TY  - CONF
AU  - Pau Torras
AU  - Mohamed Ali Souibgui
AU  - Sanket Biswas
AU  - Alicia Fornes
A2  - ICDAR
PY  - 2023//
TI  - Segmentation-Free Alignment of Arbitrary Symbol Transcripts to Images
T2  - LNCS
BT  - Document Analysis and Recognition – ICDAR 2023 Workshops
SP  - 83
EP  - 93
VL  - 14193
KW  - Historical Manuscripts
KW  - Symbol Alignment
N2  - 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.
UR  - https://link.springer.com/chapter/10.1007/978-3-031-41498-5_6
N1  - DAG
ID  - Pau Torras2023
ER  -