GCap: Graph-Based Automatic Image Captioning

Given an image, how do we automatically assign keywords to it? In this paper, we propose a novel, graph-based approach (GCap) which outperforms previously reported methods for automatic image captioning. Moreover, it is fast and scales well, with its training and testing time linear to the data set size. We report auto-captioning experiments on the "standard" Corel image database of 680 MBytes, where GCap outperforms recent, successful autocaptioning methods by up to 10 percentage points in captioning accuracy (50% relative improvement).

• Type: Conference
• Year: 2004
• Where: CVPR
• Authors: Jia-Yu Pan, Hyung-Jeong Yang, Christos Faloutsos, Pinar Duygulu
• Keywords: Computer Vision, Corel Image Database, CVPR 2004, Graph-Based Approach, Successful Autocaptioning Methods