ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer

TL;DR

ViNTER introduces an emotion-arc-aware transformer model for image narrative generation, effectively capturing emotional trajectories to produce more subjective and emotionally coherent stories from images.

Contribution

The paper proposes ViNTER, a novel model that incorporates emotion arcs into image narrative generation, enhancing emotional expressiveness and storytelling quality.

Findings

Effective in capturing emotional trajectories

Improves subjective storytelling quality

Validated by automatic and manual evaluations

Abstract

Image narrative generation is a task to create a story from an image with a subjective viewpoint. Given the importance of the subjective feelings of writers, readers, and characters in storytelling, an image narrative generation method should consider human emotion. In this study, we propose a novel method of image narrative generation called ViNTER (Visual Narrative Transformer with Emotion arc Representation), which takes "emotion arc" as input to capture a sequence of emotional changes. Since emotion arcs represent the trajectory of emotional change, it is expected that we can include detailed information about the emotional changes in the story to the model. We present experimental results of both automatic and manual evaluations on the Image Narrative dataset and demonstrate the effectiveness of the proposed approach.