Multimodal Image Collection Visualization Using Non-negative Matrix Factorization

In this paper we address the problem of generating an image collection visualization in which images and text can be projected together. Given a collection of images with attached text annotations, we aim to find a common representation for both information sources to model latent correlations among the collection. Using the proposed latent representation, an image collection visualization is built, in which images and text can be projected simultaneously. The resulting image visualization allows to identify the relationships between images and text terms, allowing to understand the distribution of the collection in a more