Fig. 9
From: Multimodal sentiment analysis based on multi-layer feature fusion and multi-task learning

Trends in the loss values as training proceeds in MOSI (a) and SIMS (b) dataset (five runs across random seeds).
From: Multimodal sentiment analysis based on multi-layer feature fusion and multi-task learning

Trends in the loss values as training proceeds in MOSI (a) and SIMS (b) dataset (five runs across random seeds).