Multimodal Multi-loss Fusion Network for Sentiment Analysis
This work addresses sentiment analysis for multimodal data, but it appears incremental as it focuses on optimizing existing fusion and training methods.
The paper tackled the problem of selecting and fusing feature encoders across multiple modalities to improve sentiment detection, achieving state-of-the-art performance on three datasets (CMU-MOSI, CMU-MOSEI, and CH-SIMS).
This paper investigates the optimal selection and fusion of feature encoders across multiple modalities and combines these in one neural network to improve sentiment detection. We compare different fusion methods and examine the impact of multi-loss training within the multi-modality fusion network, identifying surprisingly important findings relating to subnet performance. We have also found that integrating context significantly enhances model performance. Our best model achieves state-of-the-art performance for three datasets (CMU-MOSI, CMU-MOSEI and CH-SIMS). These results suggest a roadmap toward an optimized feature selection and fusion approach for enhancing sentiment detection in neural networks.