Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition

TL;DR

This paper introduces TCL-MAP, a novel multimodal intent recognition framework that uses token-level contrastive learning and modality-aware prompting to better align and fuse features from text, video, and audio modalities, significantly improving performance.

Contribution

The paper proposes a new token-level contrastive learning method with modality-aware prompting for enhanced multimodal intent recognition, effectively aligning features across modalities and guiding learning with intent labels.

Findings

Achieves significant improvements over state-of-the-art methods.

Demonstrates the effectiveness of modality-aware prompts over handcrafted prompts.

Shows the superiority of the proposed TCL framework through extensive experiments.

Abstract

Multimodal intent recognition aims to leverage diverse modalities such as expressions, body movements and tone of speech to comprehend user's intent, constituting a critical task for understanding human language and behavior in real-world multimodal scenarios. Nevertheless, the majority of existing methods ignore potential correlations among different modalities and own limitations in effectively learning semantic features from nonverbal modalities. In this paper, we introduce a token-level contrastive learning method with modality-aware prompting (TCL-MAP) to address the above challenges. To establish an optimal multimodal semantic environment for text modality, we develop a modality-aware prompting module (MAP), which effectively aligns and fuses features from text, video and audio modalities with similarity-based modality alignment and cross-modality attention mechanism. Based on the modality-aware prompt and ground truth labels, the proposed token-level contrastive learning framework (TCL) constructs augmented samples and employs NT-Xent loss on the label token. Specifically, TCL capitalizes on the optimal textual semantic insights derived from intent labels to guide the learning processes of other modalities in return. Extensive experiments show that our method achieves remarkable improvements compared to state-of-the-art methods. Additionally, ablation analyses demonstrate the superiority of the modality-aware prompt over the handcrafted prompt, which holds substantial significance for multimodal prompt learning. The codes are released at https://github.com/thuiar/TCL-MAP.