Imagine, Reason and Write: Visual Storytelling with Graph Knowledge and Relational Reasoning

Authors

  • Chunpu Xu Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Min Yang Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Chengming Li Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Ying Shen Sun Yat-Sen University
  • Xiang Ao Institute of Computing Technology, CAS
  • Ruifeng Xu Harbin Institute of Technology (Shenzhen)

Keywords:

Language and Vision

Abstract

Visual storytelling is a task of creating a short story based on photo streams. Different from visual captions, stories contain not only factual descriptions, but also imaginary concepts that do not appear in the images. In this paper, we propose a novel imagine-reason-write generation framework (IRW) for visual storytelling, inspired by the logic of humans when they write the story. First, an imagine module is leveraged to learn the imaginative storyline explicitly, improving the coherence and reasonability of the generated story. Second, we employ a reason module to fully exploit the external knowledge (commonsense knowledge base) and task-specific knowledge (scene graph and event graph) with relational reasoning method based on the storyline. In this way, we can effectively capture the most informative commonsense and visual relationships among objects in images, which enhances the diversity and informativeness of the generated story. Finally, we integrate the imaginary concepts and relational knowledge to generate human-like story based on the original semantics of images. Extensive experiments on a benchmark dataset (i.e., VIST) demonstrate that the proposed IRW framework significantly outperforms the state-of-the-art methods across multiple evaluation metrics.

Downloads

Published

2021-05-18

How to Cite

Xu, C., Yang, M., Li, C., Shen, Y., Ao, X., & Xu, R. (2021). Imagine, Reason and Write: Visual Storytelling with Graph Knowledge and Relational Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3022-3029. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16410

Issue

Section

AAAI Technical Track on Computer Vision III