@inproceedings{sahay-etal-2020-low,
    title = "Low Rank Fusion based Transformers for Multimodal Sequences",
    author = "Sahay, Saurav  and
      Okur, Eda  and
      H Kumar, Shachi  and
      Nachman, Lama",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Poria, Soujanya",
    booktitle = "Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)",
    month = jul,
    year = "2020",
    address = "Seattle, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.challengehml-1.4/",
    doi = "10.18653/v1/2020.challengehml-1.4",
    pages = "29--34",
    abstract = "Our senses individually work in a coordinated fashion to express our emotional intentions. In this work, we experiment with modeling modality-specific sensory signals to attend to our latent multimodal emotional intentions and vice versa expressed via low-rank multimodal fusion and multimodal transformers. The low-rank factorization of multimodal fusion amongst the modalities helps represent approximate multiplicative latent signal interactions. Motivated by the work of (CITATION) and (CITATION), we present our transformer-based cross-fusion architecture without any over-parameterization of the model. The low-rank fusion helps represent the latent signal interactions while the modality-specific attention helps focus on relevant parts of the signal. We present two methods for the Multimodal Sentiment and Emotion Recognition results on CMU-MOSEI, CMU-MOSI, and IEMOCAP datasets and show that our models have lesser parameters, train faster and perform comparably to many larger fusion-based architectures."
}