This paper proposes a method to optimize Viterbi beam search based on search error risk minimization in large vocabulary continuous speech recognition (LVCSR). Most speech recogni...
The numerous works on media retargeting call for a methodological approach for evaluating retargeting results. We present the first comprehensive perceptual study and analysis of ...
Michael Rubinstein, Diego Gutierrez, Olga Sorkine,...
The majority of the current information retrieval models weight the query concepts (e.g., terms or phrases) in an unsupervised manner, based solely on the collection statistics. I...
In many domains, such as bioinformatics, cheminformatics, health informatics and social networks, data can be represented naturally as labeled graphs. To address the increasing ne...
—In this paper, we present a novel approach to search and retrieve from document image collections, without explicit recognition. Existing recognition-free approaches such as wor...