ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer
This addresses the problem of generating more emotionally engaging stories from images for applications in creative writing or human-computer interaction, but it appears incremental as it builds on existing transformer-based methods with a specific emotional focus.
The paper tackled image narrative generation by incorporating emotion arcs to capture emotional changes, proposing ViNTER, and demonstrated its effectiveness through automatic and manual evaluations on the Image Narrative dataset.
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.