In this paper we present a novel descriptor and method for segmentation-based keyword spotting. We introduce Zoning-Aggregated Hypercolumn features as pixel-level cues for …
Following recent advances on parameterized hypercomplex multiplication, we explore the usefulness of hypercomplex convolutions and deconvolutions in a document labeling task …
The established paradigm in handwriting recognition techniques involves supervised learning, where training is performed over fully labelled (transcribed) data. In this paper, we …
Quaternionized versions of standard (real-valued) neural network layers have shown to lead to networks that are sparse and as effective as their real-valued counterparts. In this work …
Abstract Modern Keyword Spotting systems rely on deep learning approaches to build effective neural networks which provide state-of-the-art results. Despite their evident …
The presented thesis follows two directions. The first one disposes a technique for text and graphic separation in comics. The second one points out a learning free segmentation free …
Treating visual object tracking as foreground and background classification problem has attracted much attention in the past decade. Most methods adopt mean shift or brute force …
We propose a pyramid-based method for keyword spotting in historical document images. The documents are represented by a scale-space pyramid of their features. The search for a …
A wealth of knowledge is kept in libraries and cultural institutions in various digital forms without, however, the possibility of a simple term search, let alone of a substantial semantic …