Robust Temporal-Invariant Learning in Multimodal Disentanglement

Multimodal sentiment recognition aims to learn representations from different modalities to identify human emotions. However, previous works does not suppresses the frame-level redundancy inherent in continuous time series, resulting in incomplete modality representations with noise. To address this issue, we propose the Temporal-invariant learning, which minimizes the distributional differences between time steps to effectively capture smoother time series patterns, thereby enhancing the quality of the representations and robustness of the model. To fully exploit the rich semantic information in textual knowledge, we propose a Text-Driven Fusion Module (TDFM). To guide cross-modal interactions, TDFM evaluates the correlations between different modality through modality-invariant representations. Furthermore, we introduce a modality discriminator to disentangle modality-invariant and modality-specific subspaces. Experimental results on two public datasets demonstrate the superiority of our model.