LineCap: Line Charts for Data Visualization Captioning Models
This addresses the need for better captions to aid understanding, especially for individuals with visual impairments, but is incremental as it focuses on dataset creation rather than a new method.
The authors tackled the problem of automated figure captioning for data visualizations by introducing LineCap, a novel dataset of 3,528 figures, and provided insights from curating it and using end-to-end deep learning models.
Data visualization captions help readers understand the purpose of a visualization and are crucial for individuals with visual impairments. The prevalence of poor figure captions and the successful application of deep learning approaches to image captioning motivate the use of similar techniques for automated figure captioning. However, research in this field has been stunted by the lack of suitable datasets. We introduce LineCap, a novel figure captioning dataset of 3,528 figures, and we provide insights from curating this dataset and using end-to-end deep learning models for automated figure captioning.