In this paper, we investigate a problem of predicting what images are likely to appear on the Web at a future time point, given a query word and a database of historical image str...
: Rich, structured annotations of video recordings enable interesting uses, but existing techniques for manual, and even semi-automated, tagging can be too time-consuming. We prese...
We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions...
William Yang Wang, Elijah Mayfield, Suresh Naidu, ...
This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...
XML is the proposed electronic publishing and data interchange format of the future. Currently XML is immature with little tool support, particularly for end-user World Wide Web br...