Multimodal Event Transformer for Image-guided Story Ending Generation

TL;DR

This paper introduces a multimodal event transformer that uses event-based reasoning and graph modeling to improve image-guided story ending generation, achieving state-of-the-art results.

Contribution

It proposes a novel event-based reasoning framework with visual and semantic graphs, cross-modal fusion, and incoherence detection for better story ending generation.

Findings

Achieves state-of-the-art performance on IgSEG tasks.

Effectively mines implicit information from story plots and images.

Enhances story understanding through incoherence detection.

Abstract

Image-guided story ending generation (IgSEG) is to generate a story ending based on given story plots and ending image. Existing methods focus on cross-modal feature fusion but overlook reasoning and mining implicit information from story plots and ending image. To tackle this drawback, we propose a multimodal event transformer, an event-based reasoning framework for IgSEG. Specifically, we construct visual and semantic event graphs from story plots and ending image, and leverage event-based reasoning to reason and mine implicit information in a single modality. Next, we connect visual and semantic event graphs and utilize cross-modal fusion to integrate different-modality features. In addition, we propose a multimodal injector to adaptive pass essential information to decoder. Besides, we present an incoherence detection to enhance the understanding context of a story plot and the robustness of graph modeling for our model. Experimental results show that our method achieves state-of-the-art performance for the image-guided story ending generation.