Neural caption generation over figures

Charles Chen, Ruiyi Zhang, Sungchul Kim, Scott Cohen, Tong Yu, Ryan A. Rossi, Razvan C. Bunescu

Abstract: Figures are human-friendly but difficult for computers to process automatically. In this work, we investigate the problem of figure captioning. The goal is to automatically generate a natural language description of a given figure. We create a new dataset for figure captioning, FigCAP. To achieve accurate generation of labels in figures, we propose the Label Maps Attention Model. Extensive experiments show that our method outperforms the baselines. A successful solution to this task allows figure content to be accessible to those with visual impairment by providing input to a text-to-speech system; and enables automatic parsing of vast repositories of documents where figures are pervasive.