The field of visual document understanding has witnessed a rapid growth ...
Instance-level segmentation of documents consists in assigning a class-a...
This project explores the feasibility of remote patient monitoring based...
Assessing the physical condition in rehabilitation scenarios is a challe...
Despite recent advances in automatic text recognition, the performance
r...
Geometric Deep Learning has recently attracted significant interest in a...
Date estimation of historical document images is a challenging problem, ...
In this work, we propose Text-Degradation Invariant Auto Encoder (Text-D...
Understanding documents with rich layouts is an essential step towards
i...
Document images can be affected by many degradation scenarios, which cau...
This work investigates the problem of sketch-guided object localization
...
One of the major prerequisites for any deep learning approach is the
ava...
Despite significant progress on current state-of-the-art image generatio...
This paper presents a novel method for date estimation of historical
pho...
In this paper, we explore and evaluate the use of ranking-based objectiv...
Low resource Handwritten Text Recognition (HTR) is a hard problem due to...
The emergence of geometric deep learning as a novel framework to deal wi...
In the last years, the consolidation of deep neural network architecture...
In this paper, we investigate the problem of zero-shot sketch-based imag...
Despite being very successful within the pattern recognition and machine...
In this work we introduce a cross modal image retrieval system that allo...
When extracting information from handwritten documents, text transcripti...
This study concerned the active use of Wikipedia as a teaching tool in t...
Offline signature verification is one of the most challenging tasks in
b...
Many algorithms formulate graph matching as an optimization of an object...
Word spotting is an important recognition task in historical document
an...
Digital libraries store images which can be highly degraded and to index...
Motivation of our work is to present a new methodology for symbol
recogn...