Skip to main content
. 2021 Jan 11;14:609096. doi: 10.3389/fnhum.2020.609096

Figure 4.

Figure 4

(S_) LIT model. Each modality is indicated at the bottom. All MNets feed into one Head network and are based on what is commonly used in the literature. Before fusion in the Head network, MNets are flattened and represented in a lower-dimensional space with the help of a single densely connected layer.