Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis
This addresses the challenge of accurately identifying complex semantic relationships in multimodal data for applications like image-text understanding, though it appears incremental by building on retrieval-augmented approaches.
The paper tackled the problem of multimodal relation extraction by proposing a method that retrieves and synthesizes textual and visual evidence at object, sentence, and image levels, resulting in significant outperformance over state-of-the-art models.
Multimodal relation extraction (MRE) is the task of identifying the semantic relationships between two entities based on the context of the sentence image pair. Existing retrieval-augmented approaches mainly focused on modeling the retrieved textual knowledge, but this may not be able to accurately identify complex relations. To improve the prediction, this research proposes to retrieve textual and visual evidence based on the object, sentence, and whole image. We further develop a novel approach to synthesize the object-level, image-level, and sentence-level information for better reasoning between the same and different modalities. Extensive experiments and analyses show that the proposed method is able to effectively select and compare evidence across modalities and significantly outperforms state-of-the-art models.