@article{multimodalemotionrecognitionusingaudio,
  title = {Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention},
  author = {Joe Dhanith P R and Shravan Venkatraman and Vigya Sharma and Santhosh Malarvannan and Modigari Narendra},
  year = {2024},
  eprint = {2407.18552},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.18552v3},
}