Improving Image Captioning by Leveraging Knowledge Graphs | 您所在的位置:网站首页 › Improving Image Captioning by Leveraging Knowledge Graphs › Improving Image Captioning by Leveraging Knowledge Graphs |
Abstract
Abstract (translated by Google)
URL
PDF
Abstract
We explore the use of a knowledge graphs, that capture general or commonsense knowledge, to augment the information extracted from images by the state-of-the-art methods for image captioning. The results of our experiments, on several benchmark data sets such as MS COCO, as measured by CIDEr-D, a performance metric for image captioning, show that the variants of the state-of-the-art methods for image captioning that make use of the information extracted from knowledge graphs can substantially outperform those that rely solely on the information extracted from images. Abstract (translated by Google) URLhttp://arxiv.org/abs/1901.08942 PDFhttp://arxiv.org/pdf/1901.08942 |
CopyRight 2018-2019 实验室设备网 版权所有 |