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.- Anthology ID:
- 2020.challengehml-1.4
- Volume:
- Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)
- Month:
- July
- Year:
- 2020
- Address:
- Seattle, USA
- Venue:
- Challenge-HML
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 29–34
- Language:
- URL:
- https://aclanthology.org/2020.challengehml-1.4
- DOI:
- 10.18653/v1/2020.challengehml-1.4
- Cite (ACL):
- Saurav Sahay, Eda Okur, Shachi H Kumar, and Lama Nachman. 2020. Low Rank Fusion based Transformers for Multimodal Sequences. In Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML), pages 29–34, Seattle, USA. Association for Computational Linguistics.
- Cite (Informal):
- Low Rank Fusion based Transformers for Multimodal Sequences (Sahay et al., Challenge-HML 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.challengehml-1.4.pdf
- Data
- CMU-MOSEI, IEMOCAP