Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions
Curto, David, Clapés, Albert, Selva, Javier, Smeureanu, Sorina, Junior, Julio C. S. Jacques, Gallardo-Pujol, David, Guilera, Georgina, Leiva, David, Moeslund, Thomas B., Escalera, Sergio, Palmero, Cristina
–arXiv.org Artificial Intelligence
Personality computing has become an emerging topic in computer vision, due to the wide range of applications it can be used for. However, most works on the topic have focused on analyzing the individual, even when applied to interaction scenarios, and for short periods of time. To address these limitations, we present the Dyadformer, a novel multi-modal multi-subject Transformer architecture to model individual and interpersonal features in dyadic interactions using variable time windows, thus allowing the capture of long-term interdependencies. Our proposed cross-subject layer allows the network to explicitly model interactions among subjects through attentional operations. This proof-of-concept approach shows how multi-modality and joint modeling of both interactants for longer periods of time helps to predict individual attributes. With Dyadformer, we improve state-of-the-art self-reported personality inference results on individual subjects on the UDIVA v0.5 dataset.
arXiv.org Artificial Intelligence
Sep-20-2021
- Country:
- Europe (0.14)
- Genre:
- Research Report (1.00)
- Technology:
- Information Technology
- Artificial Intelligence
- Cognitive Science (1.00)
- Machine Learning > Neural Networks
- Deep Learning (1.00)
- Natural Language (1.00)
- Representation & Reasoning (1.00)
- Vision (1.00)
- Communications > Social Media (0.93)
- Artificial Intelligence
- Information Technology