Towards Multimodal Sentiment Analysis via Contrastive Cross-modal Retrieval Augmentation and Hierachical Prompts

Multimodal sentiment analysis is a fundamental problem in the field of affective computing. Although significant progress has been made in cross-modal interaction, it remains a challenge due to the insufficient reference context in cross-modal interactions. Current cross-modal approaches primarily focus on leveraging modality-level reference context within a individual sample for cross-modal feature enhancement, neglecting the potential cross-sample relationships that can serve as sample-level reference context to enhance the cross-modal features. To address this issue, we propose a novel multimodal retrieval-augmented framework to simultaneously incorporate inter-sample modality-level reference context and cross-sample sample-level reference context to enhance the multimodal features. In particular, we first design a contrastive cross-modal retrieval module to retrieve semantic similar samples and enhance target modality. To endow the model to capture both inter-sample and intra-sample information, we integrate two different types of prompts, modality-level prompts and sample-level prompts, to generate modality-level and sample-level reference contexts, respectively. Finally, we design a cross-modal retrieval-augmented encoder that simultaneously leverages modality-level and sample-level reference contexts to enhance the target modality. Extensive experiments demonstrate the effectiveness and superiority of our model on two publicly available datasets.