Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences
Published
2023-06-24
Xudong Hong
,
Asad Sayeed
,
Khushboo Mehra
,
Vera Demberg
,
Bernt Schiele
Xudong Hong
Saarland University;
Max Planck Institute for Informatics
Asad Sayeed
University of Gothenburg
Khushboo Mehra
Saarland University
Vera Demberg
Saarland University
Bernt Schiele
Max Planck Institute for Informatics
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 more diverse 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 more diverse than stories generated with the current state-of-the-art model. Our code, image features, annotations and collected stories are available at \url{https://vwprompt.github.io/}.
Presented at EACL 2023
Article at MIT Press