@InProceedings{DavidAldavert2013,
author="David Aldavert
and Mar{\c{c}}al Rusi{\~n}ol
and Ricardo Toledo
and Josep Llados",
title="Integrating Visual and Textual Cues for Query-by-String Word Spotting",
booktitle="12th International Conference on Document Analysis and Recognition",
year="2013",
pages="511--515",
abstract="In this paper, we present a word spotting framework that follows the query-by-string paradigm where word images are represented both by textual and visual representations. The textual representation is formulated in terms of character \$n\$-grams while the visual one is based on the bag-of-visual-words scheme. These two representations are merged together and projected to a sub-vector space. This transform allows to, given a textual query, retrieve word instances that were only represented by the visual modality. Moreover, this statistical representation can be used together with state-of-the-art indexation structures in order to deal with large-scale scenarios. The proposed method is evaluated using a collection of historical documents outperforming state-of-the-art performances.",
optnote="DAG; ADAS; 600.045; 600.055; 600.061",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=2224), last updated on Thu, 10 Nov 2016 12:07:17 +0100",
issn="1520-5363",
doi="10.1109/ICDAR.2013.108",
file=":http://refbase.cvc.uab.es/files/ART2013.pdf:PDF"
}