We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set ...
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...
Automatic video search based on semantic concept detectors has recently received significant attention. Since the number of available detectors is much smaller than the size of h...
Translation of proper names is generally recognized as a significant problem in many multi-lingual text and speech processing applications. Even when large bilingual lexicons use...
In this paper, we argue that the agglomerative clustering with vector cosine similarity measure performs poorly due to two reasons. First, the nearest neighbors of a document belo...