been extended and published in IEEE T-BIOM, which can be found here

The updated version of the code along with the model weights of the proposed model to reproduce our results can be found here