Paper: Automatic Image Annotation Using Auxiliary Text Information

ACL ID P08-1032
Title Automatic Image Annotation Using Auxiliary Text Information
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

Theavailabilityofdatabasesofimageslabeled withkeywordsisnecessaryfordevelopingand evaluating image annotation models. Dataset collection is however a costly and time con- suming task. In this paper we exploit the vast resource of images available on the web. We create a database of pictures that are natu- rally embedded into news articles and propose to use their captions as a proxy for annota- tion keywords. Experimental results show that an image annotation model can be developed on this dataset alone without the overhead of manual annotation. We also demonstrate that the news article associated with the picture can be used to boost image annotation perfor- mance.