LSDE is a novel embedding approach for representing strings that learns a space in which distances between projected points are correlated with the Levenshtein ...
LSDE is a novel embedding approach for representing strings that learns a space in which distances between projected points are correlated with the Levenshtein ...
LSDE is a novel embedding approach for representing strings that learns a space in which distances between projected points are correlated with the Levenshtein ...
[12] proposed a novel embedding scheme (LSDE), which projects both word images and the corresponding string into a space that respects the Levenshtein distance.
In this paper we present the LSDE string representation and its application to handwritten word spotting. LSDE is a novel embedding approach for ...
Dive into the research topics of 'LSDE: Levenshtein Space Deep Embedding for Query-by-String Word Spotting'. Together they form a unique fingerprint. Sort by ...
LSDE: Levenshtein space deep embedding for query-by-string word spotting. L Gómez, M Rusinol, D Karatzas. 2017 14th IAPR International Conference on Document ...
Nov 30, 2020 · Word spotting helps people like archaeologists, historian and internet censors to retrieve regions of interest from document images ...
LSDE: Levenshtein Space Deep Embedding for Query-by-string Word Spotting · Lluis Gomez, Marçal Rusiñol, Dimosthenis Karatzas. 31 Jan 2020; OpenReview Archive ...
This work proposes an End2End embedding framework which jointly learns both the text and image embeddings using state of the art deep convolutional ...