PT Unknown
AU David Curto
   Albert Clapes
   Javier Selva
   Sorina Smeureanu
   Julio C. S. Jacques Junior
   David Gallardo-Pujol
   Georgina Guilera
   David Leiva
   Thomas B. Moeslund
   Sergio Escalera
   Cristina Palmero
TI Dyadformer: A Multi-Modal Transformer for Long-Range Modeling of Dyadic Interactions
BT IEEE/CVF International Conference on Computer Vision Workshops
PY 2021
BP 2177
EP 2188
DI 10.1109/ICCVW54120.2021.00247
AB 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.
ER