Abstract

In this paper we are interested in finding images of people on the web, and more speci fically within large databases of captioned news images. It has recently been shown that visual analysis of the faces in images returned on a text-based query over captions can signi ficantly improve search results. The un- derlying idea to improve the text-based results is that although this initial result is imperfect, it will render the queried person to be relatively frequent as com- pared to other people, so we can search for a large group of highly similar faces. The performance of such methods depends strongly on this assumption: for peo- ple whose face appears in less than about 40% of the initial text-based result, the performance may be very poor. The contribution of this paper is to improve search results by exploiting faces of other people that co-occur frequently with the queried person. We refer to this process as ‘query expansion’. In the face analysis we use the query expansion to provide a query-speci fic relevant set of ‘negative’ examples which should be separated from the potentially positive examples in the text-based result set. We apply this idea to a recently-proposed method which filters the initial result set using a Gaussian mixture model, and apply the same idea using a logistic discriminant model. We experimentally evaluate the meth- ods using a set of 23 queries on a database of 15.000 captioned news stories from Yahoo!News. The results show that (i) query expansion improves both methods, (ii) that our discriminative models outperform the generative ones, and (iii) our best results surpass the state-of-the-art results by 10% precision on average.