ABSTRACT: OCR is an error-prone process. It is time-consuming and expensive to manually proofread OCR results. The errors remaining in OCRed texts can cause serious problems in rea...
We investigate methods of segmenting, visualizing, and indexing presentation videos by both audio and visual data. The audio track is segmented by speaker, and augmented with key ...
This paper describes work on Named Entity Recognition (NER), in preparation for Relation Extraction (RE), on data from a historical archive organisation. As is often the case in t...
In this paper we address the issue of continuous keyword queries on multiple textual streams. This line of work represents a significant departure from previous keyword search mod...
Vagelis Hristidis, Oscar Valdivia, Michail Vlachos...
In this demonstration, we present a system that enables users to easily generate quizzes for mobile devices. With our program, they can create multiple choice tests and general qu...