@article{hybridfusionbasedinterpretablemultimodal,
  title = {VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition},
  author = {Puneet Kumar and Sarthak Malik and Balasubramanian Raman and Xiaobai Li},
  year = {2022},
  eprint = {2208.11450},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2208.11450v3},
}