@InProceedings{PauTorras2023,
author="Pau Torras
and Mohamed Ali Souibgui
and Sanket Biswas
and Alicia Fornes",
title="Segmentation-Free Alignment of Arbitrary Symbol Transcripts to Images",
booktitle="Document Analysis and Recognition -- ICDAR 2023 Workshops",
year="2023",
volume="14193",
pages="83--93",
optkeywords="Historical Manuscripts",
optkeywords="Symbol Alignment",
abstract="Developing arbitrary symbol recognition systems is a challenging endeavour. Even using content-agnostic architectures such as few-shot models, performance can be substantially improved by providing a number of well-annotated examples into training. In some contexts, transcripts of the symbols are available without any position information associated to them, which enables using line-level recognition architectures. A way of providing this position information to detection-based architectures is finding systems that can align the input symbols with the transcription. In this paper we discuss some symbol alignment techniques that are suitable for low-data scenarios and provide an insight on their perceived strengths and weaknesses. In particular, we study the usage of Connectionist Temporal Classification models, Attention-Based Sequence to Sequence models and we compare them with the results obtained on a few-shot recognition system.",
optnote="DAG",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3850), last updated on Mon, 20 Nov 2023 12:00:47 +0100",
opturl="https://link.springer.com/chapter/10.1007/978-3-031-41498-5_6"
}