Discriminating Image Senses by Clustering with Multimodal Features

We discuss Image Sense Discrimination (ISD), and apply a method based on spectral clustering, using multimodal features from the image and text of the embedding web page. We evaluate our method on a new data set of annotated web images, retrieved with ambiguous query terms. Experiments investigate different levels of sense granularity, as well as the impact of text and image features, and global versus local text features.

• Type: Conference
• Year: 2006
• Where: ACL
• Authors: Nicolas Loeff, Cecilia Ovesdotter Alm, David A. Forsyth
• Keywords: ACL 2006, ACL 2007, Ambiguous Query Terms, Image Sense Discrimination, Versus Local Text