Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences
This addresses the issue of generating coherent stories from images for applications in creative writing and AI storytelling, though it is incremental as it builds on existing visual story generation methods.
The authors tackled the problem of incoherent plots in image-based story generation by creating a new dataset, Visual Writing Prompts (VWP), with 2K curated image sequences and 12K stories, resulting in generated stories that are more coherent, visually grounded, and narrative compared to the state-of-the-art.
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.