Join the Visually Grounded Story Generation Challenge at INLG 2024 in Tokyo, Japan!
The Visually Grounded Story Generation (VGSG) Challenge is a shared task at the Generation Challenges workshop at the International Natural Language Generation Conference (INLG) 2024 in Tokyo, Japan. This task invites participants to push the boundaries of vision-based story generation and generate stories grounded on a sequence of images. Participants will explore the intricate relations between visual prompts and textual stories, fostering innovations in techniques for coherent, visually grounded story generation. This task is particularly challenging because the output story should be a narratively coherent text with multiple sentences, and the protagonists in the generated stories need to be grounded in the images.
Major progress has been made by the industry in vision-based text generation in the last few years. While generating descriptions from images or videos is widely available, grounded story generation is not evaluated with a benchmark. Investigating vision-based story generation requires several capabilities including commonsense reasoning and content planning. The task is open to both automatic and human evaluations, and participants can submit a 4-page report, which will be peer-reviewed and included in the INLG 2024 proceedings if accepted.
To participate, please fill in this Google Form. For more information, visit the VGSG website (https://vgsg2024.github.io/) or read our shared task proposal (https://aclanthology.org/2023.inlg-genchal.3.pdf).