Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling
DOI:
https://doi.org/10.1609/aaai.v35i2.16184Keywords:
Language and Vision, GenerationAbstract
Visual storytelling is a task of generating relevant and interesting stories for given image sequences. In this work we aim at increasing the diversity of the generated stories while preserving the informative content from the images. We propose to foster the diversity and informativeness of a generated story by using a concept selection module that suggests a set of concept candidates. Then, we utilize a large scale pre-trained model to convert concepts and images into full stories. To enrich the candidate concepts, a commonsense knowledge graph is created for each image sequence from which the concept candidates are proposed. To obtain appropriate concepts from the graph, we propose two novel modules that consider the correlation among candidate concepts and the image-concept correlation. Extensive automatic and human evaluation results demonstrate that our model can produce reasonable concepts. This enables our model to outperform the previous models by a large margin on the diversity and informativeness of the story, while retaining the relevance of the story to the image sequence.Downloads
Published
2021-05-18
How to Cite
Chen, H., Huang, Y., Takamura, H., & Nakayama, H. (2021). Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 999-1008. https://doi.org/10.1609/aaai.v35i2.16184
Issue
Section
AAAI Technical Track on Computer Vision I