A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition
This addresses multimodal intent recognition for applications like human-computer interaction, but appears incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of multimodal intent recognition by proposing the A-MESS framework, which integrates multimodal inputs and synchronizes representations with label descriptions, achieving state-of-the-art results.
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 Multimodal Embedding with Semantic Synchronization (A-MESS) framework. We first design an Anchor-based Multimodal Embedding (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 process by synchronizing multimodal representation with label descriptions 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.