Paper: Topic Models for Image Annotation and Text Illustration

ACL ID N10-1125
Title Topic Models for Image Annotation and Text Illustration
Venue Human Language Technologies
Session Main Conference
Year 2010

Image annotation, the task of automatically generating description words for a picture, is a key component in various image search and retrieval applications. Creating image databases for model development is, however, costly and time consuming, since the key- words must be hand-coded and the process repeated for new collections. In this work we exploit the vast resource of images and documents available on the web for develop- ing image annotation models without any hu- man involvement. We describe a probabilistic model based on the assumption that images and their co-occurring textual data are gener- atedbymixturesoflatenttopics.Weshowthat this model outperforms previously proposed approaches when applied to image annotation and the related task of text illustration despite the noisy nat...