CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation

TL;DR

CubeMLP is a novel MLP-based framework for multimodal sentiment analysis and depression estimation that effectively mixes features across modalities, achieving state-of-the-art results with lower computational cost.

Contribution

This paper introduces CubeMLP, a purely MLP-based multimodal feature processing framework that uses a novel feature-mixing approach across three axes for improved mental state prediction.

Findings

Achieves state-of-the-art performance on CMU-MOSI and CMU-MOSEI datasets.

Demonstrates lower computational cost compared to existing methods.

Effective multimodal feature mixing improves prediction accuracy.

Abstract

Multimodal sentiment analysis and depression estimation are two important research topics that aim to predict human mental states using multimodal data. Previous research has focused on developing effective fusion strategies for exchanging and integrating mind-related information from different modalities. Some MLP-based techniques have recently achieved considerable success in a variety of computer vision tasks. Inspired by this, we explore multimodal approaches with a feature-mixing perspective in this study. To this end, we introduce CubeMLP, a multimodal feature processing framework based entirely on MLP. CubeMLP consists of three independent MLP units, each of which has two affine transformations. CubeMLP accepts all relevant modality features as input and mixes them across three axes. After extracting the characteristics using CubeMLP, the mixed multimodal features are flattened for task predictions. Our experiments are conducted on sentiment analysis datasets: CMU-MOSI and CMU-MOSEI, and depression estimation dataset: AVEC2019. The results show that CubeMLP can achieve state-of-the-art performance with a much lower computing cost.