Pan J.-Y.Yang H.-J.Faloutsos C.Duygulu, Pınar2016-02-082016-02-0820042160-7508http://hdl.handle.net/11693/27472Date of Conference: 27 June-2 July 2004Given 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 auto-captioning methods by up to 10 percentage points in captioning accuracy (50% relative improvement). © 2004 IEEE.EnglishComputer visionImage retrievalPattern recognitionStatistical testsAutomatic image captioningCorel image databaseData set sizeGraph-basedPercentage pointsTraining and testingGraphic methodsConference Paper10.1109/CVPR.2004.353