Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences

TL;DR

This paper introduces a new dataset of curated movie shot sequences with aligned stories to improve visual story generation, along with a character-based model that outperforms existing methods in coherence and narrativity.

Contribution

The creation of the Visual Writing Prompts dataset and a novel character-grounded story generation model that enhances coherence and narrativity in visual storytelling.

Findings

Generated stories are more coherent and narratively rich.

The new dataset improves the quality of visual story generation.

The proposed model outperforms state-of-the-art baselines.

Abstract

Current work on image-based story generation suffers from the fact that the existing image sequence collections do not have coherent plots behind them. We improve visual story generation by producing a new image-grounded dataset, Visual Writing Prompts (VWP). VWP contains almost 2K selected sequences of movie shots, each including 5-10 images. The image sequences are aligned with a total of 12K stories which were collected via crowdsourcing given the image sequences and a set of grounded characters from the corresponding image sequence. Our new image sequence collection and filtering process has allowed us to obtain stories that are more coherent and have more narrativity compared to previous work. We also propose a character-based story generation model driven by coherence as a strong baseline. Evaluations show that our generated stories are more coherent, visually grounded, and have more narrativity than stories generated with the current state-of-the-art model.