A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition

원문 초록

In the domain of multimodal intent recognition (MIR), the objective is to recognize human intent by integrating a variety of modalities, such as language text, body gestures, and tones. However, existing approaches face difficulties adequately capturing the intrinsic connections between the modalities and overlooking the corresponding semantic representations of intent. To address these limitations, we present the Anchor-based Mul- timodal Embedding with Semantic Synchronization (A-MESS) framework. We first design an Anchor-based Multimodal Embed- ding (A-ME) module that employs an anchor-based embedding fusion mechanism to integrate multimodal inputs. Furthermore, we develop a Semantic Synchronization (SS) strategy with the Triplet Contrastive Learning pipeline, which optimizes the pro- cess by synchronizing multimodal representation with label de- scriptions produced by the large language model. Comprehensive experiments indicate that our A-MESS achieves state-of-the-art and provides substantial insight into multimodal representation and downstream tasks.